Upload folder using huggingface_hub (#1)
Browse files- 22f03936d8657d299301a03d2b3c986d73d6b5fcc7906283683d26ff8f8fd7b1 (fe1617212536e231e8ae893a376076a7d43c89fd)
- bc0c975aafe3567f3ff176eb5616f41aefd0fb6702906e1f0202157863aa30b2 (1ab0f82046d42e15c3d804b2b4eafa23179d08b0)
- added_tokens.json +16 -0
- all_results.json +8 -0
- chat_template.json +3 -0
- config.json +46 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +129 -0
- train_results.json +8 -0
- trainer_log.jsonl +395 -0
- trainer_state.json +2800 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|box_end|>": 151649,
|
| 3 |
+
"<|box_start|>": 151648,
|
| 4 |
+
"<|endoftext|>": 151643,
|
| 5 |
+
"<|im_end|>": 151645,
|
| 6 |
+
"<|im_start|>": 151644,
|
| 7 |
+
"<|image_pad|>": 151655,
|
| 8 |
+
"<|object_ref_end|>": 151647,
|
| 9 |
+
"<|object_ref_start|>": 151646,
|
| 10 |
+
"<|quad_end|>": 151651,
|
| 11 |
+
"<|quad_start|>": 151650,
|
| 12 |
+
"<|video_pad|>": 151656,
|
| 13 |
+
"<|vision_end|>": 151653,
|
| 14 |
+
"<|vision_pad|>": 151654,
|
| 15 |
+
"<|vision_start|>": 151652
|
| 16 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9998731447418495,
|
| 3 |
+
"total_flos": 3.7575827488610714e+18,
|
| 4 |
+
"train_loss": 1.3289946492206504,
|
| 5 |
+
"train_runtime": 13442.1001,
|
| 6 |
+
"train_samples_per_second": 37.53,
|
| 7 |
+
"train_steps_per_second": 0.293
|
| 8 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2_vl",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"type": "mrope"
|
| 27 |
+
},
|
| 28 |
+
"rope_theta": 1000000.0,
|
| 29 |
+
"sliding_window": 32768,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.45.0.dev0",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"use_sliding_window": false,
|
| 35 |
+
"video_token_id": 151656,
|
| 36 |
+
"vision_config": {
|
| 37 |
+
"hidden_size": 1536,
|
| 38 |
+
"in_chans": 3,
|
| 39 |
+
"model_type": "qwen2_vl",
|
| 40 |
+
"spatial_patch_size": 14
|
| 41 |
+
},
|
| 42 |
+
"vision_end_token_id": 151653,
|
| 43 |
+
"vision_start_token_id": 151652,
|
| 44 |
+
"vision_token_id": 151654,
|
| 45 |
+
"vocab_size": 151936
|
| 46 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.01,
|
| 10 |
+
"top_k": 1,
|
| 11 |
+
"top_p": 0.001,
|
| 12 |
+
"transformers_version": "4.45.0.dev0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d21b0ee8658a4ebf68b1240713e1a05023d3799d768d45032633d6ef4d9c6d
|
| 3 |
+
size 4884798456
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"max_pixels": 12845056,
|
| 26 |
+
"min_pixels": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
}
|
| 116 |
+
},
|
| 117 |
+
"additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<|object_ref_start|>","<|object_ref_end|>","<|box_start|>","<|box_end|>","<|quad_start|>","<|quad_end|>","<|vision_start|>","<|vision_end|>","<|vision_pad|>","<|image_pad|>","<|video_pad|>"],
|
| 118 |
+
"bos_token": null,
|
| 119 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 120 |
+
"clean_up_tokenization_spaces": false,
|
| 121 |
+
"eos_token": "<|im_end|>",
|
| 122 |
+
"padding_side": "left",
|
| 123 |
+
"errors": "replace",
|
| 124 |
+
"model_max_length": 32768,
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
+
"split_special_tokens": false,
|
| 127 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 128 |
+
"unk_token": null
|
| 129 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9998731447418495,
|
| 3 |
+
"total_flos": 3.7575827488610714e+18,
|
| 4 |
+
"train_loss": 1.3289946492206504,
|
| 5 |
+
"train_runtime": 13442.1001,
|
| 6 |
+
"train_samples_per_second": 37.53,
|
| 7 |
+
"train_steps_per_second": 0.293
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,395 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 3941, "loss": 1.8196, "learning_rate": 2.5316455696202533e-07, "epoch": 0.002537105163009007, "percentage": 0.25, "elapsed_time": "0:00:32", "remaining_time": "3:34:55"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 3941, "loss": 1.8108, "learning_rate": 5.063291139240507e-07, "epoch": 0.005074210326018014, "percentage": 0.51, "elapsed_time": "0:01:08", "remaining_time": "3:44:07"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 3941, "loss": 1.8147, "learning_rate": 7.59493670886076e-07, "epoch": 0.00761131548902702, "percentage": 0.76, "elapsed_time": "0:01:42", "remaining_time": "3:42:31"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 3941, "loss": 1.7548, "learning_rate": 1.0126582278481013e-06, "epoch": 0.010148420652036028, "percentage": 1.01, "elapsed_time": "0:02:16", "remaining_time": "3:42:17"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 3941, "loss": 1.7204, "learning_rate": 1.2658227848101267e-06, "epoch": 0.012685525815045033, "percentage": 1.27, "elapsed_time": "0:02:48", "remaining_time": "3:38:29"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 3941, "loss": 1.6762, "learning_rate": 1.518987341772152e-06, "epoch": 0.01522263097805404, "percentage": 1.52, "elapsed_time": "0:03:21", "remaining_time": "3:37:36"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 3941, "loss": 1.6487, "learning_rate": 1.7721518987341774e-06, "epoch": 0.01775973614106305, "percentage": 1.78, "elapsed_time": "0:03:57", "remaining_time": "3:39:16"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 3941, "loss": 1.6116, "learning_rate": 2.0253164556962026e-06, "epoch": 0.020296841304072055, "percentage": 2.03, "elapsed_time": "0:04:29", "remaining_time": "3:36:57"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 3941, "loss": 1.5916, "learning_rate": 2.278481012658228e-06, "epoch": 0.022833946467081062, "percentage": 2.28, "elapsed_time": "0:05:02", "remaining_time": "3:35:57"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 3941, "loss": 1.598, "learning_rate": 2.5316455696202535e-06, "epoch": 0.025371051630090066, "percentage": 2.54, "elapsed_time": "0:05:36", "remaining_time": "3:35:26"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 3941, "loss": 1.5626, "learning_rate": 2.7848101265822785e-06, "epoch": 0.027908156793099072, "percentage": 2.79, "elapsed_time": "0:06:09", "remaining_time": "3:34:13"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 3941, "loss": 1.5457, "learning_rate": 3.037974683544304e-06, "epoch": 0.03044526195610808, "percentage": 3.04, "elapsed_time": "0:06:39", "remaining_time": "3:32:00"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 3941, "loss": 1.5391, "learning_rate": 3.2911392405063294e-06, "epoch": 0.03298236711911709, "percentage": 3.3, "elapsed_time": "0:07:12", "remaining_time": "3:31:05"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 3941, "loss": 1.5125, "learning_rate": 3.544303797468355e-06, "epoch": 0.0355194722821261, "percentage": 3.55, "elapsed_time": "0:07:44", "remaining_time": "3:30:08"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 3941, "loss": 1.5243, "learning_rate": 3.7974683544303802e-06, "epoch": 0.038056577445135104, "percentage": 3.81, "elapsed_time": "0:08:16", "remaining_time": "3:29:11"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 3941, "loss": 1.4856, "learning_rate": 4.050632911392405e-06, "epoch": 0.04059368260814411, "percentage": 4.06, "elapsed_time": "0:08:50", "remaining_time": "3:29:02"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 3941, "loss": 1.5129, "learning_rate": 4.303797468354431e-06, "epoch": 0.04313078777115312, "percentage": 4.31, "elapsed_time": "0:09:23", "remaining_time": "3:28:21"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 3941, "loss": 1.4961, "learning_rate": 4.556962025316456e-06, "epoch": 0.045667892934162124, "percentage": 4.57, "elapsed_time": "0:09:56", "remaining_time": "3:27:34"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 3941, "loss": 1.4893, "learning_rate": 4.8101265822784815e-06, "epoch": 0.04820499809717113, "percentage": 4.82, "elapsed_time": "0:10:29", "remaining_time": "3:27:00"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 3941, "loss": 1.5013, "learning_rate": 5.063291139240507e-06, "epoch": 0.05074210326018013, "percentage": 5.07, "elapsed_time": "0:11:02", "remaining_time": "3:26:27"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 3941, "loss": 1.473, "learning_rate": 5.3164556962025316e-06, "epoch": 0.05327920842318914, "percentage": 5.33, "elapsed_time": "0:11:34", "remaining_time": "3:25:44"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 3941, "loss": 1.4791, "learning_rate": 5.569620253164557e-06, "epoch": 0.055816313586198145, "percentage": 5.58, "elapsed_time": "0:12:07", "remaining_time": "3:25:09"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 3941, "loss": 1.4761, "learning_rate": 5.8227848101265824e-06, "epoch": 0.05835341874920715, "percentage": 5.84, "elapsed_time": "0:12:40", "remaining_time": "3:24:37"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 3941, "loss": 1.4626, "learning_rate": 6.075949367088608e-06, "epoch": 0.06089052391221616, "percentage": 6.09, "elapsed_time": "0:13:13", "remaining_time": "3:23:57"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 3941, "loss": 1.4601, "learning_rate": 6.329113924050634e-06, "epoch": 0.06342762907522517, "percentage": 6.34, "elapsed_time": "0:13:45", "remaining_time": "3:23:09"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 3941, "loss": 1.4686, "learning_rate": 6.582278481012659e-06, "epoch": 0.06596473423823418, "percentage": 6.6, "elapsed_time": "0:14:19", "remaining_time": "3:22:45"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 3941, "loss": 1.461, "learning_rate": 6.835443037974684e-06, "epoch": 0.06850183940124319, "percentage": 6.85, "elapsed_time": "0:14:52", "remaining_time": "3:22:16"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 3941, "loss": 1.47, "learning_rate": 7.08860759493671e-06, "epoch": 0.0710389445642522, "percentage": 7.1, "elapsed_time": "0:15:26", "remaining_time": "3:21:51"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 3941, "loss": 1.4526, "learning_rate": 7.341772151898735e-06, "epoch": 0.0735760497272612, "percentage": 7.36, "elapsed_time": "0:15:58", "remaining_time": "3:21:01"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 3941, "loss": 1.4501, "learning_rate": 7.5949367088607605e-06, "epoch": 0.07611315489027021, "percentage": 7.61, "elapsed_time": "0:16:29", "remaining_time": "3:20:05"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 3941, "loss": 1.4483, "learning_rate": 7.848101265822786e-06, "epoch": 0.07865026005327921, "percentage": 7.87, "elapsed_time": "0:17:01", "remaining_time": "3:19:29"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 3941, "loss": 1.4252, "learning_rate": 8.10126582278481e-06, "epoch": 0.08118736521628822, "percentage": 8.12, "elapsed_time": "0:17:34", "remaining_time": "3:18:56"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 3941, "loss": 1.4274, "learning_rate": 8.354430379746837e-06, "epoch": 0.08372447037929723, "percentage": 8.37, "elapsed_time": "0:18:08", "remaining_time": "3:18:27"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 3941, "loss": 1.437, "learning_rate": 8.607594936708861e-06, "epoch": 0.08626157554230623, "percentage": 8.63, "elapsed_time": "0:18:40", "remaining_time": "3:17:44"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 3941, "loss": 1.4388, "learning_rate": 8.860759493670886e-06, "epoch": 0.08879868070531524, "percentage": 8.88, "elapsed_time": "0:19:13", "remaining_time": "3:17:12"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 3941, "loss": 1.4151, "learning_rate": 9.113924050632912e-06, "epoch": 0.09133578586832425, "percentage": 9.13, "elapsed_time": "0:19:47", "remaining_time": "3:16:48"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 3941, "loss": 1.4274, "learning_rate": 9.367088607594937e-06, "epoch": 0.09387289103133326, "percentage": 9.39, "elapsed_time": "0:20:19", "remaining_time": "3:16:13"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 3941, "loss": 1.4309, "learning_rate": 9.620253164556963e-06, "epoch": 0.09640999619434226, "percentage": 9.64, "elapsed_time": "0:20:53", "remaining_time": "3:15:48"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 3941, "loss": 1.4173, "learning_rate": 9.87341772151899e-06, "epoch": 0.09894710135735126, "percentage": 9.9, "elapsed_time": "0:21:29", "remaining_time": "3:15:37"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 3941, "loss": 1.4312, "learning_rate": 9.999950942931784e-06, "epoch": 0.10148420652036026, "percentage": 10.15, "elapsed_time": "0:22:03", "remaining_time": "3:15:20"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 3941, "loss": 1.422, "learning_rate": 9.999558492161865e-06, "epoch": 0.10402131168336927, "percentage": 10.4, "elapsed_time": "0:22:38", "remaining_time": "3:14:56"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 3941, "loss": 1.3892, "learning_rate": 9.998773621425852e-06, "epoch": 0.10655841684637828, "percentage": 10.66, "elapsed_time": "0:23:12", "remaining_time": "3:14:35"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 3941, "loss": 1.4368, "learning_rate": 9.997596392328971e-06, "epoch": 0.10909552200938728, "percentage": 10.91, "elapsed_time": "0:23:47", "remaining_time": "3:14:14"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 3941, "loss": 1.4129, "learning_rate": 9.996026897273024e-06, "epoch": 0.11163262717239629, "percentage": 11.16, "elapsed_time": "0:24:23", "remaining_time": "3:14:08"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 3941, "loss": 1.4181, "learning_rate": 9.994065259449128e-06, "epoch": 0.1141697323354053, "percentage": 11.42, "elapsed_time": "0:24:58", "remaining_time": "3:13:42"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 3941, "loss": 1.4107, "learning_rate": 9.991711632828049e-06, "epoch": 0.1167068374984143, "percentage": 11.67, "elapsed_time": "0:25:31", "remaining_time": "3:13:11"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 3941, "loss": 1.3933, "learning_rate": 9.988966202148115e-06, "epoch": 0.11924394266142331, "percentage": 11.93, "elapsed_time": "0:26:05", "remaining_time": "3:12:38"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 3941, "loss": 1.4305, "learning_rate": 9.985829182900717e-06, "epoch": 0.12178104782443232, "percentage": 12.18, "elapsed_time": "0:26:36", "remaining_time": "3:11:51"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 3941, "loss": 1.407, "learning_rate": 9.982300821313394e-06, "epoch": 0.12431815298744132, "percentage": 12.43, "elapsed_time": "0:27:08", "remaining_time": "3:11:06"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 3941, "loss": 1.3941, "learning_rate": 9.978381394330509e-06, "epoch": 0.12685525815045035, "percentage": 12.69, "elapsed_time": "0:27:40", "remaining_time": "3:10:30"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 3941, "loss": 1.4083, "learning_rate": 9.974071209591507e-06, "epoch": 0.12939236331345935, "percentage": 12.94, "elapsed_time": "0:29:19", "remaining_time": "3:17:14"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 3941, "loss": 1.3913, "learning_rate": 9.96937060540677e-06, "epoch": 0.13192946847646836, "percentage": 13.19, "elapsed_time": "0:29:53", "remaining_time": "3:16:41"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 3941, "loss": 1.4141, "learning_rate": 9.964279950731066e-06, "epoch": 0.13446657363947737, "percentage": 13.45, "elapsed_time": "0:30:26", "remaining_time": "3:15:52"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 3941, "loss": 1.3923, "learning_rate": 9.958799645134585e-06, "epoch": 0.13700367880248637, "percentage": 13.7, "elapsed_time": "0:30:58", "remaining_time": "3:15:06"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 3941, "loss": 1.3882, "learning_rate": 9.952930118771576e-06, "epoch": 0.13954078396549538, "percentage": 13.96, "elapsed_time": "0:31:30", "remaining_time": "3:14:16"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 3941, "loss": 1.3806, "learning_rate": 9.946671832346588e-06, "epoch": 0.1420778891285044, "percentage": 14.21, "elapsed_time": "0:32:02", "remaining_time": "3:13:28"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 3941, "loss": 1.3877, "learning_rate": 9.940025277078304e-06, "epoch": 0.1446149942915134, "percentage": 14.46, "elapsed_time": "0:32:36", "remaining_time": "3:12:48"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 3941, "loss": 1.3758, "learning_rate": 9.932990974660992e-06, "epoch": 0.1471520994545224, "percentage": 14.72, "elapsed_time": "0:33:08", "remaining_time": "3:12:04"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 3941, "loss": 1.3942, "learning_rate": 9.925569477223549e-06, "epoch": 0.1496892046175314, "percentage": 14.97, "elapsed_time": "0:33:41", "remaining_time": "3:11:19"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 3941, "loss": 1.3997, "learning_rate": 9.917761367286164e-06, "epoch": 0.15222630978054041, "percentage": 15.22, "elapsed_time": "0:34:13", "remaining_time": "3:10:33"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 3941, "loss": 1.3902, "learning_rate": 9.909567257714605e-06, "epoch": 0.15476341494354942, "percentage": 15.48, "elapsed_time": "0:34:45", "remaining_time": "3:09:49"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 3941, "loss": 1.3906, "learning_rate": 9.9009877916721e-06, "epoch": 0.15730052010655843, "percentage": 15.73, "elapsed_time": "0:35:18", "remaining_time": "3:09:07"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 3941, "loss": 1.3644, "learning_rate": 9.892023642568871e-06, "epoch": 0.15983762526956743, "percentage": 15.99, "elapsed_time": "0:35:53", "remaining_time": "3:08:37"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 3941, "loss": 1.3673, "learning_rate": 9.882675514009262e-06, "epoch": 0.16237473043257644, "percentage": 16.24, "elapsed_time": "0:36:27", "remaining_time": "3:08:00"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 3941, "loss": 1.3751, "learning_rate": 9.872944139736523e-06, "epoch": 0.16491183559558545, "percentage": 16.49, "elapsed_time": "0:36:57", "remaining_time": "3:07:09"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 3941, "loss": 1.3678, "learning_rate": 9.862830283575215e-06, "epoch": 0.16744894075859446, "percentage": 16.75, "elapsed_time": "0:37:29", "remaining_time": "3:06:23"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 3941, "loss": 1.3825, "learning_rate": 9.852334739371252e-06, "epoch": 0.16998604592160346, "percentage": 17.0, "elapsed_time": "0:38:00", "remaining_time": "3:05:34"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 3941, "loss": 1.3884, "learning_rate": 9.841458330929598e-06, "epoch": 0.17252315108461247, "percentage": 17.25, "elapsed_time": "0:38:33", "remaining_time": "3:04:52"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 3941, "loss": 1.3934, "learning_rate": 9.830201911949604e-06, "epoch": 0.17506025624762148, "percentage": 17.51, "elapsed_time": "0:39:05", "remaining_time": "3:04:11"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 3941, "loss": 1.3645, "learning_rate": 9.818566365957996e-06, "epoch": 0.17759736141063048, "percentage": 17.76, "elapsed_time": "0:39:37", "remaining_time": "3:03:29"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 3941, "loss": 1.3708, "learning_rate": 9.80655260623953e-06, "epoch": 0.1801344665736395, "percentage": 18.02, "elapsed_time": "0:40:11", "remaining_time": "3:02:55"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 3941, "loss": 1.3749, "learning_rate": 9.794161575765311e-06, "epoch": 0.1826715717366485, "percentage": 18.27, "elapsed_time": "0:40:45", "remaining_time": "3:02:18"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 3941, "loss": 1.3886, "learning_rate": 9.78139424711877e-06, "epoch": 0.1852086768996575, "percentage": 18.52, "elapsed_time": "0:41:18", "remaining_time": "3:01:41"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 3941, "loss": 1.373, "learning_rate": 9.76825162241933e-06, "epoch": 0.1877457820626665, "percentage": 18.78, "elapsed_time": "0:41:52", "remaining_time": "3:01:08"}
|
| 75 |
+
{"current_steps": 750, "total_steps": 3941, "loss": 1.3742, "learning_rate": 9.754734733243749e-06, "epoch": 0.19028288722567552, "percentage": 19.03, "elapsed_time": "0:42:26", "remaining_time": "3:00:34"}
|
| 76 |
+
{"current_steps": 760, "total_steps": 3941, "loss": 1.3603, "learning_rate": 9.740844640545151e-06, "epoch": 0.19281999238868452, "percentage": 19.28, "elapsed_time": "0:43:00", "remaining_time": "2:59:59"}
|
| 77 |
+
{"current_steps": 770, "total_steps": 3941, "loss": 1.3636, "learning_rate": 9.726582434569744e-06, "epoch": 0.19535709755169353, "percentage": 19.54, "elapsed_time": "0:43:33", "remaining_time": "2:59:22"}
|
| 78 |
+
{"current_steps": 780, "total_steps": 3941, "loss": 1.3536, "learning_rate": 9.711949234771258e-06, "epoch": 0.1978942027147025, "percentage": 19.79, "elapsed_time": "0:44:05", "remaining_time": "2:58:40"}
|
| 79 |
+
{"current_steps": 790, "total_steps": 3941, "loss": 1.3777, "learning_rate": 9.696946189723067e-06, "epoch": 0.20043130787771152, "percentage": 20.05, "elapsed_time": "0:44:37", "remaining_time": "2:58:00"}
|
| 80 |
+
{"current_steps": 800, "total_steps": 3941, "loss": 1.3555, "learning_rate": 9.681574477028039e-06, "epoch": 0.20296841304072052, "percentage": 20.3, "elapsed_time": "0:45:09", "remaining_time": "2:57:17"}
|
| 81 |
+
{"current_steps": 810, "total_steps": 3941, "loss": 1.3736, "learning_rate": 9.66583530322611e-06, "epoch": 0.20550551820372953, "percentage": 20.55, "elapsed_time": "0:45:41", "remaining_time": "2:56:38"}
|
| 82 |
+
{"current_steps": 820, "total_steps": 3941, "loss": 1.3685, "learning_rate": 9.649729903699575e-06, "epoch": 0.20804262336673854, "percentage": 20.81, "elapsed_time": "0:46:15", "remaining_time": "2:56:04"}
|
| 83 |
+
{"current_steps": 830, "total_steps": 3941, "loss": 1.3516, "learning_rate": 9.633259542576127e-06, "epoch": 0.21057972852974755, "percentage": 21.06, "elapsed_time": "0:46:47", "remaining_time": "2:55:22"}
|
| 84 |
+
{"current_steps": 840, "total_steps": 3941, "loss": 1.3433, "learning_rate": 9.61642551262963e-06, "epoch": 0.21311683369275655, "percentage": 21.31, "elapsed_time": "0:47:19", "remaining_time": "2:54:42"}
|
| 85 |
+
{"current_steps": 850, "total_steps": 3941, "loss": 1.3596, "learning_rate": 9.599229135178651e-06, "epoch": 0.21565393885576556, "percentage": 21.57, "elapsed_time": "0:47:52", "remaining_time": "2:54:05"}
|
| 86 |
+
{"current_steps": 860, "total_steps": 3941, "loss": 1.3821, "learning_rate": 9.581671759982747e-06, "epoch": 0.21819104401877457, "percentage": 21.82, "elapsed_time": "0:48:25", "remaining_time": "2:53:27"}
|
| 87 |
+
{"current_steps": 870, "total_steps": 3941, "loss": 1.3568, "learning_rate": 9.563754765136522e-06, "epoch": 0.22072814918178357, "percentage": 22.08, "elapsed_time": "0:48:57", "remaining_time": "2:52:49"}
|
| 88 |
+
{"current_steps": 880, "total_steps": 3941, "loss": 1.3614, "learning_rate": 9.545479556961457e-06, "epoch": 0.22326525434479258, "percentage": 22.33, "elapsed_time": "0:49:29", "remaining_time": "2:52:10"}
|
| 89 |
+
{"current_steps": 890, "total_steps": 3941, "loss": 1.3536, "learning_rate": 9.526847569895529e-06, "epoch": 0.2258023595078016, "percentage": 22.58, "elapsed_time": "0:50:02", "remaining_time": "2:51:31"}
|
| 90 |
+
{"current_steps": 900, "total_steps": 3941, "loss": 1.3521, "learning_rate": 9.507860266380625e-06, "epoch": 0.2283394646708106, "percentage": 22.84, "elapsed_time": "0:50:35", "remaining_time": "2:50:55"}
|
| 91 |
+
{"current_steps": 910, "total_steps": 3941, "loss": 1.3455, "learning_rate": 9.488519136747741e-06, "epoch": 0.2308765698338196, "percentage": 23.09, "elapsed_time": "0:51:07", "remaining_time": "2:50:16"}
|
| 92 |
+
{"current_steps": 920, "total_steps": 3941, "loss": 1.3388, "learning_rate": 9.468825699100013e-06, "epoch": 0.2334136749968286, "percentage": 23.34, "elapsed_time": "0:51:39", "remaining_time": "2:49:39"}
|
| 93 |
+
{"current_steps": 930, "total_steps": 3941, "loss": 1.36, "learning_rate": 9.448781499193563e-06, "epoch": 0.23595078015983761, "percentage": 23.6, "elapsed_time": "0:52:13", "remaining_time": "2:49:05"}
|
| 94 |
+
{"current_steps": 940, "total_steps": 3941, "loss": 1.346, "learning_rate": 9.428388110316165e-06, "epoch": 0.23848788532284662, "percentage": 23.85, "elapsed_time": "0:52:45", "remaining_time": "2:48:25"}
|
| 95 |
+
{"current_steps": 950, "total_steps": 3941, "loss": 1.3565, "learning_rate": 9.407647133163754e-06, "epoch": 0.24102499048585563, "percentage": 24.11, "elapsed_time": "0:53:18", "remaining_time": "2:47:49"}
|
| 96 |
+
{"current_steps": 960, "total_steps": 3941, "loss": 1.3539, "learning_rate": 9.386560195714796e-06, "epoch": 0.24356209564886463, "percentage": 24.36, "elapsed_time": "0:53:50", "remaining_time": "2:47:12"}
|
| 97 |
+
{"current_steps": 970, "total_steps": 3941, "loss": 1.3443, "learning_rate": 9.365128953102495e-06, "epoch": 0.24609920081187364, "percentage": 24.61, "elapsed_time": "0:54:23", "remaining_time": "2:46:35"}
|
| 98 |
+
{"current_steps": 980, "total_steps": 3941, "loss": 1.3449, "learning_rate": 9.343355087484893e-06, "epoch": 0.24863630597488265, "percentage": 24.87, "elapsed_time": "0:54:56", "remaining_time": "2:45:59"}
|
| 99 |
+
{"current_steps": 990, "total_steps": 3941, "loss": 1.3503, "learning_rate": 9.321240307912818e-06, "epoch": 0.25117341113789166, "percentage": 25.12, "elapsed_time": "0:55:30", "remaining_time": "2:45:26"}
|
| 100 |
+
{"current_steps": 1000, "total_steps": 3941, "loss": 1.3504, "learning_rate": 9.298786350195758e-06, "epoch": 0.2537105163009007, "percentage": 25.37, "elapsed_time": "0:56:02", "remaining_time": "2:44:49"}
|
| 101 |
+
{"current_steps": 1010, "total_steps": 3941, "loss": 1.3512, "learning_rate": 9.275994976765602e-06, "epoch": 0.25624762146390967, "percentage": 25.63, "elapsed_time": "0:57:46", "remaining_time": "2:47:39"}
|
| 102 |
+
{"current_steps": 1020, "total_steps": 3941, "loss": 1.3447, "learning_rate": 9.252867976538312e-06, "epoch": 0.2587847266269187, "percentage": 25.88, "elapsed_time": "0:58:17", "remaining_time": "2:46:55"}
|
| 103 |
+
{"current_steps": 1030, "total_steps": 3941, "loss": 1.3451, "learning_rate": 9.22940716477351e-06, "epoch": 0.2613218317899277, "percentage": 26.14, "elapsed_time": "0:58:50", "remaining_time": "2:46:16"}
|
| 104 |
+
{"current_steps": 1040, "total_steps": 3941, "loss": 1.3678, "learning_rate": 9.205614382931986e-06, "epoch": 0.2638589369529367, "percentage": 26.39, "elapsed_time": "0:59:20", "remaining_time": "2:45:32"}
|
| 105 |
+
{"current_steps": 1050, "total_steps": 3941, "loss": 1.355, "learning_rate": 9.181491498531179e-06, "epoch": 0.2663960421159457, "percentage": 26.64, "elapsed_time": "0:59:53", "remaining_time": "2:44:54"}
|
| 106 |
+
{"current_steps": 1060, "total_steps": 3941, "loss": 1.3455, "learning_rate": 9.157040404998572e-06, "epoch": 0.26893314727895473, "percentage": 26.9, "elapsed_time": "1:00:26", "remaining_time": "2:44:16"}
|
| 107 |
+
{"current_steps": 1070, "total_steps": 3941, "loss": 1.353, "learning_rate": 9.132263021523096e-06, "epoch": 0.2714702524419637, "percentage": 27.15, "elapsed_time": "1:00:58", "remaining_time": "2:43:36"}
|
| 108 |
+
{"current_steps": 1080, "total_steps": 3941, "loss": 1.3428, "learning_rate": 9.107161292904476e-06, "epoch": 0.27400735760497275, "percentage": 27.4, "elapsed_time": "1:01:30", "remaining_time": "2:42:56"}
|
| 109 |
+
{"current_steps": 1090, "total_steps": 3941, "loss": 1.3421, "learning_rate": 9.081737189400583e-06, "epoch": 0.2765444627679817, "percentage": 27.66, "elapsed_time": "1:02:02", "remaining_time": "2:42:15"}
|
| 110 |
+
{"current_steps": 1100, "total_steps": 3941, "loss": 1.3377, "learning_rate": 9.0559927065728e-06, "epoch": 0.27908156793099076, "percentage": 27.91, "elapsed_time": "1:02:35", "remaining_time": "2:41:39"}
|
| 111 |
+
{"current_steps": 1110, "total_steps": 3941, "loss": 1.349, "learning_rate": 9.029929865129375e-06, "epoch": 0.28161867309399974, "percentage": 28.17, "elapsed_time": "1:03:06", "remaining_time": "2:40:57"}
|
| 112 |
+
{"current_steps": 1120, "total_steps": 3941, "loss": 1.3552, "learning_rate": 9.003550710766813e-06, "epoch": 0.2841557782570088, "percentage": 28.42, "elapsed_time": "1:03:39", "remaining_time": "2:40:20"}
|
| 113 |
+
{"current_steps": 1130, "total_steps": 3941, "loss": 1.3209, "learning_rate": 8.97685731400932e-06, "epoch": 0.28669288342001775, "percentage": 28.67, "elapsed_time": "1:04:13", "remaining_time": "2:39:46"}
|
| 114 |
+
{"current_steps": 1140, "total_steps": 3941, "loss": 1.3267, "learning_rate": 8.949851770046272e-06, "epoch": 0.2892299885830268, "percentage": 28.93, "elapsed_time": "1:04:47", "remaining_time": "2:39:11"}
|
| 115 |
+
{"current_steps": 1150, "total_steps": 3941, "loss": 1.3379, "learning_rate": 8.922536198567772e-06, "epoch": 0.29176709374603577, "percentage": 29.18, "elapsed_time": "1:05:21", "remaining_time": "2:38:36"}
|
| 116 |
+
{"current_steps": 1160, "total_steps": 3941, "loss": 1.3272, "learning_rate": 8.894912743598269e-06, "epoch": 0.2943041989090448, "percentage": 29.43, "elapsed_time": "1:05:54", "remaining_time": "2:37:59"}
|
| 117 |
+
{"current_steps": 1170, "total_steps": 3941, "loss": 1.333, "learning_rate": 8.866983573328267e-06, "epoch": 0.2968413040720538, "percentage": 29.69, "elapsed_time": "1:06:26", "remaining_time": "2:37:21"}
|
| 118 |
+
{"current_steps": 1180, "total_steps": 3941, "loss": 1.3497, "learning_rate": 8.83875087994415e-06, "epoch": 0.2993784092350628, "percentage": 29.94, "elapsed_time": "1:06:58", "remaining_time": "2:36:42"}
|
| 119 |
+
{"current_steps": 1190, "total_steps": 3941, "loss": 1.3355, "learning_rate": 8.810216879456114e-06, "epoch": 0.3019155143980718, "percentage": 30.2, "elapsed_time": "1:07:31", "remaining_time": "2:36:05"}
|
| 120 |
+
{"current_steps": 1200, "total_steps": 3941, "loss": 1.3339, "learning_rate": 8.781383811524222e-06, "epoch": 0.30445261956108083, "percentage": 30.45, "elapsed_time": "1:08:04", "remaining_time": "2:35:29"}
|
| 121 |
+
{"current_steps": 1210, "total_steps": 3941, "loss": 1.332, "learning_rate": 8.752253939282622e-06, "epoch": 0.3069897247240898, "percentage": 30.7, "elapsed_time": "1:08:35", "remaining_time": "2:34:49"}
|
| 122 |
+
{"current_steps": 1220, "total_steps": 3941, "loss": 1.3411, "learning_rate": 8.722829549161904e-06, "epoch": 0.30952682988709884, "percentage": 30.96, "elapsed_time": "1:09:08", "remaining_time": "2:34:12"}
|
| 123 |
+
{"current_steps": 1230, "total_steps": 3941, "loss": 1.321, "learning_rate": 8.69311295070964e-06, "epoch": 0.3120639350501078, "percentage": 31.21, "elapsed_time": "1:09:41", "remaining_time": "2:33:35"}
|
| 124 |
+
{"current_steps": 1240, "total_steps": 3941, "loss": 1.3511, "learning_rate": 8.663106476409107e-06, "epoch": 0.31460104021311686, "percentage": 31.46, "elapsed_time": "1:10:13", "remaining_time": "2:32:58"}
|
| 125 |
+
{"current_steps": 1250, "total_steps": 3941, "loss": 1.3491, "learning_rate": 8.632812481496195e-06, "epoch": 0.31713814537612584, "percentage": 31.72, "elapsed_time": "1:10:44", "remaining_time": "2:32:18"}
|
| 126 |
+
{"current_steps": 1260, "total_steps": 3941, "loss": 1.3294, "learning_rate": 8.602233343774562e-06, "epoch": 0.31967525053913487, "percentage": 31.97, "elapsed_time": "1:11:17", "remaining_time": "2:31:41"}
|
| 127 |
+
{"current_steps": 1270, "total_steps": 3941, "loss": 1.3419, "learning_rate": 8.571371463428986e-06, "epoch": 0.32221235570214385, "percentage": 32.23, "elapsed_time": "1:11:49", "remaining_time": "2:31:03"}
|
| 128 |
+
{"current_steps": 1280, "total_steps": 3941, "loss": 1.3245, "learning_rate": 8.540229262836974e-06, "epoch": 0.3247494608651529, "percentage": 32.48, "elapsed_time": "1:12:21", "remaining_time": "2:30:26"}
|
| 129 |
+
{"current_steps": 1290, "total_steps": 3941, "loss": 1.3357, "learning_rate": 8.508809186378631e-06, "epoch": 0.32728656602816186, "percentage": 32.73, "elapsed_time": "1:12:53", "remaining_time": "2:29:47"}
|
| 130 |
+
{"current_steps": 1300, "total_steps": 3941, "loss": 1.3297, "learning_rate": 8.477113700244788e-06, "epoch": 0.3298236711911709, "percentage": 32.99, "elapsed_time": "1:13:26", "remaining_time": "2:29:11"}
|
| 131 |
+
{"current_steps": 1310, "total_steps": 3941, "loss": 1.3361, "learning_rate": 8.445145292243446e-06, "epoch": 0.3323607763541799, "percentage": 33.24, "elapsed_time": "1:13:58", "remaining_time": "2:28:35"}
|
| 132 |
+
{"current_steps": 1320, "total_steps": 3941, "loss": 1.3365, "learning_rate": 8.412906471604489e-06, "epoch": 0.3348978815171889, "percentage": 33.49, "elapsed_time": "1:14:30", "remaining_time": "2:27:56"}
|
| 133 |
+
{"current_steps": 1330, "total_steps": 3941, "loss": 1.3364, "learning_rate": 8.380399768782742e-06, "epoch": 0.3374349866801979, "percentage": 33.75, "elapsed_time": "1:15:03", "remaining_time": "2:27:20"}
|
| 134 |
+
{"current_steps": 1340, "total_steps": 3941, "loss": 1.3572, "learning_rate": 8.347627735259344e-06, "epoch": 0.3399720918432069, "percentage": 34.0, "elapsed_time": "1:15:36", "remaining_time": "2:26:44"}
|
| 135 |
+
{"current_steps": 1350, "total_steps": 3941, "loss": 1.311, "learning_rate": 8.314592943341494e-06, "epoch": 0.3425091970062159, "percentage": 34.26, "elapsed_time": "1:16:08", "remaining_time": "2:26:07"}
|
| 136 |
+
{"current_steps": 1360, "total_steps": 3941, "loss": 1.3261, "learning_rate": 8.281297985960538e-06, "epoch": 0.34504630216922494, "percentage": 34.51, "elapsed_time": "1:16:39", "remaining_time": "2:25:29"}
|
| 137 |
+
{"current_steps": 1370, "total_steps": 3941, "loss": 1.3433, "learning_rate": 8.247745476468449e-06, "epoch": 0.3475834073322339, "percentage": 34.76, "elapsed_time": "1:17:12", "remaining_time": "2:24:52"}
|
| 138 |
+
{"current_steps": 1380, "total_steps": 3941, "loss": 1.3134, "learning_rate": 8.213938048432697e-06, "epoch": 0.35012051249524295, "percentage": 35.02, "elapsed_time": "1:17:44", "remaining_time": "2:24:16"}
|
| 139 |
+
{"current_steps": 1390, "total_steps": 3941, "loss": 1.3159, "learning_rate": 8.179878355429556e-06, "epoch": 0.35265761765825193, "percentage": 35.27, "elapsed_time": "1:18:18", "remaining_time": "2:23:42"}
|
| 140 |
+
{"current_steps": 1400, "total_steps": 3941, "loss": 1.3285, "learning_rate": 8.145569070835799e-06, "epoch": 0.35519472282126097, "percentage": 35.52, "elapsed_time": "1:18:51", "remaining_time": "2:23:07"}
|
| 141 |
+
{"current_steps": 1410, "total_steps": 3941, "loss": 1.344, "learning_rate": 8.111012887618882e-06, "epoch": 0.35773182798426995, "percentage": 35.78, "elapsed_time": "1:19:23", "remaining_time": "2:22:31"}
|
| 142 |
+
{"current_steps": 1420, "total_steps": 3941, "loss": 1.3217, "learning_rate": 8.076212518125556e-06, "epoch": 0.360268933147279, "percentage": 36.03, "elapsed_time": "1:19:56", "remaining_time": "2:21:56"}
|
| 143 |
+
{"current_steps": 1430, "total_steps": 3941, "loss": 1.3284, "learning_rate": 8.041170693868985e-06, "epoch": 0.36280603831028796, "percentage": 36.29, "elapsed_time": "1:20:30", "remaining_time": "2:21:21"}
|
| 144 |
+
{"current_steps": 1440, "total_steps": 3941, "loss": 1.3188, "learning_rate": 8.005890165314334e-06, "epoch": 0.365343143473297, "percentage": 36.54, "elapsed_time": "1:21:01", "remaining_time": "2:20:44"}
|
| 145 |
+
{"current_steps": 1450, "total_steps": 3941, "loss": 1.3123, "learning_rate": 7.970373701662892e-06, "epoch": 0.367880248636306, "percentage": 36.79, "elapsed_time": "1:21:35", "remaining_time": "2:20:09"}
|
| 146 |
+
{"current_steps": 1460, "total_steps": 3941, "loss": 1.3131, "learning_rate": 7.934624090634713e-06, "epoch": 0.370417353799315, "percentage": 37.05, "elapsed_time": "1:22:08", "remaining_time": "2:19:34"}
|
| 147 |
+
{"current_steps": 1470, "total_steps": 3941, "loss": 1.3318, "learning_rate": 7.8986441382498e-06, "epoch": 0.372954458962324, "percentage": 37.3, "elapsed_time": "1:22:40", "remaining_time": "2:18:57"}
|
| 148 |
+
{"current_steps": 1480, "total_steps": 3941, "loss": 1.3164, "learning_rate": 7.862436668607865e-06, "epoch": 0.375491564125333, "percentage": 37.55, "elapsed_time": "1:23:12", "remaining_time": "2:18:22"}
|
| 149 |
+
{"current_steps": 1490, "total_steps": 3941, "loss": 1.3292, "learning_rate": 7.826004523666661e-06, "epoch": 0.378028669288342, "percentage": 37.81, "elapsed_time": "1:23:43", "remaining_time": "2:17:43"}
|
| 150 |
+
{"current_steps": 1500, "total_steps": 3941, "loss": 1.3272, "learning_rate": 7.78935056301891e-06, "epoch": 0.38056577445135104, "percentage": 38.06, "elapsed_time": "1:24:16", "remaining_time": "2:17:08"}
|
| 151 |
+
{"current_steps": 1510, "total_steps": 3941, "loss": 1.3391, "learning_rate": 7.752477663667854e-06, "epoch": 0.38310287961436, "percentage": 38.32, "elapsed_time": "1:25:53", "remaining_time": "2:18:16"}
|
| 152 |
+
{"current_steps": 1520, "total_steps": 3941, "loss": 1.3392, "learning_rate": 7.715388719801437e-06, "epoch": 0.38563998477736905, "percentage": 38.57, "elapsed_time": "1:26:24", "remaining_time": "2:17:37"}
|
| 153 |
+
{"current_steps": 1530, "total_steps": 3941, "loss": 1.2971, "learning_rate": 7.67808664256514e-06, "epoch": 0.38817708994037803, "percentage": 38.82, "elapsed_time": "1:26:56", "remaining_time": "2:16:59"}
|
| 154 |
+
{"current_steps": 1540, "total_steps": 3941, "loss": 1.3148, "learning_rate": 7.640574359833472e-06, "epoch": 0.39071419510338706, "percentage": 39.08, "elapsed_time": "1:27:29", "remaining_time": "2:16:25"}
|
| 155 |
+
{"current_steps": 1550, "total_steps": 3941, "loss": 1.3315, "learning_rate": 7.6028548159801685e-06, "epoch": 0.39325130026639604, "percentage": 39.33, "elapsed_time": "1:28:03", "remaining_time": "2:15:49"}
|
| 156 |
+
{"current_steps": 1560, "total_steps": 3941, "loss": 1.3238, "learning_rate": 7.564930971647087e-06, "epoch": 0.395788405429405, "percentage": 39.58, "elapsed_time": "1:28:34", "remaining_time": "2:15:11"}
|
| 157 |
+
{"current_steps": 1570, "total_steps": 3941, "loss": 1.3175, "learning_rate": 7.52680580351181e-06, "epoch": 0.39832551059241406, "percentage": 39.84, "elapsed_time": "1:29:06", "remaining_time": "2:14:34"}
|
| 158 |
+
{"current_steps": 1580, "total_steps": 3941, "loss": 1.3104, "learning_rate": 7.488482304054019e-06, "epoch": 0.40086261575542304, "percentage": 40.09, "elapsed_time": "1:29:39", "remaining_time": "2:13:58"}
|
| 159 |
+
{"current_steps": 1590, "total_steps": 3941, "loss": 1.316, "learning_rate": 7.449963481320599e-06, "epoch": 0.40339972091843207, "percentage": 40.35, "elapsed_time": "1:30:11", "remaining_time": "2:13:21"}
|
| 160 |
+
{"current_steps": 1600, "total_steps": 3941, "loss": 1.3273, "learning_rate": 7.411252358689541e-06, "epoch": 0.40593682608144105, "percentage": 40.6, "elapsed_time": "1:30:44", "remaining_time": "2:12:45"}
|
| 161 |
+
{"current_steps": 1610, "total_steps": 3941, "loss": 1.3119, "learning_rate": 7.372351974632634e-06, "epoch": 0.4084739312444501, "percentage": 40.85, "elapsed_time": "1:31:16", "remaining_time": "2:12:09"}
|
| 162 |
+
{"current_steps": 1620, "total_steps": 3941, "loss": 1.3151, "learning_rate": 7.333265382476971e-06, "epoch": 0.41101103640745906, "percentage": 41.11, "elapsed_time": "1:31:52", "remaining_time": "2:11:37"}
|
| 163 |
+
{"current_steps": 1630, "total_steps": 3941, "loss": 1.3245, "learning_rate": 7.293995650165287e-06, "epoch": 0.4135481415704681, "percentage": 41.36, "elapsed_time": "1:32:24", "remaining_time": "2:11:00"}
|
| 164 |
+
{"current_steps": 1640, "total_steps": 3941, "loss": 1.3317, "learning_rate": 7.2545458600151615e-06, "epoch": 0.4160852467334771, "percentage": 41.61, "elapsed_time": "1:32:57", "remaining_time": "2:10:25"}
|
| 165 |
+
{"current_steps": 1650, "total_steps": 3941, "loss": 1.3044, "learning_rate": 7.214919108477077e-06, "epoch": 0.4186223518964861, "percentage": 41.87, "elapsed_time": "1:33:28", "remaining_time": "2:09:47"}
|
| 166 |
+
{"current_steps": 1660, "total_steps": 3941, "loss": 1.3339, "learning_rate": 7.175118505891385e-06, "epoch": 0.4211594570594951, "percentage": 42.12, "elapsed_time": "1:34:00", "remaining_time": "2:09:10"}
|
| 167 |
+
{"current_steps": 1670, "total_steps": 3941, "loss": 1.3044, "learning_rate": 7.135147176244158e-06, "epoch": 0.4236965622225041, "percentage": 42.38, "elapsed_time": "1:34:32", "remaining_time": "2:08:34"}
|
| 168 |
+
{"current_steps": 1680, "total_steps": 3941, "loss": 1.3048, "learning_rate": 7.0950082569219955e-06, "epoch": 0.4262336673855131, "percentage": 42.63, "elapsed_time": "1:35:03", "remaining_time": "2:07:55"}
|
| 169 |
+
{"current_steps": 1690, "total_steps": 3941, "loss": 1.3069, "learning_rate": 7.054704898465772e-06, "epoch": 0.42877077254852214, "percentage": 42.88, "elapsed_time": "1:35:34", "remaining_time": "2:07:18"}
|
| 170 |
+
{"current_steps": 1700, "total_steps": 3941, "loss": 1.3136, "learning_rate": 7.0142402643233346e-06, "epoch": 0.4313078777115311, "percentage": 43.14, "elapsed_time": "1:36:08", "remaining_time": "2:06:44"}
|
| 171 |
+
{"current_steps": 1710, "total_steps": 3941, "loss": 1.3165, "learning_rate": 6.973617530601209e-06, "epoch": 0.43384498287454015, "percentage": 43.39, "elapsed_time": "1:36:43", "remaining_time": "2:06:11"}
|
| 172 |
+
{"current_steps": 1720, "total_steps": 3941, "loss": 1.3301, "learning_rate": 6.932839885815304e-06, "epoch": 0.43638208803754913, "percentage": 43.64, "elapsed_time": "1:37:15", "remaining_time": "2:05:35"}
|
| 173 |
+
{"current_steps": 1730, "total_steps": 3941, "loss": 1.3145, "learning_rate": 6.891910530640642e-06, "epoch": 0.43891919320055817, "percentage": 43.9, "elapsed_time": "1:37:48", "remaining_time": "2:05:00"}
|
| 174 |
+
{"current_steps": 1740, "total_steps": 3941, "loss": 1.3139, "learning_rate": 6.850832677660134e-06, "epoch": 0.44145629836356715, "percentage": 44.15, "elapsed_time": "1:38:21", "remaining_time": "2:04:24"}
|
| 175 |
+
{"current_steps": 1750, "total_steps": 3941, "loss": 1.3085, "learning_rate": 6.809609551112419e-06, "epoch": 0.4439934035265762, "percentage": 44.4, "elapsed_time": "1:38:54", "remaining_time": "2:03:49"}
|
| 176 |
+
{"current_steps": 1760, "total_steps": 3941, "loss": 1.3158, "learning_rate": 6.768244386638793e-06, "epoch": 0.44653050868958516, "percentage": 44.66, "elapsed_time": "1:39:24", "remaining_time": "2:03:11"}
|
| 177 |
+
{"current_steps": 1770, "total_steps": 3941, "loss": 1.3167, "learning_rate": 6.726740431029243e-06, "epoch": 0.4490676138525942, "percentage": 44.91, "elapsed_time": "1:39:57", "remaining_time": "2:02:35"}
|
| 178 |
+
{"current_steps": 1780, "total_steps": 3941, "loss": 1.3118, "learning_rate": 6.685100941967596e-06, "epoch": 0.4516047190156032, "percentage": 45.17, "elapsed_time": "1:40:29", "remaining_time": "2:01:59"}
|
| 179 |
+
{"current_steps": 1790, "total_steps": 3941, "loss": 1.307, "learning_rate": 6.643329187775827e-06, "epoch": 0.4541418241786122, "percentage": 45.42, "elapsed_time": "1:41:01", "remaining_time": "2:01:23"}
|
| 180 |
+
{"current_steps": 1800, "total_steps": 3941, "loss": 1.3086, "learning_rate": 6.601428447157525e-06, "epoch": 0.4566789293416212, "percentage": 45.67, "elapsed_time": "1:41:31", "remaining_time": "2:00:45"}
|
| 181 |
+
{"current_steps": 1810, "total_steps": 3941, "loss": 1.3025, "learning_rate": 6.559402008940539e-06, "epoch": 0.4592160345046302, "percentage": 45.93, "elapsed_time": "1:42:03", "remaining_time": "2:00:09"}
|
| 182 |
+
{"current_steps": 1820, "total_steps": 3941, "loss": 1.3146, "learning_rate": 6.517253171818844e-06, "epoch": 0.4617531396676392, "percentage": 46.18, "elapsed_time": "1:42:36", "remaining_time": "1:59:34"}
|
| 183 |
+
{"current_steps": 1830, "total_steps": 3941, "loss": 1.307, "learning_rate": 6.474985244093613e-06, "epoch": 0.46429024483064824, "percentage": 46.43, "elapsed_time": "1:43:07", "remaining_time": "1:58:57"}
|
| 184 |
+
{"current_steps": 1840, "total_steps": 3941, "loss": 1.2996, "learning_rate": 6.432601543413552e-06, "epoch": 0.4668273499936572, "percentage": 46.69, "elapsed_time": "1:43:39", "remaining_time": "1:58:21"}
|
| 185 |
+
{"current_steps": 1850, "total_steps": 3941, "loss": 1.3013, "learning_rate": 6.390105396514497e-06, "epoch": 0.46936445515666625, "percentage": 46.94, "elapsed_time": "1:44:11", "remaining_time": "1:57:45"}
|
| 186 |
+
{"current_steps": 1860, "total_steps": 3941, "loss": 1.3086, "learning_rate": 6.347500138958285e-06, "epoch": 0.47190156031967523, "percentage": 47.2, "elapsed_time": "1:44:43", "remaining_time": "1:57:10"}
|
| 187 |
+
{"current_steps": 1870, "total_steps": 3941, "loss": 1.3121, "learning_rate": 6.304789114870953e-06, "epoch": 0.47443866548268426, "percentage": 47.45, "elapsed_time": "1:45:16", "remaining_time": "1:56:35"}
|
| 188 |
+
{"current_steps": 1880, "total_steps": 3941, "loss": 1.3109, "learning_rate": 6.261975676680252e-06, "epoch": 0.47697577064569324, "percentage": 47.7, "elapsed_time": "1:45:49", "remaining_time": "1:56:00"}
|
| 189 |
+
{"current_steps": 1890, "total_steps": 3941, "loss": 1.3057, "learning_rate": 6.219063184852509e-06, "epoch": 0.4795128758087023, "percentage": 47.96, "elapsed_time": "1:46:21", "remaining_time": "1:55:25"}
|
| 190 |
+
{"current_steps": 1900, "total_steps": 3941, "loss": 1.2978, "learning_rate": 6.176055007628859e-06, "epoch": 0.48204998097171126, "percentage": 48.21, "elapsed_time": "1:46:54", "remaining_time": "1:54:50"}
|
| 191 |
+
{"current_steps": 1910, "total_steps": 3941, "loss": 1.2936, "learning_rate": 6.132954520760882e-06, "epoch": 0.4845870861347203, "percentage": 48.46, "elapsed_time": "1:47:26", "remaining_time": "1:54:14"}
|
| 192 |
+
{"current_steps": 1920, "total_steps": 3941, "loss": 1.311, "learning_rate": 6.089765107245616e-06, "epoch": 0.48712419129772927, "percentage": 48.72, "elapsed_time": "1:47:59", "remaining_time": "1:53:40"}
|
| 193 |
+
{"current_steps": 1930, "total_steps": 3941, "loss": 1.2917, "learning_rate": 6.046490157060041e-06, "epoch": 0.4896612964607383, "percentage": 48.97, "elapsed_time": "1:48:31", "remaining_time": "1:53:04"}
|
| 194 |
+
{"current_steps": 1940, "total_steps": 3941, "loss": 1.3173, "learning_rate": 6.003133066894987e-06, "epoch": 0.4921984016237473, "percentage": 49.23, "elapsed_time": "1:49:03", "remaining_time": "1:52:29"}
|
| 195 |
+
{"current_steps": 1950, "total_steps": 3941, "loss": 1.2978, "learning_rate": 5.959697239888525e-06, "epoch": 0.4947355067867563, "percentage": 49.48, "elapsed_time": "1:49:36", "remaining_time": "1:51:54"}
|
| 196 |
+
{"current_steps": 1960, "total_steps": 3941, "loss": 1.3125, "learning_rate": 5.916186085358858e-06, "epoch": 0.4972726119497653, "percentage": 49.73, "elapsed_time": "1:50:08", "remaining_time": "1:51:19"}
|
| 197 |
+
{"current_steps": 1970, "total_steps": 3941, "loss": 1.3035, "learning_rate": 5.872603018536713e-06, "epoch": 0.49980971711277433, "percentage": 49.99, "elapsed_time": "1:50:41", "remaining_time": "1:50:44"}
|
| 198 |
+
{"current_steps": 1980, "total_steps": 3941, "loss": 1.2943, "learning_rate": 5.828951460297277e-06, "epoch": 0.5023468222757833, "percentage": 50.24, "elapsed_time": "1:51:13", "remaining_time": "1:50:09"}
|
| 199 |
+
{"current_steps": 1990, "total_steps": 3941, "loss": 1.3019, "learning_rate": 5.785234836891697e-06, "epoch": 0.5048839274387923, "percentage": 50.49, "elapsed_time": "1:51:45", "remaining_time": "1:49:33"}
|
| 200 |
+
{"current_steps": 2000, "total_steps": 3941, "loss": 1.2929, "learning_rate": 5.741456579678141e-06, "epoch": 0.5074210326018014, "percentage": 50.75, "elapsed_time": "1:52:16", "remaining_time": "1:48:58"}
|
| 201 |
+
{"current_steps": 2010, "total_steps": 3941, "loss": 1.2868, "learning_rate": 5.697620124852472e-06, "epoch": 0.5099581377648104, "percentage": 51.0, "elapsed_time": "1:53:55", "remaining_time": "1:49:27"}
|
| 202 |
+
{"current_steps": 2020, "total_steps": 3941, "loss": 1.2875, "learning_rate": 5.65372891317854e-06, "epoch": 0.5124952429278193, "percentage": 51.26, "elapsed_time": "1:54:27", "remaining_time": "1:48:50"}
|
| 203 |
+
{"current_steps": 2030, "total_steps": 3941, "loss": 1.2963, "learning_rate": 5.6097863897181075e-06, "epoch": 0.5150323480908283, "percentage": 51.51, "elapsed_time": "1:54:59", "remaining_time": "1:48:14"}
|
| 204 |
+
{"current_steps": 2040, "total_steps": 3941, "loss": 1.3121, "learning_rate": 5.565796003560447e-06, "epoch": 0.5175694532538374, "percentage": 51.76, "elapsed_time": "1:55:32", "remaining_time": "1:47:40"}
|
| 205 |
+
{"current_steps": 2050, "total_steps": 3941, "loss": 1.2979, "learning_rate": 5.521761207551622e-06, "epoch": 0.5201065584168464, "percentage": 52.02, "elapsed_time": "1:56:05", "remaining_time": "1:47:05"}
|
| 206 |
+
{"current_steps": 2060, "total_steps": 3941, "loss": 1.3107, "learning_rate": 5.47768545802346e-06, "epoch": 0.5226436635798554, "percentage": 52.27, "elapsed_time": "1:56:38", "remaining_time": "1:46:30"}
|
| 207 |
+
{"current_steps": 2070, "total_steps": 3941, "loss": 1.2952, "learning_rate": 5.433572214522275e-06, "epoch": 0.5251807687428643, "percentage": 52.52, "elapsed_time": "1:57:10", "remaining_time": "1:45:54"}
|
| 208 |
+
{"current_steps": 2080, "total_steps": 3941, "loss": 1.2922, "learning_rate": 5.389424939537311e-06, "epoch": 0.5277178739058734, "percentage": 52.78, "elapsed_time": "1:57:41", "remaining_time": "1:45:18"}
|
| 209 |
+
{"current_steps": 2090, "total_steps": 3941, "loss": 1.2942, "learning_rate": 5.345247098228977e-06, "epoch": 0.5302549790688824, "percentage": 53.03, "elapsed_time": "1:58:14", "remaining_time": "1:44:43"}
|
| 210 |
+
{"current_steps": 2100, "total_steps": 3941, "loss": 1.2898, "learning_rate": 5.301042158156866e-06, "epoch": 0.5327920842318914, "percentage": 53.29, "elapsed_time": "1:58:47", "remaining_time": "1:44:08"}
|
| 211 |
+
{"current_steps": 2110, "total_steps": 3941, "loss": 1.2967, "learning_rate": 5.256813589007571e-06, "epoch": 0.5353291893949004, "percentage": 53.54, "elapsed_time": "1:59:20", "remaining_time": "1:43:34"}
|
| 212 |
+
{"current_steps": 2120, "total_steps": 3941, "loss": 1.2987, "learning_rate": 5.212564862322355e-06, "epoch": 0.5378662945579095, "percentage": 53.79, "elapsed_time": "1:59:52", "remaining_time": "1:42:58"}
|
| 213 |
+
{"current_steps": 2130, "total_steps": 3941, "loss": 1.2859, "learning_rate": 5.168299451224665e-06, "epoch": 0.5404033997209184, "percentage": 54.05, "elapsed_time": "2:00:27", "remaining_time": "1:42:24"}
|
| 214 |
+
{"current_steps": 2140, "total_steps": 3941, "loss": 1.2942, "learning_rate": 5.124020830147525e-06, "epoch": 0.5429405048839274, "percentage": 54.3, "elapsed_time": "2:01:00", "remaining_time": "1:41:50"}
|
| 215 |
+
{"current_steps": 2150, "total_steps": 3941, "loss": 1.2967, "learning_rate": 5.079732474560821e-06, "epoch": 0.5454776100469364, "percentage": 54.55, "elapsed_time": "2:01:31", "remaining_time": "1:41:13"}
|
| 216 |
+
{"current_steps": 2160, "total_steps": 3941, "loss": 1.2792, "learning_rate": 5.035437860698508e-06, "epoch": 0.5480147152099455, "percentage": 54.81, "elapsed_time": "2:02:02", "remaining_time": "1:40:37"}
|
| 217 |
+
{"current_steps": 2170, "total_steps": 3941, "loss": 1.2722, "learning_rate": 4.991140465285762e-06, "epoch": 0.5505518203729545, "percentage": 55.06, "elapsed_time": "2:02:34", "remaining_time": "1:40:02"}
|
| 218 |
+
{"current_steps": 2180, "total_steps": 3941, "loss": 1.294, "learning_rate": 4.94684376526608e-06, "epoch": 0.5530889255359634, "percentage": 55.32, "elapsed_time": "2:03:08", "remaining_time": "1:39:28"}
|
| 219 |
+
{"current_steps": 2190, "total_steps": 3941, "loss": 1.2898, "learning_rate": 4.902551237528387e-06, "epoch": 0.5556260306989724, "percentage": 55.57, "elapsed_time": "2:03:40", "remaining_time": "1:38:52"}
|
| 220 |
+
{"current_steps": 2200, "total_steps": 3941, "loss": 1.2943, "learning_rate": 4.858266358634109e-06, "epoch": 0.5581631358619815, "percentage": 55.82, "elapsed_time": "2:04:14", "remaining_time": "1:38:19"}
|
| 221 |
+
{"current_steps": 2210, "total_steps": 3941, "loss": 1.309, "learning_rate": 4.813992604544319e-06, "epoch": 0.5607002410249905, "percentage": 56.08, "elapsed_time": "2:04:47", "remaining_time": "1:37:44"}
|
| 222 |
+
{"current_steps": 2220, "total_steps": 3941, "loss": 1.2941, "learning_rate": 4.769733450346885e-06, "epoch": 0.5632373461879995, "percentage": 56.33, "elapsed_time": "2:05:20", "remaining_time": "1:37:09"}
|
| 223 |
+
{"current_steps": 2230, "total_steps": 3941, "loss": 1.2808, "learning_rate": 4.725492369983721e-06, "epoch": 0.5657744513510085, "percentage": 56.58, "elapsed_time": "2:05:53", "remaining_time": "1:36:35"}
|
| 224 |
+
{"current_steps": 2240, "total_steps": 3941, "loss": 1.2886, "learning_rate": 4.6812728359781064e-06, "epoch": 0.5683115565140175, "percentage": 56.84, "elapsed_time": "2:06:27", "remaining_time": "1:36:01"}
|
| 225 |
+
{"current_steps": 2250, "total_steps": 3941, "loss": 1.2848, "learning_rate": 4.637078319162127e-06, "epoch": 0.5708486616770265, "percentage": 57.09, "elapsed_time": "2:06:59", "remaining_time": "1:35:26"}
|
| 226 |
+
{"current_steps": 2260, "total_steps": 3941, "loss": 1.2747, "learning_rate": 4.592912288404251e-06, "epoch": 0.5733857668400355, "percentage": 57.35, "elapsed_time": "2:07:31", "remaining_time": "1:34:51"}
|
| 227 |
+
{"current_steps": 2270, "total_steps": 3941, "loss": 1.2889, "learning_rate": 4.5487782103370445e-06, "epoch": 0.5759228720030445, "percentage": 57.6, "elapsed_time": "2:08:08", "remaining_time": "1:34:19"}
|
| 228 |
+
{"current_steps": 2280, "total_steps": 3941, "loss": 1.2956, "learning_rate": 4.504679549085077e-06, "epoch": 0.5784599771660536, "percentage": 57.85, "elapsed_time": "2:08:41", "remaining_time": "1:33:45"}
|
| 229 |
+
{"current_steps": 2290, "total_steps": 3941, "loss": 1.2974, "learning_rate": 4.460619765993025e-06, "epoch": 0.5809970823290626, "percentage": 58.11, "elapsed_time": "2:09:12", "remaining_time": "1:33:09"}
|
| 230 |
+
{"current_steps": 2300, "total_steps": 3941, "loss": 1.29, "learning_rate": 4.416602319353974e-06, "epoch": 0.5835341874920715, "percentage": 58.36, "elapsed_time": "2:09:45", "remaining_time": "1:32:35"}
|
| 231 |
+
{"current_steps": 2310, "total_steps": 3941, "loss": 1.2745, "learning_rate": 4.3726306641379915e-06, "epoch": 0.5860712926550805, "percentage": 58.61, "elapsed_time": "2:10:19", "remaining_time": "1:32:01"}
|
| 232 |
+
{"current_steps": 2320, "total_steps": 3941, "loss": 1.2739, "learning_rate": 4.328708251720924e-06, "epoch": 0.5886083978180896, "percentage": 58.87, "elapsed_time": "2:10:54", "remaining_time": "1:31:28"}
|
| 233 |
+
{"current_steps": 2330, "total_steps": 3941, "loss": 1.3101, "learning_rate": 4.2848385296135165e-06, "epoch": 0.5911455029810986, "percentage": 59.12, "elapsed_time": "2:11:28", "remaining_time": "1:30:54"}
|
| 234 |
+
{"current_steps": 2340, "total_steps": 3941, "loss": 1.2771, "learning_rate": 4.241024941190792e-06, "epoch": 0.5936826081441076, "percentage": 59.38, "elapsed_time": "2:12:01", "remaining_time": "1:30:19"}
|
| 235 |
+
{"current_steps": 2350, "total_steps": 3941, "loss": 1.2877, "learning_rate": 4.197270925421796e-06, "epoch": 0.5962197133071165, "percentage": 59.63, "elapsed_time": "2:12:35", "remaining_time": "1:29:45"}
|
| 236 |
+
{"current_steps": 2360, "total_steps": 3941, "loss": 1.2969, "learning_rate": 4.153579916599659e-06, "epoch": 0.5987568184701256, "percentage": 59.88, "elapsed_time": "2:13:08", "remaining_time": "1:29:11"}
|
| 237 |
+
{"current_steps": 2370, "total_steps": 3941, "loss": 1.2745, "learning_rate": 4.109955344072036e-06, "epoch": 0.6012939236331346, "percentage": 60.14, "elapsed_time": "2:13:39", "remaining_time": "1:28:35"}
|
| 238 |
+
{"current_steps": 2380, "total_steps": 3941, "loss": 1.2714, "learning_rate": 4.066400631971938e-06, "epoch": 0.6038310287961436, "percentage": 60.39, "elapsed_time": "2:14:12", "remaining_time": "1:28:01"}
|
| 239 |
+
{"current_steps": 2390, "total_steps": 3941, "loss": 1.2759, "learning_rate": 4.022919198948966e-06, "epoch": 0.6063681339591526, "percentage": 60.64, "elapsed_time": "2:14:45", "remaining_time": "1:27:26"}
|
| 240 |
+
{"current_steps": 2400, "total_steps": 3941, "loss": 1.2845, "learning_rate": 3.979514457900982e-06, "epoch": 0.6089052391221617, "percentage": 60.9, "elapsed_time": "2:15:16", "remaining_time": "1:26:51"}
|
| 241 |
+
{"current_steps": 2410, "total_steps": 3941, "loss": 1.2833, "learning_rate": 3.936189815706219e-06, "epoch": 0.6114423442851706, "percentage": 61.15, "elapsed_time": "2:15:49", "remaining_time": "1:26:17"}
|
| 242 |
+
{"current_steps": 2420, "total_steps": 3941, "loss": 1.2941, "learning_rate": 3.8929486729558775e-06, "epoch": 0.6139794494481796, "percentage": 61.41, "elapsed_time": "2:16:20", "remaining_time": "1:25:41"}
|
| 243 |
+
{"current_steps": 2430, "total_steps": 3941, "loss": 1.2775, "learning_rate": 3.849794423687212e-06, "epoch": 0.6165165546111886, "percentage": 61.66, "elapsed_time": "2:16:52", "remaining_time": "1:25:06"}
|
| 244 |
+
{"current_steps": 2440, "total_steps": 3941, "loss": 1.2627, "learning_rate": 3.8067304551171247e-06, "epoch": 0.6190536597741977, "percentage": 61.91, "elapsed_time": "2:17:25", "remaining_time": "1:24:32"}
|
| 245 |
+
{"current_steps": 2450, "total_steps": 3941, "loss": 1.284, "learning_rate": 3.7637601473763035e-06, "epoch": 0.6215907649372067, "percentage": 62.17, "elapsed_time": "2:17:57", "remaining_time": "1:23:57"}
|
| 246 |
+
{"current_steps": 2460, "total_steps": 3941, "loss": 1.2927, "learning_rate": 3.7208868732439145e-06, "epoch": 0.6241278701002156, "percentage": 62.42, "elapsed_time": "2:18:29", "remaining_time": "1:23:22"}
|
| 247 |
+
{"current_steps": 2470, "total_steps": 3941, "loss": 1.2947, "learning_rate": 3.6781139978828606e-06, "epoch": 0.6266649752632246, "percentage": 62.67, "elapsed_time": "2:19:02", "remaining_time": "1:22:48"}
|
| 248 |
+
{"current_steps": 2480, "total_steps": 3941, "loss": 1.2843, "learning_rate": 3.6354448785756558e-06, "epoch": 0.6292020804262337, "percentage": 62.93, "elapsed_time": "2:19:35", "remaining_time": "1:22:14"}
|
| 249 |
+
{"current_steps": 2490, "total_steps": 3941, "loss": 1.265, "learning_rate": 3.592882864460905e-06, "epoch": 0.6317391855892427, "percentage": 63.18, "elapsed_time": "2:20:08", "remaining_time": "1:21:39"}
|
| 250 |
+
{"current_steps": 2500, "total_steps": 3941, "loss": 1.2709, "learning_rate": 3.5504312962704245e-06, "epoch": 0.6342762907522517, "percentage": 63.44, "elapsed_time": "2:20:43", "remaining_time": "1:21:06"}
|
| 251 |
+
{"current_steps": 2510, "total_steps": 3941, "loss": 1.2679, "learning_rate": 3.5080935060670345e-06, "epoch": 0.6368133959152606, "percentage": 63.69, "elapsed_time": "2:22:56", "remaining_time": "1:21:29"}
|
| 252 |
+
{"current_steps": 2520, "total_steps": 3941, "loss": 1.2821, "learning_rate": 3.465872816983008e-06, "epoch": 0.6393505010782697, "percentage": 63.94, "elapsed_time": "2:23:29", "remaining_time": "1:20:54"}
|
| 253 |
+
{"current_steps": 2530, "total_steps": 3941, "loss": 1.2865, "learning_rate": 3.4237725429592507e-06, "epoch": 0.6418876062412787, "percentage": 64.2, "elapsed_time": "2:24:03", "remaining_time": "1:20:20"}
|
| 254 |
+
{"current_steps": 2540, "total_steps": 3941, "loss": 1.2698, "learning_rate": 3.3817959884851735e-06, "epoch": 0.6444247114042877, "percentage": 64.45, "elapsed_time": "2:24:37", "remaining_time": "1:19:46"}
|
| 255 |
+
{"current_steps": 2550, "total_steps": 3941, "loss": 1.291, "learning_rate": 3.3399464483393272e-06, "epoch": 0.6469618165672967, "percentage": 64.7, "elapsed_time": "2:25:11", "remaining_time": "1:19:12"}
|
| 256 |
+
{"current_steps": 2560, "total_steps": 3941, "loss": 1.2765, "learning_rate": 3.298227207330792e-06, "epoch": 0.6494989217303058, "percentage": 64.96, "elapsed_time": "2:25:44", "remaining_time": "1:18:37"}
|
| 257 |
+
{"current_steps": 2570, "total_steps": 3941, "loss": 1.2905, "learning_rate": 3.256641540041346e-06, "epoch": 0.6520360268933147, "percentage": 65.21, "elapsed_time": "2:26:15", "remaining_time": "1:18:01"}
|
| 258 |
+
{"current_steps": 2580, "total_steps": 3941, "loss": 1.298, "learning_rate": 3.2151927105684423e-06, "epoch": 0.6545731320563237, "percentage": 65.47, "elapsed_time": "2:26:48", "remaining_time": "1:17:26"}
|
| 259 |
+
{"current_steps": 2590, "total_steps": 3941, "loss": 1.2742, "learning_rate": 3.1738839722690085e-06, "epoch": 0.6571102372193327, "percentage": 65.72, "elapsed_time": "2:27:19", "remaining_time": "1:16:50"}
|
| 260 |
+
{"current_steps": 2600, "total_steps": 3941, "loss": 1.2769, "learning_rate": 3.1327185675040907e-06, "epoch": 0.6596473423823418, "percentage": 65.97, "elapsed_time": "2:27:52", "remaining_time": "1:16:16"}
|
| 261 |
+
{"current_steps": 2610, "total_steps": 3941, "loss": 1.2938, "learning_rate": 3.0916997273843454e-06, "epoch": 0.6621844475453508, "percentage": 66.23, "elapsed_time": "2:28:24", "remaining_time": "1:15:41"}
|
| 262 |
+
{"current_steps": 2620, "total_steps": 3941, "loss": 1.2913, "learning_rate": 3.0508306715164416e-06, "epoch": 0.6647215527083598, "percentage": 66.48, "elapsed_time": "2:28:58", "remaining_time": "1:15:06"}
|
| 263 |
+
{"current_steps": 2630, "total_steps": 3941, "loss": 1.2777, "learning_rate": 3.0101146077503386e-06, "epoch": 0.6672586578713687, "percentage": 66.73, "elapsed_time": "2:29:32", "remaining_time": "1:14:32"}
|
| 264 |
+
{"current_steps": 2640, "total_steps": 3941, "loss": 1.2633, "learning_rate": 2.9695547319275093e-06, "epoch": 0.6697957630343778, "percentage": 66.99, "elapsed_time": "2:30:06", "remaining_time": "1:13:58"}
|
| 265 |
+
{"current_steps": 2650, "total_steps": 3941, "loss": 1.289, "learning_rate": 2.9291542276300866e-06, "epoch": 0.6723328681973868, "percentage": 67.24, "elapsed_time": "2:30:40", "remaining_time": "1:13:24"}
|
| 266 |
+
{"current_steps": 2660, "total_steps": 3941, "loss": 1.2729, "learning_rate": 2.8889162659309832e-06, "epoch": 0.6748699733603958, "percentage": 67.5, "elapsed_time": "2:31:13", "remaining_time": "1:12:49"}
|
| 267 |
+
{"current_steps": 2670, "total_steps": 3941, "loss": 1.3024, "learning_rate": 2.848844005145004e-06, "epoch": 0.6774070785234048, "percentage": 67.75, "elapsed_time": "2:31:47", "remaining_time": "1:12:15"}
|
| 268 |
+
{"current_steps": 2680, "total_steps": 3941, "loss": 1.2845, "learning_rate": 2.808940590580922e-06, "epoch": 0.6799441836864138, "percentage": 68.0, "elapsed_time": "2:32:21", "remaining_time": "1:11:41"}
|
| 269 |
+
{"current_steps": 2690, "total_steps": 3941, "loss": 1.2844, "learning_rate": 2.769209154294623e-06, "epoch": 0.6824812888494228, "percentage": 68.26, "elapsed_time": "2:32:53", "remaining_time": "1:11:06"}
|
| 270 |
+
{"current_steps": 2700, "total_steps": 3941, "loss": 1.2683, "learning_rate": 2.7296528148432565e-06, "epoch": 0.6850183940124318, "percentage": 68.51, "elapsed_time": "2:33:26", "remaining_time": "1:10:31"}
|
| 271 |
+
{"current_steps": 2710, "total_steps": 3941, "loss": 1.2776, "learning_rate": 2.690274677040462e-06, "epoch": 0.6875554991754408, "percentage": 68.76, "elapsed_time": "2:33:59", "remaining_time": "1:09:56"}
|
| 272 |
+
{"current_steps": 2720, "total_steps": 3941, "loss": 1.2807, "learning_rate": 2.6510778317126597e-06, "epoch": 0.6900926043384499, "percentage": 69.02, "elapsed_time": "2:34:31", "remaining_time": "1:09:21"}
|
| 273 |
+
{"current_steps": 2730, "total_steps": 3941, "loss": 1.2777, "learning_rate": 2.6120653554564624e-06, "epoch": 0.6926297095014589, "percentage": 69.27, "elapsed_time": "2:35:04", "remaining_time": "1:08:47"}
|
| 274 |
+
{"current_steps": 2740, "total_steps": 3941, "loss": 1.2736, "learning_rate": 2.573240310397187e-06, "epoch": 0.6951668146644678, "percentage": 69.53, "elapsed_time": "2:35:38", "remaining_time": "1:08:13"}
|
| 275 |
+
{"current_steps": 2750, "total_steps": 3941, "loss": 1.2803, "learning_rate": 2.5346057439484923e-06, "epoch": 0.6977039198274768, "percentage": 69.78, "elapsed_time": "2:36:10", "remaining_time": "1:07:38"}
|
| 276 |
+
{"current_steps": 2760, "total_steps": 3941, "loss": 1.2744, "learning_rate": 2.4961646885732034e-06, "epoch": 0.7002410249904859, "percentage": 70.03, "elapsed_time": "2:36:42", "remaining_time": "1:07:03"}
|
| 277 |
+
{"current_steps": 2770, "total_steps": 3941, "loss": 1.2842, "learning_rate": 2.4579201615452812e-06, "epoch": 0.7027781301534949, "percentage": 70.29, "elapsed_time": "2:37:14", "remaining_time": "1:06:28"}
|
| 278 |
+
{"current_steps": 2780, "total_steps": 3941, "loss": 1.2963, "learning_rate": 2.4198751647129896e-06, "epoch": 0.7053152353165039, "percentage": 70.54, "elapsed_time": "2:37:47", "remaining_time": "1:05:53"}
|
| 279 |
+
{"current_steps": 2790, "total_steps": 3941, "loss": 1.2637, "learning_rate": 2.3820326842632894e-06, "epoch": 0.7078523404795128, "percentage": 70.79, "elapsed_time": "2:38:21", "remaining_time": "1:05:19"}
|
| 280 |
+
{"current_steps": 2800, "total_steps": 3941, "loss": 1.2856, "learning_rate": 2.344395690487441e-06, "epoch": 0.7103894456425219, "percentage": 71.05, "elapsed_time": "2:38:54", "remaining_time": "1:04:45"}
|
| 281 |
+
{"current_steps": 2810, "total_steps": 3941, "loss": 1.2848, "learning_rate": 2.3069671375478645e-06, "epoch": 0.7129265508055309, "percentage": 71.3, "elapsed_time": "2:39:27", "remaining_time": "1:04:10"}
|
| 282 |
+
{"current_steps": 2820, "total_steps": 3941, "loss": 1.2536, "learning_rate": 2.2697499632462695e-06, "epoch": 0.7154636559685399, "percentage": 71.56, "elapsed_time": "2:39:59", "remaining_time": "1:03:36"}
|
| 283 |
+
{"current_steps": 2830, "total_steps": 3941, "loss": 1.3015, "learning_rate": 2.2327470887930595e-06, "epoch": 0.7180007611315489, "percentage": 71.81, "elapsed_time": "2:40:32", "remaining_time": "1:03:01"}
|
| 284 |
+
{"current_steps": 2840, "total_steps": 3941, "loss": 1.2744, "learning_rate": 2.195961418578041e-06, "epoch": 0.720537866294558, "percentage": 72.06, "elapsed_time": "2:41:04", "remaining_time": "1:02:26"}
|
| 285 |
+
{"current_steps": 2850, "total_steps": 3941, "loss": 1.2664, "learning_rate": 2.159395839942464e-06, "epoch": 0.7230749714575669, "percentage": 72.32, "elapsed_time": "2:41:38", "remaining_time": "1:01:52"}
|
| 286 |
+
{"current_steps": 2860, "total_steps": 3941, "loss": 1.2489, "learning_rate": 2.1230532229523865e-06, "epoch": 0.7256120766205759, "percentage": 72.57, "elapsed_time": "2:42:09", "remaining_time": "1:01:17"}
|
| 287 |
+
{"current_steps": 2870, "total_steps": 3941, "loss": 1.2719, "learning_rate": 2.086936420173399e-06, "epoch": 0.7281491817835849, "percentage": 72.82, "elapsed_time": "2:42:42", "remaining_time": "1:00:42"}
|
| 288 |
+
{"current_steps": 2880, "total_steps": 3941, "loss": 1.2652, "learning_rate": 2.051048266446727e-06, "epoch": 0.730686286946594, "percentage": 73.08, "elapsed_time": "2:43:14", "remaining_time": "1:00:08"}
|
| 289 |
+
{"current_steps": 2890, "total_steps": 3941, "loss": 1.26, "learning_rate": 2.0153915786667203e-06, "epoch": 0.733223392109603, "percentage": 73.33, "elapsed_time": "2:43:46", "remaining_time": "0:59:33"}
|
| 290 |
+
{"current_steps": 2900, "total_steps": 3941, "loss": 1.2881, "learning_rate": 1.9799691555597555e-06, "epoch": 0.735760497272612, "percentage": 73.59, "elapsed_time": "2:44:20", "remaining_time": "0:58:59"}
|
| 291 |
+
{"current_steps": 2910, "total_steps": 3941, "loss": 1.2702, "learning_rate": 1.9447837774645513e-06, "epoch": 0.7382976024356209, "percentage": 73.84, "elapsed_time": "2:44:51", "remaining_time": "0:58:24"}
|
| 292 |
+
{"current_steps": 2920, "total_steps": 3941, "loss": 1.2699, "learning_rate": 1.9098382061139503e-06, "epoch": 0.74083470759863, "percentage": 74.09, "elapsed_time": "2:45:24", "remaining_time": "0:57:50"}
|
| 293 |
+
{"current_steps": 2930, "total_steps": 3941, "loss": 1.2612, "learning_rate": 1.8751351844181414e-06, "epoch": 0.743371812761639, "percentage": 74.35, "elapsed_time": "2:45:55", "remaining_time": "0:57:15"}
|
| 294 |
+
{"current_steps": 2940, "total_steps": 3941, "loss": 1.2754, "learning_rate": 1.8406774362493662e-06, "epoch": 0.745908917924648, "percentage": 74.6, "elapsed_time": "2:46:26", "remaining_time": "0:56:40"}
|
| 295 |
+
{"current_steps": 2950, "total_steps": 3941, "loss": 1.2902, "learning_rate": 1.8064676662281206e-06, "epoch": 0.748446023087657, "percentage": 74.85, "elapsed_time": "2:46:59", "remaining_time": "0:56:05"}
|
| 296 |
+
{"current_steps": 2960, "total_steps": 3941, "loss": 1.273, "learning_rate": 1.7725085595108682e-06, "epoch": 0.750983128250666, "percentage": 75.11, "elapsed_time": "2:47:32", "remaining_time": "0:55:31"}
|
| 297 |
+
{"current_steps": 2970, "total_steps": 3941, "loss": 1.2787, "learning_rate": 1.7388027815792725e-06, "epoch": 0.753520233413675, "percentage": 75.36, "elapsed_time": "2:48:07", "remaining_time": "0:54:57"}
|
| 298 |
+
{"current_steps": 2980, "total_steps": 3941, "loss": 1.2627, "learning_rate": 1.705352978030993e-06, "epoch": 0.756057338576684, "percentage": 75.62, "elapsed_time": "2:48:39", "remaining_time": "0:54:23"}
|
| 299 |
+
{"current_steps": 2990, "total_steps": 3941, "loss": 1.2911, "learning_rate": 1.672161774372022e-06, "epoch": 0.758594443739693, "percentage": 75.87, "elapsed_time": "2:49:12", "remaining_time": "0:53:49"}
|
| 300 |
+
{"current_steps": 3000, "total_steps": 3941, "loss": 1.2907, "learning_rate": 1.639231775810602e-06, "epoch": 0.7611315489027021, "percentage": 76.12, "elapsed_time": "2:49:44", "remaining_time": "0:53:14"}
|
| 301 |
+
{"current_steps": 3010, "total_steps": 3941, "loss": 1.2632, "learning_rate": 1.6065655670527546e-06, "epoch": 0.763668654065711, "percentage": 76.38, "elapsed_time": "2:51:21", "remaining_time": "0:53:00"}
|
| 302 |
+
{"current_steps": 3020, "total_steps": 3941, "loss": 1.2542, "learning_rate": 1.574165712099392e-06, "epoch": 0.76620575922872, "percentage": 76.63, "elapsed_time": "2:51:54", "remaining_time": "0:52:25"}
|
| 303 |
+
{"current_steps": 3030, "total_steps": 3941, "loss": 1.2693, "learning_rate": 1.542034754045067e-06, "epoch": 0.768742864391729, "percentage": 76.88, "elapsed_time": "2:52:24", "remaining_time": "0:51:50"}
|
| 304 |
+
{"current_steps": 3040, "total_steps": 3941, "loss": 1.2728, "learning_rate": 1.5101752148783705e-06, "epoch": 0.7712799695547381, "percentage": 77.14, "elapsed_time": "2:52:57", "remaining_time": "0:51:15"}
|
| 305 |
+
{"current_steps": 3050, "total_steps": 3941, "loss": 1.2671, "learning_rate": 1.4785895952839735e-06, "epoch": 0.7738170747177471, "percentage": 77.39, "elapsed_time": "2:53:29", "remaining_time": "0:50:41"}
|
| 306 |
+
{"current_steps": 3060, "total_steps": 3941, "loss": 1.2778, "learning_rate": 1.447280374446346e-06, "epoch": 0.7763541798807561, "percentage": 77.65, "elapsed_time": "2:54:02", "remaining_time": "0:50:06"}
|
| 307 |
+
{"current_steps": 3070, "total_steps": 3941, "loss": 1.276, "learning_rate": 1.4162500098551608e-06, "epoch": 0.778891285043765, "percentage": 77.9, "elapsed_time": "2:54:35", "remaining_time": "0:49:31"}
|
| 308 |
+
{"current_steps": 3080, "total_steps": 3941, "loss": 1.2804, "learning_rate": 1.385500937112415e-06, "epoch": 0.7814283902067741, "percentage": 78.15, "elapsed_time": "2:55:07", "remaining_time": "0:48:57"}
|
| 309 |
+
{"current_steps": 3090, "total_steps": 3941, "loss": 1.2586, "learning_rate": 1.3550355697412386e-06, "epoch": 0.7839654953697831, "percentage": 78.41, "elapsed_time": "2:55:39", "remaining_time": "0:48:22"}
|
| 310 |
+
{"current_steps": 3100, "total_steps": 3941, "loss": 1.2843, "learning_rate": 1.3248562989964719e-06, "epoch": 0.7865026005327921, "percentage": 78.66, "elapsed_time": "2:56:12", "remaining_time": "0:47:48"}
|
| 311 |
+
{"current_steps": 3110, "total_steps": 3941, "loss": 1.2723, "learning_rate": 1.2949654936769622e-06, "epoch": 0.7890397056958011, "percentage": 78.91, "elapsed_time": "2:56:44", "remaining_time": "0:47:13"}
|
| 312 |
+
{"current_steps": 3120, "total_steps": 3941, "loss": 1.2621, "learning_rate": 1.2653654999396436e-06, "epoch": 0.79157681085881, "percentage": 79.17, "elapsed_time": "2:57:15", "remaining_time": "0:46:38"}
|
| 313 |
+
{"current_steps": 3130, "total_steps": 3941, "loss": 1.2897, "learning_rate": 1.2360586411153747e-06, "epoch": 0.7941139160218191, "percentage": 79.42, "elapsed_time": "2:57:46", "remaining_time": "0:46:03"}
|
| 314 |
+
{"current_steps": 3140, "total_steps": 3941, "loss": 1.2657, "learning_rate": 1.2070472175265857e-06, "epoch": 0.7966510211848281, "percentage": 79.68, "elapsed_time": "2:58:19", "remaining_time": "0:45:29"}
|
| 315 |
+
{"current_steps": 3150, "total_steps": 3941, "loss": 1.2974, "learning_rate": 1.1783335063067286e-06, "epoch": 0.7991881263478371, "percentage": 79.93, "elapsed_time": "2:58:51", "remaining_time": "0:44:54"}
|
| 316 |
+
{"current_steps": 3160, "total_steps": 3941, "loss": 1.2914, "learning_rate": 1.1499197612215269e-06, "epoch": 0.8017252315108461, "percentage": 80.18, "elapsed_time": "2:59:23", "remaining_time": "0:44:20"}
|
| 317 |
+
{"current_steps": 3170, "total_steps": 3941, "loss": 1.2583, "learning_rate": 1.1218082124920903e-06, "epoch": 0.8042623366738552, "percentage": 80.44, "elapsed_time": "2:59:55", "remaining_time": "0:43:45"}
|
| 318 |
+
{"current_steps": 3180, "total_steps": 3941, "loss": 1.2588, "learning_rate": 1.0940010666198575e-06, "epoch": 0.8067994418368641, "percentage": 80.69, "elapsed_time": "3:00:27", "remaining_time": "0:43:11"}
|
| 319 |
+
{"current_steps": 3190, "total_steps": 3941, "loss": 1.2641, "learning_rate": 1.0665005062134015e-06, "epoch": 0.8093365469998731, "percentage": 80.94, "elapsed_time": "3:01:01", "remaining_time": "0:42:36"}
|
| 320 |
+
{"current_steps": 3200, "total_steps": 3941, "loss": 1.2623, "learning_rate": 1.0393086898171234e-06, "epoch": 0.8118736521628821, "percentage": 81.2, "elapsed_time": "3:01:35", "remaining_time": "0:42:02"}
|
| 321 |
+
{"current_steps": 3210, "total_steps": 3941, "loss": 1.2701, "learning_rate": 1.0124277517418196e-06, "epoch": 0.8144107573258912, "percentage": 81.45, "elapsed_time": "3:02:06", "remaining_time": "0:41:28"}
|
| 322 |
+
{"current_steps": 3220, "total_steps": 3941, "loss": 1.2665, "learning_rate": 9.858598018971599e-07, "epoch": 0.8169478624889002, "percentage": 81.71, "elapsed_time": "3:02:38", "remaining_time": "0:40:53"}
|
| 323 |
+
{"current_steps": 3230, "total_steps": 3941, "loss": 1.2811, "learning_rate": 9.596069256260792e-07, "epoch": 0.8194849676519091, "percentage": 81.96, "elapsed_time": "3:03:10", "remaining_time": "0:40:19"}
|
| 324 |
+
{"current_steps": 3240, "total_steps": 3941, "loss": 1.2577, "learning_rate": 9.336711835410972e-07, "epoch": 0.8220220728149181, "percentage": 82.21, "elapsed_time": "3:03:43", "remaining_time": "0:39:45"}
|
| 325 |
+
{"current_steps": 3250, "total_steps": 3941, "loss": 1.2675, "learning_rate": 9.080546113625738e-07, "epoch": 0.8245591779779272, "percentage": 82.47, "elapsed_time": "3:04:19", "remaining_time": "0:39:11"}
|
| 326 |
+
{"current_steps": 3260, "total_steps": 3941, "loss": 1.2573, "learning_rate": 8.827592197589341e-07, "epoch": 0.8270962831409362, "percentage": 82.72, "elapsed_time": "3:04:53", "remaining_time": "0:38:37"}
|
| 327 |
+
{"current_steps": 3270, "total_steps": 3941, "loss": 1.2654, "learning_rate": 8.577869941888389e-07, "epoch": 0.8296333883039452, "percentage": 82.97, "elapsed_time": "3:05:24", "remaining_time": "0:38:02"}
|
| 328 |
+
{"current_steps": 3280, "total_steps": 3941, "loss": 1.271, "learning_rate": 8.331398947453512e-07, "epoch": 0.8321704934669542, "percentage": 83.23, "elapsed_time": "3:05:57", "remaining_time": "0:37:28"}
|
| 329 |
+
{"current_steps": 3290, "total_steps": 3941, "loss": 1.2771, "learning_rate": 8.08819856002081e-07, "epoch": 0.8347075986299632, "percentage": 83.48, "elapsed_time": "3:06:30", "remaining_time": "0:36:54"}
|
| 330 |
+
{"current_steps": 3300, "total_steps": 3941, "loss": 1.2511, "learning_rate": 7.848287868613441e-07, "epoch": 0.8372447037929722, "percentage": 83.74, "elapsed_time": "3:07:03", "remaining_time": "0:36:20"}
|
| 331 |
+
{"current_steps": 3310, "total_steps": 3941, "loss": 1.2724, "learning_rate": 7.611685704043281e-07, "epoch": 0.8397818089559812, "percentage": 83.99, "elapsed_time": "3:07:37", "remaining_time": "0:35:45"}
|
| 332 |
+
{"current_steps": 3320, "total_steps": 3941, "loss": 1.2761, "learning_rate": 7.378410637432848e-07, "epoch": 0.8423189141189902, "percentage": 84.24, "elapsed_time": "3:08:07", "remaining_time": "0:35:11"}
|
| 333 |
+
{"current_steps": 3330, "total_steps": 3941, "loss": 1.2808, "learning_rate": 7.148480978757694e-07, "epoch": 0.8448560192819993, "percentage": 84.5, "elapsed_time": "3:08:40", "remaining_time": "0:34:37"}
|
| 334 |
+
{"current_steps": 3340, "total_steps": 3941, "loss": 1.2764, "learning_rate": 6.921914775409211e-07, "epoch": 0.8473931244450083, "percentage": 84.75, "elapsed_time": "3:09:12", "remaining_time": "0:34:02"}
|
| 335 |
+
{"current_steps": 3350, "total_steps": 3941, "loss": 1.2724, "learning_rate": 6.698729810778065e-07, "epoch": 0.8499302296080172, "percentage": 85.0, "elapsed_time": "3:09:45", "remaining_time": "0:33:28"}
|
| 336 |
+
{"current_steps": 3360, "total_steps": 3941, "loss": 1.2703, "learning_rate": 6.478943602858373e-07, "epoch": 0.8524673347710262, "percentage": 85.26, "elapsed_time": "3:10:17", "remaining_time": "0:32:54"}
|
| 337 |
+
{"current_steps": 3370, "total_steps": 3941, "loss": 1.2702, "learning_rate": 6.262573402872707e-07, "epoch": 0.8550044399340353, "percentage": 85.51, "elapsed_time": "3:10:50", "remaining_time": "0:32:20"}
|
| 338 |
+
{"current_steps": 3380, "total_steps": 3941, "loss": 1.2652, "learning_rate": 6.04963619391799e-07, "epoch": 0.8575415450970443, "percentage": 85.77, "elapsed_time": "3:11:23", "remaining_time": "0:31:45"}
|
| 339 |
+
{"current_steps": 3390, "total_steps": 3941, "loss": 1.2628, "learning_rate": 5.840148689632536e-07, "epoch": 0.8600786502600533, "percentage": 86.02, "elapsed_time": "3:11:56", "remaining_time": "0:31:11"}
|
| 340 |
+
{"current_steps": 3400, "total_steps": 3941, "loss": 1.2649, "learning_rate": 5.634127332884143e-07, "epoch": 0.8626157554230622, "percentage": 86.27, "elapsed_time": "3:12:29", "remaining_time": "0:30:37"}
|
| 341 |
+
{"current_steps": 3410, "total_steps": 3941, "loss": 1.2863, "learning_rate": 5.431588294479479e-07, "epoch": 0.8651528605860713, "percentage": 86.53, "elapsed_time": "3:13:00", "remaining_time": "0:30:03"}
|
| 342 |
+
{"current_steps": 3420, "total_steps": 3941, "loss": 1.2603, "learning_rate": 5.232547471894839e-07, "epoch": 0.8676899657490803, "percentage": 86.78, "elapsed_time": "3:13:33", "remaining_time": "0:29:29"}
|
| 343 |
+
{"current_steps": 3430, "total_steps": 3941, "loss": 1.2659, "learning_rate": 5.037020488028322e-07, "epoch": 0.8702270709120893, "percentage": 87.03, "elapsed_time": "3:14:06", "remaining_time": "0:28:55"}
|
| 344 |
+
{"current_steps": 3440, "total_steps": 3941, "loss": 1.2622, "learning_rate": 4.845022689973567e-07, "epoch": 0.8727641760750983, "percentage": 87.29, "elapsed_time": "3:14:39", "remaining_time": "0:28:21"}
|
| 345 |
+
{"current_steps": 3450, "total_steps": 3941, "loss": 1.2675, "learning_rate": 4.656569147815171e-07, "epoch": 0.8753012812381074, "percentage": 87.54, "elapsed_time": "3:15:11", "remaining_time": "0:27:46"}
|
| 346 |
+
{"current_steps": 3460, "total_steps": 3941, "loss": 1.2657, "learning_rate": 4.471674653445801e-07, "epoch": 0.8778383864011163, "percentage": 87.79, "elapsed_time": "3:15:44", "remaining_time": "0:27:12"}
|
| 347 |
+
{"current_steps": 3470, "total_steps": 3941, "loss": 1.2622, "learning_rate": 4.290353719405199e-07, "epoch": 0.8803754915641253, "percentage": 88.05, "elapsed_time": "3:16:16", "remaining_time": "0:26:38"}
|
| 348 |
+
{"current_steps": 3480, "total_steps": 3941, "loss": 1.2658, "learning_rate": 4.1126205777410054e-07, "epoch": 0.8829125967271343, "percentage": 88.3, "elapsed_time": "3:16:47", "remaining_time": "0:26:04"}
|
| 349 |
+
{"current_steps": 3490, "total_steps": 3941, "loss": 1.26, "learning_rate": 3.938489178891769e-07, "epoch": 0.8854497018901434, "percentage": 88.56, "elapsed_time": "3:17:19", "remaining_time": "0:25:29"}
|
| 350 |
+
{"current_steps": 3500, "total_steps": 3941, "loss": 1.252, "learning_rate": 3.767973190591906e-07, "epoch": 0.8879868070531524, "percentage": 88.81, "elapsed_time": "3:17:52", "remaining_time": "0:24:55"}
|
| 351 |
+
{"current_steps": 3510, "total_steps": 3941, "loss": 1.2684, "learning_rate": 3.6010859967988975e-07, "epoch": 0.8905239122161613, "percentage": 89.06, "elapsed_time": "3:19:31", "remaining_time": "0:24:30"}
|
| 352 |
+
{"current_steps": 3520, "total_steps": 3941, "loss": 1.28, "learning_rate": 3.437840696642797e-07, "epoch": 0.8930610173791703, "percentage": 89.32, "elapsed_time": "3:20:02", "remaining_time": "0:23:55"}
|
| 353 |
+
{"current_steps": 3530, "total_steps": 3941, "loss": 1.2596, "learning_rate": 3.2782501033980897e-07, "epoch": 0.8955981225421794, "percentage": 89.57, "elapsed_time": "3:20:34", "remaining_time": "0:23:21"}
|
| 354 |
+
{"current_steps": 3540, "total_steps": 3941, "loss": 1.2548, "learning_rate": 3.1223267434778934e-07, "epoch": 0.8981352277051884, "percentage": 89.82, "elapsed_time": "3:21:06", "remaining_time": "0:22:46"}
|
| 355 |
+
{"current_steps": 3550, "total_steps": 3941, "loss": 1.2714, "learning_rate": 2.9700828554508175e-07, "epoch": 0.9006723328681974, "percentage": 90.08, "elapsed_time": "3:21:40", "remaining_time": "0:22:12"}
|
| 356 |
+
{"current_steps": 3560, "total_steps": 3941, "loss": 1.271, "learning_rate": 2.82153038908034e-07, "epoch": 0.9032094380312063, "percentage": 90.33, "elapsed_time": "3:22:10", "remaining_time": "0:21:38"}
|
| 357 |
+
{"current_steps": 3570, "total_steps": 3941, "loss": 1.2636, "learning_rate": 2.6766810043867996e-07, "epoch": 0.9057465431942154, "percentage": 90.59, "elapsed_time": "3:22:43", "remaining_time": "0:21:04"}
|
| 358 |
+
{"current_steps": 3580, "total_steps": 3941, "loss": 1.2555, "learning_rate": 2.53554607073227e-07, "epoch": 0.9082836483572244, "percentage": 90.84, "elapsed_time": "3:23:15", "remaining_time": "0:20:29"}
|
| 359 |
+
{"current_steps": 3590, "total_steps": 3941, "loss": 1.2741, "learning_rate": 2.3981366659281135e-07, "epoch": 0.9108207535202334, "percentage": 91.09, "elapsed_time": "3:23:48", "remaining_time": "0:19:55"}
|
| 360 |
+
{"current_steps": 3600, "total_steps": 3941, "loss": 1.2641, "learning_rate": 2.2644635753654832e-07, "epoch": 0.9133578586832424, "percentage": 91.35, "elapsed_time": "3:24:20", "remaining_time": "0:19:21"}
|
| 361 |
+
{"current_steps": 3610, "total_steps": 3941, "loss": 1.2719, "learning_rate": 2.1345372911687868e-07, "epoch": 0.9158949638462515, "percentage": 91.6, "elapsed_time": "3:24:53", "remaining_time": "0:18:47"}
|
| 362 |
+
{"current_steps": 3620, "total_steps": 3941, "loss": 1.2574, "learning_rate": 2.008368011372136e-07, "epoch": 0.9184320690092604, "percentage": 91.85, "elapsed_time": "3:25:26", "remaining_time": "0:18:13"}
|
| 363 |
+
{"current_steps": 3630, "total_steps": 3941, "loss": 1.2678, "learning_rate": 1.8859656391188918e-07, "epoch": 0.9209691741722694, "percentage": 92.11, "elapsed_time": "3:25:57", "remaining_time": "0:17:38"}
|
| 364 |
+
{"current_steps": 3640, "total_steps": 3941, "loss": 1.2631, "learning_rate": 1.7673397818843696e-07, "epoch": 0.9235062793352784, "percentage": 92.36, "elapsed_time": "3:26:30", "remaining_time": "0:17:04"}
|
| 365 |
+
{"current_steps": 3650, "total_steps": 3941, "loss": 1.2676, "learning_rate": 1.65249975072172e-07, "epoch": 0.9260433844982875, "percentage": 92.62, "elapsed_time": "3:27:04", "remaining_time": "0:16:30"}
|
| 366 |
+
{"current_steps": 3660, "total_steps": 3941, "loss": 1.2363, "learning_rate": 1.5414545595311193e-07, "epoch": 0.9285804896612965, "percentage": 92.87, "elapsed_time": "3:27:37", "remaining_time": "0:15:56"}
|
| 367 |
+
{"current_steps": 3670, "total_steps": 3941, "loss": 1.2716, "learning_rate": 1.4342129243522241e-07, "epoch": 0.9311175948243055, "percentage": 93.12, "elapsed_time": "3:28:11", "remaining_time": "0:15:22"}
|
| 368 |
+
{"current_steps": 3680, "total_steps": 3941, "loss": 1.2674, "learning_rate": 1.3307832626800966e-07, "epoch": 0.9336546999873144, "percentage": 93.38, "elapsed_time": "3:28:43", "remaining_time": "0:14:48"}
|
| 369 |
+
{"current_steps": 3690, "total_steps": 3941, "loss": 1.2662, "learning_rate": 1.2311736928044437e-07, "epoch": 0.9361918051503235, "percentage": 93.63, "elapsed_time": "3:29:16", "remaining_time": "0:14:14"}
|
| 370 |
+
{"current_steps": 3700, "total_steps": 3941, "loss": 1.2743, "learning_rate": 1.1353920331724666e-07, "epoch": 0.9387289103133325, "percentage": 93.88, "elapsed_time": "3:29:49", "remaining_time": "0:13:39"}
|
| 371 |
+
{"current_steps": 3710, "total_steps": 3941, "loss": 1.2505, "learning_rate": 1.0434458017751392e-07, "epoch": 0.9412660154763415, "percentage": 94.14, "elapsed_time": "3:30:21", "remaining_time": "0:13:05"}
|
| 372 |
+
{"current_steps": 3720, "total_steps": 3941, "loss": 1.2637, "learning_rate": 9.553422155571257e-08, "epoch": 0.9438031206393505, "percentage": 94.39, "elapsed_time": "3:30:54", "remaining_time": "0:12:31"}
|
| 373 |
+
{"current_steps": 3730, "total_steps": 3941, "loss": 1.2706, "learning_rate": 8.710881898503276e-08, "epoch": 0.9463402258023595, "percentage": 94.65, "elapsed_time": "3:31:27", "remaining_time": "0:11:57"}
|
| 374 |
+
{"current_steps": 3740, "total_steps": 3941, "loss": 1.2717, "learning_rate": 7.906903378310738e-08, "epoch": 0.9488773309653685, "percentage": 94.9, "elapsed_time": "3:32:01", "remaining_time": "0:11:23"}
|
| 375 |
+
{"current_steps": 3750, "total_steps": 3941, "loss": 1.2764, "learning_rate": 7.141549700010741e-08, "epoch": 0.9514144361283775, "percentage": 95.15, "elapsed_time": "3:32:34", "remaining_time": "0:10:49"}
|
| 376 |
+
{"current_steps": 3760, "total_steps": 3941, "loss": 1.2454, "learning_rate": 6.414880936920665e-08, "epoch": 0.9539515412913865, "percentage": 95.41, "elapsed_time": "3:33:08", "remaining_time": "0:10:15"}
|
| 377 |
+
{"current_steps": 3770, "total_steps": 3941, "loss": 1.2747, "learning_rate": 5.726954125943318e-08, "epoch": 0.9564886464543956, "percentage": 95.66, "elapsed_time": "3:33:39", "remaining_time": "0:09:41"}
|
| 378 |
+
{"current_steps": 3780, "total_steps": 3941, "loss": 1.2717, "learning_rate": 5.0778232630897536e-08, "epoch": 0.9590257516174046, "percentage": 95.91, "elapsed_time": "3:34:10", "remaining_time": "0:09:07"}
|
| 379 |
+
{"current_steps": 3790, "total_steps": 3941, "loss": 1.2728, "learning_rate": 4.4675392992412634e-08, "epoch": 0.9615628567804135, "percentage": 96.17, "elapsed_time": "3:34:43", "remaining_time": "0:08:33"}
|
| 380 |
+
{"current_steps": 3800, "total_steps": 3941, "loss": 1.2826, "learning_rate": 3.896150136150134e-08, "epoch": 0.9640999619434225, "percentage": 96.42, "elapsed_time": "3:35:14", "remaining_time": "0:07:59"}
|
| 381 |
+
{"current_steps": 3810, "total_steps": 3941, "loss": 1.2534, "learning_rate": 3.3637006226797665e-08, "epoch": 0.9666370671064316, "percentage": 96.68, "elapsed_time": "3:35:49", "remaining_time": "0:07:25"}
|
| 382 |
+
{"current_steps": 3820, "total_steps": 3941, "loss": 1.2609, "learning_rate": 2.8702325512844908e-08, "epoch": 0.9691741722694406, "percentage": 96.93, "elapsed_time": "3:36:25", "remaining_time": "0:06:51"}
|
| 383 |
+
{"current_steps": 3830, "total_steps": 3941, "loss": 1.2787, "learning_rate": 2.4157846547292473e-08, "epoch": 0.9717112774324496, "percentage": 97.18, "elapsed_time": "3:36:58", "remaining_time": "0:06:17"}
|
| 384 |
+
{"current_steps": 3840, "total_steps": 3941, "loss": 1.2665, "learning_rate": 2.000392603049517e-08, "epoch": 0.9742483825954585, "percentage": 97.44, "elapsed_time": "3:37:31", "remaining_time": "0:05:43"}
|
| 385 |
+
{"current_steps": 3850, "total_steps": 3941, "loss": 1.2785, "learning_rate": 1.6240890007510612e-08, "epoch": 0.9767854877584676, "percentage": 97.69, "elapsed_time": "3:38:04", "remaining_time": "0:05:09"}
|
| 386 |
+
{"current_steps": 3860, "total_steps": 3941, "loss": 1.2539, "learning_rate": 1.286903384251581e-08, "epoch": 0.9793225929214766, "percentage": 97.94, "elapsed_time": "3:38:35", "remaining_time": "0:04:35"}
|
| 387 |
+
{"current_steps": 3870, "total_steps": 3941, "loss": 1.2725, "learning_rate": 9.888622195615705e-09, "epoch": 0.9818596980844856, "percentage": 98.2, "elapsed_time": "3:39:08", "remaining_time": "0:04:01"}
|
| 388 |
+
{"current_steps": 3880, "total_steps": 3941, "loss": 1.2726, "learning_rate": 7.299889002075344e-09, "epoch": 0.9843968032474946, "percentage": 98.45, "elapsed_time": "3:39:41", "remaining_time": "0:03:27"}
|
| 389 |
+
{"current_steps": 3890, "total_steps": 3941, "loss": 1.2548, "learning_rate": 5.103037453954573e-09, "epoch": 0.9869339084105037, "percentage": 98.71, "elapsed_time": "3:40:13", "remaining_time": "0:02:53"}
|
| 390 |
+
{"current_steps": 3900, "total_steps": 3941, "loss": 1.2859, "learning_rate": 3.2982399841618996e-09, "epoch": 0.9894710135735126, "percentage": 98.96, "elapsed_time": "3:40:44", "remaining_time": "0:02:19"}
|
| 391 |
+
{"current_steps": 3910, "total_steps": 3941, "loss": 1.2842, "learning_rate": 1.8856382529192085e-09, "epoch": 0.9920081187365216, "percentage": 99.21, "elapsed_time": "3:41:17", "remaining_time": "0:01:45"}
|
| 392 |
+
{"current_steps": 3920, "total_steps": 3941, "loss": 1.2447, "learning_rate": 8.653431366406617e-10, "epoch": 0.9945452238995306, "percentage": 99.47, "elapsed_time": "3:41:50", "remaining_time": "0:01:11"}
|
| 393 |
+
{"current_steps": 3930, "total_steps": 3941, "loss": 1.2707, "learning_rate": 2.374347192335424e-10, "epoch": 0.9970823290625397, "percentage": 99.72, "elapsed_time": "3:42:22", "remaining_time": "0:00:37"}
|
| 394 |
+
{"current_steps": 3940, "total_steps": 3941, "loss": 1.2737, "learning_rate": 1.9622858088430564e-12, "epoch": 0.9996194342255487, "percentage": 99.97, "elapsed_time": "3:42:54", "remaining_time": "0:00:03"}
|
| 395 |
+
{"current_steps": 3941, "total_steps": 3941, "epoch": 0.9998731447418495, "percentage": 100.0, "elapsed_time": "3:44:02", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2800 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9998731447418495,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3941,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002537105163009007,
|
| 13 |
+
"grad_norm": 4.350327938684374,
|
| 14 |
+
"learning_rate": 2.5316455696202533e-07,
|
| 15 |
+
"loss": 1.8196,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005074210326018014,
|
| 20 |
+
"grad_norm": 3.678530456221003,
|
| 21 |
+
"learning_rate": 5.063291139240507e-07,
|
| 22 |
+
"loss": 1.8108,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00761131548902702,
|
| 27 |
+
"grad_norm": 2.945036910011768,
|
| 28 |
+
"learning_rate": 7.59493670886076e-07,
|
| 29 |
+
"loss": 1.8147,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010148420652036028,
|
| 34 |
+
"grad_norm": 2.3190574498378447,
|
| 35 |
+
"learning_rate": 1.0126582278481013e-06,
|
| 36 |
+
"loss": 1.7548,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.012685525815045033,
|
| 41 |
+
"grad_norm": 2.074674879169714,
|
| 42 |
+
"learning_rate": 1.2658227848101267e-06,
|
| 43 |
+
"loss": 1.7204,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01522263097805404,
|
| 48 |
+
"grad_norm": 1.748653753253889,
|
| 49 |
+
"learning_rate": 1.518987341772152e-06,
|
| 50 |
+
"loss": 1.6762,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01775973614106305,
|
| 55 |
+
"grad_norm": 1.6751399170091914,
|
| 56 |
+
"learning_rate": 1.7721518987341774e-06,
|
| 57 |
+
"loss": 1.6487,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020296841304072055,
|
| 62 |
+
"grad_norm": 1.6363195765660283,
|
| 63 |
+
"learning_rate": 2.0253164556962026e-06,
|
| 64 |
+
"loss": 1.6116,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.022833946467081062,
|
| 69 |
+
"grad_norm": 1.5794976909544993,
|
| 70 |
+
"learning_rate": 2.278481012658228e-06,
|
| 71 |
+
"loss": 1.5916,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.025371051630090066,
|
| 76 |
+
"grad_norm": 1.6233632992191482,
|
| 77 |
+
"learning_rate": 2.5316455696202535e-06,
|
| 78 |
+
"loss": 1.598,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.027908156793099072,
|
| 83 |
+
"grad_norm": 1.5800661094425872,
|
| 84 |
+
"learning_rate": 2.7848101265822785e-06,
|
| 85 |
+
"loss": 1.5626,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.03044526195610808,
|
| 90 |
+
"grad_norm": 1.6072050143283245,
|
| 91 |
+
"learning_rate": 3.037974683544304e-06,
|
| 92 |
+
"loss": 1.5457,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03298236711911709,
|
| 97 |
+
"grad_norm": 1.6572306247078625,
|
| 98 |
+
"learning_rate": 3.2911392405063294e-06,
|
| 99 |
+
"loss": 1.5391,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0355194722821261,
|
| 104 |
+
"grad_norm": 1.586848380490154,
|
| 105 |
+
"learning_rate": 3.544303797468355e-06,
|
| 106 |
+
"loss": 1.5125,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.038056577445135104,
|
| 111 |
+
"grad_norm": 1.638449311664989,
|
| 112 |
+
"learning_rate": 3.7974683544303802e-06,
|
| 113 |
+
"loss": 1.5243,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04059368260814411,
|
| 118 |
+
"grad_norm": 1.6031920359772533,
|
| 119 |
+
"learning_rate": 4.050632911392405e-06,
|
| 120 |
+
"loss": 1.4856,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04313078777115312,
|
| 125 |
+
"grad_norm": 1.5967439995800559,
|
| 126 |
+
"learning_rate": 4.303797468354431e-06,
|
| 127 |
+
"loss": 1.5129,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.045667892934162124,
|
| 132 |
+
"grad_norm": 1.6075212497819606,
|
| 133 |
+
"learning_rate": 4.556962025316456e-06,
|
| 134 |
+
"loss": 1.4961,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04820499809717113,
|
| 139 |
+
"grad_norm": 1.6791238021539772,
|
| 140 |
+
"learning_rate": 4.8101265822784815e-06,
|
| 141 |
+
"loss": 1.4893,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05074210326018013,
|
| 146 |
+
"grad_norm": 1.6210921331693446,
|
| 147 |
+
"learning_rate": 5.063291139240507e-06,
|
| 148 |
+
"loss": 1.5013,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05327920842318914,
|
| 153 |
+
"grad_norm": 1.7652729374280518,
|
| 154 |
+
"learning_rate": 5.3164556962025316e-06,
|
| 155 |
+
"loss": 1.473,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.055816313586198145,
|
| 160 |
+
"grad_norm": 1.6723244529240142,
|
| 161 |
+
"learning_rate": 5.569620253164557e-06,
|
| 162 |
+
"loss": 1.4791,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.05835341874920715,
|
| 167 |
+
"grad_norm": 1.825326138794735,
|
| 168 |
+
"learning_rate": 5.8227848101265824e-06,
|
| 169 |
+
"loss": 1.4761,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06089052391221616,
|
| 174 |
+
"grad_norm": 1.9131148271572453,
|
| 175 |
+
"learning_rate": 6.075949367088608e-06,
|
| 176 |
+
"loss": 1.4626,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06342762907522517,
|
| 181 |
+
"grad_norm": 1.6613770739809675,
|
| 182 |
+
"learning_rate": 6.329113924050634e-06,
|
| 183 |
+
"loss": 1.4601,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06596473423823418,
|
| 188 |
+
"grad_norm": 1.6666458237214428,
|
| 189 |
+
"learning_rate": 6.582278481012659e-06,
|
| 190 |
+
"loss": 1.4686,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.06850183940124319,
|
| 195 |
+
"grad_norm": 1.5745675069520453,
|
| 196 |
+
"learning_rate": 6.835443037974684e-06,
|
| 197 |
+
"loss": 1.461,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0710389445642522,
|
| 202 |
+
"grad_norm": 1.6507776778175596,
|
| 203 |
+
"learning_rate": 7.08860759493671e-06,
|
| 204 |
+
"loss": 1.47,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0735760497272612,
|
| 209 |
+
"grad_norm": 1.6009958375778823,
|
| 210 |
+
"learning_rate": 7.341772151898735e-06,
|
| 211 |
+
"loss": 1.4526,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07611315489027021,
|
| 216 |
+
"grad_norm": 1.6786912574149853,
|
| 217 |
+
"learning_rate": 7.5949367088607605e-06,
|
| 218 |
+
"loss": 1.4501,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.07865026005327921,
|
| 223 |
+
"grad_norm": 1.6698693144659327,
|
| 224 |
+
"learning_rate": 7.848101265822786e-06,
|
| 225 |
+
"loss": 1.4483,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08118736521628822,
|
| 230 |
+
"grad_norm": 1.7393580296857223,
|
| 231 |
+
"learning_rate": 8.10126582278481e-06,
|
| 232 |
+
"loss": 1.4252,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.08372447037929723,
|
| 237 |
+
"grad_norm": 1.6124831573952214,
|
| 238 |
+
"learning_rate": 8.354430379746837e-06,
|
| 239 |
+
"loss": 1.4274,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08626157554230623,
|
| 244 |
+
"grad_norm": 1.6899774259466704,
|
| 245 |
+
"learning_rate": 8.607594936708861e-06,
|
| 246 |
+
"loss": 1.437,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.08879868070531524,
|
| 251 |
+
"grad_norm": 1.6821954539953226,
|
| 252 |
+
"learning_rate": 8.860759493670886e-06,
|
| 253 |
+
"loss": 1.4388,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09133578586832425,
|
| 258 |
+
"grad_norm": 1.8121412852354848,
|
| 259 |
+
"learning_rate": 9.113924050632912e-06,
|
| 260 |
+
"loss": 1.4151,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09387289103133326,
|
| 265 |
+
"grad_norm": 1.5407350947949157,
|
| 266 |
+
"learning_rate": 9.367088607594937e-06,
|
| 267 |
+
"loss": 1.4274,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09640999619434226,
|
| 272 |
+
"grad_norm": 1.7381357929095853,
|
| 273 |
+
"learning_rate": 9.620253164556963e-06,
|
| 274 |
+
"loss": 1.4309,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.09894710135735126,
|
| 279 |
+
"grad_norm": 1.6085237968347799,
|
| 280 |
+
"learning_rate": 9.87341772151899e-06,
|
| 281 |
+
"loss": 1.4173,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.10148420652036026,
|
| 286 |
+
"grad_norm": 1.728407830056737,
|
| 287 |
+
"learning_rate": 9.999950942931784e-06,
|
| 288 |
+
"loss": 1.4312,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.10402131168336927,
|
| 293 |
+
"grad_norm": 1.6972786696047149,
|
| 294 |
+
"learning_rate": 9.999558492161865e-06,
|
| 295 |
+
"loss": 1.422,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.10655841684637828,
|
| 300 |
+
"grad_norm": 1.6297612720977512,
|
| 301 |
+
"learning_rate": 9.998773621425852e-06,
|
| 302 |
+
"loss": 1.3892,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.10909552200938728,
|
| 307 |
+
"grad_norm": 1.7368434280409393,
|
| 308 |
+
"learning_rate": 9.997596392328971e-06,
|
| 309 |
+
"loss": 1.4368,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.11163262717239629,
|
| 314 |
+
"grad_norm": 1.8196387241516612,
|
| 315 |
+
"learning_rate": 9.996026897273024e-06,
|
| 316 |
+
"loss": 1.4129,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1141697323354053,
|
| 321 |
+
"grad_norm": 1.6083388947957715,
|
| 322 |
+
"learning_rate": 9.994065259449128e-06,
|
| 323 |
+
"loss": 1.4181,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1167068374984143,
|
| 328 |
+
"grad_norm": 1.7315485017229137,
|
| 329 |
+
"learning_rate": 9.991711632828049e-06,
|
| 330 |
+
"loss": 1.4107,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.11924394266142331,
|
| 335 |
+
"grad_norm": 1.6192259621686464,
|
| 336 |
+
"learning_rate": 9.988966202148115e-06,
|
| 337 |
+
"loss": 1.3933,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.12178104782443232,
|
| 342 |
+
"grad_norm": 1.685661277294985,
|
| 343 |
+
"learning_rate": 9.985829182900717e-06,
|
| 344 |
+
"loss": 1.4305,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12431815298744132,
|
| 349 |
+
"grad_norm": 1.7673237121898477,
|
| 350 |
+
"learning_rate": 9.982300821313394e-06,
|
| 351 |
+
"loss": 1.407,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.12685525815045035,
|
| 356 |
+
"grad_norm": 1.6729684650970384,
|
| 357 |
+
"learning_rate": 9.978381394330509e-06,
|
| 358 |
+
"loss": 1.3941,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.12939236331345935,
|
| 363 |
+
"grad_norm": 1.6737204711157692,
|
| 364 |
+
"learning_rate": 9.974071209591507e-06,
|
| 365 |
+
"loss": 1.4083,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.13192946847646836,
|
| 370 |
+
"grad_norm": 1.5846450496238496,
|
| 371 |
+
"learning_rate": 9.96937060540677e-06,
|
| 372 |
+
"loss": 1.3913,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.13446657363947737,
|
| 377 |
+
"grad_norm": 1.6440175318683266,
|
| 378 |
+
"learning_rate": 9.964279950731066e-06,
|
| 379 |
+
"loss": 1.4141,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.13700367880248637,
|
| 384 |
+
"grad_norm": 1.5435352480418292,
|
| 385 |
+
"learning_rate": 9.958799645134585e-06,
|
| 386 |
+
"loss": 1.3923,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.13954078396549538,
|
| 391 |
+
"grad_norm": 1.6806917695478834,
|
| 392 |
+
"learning_rate": 9.952930118771576e-06,
|
| 393 |
+
"loss": 1.3882,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1420778891285044,
|
| 398 |
+
"grad_norm": 1.6991483906725386,
|
| 399 |
+
"learning_rate": 9.946671832346588e-06,
|
| 400 |
+
"loss": 1.3806,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.1446149942915134,
|
| 405 |
+
"grad_norm": 1.6444779930069549,
|
| 406 |
+
"learning_rate": 9.940025277078304e-06,
|
| 407 |
+
"loss": 1.3877,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.1471520994545224,
|
| 412 |
+
"grad_norm": 1.584958906864304,
|
| 413 |
+
"learning_rate": 9.932990974660992e-06,
|
| 414 |
+
"loss": 1.3758,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.1496892046175314,
|
| 419 |
+
"grad_norm": 1.6339337045637337,
|
| 420 |
+
"learning_rate": 9.925569477223549e-06,
|
| 421 |
+
"loss": 1.3942,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.15222630978054041,
|
| 426 |
+
"grad_norm": 1.6782688039697937,
|
| 427 |
+
"learning_rate": 9.917761367286164e-06,
|
| 428 |
+
"loss": 1.3997,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.15476341494354942,
|
| 433 |
+
"grad_norm": 1.722985917307532,
|
| 434 |
+
"learning_rate": 9.909567257714605e-06,
|
| 435 |
+
"loss": 1.3902,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.15730052010655843,
|
| 440 |
+
"grad_norm": 1.515629790408513,
|
| 441 |
+
"learning_rate": 9.9009877916721e-06,
|
| 442 |
+
"loss": 1.3906,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.15983762526956743,
|
| 447 |
+
"grad_norm": 1.6832684084973726,
|
| 448 |
+
"learning_rate": 9.892023642568871e-06,
|
| 449 |
+
"loss": 1.3644,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.16237473043257644,
|
| 454 |
+
"grad_norm": 1.7217857604177804,
|
| 455 |
+
"learning_rate": 9.882675514009262e-06,
|
| 456 |
+
"loss": 1.3673,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.16491183559558545,
|
| 461 |
+
"grad_norm": 1.772784930329774,
|
| 462 |
+
"learning_rate": 9.872944139736523e-06,
|
| 463 |
+
"loss": 1.3751,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.16744894075859446,
|
| 468 |
+
"grad_norm": 1.528731449667675,
|
| 469 |
+
"learning_rate": 9.862830283575215e-06,
|
| 470 |
+
"loss": 1.3678,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.16998604592160346,
|
| 475 |
+
"grad_norm": 1.6156407009731812,
|
| 476 |
+
"learning_rate": 9.852334739371252e-06,
|
| 477 |
+
"loss": 1.3825,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.17252315108461247,
|
| 482 |
+
"grad_norm": 1.6415774929326135,
|
| 483 |
+
"learning_rate": 9.841458330929598e-06,
|
| 484 |
+
"loss": 1.3884,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.17506025624762148,
|
| 489 |
+
"grad_norm": 1.6070221223746397,
|
| 490 |
+
"learning_rate": 9.830201911949604e-06,
|
| 491 |
+
"loss": 1.3934,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.17759736141063048,
|
| 496 |
+
"grad_norm": 1.562454926578275,
|
| 497 |
+
"learning_rate": 9.818566365957996e-06,
|
| 498 |
+
"loss": 1.3645,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.1801344665736395,
|
| 503 |
+
"grad_norm": 1.5996614008577792,
|
| 504 |
+
"learning_rate": 9.80655260623953e-06,
|
| 505 |
+
"loss": 1.3708,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.1826715717366485,
|
| 510 |
+
"grad_norm": 1.5048794279696338,
|
| 511 |
+
"learning_rate": 9.794161575765311e-06,
|
| 512 |
+
"loss": 1.3749,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1852086768996575,
|
| 517 |
+
"grad_norm": 1.5935516523984996,
|
| 518 |
+
"learning_rate": 9.78139424711877e-06,
|
| 519 |
+
"loss": 1.3886,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1877457820626665,
|
| 524 |
+
"grad_norm": 1.5282445861981415,
|
| 525 |
+
"learning_rate": 9.76825162241933e-06,
|
| 526 |
+
"loss": 1.373,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.19028288722567552,
|
| 531 |
+
"grad_norm": 1.6358363561782086,
|
| 532 |
+
"learning_rate": 9.754734733243749e-06,
|
| 533 |
+
"loss": 1.3742,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.19281999238868452,
|
| 538 |
+
"grad_norm": 1.587601691095452,
|
| 539 |
+
"learning_rate": 9.740844640545151e-06,
|
| 540 |
+
"loss": 1.3603,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.19535709755169353,
|
| 545 |
+
"grad_norm": 1.5280980736395107,
|
| 546 |
+
"learning_rate": 9.726582434569744e-06,
|
| 547 |
+
"loss": 1.3636,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.1978942027147025,
|
| 552 |
+
"grad_norm": 1.5821827900533842,
|
| 553 |
+
"learning_rate": 9.711949234771258e-06,
|
| 554 |
+
"loss": 1.3536,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.20043130787771152,
|
| 559 |
+
"grad_norm": 1.6354511380141648,
|
| 560 |
+
"learning_rate": 9.696946189723067e-06,
|
| 561 |
+
"loss": 1.3777,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.20296841304072052,
|
| 566 |
+
"grad_norm": 1.4961728532518945,
|
| 567 |
+
"learning_rate": 9.681574477028039e-06,
|
| 568 |
+
"loss": 1.3555,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.20550551820372953,
|
| 573 |
+
"grad_norm": 1.6165039622149184,
|
| 574 |
+
"learning_rate": 9.66583530322611e-06,
|
| 575 |
+
"loss": 1.3736,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.20804262336673854,
|
| 580 |
+
"grad_norm": 1.6085071421673924,
|
| 581 |
+
"learning_rate": 9.649729903699575e-06,
|
| 582 |
+
"loss": 1.3685,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.21057972852974755,
|
| 587 |
+
"grad_norm": 1.674024959469941,
|
| 588 |
+
"learning_rate": 9.633259542576127e-06,
|
| 589 |
+
"loss": 1.3516,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.21311683369275655,
|
| 594 |
+
"grad_norm": 1.5457350813422102,
|
| 595 |
+
"learning_rate": 9.61642551262963e-06,
|
| 596 |
+
"loss": 1.3433,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.21565393885576556,
|
| 601 |
+
"grad_norm": 1.5638603110160445,
|
| 602 |
+
"learning_rate": 9.599229135178651e-06,
|
| 603 |
+
"loss": 1.3596,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.21819104401877457,
|
| 608 |
+
"grad_norm": 1.5845605847496684,
|
| 609 |
+
"learning_rate": 9.581671759982747e-06,
|
| 610 |
+
"loss": 1.3821,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.22072814918178357,
|
| 615 |
+
"grad_norm": 1.56321358587459,
|
| 616 |
+
"learning_rate": 9.563754765136522e-06,
|
| 617 |
+
"loss": 1.3568,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.22326525434479258,
|
| 622 |
+
"grad_norm": 1.621089242536098,
|
| 623 |
+
"learning_rate": 9.545479556961457e-06,
|
| 624 |
+
"loss": 1.3614,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2258023595078016,
|
| 629 |
+
"grad_norm": 1.5746598904044478,
|
| 630 |
+
"learning_rate": 9.526847569895529e-06,
|
| 631 |
+
"loss": 1.3536,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.2283394646708106,
|
| 636 |
+
"grad_norm": 1.632144120218129,
|
| 637 |
+
"learning_rate": 9.507860266380625e-06,
|
| 638 |
+
"loss": 1.3521,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2308765698338196,
|
| 643 |
+
"grad_norm": 1.6660492103415234,
|
| 644 |
+
"learning_rate": 9.488519136747741e-06,
|
| 645 |
+
"loss": 1.3455,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.2334136749968286,
|
| 650 |
+
"grad_norm": 1.6307872469664786,
|
| 651 |
+
"learning_rate": 9.468825699100013e-06,
|
| 652 |
+
"loss": 1.3388,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.23595078015983761,
|
| 657 |
+
"grad_norm": 1.51760811186189,
|
| 658 |
+
"learning_rate": 9.448781499193563e-06,
|
| 659 |
+
"loss": 1.36,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.23848788532284662,
|
| 664 |
+
"grad_norm": 1.6298958079571104,
|
| 665 |
+
"learning_rate": 9.428388110316165e-06,
|
| 666 |
+
"loss": 1.346,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.24102499048585563,
|
| 671 |
+
"grad_norm": 1.6241168589647443,
|
| 672 |
+
"learning_rate": 9.407647133163754e-06,
|
| 673 |
+
"loss": 1.3565,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.24356209564886463,
|
| 678 |
+
"grad_norm": 1.6330870068463266,
|
| 679 |
+
"learning_rate": 9.386560195714796e-06,
|
| 680 |
+
"loss": 1.3539,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.24609920081187364,
|
| 685 |
+
"grad_norm": 1.5846187793083721,
|
| 686 |
+
"learning_rate": 9.365128953102495e-06,
|
| 687 |
+
"loss": 1.3443,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.24863630597488265,
|
| 692 |
+
"grad_norm": 1.5816319458789425,
|
| 693 |
+
"learning_rate": 9.343355087484893e-06,
|
| 694 |
+
"loss": 1.3449,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.25117341113789166,
|
| 699 |
+
"grad_norm": 1.608667389007063,
|
| 700 |
+
"learning_rate": 9.321240307912818e-06,
|
| 701 |
+
"loss": 1.3503,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.2537105163009007,
|
| 706 |
+
"grad_norm": 1.535736158897923,
|
| 707 |
+
"learning_rate": 9.298786350195758e-06,
|
| 708 |
+
"loss": 1.3504,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.25624762146390967,
|
| 713 |
+
"grad_norm": 1.6105502703548435,
|
| 714 |
+
"learning_rate": 9.275994976765602e-06,
|
| 715 |
+
"loss": 1.3512,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.2587847266269187,
|
| 720 |
+
"grad_norm": 1.457234439212148,
|
| 721 |
+
"learning_rate": 9.252867976538312e-06,
|
| 722 |
+
"loss": 1.3447,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.2613218317899277,
|
| 727 |
+
"grad_norm": 1.632312084639862,
|
| 728 |
+
"learning_rate": 9.22940716477351e-06,
|
| 729 |
+
"loss": 1.3451,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2638589369529367,
|
| 734 |
+
"grad_norm": 1.5657163405769847,
|
| 735 |
+
"learning_rate": 9.205614382931986e-06,
|
| 736 |
+
"loss": 1.3678,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2663960421159457,
|
| 741 |
+
"grad_norm": 1.523325498659843,
|
| 742 |
+
"learning_rate": 9.181491498531179e-06,
|
| 743 |
+
"loss": 1.355,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.26893314727895473,
|
| 748 |
+
"grad_norm": 1.5647021825494114,
|
| 749 |
+
"learning_rate": 9.157040404998572e-06,
|
| 750 |
+
"loss": 1.3455,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2714702524419637,
|
| 755 |
+
"grad_norm": 1.581907280598391,
|
| 756 |
+
"learning_rate": 9.132263021523096e-06,
|
| 757 |
+
"loss": 1.353,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.27400735760497275,
|
| 762 |
+
"grad_norm": 1.4861566014453274,
|
| 763 |
+
"learning_rate": 9.107161292904476e-06,
|
| 764 |
+
"loss": 1.3428,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.2765444627679817,
|
| 769 |
+
"grad_norm": 1.6256210181495103,
|
| 770 |
+
"learning_rate": 9.081737189400583e-06,
|
| 771 |
+
"loss": 1.3421,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.27908156793099076,
|
| 776 |
+
"grad_norm": 1.4876360574590954,
|
| 777 |
+
"learning_rate": 9.0559927065728e-06,
|
| 778 |
+
"loss": 1.3377,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.28161867309399974,
|
| 783 |
+
"grad_norm": 1.5204275847901962,
|
| 784 |
+
"learning_rate": 9.029929865129375e-06,
|
| 785 |
+
"loss": 1.349,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2841557782570088,
|
| 790 |
+
"grad_norm": 1.5624633516357405,
|
| 791 |
+
"learning_rate": 9.003550710766813e-06,
|
| 792 |
+
"loss": 1.3552,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.28669288342001775,
|
| 797 |
+
"grad_norm": 1.5591567540085947,
|
| 798 |
+
"learning_rate": 8.97685731400932e-06,
|
| 799 |
+
"loss": 1.3209,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.2892299885830268,
|
| 804 |
+
"grad_norm": 1.5373317845285133,
|
| 805 |
+
"learning_rate": 8.949851770046272e-06,
|
| 806 |
+
"loss": 1.3267,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.29176709374603577,
|
| 811 |
+
"grad_norm": 1.5556061129094692,
|
| 812 |
+
"learning_rate": 8.922536198567772e-06,
|
| 813 |
+
"loss": 1.3379,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.2943041989090448,
|
| 818 |
+
"grad_norm": 1.971486780664198,
|
| 819 |
+
"learning_rate": 8.894912743598269e-06,
|
| 820 |
+
"loss": 1.3272,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.2968413040720538,
|
| 825 |
+
"grad_norm": 1.5365700226491938,
|
| 826 |
+
"learning_rate": 8.866983573328267e-06,
|
| 827 |
+
"loss": 1.333,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.2993784092350628,
|
| 832 |
+
"grad_norm": 1.6217713070921793,
|
| 833 |
+
"learning_rate": 8.83875087994415e-06,
|
| 834 |
+
"loss": 1.3497,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3019155143980718,
|
| 839 |
+
"grad_norm": 1.4917017043884344,
|
| 840 |
+
"learning_rate": 8.810216879456114e-06,
|
| 841 |
+
"loss": 1.3355,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.30445261956108083,
|
| 846 |
+
"grad_norm": 1.5427563058731948,
|
| 847 |
+
"learning_rate": 8.781383811524222e-06,
|
| 848 |
+
"loss": 1.3339,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.3069897247240898,
|
| 853 |
+
"grad_norm": 1.5666645778409243,
|
| 854 |
+
"learning_rate": 8.752253939282622e-06,
|
| 855 |
+
"loss": 1.332,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.30952682988709884,
|
| 860 |
+
"grad_norm": 1.5940427272465527,
|
| 861 |
+
"learning_rate": 8.722829549161904e-06,
|
| 862 |
+
"loss": 1.3411,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3120639350501078,
|
| 867 |
+
"grad_norm": 1.569355522659196,
|
| 868 |
+
"learning_rate": 8.69311295070964e-06,
|
| 869 |
+
"loss": 1.321,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.31460104021311686,
|
| 874 |
+
"grad_norm": 1.5823744419831982,
|
| 875 |
+
"learning_rate": 8.663106476409107e-06,
|
| 876 |
+
"loss": 1.3511,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.31713814537612584,
|
| 881 |
+
"grad_norm": 1.5626340370876246,
|
| 882 |
+
"learning_rate": 8.632812481496195e-06,
|
| 883 |
+
"loss": 1.3491,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.31967525053913487,
|
| 888 |
+
"grad_norm": 1.6216546055767536,
|
| 889 |
+
"learning_rate": 8.602233343774562e-06,
|
| 890 |
+
"loss": 1.3294,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.32221235570214385,
|
| 895 |
+
"grad_norm": 1.4885399811487754,
|
| 896 |
+
"learning_rate": 8.571371463428986e-06,
|
| 897 |
+
"loss": 1.3419,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.3247494608651529,
|
| 902 |
+
"grad_norm": 1.597124872589071,
|
| 903 |
+
"learning_rate": 8.540229262836974e-06,
|
| 904 |
+
"loss": 1.3245,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.32728656602816186,
|
| 909 |
+
"grad_norm": 1.5069638761813242,
|
| 910 |
+
"learning_rate": 8.508809186378631e-06,
|
| 911 |
+
"loss": 1.3357,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.3298236711911709,
|
| 916 |
+
"grad_norm": 1.5496475251999724,
|
| 917 |
+
"learning_rate": 8.477113700244788e-06,
|
| 918 |
+
"loss": 1.3297,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3323607763541799,
|
| 923 |
+
"grad_norm": 1.5177410295586948,
|
| 924 |
+
"learning_rate": 8.445145292243446e-06,
|
| 925 |
+
"loss": 1.3361,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3348978815171889,
|
| 930 |
+
"grad_norm": 1.4375424317665,
|
| 931 |
+
"learning_rate": 8.412906471604489e-06,
|
| 932 |
+
"loss": 1.3365,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.3374349866801979,
|
| 937 |
+
"grad_norm": 1.4733958562961815,
|
| 938 |
+
"learning_rate": 8.380399768782742e-06,
|
| 939 |
+
"loss": 1.3364,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.3399720918432069,
|
| 944 |
+
"grad_norm": 1.5665888162471464,
|
| 945 |
+
"learning_rate": 8.347627735259344e-06,
|
| 946 |
+
"loss": 1.3572,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3425091970062159,
|
| 951 |
+
"grad_norm": 1.5175787042273947,
|
| 952 |
+
"learning_rate": 8.314592943341494e-06,
|
| 953 |
+
"loss": 1.311,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.34504630216922494,
|
| 958 |
+
"grad_norm": 1.5210307965368668,
|
| 959 |
+
"learning_rate": 8.281297985960538e-06,
|
| 960 |
+
"loss": 1.3261,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.3475834073322339,
|
| 965 |
+
"grad_norm": 1.5365431443148119,
|
| 966 |
+
"learning_rate": 8.247745476468449e-06,
|
| 967 |
+
"loss": 1.3433,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.35012051249524295,
|
| 972 |
+
"grad_norm": 1.5548012069585933,
|
| 973 |
+
"learning_rate": 8.213938048432697e-06,
|
| 974 |
+
"loss": 1.3134,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.35265761765825193,
|
| 979 |
+
"grad_norm": 1.4642811591908687,
|
| 980 |
+
"learning_rate": 8.179878355429556e-06,
|
| 981 |
+
"loss": 1.3159,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.35519472282126097,
|
| 986 |
+
"grad_norm": 1.6713134353309254,
|
| 987 |
+
"learning_rate": 8.145569070835799e-06,
|
| 988 |
+
"loss": 1.3285,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.35773182798426995,
|
| 993 |
+
"grad_norm": 1.5444628338197106,
|
| 994 |
+
"learning_rate": 8.111012887618882e-06,
|
| 995 |
+
"loss": 1.344,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.360268933147279,
|
| 1000 |
+
"grad_norm": 1.5042040298049457,
|
| 1001 |
+
"learning_rate": 8.076212518125556e-06,
|
| 1002 |
+
"loss": 1.3217,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.36280603831028796,
|
| 1007 |
+
"grad_norm": 1.5827643194628298,
|
| 1008 |
+
"learning_rate": 8.041170693868985e-06,
|
| 1009 |
+
"loss": 1.3284,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.365343143473297,
|
| 1014 |
+
"grad_norm": 1.4314485322723574,
|
| 1015 |
+
"learning_rate": 8.005890165314334e-06,
|
| 1016 |
+
"loss": 1.3188,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.367880248636306,
|
| 1021 |
+
"grad_norm": 1.5452457890288078,
|
| 1022 |
+
"learning_rate": 7.970373701662892e-06,
|
| 1023 |
+
"loss": 1.3123,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.370417353799315,
|
| 1028 |
+
"grad_norm": 1.5944938106930338,
|
| 1029 |
+
"learning_rate": 7.934624090634713e-06,
|
| 1030 |
+
"loss": 1.3131,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.372954458962324,
|
| 1035 |
+
"grad_norm": 1.5553727991379855,
|
| 1036 |
+
"learning_rate": 7.8986441382498e-06,
|
| 1037 |
+
"loss": 1.3318,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.375491564125333,
|
| 1042 |
+
"grad_norm": 1.5196578480754726,
|
| 1043 |
+
"learning_rate": 7.862436668607865e-06,
|
| 1044 |
+
"loss": 1.3164,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.378028669288342,
|
| 1049 |
+
"grad_norm": 1.5354385242535227,
|
| 1050 |
+
"learning_rate": 7.826004523666661e-06,
|
| 1051 |
+
"loss": 1.3292,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.38056577445135104,
|
| 1056 |
+
"grad_norm": 1.5449910825994637,
|
| 1057 |
+
"learning_rate": 7.78935056301891e-06,
|
| 1058 |
+
"loss": 1.3272,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.38310287961436,
|
| 1063 |
+
"grad_norm": 1.4946907973724173,
|
| 1064 |
+
"learning_rate": 7.752477663667854e-06,
|
| 1065 |
+
"loss": 1.3391,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.38563998477736905,
|
| 1070 |
+
"grad_norm": 1.5791940161814702,
|
| 1071 |
+
"learning_rate": 7.715388719801437e-06,
|
| 1072 |
+
"loss": 1.3392,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.38817708994037803,
|
| 1077 |
+
"grad_norm": 1.4567702862839176,
|
| 1078 |
+
"learning_rate": 7.67808664256514e-06,
|
| 1079 |
+
"loss": 1.2971,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.39071419510338706,
|
| 1084 |
+
"grad_norm": 1.4605769814867744,
|
| 1085 |
+
"learning_rate": 7.640574359833472e-06,
|
| 1086 |
+
"loss": 1.3148,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.39325130026639604,
|
| 1091 |
+
"grad_norm": 1.5566796816874888,
|
| 1092 |
+
"learning_rate": 7.6028548159801685e-06,
|
| 1093 |
+
"loss": 1.3315,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.395788405429405,
|
| 1098 |
+
"grad_norm": 1.5768032029757384,
|
| 1099 |
+
"learning_rate": 7.564930971647087e-06,
|
| 1100 |
+
"loss": 1.3238,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.39832551059241406,
|
| 1105 |
+
"grad_norm": 1.5702550171255043,
|
| 1106 |
+
"learning_rate": 7.52680580351181e-06,
|
| 1107 |
+
"loss": 1.3175,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.40086261575542304,
|
| 1112 |
+
"grad_norm": 1.5687466837527182,
|
| 1113 |
+
"learning_rate": 7.488482304054019e-06,
|
| 1114 |
+
"loss": 1.3104,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.40339972091843207,
|
| 1119 |
+
"grad_norm": 1.5897550883645912,
|
| 1120 |
+
"learning_rate": 7.449963481320599e-06,
|
| 1121 |
+
"loss": 1.316,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.40593682608144105,
|
| 1126 |
+
"grad_norm": 1.5236147067965886,
|
| 1127 |
+
"learning_rate": 7.411252358689541e-06,
|
| 1128 |
+
"loss": 1.3273,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.4084739312444501,
|
| 1133 |
+
"grad_norm": 1.5469446528938424,
|
| 1134 |
+
"learning_rate": 7.372351974632634e-06,
|
| 1135 |
+
"loss": 1.3119,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.41101103640745906,
|
| 1140 |
+
"grad_norm": 1.4722026799112722,
|
| 1141 |
+
"learning_rate": 7.333265382476971e-06,
|
| 1142 |
+
"loss": 1.3151,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4135481415704681,
|
| 1147 |
+
"grad_norm": 1.5178886141824586,
|
| 1148 |
+
"learning_rate": 7.293995650165287e-06,
|
| 1149 |
+
"loss": 1.3245,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.4160852467334771,
|
| 1154 |
+
"grad_norm": 1.5308435376939995,
|
| 1155 |
+
"learning_rate": 7.2545458600151615e-06,
|
| 1156 |
+
"loss": 1.3317,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4186223518964861,
|
| 1161 |
+
"grad_norm": 1.5091424984828243,
|
| 1162 |
+
"learning_rate": 7.214919108477077e-06,
|
| 1163 |
+
"loss": 1.3044,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.4211594570594951,
|
| 1168 |
+
"grad_norm": 1.457202507709852,
|
| 1169 |
+
"learning_rate": 7.175118505891385e-06,
|
| 1170 |
+
"loss": 1.3339,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4236965622225041,
|
| 1175 |
+
"grad_norm": 1.530896247556501,
|
| 1176 |
+
"learning_rate": 7.135147176244158e-06,
|
| 1177 |
+
"loss": 1.3044,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.4262336673855131,
|
| 1182 |
+
"grad_norm": 1.5274463812149695,
|
| 1183 |
+
"learning_rate": 7.0950082569219955e-06,
|
| 1184 |
+
"loss": 1.3048,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.42877077254852214,
|
| 1189 |
+
"grad_norm": 1.507428973101804,
|
| 1190 |
+
"learning_rate": 7.054704898465772e-06,
|
| 1191 |
+
"loss": 1.3069,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.4313078777115311,
|
| 1196 |
+
"grad_norm": 1.5716469315983397,
|
| 1197 |
+
"learning_rate": 7.0142402643233346e-06,
|
| 1198 |
+
"loss": 1.3136,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.43384498287454015,
|
| 1203 |
+
"grad_norm": 1.4220881687524514,
|
| 1204 |
+
"learning_rate": 6.973617530601209e-06,
|
| 1205 |
+
"loss": 1.3165,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.43638208803754913,
|
| 1210 |
+
"grad_norm": 1.5926945403384438,
|
| 1211 |
+
"learning_rate": 6.932839885815304e-06,
|
| 1212 |
+
"loss": 1.3301,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.43891919320055817,
|
| 1217 |
+
"grad_norm": 1.4527595611730801,
|
| 1218 |
+
"learning_rate": 6.891910530640642e-06,
|
| 1219 |
+
"loss": 1.3145,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.44145629836356715,
|
| 1224 |
+
"grad_norm": 1.5069254389998272,
|
| 1225 |
+
"learning_rate": 6.850832677660134e-06,
|
| 1226 |
+
"loss": 1.3139,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.4439934035265762,
|
| 1231 |
+
"grad_norm": 1.4587280578384394,
|
| 1232 |
+
"learning_rate": 6.809609551112419e-06,
|
| 1233 |
+
"loss": 1.3085,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.44653050868958516,
|
| 1238 |
+
"grad_norm": 1.5122830472595903,
|
| 1239 |
+
"learning_rate": 6.768244386638793e-06,
|
| 1240 |
+
"loss": 1.3158,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.4490676138525942,
|
| 1245 |
+
"grad_norm": 1.4912245201929943,
|
| 1246 |
+
"learning_rate": 6.726740431029243e-06,
|
| 1247 |
+
"loss": 1.3167,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.4516047190156032,
|
| 1252 |
+
"grad_norm": 1.5574941259720791,
|
| 1253 |
+
"learning_rate": 6.685100941967596e-06,
|
| 1254 |
+
"loss": 1.3118,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.4541418241786122,
|
| 1259 |
+
"grad_norm": 1.4994130740882026,
|
| 1260 |
+
"learning_rate": 6.643329187775827e-06,
|
| 1261 |
+
"loss": 1.307,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.4566789293416212,
|
| 1266 |
+
"grad_norm": 1.5791237950971593,
|
| 1267 |
+
"learning_rate": 6.601428447157525e-06,
|
| 1268 |
+
"loss": 1.3086,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.4592160345046302,
|
| 1273 |
+
"grad_norm": 1.5319564794342408,
|
| 1274 |
+
"learning_rate": 6.559402008940539e-06,
|
| 1275 |
+
"loss": 1.3025,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.4617531396676392,
|
| 1280 |
+
"grad_norm": 1.5560620624811086,
|
| 1281 |
+
"learning_rate": 6.517253171818844e-06,
|
| 1282 |
+
"loss": 1.3146,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.46429024483064824,
|
| 1287 |
+
"grad_norm": 1.5762189341956727,
|
| 1288 |
+
"learning_rate": 6.474985244093613e-06,
|
| 1289 |
+
"loss": 1.307,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.4668273499936572,
|
| 1294 |
+
"grad_norm": 1.568824162809672,
|
| 1295 |
+
"learning_rate": 6.432601543413552e-06,
|
| 1296 |
+
"loss": 1.2996,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.46936445515666625,
|
| 1301 |
+
"grad_norm": 1.461712822890638,
|
| 1302 |
+
"learning_rate": 6.390105396514497e-06,
|
| 1303 |
+
"loss": 1.3013,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.47190156031967523,
|
| 1308 |
+
"grad_norm": 1.4727912142252813,
|
| 1309 |
+
"learning_rate": 6.347500138958285e-06,
|
| 1310 |
+
"loss": 1.3086,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.47443866548268426,
|
| 1315 |
+
"grad_norm": 1.4842630358439066,
|
| 1316 |
+
"learning_rate": 6.304789114870953e-06,
|
| 1317 |
+
"loss": 1.3121,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.47697577064569324,
|
| 1322 |
+
"grad_norm": 1.5147058669468259,
|
| 1323 |
+
"learning_rate": 6.261975676680252e-06,
|
| 1324 |
+
"loss": 1.3109,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.4795128758087023,
|
| 1329 |
+
"grad_norm": 1.5879467208142688,
|
| 1330 |
+
"learning_rate": 6.219063184852509e-06,
|
| 1331 |
+
"loss": 1.3057,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.48204998097171126,
|
| 1336 |
+
"grad_norm": 1.4622817504218393,
|
| 1337 |
+
"learning_rate": 6.176055007628859e-06,
|
| 1338 |
+
"loss": 1.2978,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.4845870861347203,
|
| 1343 |
+
"grad_norm": 1.4651555100721898,
|
| 1344 |
+
"learning_rate": 6.132954520760882e-06,
|
| 1345 |
+
"loss": 1.2936,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.48712419129772927,
|
| 1350 |
+
"grad_norm": 1.4242680820832143,
|
| 1351 |
+
"learning_rate": 6.089765107245616e-06,
|
| 1352 |
+
"loss": 1.311,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.4896612964607383,
|
| 1357 |
+
"grad_norm": 1.4510357489546541,
|
| 1358 |
+
"learning_rate": 6.046490157060041e-06,
|
| 1359 |
+
"loss": 1.2917,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.4921984016237473,
|
| 1364 |
+
"grad_norm": 1.5389362630585735,
|
| 1365 |
+
"learning_rate": 6.003133066894987e-06,
|
| 1366 |
+
"loss": 1.3173,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.4947355067867563,
|
| 1371 |
+
"grad_norm": 1.5597918071325416,
|
| 1372 |
+
"learning_rate": 5.959697239888525e-06,
|
| 1373 |
+
"loss": 1.2978,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.4972726119497653,
|
| 1378 |
+
"grad_norm": 1.481163850939429,
|
| 1379 |
+
"learning_rate": 5.916186085358858e-06,
|
| 1380 |
+
"loss": 1.3125,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.49980971711277433,
|
| 1385 |
+
"grad_norm": 1.5172196100773179,
|
| 1386 |
+
"learning_rate": 5.872603018536713e-06,
|
| 1387 |
+
"loss": 1.3035,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.5023468222757833,
|
| 1392 |
+
"grad_norm": 1.520182324070576,
|
| 1393 |
+
"learning_rate": 5.828951460297277e-06,
|
| 1394 |
+
"loss": 1.2943,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5048839274387923,
|
| 1399 |
+
"grad_norm": 1.374020881318329,
|
| 1400 |
+
"learning_rate": 5.785234836891697e-06,
|
| 1401 |
+
"loss": 1.3019,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5074210326018014,
|
| 1406 |
+
"grad_norm": 1.609172422257604,
|
| 1407 |
+
"learning_rate": 5.741456579678141e-06,
|
| 1408 |
+
"loss": 1.2929,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.5099581377648104,
|
| 1413 |
+
"grad_norm": 1.451921659432821,
|
| 1414 |
+
"learning_rate": 5.697620124852472e-06,
|
| 1415 |
+
"loss": 1.2868,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5124952429278193,
|
| 1420 |
+
"grad_norm": 1.531522896512812,
|
| 1421 |
+
"learning_rate": 5.65372891317854e-06,
|
| 1422 |
+
"loss": 1.2875,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.5150323480908283,
|
| 1427 |
+
"grad_norm": 1.443649652350418,
|
| 1428 |
+
"learning_rate": 5.6097863897181075e-06,
|
| 1429 |
+
"loss": 1.2963,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.5175694532538374,
|
| 1434 |
+
"grad_norm": 1.5591743411035264,
|
| 1435 |
+
"learning_rate": 5.565796003560447e-06,
|
| 1436 |
+
"loss": 1.3121,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.5201065584168464,
|
| 1441 |
+
"grad_norm": 1.428229068798765,
|
| 1442 |
+
"learning_rate": 5.521761207551622e-06,
|
| 1443 |
+
"loss": 1.2979,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.5226436635798554,
|
| 1448 |
+
"grad_norm": 1.5164415865949983,
|
| 1449 |
+
"learning_rate": 5.47768545802346e-06,
|
| 1450 |
+
"loss": 1.3107,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.5251807687428643,
|
| 1455 |
+
"grad_norm": 1.5292361648846982,
|
| 1456 |
+
"learning_rate": 5.433572214522275e-06,
|
| 1457 |
+
"loss": 1.2952,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5277178739058734,
|
| 1462 |
+
"grad_norm": 1.4451039662214231,
|
| 1463 |
+
"learning_rate": 5.389424939537311e-06,
|
| 1464 |
+
"loss": 1.2922,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.5302549790688824,
|
| 1469 |
+
"grad_norm": 1.558654012548035,
|
| 1470 |
+
"learning_rate": 5.345247098228977e-06,
|
| 1471 |
+
"loss": 1.2942,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5327920842318914,
|
| 1476 |
+
"grad_norm": 1.5393309134302235,
|
| 1477 |
+
"learning_rate": 5.301042158156866e-06,
|
| 1478 |
+
"loss": 1.2898,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.5353291893949004,
|
| 1483 |
+
"grad_norm": 1.5206662969722375,
|
| 1484 |
+
"learning_rate": 5.256813589007571e-06,
|
| 1485 |
+
"loss": 1.2967,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.5378662945579095,
|
| 1490 |
+
"grad_norm": 1.5295277898061372,
|
| 1491 |
+
"learning_rate": 5.212564862322355e-06,
|
| 1492 |
+
"loss": 1.2987,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.5404033997209184,
|
| 1497 |
+
"grad_norm": 1.5121887795702076,
|
| 1498 |
+
"learning_rate": 5.168299451224665e-06,
|
| 1499 |
+
"loss": 1.2859,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5429405048839274,
|
| 1504 |
+
"grad_norm": 1.5405224763949017,
|
| 1505 |
+
"learning_rate": 5.124020830147525e-06,
|
| 1506 |
+
"loss": 1.2942,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.5454776100469364,
|
| 1511 |
+
"grad_norm": 1.5241647102261355,
|
| 1512 |
+
"learning_rate": 5.079732474560821e-06,
|
| 1513 |
+
"loss": 1.2967,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.5480147152099455,
|
| 1518 |
+
"grad_norm": 1.5740459163455902,
|
| 1519 |
+
"learning_rate": 5.035437860698508e-06,
|
| 1520 |
+
"loss": 1.2792,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.5505518203729545,
|
| 1525 |
+
"grad_norm": 1.455514390960437,
|
| 1526 |
+
"learning_rate": 4.991140465285762e-06,
|
| 1527 |
+
"loss": 1.2722,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.5530889255359634,
|
| 1532 |
+
"grad_norm": 1.4543563727275153,
|
| 1533 |
+
"learning_rate": 4.94684376526608e-06,
|
| 1534 |
+
"loss": 1.294,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5556260306989724,
|
| 1539 |
+
"grad_norm": 1.415880887469612,
|
| 1540 |
+
"learning_rate": 4.902551237528387e-06,
|
| 1541 |
+
"loss": 1.2898,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.5581631358619815,
|
| 1546 |
+
"grad_norm": 1.5027054686198038,
|
| 1547 |
+
"learning_rate": 4.858266358634109e-06,
|
| 1548 |
+
"loss": 1.2943,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.5607002410249905,
|
| 1553 |
+
"grad_norm": 1.495415983271707,
|
| 1554 |
+
"learning_rate": 4.813992604544319e-06,
|
| 1555 |
+
"loss": 1.309,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.5632373461879995,
|
| 1560 |
+
"grad_norm": 1.5256997169566149,
|
| 1561 |
+
"learning_rate": 4.769733450346885e-06,
|
| 1562 |
+
"loss": 1.2941,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.5657744513510085,
|
| 1567 |
+
"grad_norm": 1.4207029137255274,
|
| 1568 |
+
"learning_rate": 4.725492369983721e-06,
|
| 1569 |
+
"loss": 1.2808,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5683115565140175,
|
| 1574 |
+
"grad_norm": 1.5127789303300487,
|
| 1575 |
+
"learning_rate": 4.6812728359781064e-06,
|
| 1576 |
+
"loss": 1.2886,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5708486616770265,
|
| 1581 |
+
"grad_norm": 1.4480660719145084,
|
| 1582 |
+
"learning_rate": 4.637078319162127e-06,
|
| 1583 |
+
"loss": 1.2848,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.5733857668400355,
|
| 1588 |
+
"grad_norm": 1.4818074524822986,
|
| 1589 |
+
"learning_rate": 4.592912288404251e-06,
|
| 1590 |
+
"loss": 1.2747,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.5759228720030445,
|
| 1595 |
+
"grad_norm": 1.496021447098999,
|
| 1596 |
+
"learning_rate": 4.5487782103370445e-06,
|
| 1597 |
+
"loss": 1.2889,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.5784599771660536,
|
| 1602 |
+
"grad_norm": 1.4726400774082267,
|
| 1603 |
+
"learning_rate": 4.504679549085077e-06,
|
| 1604 |
+
"loss": 1.2956,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.5809970823290626,
|
| 1609 |
+
"grad_norm": 1.492109044123467,
|
| 1610 |
+
"learning_rate": 4.460619765993025e-06,
|
| 1611 |
+
"loss": 1.2974,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.5835341874920715,
|
| 1616 |
+
"grad_norm": 1.4567515467141523,
|
| 1617 |
+
"learning_rate": 4.416602319353974e-06,
|
| 1618 |
+
"loss": 1.29,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.5860712926550805,
|
| 1623 |
+
"grad_norm": 1.460535915347314,
|
| 1624 |
+
"learning_rate": 4.3726306641379915e-06,
|
| 1625 |
+
"loss": 1.2745,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.5886083978180896,
|
| 1630 |
+
"grad_norm": 1.4651576736560898,
|
| 1631 |
+
"learning_rate": 4.328708251720924e-06,
|
| 1632 |
+
"loss": 1.2739,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.5911455029810986,
|
| 1637 |
+
"grad_norm": 1.6196158147206026,
|
| 1638 |
+
"learning_rate": 4.2848385296135165e-06,
|
| 1639 |
+
"loss": 1.3101,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.5936826081441076,
|
| 1644 |
+
"grad_norm": 1.527439804056797,
|
| 1645 |
+
"learning_rate": 4.241024941190792e-06,
|
| 1646 |
+
"loss": 1.2771,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.5962197133071165,
|
| 1651 |
+
"grad_norm": 1.4872645401772542,
|
| 1652 |
+
"learning_rate": 4.197270925421796e-06,
|
| 1653 |
+
"loss": 1.2877,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.5987568184701256,
|
| 1658 |
+
"grad_norm": 1.4908027336325684,
|
| 1659 |
+
"learning_rate": 4.153579916599659e-06,
|
| 1660 |
+
"loss": 1.2969,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.6012939236331346,
|
| 1665 |
+
"grad_norm": 1.370441167203172,
|
| 1666 |
+
"learning_rate": 4.109955344072036e-06,
|
| 1667 |
+
"loss": 1.2745,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.6038310287961436,
|
| 1672 |
+
"grad_norm": 1.457801692594122,
|
| 1673 |
+
"learning_rate": 4.066400631971938e-06,
|
| 1674 |
+
"loss": 1.2714,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6063681339591526,
|
| 1679 |
+
"grad_norm": 1.5047248748403204,
|
| 1680 |
+
"learning_rate": 4.022919198948966e-06,
|
| 1681 |
+
"loss": 1.2759,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6089052391221617,
|
| 1686 |
+
"grad_norm": 1.5232259549425642,
|
| 1687 |
+
"learning_rate": 3.979514457900982e-06,
|
| 1688 |
+
"loss": 1.2845,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.6114423442851706,
|
| 1693 |
+
"grad_norm": 1.4170452963382303,
|
| 1694 |
+
"learning_rate": 3.936189815706219e-06,
|
| 1695 |
+
"loss": 1.2833,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.6139794494481796,
|
| 1700 |
+
"grad_norm": 1.5010818180720833,
|
| 1701 |
+
"learning_rate": 3.8929486729558775e-06,
|
| 1702 |
+
"loss": 1.2941,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.6165165546111886,
|
| 1707 |
+
"grad_norm": 1.4420347497785075,
|
| 1708 |
+
"learning_rate": 3.849794423687212e-06,
|
| 1709 |
+
"loss": 1.2775,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.6190536597741977,
|
| 1714 |
+
"grad_norm": 1.520468191298721,
|
| 1715 |
+
"learning_rate": 3.8067304551171247e-06,
|
| 1716 |
+
"loss": 1.2627,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.6215907649372067,
|
| 1721 |
+
"grad_norm": 1.4753704862458017,
|
| 1722 |
+
"learning_rate": 3.7637601473763035e-06,
|
| 1723 |
+
"loss": 1.284,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.6241278701002156,
|
| 1728 |
+
"grad_norm": 1.469877746697786,
|
| 1729 |
+
"learning_rate": 3.7208868732439145e-06,
|
| 1730 |
+
"loss": 1.2927,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.6266649752632246,
|
| 1735 |
+
"grad_norm": 1.4601548141707599,
|
| 1736 |
+
"learning_rate": 3.6781139978828606e-06,
|
| 1737 |
+
"loss": 1.2947,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.6292020804262337,
|
| 1742 |
+
"grad_norm": 1.5092438879342172,
|
| 1743 |
+
"learning_rate": 3.6354448785756558e-06,
|
| 1744 |
+
"loss": 1.2843,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.6317391855892427,
|
| 1749 |
+
"grad_norm": 1.4368007055488876,
|
| 1750 |
+
"learning_rate": 3.592882864460905e-06,
|
| 1751 |
+
"loss": 1.265,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.6342762907522517,
|
| 1756 |
+
"grad_norm": 1.4672055312297339,
|
| 1757 |
+
"learning_rate": 3.5504312962704245e-06,
|
| 1758 |
+
"loss": 1.2709,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.6368133959152606,
|
| 1763 |
+
"grad_norm": 1.4995451462382032,
|
| 1764 |
+
"learning_rate": 3.5080935060670345e-06,
|
| 1765 |
+
"loss": 1.2679,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.6393505010782697,
|
| 1770 |
+
"grad_norm": 1.458116276283539,
|
| 1771 |
+
"learning_rate": 3.465872816983008e-06,
|
| 1772 |
+
"loss": 1.2821,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.6418876062412787,
|
| 1777 |
+
"grad_norm": 1.4447640379158275,
|
| 1778 |
+
"learning_rate": 3.4237725429592507e-06,
|
| 1779 |
+
"loss": 1.2865,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.6444247114042877,
|
| 1784 |
+
"grad_norm": 1.3965736731366891,
|
| 1785 |
+
"learning_rate": 3.3817959884851735e-06,
|
| 1786 |
+
"loss": 1.2698,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.6469618165672967,
|
| 1791 |
+
"grad_norm": 1.4648194884238146,
|
| 1792 |
+
"learning_rate": 3.3399464483393272e-06,
|
| 1793 |
+
"loss": 1.291,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.6494989217303058,
|
| 1798 |
+
"grad_norm": 1.4271493727093771,
|
| 1799 |
+
"learning_rate": 3.298227207330792e-06,
|
| 1800 |
+
"loss": 1.2765,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.6520360268933147,
|
| 1805 |
+
"grad_norm": 1.5962462881292958,
|
| 1806 |
+
"learning_rate": 3.256641540041346e-06,
|
| 1807 |
+
"loss": 1.2905,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.6545731320563237,
|
| 1812 |
+
"grad_norm": 1.4501719681830862,
|
| 1813 |
+
"learning_rate": 3.2151927105684423e-06,
|
| 1814 |
+
"loss": 1.298,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.6571102372193327,
|
| 1819 |
+
"grad_norm": 1.5186349976521718,
|
| 1820 |
+
"learning_rate": 3.1738839722690085e-06,
|
| 1821 |
+
"loss": 1.2742,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.6596473423823418,
|
| 1826 |
+
"grad_norm": 1.3901740398219145,
|
| 1827 |
+
"learning_rate": 3.1327185675040907e-06,
|
| 1828 |
+
"loss": 1.2769,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.6621844475453508,
|
| 1833 |
+
"grad_norm": 1.4618375024699428,
|
| 1834 |
+
"learning_rate": 3.0916997273843454e-06,
|
| 1835 |
+
"loss": 1.2938,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.6647215527083598,
|
| 1840 |
+
"grad_norm": 1.4675982361039484,
|
| 1841 |
+
"learning_rate": 3.0508306715164416e-06,
|
| 1842 |
+
"loss": 1.2913,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.6672586578713687,
|
| 1847 |
+
"grad_norm": 1.5086185778550512,
|
| 1848 |
+
"learning_rate": 3.0101146077503386e-06,
|
| 1849 |
+
"loss": 1.2777,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.6697957630343778,
|
| 1854 |
+
"grad_norm": 1.4573487737483761,
|
| 1855 |
+
"learning_rate": 2.9695547319275093e-06,
|
| 1856 |
+
"loss": 1.2633,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.6723328681973868,
|
| 1861 |
+
"grad_norm": 1.43323809832072,
|
| 1862 |
+
"learning_rate": 2.9291542276300866e-06,
|
| 1863 |
+
"loss": 1.289,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.6748699733603958,
|
| 1868 |
+
"grad_norm": 1.420082813628849,
|
| 1869 |
+
"learning_rate": 2.8889162659309832e-06,
|
| 1870 |
+
"loss": 1.2729,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.6774070785234048,
|
| 1875 |
+
"grad_norm": 1.424990219399345,
|
| 1876 |
+
"learning_rate": 2.848844005145004e-06,
|
| 1877 |
+
"loss": 1.3024,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.6799441836864138,
|
| 1882 |
+
"grad_norm": 1.4395745448115305,
|
| 1883 |
+
"learning_rate": 2.808940590580922e-06,
|
| 1884 |
+
"loss": 1.2845,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.6824812888494228,
|
| 1889 |
+
"grad_norm": 1.4802086998925903,
|
| 1890 |
+
"learning_rate": 2.769209154294623e-06,
|
| 1891 |
+
"loss": 1.2844,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.6850183940124318,
|
| 1896 |
+
"grad_norm": 1.491623196795251,
|
| 1897 |
+
"learning_rate": 2.7296528148432565e-06,
|
| 1898 |
+
"loss": 1.2683,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.6875554991754408,
|
| 1903 |
+
"grad_norm": 1.416764375906272,
|
| 1904 |
+
"learning_rate": 2.690274677040462e-06,
|
| 1905 |
+
"loss": 1.2776,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.6900926043384499,
|
| 1910 |
+
"grad_norm": 1.519033593874162,
|
| 1911 |
+
"learning_rate": 2.6510778317126597e-06,
|
| 1912 |
+
"loss": 1.2807,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.6926297095014589,
|
| 1917 |
+
"grad_norm": 1.3894691132515595,
|
| 1918 |
+
"learning_rate": 2.6120653554564624e-06,
|
| 1919 |
+
"loss": 1.2777,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.6951668146644678,
|
| 1924 |
+
"grad_norm": 1.4049713206074572,
|
| 1925 |
+
"learning_rate": 2.573240310397187e-06,
|
| 1926 |
+
"loss": 1.2736,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.6977039198274768,
|
| 1931 |
+
"grad_norm": 1.4357642101900112,
|
| 1932 |
+
"learning_rate": 2.5346057439484923e-06,
|
| 1933 |
+
"loss": 1.2803,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.7002410249904859,
|
| 1938 |
+
"grad_norm": 1.490167340198777,
|
| 1939 |
+
"learning_rate": 2.4961646885732034e-06,
|
| 1940 |
+
"loss": 1.2744,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.7027781301534949,
|
| 1945 |
+
"grad_norm": 1.4179312953545702,
|
| 1946 |
+
"learning_rate": 2.4579201615452812e-06,
|
| 1947 |
+
"loss": 1.2842,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.7053152353165039,
|
| 1952 |
+
"grad_norm": 1.6140649717523825,
|
| 1953 |
+
"learning_rate": 2.4198751647129896e-06,
|
| 1954 |
+
"loss": 1.2963,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.7078523404795128,
|
| 1959 |
+
"grad_norm": 1.530468810042779,
|
| 1960 |
+
"learning_rate": 2.3820326842632894e-06,
|
| 1961 |
+
"loss": 1.2637,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7103894456425219,
|
| 1966 |
+
"grad_norm": 1.412588711043796,
|
| 1967 |
+
"learning_rate": 2.344395690487441e-06,
|
| 1968 |
+
"loss": 1.2856,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.7129265508055309,
|
| 1973 |
+
"grad_norm": 1.5447254908338892,
|
| 1974 |
+
"learning_rate": 2.3069671375478645e-06,
|
| 1975 |
+
"loss": 1.2848,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.7154636559685399,
|
| 1980 |
+
"grad_norm": 1.43691808431636,
|
| 1981 |
+
"learning_rate": 2.2697499632462695e-06,
|
| 1982 |
+
"loss": 1.2536,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.7180007611315489,
|
| 1987 |
+
"grad_norm": 1.5560428170621574,
|
| 1988 |
+
"learning_rate": 2.2327470887930595e-06,
|
| 1989 |
+
"loss": 1.3015,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.720537866294558,
|
| 1994 |
+
"grad_norm": 1.450374747082515,
|
| 1995 |
+
"learning_rate": 2.195961418578041e-06,
|
| 1996 |
+
"loss": 1.2744,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.7230749714575669,
|
| 2001 |
+
"grad_norm": 1.484538648746269,
|
| 2002 |
+
"learning_rate": 2.159395839942464e-06,
|
| 2003 |
+
"loss": 1.2664,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.7256120766205759,
|
| 2008 |
+
"grad_norm": 1.3953379506558543,
|
| 2009 |
+
"learning_rate": 2.1230532229523865e-06,
|
| 2010 |
+
"loss": 1.2489,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.7281491817835849,
|
| 2015 |
+
"grad_norm": 1.4415654155573785,
|
| 2016 |
+
"learning_rate": 2.086936420173399e-06,
|
| 2017 |
+
"loss": 1.2719,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.730686286946594,
|
| 2022 |
+
"grad_norm": 1.4271516629005172,
|
| 2023 |
+
"learning_rate": 2.051048266446727e-06,
|
| 2024 |
+
"loss": 1.2652,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.733223392109603,
|
| 2029 |
+
"grad_norm": 1.4951992832082914,
|
| 2030 |
+
"learning_rate": 2.0153915786667203e-06,
|
| 2031 |
+
"loss": 1.26,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.735760497272612,
|
| 2036 |
+
"grad_norm": 1.4351479751585414,
|
| 2037 |
+
"learning_rate": 1.9799691555597555e-06,
|
| 2038 |
+
"loss": 1.2881,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.7382976024356209,
|
| 2043 |
+
"grad_norm": 1.474899241565124,
|
| 2044 |
+
"learning_rate": 1.9447837774645513e-06,
|
| 2045 |
+
"loss": 1.2702,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.74083470759863,
|
| 2050 |
+
"grad_norm": 1.4426835070499822,
|
| 2051 |
+
"learning_rate": 1.9098382061139503e-06,
|
| 2052 |
+
"loss": 1.2699,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.743371812761639,
|
| 2057 |
+
"grad_norm": 1.4876818985570295,
|
| 2058 |
+
"learning_rate": 1.8751351844181414e-06,
|
| 2059 |
+
"loss": 1.2612,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.745908917924648,
|
| 2064 |
+
"grad_norm": 1.4360645410392319,
|
| 2065 |
+
"learning_rate": 1.8406774362493662e-06,
|
| 2066 |
+
"loss": 1.2754,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.748446023087657,
|
| 2071 |
+
"grad_norm": 1.4473888665732064,
|
| 2072 |
+
"learning_rate": 1.8064676662281206e-06,
|
| 2073 |
+
"loss": 1.2902,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.750983128250666,
|
| 2078 |
+
"grad_norm": 1.4434612838312966,
|
| 2079 |
+
"learning_rate": 1.7725085595108682e-06,
|
| 2080 |
+
"loss": 1.273,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.753520233413675,
|
| 2085 |
+
"grad_norm": 1.558136105535075,
|
| 2086 |
+
"learning_rate": 1.7388027815792725e-06,
|
| 2087 |
+
"loss": 1.2787,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.756057338576684,
|
| 2092 |
+
"grad_norm": 1.4724878594646564,
|
| 2093 |
+
"learning_rate": 1.705352978030993e-06,
|
| 2094 |
+
"loss": 1.2627,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.758594443739693,
|
| 2099 |
+
"grad_norm": 1.4768497018650097,
|
| 2100 |
+
"learning_rate": 1.672161774372022e-06,
|
| 2101 |
+
"loss": 1.2911,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.7611315489027021,
|
| 2106 |
+
"grad_norm": 1.4598692131173956,
|
| 2107 |
+
"learning_rate": 1.639231775810602e-06,
|
| 2108 |
+
"loss": 1.2907,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.763668654065711,
|
| 2113 |
+
"grad_norm": 1.3971487709781405,
|
| 2114 |
+
"learning_rate": 1.6065655670527546e-06,
|
| 2115 |
+
"loss": 1.2632,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.76620575922872,
|
| 2120 |
+
"grad_norm": 1.4196228285690422,
|
| 2121 |
+
"learning_rate": 1.574165712099392e-06,
|
| 2122 |
+
"loss": 1.2542,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.768742864391729,
|
| 2127 |
+
"grad_norm": 1.4395590200787511,
|
| 2128 |
+
"learning_rate": 1.542034754045067e-06,
|
| 2129 |
+
"loss": 1.2693,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.7712799695547381,
|
| 2134 |
+
"grad_norm": 1.4538143237649903,
|
| 2135 |
+
"learning_rate": 1.5101752148783705e-06,
|
| 2136 |
+
"loss": 1.2728,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.7738170747177471,
|
| 2141 |
+
"grad_norm": 1.4483981816763403,
|
| 2142 |
+
"learning_rate": 1.4785895952839735e-06,
|
| 2143 |
+
"loss": 1.2671,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.7763541798807561,
|
| 2148 |
+
"grad_norm": 1.5335192207213328,
|
| 2149 |
+
"learning_rate": 1.447280374446346e-06,
|
| 2150 |
+
"loss": 1.2778,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.778891285043765,
|
| 2155 |
+
"grad_norm": 1.4504666284348766,
|
| 2156 |
+
"learning_rate": 1.4162500098551608e-06,
|
| 2157 |
+
"loss": 1.276,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.7814283902067741,
|
| 2162 |
+
"grad_norm": 1.454412830474016,
|
| 2163 |
+
"learning_rate": 1.385500937112415e-06,
|
| 2164 |
+
"loss": 1.2804,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.7839654953697831,
|
| 2169 |
+
"grad_norm": 1.462536001446098,
|
| 2170 |
+
"learning_rate": 1.3550355697412386e-06,
|
| 2171 |
+
"loss": 1.2586,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.7865026005327921,
|
| 2176 |
+
"grad_norm": 1.4861860594882876,
|
| 2177 |
+
"learning_rate": 1.3248562989964719e-06,
|
| 2178 |
+
"loss": 1.2843,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.7890397056958011,
|
| 2183 |
+
"grad_norm": 1.391241218546658,
|
| 2184 |
+
"learning_rate": 1.2949654936769622e-06,
|
| 2185 |
+
"loss": 1.2723,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.79157681085881,
|
| 2190 |
+
"grad_norm": 1.412674356321388,
|
| 2191 |
+
"learning_rate": 1.2653654999396436e-06,
|
| 2192 |
+
"loss": 1.2621,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.7941139160218191,
|
| 2197 |
+
"grad_norm": 1.406341007739084,
|
| 2198 |
+
"learning_rate": 1.2360586411153747e-06,
|
| 2199 |
+
"loss": 1.2897,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.7966510211848281,
|
| 2204 |
+
"grad_norm": 1.4125498017483746,
|
| 2205 |
+
"learning_rate": 1.2070472175265857e-06,
|
| 2206 |
+
"loss": 1.2657,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.7991881263478371,
|
| 2211 |
+
"grad_norm": 1.575395352386111,
|
| 2212 |
+
"learning_rate": 1.1783335063067286e-06,
|
| 2213 |
+
"loss": 1.2974,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.8017252315108461,
|
| 2218 |
+
"grad_norm": 1.4632409776646316,
|
| 2219 |
+
"learning_rate": 1.1499197612215269e-06,
|
| 2220 |
+
"loss": 1.2914,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8042623366738552,
|
| 2225 |
+
"grad_norm": 1.420307782085356,
|
| 2226 |
+
"learning_rate": 1.1218082124920903e-06,
|
| 2227 |
+
"loss": 1.2583,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8067994418368641,
|
| 2232 |
+
"grad_norm": 1.4073518626370982,
|
| 2233 |
+
"learning_rate": 1.0940010666198575e-06,
|
| 2234 |
+
"loss": 1.2588,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8093365469998731,
|
| 2239 |
+
"grad_norm": 1.427712685491864,
|
| 2240 |
+
"learning_rate": 1.0665005062134015e-06,
|
| 2241 |
+
"loss": 1.2641,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.8118736521628821,
|
| 2246 |
+
"grad_norm": 1.4042233353051128,
|
| 2247 |
+
"learning_rate": 1.0393086898171234e-06,
|
| 2248 |
+
"loss": 1.2623,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.8144107573258912,
|
| 2253 |
+
"grad_norm": 1.4353551061219325,
|
| 2254 |
+
"learning_rate": 1.0124277517418196e-06,
|
| 2255 |
+
"loss": 1.2701,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.8169478624889002,
|
| 2260 |
+
"grad_norm": 1.4714738106408498,
|
| 2261 |
+
"learning_rate": 9.858598018971599e-07,
|
| 2262 |
+
"loss": 1.2665,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.8194849676519091,
|
| 2267 |
+
"grad_norm": 1.3867710691517015,
|
| 2268 |
+
"learning_rate": 9.596069256260792e-07,
|
| 2269 |
+
"loss": 1.2811,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.8220220728149181,
|
| 2274 |
+
"grad_norm": 1.5556697110120234,
|
| 2275 |
+
"learning_rate": 9.336711835410972e-07,
|
| 2276 |
+
"loss": 1.2577,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.8245591779779272,
|
| 2281 |
+
"grad_norm": 1.4677232808017586,
|
| 2282 |
+
"learning_rate": 9.080546113625738e-07,
|
| 2283 |
+
"loss": 1.2675,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.8270962831409362,
|
| 2288 |
+
"grad_norm": 1.4009076826572764,
|
| 2289 |
+
"learning_rate": 8.827592197589341e-07,
|
| 2290 |
+
"loss": 1.2573,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.8296333883039452,
|
| 2295 |
+
"grad_norm": 1.3584163410682717,
|
| 2296 |
+
"learning_rate": 8.577869941888389e-07,
|
| 2297 |
+
"loss": 1.2654,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.8321704934669542,
|
| 2302 |
+
"grad_norm": 1.4763004523041792,
|
| 2303 |
+
"learning_rate": 8.331398947453512e-07,
|
| 2304 |
+
"loss": 1.271,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.8347075986299632,
|
| 2309 |
+
"grad_norm": 1.432107775038367,
|
| 2310 |
+
"learning_rate": 8.08819856002081e-07,
|
| 2311 |
+
"loss": 1.2771,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.8372447037929722,
|
| 2316 |
+
"grad_norm": 1.4636493219573536,
|
| 2317 |
+
"learning_rate": 7.848287868613441e-07,
|
| 2318 |
+
"loss": 1.2511,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.8397818089559812,
|
| 2323 |
+
"grad_norm": 1.501456048501624,
|
| 2324 |
+
"learning_rate": 7.611685704043281e-07,
|
| 2325 |
+
"loss": 1.2724,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.8423189141189902,
|
| 2330 |
+
"grad_norm": 1.4533194309629769,
|
| 2331 |
+
"learning_rate": 7.378410637432848e-07,
|
| 2332 |
+
"loss": 1.2761,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.8448560192819993,
|
| 2337 |
+
"grad_norm": 1.4930040288043631,
|
| 2338 |
+
"learning_rate": 7.148480978757694e-07,
|
| 2339 |
+
"loss": 1.2808,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.8473931244450083,
|
| 2344 |
+
"grad_norm": 1.4327631888495864,
|
| 2345 |
+
"learning_rate": 6.921914775409211e-07,
|
| 2346 |
+
"loss": 1.2764,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.8499302296080172,
|
| 2351 |
+
"grad_norm": 1.4066505744498654,
|
| 2352 |
+
"learning_rate": 6.698729810778065e-07,
|
| 2353 |
+
"loss": 1.2724,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.8524673347710262,
|
| 2358 |
+
"grad_norm": 1.4214214237910756,
|
| 2359 |
+
"learning_rate": 6.478943602858373e-07,
|
| 2360 |
+
"loss": 1.2703,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.8550044399340353,
|
| 2365 |
+
"grad_norm": 1.4609797404161982,
|
| 2366 |
+
"learning_rate": 6.262573402872707e-07,
|
| 2367 |
+
"loss": 1.2702,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.8575415450970443,
|
| 2372 |
+
"grad_norm": 1.4426076897314533,
|
| 2373 |
+
"learning_rate": 6.04963619391799e-07,
|
| 2374 |
+
"loss": 1.2652,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.8600786502600533,
|
| 2379 |
+
"grad_norm": 1.4557782632700174,
|
| 2380 |
+
"learning_rate": 5.840148689632536e-07,
|
| 2381 |
+
"loss": 1.2628,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.8626157554230622,
|
| 2386 |
+
"grad_norm": 1.4465949605683495,
|
| 2387 |
+
"learning_rate": 5.634127332884143e-07,
|
| 2388 |
+
"loss": 1.2649,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.8651528605860713,
|
| 2393 |
+
"grad_norm": 1.4543385042228827,
|
| 2394 |
+
"learning_rate": 5.431588294479479e-07,
|
| 2395 |
+
"loss": 1.2863,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.8676899657490803,
|
| 2400 |
+
"grad_norm": 1.4211990179028964,
|
| 2401 |
+
"learning_rate": 5.232547471894839e-07,
|
| 2402 |
+
"loss": 1.2603,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.8702270709120893,
|
| 2407 |
+
"grad_norm": 1.4970252757505178,
|
| 2408 |
+
"learning_rate": 5.037020488028322e-07,
|
| 2409 |
+
"loss": 1.2659,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.8727641760750983,
|
| 2414 |
+
"grad_norm": 1.476846612856639,
|
| 2415 |
+
"learning_rate": 4.845022689973567e-07,
|
| 2416 |
+
"loss": 1.2622,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.8753012812381074,
|
| 2421 |
+
"grad_norm": 1.3975933791175674,
|
| 2422 |
+
"learning_rate": 4.656569147815171e-07,
|
| 2423 |
+
"loss": 1.2675,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.8778383864011163,
|
| 2428 |
+
"grad_norm": 1.4066115466115592,
|
| 2429 |
+
"learning_rate": 4.471674653445801e-07,
|
| 2430 |
+
"loss": 1.2657,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.8803754915641253,
|
| 2435 |
+
"grad_norm": 1.4093052515025426,
|
| 2436 |
+
"learning_rate": 4.290353719405199e-07,
|
| 2437 |
+
"loss": 1.2622,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.8829125967271343,
|
| 2442 |
+
"grad_norm": 1.517434872609148,
|
| 2443 |
+
"learning_rate": 4.1126205777410054e-07,
|
| 2444 |
+
"loss": 1.2658,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.8854497018901434,
|
| 2449 |
+
"grad_norm": 1.3671982309013966,
|
| 2450 |
+
"learning_rate": 3.938489178891769e-07,
|
| 2451 |
+
"loss": 1.26,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.8879868070531524,
|
| 2456 |
+
"grad_norm": 1.3848746120915914,
|
| 2457 |
+
"learning_rate": 3.767973190591906e-07,
|
| 2458 |
+
"loss": 1.252,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.8905239122161613,
|
| 2463 |
+
"grad_norm": 1.404335518132526,
|
| 2464 |
+
"learning_rate": 3.6010859967988975e-07,
|
| 2465 |
+
"loss": 1.2684,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.8930610173791703,
|
| 2470 |
+
"grad_norm": 1.4696908362694405,
|
| 2471 |
+
"learning_rate": 3.437840696642797e-07,
|
| 2472 |
+
"loss": 1.28,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.8955981225421794,
|
| 2477 |
+
"grad_norm": 1.4394982066957633,
|
| 2478 |
+
"learning_rate": 3.2782501033980897e-07,
|
| 2479 |
+
"loss": 1.2596,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.8981352277051884,
|
| 2484 |
+
"grad_norm": 1.441827806292722,
|
| 2485 |
+
"learning_rate": 3.1223267434778934e-07,
|
| 2486 |
+
"loss": 1.2548,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9006723328681974,
|
| 2491 |
+
"grad_norm": 1.4029572337771223,
|
| 2492 |
+
"learning_rate": 2.9700828554508175e-07,
|
| 2493 |
+
"loss": 1.2714,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9032094380312063,
|
| 2498 |
+
"grad_norm": 1.456563644801128,
|
| 2499 |
+
"learning_rate": 2.82153038908034e-07,
|
| 2500 |
+
"loss": 1.271,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.9057465431942154,
|
| 2505 |
+
"grad_norm": 1.4854658320433165,
|
| 2506 |
+
"learning_rate": 2.6766810043867996e-07,
|
| 2507 |
+
"loss": 1.2636,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.9082836483572244,
|
| 2512 |
+
"grad_norm": 1.3976434876269141,
|
| 2513 |
+
"learning_rate": 2.53554607073227e-07,
|
| 2514 |
+
"loss": 1.2555,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.9108207535202334,
|
| 2519 |
+
"grad_norm": 1.4520566750739115,
|
| 2520 |
+
"learning_rate": 2.3981366659281135e-07,
|
| 2521 |
+
"loss": 1.2741,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.9133578586832424,
|
| 2526 |
+
"grad_norm": 1.431635462724296,
|
| 2527 |
+
"learning_rate": 2.2644635753654832e-07,
|
| 2528 |
+
"loss": 1.2641,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.9158949638462515,
|
| 2533 |
+
"grad_norm": 1.4459695881350807,
|
| 2534 |
+
"learning_rate": 2.1345372911687868e-07,
|
| 2535 |
+
"loss": 1.2719,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.9184320690092604,
|
| 2540 |
+
"grad_norm": 1.4523937909973577,
|
| 2541 |
+
"learning_rate": 2.008368011372136e-07,
|
| 2542 |
+
"loss": 1.2574,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.9209691741722694,
|
| 2547 |
+
"grad_norm": 1.448000545062192,
|
| 2548 |
+
"learning_rate": 1.8859656391188918e-07,
|
| 2549 |
+
"loss": 1.2678,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.9235062793352784,
|
| 2554 |
+
"grad_norm": 1.4574912967654818,
|
| 2555 |
+
"learning_rate": 1.7673397818843696e-07,
|
| 2556 |
+
"loss": 1.2631,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.9260433844982875,
|
| 2561 |
+
"grad_norm": 1.469570266612804,
|
| 2562 |
+
"learning_rate": 1.65249975072172e-07,
|
| 2563 |
+
"loss": 1.2676,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.9285804896612965,
|
| 2568 |
+
"grad_norm": 1.4705072480655184,
|
| 2569 |
+
"learning_rate": 1.5414545595311193e-07,
|
| 2570 |
+
"loss": 1.2363,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.9311175948243055,
|
| 2575 |
+
"grad_norm": 1.469943074464241,
|
| 2576 |
+
"learning_rate": 1.4342129243522241e-07,
|
| 2577 |
+
"loss": 1.2716,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.9336546999873144,
|
| 2582 |
+
"grad_norm": 1.4039691988667693,
|
| 2583 |
+
"learning_rate": 1.3307832626800966e-07,
|
| 2584 |
+
"loss": 1.2674,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.9361918051503235,
|
| 2589 |
+
"grad_norm": 1.4357184274036978,
|
| 2590 |
+
"learning_rate": 1.2311736928044437e-07,
|
| 2591 |
+
"loss": 1.2662,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.9387289103133325,
|
| 2596 |
+
"grad_norm": 1.4198942808558601,
|
| 2597 |
+
"learning_rate": 1.1353920331724666e-07,
|
| 2598 |
+
"loss": 1.2743,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.9412660154763415,
|
| 2603 |
+
"grad_norm": 1.472183542066415,
|
| 2604 |
+
"learning_rate": 1.0434458017751392e-07,
|
| 2605 |
+
"loss": 1.2505,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.9438031206393505,
|
| 2610 |
+
"grad_norm": 1.4530560276575668,
|
| 2611 |
+
"learning_rate": 9.553422155571257e-08,
|
| 2612 |
+
"loss": 1.2637,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.9463402258023595,
|
| 2617 |
+
"grad_norm": 1.4342800198901315,
|
| 2618 |
+
"learning_rate": 8.710881898503276e-08,
|
| 2619 |
+
"loss": 1.2706,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.9488773309653685,
|
| 2624 |
+
"grad_norm": 1.4769111711160674,
|
| 2625 |
+
"learning_rate": 7.906903378310738e-08,
|
| 2626 |
+
"loss": 1.2717,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.9514144361283775,
|
| 2631 |
+
"grad_norm": 1.4434198544006103,
|
| 2632 |
+
"learning_rate": 7.141549700010741e-08,
|
| 2633 |
+
"loss": 1.2764,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.9539515412913865,
|
| 2638 |
+
"grad_norm": 1.3967239883734883,
|
| 2639 |
+
"learning_rate": 6.414880936920665e-08,
|
| 2640 |
+
"loss": 1.2454,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.9564886464543956,
|
| 2645 |
+
"grad_norm": 1.4745766429828837,
|
| 2646 |
+
"learning_rate": 5.726954125943318e-08,
|
| 2647 |
+
"loss": 1.2747,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.9590257516174046,
|
| 2652 |
+
"grad_norm": 1.3354472782196753,
|
| 2653 |
+
"learning_rate": 5.0778232630897536e-08,
|
| 2654 |
+
"loss": 1.2717,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.9615628567804135,
|
| 2659 |
+
"grad_norm": 1.5048063707346293,
|
| 2660 |
+
"learning_rate": 4.4675392992412634e-08,
|
| 2661 |
+
"loss": 1.2728,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.9640999619434225,
|
| 2666 |
+
"grad_norm": 1.4399837174477832,
|
| 2667 |
+
"learning_rate": 3.896150136150134e-08,
|
| 2668 |
+
"loss": 1.2826,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.9666370671064316,
|
| 2673 |
+
"grad_norm": 1.4450380885385077,
|
| 2674 |
+
"learning_rate": 3.3637006226797665e-08,
|
| 2675 |
+
"loss": 1.2534,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.9691741722694406,
|
| 2680 |
+
"grad_norm": 1.35673950609508,
|
| 2681 |
+
"learning_rate": 2.8702325512844908e-08,
|
| 2682 |
+
"loss": 1.2609,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.9717112774324496,
|
| 2687 |
+
"grad_norm": 1.43190405721669,
|
| 2688 |
+
"learning_rate": 2.4157846547292473e-08,
|
| 2689 |
+
"loss": 1.2787,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.9742483825954585,
|
| 2694 |
+
"grad_norm": 1.4245067018508633,
|
| 2695 |
+
"learning_rate": 2.000392603049517e-08,
|
| 2696 |
+
"loss": 1.2665,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.9767854877584676,
|
| 2701 |
+
"grad_norm": 1.4112885660620007,
|
| 2702 |
+
"learning_rate": 1.6240890007510612e-08,
|
| 2703 |
+
"loss": 1.2785,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.9793225929214766,
|
| 2708 |
+
"grad_norm": 1.499341122900986,
|
| 2709 |
+
"learning_rate": 1.286903384251581e-08,
|
| 2710 |
+
"loss": 1.2539,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.9818596980844856,
|
| 2715 |
+
"grad_norm": 1.4494246005853764,
|
| 2716 |
+
"learning_rate": 9.888622195615705e-09,
|
| 2717 |
+
"loss": 1.2725,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.9843968032474946,
|
| 2722 |
+
"grad_norm": 1.421431046100693,
|
| 2723 |
+
"learning_rate": 7.299889002075344e-09,
|
| 2724 |
+
"loss": 1.2726,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.9869339084105037,
|
| 2729 |
+
"grad_norm": 1.4209346862475516,
|
| 2730 |
+
"learning_rate": 5.103037453954573e-09,
|
| 2731 |
+
"loss": 1.2548,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.9894710135735126,
|
| 2736 |
+
"grad_norm": 1.3751824191752333,
|
| 2737 |
+
"learning_rate": 3.2982399841618996e-09,
|
| 2738 |
+
"loss": 1.2859,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.9920081187365216,
|
| 2743 |
+
"grad_norm": 1.4627888810880714,
|
| 2744 |
+
"learning_rate": 1.8856382529192085e-09,
|
| 2745 |
+
"loss": 1.2842,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.9945452238995306,
|
| 2750 |
+
"grad_norm": 1.3905016842842302,
|
| 2751 |
+
"learning_rate": 8.653431366406617e-10,
|
| 2752 |
+
"loss": 1.2447,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.9970823290625397,
|
| 2757 |
+
"grad_norm": 1.5470180096733397,
|
| 2758 |
+
"learning_rate": 2.374347192335424e-10,
|
| 2759 |
+
"loss": 1.2707,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.9996194342255487,
|
| 2764 |
+
"grad_norm": 1.4506027900307656,
|
| 2765 |
+
"learning_rate": 1.9622858088430564e-12,
|
| 2766 |
+
"loss": 1.2737,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.9998731447418495,
|
| 2771 |
+
"step": 3941,
|
| 2772 |
+
"total_flos": 3.7575827488610714e+18,
|
| 2773 |
+
"train_loss": 1.3289946492206504,
|
| 2774 |
+
"train_runtime": 13442.1001,
|
| 2775 |
+
"train_samples_per_second": 37.53,
|
| 2776 |
+
"train_steps_per_second": 0.293
|
| 2777 |
+
}
|
| 2778 |
+
],
|
| 2779 |
+
"logging_steps": 10,
|
| 2780 |
+
"max_steps": 3941,
|
| 2781 |
+
"num_input_tokens_seen": 0,
|
| 2782 |
+
"num_train_epochs": 1,
|
| 2783 |
+
"save_steps": 500,
|
| 2784 |
+
"stateful_callbacks": {
|
| 2785 |
+
"TrainerControl": {
|
| 2786 |
+
"args": {
|
| 2787 |
+
"should_epoch_stop": false,
|
| 2788 |
+
"should_evaluate": false,
|
| 2789 |
+
"should_log": false,
|
| 2790 |
+
"should_save": true,
|
| 2791 |
+
"should_training_stop": true
|
| 2792 |
+
},
|
| 2793 |
+
"attributes": {}
|
| 2794 |
+
}
|
| 2795 |
+
},
|
| 2796 |
+
"total_flos": 3.7575827488610714e+18,
|
| 2797 |
+
"train_batch_size": 8,
|
| 2798 |
+
"trial_name": null,
|
| 2799 |
+
"trial_params": null
|
| 2800 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65cf1f2e9703de4bb06c3bb6408bedea884627a4f53c87c6d91f434bba63ab2
|
| 3 |
+
size 6776
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|