Initial upload of fine-tuned Qwen2VL
Browse files- .gitattributes +1 -0
- added_tokens.json +16 -0
- chat_template.json +3 -0
- config.json +51 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +145 -0
- trainer_state.json +2114 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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 |
+
}
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8960,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen2_vl",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": {
|
| 22 |
+
"mrope_section": [
|
| 23 |
+
16,
|
| 24 |
+
24,
|
| 25 |
+
24
|
| 26 |
+
],
|
| 27 |
+
"rope_type": "default",
|
| 28 |
+
"type": "default"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 1000000.0,
|
| 31 |
+
"sliding_window": 32768,
|
| 32 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"tokenizer_padding_side": "right",
|
| 34 |
+
"torch_dtype": "bfloat16",
|
| 35 |
+
"transformers_version": "4.49.0.dev0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"use_sliding_window": false,
|
| 38 |
+
"video_token_id": 151656,
|
| 39 |
+
"vision_config": {
|
| 40 |
+
"hidden_size": 1536,
|
| 41 |
+
"in_chans": 3,
|
| 42 |
+
"model_type": "qwen2_vl",
|
| 43 |
+
"spatial_patch_size": 14,
|
| 44 |
+
"torch_dtype": "bfloat16"
|
| 45 |
+
},
|
| 46 |
+
"vision_end_token_id": 151653,
|
| 47 |
+
"vision_lr": 2e-06,
|
| 48 |
+
"vision_start_token_id": 151652,
|
| 49 |
+
"vision_token_id": 151654,
|
| 50 |
+
"vocab_size": 151936
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_implementation": "flash_attention_2",
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"temperature": 0.01,
|
| 11 |
+
"top_k": 1,
|
| 12 |
+
"top_p": 0.001,
|
| 13 |
+
"transformers_version": "4.49.0.dev0"
|
| 14 |
+
}
|
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 sha256:46b30261c1754b040809b0e59579ef881d460d659ebb513e5687baed6154ce2b
|
| 3 |
+
size 4418050848
|
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
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
| 3 |
+
size 11420371
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": [
|
| 118 |
+
"<|im_start|>",
|
| 119 |
+
"<|im_end|>",
|
| 120 |
+
"<|object_ref_start|>",
|
| 121 |
+
"<|object_ref_end|>",
|
| 122 |
+
"<|box_start|>",
|
| 123 |
+
"<|box_end|>",
|
| 124 |
+
"<|quad_start|>",
|
| 125 |
+
"<|quad_end|>",
|
| 126 |
+
"<|vision_start|>",
|
| 127 |
+
"<|vision_end|>",
|
| 128 |
+
"<|vision_pad|>",
|
| 129 |
+
"<|image_pad|>",
|
| 130 |
+
"<|video_pad|>"
|
| 131 |
+
],
|
| 132 |
+
"bos_token": null,
|
| 133 |
+
"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 %}",
|
| 134 |
+
"clean_up_tokenization_spaces": false,
|
| 135 |
+
"eos_token": "<|im_end|>",
|
| 136 |
+
"errors": "replace",
|
| 137 |
+
"extra_special_tokens": {},
|
| 138 |
+
"model_max_length": 32768,
|
| 139 |
+
"pad_token": "<|endoftext|>",
|
| 140 |
+
"padding_side": "right",
|
| 141 |
+
"processor_class": "Qwen2VLProcessor",
|
| 142 |
+
"split_special_tokens": false,
|
| 143 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 144 |
+
"unk_token": null
|
| 145 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 296,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0033783783783783786,
|
| 13 |
+
"grad_norm": 36.34380519652221,
|
| 14 |
+
"learning_rate": 1.3333333333333334e-07,
|
| 15 |
+
"loss": 2.2099,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006756756756756757,
|
| 20 |
+
"grad_norm": 43.12351911465486,
|
| 21 |
+
"learning_rate": 2.6666666666666667e-07,
|
| 22 |
+
"loss": 2.4903,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010135135135135136,
|
| 27 |
+
"grad_norm": 33.70796850311383,
|
| 28 |
+
"learning_rate": 4e-07,
|
| 29 |
+
"loss": 2.3356,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.013513513513513514,
|
| 34 |
+
"grad_norm": 31.7090384793013,
|
| 35 |
+
"learning_rate": 5.333333333333333e-07,
|
| 36 |
+
"loss": 2.2996,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016891891891891893,
|
| 41 |
+
"grad_norm": 30.995319786698367,
|
| 42 |
+
"learning_rate": 6.666666666666666e-07,
|
| 43 |
+
"loss": 2.1342,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02027027027027027,
|
| 48 |
+
"grad_norm": 27.19976776248371,
|
| 49 |
+
"learning_rate": 8e-07,
|
| 50 |
+
"loss": 2.1238,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02364864864864865,
|
| 55 |
+
"grad_norm": 49.38079524720527,
|
| 56 |
+
"learning_rate": 9.333333333333333e-07,
|
| 57 |
+
"loss": 2.157,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02702702702702703,
|
| 62 |
+
"grad_norm": 31.886223217594186,
|
| 63 |
+
"learning_rate": 1.0666666666666667e-06,
|
| 64 |
+
"loss": 2.3635,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.030405405405405407,
|
| 69 |
+
"grad_norm": 37.55625594869856,
|
| 70 |
+
"learning_rate": 1.2e-06,
|
| 71 |
+
"loss": 2.1915,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.033783783783783786,
|
| 76 |
+
"grad_norm": 25.123307169130868,
|
| 77 |
+
"learning_rate": 1.3333333333333332e-06,
|
| 78 |
+
"loss": 1.9731,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.037162162162162164,
|
| 83 |
+
"grad_norm": 29.757842745480946,
|
| 84 |
+
"learning_rate": 1.4666666666666665e-06,
|
| 85 |
+
"loss": 2.1449,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04054054054054054,
|
| 90 |
+
"grad_norm": 22.481194702963542,
|
| 91 |
+
"learning_rate": 1.6e-06,
|
| 92 |
+
"loss": 2.0405,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04391891891891892,
|
| 97 |
+
"grad_norm": 30.458380385399302,
|
| 98 |
+
"learning_rate": 1.7333333333333334e-06,
|
| 99 |
+
"loss": 1.9419,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0472972972972973,
|
| 104 |
+
"grad_norm": 20.855918382779514,
|
| 105 |
+
"learning_rate": 1.8666666666666667e-06,
|
| 106 |
+
"loss": 1.9829,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05067567567567568,
|
| 111 |
+
"grad_norm": 21.231075468114902,
|
| 112 |
+
"learning_rate": 2e-06,
|
| 113 |
+
"loss": 1.9225,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05405405405405406,
|
| 118 |
+
"grad_norm": 17.774330943488085,
|
| 119 |
+
"learning_rate": 1.9999375039475274e-06,
|
| 120 |
+
"loss": 1.58,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.057432432432432436,
|
| 125 |
+
"grad_norm": 19.627350580221414,
|
| 126 |
+
"learning_rate": 1.999750023601623e-06,
|
| 127 |
+
"loss": 1.6316,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.060810810810810814,
|
| 132 |
+
"grad_norm": 28.631482442571215,
|
| 133 |
+
"learning_rate": 1.99943758239585e-06,
|
| 134 |
+
"loss": 1.6123,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06418918918918919,
|
| 139 |
+
"grad_norm": 23.803441493571015,
|
| 140 |
+
"learning_rate": 1.9990002193828922e-06,
|
| 141 |
+
"loss": 1.6029,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06756756756756757,
|
| 146 |
+
"grad_norm": 20.03806905922976,
|
| 147 |
+
"learning_rate": 1.998437989229673e-06,
|
| 148 |
+
"loss": 1.4575,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07094594594594594,
|
| 153 |
+
"grad_norm": 21.359976695534908,
|
| 154 |
+
"learning_rate": 1.997750962210523e-06,
|
| 155 |
+
"loss": 1.6098,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07432432432432433,
|
| 160 |
+
"grad_norm": 23.578089050443996,
|
| 161 |
+
"learning_rate": 1.9969392241983957e-06,
|
| 162 |
+
"loss": 1.4387,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0777027027027027,
|
| 167 |
+
"grad_norm": 14.674921238518616,
|
| 168 |
+
"learning_rate": 1.9960028766541334e-06,
|
| 169 |
+
"loss": 1.3932,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08108108108108109,
|
| 174 |
+
"grad_norm": 13.227927089095965,
|
| 175 |
+
"learning_rate": 1.994942036613787e-06,
|
| 176 |
+
"loss": 1.4077,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08445945945945946,
|
| 181 |
+
"grad_norm": 15.574430658611846,
|
| 182 |
+
"learning_rate": 1.993756836673986e-06,
|
| 183 |
+
"loss": 1.4349,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08783783783783784,
|
| 188 |
+
"grad_norm": 19.126636575076304,
|
| 189 |
+
"learning_rate": 1.9924474249753655e-06,
|
| 190 |
+
"loss": 1.5871,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.09121621621621621,
|
| 195 |
+
"grad_norm": 15.53968043351724,
|
| 196 |
+
"learning_rate": 1.9910139651840495e-06,
|
| 197 |
+
"loss": 1.3996,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0945945945945946,
|
| 202 |
+
"grad_norm": 14.495055986002711,
|
| 203 |
+
"learning_rate": 1.9894566364711964e-06,
|
| 204 |
+
"loss": 1.0977,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09797297297297297,
|
| 209 |
+
"grad_norm": 18.132042390935435,
|
| 210 |
+
"learning_rate": 1.9877756334905984e-06,
|
| 211 |
+
"loss": 1.1517,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.10135135135135136,
|
| 216 |
+
"grad_norm": 14.688433551859184,
|
| 217 |
+
"learning_rate": 1.985971166354357e-06,
|
| 218 |
+
"loss": 1.0703,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.10472972972972973,
|
| 223 |
+
"grad_norm": 15.83861615347013,
|
| 224 |
+
"learning_rate": 1.984043460606618e-06,
|
| 225 |
+
"loss": 1.4695,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.10810810810810811,
|
| 230 |
+
"grad_norm": 34.733540858026394,
|
| 231 |
+
"learning_rate": 1.98199275719538e-06,
|
| 232 |
+
"loss": 1.2256,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11148648648648649,
|
| 237 |
+
"grad_norm": 15.846299326934696,
|
| 238 |
+
"learning_rate": 1.97981931244238e-06,
|
| 239 |
+
"loss": 1.1088,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11486486486486487,
|
| 244 |
+
"grad_norm": 22.384010094966825,
|
| 245 |
+
"learning_rate": 1.977523398011052e-06,
|
| 246 |
+
"loss": 1.2592,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11824324324324324,
|
| 251 |
+
"grad_norm": 39.18577419559952,
|
| 252 |
+
"learning_rate": 1.9751053008725736e-06,
|
| 253 |
+
"loss": 1.194,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.12162162162162163,
|
| 258 |
+
"grad_norm": 14.647449051382507,
|
| 259 |
+
"learning_rate": 1.972565323269996e-06,
|
| 260 |
+
"loss": 1.1682,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.125,
|
| 265 |
+
"grad_norm": 16.03811654501116,
|
| 266 |
+
"learning_rate": 1.9699037826804664e-06,
|
| 267 |
+
"loss": 1.401,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12837837837837837,
|
| 272 |
+
"grad_norm": 16.214806020128417,
|
| 273 |
+
"learning_rate": 1.9671210117755453e-06,
|
| 274 |
+
"loss": 1.2358,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.13175675675675674,
|
| 279 |
+
"grad_norm": 17.907345123987813,
|
| 280 |
+
"learning_rate": 1.9642173583796264e-06,
|
| 281 |
+
"loss": 1.1862,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13513513513513514,
|
| 286 |
+
"grad_norm": 11.043652460472568,
|
| 287 |
+
"learning_rate": 1.9611931854264588e-06,
|
| 288 |
+
"loss": 1.1875,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13851351351351351,
|
| 293 |
+
"grad_norm": 13.159525091508891,
|
| 294 |
+
"learning_rate": 1.958048870913786e-06,
|
| 295 |
+
"loss": 1.343,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.14189189189189189,
|
| 300 |
+
"grad_norm": 19.11958542393229,
|
| 301 |
+
"learning_rate": 1.9547848078560974e-06,
|
| 302 |
+
"loss": 1.1634,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14527027027027026,
|
| 307 |
+
"grad_norm": 13.966803976520843,
|
| 308 |
+
"learning_rate": 1.9514014042355057e-06,
|
| 309 |
+
"loss": 1.416,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14864864864864866,
|
| 314 |
+
"grad_norm": 16.13133392280448,
|
| 315 |
+
"learning_rate": 1.9478990829507503e-06,
|
| 316 |
+
"loss": 1.0926,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.15202702702702703,
|
| 321 |
+
"grad_norm": 14.087543401416761,
|
| 322 |
+
"learning_rate": 1.9442782817643423e-06,
|
| 323 |
+
"loss": 1.2186,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1554054054054054,
|
| 328 |
+
"grad_norm": 13.891194600676148,
|
| 329 |
+
"learning_rate": 1.940539453247842e-06,
|
| 330 |
+
"loss": 1.275,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15878378378378377,
|
| 335 |
+
"grad_norm": 13.751120445570239,
|
| 336 |
+
"learning_rate": 1.936683064725297e-06,
|
| 337 |
+
"loss": 1.2448,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.16216216216216217,
|
| 342 |
+
"grad_norm": 10.621288857033353,
|
| 343 |
+
"learning_rate": 1.9327095982148254e-06,
|
| 344 |
+
"loss": 1.2423,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16554054054054054,
|
| 349 |
+
"grad_norm": 20.30123153553206,
|
| 350 |
+
"learning_rate": 1.928619550368371e-06,
|
| 351 |
+
"loss": 1.2193,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16891891891891891,
|
| 356 |
+
"grad_norm": 15.94549584448776,
|
| 357 |
+
"learning_rate": 1.9244134324096223e-06,
|
| 358 |
+
"loss": 1.123,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.17229729729729729,
|
| 363 |
+
"grad_norm": 12.893089830970485,
|
| 364 |
+
"learning_rate": 1.9200917700701174e-06,
|
| 365 |
+
"loss": 1.0987,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.17567567567567569,
|
| 370 |
+
"grad_norm": 13.000755551355759,
|
| 371 |
+
"learning_rate": 1.915655103523529e-06,
|
| 372 |
+
"loss": 1.2287,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.17905405405405406,
|
| 377 |
+
"grad_norm": 14.512922569263976,
|
| 378 |
+
"learning_rate": 1.9111039873181477e-06,
|
| 379 |
+
"loss": 1.3532,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.18243243243243243,
|
| 384 |
+
"grad_norm": 10.37592278441411,
|
| 385 |
+
"learning_rate": 1.9064389903075675e-06,
|
| 386 |
+
"loss": 1.1853,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1858108108108108,
|
| 391 |
+
"grad_norm": 11.492056848653965,
|
| 392 |
+
"learning_rate": 1.9016606955795846e-06,
|
| 393 |
+
"loss": 1.1262,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1891891891891892,
|
| 398 |
+
"grad_norm": 10.290059803109717,
|
| 399 |
+
"learning_rate": 1.8967697003833154e-06,
|
| 400 |
+
"loss": 1.2707,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.19256756756756757,
|
| 405 |
+
"grad_norm": 15.051936191343389,
|
| 406 |
+
"learning_rate": 1.8917666160545443e-06,
|
| 407 |
+
"loss": 1.2969,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.19594594594594594,
|
| 412 |
+
"grad_norm": 10.869602488951811,
|
| 413 |
+
"learning_rate": 1.8866520679393125e-06,
|
| 414 |
+
"loss": 1.2578,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19932432432432431,
|
| 419 |
+
"grad_norm": 8.613911997434,
|
| 420 |
+
"learning_rate": 1.8814266953157553e-06,
|
| 421 |
+
"loss": 1.1504,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.20270270270270271,
|
| 426 |
+
"grad_norm": 21.935573372865576,
|
| 427 |
+
"learning_rate": 1.876091151314196e-06,
|
| 428 |
+
"loss": 1.187,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.20608108108108109,
|
| 433 |
+
"grad_norm": 10.017603653888672,
|
| 434 |
+
"learning_rate": 1.8706461028355102e-06,
|
| 435 |
+
"loss": 1.0335,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.20945945945945946,
|
| 440 |
+
"grad_norm": 10.309662768509451,
|
| 441 |
+
"learning_rate": 1.865092230467769e-06,
|
| 442 |
+
"loss": 1.2194,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.21283783783783783,
|
| 447 |
+
"grad_norm": 22.827754584922435,
|
| 448 |
+
"learning_rate": 1.85943022840117e-06,
|
| 449 |
+
"loss": 0.9855,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.21621621621621623,
|
| 454 |
+
"grad_norm": 17.84035229484401,
|
| 455 |
+
"learning_rate": 1.8536608043412696e-06,
|
| 456 |
+
"loss": 1.251,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2195945945945946,
|
| 461 |
+
"grad_norm": 14.461128388669215,
|
| 462 |
+
"learning_rate": 1.8477846794205257e-06,
|
| 463 |
+
"loss": 1.1054,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.22297297297297297,
|
| 468 |
+
"grad_norm": 8.992434654243354,
|
| 469 |
+
"learning_rate": 1.841802588108161e-06,
|
| 470 |
+
"loss": 1.0763,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.22635135135135134,
|
| 475 |
+
"grad_norm": 29.874670396525875,
|
| 476 |
+
"learning_rate": 1.8357152781183601e-06,
|
| 477 |
+
"loss": 1.1346,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.22972972972972974,
|
| 482 |
+
"grad_norm": 14.215939420951964,
|
| 483 |
+
"learning_rate": 1.829523510316813e-06,
|
| 484 |
+
"loss": 1.2661,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.23310810810810811,
|
| 489 |
+
"grad_norm": 12.702867889510674,
|
| 490 |
+
"learning_rate": 1.82322805862561e-06,
|
| 491 |
+
"loss": 1.3305,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.23648648648648649,
|
| 496 |
+
"grad_norm": 12.166026031104051,
|
| 497 |
+
"learning_rate": 1.8168297099265092e-06,
|
| 498 |
+
"loss": 1.194,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.23986486486486486,
|
| 503 |
+
"grad_norm": 9.23387590487161,
|
| 504 |
+
"learning_rate": 1.8103292639625835e-06,
|
| 505 |
+
"loss": 1.175,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.24324324324324326,
|
| 510 |
+
"grad_norm": 13.140233293728443,
|
| 511 |
+
"learning_rate": 1.8037275332382564e-06,
|
| 512 |
+
"loss": 1.091,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.24662162162162163,
|
| 517 |
+
"grad_norm": 12.516098212551523,
|
| 518 |
+
"learning_rate": 1.7970253429177476e-06,
|
| 519 |
+
"loss": 1.0048,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.25,
|
| 524 |
+
"grad_norm": 12.543922196451009,
|
| 525 |
+
"learning_rate": 1.790223530721933e-06,
|
| 526 |
+
"loss": 1.2212,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2533783783783784,
|
| 531 |
+
"grad_norm": 12.59410138415326,
|
| 532 |
+
"learning_rate": 1.7833229468236366e-06,
|
| 533 |
+
"loss": 0.9638,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.25675675675675674,
|
| 538 |
+
"grad_norm": 11.269394793559412,
|
| 539 |
+
"learning_rate": 1.7763244537413649e-06,
|
| 540 |
+
"loss": 1.3276,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.26013513513513514,
|
| 545 |
+
"grad_norm": 12.194980274405472,
|
| 546 |
+
"learning_rate": 1.7692289262314999e-06,
|
| 547 |
+
"loss": 1.2024,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.2635135135135135,
|
| 552 |
+
"grad_norm": 11.745939711228226,
|
| 553 |
+
"learning_rate": 1.7620372511789604e-06,
|
| 554 |
+
"loss": 1.1291,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2668918918918919,
|
| 559 |
+
"grad_norm": 13.359122311655632,
|
| 560 |
+
"learning_rate": 1.7547503274863496e-06,
|
| 561 |
+
"loss": 1.2605,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2702702702702703,
|
| 566 |
+
"grad_norm": 14.106860208081626,
|
| 567 |
+
"learning_rate": 1.7473690659615985e-06,
|
| 568 |
+
"loss": 0.9653,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.27364864864864863,
|
| 573 |
+
"grad_norm": 11.571558992959682,
|
| 574 |
+
"learning_rate": 1.739894389204122e-06,
|
| 575 |
+
"loss": 1.0096,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.27702702702702703,
|
| 580 |
+
"grad_norm": 10.630802336779617,
|
| 581 |
+
"learning_rate": 1.732327231489502e-06,
|
| 582 |
+
"loss": 0.9956,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.28040540540540543,
|
| 587 |
+
"grad_norm": 9.425350956927328,
|
| 588 |
+
"learning_rate": 1.7246685386527096e-06,
|
| 589 |
+
"loss": 1.2427,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.28378378378378377,
|
| 594 |
+
"grad_norm": 10.454341153901584,
|
| 595 |
+
"learning_rate": 1.7169192679698834e-06,
|
| 596 |
+
"loss": 1.3052,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.28716216216216217,
|
| 601 |
+
"grad_norm": 17.663808509868556,
|
| 602 |
+
"learning_rate": 1.7090803880386782e-06,
|
| 603 |
+
"loss": 1.0632,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.2905405405405405,
|
| 608 |
+
"grad_norm": 10.721021803772425,
|
| 609 |
+
"learning_rate": 1.7011528786571966e-06,
|
| 610 |
+
"loss": 1.0583,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2939189189189189,
|
| 615 |
+
"grad_norm": 10.644943223946195,
|
| 616 |
+
"learning_rate": 1.6931377307015237e-06,
|
| 617 |
+
"loss": 1.1637,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2972972972972973,
|
| 622 |
+
"grad_norm": 13.752602696728736,
|
| 623 |
+
"learning_rate": 1.6850359460018735e-06,
|
| 624 |
+
"loss": 1.096,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.30067567567567566,
|
| 629 |
+
"grad_norm": 11.397981680389693,
|
| 630 |
+
"learning_rate": 1.6768485372173696e-06,
|
| 631 |
+
"loss": 1.0631,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.30405405405405406,
|
| 636 |
+
"grad_norm": 13.659048080662533,
|
| 637 |
+
"learning_rate": 1.6685765277094698e-06,
|
| 638 |
+
"loss": 1.2796,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.30743243243243246,
|
| 643 |
+
"grad_norm": 13.560625259375408,
|
| 644 |
+
"learning_rate": 1.6602209514140548e-06,
|
| 645 |
+
"loss": 1.016,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3108108108108108,
|
| 650 |
+
"grad_norm": 10.86346218035453,
|
| 651 |
+
"learning_rate": 1.651782852712194e-06,
|
| 652 |
+
"loss": 1.1796,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3141891891891892,
|
| 657 |
+
"grad_norm": 21.596462888345016,
|
| 658 |
+
"learning_rate": 1.6432632862996055e-06,
|
| 659 |
+
"loss": 1.2562,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.31756756756756754,
|
| 664 |
+
"grad_norm": 8.508599025148868,
|
| 665 |
+
"learning_rate": 1.6346633170548287e-06,
|
| 666 |
+
"loss": 1.0791,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.32094594594594594,
|
| 671 |
+
"grad_norm": 11.214841198519808,
|
| 672 |
+
"learning_rate": 1.6259840199061215e-06,
|
| 673 |
+
"loss": 1.1807,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.32432432432432434,
|
| 678 |
+
"grad_norm": 11.436685584271823,
|
| 679 |
+
"learning_rate": 1.6172264796971047e-06,
|
| 680 |
+
"loss": 1.1592,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3277027027027027,
|
| 685 |
+
"grad_norm": 12.743661407095667,
|
| 686 |
+
"learning_rate": 1.6083917910511626e-06,
|
| 687 |
+
"loss": 1.0503,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.3310810810810811,
|
| 692 |
+
"grad_norm": 11.496627678191913,
|
| 693 |
+
"learning_rate": 1.5994810582346258e-06,
|
| 694 |
+
"loss": 1.2596,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.3344594594594595,
|
| 699 |
+
"grad_norm": 13.004007245231266,
|
| 700 |
+
"learning_rate": 1.5904953950187457e-06,
|
| 701 |
+
"loss": 1.0893,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.33783783783783783,
|
| 706 |
+
"grad_norm": 16.167110670859195,
|
| 707 |
+
"learning_rate": 1.5814359245404817e-06,
|
| 708 |
+
"loss": 0.9954,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.34121621621621623,
|
| 713 |
+
"grad_norm": 10.40481921619085,
|
| 714 |
+
"learning_rate": 1.572303779162119e-06,
|
| 715 |
+
"loss": 1.1096,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.34459459459459457,
|
| 720 |
+
"grad_norm": 14.377831724975822,
|
| 721 |
+
"learning_rate": 1.5631001003297305e-06,
|
| 722 |
+
"loss": 1.2811,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.34797297297297297,
|
| 727 |
+
"grad_norm": 39.37962132100598,
|
| 728 |
+
"learning_rate": 1.5538260384305073e-06,
|
| 729 |
+
"loss": 1.2193,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.35135135135135137,
|
| 734 |
+
"grad_norm": 10.968455837163882,
|
| 735 |
+
"learning_rate": 1.5444827526489675e-06,
|
| 736 |
+
"loss": 1.1259,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.3547297297297297,
|
| 741 |
+
"grad_norm": 21.6055293650324,
|
| 742 |
+
"learning_rate": 1.5350714108220673e-06,
|
| 743 |
+
"loss": 1.2394,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.3581081081081081,
|
| 748 |
+
"grad_norm": 12.376118934560434,
|
| 749 |
+
"learning_rate": 1.5255931892932333e-06,
|
| 750 |
+
"loss": 1.0541,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.3614864864864865,
|
| 755 |
+
"grad_norm": 15.40253327518173,
|
| 756 |
+
"learning_rate": 1.516049272765324e-06,
|
| 757 |
+
"loss": 1.1722,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.36486486486486486,
|
| 762 |
+
"grad_norm": 11.208292608197336,
|
| 763 |
+
"learning_rate": 1.506440854152557e-06,
|
| 764 |
+
"loss": 1.1011,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.36824324324324326,
|
| 769 |
+
"grad_norm": 10.250796198350079,
|
| 770 |
+
"learning_rate": 1.4967691344313992e-06,
|
| 771 |
+
"loss": 0.874,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.3716216216216216,
|
| 776 |
+
"grad_norm": 10.603118241909707,
|
| 777 |
+
"learning_rate": 1.487035322490457e-06,
|
| 778 |
+
"loss": 0.997,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.375,
|
| 783 |
+
"grad_norm": 13.675717972507808,
|
| 784 |
+
"learning_rate": 1.4772406349793743e-06,
|
| 785 |
+
"loss": 1.1241,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.3783783783783784,
|
| 790 |
+
"grad_norm": 11.799276261636487,
|
| 791 |
+
"learning_rate": 1.46738629615676e-06,
|
| 792 |
+
"loss": 1.0529,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.38175675675675674,
|
| 797 |
+
"grad_norm": 11.919760841402619,
|
| 798 |
+
"learning_rate": 1.457473537737167e-06,
|
| 799 |
+
"loss": 1.149,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.38513513513513514,
|
| 804 |
+
"grad_norm": 15.737523035261258,
|
| 805 |
+
"learning_rate": 1.4475035987371353e-06,
|
| 806 |
+
"loss": 1.1189,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3885135135135135,
|
| 811 |
+
"grad_norm": 14.60675782295418,
|
| 812 |
+
"learning_rate": 1.437477725320327e-06,
|
| 813 |
+
"loss": 1.0883,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.3918918918918919,
|
| 818 |
+
"grad_norm": 21.750751609412216,
|
| 819 |
+
"learning_rate": 1.4273971706417647e-06,
|
| 820 |
+
"loss": 1.0055,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3952702702702703,
|
| 825 |
+
"grad_norm": 17.648998366903356,
|
| 826 |
+
"learning_rate": 1.4172631946911961e-06,
|
| 827 |
+
"loss": 1.2696,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.39864864864864863,
|
| 832 |
+
"grad_norm": 12.715699674470592,
|
| 833 |
+
"learning_rate": 1.4070770641356069e-06,
|
| 834 |
+
"loss": 1.1822,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.40202702702702703,
|
| 839 |
+
"grad_norm": 16.775298402210872,
|
| 840 |
+
"learning_rate": 1.3968400521608968e-06,
|
| 841 |
+
"loss": 1.0353,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.40540540540540543,
|
| 846 |
+
"grad_norm": 9.67872096145976,
|
| 847 |
+
"learning_rate": 1.3865534383127405e-06,
|
| 848 |
+
"loss": 1.0151,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.40878378378378377,
|
| 853 |
+
"grad_norm": 15.090462871849569,
|
| 854 |
+
"learning_rate": 1.3762185083366556e-06,
|
| 855 |
+
"loss": 1.2723,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.41216216216216217,
|
| 860 |
+
"grad_norm": 12.054991581222485,
|
| 861 |
+
"learning_rate": 1.3658365540172947e-06,
|
| 862 |
+
"loss": 1.1311,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.4155405405405405,
|
| 867 |
+
"grad_norm": 46.96463144064033,
|
| 868 |
+
"learning_rate": 1.3554088730169812e-06,
|
| 869 |
+
"loss": 1.0084,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.4189189189189189,
|
| 874 |
+
"grad_norm": 15.379435297216096,
|
| 875 |
+
"learning_rate": 1.3449367687135134e-06,
|
| 876 |
+
"loss": 1.0913,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4222972972972973,
|
| 881 |
+
"grad_norm": 14.098474644361811,
|
| 882 |
+
"learning_rate": 1.334421550037251e-06,
|
| 883 |
+
"loss": 0.8864,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.42567567567567566,
|
| 888 |
+
"grad_norm": 14.097731558642154,
|
| 889 |
+
"learning_rate": 1.3238645313075104e-06,
|
| 890 |
+
"loss": 1.1372,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.42905405405405406,
|
| 895 |
+
"grad_norm": 12.81244235157509,
|
| 896 |
+
"learning_rate": 1.3132670320682849e-06,
|
| 897 |
+
"loss": 0.9365,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.43243243243243246,
|
| 902 |
+
"grad_norm": 18.821215912404902,
|
| 903 |
+
"learning_rate": 1.3026303769233111e-06,
|
| 904 |
+
"loss": 1.1202,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.4358108108108108,
|
| 909 |
+
"grad_norm": 11.671699264939019,
|
| 910 |
+
"learning_rate": 1.2919558953705054e-06,
|
| 911 |
+
"loss": 0.9788,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.4391891891891892,
|
| 916 |
+
"grad_norm": 19.68649954082118,
|
| 917 |
+
"learning_rate": 1.2812449216357862e-06,
|
| 918 |
+
"loss": 1.1731,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.44256756756756754,
|
| 923 |
+
"grad_norm": 13.043364628647394,
|
| 924 |
+
"learning_rate": 1.2704987945063068e-06,
|
| 925 |
+
"loss": 1.1086,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.44594594594594594,
|
| 930 |
+
"grad_norm": 20.30201878405142,
|
| 931 |
+
"learning_rate": 1.2597188571631168e-06,
|
| 932 |
+
"loss": 1.2371,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.44932432432432434,
|
| 937 |
+
"grad_norm": 20.364065829812596,
|
| 938 |
+
"learning_rate": 1.2489064570132764e-06,
|
| 939 |
+
"loss": 1.1033,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.4527027027027027,
|
| 944 |
+
"grad_norm": 10.820647705204983,
|
| 945 |
+
"learning_rate": 1.238062945521439e-06,
|
| 946 |
+
"loss": 1.0268,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.4560810810810811,
|
| 951 |
+
"grad_norm": 10.54163930117814,
|
| 952 |
+
"learning_rate": 1.227189678040932e-06,
|
| 953 |
+
"loss": 1.0175,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.4594594594594595,
|
| 958 |
+
"grad_norm": 32.827329101325944,
|
| 959 |
+
"learning_rate": 1.2162880136443445e-06,
|
| 960 |
+
"loss": 1.0376,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.46283783783783783,
|
| 965 |
+
"grad_norm": 9.227403119787086,
|
| 966 |
+
"learning_rate": 1.2053593149536574e-06,
|
| 967 |
+
"loss": 1.0051,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.46621621621621623,
|
| 972 |
+
"grad_norm": 10.894935911975288,
|
| 973 |
+
"learning_rate": 1.1944049479699243e-06,
|
| 974 |
+
"loss": 0.938,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.46959459459459457,
|
| 979 |
+
"grad_norm": 12.137253329529186,
|
| 980 |
+
"learning_rate": 1.1834262819025326e-06,
|
| 981 |
+
"loss": 1.1787,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.47297297297297297,
|
| 986 |
+
"grad_norm": 9.069326074607018,
|
| 987 |
+
"learning_rate": 1.1724246889980636e-06,
|
| 988 |
+
"loss": 1.1851,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.47635135135135137,
|
| 993 |
+
"grad_norm": 19.148513034329444,
|
| 994 |
+
"learning_rate": 1.1614015443687722e-06,
|
| 995 |
+
"loss": 1.0901,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.4797297297297297,
|
| 1000 |
+
"grad_norm": 11.333021861338224,
|
| 1001 |
+
"learning_rate": 1.1503582258207087e-06,
|
| 1002 |
+
"loss": 1.2489,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.4831081081081081,
|
| 1007 |
+
"grad_norm": 21.947337127900077,
|
| 1008 |
+
"learning_rate": 1.1392961136815045e-06,
|
| 1009 |
+
"loss": 1.1378,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4864864864864865,
|
| 1014 |
+
"grad_norm": 11.072312577652738,
|
| 1015 |
+
"learning_rate": 1.12821659062784e-06,
|
| 1016 |
+
"loss": 1.0135,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.48986486486486486,
|
| 1021 |
+
"grad_norm": 16.58390272135636,
|
| 1022 |
+
"learning_rate": 1.1171210415126246e-06,
|
| 1023 |
+
"loss": 1.0018,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.49324324324324326,
|
| 1028 |
+
"grad_norm": 14.490944986218912,
|
| 1029 |
+
"learning_rate": 1.106010853191897e-06,
|
| 1030 |
+
"loss": 1.2411,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.4966216216216216,
|
| 1035 |
+
"grad_norm": 13.232211431876486,
|
| 1036 |
+
"learning_rate": 1.094887414351482e-06,
|
| 1037 |
+
"loss": 1.0919,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.5,
|
| 1042 |
+
"grad_norm": 11.52150090382748,
|
| 1043 |
+
"learning_rate": 1.0837521153334141e-06,
|
| 1044 |
+
"loss": 0.9432,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.5033783783783784,
|
| 1049 |
+
"grad_norm": 11.102200287695098,
|
| 1050 |
+
"learning_rate": 1.0726063479621572e-06,
|
| 1051 |
+
"loss": 0.9707,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.5067567567567568,
|
| 1056 |
+
"grad_norm": 11.804415443759472,
|
| 1057 |
+
"learning_rate": 1.0614515053706365e-06,
|
| 1058 |
+
"loss": 1.1248,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.5101351351351351,
|
| 1063 |
+
"grad_norm": 15.516856282700303,
|
| 1064 |
+
"learning_rate": 1.0502889818261073e-06,
|
| 1065 |
+
"loss": 1.2424,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.5135135135135135,
|
| 1070 |
+
"grad_norm": 9.407255284950214,
|
| 1071 |
+
"learning_rate": 1.039120172555884e-06,
|
| 1072 |
+
"loss": 1.0424,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.5168918918918919,
|
| 1077 |
+
"grad_norm": 17.961821954633418,
|
| 1078 |
+
"learning_rate": 1.0279464735729471e-06,
|
| 1079 |
+
"loss": 1.0045,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.5202702702702703,
|
| 1084 |
+
"grad_norm": 11.337800562263089,
|
| 1085 |
+
"learning_rate": 1.0167692815014526e-06,
|
| 1086 |
+
"loss": 1.1381,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.5236486486486487,
|
| 1091 |
+
"grad_norm": 12.033824811722921,
|
| 1092 |
+
"learning_rate": 1.0055899934021649e-06,
|
| 1093 |
+
"loss": 1.2202,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.527027027027027,
|
| 1098 |
+
"grad_norm": 15.252188339802737,
|
| 1099 |
+
"learning_rate": 9.944100065978348e-07,
|
| 1100 |
+
"loss": 1.0269,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5304054054054054,
|
| 1105 |
+
"grad_norm": 18.646832631473462,
|
| 1106 |
+
"learning_rate": 9.832307184985473e-07,
|
| 1107 |
+
"loss": 1.0812,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.5337837837837838,
|
| 1112 |
+
"grad_norm": 12.805833037823682,
|
| 1113 |
+
"learning_rate": 9.720535264270528e-07,
|
| 1114 |
+
"loss": 1.0502,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.5371621621621622,
|
| 1119 |
+
"grad_norm": 12.134333071934153,
|
| 1120 |
+
"learning_rate": 9.608798274441159e-07,
|
| 1121 |
+
"loss": 1.1803,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.5405405405405406,
|
| 1126 |
+
"grad_norm": 10.649811180920313,
|
| 1127 |
+
"learning_rate": 9.497110181738927e-07,
|
| 1128 |
+
"loss": 0.9571,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.543918918918919,
|
| 1133 |
+
"grad_norm": 146.33125718065153,
|
| 1134 |
+
"learning_rate": 9.385484946293636e-07,
|
| 1135 |
+
"loss": 0.9618,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.5472972972972973,
|
| 1140 |
+
"grad_norm": 11.299402827185753,
|
| 1141 |
+
"learning_rate": 9.273936520378427e-07,
|
| 1142 |
+
"loss": 0.9918,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.5506756756756757,
|
| 1147 |
+
"grad_norm": 16.15355106972394,
|
| 1148 |
+
"learning_rate": 9.16247884666586e-07,
|
| 1149 |
+
"loss": 1.0062,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.5540540540540541,
|
| 1154 |
+
"grad_norm": 10.622416071908305,
|
| 1155 |
+
"learning_rate": 9.051125856485182e-07,
|
| 1156 |
+
"loss": 0.9373,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.5574324324324325,
|
| 1161 |
+
"grad_norm": 11.592528932394504,
|
| 1162 |
+
"learning_rate": 8.939891468081033e-07,
|
| 1163 |
+
"loss": 1.154,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.5608108108108109,
|
| 1168 |
+
"grad_norm": 11.485409936611834,
|
| 1169 |
+
"learning_rate": 8.828789584873753e-07,
|
| 1170 |
+
"loss": 0.9575,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.5641891891891891,
|
| 1175 |
+
"grad_norm": 10.772881325566155,
|
| 1176 |
+
"learning_rate": 8.717834093721596e-07,
|
| 1177 |
+
"loss": 1.0965,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5675675675675675,
|
| 1182 |
+
"grad_norm": 11.351726294590271,
|
| 1183 |
+
"learning_rate": 8.607038863184957e-07,
|
| 1184 |
+
"loss": 0.8089,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.5709459459459459,
|
| 1189 |
+
"grad_norm": 12.523379929152632,
|
| 1190 |
+
"learning_rate": 8.496417741792912e-07,
|
| 1191 |
+
"loss": 1.135,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.5743243243243243,
|
| 1196 |
+
"grad_norm": 8.660990496307493,
|
| 1197 |
+
"learning_rate": 8.38598455631228e-07,
|
| 1198 |
+
"loss": 1.0962,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5777027027027027,
|
| 1203 |
+
"grad_norm": 10.20650403354362,
|
| 1204 |
+
"learning_rate": 8.275753110019366e-07,
|
| 1205 |
+
"loss": 0.9328,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.581081081081081,
|
| 1210 |
+
"grad_norm": 9.932032967865965,
|
| 1211 |
+
"learning_rate": 8.165737180974677e-07,
|
| 1212 |
+
"loss": 1.0781,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5844594594594594,
|
| 1217 |
+
"grad_norm": 16.554523058533654,
|
| 1218 |
+
"learning_rate": 8.05595052030076e-07,
|
| 1219 |
+
"loss": 1.0595,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.5878378378378378,
|
| 1224 |
+
"grad_norm": 12.257448261024532,
|
| 1225 |
+
"learning_rate": 7.946406850463428e-07,
|
| 1226 |
+
"loss": 1.0251,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.5912162162162162,
|
| 1231 |
+
"grad_norm": 25.519007157939814,
|
| 1232 |
+
"learning_rate": 7.837119863556553e-07,
|
| 1233 |
+
"loss": 0.9365,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5945945945945946,
|
| 1238 |
+
"grad_norm": 15.504936576666402,
|
| 1239 |
+
"learning_rate": 7.728103219590681e-07,
|
| 1240 |
+
"loss": 1.0767,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.597972972972973,
|
| 1245 |
+
"grad_norm": 11.120206251286776,
|
| 1246 |
+
"learning_rate": 7.619370544785607e-07,
|
| 1247 |
+
"loss": 1.1879,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.6013513513513513,
|
| 1252 |
+
"grad_norm": 13.01469909954165,
|
| 1253 |
+
"learning_rate": 7.510935429867237e-07,
|
| 1254 |
+
"loss": 1.1855,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.6047297297297297,
|
| 1259 |
+
"grad_norm": 10.891606687549986,
|
| 1260 |
+
"learning_rate": 7.402811428368832e-07,
|
| 1261 |
+
"loss": 1.1117,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.6081081081081081,
|
| 1266 |
+
"grad_norm": 12.726234096413455,
|
| 1267 |
+
"learning_rate": 7.295012054936934e-07,
|
| 1268 |
+
"loss": 1.0635,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.6114864864864865,
|
| 1273 |
+
"grad_norm": 14.081931562212292,
|
| 1274 |
+
"learning_rate": 7.18755078364214e-07,
|
| 1275 |
+
"loss": 1.0642,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.6148648648648649,
|
| 1280 |
+
"grad_norm": 11.818688785165225,
|
| 1281 |
+
"learning_rate": 7.080441046294947e-07,
|
| 1282 |
+
"loss": 0.8723,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.6182432432432432,
|
| 1287 |
+
"grad_norm": 12.519818734380365,
|
| 1288 |
+
"learning_rate": 6.97369623076689e-07,
|
| 1289 |
+
"loss": 0.9427,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.6216216216216216,
|
| 1294 |
+
"grad_norm": 15.41545750080243,
|
| 1295 |
+
"learning_rate": 6.867329679317155e-07,
|
| 1296 |
+
"loss": 1.2919,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.625,
|
| 1301 |
+
"grad_norm": 13.611860653642745,
|
| 1302 |
+
"learning_rate": 6.761354686924893e-07,
|
| 1303 |
+
"loss": 1.2166,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.6283783783783784,
|
| 1308 |
+
"grad_norm": 15.729242445078606,
|
| 1309 |
+
"learning_rate": 6.655784499627491e-07,
|
| 1310 |
+
"loss": 0.9994,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.6317567567567568,
|
| 1315 |
+
"grad_norm": 104.86681001036531,
|
| 1316 |
+
"learning_rate": 6.550632312864868e-07,
|
| 1317 |
+
"loss": 1.0512,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.6351351351351351,
|
| 1322 |
+
"grad_norm": 13.568567585972945,
|
| 1323 |
+
"learning_rate": 6.445911269830188e-07,
|
| 1324 |
+
"loss": 1.0875,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6385135135135135,
|
| 1329 |
+
"grad_norm": 16.847818194342956,
|
| 1330 |
+
"learning_rate": 6.341634459827052e-07,
|
| 1331 |
+
"loss": 1.141,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.6418918918918919,
|
| 1336 |
+
"grad_norm": 12.269547242713127,
|
| 1337 |
+
"learning_rate": 6.237814916633444e-07,
|
| 1338 |
+
"loss": 1.0208,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.6452702702702703,
|
| 1343 |
+
"grad_norm": 11.616524689542663,
|
| 1344 |
+
"learning_rate": 6.134465616872597e-07,
|
| 1345 |
+
"loss": 1.1168,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.6486486486486487,
|
| 1350 |
+
"grad_norm": 10.724072940235493,
|
| 1351 |
+
"learning_rate": 6.031599478391034e-07,
|
| 1352 |
+
"loss": 1.169,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.652027027027027,
|
| 1357 |
+
"grad_norm": 13.015769208492884,
|
| 1358 |
+
"learning_rate": 5.929229358643931e-07,
|
| 1359 |
+
"loss": 1.0416,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.6554054054054054,
|
| 1364 |
+
"grad_norm": 9.990134594775737,
|
| 1365 |
+
"learning_rate": 5.827368053088042e-07,
|
| 1366 |
+
"loss": 0.9535,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.6587837837837838,
|
| 1371 |
+
"grad_norm": 13.177572331525829,
|
| 1372 |
+
"learning_rate": 5.726028293582355e-07,
|
| 1373 |
+
"loss": 1.0943,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.6621621621621622,
|
| 1378 |
+
"grad_norm": 10.58458317529772,
|
| 1379 |
+
"learning_rate": 5.625222746796729e-07,
|
| 1380 |
+
"loss": 1.0295,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.6655405405405406,
|
| 1385 |
+
"grad_norm": 13.024298303825404,
|
| 1386 |
+
"learning_rate": 5.524964012628648e-07,
|
| 1387 |
+
"loss": 1.2265,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.668918918918919,
|
| 1392 |
+
"grad_norm": 35.7979648422802,
|
| 1393 |
+
"learning_rate": 5.425264622628329e-07,
|
| 1394 |
+
"loss": 1.1297,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.6722972972972973,
|
| 1399 |
+
"grad_norm": 13.328769350224942,
|
| 1400 |
+
"learning_rate": 5.326137038432398e-07,
|
| 1401 |
+
"loss": 1.1642,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.6756756756756757,
|
| 1406 |
+
"grad_norm": 10.446275120566474,
|
| 1407 |
+
"learning_rate": 5.227593650206257e-07,
|
| 1408 |
+
"loss": 1.1484,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.6790540540540541,
|
| 1413 |
+
"grad_norm": 14.097446388563373,
|
| 1414 |
+
"learning_rate": 5.129646775095431e-07,
|
| 1415 |
+
"loss": 0.9661,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.6824324324324325,
|
| 1420 |
+
"grad_norm": 10.169592050671367,
|
| 1421 |
+
"learning_rate": 5.032308655686011e-07,
|
| 1422 |
+
"loss": 1.1192,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6858108108108109,
|
| 1427 |
+
"grad_norm": 29.867456180681256,
|
| 1428 |
+
"learning_rate": 4.935591458474433e-07,
|
| 1429 |
+
"loss": 0.9426,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.6891891891891891,
|
| 1434 |
+
"grad_norm": 10.328491534330352,
|
| 1435 |
+
"learning_rate": 4.839507272346758e-07,
|
| 1436 |
+
"loss": 1.172,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.6925675675675675,
|
| 1441 |
+
"grad_norm": 12.154859600077485,
|
| 1442 |
+
"learning_rate": 4.7440681070676693e-07,
|
| 1443 |
+
"loss": 1.0143,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6959459459459459,
|
| 1448 |
+
"grad_norm": 10.31503474598816,
|
| 1449 |
+
"learning_rate": 4.6492858917793265e-07,
|
| 1450 |
+
"loss": 0.9418,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.6993243243243243,
|
| 1455 |
+
"grad_norm": 8.872377670254492,
|
| 1456 |
+
"learning_rate": 4.555172473510328e-07,
|
| 1457 |
+
"loss": 0.9625,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.7027027027027027,
|
| 1462 |
+
"grad_norm": 15.014398417567671,
|
| 1463 |
+
"learning_rate": 4.461739615694928e-07,
|
| 1464 |
+
"loss": 1.0399,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.706081081081081,
|
| 1469 |
+
"grad_norm": 58.62921214550316,
|
| 1470 |
+
"learning_rate": 4.368998996702693e-07,
|
| 1471 |
+
"loss": 1.041,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.7094594594594594,
|
| 1476 |
+
"grad_norm": 12.274462720920456,
|
| 1477 |
+
"learning_rate": 4.27696220837881e-07,
|
| 1478 |
+
"loss": 1.1735,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.7128378378378378,
|
| 1483 |
+
"grad_norm": 16.119473658524043,
|
| 1484 |
+
"learning_rate": 4.185640754595183e-07,
|
| 1485 |
+
"loss": 1.014,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.7162162162162162,
|
| 1490 |
+
"grad_norm": 11.278563625017608,
|
| 1491 |
+
"learning_rate": 4.095046049812545e-07,
|
| 1492 |
+
"loss": 1.3416,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.7195945945945946,
|
| 1497 |
+
"grad_norm": 13.274461109657771,
|
| 1498 |
+
"learning_rate": 4.0051894176537427e-07,
|
| 1499 |
+
"loss": 1.183,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.722972972972973,
|
| 1504 |
+
"grad_norm": 8.444784895793578,
|
| 1505 |
+
"learning_rate": 3.9160820894883716e-07,
|
| 1506 |
+
"loss": 1.0165,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.7263513513513513,
|
| 1511 |
+
"grad_norm": 11.129666251524446,
|
| 1512 |
+
"learning_rate": 3.827735203028952e-07,
|
| 1513 |
+
"loss": 1.0201,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.7297297297297297,
|
| 1518 |
+
"grad_norm": 11.332329986651276,
|
| 1519 |
+
"learning_rate": 3.7401598009387834e-07,
|
| 1520 |
+
"loss": 0.9716,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.7331081081081081,
|
| 1525 |
+
"grad_norm": 13.657182251159359,
|
| 1526 |
+
"learning_rate": 3.653366829451715e-07,
|
| 1527 |
+
"loss": 1.1229,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.7364864864864865,
|
| 1532 |
+
"grad_norm": 12.650623514067478,
|
| 1533 |
+
"learning_rate": 3.567367137003946e-07,
|
| 1534 |
+
"loss": 1.0193,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.7398648648648649,
|
| 1539 |
+
"grad_norm": 12.528284571797652,
|
| 1540 |
+
"learning_rate": 3.482171472878062e-07,
|
| 1541 |
+
"loss": 1.0768,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.7432432432432432,
|
| 1546 |
+
"grad_norm": 12.123543919859786,
|
| 1547 |
+
"learning_rate": 3.3977904858594497e-07,
|
| 1548 |
+
"loss": 0.9892,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.7466216216216216,
|
| 1553 |
+
"grad_norm": 18.08029741586697,
|
| 1554 |
+
"learning_rate": 3.314234722905301e-07,
|
| 1555 |
+
"loss": 1.2056,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.75,
|
| 1560 |
+
"grad_norm": 24.021587551266194,
|
| 1561 |
+
"learning_rate": 3.231514627826305e-07,
|
| 1562 |
+
"loss": 1.1163,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.7533783783783784,
|
| 1567 |
+
"grad_norm": 16.31974810568319,
|
| 1568 |
+
"learning_rate": 3.149640539981266e-07,
|
| 1569 |
+
"loss": 1.1707,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.7567567567567568,
|
| 1574 |
+
"grad_norm": 15.102380917033527,
|
| 1575 |
+
"learning_rate": 3.0686226929847615e-07,
|
| 1576 |
+
"loss": 0.9811,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.7601351351351351,
|
| 1581 |
+
"grad_norm": 11.15626873102825,
|
| 1582 |
+
"learning_rate": 2.988471213428032e-07,
|
| 1583 |
+
"loss": 0.909,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.7635135135135135,
|
| 1588 |
+
"grad_norm": 21.234345693238527,
|
| 1589 |
+
"learning_rate": 2.9091961196132176e-07,
|
| 1590 |
+
"loss": 1.0221,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.7668918918918919,
|
| 1595 |
+
"grad_norm": 9.927603168407055,
|
| 1596 |
+
"learning_rate": 2.830807320301166e-07,
|
| 1597 |
+
"loss": 1.0367,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.7702702702702703,
|
| 1602 |
+
"grad_norm": 17.536876256036734,
|
| 1603 |
+
"learning_rate": 2.7533146134729057e-07,
|
| 1604 |
+
"loss": 1.1213,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7736486486486487,
|
| 1609 |
+
"grad_norm": 16.188624993854788,
|
| 1610 |
+
"learning_rate": 2.676727685104981e-07,
|
| 1611 |
+
"loss": 0.9149,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.777027027027027,
|
| 1616 |
+
"grad_norm": 9.957744995273686,
|
| 1617 |
+
"learning_rate": 2.601056107958781e-07,
|
| 1618 |
+
"loss": 1.0756,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.7804054054054054,
|
| 1623 |
+
"grad_norm": 14.408469523826174,
|
| 1624 |
+
"learning_rate": 2.526309340384014e-07,
|
| 1625 |
+
"loss": 1.0573,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.7837837837837838,
|
| 1630 |
+
"grad_norm": 10.834629307505528,
|
| 1631 |
+
"learning_rate": 2.4524967251365023e-07,
|
| 1632 |
+
"loss": 1.1088,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.7871621621621622,
|
| 1637 |
+
"grad_norm": 9.363097104773187,
|
| 1638 |
+
"learning_rate": 2.379627488210396e-07,
|
| 1639 |
+
"loss": 0.954,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.7905405405405406,
|
| 1644 |
+
"grad_norm": 13.468035984566487,
|
| 1645 |
+
"learning_rate": 2.3077107376850002e-07,
|
| 1646 |
+
"loss": 1.199,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.793918918918919,
|
| 1651 |
+
"grad_norm": 13.027311270875577,
|
| 1652 |
+
"learning_rate": 2.2367554625863494e-07,
|
| 1653 |
+
"loss": 0.971,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.7972972972972973,
|
| 1658 |
+
"grad_norm": 9.88730767155789,
|
| 1659 |
+
"learning_rate": 2.166770531763633e-07,
|
| 1660 |
+
"loss": 1.1151,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.8006756756756757,
|
| 1665 |
+
"grad_norm": 20.98172786182695,
|
| 1666 |
+
"learning_rate": 2.097764692780668e-07,
|
| 1667 |
+
"loss": 0.9664,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.8040540540540541,
|
| 1672 |
+
"grad_norm": 18.45995490190523,
|
| 1673 |
+
"learning_rate": 2.0297465708225235e-07,
|
| 1674 |
+
"loss": 1.1172,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.8074324324324325,
|
| 1679 |
+
"grad_norm": 14.91008941631961,
|
| 1680 |
+
"learning_rate": 1.9627246676174358e-07,
|
| 1681 |
+
"loss": 1.0203,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.8108108108108109,
|
| 1686 |
+
"grad_norm": 15.953913058924941,
|
| 1687 |
+
"learning_rate": 1.8967073603741667e-07,
|
| 1688 |
+
"loss": 1.0657,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.8141891891891891,
|
| 1693 |
+
"grad_norm": 9.991751591576667,
|
| 1694 |
+
"learning_rate": 1.8317029007349084e-07,
|
| 1695 |
+
"loss": 0.8895,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.8175675675675675,
|
| 1700 |
+
"grad_norm": 11.839375680518268,
|
| 1701 |
+
"learning_rate": 1.7677194137439032e-07,
|
| 1702 |
+
"loss": 1.1026,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.8209459459459459,
|
| 1707 |
+
"grad_norm": 37.150059957247166,
|
| 1708 |
+
"learning_rate": 1.7047648968318694e-07,
|
| 1709 |
+
"loss": 0.9957,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.8243243243243243,
|
| 1714 |
+
"grad_norm": 17.05682633917313,
|
| 1715 |
+
"learning_rate": 1.642847218816398e-07,
|
| 1716 |
+
"loss": 1.0413,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.8277027027027027,
|
| 1721 |
+
"grad_norm": 24.33954045306361,
|
| 1722 |
+
"learning_rate": 1.5819741189183898e-07,
|
| 1723 |
+
"loss": 1.0788,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.831081081081081,
|
| 1728 |
+
"grad_norm": 13.273586281849699,
|
| 1729 |
+
"learning_rate": 1.5221532057947418e-07,
|
| 1730 |
+
"loss": 1.1628,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.8344594594594594,
|
| 1735 |
+
"grad_norm": 15.1100908937076,
|
| 1736 |
+
"learning_rate": 1.4633919565873031e-07,
|
| 1737 |
+
"loss": 1.1952,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.8378378378378378,
|
| 1742 |
+
"grad_norm": 10.71580728685235,
|
| 1743 |
+
"learning_rate": 1.405697715988301e-07,
|
| 1744 |
+
"loss": 0.9652,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.8412162162162162,
|
| 1749 |
+
"grad_norm": 19.873000698874176,
|
| 1750 |
+
"learning_rate": 1.3490776953223105e-07,
|
| 1751 |
+
"loss": 1.3244,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.8445945945945946,
|
| 1756 |
+
"grad_norm": 10.13343973333245,
|
| 1757 |
+
"learning_rate": 1.2935389716448975e-07,
|
| 1758 |
+
"loss": 0.9577,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.847972972972973,
|
| 1763 |
+
"grad_norm": 14.431217293287924,
|
| 1764 |
+
"learning_rate": 1.23908848685804e-07,
|
| 1765 |
+
"loss": 1.147,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.8513513513513513,
|
| 1770 |
+
"grad_norm": 12.256645041926157,
|
| 1771 |
+
"learning_rate": 1.1857330468424464e-07,
|
| 1772 |
+
"loss": 1.0371,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.8547297297297297,
|
| 1777 |
+
"grad_norm": 16.382108194565067,
|
| 1778 |
+
"learning_rate": 1.1334793206068738e-07,
|
| 1779 |
+
"loss": 1.1421,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.8581081081081081,
|
| 1784 |
+
"grad_norm": 11.011451523238076,
|
| 1785 |
+
"learning_rate": 1.0823338394545589e-07,
|
| 1786 |
+
"loss": 0.9227,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.8614864864864865,
|
| 1791 |
+
"grad_norm": 12.960927963028357,
|
| 1792 |
+
"learning_rate": 1.0323029961668462e-07,
|
| 1793 |
+
"loss": 1.0059,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.8648648648648649,
|
| 1798 |
+
"grad_norm": 11.564760088134562,
|
| 1799 |
+
"learning_rate": 9.833930442041504e-08,
|
| 1800 |
+
"loss": 0.848,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.8682432432432432,
|
| 1805 |
+
"grad_norm": 9.963842599666545,
|
| 1806 |
+
"learning_rate": 9.35610096924323e-08,
|
| 1807 |
+
"loss": 1.0526,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.8716216216216216,
|
| 1812 |
+
"grad_norm": 10.992866785789206,
|
| 1813 |
+
"learning_rate": 8.889601268185232e-08,
|
| 1814 |
+
"loss": 1.1633,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.875,
|
| 1819 |
+
"grad_norm": 11.726628665900261,
|
| 1820 |
+
"learning_rate": 8.434489647647092e-08,
|
| 1821 |
+
"loss": 0.8408,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.8783783783783784,
|
| 1826 |
+
"grad_norm": 8.881905774747459,
|
| 1827 |
+
"learning_rate": 7.990822992988267e-08,
|
| 1828 |
+
"loss": 0.8675,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.8817567567567568,
|
| 1833 |
+
"grad_norm": 22.2126831514475,
|
| 1834 |
+
"learning_rate": 7.558656759037796e-08,
|
| 1835 |
+
"loss": 1.3045,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.8851351351351351,
|
| 1840 |
+
"grad_norm": 11.171932421978283,
|
| 1841 |
+
"learning_rate": 7.138044963162959e-08,
|
| 1842 |
+
"loss": 1.0872,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.8885135135135135,
|
| 1847 |
+
"grad_norm": 8.951655298900414,
|
| 1848 |
+
"learning_rate": 6.729040178517453e-08,
|
| 1849 |
+
"loss": 0.9246,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.8918918918918919,
|
| 1854 |
+
"grad_norm": 11.756152011031759,
|
| 1855 |
+
"learning_rate": 6.331693527470305e-08,
|
| 1856 |
+
"loss": 0.9987,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.8952702702702703,
|
| 1861 |
+
"grad_norm": 28.59857773686451,
|
| 1862 |
+
"learning_rate": 5.946054675215784e-08,
|
| 1863 |
+
"loss": 1.0576,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.8986486486486487,
|
| 1868 |
+
"grad_norm": 10.399047421768794,
|
| 1869 |
+
"learning_rate": 5.5721718235657963e-08,
|
| 1870 |
+
"loss": 0.9176,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.902027027027027,
|
| 1875 |
+
"grad_norm": 9.366247103886712,
|
| 1876 |
+
"learning_rate": 5.210091704924946e-08,
|
| 1877 |
+
"loss": 1.1085,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.9054054054054054,
|
| 1882 |
+
"grad_norm": 10.510092232680053,
|
| 1883 |
+
"learning_rate": 4.8598595764494434e-08,
|
| 1884 |
+
"loss": 1.1477,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.9087837837837838,
|
| 1889 |
+
"grad_norm": 10.988320315716262,
|
| 1890 |
+
"learning_rate": 4.521519214390257e-08,
|
| 1891 |
+
"loss": 1.083,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.9121621621621622,
|
| 1896 |
+
"grad_norm": 9.422046394244651,
|
| 1897 |
+
"learning_rate": 4.195112908621401e-08,
|
| 1898 |
+
"loss": 1.0864,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.9155405405405406,
|
| 1903 |
+
"grad_norm": 59.96258527562246,
|
| 1904 |
+
"learning_rate": 3.880681457354118e-08,
|
| 1905 |
+
"loss": 1.1644,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.918918918918919,
|
| 1910 |
+
"grad_norm": 11.419772592417507,
|
| 1911 |
+
"learning_rate": 3.578264162037348e-08,
|
| 1912 |
+
"loss": 1.0481,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.9222972972972973,
|
| 1917 |
+
"grad_norm": 9.894693485395429,
|
| 1918 |
+
"learning_rate": 3.287898822445434e-08,
|
| 1919 |
+
"loss": 0.8008,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.9256756756756757,
|
| 1924 |
+
"grad_norm": 16.98073659436826,
|
| 1925 |
+
"learning_rate": 3.009621731953338e-08,
|
| 1926 |
+
"loss": 1.0858,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.9290540540540541,
|
| 1931 |
+
"grad_norm": 11.258423278993948,
|
| 1932 |
+
"learning_rate": 2.743467673000388e-08,
|
| 1933 |
+
"loss": 1.1409,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.9324324324324325,
|
| 1938 |
+
"grad_norm": 14.003643864971671,
|
| 1939 |
+
"learning_rate": 2.4894699127426365e-08,
|
| 1940 |
+
"loss": 1.1027,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.9358108108108109,
|
| 1945 |
+
"grad_norm": 14.178437502365894,
|
| 1946 |
+
"learning_rate": 2.2476601988947963e-08,
|
| 1947 |
+
"loss": 1.1833,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.9391891891891891,
|
| 1952 |
+
"grad_norm": 16.461107706437943,
|
| 1953 |
+
"learning_rate": 2.0180687557619812e-08,
|
| 1954 |
+
"loss": 1.2019,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.9425675675675675,
|
| 1959 |
+
"grad_norm": 13.576993179328168,
|
| 1960 |
+
"learning_rate": 1.8007242804619627e-08,
|
| 1961 |
+
"loss": 1.0821,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.9459459459459459,
|
| 1966 |
+
"grad_norm": 14.294674356418733,
|
| 1967 |
+
"learning_rate": 1.595653939338204e-08,
|
| 1968 |
+
"loss": 0.9675,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.9493243243243243,
|
| 1973 |
+
"grad_norm": 29.481688805590153,
|
| 1974 |
+
"learning_rate": 1.4028833645643112e-08,
|
| 1975 |
+
"loss": 1.0754,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.9527027027027027,
|
| 1980 |
+
"grad_norm": 15.753446563795709,
|
| 1981 |
+
"learning_rate": 1.2224366509401728e-08,
|
| 1982 |
+
"loss": 1.0815,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.956081081081081,
|
| 1987 |
+
"grad_norm": 10.43066589789782,
|
| 1988 |
+
"learning_rate": 1.0543363528803695e-08,
|
| 1989 |
+
"loss": 0.9411,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.9594594594594594,
|
| 1994 |
+
"grad_norm": 10.308024502652335,
|
| 1995 |
+
"learning_rate": 8.986034815950173e-09,
|
| 1996 |
+
"loss": 1.0523,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.9628378378378378,
|
| 2001 |
+
"grad_norm": 11.257358614798429,
|
| 2002 |
+
"learning_rate": 7.55257502463469e-09,
|
| 2003 |
+
"loss": 1.0666,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.9662162162162162,
|
| 2008 |
+
"grad_norm": 18.30851770045993,
|
| 2009 |
+
"learning_rate": 6.243163326014267e-09,
|
| 2010 |
+
"loss": 1.0719,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.9695945945945946,
|
| 2015 |
+
"grad_norm": 11.663075265992216,
|
| 2016 |
+
"learning_rate": 5.057963386213116e-09,
|
| 2017 |
+
"loss": 0.9051,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.972972972972973,
|
| 2022 |
+
"grad_norm": 15.617029665112927,
|
| 2023 |
+
"learning_rate": 3.9971233458665485e-09,
|
| 2024 |
+
"loss": 1.1801,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.9763513513513513,
|
| 2029 |
+
"grad_norm": 10.717531089234555,
|
| 2030 |
+
"learning_rate": 3.0607758016043538e-09,
|
| 2031 |
+
"loss": 0.8987,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.9797297297297297,
|
| 2036 |
+
"grad_norm": 13.478109909109575,
|
| 2037 |
+
"learning_rate": 2.2490377894768263e-09,
|
| 2038 |
+
"loss": 0.9534,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.9831081081081081,
|
| 2043 |
+
"grad_norm": 11.495983174904561,
|
| 2044 |
+
"learning_rate": 1.5620107703269158e-09,
|
| 2045 |
+
"loss": 1.1178,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.9864864864864865,
|
| 2050 |
+
"grad_norm": 11.155920371528513,
|
| 2051 |
+
"learning_rate": 9.99780617107815e-10,
|
| 2052 |
+
"loss": 1.2565,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.9898648648648649,
|
| 2057 |
+
"grad_norm": 12.08405920919666,
|
| 2058 |
+
"learning_rate": 5.624176041498785e-10,
|
| 2059 |
+
"loss": 0.9727,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.9932432432432432,
|
| 2064 |
+
"grad_norm": 10.571871050344438,
|
| 2065 |
+
"learning_rate": 2.499763983768721e-10,
|
| 2066 |
+
"loss": 1.1216,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.9966216216216216,
|
| 2071 |
+
"grad_norm": 9.386471825756521,
|
| 2072 |
+
"learning_rate": 6.24960524725493e-11,
|
| 2073 |
+
"loss": 0.8506,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.0,
|
| 2078 |
+
"grad_norm": 11.0370229285448,
|
| 2079 |
+
"learning_rate": 0.0,
|
| 2080 |
+
"loss": 1.0426,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.0,
|
| 2085 |
+
"step": 296,
|
| 2086 |
+
"total_flos": 214906088767488.0,
|
| 2087 |
+
"train_loss": 1.1669919788837433,
|
| 2088 |
+
"train_runtime": 1864.0349,
|
| 2089 |
+
"train_samples_per_second": 2.541,
|
| 2090 |
+
"train_steps_per_second": 0.159
|
| 2091 |
+
}
|
| 2092 |
+
],
|
| 2093 |
+
"logging_steps": 1.0,
|
| 2094 |
+
"max_steps": 296,
|
| 2095 |
+
"num_input_tokens_seen": 0,
|
| 2096 |
+
"num_train_epochs": 1,
|
| 2097 |
+
"save_steps": 500,
|
| 2098 |
+
"stateful_callbacks": {
|
| 2099 |
+
"TrainerControl": {
|
| 2100 |
+
"args": {
|
| 2101 |
+
"should_epoch_stop": false,
|
| 2102 |
+
"should_evaluate": false,
|
| 2103 |
+
"should_log": false,
|
| 2104 |
+
"should_save": true,
|
| 2105 |
+
"should_training_stop": true
|
| 2106 |
+
},
|
| 2107 |
+
"attributes": {}
|
| 2108 |
+
}
|
| 2109 |
+
},
|
| 2110 |
+
"total_flos": 214906088767488.0,
|
| 2111 |
+
"train_batch_size": 4,
|
| 2112 |
+
"trial_name": null,
|
| 2113 |
+
"trial_params": null
|
| 2114 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ffd61de839f726a0798b759985a206ebe0993f8499b2b5f7d491e893356f8ec
|
| 3 |
+
size 7608
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|