Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9979661016949153,
+    "total_flos": 100810460790784.0,
+    "train_loss": 0.7222011056931122,
+    "train_runtime": 4200.972,
+    "train_samples_per_second": 8.426,
+    "train_steps_per_second": 0.066
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "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 %}"
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec976dcb00bd9f7c9a96292c10c9cd429b4138d489d34d1bacc7ca4ab3c88d39
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bcc74bac66af47b546405a141b90a5a7ec6e689ff74901ebf7f68f855cf05e
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccba519ebb2961c98c2f1cd8feefce1cccc0e31cf444f6694a9a986d8173537
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0a6d55cfbc462d64d142857fdb06884c10ec2b9e45dea9c551915c8d2443ba
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9979661016949153,
+    "total_flos": 100810460790784.0,
+    "train_loss": 0.7222011056931122,
+    "train_runtime": 4200.972,
+    "train_samples_per_second": 8.426,
+    "train_steps_per_second": 0.066
+}

trainer_log.jsonl

@@ -0,0 +1,277 @@
+{"current_steps": 1, "total_steps": 276, "loss": 1.4293, "lr": 0.0, "epoch": 0.003615819209039548, "percentage": 0.36, "elapsed_time": "0:00:19", "remaining_time": "1:28:47"}
+{"current_steps": 2, "total_steps": 276, "loss": 1.4193, "lr": 1.7857142857142858e-07, "epoch": 0.007231638418079096, "percentage": 0.72, "elapsed_time": "0:00:33", "remaining_time": "1:17:22"}
+{"current_steps": 3, "total_steps": 276, "loss": 1.3691, "lr": 3.5714285714285716e-07, "epoch": 0.010847457627118645, "percentage": 1.09, "elapsed_time": "0:00:48", "remaining_time": "1:13:39"}
+{"current_steps": 4, "total_steps": 276, "loss": 1.4337, "lr": 5.357142857142857e-07, "epoch": 0.014463276836158192, "percentage": 1.45, "elapsed_time": "0:01:03", "remaining_time": "1:11:35"}
+{"current_steps": 5, "total_steps": 276, "loss": 1.335, "lr": 7.142857142857143e-07, "epoch": 0.01807909604519774, "percentage": 1.81, "elapsed_time": "0:01:17", "remaining_time": "1:10:17"}
+{"current_steps": 6, "total_steps": 276, "loss": 1.4104, "lr": 8.928571428571429e-07, "epoch": 0.02169491525423729, "percentage": 2.17, "elapsed_time": "0:01:32", "remaining_time": "1:09:28"}
+{"current_steps": 7, "total_steps": 276, "loss": 1.3364, "lr": 1.0714285714285714e-06, "epoch": 0.025310734463276835, "percentage": 2.54, "elapsed_time": "0:01:47", "remaining_time": "1:08:58"}
+{"current_steps": 8, "total_steps": 276, "loss": 1.3289, "lr": 1.25e-06, "epoch": 0.028926553672316384, "percentage": 2.9, "elapsed_time": "0:02:02", "remaining_time": "1:08:23"}
+{"current_steps": 9, "total_steps": 276, "loss": 1.2395, "lr": 1.4285714285714286e-06, "epoch": 0.03254237288135593, "percentage": 3.26, "elapsed_time": "0:02:18", "remaining_time": "1:08:24"}
+{"current_steps": 10, "total_steps": 276, "loss": 1.2597, "lr": 1.6071428571428574e-06, "epoch": 0.03615819209039548, "percentage": 3.62, "elapsed_time": "0:02:32", "remaining_time": "1:07:47"}
+{"current_steps": 11, "total_steps": 276, "loss": 1.1323, "lr": 1.7857142857142859e-06, "epoch": 0.03977401129943503, "percentage": 3.99, "elapsed_time": "0:02:47", "remaining_time": "1:07:19"}
+{"current_steps": 12, "total_steps": 276, "loss": 1.1555, "lr": 1.9642857142857144e-06, "epoch": 0.04338983050847458, "percentage": 4.35, "elapsed_time": "0:03:02", "remaining_time": "1:06:58"}
+{"current_steps": 13, "total_steps": 276, "loss": 1.1208, "lr": 2.1428571428571427e-06, "epoch": 0.04700564971751412, "percentage": 4.71, "elapsed_time": "0:03:17", "remaining_time": "1:06:35"}
+{"current_steps": 14, "total_steps": 276, "loss": 1.1211, "lr": 2.321428571428572e-06, "epoch": 0.05062146892655367, "percentage": 5.07, "elapsed_time": "0:03:32", "remaining_time": "1:06:09"}
+{"current_steps": 15, "total_steps": 276, "loss": 1.0921, "lr": 2.5e-06, "epoch": 0.05423728813559322, "percentage": 5.43, "elapsed_time": "0:03:46", "remaining_time": "1:05:39"}
+{"current_steps": 16, "total_steps": 276, "loss": 1.0519, "lr": 2.6785714285714285e-06, "epoch": 0.05785310734463277, "percentage": 5.8, "elapsed_time": "0:04:01", "remaining_time": "1:05:26"}
+{"current_steps": 17, "total_steps": 276, "loss": 1.0559, "lr": 2.8571428571428573e-06, "epoch": 0.061468926553672316, "percentage": 6.16, "elapsed_time": "0:04:15", "remaining_time": "1:04:58"}
+{"current_steps": 18, "total_steps": 276, "loss": 1.0629, "lr": 3.0357142857142856e-06, "epoch": 0.06508474576271187, "percentage": 6.52, "elapsed_time": "0:04:30", "remaining_time": "1:04:40"}
+{"current_steps": 19, "total_steps": 276, "loss": 1.0244, "lr": 3.2142857142857147e-06, "epoch": 0.06870056497175141, "percentage": 6.88, "elapsed_time": "0:04:45", "remaining_time": "1:04:15"}
+{"current_steps": 20, "total_steps": 276, "loss": 0.9697, "lr": 3.3928571428571435e-06, "epoch": 0.07231638418079096, "percentage": 7.25, "elapsed_time": "0:04:59", "remaining_time": "1:03:50"}
+{"current_steps": 21, "total_steps": 276, "loss": 0.9601, "lr": 3.5714285714285718e-06, "epoch": 0.0759322033898305, "percentage": 7.61, "elapsed_time": "0:05:13", "remaining_time": "1:03:26"}
+{"current_steps": 22, "total_steps": 276, "loss": 0.9409, "lr": 3.7500000000000005e-06, "epoch": 0.07954802259887006, "percentage": 7.97, "elapsed_time": "0:05:28", "remaining_time": "1:03:10"}
+{"current_steps": 23, "total_steps": 276, "loss": 0.9486, "lr": 3.928571428571429e-06, "epoch": 0.0831638418079096, "percentage": 8.33, "elapsed_time": "0:05:42", "remaining_time": "1:02:46"}
+{"current_steps": 24, "total_steps": 276, "loss": 0.8874, "lr": 4.107142857142857e-06, "epoch": 0.08677966101694916, "percentage": 8.7, "elapsed_time": "0:05:57", "remaining_time": "1:02:32"}
+{"current_steps": 25, "total_steps": 276, "loss": 0.8994, "lr": 4.2857142857142855e-06, "epoch": 0.0903954802259887, "percentage": 9.06, "elapsed_time": "0:06:11", "remaining_time": "1:02:13"}
+{"current_steps": 26, "total_steps": 276, "loss": 0.8975, "lr": 4.464285714285715e-06, "epoch": 0.09401129943502824, "percentage": 9.42, "elapsed_time": "0:06:25", "remaining_time": "1:01:51"}
+{"current_steps": 27, "total_steps": 276, "loss": 0.8581, "lr": 4.642857142857144e-06, "epoch": 0.0976271186440678, "percentage": 9.78, "elapsed_time": "0:06:40", "remaining_time": "1:01:30"}
+{"current_steps": 28, "total_steps": 276, "loss": 0.8423, "lr": 4.821428571428572e-06, "epoch": 0.10124293785310734, "percentage": 10.14, "elapsed_time": "0:06:56", "remaining_time": "1:01:28"}
+{"current_steps": 29, "total_steps": 276, "loss": 0.8205, "lr": 5e-06, "epoch": 0.1048587570621469, "percentage": 10.51, "elapsed_time": "0:07:10", "remaining_time": "1:01:08"}
+{"current_steps": 30, "total_steps": 276, "loss": 0.8754, "lr": 4.999799414013322e-06, "epoch": 0.10847457627118644, "percentage": 10.87, "elapsed_time": "0:07:24", "remaining_time": "1:00:47"}
+{"current_steps": 31, "total_steps": 276, "loss": 0.8267, "lr": 4.999197688241076e-06, "epoch": 0.112090395480226, "percentage": 11.23, "elapsed_time": "0:07:39", "remaining_time": "1:00:29"}
+{"current_steps": 32, "total_steps": 276, "loss": 0.8312, "lr": 4.998194919241471e-06, "epoch": 0.11570621468926554, "percentage": 11.59, "elapsed_time": "0:07:53", "remaining_time": "1:00:11"}
+{"current_steps": 33, "total_steps": 276, "loss": 0.7878, "lr": 4.996791267927632e-06, "epoch": 0.11932203389830509, "percentage": 11.96, "elapsed_time": "0:08:08", "remaining_time": "0:59:56"}
+{"current_steps": 34, "total_steps": 276, "loss": 0.7816, "lr": 4.994986959541788e-06, "epoch": 0.12293785310734463, "percentage": 12.32, "elapsed_time": "0:08:23", "remaining_time": "0:59:41"}
+{"current_steps": 35, "total_steps": 276, "loss": 0.7818, "lr": 4.9927822836191185e-06, "epoch": 0.12655367231638417, "percentage": 12.68, "elapsed_time": "0:08:38", "remaining_time": "0:59:27"}
+{"current_steps": 36, "total_steps": 276, "loss": 0.7674, "lr": 4.990177593941303e-06, "epoch": 0.13016949152542373, "percentage": 13.04, "elapsed_time": "0:08:52", "remaining_time": "0:59:12"}
+{"current_steps": 37, "total_steps": 276, "loss": 0.7652, "lr": 4.987173308479738e-06, "epoch": 0.1337853107344633, "percentage": 13.41, "elapsed_time": "0:09:07", "remaining_time": "0:58:56"}
+{"current_steps": 38, "total_steps": 276, "loss": 0.7457, "lr": 4.9837699093284765e-06, "epoch": 0.13740112994350281, "percentage": 13.77, "elapsed_time": "0:09:22", "remaining_time": "0:58:40"}
+{"current_steps": 39, "total_steps": 276, "loss": 0.7943, "lr": 4.9799679426268575e-06, "epoch": 0.14101694915254237, "percentage": 14.13, "elapsed_time": "0:09:37", "remaining_time": "0:58:30"}
+{"current_steps": 40, "total_steps": 276, "loss": 0.7815, "lr": 4.975768018471877e-06, "epoch": 0.14463276836158193, "percentage": 14.49, "elapsed_time": "0:09:53", "remaining_time": "0:58:21"}
+{"current_steps": 41, "total_steps": 276, "loss": 0.7557, "lr": 4.971170810820279e-06, "epoch": 0.14824858757062148, "percentage": 14.86, "elapsed_time": "0:10:08", "remaining_time": "0:58:06"}
+{"current_steps": 42, "total_steps": 276, "loss": 0.7561, "lr": 4.966177057380409e-06, "epoch": 0.151864406779661, "percentage": 15.22, "elapsed_time": "0:10:23", "remaining_time": "0:57:52"}
+{"current_steps": 43, "total_steps": 276, "loss": 0.7474, "lr": 4.960787559493836e-06, "epoch": 0.15548022598870057, "percentage": 15.58, "elapsed_time": "0:10:37", "remaining_time": "0:57:34"}
+{"current_steps": 44, "total_steps": 276, "loss": 0.716, "lr": 4.955003182006761e-06, "epoch": 0.15909604519774012, "percentage": 15.94, "elapsed_time": "0:10:51", "remaining_time": "0:57:16"}
+{"current_steps": 45, "total_steps": 276, "loss": 0.7353, "lr": 4.948824853131237e-06, "epoch": 0.16271186440677965, "percentage": 16.3, "elapsed_time": "0:11:06", "remaining_time": "0:57:01"}
+{"current_steps": 46, "total_steps": 276, "loss": 0.7358, "lr": 4.942253564296217e-06, "epoch": 0.1663276836158192, "percentage": 16.67, "elapsed_time": "0:11:20", "remaining_time": "0:56:44"}
+{"current_steps": 47, "total_steps": 276, "loss": 0.7419, "lr": 4.935290369988468e-06, "epoch": 0.16994350282485876, "percentage": 17.03, "elapsed_time": "0:11:34", "remaining_time": "0:56:26"}
+{"current_steps": 48, "total_steps": 276, "loss": 0.748, "lr": 4.927936387583348e-06, "epoch": 0.17355932203389832, "percentage": 17.39, "elapsed_time": "0:11:49", "remaining_time": "0:56:09"}
+{"current_steps": 49, "total_steps": 276, "loss": 0.7571, "lr": 4.920192797165511e-06, "epoch": 0.17717514124293784, "percentage": 17.75, "elapsed_time": "0:12:04", "remaining_time": "0:55:54"}
+{"current_steps": 50, "total_steps": 276, "loss": 0.7127, "lr": 4.912060841339536e-06, "epoch": 0.1807909604519774, "percentage": 18.12, "elapsed_time": "0:12:18", "remaining_time": "0:55:37"}
+{"current_steps": 51, "total_steps": 276, "loss": 0.7272, "lr": 4.9035418250305314e-06, "epoch": 0.18440677966101696, "percentage": 18.48, "elapsed_time": "0:12:32", "remaining_time": "0:55:21"}
+{"current_steps": 52, "total_steps": 276, "loss": 0.7258, "lr": 4.894637115274728e-06, "epoch": 0.18802259887005648, "percentage": 18.84, "elapsed_time": "0:12:47", "remaining_time": "0:55:05"}
+{"current_steps": 53, "total_steps": 276, "loss": 0.7316, "lr": 4.8853481410001225e-06, "epoch": 0.19163841807909604, "percentage": 19.2, "elapsed_time": "0:13:01", "remaining_time": "0:54:49"}
+{"current_steps": 54, "total_steps": 276, "loss": 0.7551, "lr": 4.875676392797169e-06, "epoch": 0.1952542372881356, "percentage": 19.57, "elapsed_time": "0:13:16", "remaining_time": "0:54:34"}
+{"current_steps": 55, "total_steps": 276, "loss": 0.7446, "lr": 4.865623422679593e-06, "epoch": 0.19887005649717515, "percentage": 19.93, "elapsed_time": "0:13:30", "remaining_time": "0:54:17"}
+{"current_steps": 56, "total_steps": 276, "loss": 0.6955, "lr": 4.855190843835338e-06, "epoch": 0.20248587570621468, "percentage": 20.29, "elapsed_time": "0:13:45", "remaining_time": "0:54:01"}
+{"current_steps": 57, "total_steps": 276, "loss": 0.7214, "lr": 4.844380330367701e-06, "epoch": 0.20610169491525424, "percentage": 20.65, "elapsed_time": "0:13:59", "remaining_time": "0:53:45"}
+{"current_steps": 58, "total_steps": 276, "loss": 0.7386, "lr": 4.833193617026692e-06, "epoch": 0.2097175141242938, "percentage": 21.01, "elapsed_time": "0:14:13", "remaining_time": "0:53:28"}
+{"current_steps": 59, "total_steps": 276, "loss": 0.7156, "lr": 4.821632498930656e-06, "epoch": 0.21333333333333335, "percentage": 21.38, "elapsed_time": "0:14:27", "remaining_time": "0:53:12"}
+{"current_steps": 60, "total_steps": 276, "loss": 0.6961, "lr": 4.809698831278217e-06, "epoch": 0.21694915254237288, "percentage": 21.74, "elapsed_time": "0:14:42", "remaining_time": "0:52:56"}
+{"current_steps": 61, "total_steps": 276, "loss": 0.7223, "lr": 4.797394529050577e-06, "epoch": 0.22056497175141243, "percentage": 22.1, "elapsed_time": "0:14:56", "remaining_time": "0:52:40"}
+{"current_steps": 62, "total_steps": 276, "loss": 0.7157, "lr": 4.784721566704217e-06, "epoch": 0.224180790960452, "percentage": 22.46, "elapsed_time": "0:15:11", "remaining_time": "0:52:24"}
+{"current_steps": 63, "total_steps": 276, "loss": 0.7091, "lr": 4.771681977854062e-06, "epoch": 0.22779661016949151, "percentage": 22.83, "elapsed_time": "0:15:25", "remaining_time": "0:52:09"}
+{"current_steps": 64, "total_steps": 276, "loss": 0.7012, "lr": 4.75827785494715e-06, "epoch": 0.23141242937853107, "percentage": 23.19, "elapsed_time": "0:15:39", "remaining_time": "0:51:52"}
+{"current_steps": 65, "total_steps": 276, "loss": 0.7124, "lr": 4.744511348926855e-06, "epoch": 0.23502824858757063, "percentage": 23.55, "elapsed_time": "0:15:53", "remaining_time": "0:51:36"}
+{"current_steps": 66, "total_steps": 276, "loss": 0.7215, "lr": 4.730384668887731e-06, "epoch": 0.23864406779661018, "percentage": 23.91, "elapsed_time": "0:16:08", "remaining_time": "0:51:20"}
+{"current_steps": 67, "total_steps": 276, "loss": 0.6946, "lr": 4.715900081721021e-06, "epoch": 0.2422598870056497, "percentage": 24.28, "elapsed_time": "0:16:22", "remaining_time": "0:51:04"}
+{"current_steps": 68, "total_steps": 276, "loss": 0.7109, "lr": 4.7010599117508936e-06, "epoch": 0.24587570621468927, "percentage": 24.64, "elapsed_time": "0:16:37", "remaining_time": "0:50:50"}
+{"current_steps": 69, "total_steps": 276, "loss": 0.7092, "lr": 4.685866540361456e-06, "epoch": 0.24949152542372882, "percentage": 25.0, "elapsed_time": "0:16:51", "remaining_time": "0:50:35"}
+{"current_steps": 70, "total_steps": 276, "loss": 0.7055, "lr": 4.670322405614621e-06, "epoch": 0.25310734463276835, "percentage": 25.36, "elapsed_time": "0:17:05", "remaining_time": "0:50:19"}
+{"current_steps": 71, "total_steps": 276, "loss": 0.6878, "lr": 4.654430001858874e-06, "epoch": 0.25672316384180793, "percentage": 25.72, "elapsed_time": "0:17:20", "remaining_time": "0:50:03"}
+{"current_steps": 72, "total_steps": 276, "loss": 0.7222, "lr": 4.638191879329005e-06, "epoch": 0.26033898305084746, "percentage": 26.09, "elapsed_time": "0:17:35", "remaining_time": "0:49:50"}
+{"current_steps": 73, "total_steps": 276, "loss": 0.7237, "lr": 4.621610643736878e-06, "epoch": 0.263954802259887, "percentage": 26.45, "elapsed_time": "0:17:50", "remaining_time": "0:49:37"}
+{"current_steps": 74, "total_steps": 276, "loss": 0.6966, "lr": 4.6046889558532925e-06, "epoch": 0.2675706214689266, "percentage": 26.81, "elapsed_time": "0:18:05", "remaining_time": "0:49:22"}
+{"current_steps": 75, "total_steps": 276, "loss": 0.7018, "lr": 4.587429531081019e-06, "epoch": 0.2711864406779661, "percentage": 27.17, "elapsed_time": "0:18:19", "remaining_time": "0:49:06"}
+{"current_steps": 76, "total_steps": 276, "loss": 0.6548, "lr": 4.569835139019054e-06, "epoch": 0.27480225988700563, "percentage": 27.54, "elapsed_time": "0:18:34", "remaining_time": "0:48:52"}
+{"current_steps": 77, "total_steps": 276, "loss": 0.6976, "lr": 4.551908603018191e-06, "epoch": 0.2784180790960452, "percentage": 27.9, "elapsed_time": "0:18:49", "remaining_time": "0:48:38"}
+{"current_steps": 78, "total_steps": 276, "loss": 0.693, "lr": 4.53365279972796e-06, "epoch": 0.28203389830508474, "percentage": 28.26, "elapsed_time": "0:19:03", "remaining_time": "0:48:23"}
+{"current_steps": 79, "total_steps": 276, "loss": 0.697, "lr": 4.515070658635013e-06, "epoch": 0.28564971751412427, "percentage": 28.62, "elapsed_time": "0:19:18", "remaining_time": "0:48:10"}
+{"current_steps": 80, "total_steps": 276, "loss": 0.7115, "lr": 4.4961651615930344e-06, "epoch": 0.28926553672316385, "percentage": 28.99, "elapsed_time": "0:19:34", "remaining_time": "0:47:56"}
+{"current_steps": 81, "total_steps": 276, "loss": 0.7163, "lr": 4.476939342344246e-06, "epoch": 0.2928813559322034, "percentage": 29.35, "elapsed_time": "0:19:48", "remaining_time": "0:47:41"}
+{"current_steps": 82, "total_steps": 276, "loss": 0.6886, "lr": 4.457396286032589e-06, "epoch": 0.29649717514124296, "percentage": 29.71, "elapsed_time": "0:20:03", "remaining_time": "0:47:28"}
+{"current_steps": 83, "total_steps": 276, "loss": 0.7339, "lr": 4.437539128708647e-06, "epoch": 0.3001129943502825, "percentage": 30.07, "elapsed_time": "0:20:18", "remaining_time": "0:47:14"}
+{"current_steps": 84, "total_steps": 276, "loss": 0.7149, "lr": 4.417371056826417e-06, "epoch": 0.303728813559322, "percentage": 30.43, "elapsed_time": "0:20:33", "remaining_time": "0:47:00"}
+{"current_steps": 85, "total_steps": 276, "loss": 0.6822, "lr": 4.396895306731978e-06, "epoch": 0.3073446327683616, "percentage": 30.8, "elapsed_time": "0:20:48", "remaining_time": "0:46:46"}
+{"current_steps": 86, "total_steps": 276, "loss": 0.6836, "lr": 4.376115164144157e-06, "epoch": 0.31096045197740113, "percentage": 31.16, "elapsed_time": "0:21:03", "remaining_time": "0:46:31"}
+{"current_steps": 87, "total_steps": 276, "loss": 0.7131, "lr": 4.355033963627277e-06, "epoch": 0.31457627118644066, "percentage": 31.52, "elapsed_time": "0:21:18", "remaining_time": "0:46:17"}
+{"current_steps": 88, "total_steps": 276, "loss": 0.6854, "lr": 4.333655088056065e-06, "epoch": 0.31819209039548024, "percentage": 31.88, "elapsed_time": "0:21:33", "remaining_time": "0:46:02"}
+{"current_steps": 89, "total_steps": 276, "loss": 0.7094, "lr": 4.3119819680728e-06, "epoch": 0.32180790960451977, "percentage": 32.25, "elapsed_time": "0:21:47", "remaining_time": "0:45:46"}
+{"current_steps": 90, "total_steps": 276, "loss": 0.6872, "lr": 4.290018081536807e-06, "epoch": 0.3254237288135593, "percentage": 32.61, "elapsed_time": "0:22:01", "remaining_time": "0:45:32"}
+{"current_steps": 91, "total_steps": 276, "loss": 0.7139, "lr": 4.267766952966369e-06, "epoch": 0.3290395480225989, "percentage": 32.97, "elapsed_time": "0:22:16", "remaining_time": "0:45:16"}
+{"current_steps": 92, "total_steps": 276, "loss": 0.6778, "lr": 4.245232152973148e-06, "epoch": 0.3326553672316384, "percentage": 33.33, "elapsed_time": "0:22:30", "remaining_time": "0:45:00"}
+{"current_steps": 93, "total_steps": 276, "loss": 0.6689, "lr": 4.222417297689217e-06, "epoch": 0.336271186440678, "percentage": 33.7, "elapsed_time": "0:22:44", "remaining_time": "0:44:45"}
+{"current_steps": 94, "total_steps": 276, "loss": 0.6894, "lr": 4.199326048186783e-06, "epoch": 0.3398870056497175, "percentage": 34.06, "elapsed_time": "0:22:58", "remaining_time": "0:44:29"}
+{"current_steps": 95, "total_steps": 276, "loss": 0.6554, "lr": 4.175962109890697e-06, "epoch": 0.34350282485875705, "percentage": 34.42, "elapsed_time": "0:23:12", "remaining_time": "0:44:13"}
+{"current_steps": 96, "total_steps": 276, "loss": 0.7023, "lr": 4.152329231983852e-06, "epoch": 0.34711864406779663, "percentage": 34.78, "elapsed_time": "0:23:26", "remaining_time": "0:43:57"}
+{"current_steps": 97, "total_steps": 276, "loss": 0.7107, "lr": 4.128431206805556e-06, "epoch": 0.35073446327683616, "percentage": 35.14, "elapsed_time": "0:23:40", "remaining_time": "0:43:41"}
+{"current_steps": 98, "total_steps": 276, "loss": 0.6894, "lr": 4.104271869242975e-06, "epoch": 0.3543502824858757, "percentage": 35.51, "elapsed_time": "0:23:55", "remaining_time": "0:43:27"}
+{"current_steps": 99, "total_steps": 276, "loss": 0.677, "lr": 4.07985509611576e-06, "epoch": 0.3579661016949153, "percentage": 35.87, "elapsed_time": "0:24:09", "remaining_time": "0:43:12"}
+{"current_steps": 100, "total_steps": 276, "loss": 0.6699, "lr": 4.0551848055539345e-06, "epoch": 0.3615819209039548, "percentage": 36.23, "elapsed_time": "0:24:24", "remaining_time": "0:42:57"}
+{"current_steps": 101, "total_steps": 276, "loss": 0.7368, "lr": 4.030264956369158e-06, "epoch": 0.36519774011299433, "percentage": 36.59, "elapsed_time": "0:24:39", "remaining_time": "0:42:43"}
+{"current_steps": 102, "total_steps": 276, "loss": 0.7034, "lr": 4.005099547419458e-06, "epoch": 0.3688135593220339, "percentage": 36.96, "elapsed_time": "0:24:53", "remaining_time": "0:42:28"}
+{"current_steps": 103, "total_steps": 276, "loss": 0.6837, "lr": 3.979692616967543e-06, "epoch": 0.37242937853107344, "percentage": 37.32, "elapsed_time": "0:25:08", "remaining_time": "0:42:12"}
+{"current_steps": 104, "total_steps": 276, "loss": 0.6875, "lr": 3.9540482420327845e-06, "epoch": 0.37604519774011297, "percentage": 37.68, "elapsed_time": "0:25:22", "remaining_time": "0:41:57"}
+{"current_steps": 105, "total_steps": 276, "loss": 0.6901, "lr": 3.9281705377369814e-06, "epoch": 0.37966101694915255, "percentage": 38.04, "elapsed_time": "0:25:37", "remaining_time": "0:41:43"}
+{"current_steps": 106, "total_steps": 276, "loss": 0.6792, "lr": 3.902063656644012e-06, "epoch": 0.3832768361581921, "percentage": 38.41, "elapsed_time": "0:25:52", "remaining_time": "0:41:29"}
+{"current_steps": 107, "total_steps": 276, "loss": 0.6876, "lr": 3.875731788093478e-06, "epoch": 0.38689265536723166, "percentage": 38.77, "elapsed_time": "0:26:08", "remaining_time": "0:41:17"}
+{"current_steps": 108, "total_steps": 276, "loss": 0.6761, "lr": 3.84917915752845e-06, "epoch": 0.3905084745762712, "percentage": 39.13, "elapsed_time": "0:26:22", "remaining_time": "0:41:01"}
+{"current_steps": 109, "total_steps": 276, "loss": 0.6838, "lr": 3.8224100258174066e-06, "epoch": 0.3941242937853107, "percentage": 39.49, "elapsed_time": "0:26:37", "remaining_time": "0:40:46"}
+{"current_steps": 110, "total_steps": 276, "loss": 0.684, "lr": 3.795428688570505e-06, "epoch": 0.3977401129943503, "percentage": 39.86, "elapsed_time": "0:26:51", "remaining_time": "0:40:32"}
+{"current_steps": 111, "total_steps": 276, "loss": 0.6824, "lr": 3.7682394754502687e-06, "epoch": 0.40135593220338983, "percentage": 40.22, "elapsed_time": "0:27:05", "remaining_time": "0:40:16"}
+{"current_steps": 112, "total_steps": 276, "loss": 0.6969, "lr": 3.7408467494768104e-06, "epoch": 0.40497175141242936, "percentage": 40.58, "elapsed_time": "0:27:19", "remaining_time": "0:40:01"}
+{"current_steps": 113, "total_steps": 276, "loss": 0.7097, "lr": 3.7132549063277033e-06, "epoch": 0.40858757062146894, "percentage": 40.94, "elapsed_time": "0:27:34", "remaining_time": "0:39:46"}
+{"current_steps": 114, "total_steps": 276, "loss": 0.6746, "lr": 3.685468373632613e-06, "epoch": 0.41220338983050847, "percentage": 41.3, "elapsed_time": "0:27:48", "remaining_time": "0:39:31"}
+{"current_steps": 115, "total_steps": 276, "loss": 0.6448, "lr": 3.657491610262802e-06, "epoch": 0.415819209039548, "percentage": 41.67, "elapsed_time": "0:28:03", "remaining_time": "0:39:17"}
+{"current_steps": 116, "total_steps": 276, "loss": 0.6819, "lr": 3.6293291056156178e-06, "epoch": 0.4194350282485876, "percentage": 42.03, "elapsed_time": "0:28:17", "remaining_time": "0:39:01"}
+{"current_steps": 117, "total_steps": 276, "loss": 0.6876, "lr": 3.600985378894086e-06, "epoch": 0.4230508474576271, "percentage": 42.39, "elapsed_time": "0:28:33", "remaining_time": "0:38:47"}
+{"current_steps": 118, "total_steps": 276, "loss": 0.684, "lr": 3.572464978381719e-06, "epoch": 0.4266666666666667, "percentage": 42.75, "elapsed_time": "0:28:47", "remaining_time": "0:38:32"}
+{"current_steps": 119, "total_steps": 276, "loss": 0.6505, "lr": 3.5437724807126583e-06, "epoch": 0.4302824858757062, "percentage": 43.12, "elapsed_time": "0:29:01", "remaining_time": "0:38:18"}
+{"current_steps": 120, "total_steps": 276, "loss": 0.6357, "lr": 3.514912490137268e-06, "epoch": 0.43389830508474575, "percentage": 43.48, "elapsed_time": "0:29:16", "remaining_time": "0:38:03"}
+{"current_steps": 121, "total_steps": 276, "loss": 0.6716, "lr": 3.4858896377832966e-06, "epoch": 0.43751412429378533, "percentage": 43.84, "elapsed_time": "0:29:30", "remaining_time": "0:37:47"}
+{"current_steps": 122, "total_steps": 276, "loss": 0.6749, "lr": 3.4567085809127247e-06, "epoch": 0.44112994350282486, "percentage": 44.2, "elapsed_time": "0:29:44", "remaining_time": "0:37:32"}
+{"current_steps": 123, "total_steps": 276, "loss": 0.6675, "lr": 3.42737400217442e-06, "epoch": 0.4447457627118644, "percentage": 44.57, "elapsed_time": "0:29:58", "remaining_time": "0:37:17"}
+{"current_steps": 124, "total_steps": 276, "loss": 0.6795, "lr": 3.397890608852718e-06, "epoch": 0.448361581920904, "percentage": 44.93, "elapsed_time": "0:30:13", "remaining_time": "0:37:03"}
+{"current_steps": 125, "total_steps": 276, "loss": 0.6834, "lr": 3.3682631321120507e-06, "epoch": 0.4519774011299435, "percentage": 45.29, "elapsed_time": "0:30:27", "remaining_time": "0:36:47"}
+{"current_steps": 126, "total_steps": 276, "loss": 0.6546, "lr": 3.3384963262377434e-06, "epoch": 0.45559322033898303, "percentage": 45.65, "elapsed_time": "0:30:42", "remaining_time": "0:36:33"}
+{"current_steps": 127, "total_steps": 276, "loss": 0.6687, "lr": 3.3085949678730953e-06, "epoch": 0.4592090395480226, "percentage": 46.01, "elapsed_time": "0:30:56", "remaining_time": "0:36:18"}
+{"current_steps": 128, "total_steps": 276, "loss": 0.6927, "lr": 3.278563855252885e-06, "epoch": 0.46282485875706214, "percentage": 46.38, "elapsed_time": "0:31:11", "remaining_time": "0:36:03"}
+{"current_steps": 129, "total_steps": 276, "loss": 0.6843, "lr": 3.248407807433396e-06, "epoch": 0.46644067796610167, "percentage": 46.74, "elapsed_time": "0:31:25", "remaining_time": "0:35:48"}
+{"current_steps": 130, "total_steps": 276, "loss": 0.6639, "lr": 3.2181316635191125e-06, "epoch": 0.47005649717514125, "percentage": 47.1, "elapsed_time": "0:31:40", "remaining_time": "0:35:34"}
+{"current_steps": 131, "total_steps": 276, "loss": 0.6655, "lr": 3.1877402818861954e-06, "epoch": 0.4736723163841808, "percentage": 47.46, "elapsed_time": "0:31:54", "remaining_time": "0:35:19"}
+{"current_steps": 132, "total_steps": 276, "loss": 0.6648, "lr": 3.157238539402862e-06, "epoch": 0.47728813559322036, "percentage": 47.83, "elapsed_time": "0:32:08", "remaining_time": "0:35:04"}
+{"current_steps": 133, "total_steps": 276, "loss": 0.6793, "lr": 3.1266313306468018e-06, "epoch": 0.4809039548022599, "percentage": 48.19, "elapsed_time": "0:32:23", "remaining_time": "0:34:49"}
+{"current_steps": 134, "total_steps": 276, "loss": 0.6808, "lr": 3.095923567119748e-06, "epoch": 0.4845197740112994, "percentage": 48.55, "elapsed_time": "0:32:37", "remaining_time": "0:34:34"}
+{"current_steps": 135, "total_steps": 276, "loss": 0.669, "lr": 3.0651201764593375e-06, "epoch": 0.488135593220339, "percentage": 48.91, "elapsed_time": "0:32:52", "remaining_time": "0:34:19"}
+{"current_steps": 136, "total_steps": 276, "loss": 0.6685, "lr": 3.034226101648377e-06, "epoch": 0.49175141242937853, "percentage": 49.28, "elapsed_time": "0:33:07", "remaining_time": "0:34:06"}
+{"current_steps": 137, "total_steps": 276, "loss": 0.6803, "lr": 3.0032463002216504e-06, "epoch": 0.49536723163841806, "percentage": 49.64, "elapsed_time": "0:33:22", "remaining_time": "0:33:52"}
+{"current_steps": 138, "total_steps": 276, "loss": 0.6293, "lr": 2.972185743470386e-06, "epoch": 0.49898305084745764, "percentage": 50.0, "elapsed_time": "0:33:38", "remaining_time": "0:33:38"}
+{"current_steps": 139, "total_steps": 276, "loss": 0.6981, "lr": 2.941049415644522e-06, "epoch": 0.5025988700564972, "percentage": 50.36, "elapsed_time": "0:33:53", "remaining_time": "0:33:24"}
+{"current_steps": 140, "total_steps": 276, "loss": 0.6738, "lr": 2.909842313152888e-06, "epoch": 0.5062146892655367, "percentage": 50.72, "elapsed_time": "0:34:08", "remaining_time": "0:33:10"}
+{"current_steps": 141, "total_steps": 276, "loss": 0.7131, "lr": 2.878569443761442e-06, "epoch": 0.5098305084745762, "percentage": 51.09, "elapsed_time": "0:34:23", "remaining_time": "0:32:55"}
+{"current_steps": 142, "total_steps": 276, "loss": 0.7016, "lr": 2.847235825789673e-06, "epoch": 0.5134463276836159, "percentage": 51.45, "elapsed_time": "0:34:38", "remaining_time": "0:32:41"}
+{"current_steps": 143, "total_steps": 276, "loss": 0.6724, "lr": 2.8158464873053236e-06, "epoch": 0.5170621468926554, "percentage": 51.81, "elapsed_time": "0:34:53", "remaining_time": "0:32:27"}
+{"current_steps": 144, "total_steps": 276, "loss": 0.6662, "lr": 2.784406465317538e-06, "epoch": 0.5206779661016949, "percentage": 52.17, "elapsed_time": "0:35:07", "remaining_time": "0:32:12"}
+{"current_steps": 145, "total_steps": 276, "loss": 0.6631, "lr": 2.752920804968581e-06, "epoch": 0.5242937853107345, "percentage": 52.54, "elapsed_time": "0:35:22", "remaining_time": "0:31:57"}
+{"current_steps": 146, "total_steps": 276, "loss": 0.6513, "lr": 2.7213945587242507e-06, "epoch": 0.527909604519774, "percentage": 52.9, "elapsed_time": "0:35:37", "remaining_time": "0:31:43"}
+{"current_steps": 147, "total_steps": 276, "loss": 0.6555, "lr": 2.689832785563116e-06, "epoch": 0.5315254237288135, "percentage": 53.26, "elapsed_time": "0:35:52", "remaining_time": "0:31:29"}
+{"current_steps": 148, "total_steps": 276, "loss": 0.6661, "lr": 2.658240550164704e-06, "epoch": 0.5351412429378531, "percentage": 53.62, "elapsed_time": "0:36:07", "remaining_time": "0:31:14"}
+{"current_steps": 149, "total_steps": 276, "loss": 0.6621, "lr": 2.626622922096782e-06, "epoch": 0.5387570621468927, "percentage": 53.99, "elapsed_time": "0:36:21", "remaining_time": "0:30:59"}
+{"current_steps": 150, "total_steps": 276, "loss": 0.6758, "lr": 2.5949849750018486e-06, "epoch": 0.5423728813559322, "percentage": 54.35, "elapsed_time": "0:36:37", "remaining_time": "0:30:45"}
+{"current_steps": 151, "total_steps": 276, "loss": 0.6559, "lr": 2.56333178578297e-06, "epoch": 0.5459887005649717, "percentage": 54.71, "elapsed_time": "0:36:51", "remaining_time": "0:30:30"}
+{"current_steps": 152, "total_steps": 276, "loss": 0.6232, "lr": 2.5316684337891005e-06, "epoch": 0.5496045197740113, "percentage": 55.07, "elapsed_time": "0:37:06", "remaining_time": "0:30:16"}
+{"current_steps": 153, "total_steps": 276, "loss": 0.6373, "lr": 2.5e-06, "epoch": 0.5532203389830509, "percentage": 55.43, "elapsed_time": "0:37:21", "remaining_time": "0:30:01"}
+{"current_steps": 154, "total_steps": 276, "loss": 0.6779, "lr": 2.4683315662109003e-06, "epoch": 0.5568361581920904, "percentage": 55.8, "elapsed_time": "0:37:35", "remaining_time": "0:29:46"}
+{"current_steps": 155, "total_steps": 276, "loss": 0.654, "lr": 2.436668214217031e-06, "epoch": 0.56045197740113, "percentage": 56.16, "elapsed_time": "0:37:50", "remaining_time": "0:29:32"}
+{"current_steps": 156, "total_steps": 276, "loss": 0.6625, "lr": 2.4050150249981522e-06, "epoch": 0.5640677966101695, "percentage": 56.52, "elapsed_time": "0:38:05", "remaining_time": "0:29:17"}
+{"current_steps": 157, "total_steps": 276, "loss": 0.6862, "lr": 2.3733770779032185e-06, "epoch": 0.567683615819209, "percentage": 56.88, "elapsed_time": "0:38:19", "remaining_time": "0:29:02"}
+{"current_steps": 158, "total_steps": 276, "loss": 0.669, "lr": 2.341759449835297e-06, "epoch": 0.5712994350282485, "percentage": 57.25, "elapsed_time": "0:38:35", "remaining_time": "0:28:48"}
+{"current_steps": 159, "total_steps": 276, "loss": 0.6389, "lr": 2.310167214436885e-06, "epoch": 0.5749152542372882, "percentage": 57.61, "elapsed_time": "0:38:49", "remaining_time": "0:28:34"}
+{"current_steps": 160, "total_steps": 276, "loss": 0.6472, "lr": 2.27860544127575e-06, "epoch": 0.5785310734463277, "percentage": 57.97, "elapsed_time": "0:39:03", "remaining_time": "0:28:19"}
+{"current_steps": 161, "total_steps": 276, "loss": 0.6579, "lr": 2.24707919503142e-06, "epoch": 0.5821468926553672, "percentage": 58.33, "elapsed_time": "0:39:19", "remaining_time": "0:28:05"}
+{"current_steps": 162, "total_steps": 276, "loss": 0.6481, "lr": 2.2155935346824634e-06, "epoch": 0.5857627118644068, "percentage": 58.7, "elapsed_time": "0:39:34", "remaining_time": "0:27:50"}
+{"current_steps": 163, "total_steps": 276, "loss": 0.6535, "lr": 2.1841535126946777e-06, "epoch": 0.5893785310734463, "percentage": 59.06, "elapsed_time": "0:39:49", "remaining_time": "0:27:36"}
+{"current_steps": 164, "total_steps": 276, "loss": 0.6707, "lr": 2.1527641742103282e-06, "epoch": 0.5929943502824859, "percentage": 59.42, "elapsed_time": "0:40:04", "remaining_time": "0:27:22"}
+{"current_steps": 165, "total_steps": 276, "loss": 0.6663, "lr": 2.1214305562385592e-06, "epoch": 0.5966101694915255, "percentage": 59.78, "elapsed_time": "0:40:19", "remaining_time": "0:27:07"}
+{"current_steps": 166, "total_steps": 276, "loss": 0.6747, "lr": 2.0901576868471125e-06, "epoch": 0.600225988700565, "percentage": 60.14, "elapsed_time": "0:40:34", "remaining_time": "0:26:53"}
+{"current_steps": 167, "total_steps": 276, "loss": 0.6512, "lr": 2.05895058435548e-06, "epoch": 0.6038418079096045, "percentage": 60.51, "elapsed_time": "0:40:49", "remaining_time": "0:26:38"}
+{"current_steps": 168, "total_steps": 276, "loss": 0.6324, "lr": 2.0278142565296153e-06, "epoch": 0.607457627118644, "percentage": 60.87, "elapsed_time": "0:41:03", "remaining_time": "0:26:23"}
+{"current_steps": 169, "total_steps": 276, "loss": 0.6679, "lr": 1.9967536997783495e-06, "epoch": 0.6110734463276836, "percentage": 61.23, "elapsed_time": "0:41:18", "remaining_time": "0:26:09"}
+{"current_steps": 170, "total_steps": 276, "loss": 0.6729, "lr": 1.9657738983516227e-06, "epoch": 0.6146892655367232, "percentage": 61.59, "elapsed_time": "0:41:32", "remaining_time": "0:25:54"}
+{"current_steps": 171, "total_steps": 276, "loss": 0.6493, "lr": 1.934879823540663e-06, "epoch": 0.6183050847457627, "percentage": 61.96, "elapsed_time": "0:41:47", "remaining_time": "0:25:39"}
+{"current_steps": 172, "total_steps": 276, "loss": 0.6398, "lr": 1.9040764328802523e-06, "epoch": 0.6219209039548023, "percentage": 62.32, "elapsed_time": "0:42:01", "remaining_time": "0:25:24"}
+{"current_steps": 173, "total_steps": 276, "loss": 0.6582, "lr": 1.8733686693531986e-06, "epoch": 0.6255367231638418, "percentage": 62.68, "elapsed_time": "0:42:15", "remaining_time": "0:25:09"}
+{"current_steps": 174, "total_steps": 276, "loss": 0.6532, "lr": 1.842761460597138e-06, "epoch": 0.6291525423728813, "percentage": 63.04, "elapsed_time": "0:42:29", "remaining_time": "0:24:54"}
+{"current_steps": 175, "total_steps": 276, "loss": 0.6603, "lr": 1.812259718113805e-06, "epoch": 0.632768361581921, "percentage": 63.41, "elapsed_time": "0:42:44", "remaining_time": "0:24:39"}
+{"current_steps": 176, "total_steps": 276, "loss": 0.658, "lr": 1.7818683364808883e-06, "epoch": 0.6363841807909605, "percentage": 63.77, "elapsed_time": "0:42:58", "remaining_time": "0:24:25"}
+{"current_steps": 177, "total_steps": 276, "loss": 0.6317, "lr": 1.7515921925666053e-06, "epoch": 0.64, "percentage": 64.13, "elapsed_time": "0:43:14", "remaining_time": "0:24:10"}
+{"current_steps": 178, "total_steps": 276, "loss": 0.677, "lr": 1.7214361447471156e-06, "epoch": 0.6436158192090395, "percentage": 64.49, "elapsed_time": "0:43:28", "remaining_time": "0:23:55"}
+{"current_steps": 179, "total_steps": 276, "loss": 0.6736, "lr": 1.6914050321269049e-06, "epoch": 0.6472316384180791, "percentage": 64.86, "elapsed_time": "0:43:42", "remaining_time": "0:23:41"}
+{"current_steps": 180, "total_steps": 276, "loss": 0.6802, "lr": 1.6615036737622574e-06, "epoch": 0.6508474576271186, "percentage": 65.22, "elapsed_time": "0:43:56", "remaining_time": "0:23:26"}
+{"current_steps": 181, "total_steps": 276, "loss": 0.646, "lr": 1.6317368678879497e-06, "epoch": 0.6544632768361582, "percentage": 65.58, "elapsed_time": "0:44:12", "remaining_time": "0:23:12"}
+{"current_steps": 182, "total_steps": 276, "loss": 0.6502, "lr": 1.6021093911472825e-06, "epoch": 0.6580790960451978, "percentage": 65.94, "elapsed_time": "0:44:26", "remaining_time": "0:22:57"}
+{"current_steps": 183, "total_steps": 276, "loss": 0.6392, "lr": 1.572625997825581e-06, "epoch": 0.6616949152542373, "percentage": 66.3, "elapsed_time": "0:44:41", "remaining_time": "0:22:42"}
+{"current_steps": 184, "total_steps": 276, "loss": 0.6478, "lr": 1.5432914190872757e-06, "epoch": 0.6653107344632768, "percentage": 66.67, "elapsed_time": "0:44:57", "remaining_time": "0:22:28"}
+{"current_steps": 185, "total_steps": 276, "loss": 0.6624, "lr": 1.5141103622167042e-06, "epoch": 0.6689265536723163, "percentage": 67.03, "elapsed_time": "0:45:13", "remaining_time": "0:22:14"}
+{"current_steps": 186, "total_steps": 276, "loss": 0.6519, "lr": 1.4850875098627326e-06, "epoch": 0.672542372881356, "percentage": 67.39, "elapsed_time": "0:45:27", "remaining_time": "0:21:59"}
+{"current_steps": 187, "total_steps": 276, "loss": 0.6382, "lr": 1.456227519287343e-06, "epoch": 0.6761581920903955, "percentage": 67.75, "elapsed_time": "0:45:41", "remaining_time": "0:21:44"}
+{"current_steps": 188, "total_steps": 276, "loss": 0.6391, "lr": 1.4275350216182824e-06, "epoch": 0.679774011299435, "percentage": 68.12, "elapsed_time": "0:45:56", "remaining_time": "0:21:30"}
+{"current_steps": 189, "total_steps": 276, "loss": 0.6456, "lr": 1.3990146211059141e-06, "epoch": 0.6833898305084746, "percentage": 68.48, "elapsed_time": "0:46:11", "remaining_time": "0:21:15"}
+{"current_steps": 190, "total_steps": 276, "loss": 0.6441, "lr": 1.3706708943843822e-06, "epoch": 0.6870056497175141, "percentage": 68.84, "elapsed_time": "0:46:25", "remaining_time": "0:21:00"}
+{"current_steps": 191, "total_steps": 276, "loss": 0.6603, "lr": 1.3425083897371983e-06, "epoch": 0.6906214689265536, "percentage": 69.2, "elapsed_time": "0:46:40", "remaining_time": "0:20:46"}
+{"current_steps": 192, "total_steps": 276, "loss": 0.6721, "lr": 1.3145316263673874e-06, "epoch": 0.6942372881355933, "percentage": 69.57, "elapsed_time": "0:46:54", "remaining_time": "0:20:31"}
+{"current_steps": 193, "total_steps": 276, "loss": 0.649, "lr": 1.286745093672298e-06, "epoch": 0.6978531073446328, "percentage": 69.93, "elapsed_time": "0:47:09", "remaining_time": "0:20:16"}
+{"current_steps": 194, "total_steps": 276, "loss": 0.6573, "lr": 1.2591532505231906e-06, "epoch": 0.7014689265536723, "percentage": 70.29, "elapsed_time": "0:47:23", "remaining_time": "0:20:02"}
+{"current_steps": 195, "total_steps": 276, "loss": 0.6727, "lr": 1.2317605245497324e-06, "epoch": 0.7050847457627119, "percentage": 70.65, "elapsed_time": "0:47:37", "remaining_time": "0:19:47"}
+{"current_steps": 196, "total_steps": 276, "loss": 0.6131, "lr": 1.204571311429496e-06, "epoch": 0.7087005649717514, "percentage": 71.01, "elapsed_time": "0:47:52", "remaining_time": "0:19:32"}
+{"current_steps": 197, "total_steps": 276, "loss": 0.6434, "lr": 1.1775899741825947e-06, "epoch": 0.7123163841807909, "percentage": 71.38, "elapsed_time": "0:48:06", "remaining_time": "0:19:17"}
+{"current_steps": 198, "total_steps": 276, "loss": 0.656, "lr": 1.1508208424715511e-06, "epoch": 0.7159322033898305, "percentage": 71.74, "elapsed_time": "0:48:21", "remaining_time": "0:19:03"}
+{"current_steps": 199, "total_steps": 276, "loss": 0.6613, "lr": 1.1242682119065217e-06, "epoch": 0.7195480225988701, "percentage": 72.1, "elapsed_time": "0:48:37", "remaining_time": "0:18:48"}
+{"current_steps": 200, "total_steps": 276, "loss": 0.6577, "lr": 1.0979363433559892e-06, "epoch": 0.7231638418079096, "percentage": 72.46, "elapsed_time": "0:48:53", "remaining_time": "0:18:34"}
+{"current_steps": 201, "total_steps": 276, "loss": 0.6905, "lr": 1.0718294622630188e-06, "epoch": 0.7267796610169491, "percentage": 72.83, "elapsed_time": "0:50:27", "remaining_time": "0:18:49"}
+{"current_steps": 202, "total_steps": 276, "loss": 0.6448, "lr": 1.045951757967215e-06, "epoch": 0.7303954802259887, "percentage": 73.19, "elapsed_time": "0:50:41", "remaining_time": "0:18:34"}
+{"current_steps": 203, "total_steps": 276, "loss": 0.6395, "lr": 1.0203073830324566e-06, "epoch": 0.7340112994350283, "percentage": 73.55, "elapsed_time": "0:50:55", "remaining_time": "0:18:18"}
+{"current_steps": 204, "total_steps": 276, "loss": 0.6148, "lr": 9.949004525805423e-07, "epoch": 0.7376271186440678, "percentage": 73.91, "elapsed_time": "0:51:10", "remaining_time": "0:18:03"}
+{"current_steps": 205, "total_steps": 276, "loss": 0.6322, "lr": 9.697350436308428e-07, "epoch": 0.7412429378531074, "percentage": 74.28, "elapsed_time": "0:51:24", "remaining_time": "0:17:48"}
+{"current_steps": 206, "total_steps": 276, "loss": 0.6835, "lr": 9.448151944460657e-07, "epoch": 0.7448587570621469, "percentage": 74.64, "elapsed_time": "0:51:38", "remaining_time": "0:17:32"}
+{"current_steps": 207, "total_steps": 276, "loss": 0.6713, "lr": 9.201449038842403e-07, "epoch": 0.7484745762711864, "percentage": 75.0, "elapsed_time": "0:51:53", "remaining_time": "0:17:17"}
+{"current_steps": 208, "total_steps": 276, "loss": 0.6349, "lr": 8.957281307570254e-07, "epoch": 0.7520903954802259, "percentage": 75.36, "elapsed_time": "0:52:07", "remaining_time": "0:17:02"}
+{"current_steps": 209, "total_steps": 276, "loss": 0.6395, "lr": 8.71568793194445e-07, "epoch": 0.7557062146892656, "percentage": 75.72, "elapsed_time": "0:52:22", "remaining_time": "0:16:47"}
+{"current_steps": 210, "total_steps": 276, "loss": 0.6566, "lr": 8.476707680161486e-07, "epoch": 0.7593220338983051, "percentage": 76.09, "elapsed_time": "0:52:36", "remaining_time": "0:16:31"}
+{"current_steps": 211, "total_steps": 276, "loss": 0.6498, "lr": 8.240378901093035e-07, "epoch": 0.7629378531073446, "percentage": 76.45, "elapsed_time": "0:52:50", "remaining_time": "0:16:16"}
+{"current_steps": 212, "total_steps": 276, "loss": 0.6702, "lr": 8.006739518132179e-07, "epoch": 0.7665536723163842, "percentage": 76.81, "elapsed_time": "0:53:05", "remaining_time": "0:16:01"}
+{"current_steps": 213, "total_steps": 276, "loss": 0.6403, "lr": 7.775827023107835e-07, "epoch": 0.7701694915254237, "percentage": 77.17, "elapsed_time": "0:53:19", "remaining_time": "0:15:46"}
+{"current_steps": 214, "total_steps": 276, "loss": 0.6492, "lr": 7.547678470268526e-07, "epoch": 0.7737853107344633, "percentage": 77.54, "elapsed_time": "0:53:34", "remaining_time": "0:15:31"}
+{"current_steps": 215, "total_steps": 276, "loss": 0.6289, "lr": 7.322330470336314e-07, "epoch": 0.7774011299435029, "percentage": 77.9, "elapsed_time": "0:53:49", "remaining_time": "0:15:16"}
+{"current_steps": 216, "total_steps": 276, "loss": 0.6393, "lr": 7.099819184631929e-07, "epoch": 0.7810169491525424, "percentage": 78.26, "elapsed_time": "0:54:03", "remaining_time": "0:15:00"}
+{"current_steps": 217, "total_steps": 276, "loss": 0.6429, "lr": 6.880180319272006e-07, "epoch": 0.7846327683615819, "percentage": 78.62, "elapsed_time": "0:54:17", "remaining_time": "0:14:45"}
+{"current_steps": 218, "total_steps": 276, "loss": 0.6652, "lr": 6.663449119439358e-07, "epoch": 0.7882485875706214, "percentage": 78.99, "elapsed_time": "0:54:32", "remaining_time": "0:14:30"}
+{"current_steps": 219, "total_steps": 276, "loss": 0.6424, "lr": 6.449660363727236e-07, "epoch": 0.791864406779661, "percentage": 79.35, "elapsed_time": "0:54:47", "remaining_time": "0:14:15"}
+{"current_steps": 220, "total_steps": 276, "loss": 0.6409, "lr": 6.238848358558439e-07, "epoch": 0.7954802259887006, "percentage": 79.71, "elapsed_time": "0:55:02", "remaining_time": "0:14:00"}
+{"current_steps": 221, "total_steps": 276, "loss": 0.6815, "lr": 6.031046932680229e-07, "epoch": 0.7990960451977401, "percentage": 80.07, "elapsed_time": "0:55:16", "remaining_time": "0:13:45"}
+{"current_steps": 222, "total_steps": 276, "loss": 0.6489, "lr": 5.826289431735832e-07, "epoch": 0.8027118644067797, "percentage": 80.43, "elapsed_time": "0:55:31", "remaining_time": "0:13:30"}
+{"current_steps": 223, "total_steps": 276, "loss": 0.6298, "lr": 5.624608712913531e-07, "epoch": 0.8063276836158192, "percentage": 80.8, "elapsed_time": "0:55:45", "remaining_time": "0:13:15"}
+{"current_steps": 224, "total_steps": 276, "loss": 0.6509, "lr": 5.426037139674117e-07, "epoch": 0.8099435028248587, "percentage": 81.16, "elapsed_time": "0:55:59", "remaining_time": "0:12:59"}
+{"current_steps": 225, "total_steps": 276, "loss": 0.6573, "lr": 5.23060657655754e-07, "epoch": 0.8135593220338984, "percentage": 81.52, "elapsed_time": "0:56:14", "remaining_time": "0:12:44"}
+{"current_steps": 226, "total_steps": 276, "loss": 0.633, "lr": 5.038348384069663e-07, "epoch": 0.8171751412429379, "percentage": 81.88, "elapsed_time": "0:56:28", "remaining_time": "0:12:29"}
+{"current_steps": 227, "total_steps": 276, "loss": 0.6754, "lr": 4.84929341364988e-07, "epoch": 0.8207909604519774, "percentage": 82.25, "elapsed_time": "0:56:44", "remaining_time": "0:12:14"}
+{"current_steps": 228, "total_steps": 276, "loss": 0.6614, "lr": 4.6634720027204093e-07, "epoch": 0.8244067796610169, "percentage": 82.61, "elapsed_time": "0:56:58", "remaining_time": "0:11:59"}
+{"current_steps": 229, "total_steps": 276, "loss": 0.6281, "lr": 4.480913969818099e-07, "epoch": 0.8280225988700565, "percentage": 82.97, "elapsed_time": "0:57:12", "remaining_time": "0:11:44"}
+{"current_steps": 230, "total_steps": 276, "loss": 0.6161, "lr": 4.3016486098094667e-07, "epoch": 0.831638418079096, "percentage": 83.33, "elapsed_time": "0:57:27", "remaining_time": "0:11:29"}
+{"current_steps": 231, "total_steps": 276, "loss": 0.6247, "lr": 4.125704689189819e-07, "epoch": 0.8352542372881356, "percentage": 83.7, "elapsed_time": "0:57:42", "remaining_time": "0:11:14"}
+{"current_steps": 232, "total_steps": 276, "loss": 0.6586, "lr": 3.953110441467073e-07, "epoch": 0.8388700564971752, "percentage": 84.06, "elapsed_time": "0:57:57", "remaining_time": "0:10:59"}
+{"current_steps": 233, "total_steps": 276, "loss": 0.6463, "lr": 3.7838935626312246e-07, "epoch": 0.8424858757062147, "percentage": 84.42, "elapsed_time": "0:58:12", "remaining_time": "0:10:44"}
+{"current_steps": 234, "total_steps": 276, "loss": 0.6726, "lr": 3.6180812067099477e-07, "epoch": 0.8461016949152542, "percentage": 84.78, "elapsed_time": "0:58:27", "remaining_time": "0:10:29"}
+{"current_steps": 235, "total_steps": 276, "loss": 0.6378, "lr": 3.455699981411259e-07, "epoch": 0.8497175141242937, "percentage": 85.14, "elapsed_time": "0:58:41", "remaining_time": "0:10:14"}
+{"current_steps": 236, "total_steps": 276, "loss": 0.6381, "lr": 3.296775943853789e-07, "epoch": 0.8533333333333334, "percentage": 85.51, "elapsed_time": "0:58:56", "remaining_time": "0:09:59"}
+{"current_steps": 237, "total_steps": 276, "loss": 0.6361, "lr": 3.141334596385448e-07, "epoch": 0.8569491525423729, "percentage": 85.87, "elapsed_time": "0:59:10", "remaining_time": "0:09:44"}
+{"current_steps": 238, "total_steps": 276, "loss": 0.6311, "lr": 2.9894008824910726e-07, "epoch": 0.8605649717514124, "percentage": 86.23, "elapsed_time": "0:59:24", "remaining_time": "0:09:29"}
+{"current_steps": 239, "total_steps": 276, "loss": 0.6584, "lr": 2.840999182789797e-07, "epoch": 0.864180790960452, "percentage": 86.59, "elapsed_time": "0:59:39", "remaining_time": "0:09:14"}
+{"current_steps": 240, "total_steps": 276, "loss": 0.6275, "lr": 2.696153311122704e-07, "epoch": 0.8677966101694915, "percentage": 86.96, "elapsed_time": "0:59:53", "remaining_time": "0:08:59"}
+{"current_steps": 241, "total_steps": 276, "loss": 0.6574, "lr": 2.5548865107314606e-07, "epoch": 0.871412429378531, "percentage": 87.32, "elapsed_time": "1:00:07", "remaining_time": "0:08:43"}
+{"current_steps": 242, "total_steps": 276, "loss": 0.6394, "lr": 2.4172214505285006e-07, "epoch": 0.8750282485875707, "percentage": 87.68, "elapsed_time": "1:00:22", "remaining_time": "0:08:28"}
+{"current_steps": 243, "total_steps": 276, "loss": 0.6352, "lr": 2.2831802214593774e-07, "epoch": 0.8786440677966102, "percentage": 88.04, "elapsed_time": "1:00:37", "remaining_time": "0:08:13"}
+{"current_steps": 244, "total_steps": 276, "loss": 0.6332, "lr": 2.1527843329578328e-07, "epoch": 0.8822598870056497, "percentage": 88.41, "elapsed_time": "1:00:51", "remaining_time": "0:07:58"}
+{"current_steps": 245, "total_steps": 276, "loss": 0.6488, "lr": 2.026054709494235e-07, "epoch": 0.8858757062146893, "percentage": 88.77, "elapsed_time": "1:01:06", "remaining_time": "0:07:43"}
+{"current_steps": 246, "total_steps": 276, "loss": 0.6268, "lr": 1.9030116872178317e-07, "epoch": 0.8894915254237288, "percentage": 89.13, "elapsed_time": "1:01:20", "remaining_time": "0:07:28"}
+{"current_steps": 247, "total_steps": 276, "loss": 0.6098, "lr": 1.7836750106934475e-07, "epoch": 0.8931073446327683, "percentage": 89.49, "elapsed_time": "1:01:34", "remaining_time": "0:07:13"}
+{"current_steps": 248, "total_steps": 276, "loss": 0.6328, "lr": 1.6680638297330854e-07, "epoch": 0.896723163841808, "percentage": 89.86, "elapsed_time": "1:01:49", "remaining_time": "0:06:58"}
+{"current_steps": 249, "total_steps": 276, "loss": 0.6353, "lr": 1.5561966963229925e-07, "epoch": 0.9003389830508475, "percentage": 90.22, "elapsed_time": "1:02:03", "remaining_time": "0:06:43"}
+{"current_steps": 250, "total_steps": 276, "loss": 0.6212, "lr": 1.448091561646628e-07, "epoch": 0.903954802259887, "percentage": 90.58, "elapsed_time": "1:02:17", "remaining_time": "0:06:28"}
+{"current_steps": 251, "total_steps": 276, "loss": 0.6581, "lr": 1.3437657732040783e-07, "epoch": 0.9075706214689265, "percentage": 90.94, "elapsed_time": "1:02:31", "remaining_time": "0:06:13"}
+{"current_steps": 252, "total_steps": 276, "loss": 0.6483, "lr": 1.243236072028317e-07, "epoch": 0.9111864406779661, "percentage": 91.3, "elapsed_time": "1:02:46", "remaining_time": "0:05:58"}
+{"current_steps": 253, "total_steps": 276, "loss": 0.6688, "lr": 1.1465185899987797e-07, "epoch": 0.9148022598870057, "percentage": 91.67, "elapsed_time": "1:03:00", "remaining_time": "0:05:43"}
+{"current_steps": 254, "total_steps": 276, "loss": 0.6702, "lr": 1.0536288472527162e-07, "epoch": 0.9184180790960452, "percentage": 92.03, "elapsed_time": "1:03:15", "remaining_time": "0:05:28"}
+{"current_steps": 255, "total_steps": 276, "loss": 0.663, "lr": 9.645817496946902e-08, "epoch": 0.9220338983050848, "percentage": 92.39, "elapsed_time": "1:03:29", "remaining_time": "0:05:13"}
+{"current_steps": 256, "total_steps": 276, "loss": 0.64, "lr": 8.79391586604636e-08, "epoch": 0.9256497175141243, "percentage": 92.75, "elapsed_time": "1:03:44", "remaining_time": "0:04:58"}
+{"current_steps": 257, "total_steps": 276, "loss": 0.6335, "lr": 7.980720283448957e-08, "epoch": 0.9292655367231638, "percentage": 93.12, "elapsed_time": "1:03:59", "remaining_time": "0:04:43"}
+{"current_steps": 258, "total_steps": 276, "loss": 0.6403, "lr": 7.206361241665266e-08, "epoch": 0.9328813559322033, "percentage": 93.48, "elapsed_time": "1:04:14", "remaining_time": "0:04:28"}
+{"current_steps": 259, "total_steps": 276, "loss": 0.6383, "lr": 6.470963001153268e-08, "epoch": 0.936497175141243, "percentage": 93.84, "elapsed_time": "1:04:29", "remaining_time": "0:04:13"}
+{"current_steps": 260, "total_steps": 276, "loss": 0.6485, "lr": 5.774643570378296e-08, "epoch": 0.9401129943502825, "percentage": 94.2, "elapsed_time": "1:04:43", "remaining_time": "0:03:58"}
+{"current_steps": 261, "total_steps": 276, "loss": 0.6479, "lr": 5.117514686876379e-08, "epoch": 0.943728813559322, "percentage": 94.57, "elapsed_time": "1:04:59", "remaining_time": "0:03:44"}
+{"current_steps": 262, "total_steps": 276, "loss": 0.6363, "lr": 4.4996817993239464e-08, "epoch": 0.9473446327683616, "percentage": 94.93, "elapsed_time": "1:05:13", "remaining_time": "0:03:29"}
+{"current_steps": 263, "total_steps": 276, "loss": 0.6417, "lr": 3.9212440506164465e-08, "epoch": 0.9509604519774011, "percentage": 95.29, "elapsed_time": "1:05:27", "remaining_time": "0:03:14"}
+{"current_steps": 264, "total_steps": 276, "loss": 0.676, "lr": 3.382294261959157e-08, "epoch": 0.9545762711864407, "percentage": 95.65, "elapsed_time": "1:05:41", "remaining_time": "0:02:59"}
+{"current_steps": 265, "total_steps": 276, "loss": 0.6502, "lr": 2.8829189179721552e-08, "epoch": 0.9581920903954803, "percentage": 96.01, "elapsed_time": "1:05:56", "remaining_time": "0:02:44"}
+{"current_steps": 266, "total_steps": 276, "loss": 0.6271, "lr": 2.423198152812306e-08, "epoch": 0.9618079096045198, "percentage": 96.38, "elapsed_time": "1:06:11", "remaining_time": "0:02:29"}
+{"current_steps": 267, "total_steps": 276, "loss": 0.6312, "lr": 2.0032057373142453e-08, "epoch": 0.9654237288135593, "percentage": 96.74, "elapsed_time": "1:06:25", "remaining_time": "0:02:14"}
+{"current_steps": 268, "total_steps": 276, "loss": 0.6313, "lr": 1.6230090671524312e-08, "epoch": 0.9690395480225988, "percentage": 97.1, "elapsed_time": "1:06:40", "remaining_time": "0:01:59"}
+{"current_steps": 269, "total_steps": 276, "loss": 0.6328, "lr": 1.2826691520262114e-08, "epoch": 0.9726553672316384, "percentage": 97.46, "elapsed_time": "1:06:55", "remaining_time": "0:01:44"}
+{"current_steps": 270, "total_steps": 276, "loss": 0.6247, "lr": 9.822406058697665e-09, "epoch": 0.976271186440678, "percentage": 97.83, "elapsed_time": "1:07:09", "remaining_time": "0:01:29"}
+{"current_steps": 271, "total_steps": 276, "loss": 0.6185, "lr": 7.217716380881479e-09, "epoch": 0.9798870056497175, "percentage": 98.19, "elapsed_time": "1:07:23", "remaining_time": "0:01:14"}
+{"current_steps": 272, "total_steps": 276, "loss": 0.6308, "lr": 5.0130404582127144e-09, "epoch": 0.9835028248587571, "percentage": 98.55, "elapsed_time": "1:07:38", "remaining_time": "0:00:59"}
+{"current_steps": 273, "total_steps": 276, "loss": 0.6383, "lr": 3.208732072368104e-09, "epoch": 0.9871186440677966, "percentage": 98.91, "elapsed_time": "1:07:52", "remaining_time": "0:00:44"}
+{"current_steps": 274, "total_steps": 276, "loss": 0.6559, "lr": 1.8050807585293095e-09, "epoch": 0.9907344632768361, "percentage": 99.28, "elapsed_time": "1:08:06", "remaining_time": "0:00:29"}
+{"current_steps": 275, "total_steps": 276, "loss": 0.6701, "lr": 8.023117589237017e-10, "epoch": 0.9943502824858758, "percentage": 99.64, "elapsed_time": "1:08:20", "remaining_time": "0:00:14"}
+{"current_steps": 276, "total_steps": 276, "loss": 0.6445, "lr": 2.0058598667854755e-10, "epoch": 0.9979661016949153, "percentage": 100.0, "elapsed_time": "1:08:35", "remaining_time": "0:00:00"}
+{"current_steps": 276, "total_steps": 276, "epoch": 0.9979661016949153, "percentage": 100.0, "elapsed_time": "1:09:54", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1975 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9979661016949153,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003615819209039548,
+      "grad_norm": 14.63072256054265,
+      "learning_rate": 0.0,
+      "loss": 1.4293,
+      "step": 1
+    },
+    {
+      "epoch": 0.007231638418079096,
+      "grad_norm": 13.703421994615557,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 1.4193,
+      "step": 2
+    },
+    {
+      "epoch": 0.010847457627118645,
+      "grad_norm": 13.716616968172858,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 1.3691,
+      "step": 3
+    },
+    {
+      "epoch": 0.014463276836158192,
+      "grad_norm": 13.81492601698403,
+      "learning_rate": 5.357142857142857e-07,
+      "loss": 1.4337,
+      "step": 4
+    },
+    {
+      "epoch": 0.01807909604519774,
+      "grad_norm": 13.013807610008277,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 1.335,
+      "step": 5
+    },
+    {
+      "epoch": 0.02169491525423729,
+      "grad_norm": 13.316675508543259,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 1.4104,
+      "step": 6
+    },
+    {
+      "epoch": 0.025310734463276835,
+      "grad_norm": 12.54293399835329,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 1.3364,
+      "step": 7
+    },
+    {
+      "epoch": 0.028926553672316384,
+      "grad_norm": 11.706383970770567,
+      "learning_rate": 1.25e-06,
+      "loss": 1.3289,
+      "step": 8
+    },
+    {
+      "epoch": 0.03254237288135593,
+      "grad_norm": 9.135561727877839,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.2395,
+      "step": 9
+    },
+    {
+      "epoch": 0.03615819209039548,
+      "grad_norm": 8.24371141549115,
+      "learning_rate": 1.6071428571428574e-06,
+      "loss": 1.2597,
+      "step": 10
+    },
+    {
+      "epoch": 0.03977401129943503,
+      "grad_norm": 5.641164800490142,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 1.1323,
+      "step": 11
+    },
+    {
+      "epoch": 0.04338983050847458,
+      "grad_norm": 5.154352679322036,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 1.1555,
+      "step": 12
+    },
+    {
+      "epoch": 0.04700564971751412,
+      "grad_norm": 4.902918571287102,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 1.1208,
+      "step": 13
+    },
+    {
+      "epoch": 0.05062146892655367,
+      "grad_norm": 4.651473817511105,
+      "learning_rate": 2.321428571428572e-06,
+      "loss": 1.1211,
+      "step": 14
+    },
+    {
+      "epoch": 0.05423728813559322,
+      "grad_norm": 7.855915558603105,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0921,
+      "step": 15
+    },
+    {
+      "epoch": 0.05785310734463277,
+      "grad_norm": 9.766906290977035,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 1.0519,
+      "step": 16
+    },
+    {
+      "epoch": 0.061468926553672316,
+      "grad_norm": 7.745681824751476,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.0559,
+      "step": 17
+    },
+    {
+      "epoch": 0.06508474576271187,
+      "grad_norm": 4.81594013217655,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 1.0629,
+      "step": 18
+    },
+    {
+      "epoch": 0.06870056497175141,
+      "grad_norm": 4.091417378072179,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 1.0244,
+      "step": 19
+    },
+    {
+      "epoch": 0.07231638418079096,
+      "grad_norm": 2.8101858455670237,
+      "learning_rate": 3.3928571428571435e-06,
+      "loss": 0.9697,
+      "step": 20
+    },
+    {
+      "epoch": 0.0759322033898305,
+      "grad_norm": 3.180728091735543,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.9601,
+      "step": 21
+    },
+    {
+      "epoch": 0.07954802259887006,
+      "grad_norm": 3.6493251911677658,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.9409,
+      "step": 22
+    },
+    {
+      "epoch": 0.0831638418079096,
+      "grad_norm": 3.415956781592975,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.9486,
+      "step": 23
+    },
+    {
+      "epoch": 0.08677966101694916,
+      "grad_norm": 3.0472462438826,
+      "learning_rate": 4.107142857142857e-06,
+      "loss": 0.8874,
+      "step": 24
+    },
+    {
+      "epoch": 0.0903954802259887,
+      "grad_norm": 2.264144754905512,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.8994,
+      "step": 25
+    },
+    {
+      "epoch": 0.09401129943502824,
+      "grad_norm": 2.191754581281806,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.8975,
+      "step": 26
+    },
+    {
+      "epoch": 0.0976271186440678,
+      "grad_norm": 2.3668184420746385,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.8581,
+      "step": 27
+    },
+    {
+      "epoch": 0.10124293785310734,
+      "grad_norm": 2.7515269578252193,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 0.8423,
+      "step": 28
+    },
+    {
+      "epoch": 0.1048587570621469,
+      "grad_norm": 2.3735525312849837,
+      "learning_rate": 5e-06,
+      "loss": 0.8205,
+      "step": 29
+    },
+    {
+      "epoch": 0.10847457627118644,
+      "grad_norm": 2.032163014842967,
+      "learning_rate": 4.999799414013322e-06,
+      "loss": 0.8754,
+      "step": 30
+    },
+    {
+      "epoch": 0.112090395480226,
+      "grad_norm": 2.0590504400576997,
+      "learning_rate": 4.999197688241076e-06,
+      "loss": 0.8267,
+      "step": 31
+    },
+    {
+      "epoch": 0.11570621468926554,
+      "grad_norm": 2.092420106610846,
+      "learning_rate": 4.998194919241471e-06,
+      "loss": 0.8312,
+      "step": 32
+    },
+    {
+      "epoch": 0.11932203389830509,
+      "grad_norm": 1.9381311525751297,
+      "learning_rate": 4.996791267927632e-06,
+      "loss": 0.7878,
+      "step": 33
+    },
+    {
+      "epoch": 0.12293785310734463,
+      "grad_norm": 1.7374506458276127,
+      "learning_rate": 4.994986959541788e-06,
+      "loss": 0.7816,
+      "step": 34
+    },
+    {
+      "epoch": 0.12655367231638417,
+      "grad_norm": 2.0807346358096166,
+      "learning_rate": 4.9927822836191185e-06,
+      "loss": 0.7818,
+      "step": 35
+    },
+    {
+      "epoch": 0.13016949152542373,
+      "grad_norm": 1.73060241181151,
+      "learning_rate": 4.990177593941303e-06,
+      "loss": 0.7674,
+      "step": 36
+    },
+    {
+      "epoch": 0.1337853107344633,
+      "grad_norm": 1.7060389302256593,
+      "learning_rate": 4.987173308479738e-06,
+      "loss": 0.7652,
+      "step": 37
+    },
+    {
+      "epoch": 0.13740112994350281,
+      "grad_norm": 1.6025020216781503,
+      "learning_rate": 4.9837699093284765e-06,
+      "loss": 0.7457,
+      "step": 38
+    },
+    {
+      "epoch": 0.14101694915254237,
+      "grad_norm": 1.7291972266390814,
+      "learning_rate": 4.9799679426268575e-06,
+      "loss": 0.7943,
+      "step": 39
+    },
+    {
+      "epoch": 0.14463276836158193,
+      "grad_norm": 1.6572877077102874,
+      "learning_rate": 4.975768018471877e-06,
+      "loss": 0.7815,
+      "step": 40
+    },
+    {
+      "epoch": 0.14824858757062148,
+      "grad_norm": 1.5680833894820443,
+      "learning_rate": 4.971170810820279e-06,
+      "loss": 0.7557,
+      "step": 41
+    },
+    {
+      "epoch": 0.151864406779661,
+      "grad_norm": 1.4822606907798626,
+      "learning_rate": 4.966177057380409e-06,
+      "loss": 0.7561,
+      "step": 42
+    },
+    {
+      "epoch": 0.15548022598870057,
+      "grad_norm": 1.6178903613745546,
+      "learning_rate": 4.960787559493836e-06,
+      "loss": 0.7474,
+      "step": 43
+    },
+    {
+      "epoch": 0.15909604519774012,
+      "grad_norm": 1.5096967013865987,
+      "learning_rate": 4.955003182006761e-06,
+      "loss": 0.716,
+      "step": 44
+    },
+    {
+      "epoch": 0.16271186440677965,
+      "grad_norm": 1.4671027619246142,
+      "learning_rate": 4.948824853131237e-06,
+      "loss": 0.7353,
+      "step": 45
+    },
+    {
+      "epoch": 0.1663276836158192,
+      "grad_norm": 1.4778933913112275,
+      "learning_rate": 4.942253564296217e-06,
+      "loss": 0.7358,
+      "step": 46
+    },
+    {
+      "epoch": 0.16994350282485876,
+      "grad_norm": 1.4672254672280391,
+      "learning_rate": 4.935290369988468e-06,
+      "loss": 0.7419,
+      "step": 47
+    },
+    {
+      "epoch": 0.17355932203389832,
+      "grad_norm": 1.4415543659264245,
+      "learning_rate": 4.927936387583348e-06,
+      "loss": 0.748,
+      "step": 48
+    },
+    {
+      "epoch": 0.17717514124293784,
+      "grad_norm": 1.3940953807201077,
+      "learning_rate": 4.920192797165511e-06,
+      "loss": 0.7571,
+      "step": 49
+    },
+    {
+      "epoch": 0.1807909604519774,
+      "grad_norm": 1.4519222988783331,
+      "learning_rate": 4.912060841339536e-06,
+      "loss": 0.7127,
+      "step": 50
+    },
+    {
+      "epoch": 0.18440677966101696,
+      "grad_norm": 1.4865547512367276,
+      "learning_rate": 4.9035418250305314e-06,
+      "loss": 0.7272,
+      "step": 51
+    },
+    {
+      "epoch": 0.18802259887005648,
+      "grad_norm": 1.5008090646455723,
+      "learning_rate": 4.894637115274728e-06,
+      "loss": 0.7258,
+      "step": 52
+    },
+    {
+      "epoch": 0.19163841807909604,
+      "grad_norm": 1.7037112279423843,
+      "learning_rate": 4.8853481410001225e-06,
+      "loss": 0.7316,
+      "step": 53
+    },
+    {
+      "epoch": 0.1952542372881356,
+      "grad_norm": 1.440963552161302,
+      "learning_rate": 4.875676392797169e-06,
+      "loss": 0.7551,
+      "step": 54
+    },
+    {
+      "epoch": 0.19887005649717515,
+      "grad_norm": 1.440064113753515,
+      "learning_rate": 4.865623422679593e-06,
+      "loss": 0.7446,
+      "step": 55
+    },
+    {
+      "epoch": 0.20248587570621468,
+      "grad_norm": 1.6503815942075044,
+      "learning_rate": 4.855190843835338e-06,
+      "loss": 0.6955,
+      "step": 56
+    },
+    {
+      "epoch": 0.20610169491525424,
+      "grad_norm": 1.3995241998208656,
+      "learning_rate": 4.844380330367701e-06,
+      "loss": 0.7214,
+      "step": 57
+    },
+    {
+      "epoch": 0.2097175141242938,
+      "grad_norm": 1.461439825228087,
+      "learning_rate": 4.833193617026692e-06,
+      "loss": 0.7386,
+      "step": 58
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.5840510779057535,
+      "learning_rate": 4.821632498930656e-06,
+      "loss": 0.7156,
+      "step": 59
+    },
+    {
+      "epoch": 0.21694915254237288,
+      "grad_norm": 1.5720479925852917,
+      "learning_rate": 4.809698831278217e-06,
+      "loss": 0.6961,
+      "step": 60
+    },
+    {
+      "epoch": 0.22056497175141243,
+      "grad_norm": 1.6408543211624975,
+      "learning_rate": 4.797394529050577e-06,
+      "loss": 0.7223,
+      "step": 61
+    },
+    {
+      "epoch": 0.224180790960452,
+      "grad_norm": 1.4636770967664614,
+      "learning_rate": 4.784721566704217e-06,
+      "loss": 0.7157,
+      "step": 62
+    },
+    {
+      "epoch": 0.22779661016949151,
+      "grad_norm": 1.5059556334177817,
+      "learning_rate": 4.771681977854062e-06,
+      "loss": 0.7091,
+      "step": 63
+    },
+    {
+      "epoch": 0.23141242937853107,
+      "grad_norm": 1.3659765286811016,
+      "learning_rate": 4.75827785494715e-06,
+      "loss": 0.7012,
+      "step": 64
+    },
+    {
+      "epoch": 0.23502824858757063,
+      "grad_norm": 1.418860606361076,
+      "learning_rate": 4.744511348926855e-06,
+      "loss": 0.7124,
+      "step": 65
+    },
+    {
+      "epoch": 0.23864406779661018,
+      "grad_norm": 1.4260454819088881,
+      "learning_rate": 4.730384668887731e-06,
+      "loss": 0.7215,
+      "step": 66
+    },
+    {
+      "epoch": 0.2422598870056497,
+      "grad_norm": 1.5391993842680236,
+      "learning_rate": 4.715900081721021e-06,
+      "loss": 0.6946,
+      "step": 67
+    },
+    {
+      "epoch": 0.24587570621468927,
+      "grad_norm": 1.552630241762705,
+      "learning_rate": 4.7010599117508936e-06,
+      "loss": 0.7109,
+      "step": 68
+    },
+    {
+      "epoch": 0.24949152542372882,
+      "grad_norm": 1.5270739656846004,
+      "learning_rate": 4.685866540361456e-06,
+      "loss": 0.7092,
+      "step": 69
+    },
+    {
+      "epoch": 0.25310734463276835,
+      "grad_norm": 1.5114873681601728,
+      "learning_rate": 4.670322405614621e-06,
+      "loss": 0.7055,
+      "step": 70
+    },
+    {
+      "epoch": 0.25672316384180793,
+      "grad_norm": 1.5299853438436042,
+      "learning_rate": 4.654430001858874e-06,
+      "loss": 0.6878,
+      "step": 71
+    },
+    {
+      "epoch": 0.26033898305084746,
+      "grad_norm": 1.445451157672883,
+      "learning_rate": 4.638191879329005e-06,
+      "loss": 0.7222,
+      "step": 72
+    },
+    {
+      "epoch": 0.263954802259887,
+      "grad_norm": 1.4221665529233392,
+      "learning_rate": 4.621610643736878e-06,
+      "loss": 0.7237,
+      "step": 73
+    },
+    {
+      "epoch": 0.2675706214689266,
+      "grad_norm": 1.469857395185097,
+      "learning_rate": 4.6046889558532925e-06,
+      "loss": 0.6966,
+      "step": 74
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 1.5144096217089977,
+      "learning_rate": 4.587429531081019e-06,
+      "loss": 0.7018,
+      "step": 75
+    },
+    {
+      "epoch": 0.27480225988700563,
+      "grad_norm": 1.3933861614255332,
+      "learning_rate": 4.569835139019054e-06,
+      "loss": 0.6548,
+      "step": 76
+    },
+    {
+      "epoch": 0.2784180790960452,
+      "grad_norm": 1.7309884671892724,
+      "learning_rate": 4.551908603018191e-06,
+      "loss": 0.6976,
+      "step": 77
+    },
+    {
+      "epoch": 0.28203389830508474,
+      "grad_norm": 1.5328106326816477,
+      "learning_rate": 4.53365279972796e-06,
+      "loss": 0.693,
+      "step": 78
+    },
+    {
+      "epoch": 0.28564971751412427,
+      "grad_norm": 1.5098349501089556,
+      "learning_rate": 4.515070658635013e-06,
+      "loss": 0.697,
+      "step": 79
+    },
+    {
+      "epoch": 0.28926553672316385,
+      "grad_norm": 1.7412535656694954,
+      "learning_rate": 4.4961651615930344e-06,
+      "loss": 0.7115,
+      "step": 80
+    },
+    {
+      "epoch": 0.2928813559322034,
+      "grad_norm": 1.5076941472793814,
+      "learning_rate": 4.476939342344246e-06,
+      "loss": 0.7163,
+      "step": 81
+    },
+    {
+      "epoch": 0.29649717514124296,
+      "grad_norm": 1.4730053806555845,
+      "learning_rate": 4.457396286032589e-06,
+      "loss": 0.6886,
+      "step": 82
+    },
+    {
+      "epoch": 0.3001129943502825,
+      "grad_norm": 1.4855157413144469,
+      "learning_rate": 4.437539128708647e-06,
+      "loss": 0.7339,
+      "step": 83
+    },
+    {
+      "epoch": 0.303728813559322,
+      "grad_norm": 1.5405150766486688,
+      "learning_rate": 4.417371056826417e-06,
+      "loss": 0.7149,
+      "step": 84
+    },
+    {
+      "epoch": 0.3073446327683616,
+      "grad_norm": 1.5508769466195937,
+      "learning_rate": 4.396895306731978e-06,
+      "loss": 0.6822,
+      "step": 85
+    },
+    {
+      "epoch": 0.31096045197740113,
+      "grad_norm": 1.4588960420622106,
+      "learning_rate": 4.376115164144157e-06,
+      "loss": 0.6836,
+      "step": 86
+    },
+    {
+      "epoch": 0.31457627118644066,
+      "grad_norm": 1.6627413334009173,
+      "learning_rate": 4.355033963627277e-06,
+      "loss": 0.7131,
+      "step": 87
+    },
+    {
+      "epoch": 0.31819209039548024,
+      "grad_norm": 1.5553517341256553,
+      "learning_rate": 4.333655088056065e-06,
+      "loss": 0.6854,
+      "step": 88
+    },
+    {
+      "epoch": 0.32180790960451977,
+      "grad_norm": 1.6684230900983013,
+      "learning_rate": 4.3119819680728e-06,
+      "loss": 0.7094,
+      "step": 89
+    },
+    {
+      "epoch": 0.3254237288135593,
+      "grad_norm": 1.3726285594917855,
+      "learning_rate": 4.290018081536807e-06,
+      "loss": 0.6872,
+      "step": 90
+    },
+    {
+      "epoch": 0.3290395480225989,
+      "grad_norm": 1.380724539985608,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.7139,
+      "step": 91
+    },
+    {
+      "epoch": 0.3326553672316384,
+      "grad_norm": 1.5348446771711333,
+      "learning_rate": 4.245232152973148e-06,
+      "loss": 0.6778,
+      "step": 92
+    },
+    {
+      "epoch": 0.336271186440678,
+      "grad_norm": 1.5229418737475282,
+      "learning_rate": 4.222417297689217e-06,
+      "loss": 0.6689,
+      "step": 93
+    },
+    {
+      "epoch": 0.3398870056497175,
+      "grad_norm": 1.5070456041355724,
+      "learning_rate": 4.199326048186783e-06,
+      "loss": 0.6894,
+      "step": 94
+    },
+    {
+      "epoch": 0.34350282485875705,
+      "grad_norm": 1.3616666744687627,
+      "learning_rate": 4.175962109890697e-06,
+      "loss": 0.6554,
+      "step": 95
+    },
+    {
+      "epoch": 0.34711864406779663,
+      "grad_norm": 1.5391506984706091,
+      "learning_rate": 4.152329231983852e-06,
+      "loss": 0.7023,
+      "step": 96
+    },
+    {
+      "epoch": 0.35073446327683616,
+      "grad_norm": 1.4241158917993244,
+      "learning_rate": 4.128431206805556e-06,
+      "loss": 0.7107,
+      "step": 97
+    },
+    {
+      "epoch": 0.3543502824858757,
+      "grad_norm": 1.4631603034598988,
+      "learning_rate": 4.104271869242975e-06,
+      "loss": 0.6894,
+      "step": 98
+    },
+    {
+      "epoch": 0.3579661016949153,
+      "grad_norm": 1.4094826388778878,
+      "learning_rate": 4.07985509611576e-06,
+      "loss": 0.677,
+      "step": 99
+    },
+    {
+      "epoch": 0.3615819209039548,
+      "grad_norm": 1.4740189681153695,
+      "learning_rate": 4.0551848055539345e-06,
+      "loss": 0.6699,
+      "step": 100
+    },
+    {
+      "epoch": 0.36519774011299433,
+      "grad_norm": 1.4525217649150708,
+      "learning_rate": 4.030264956369158e-06,
+      "loss": 0.7368,
+      "step": 101
+    },
+    {
+      "epoch": 0.3688135593220339,
+      "grad_norm": 1.451460518174865,
+      "learning_rate": 4.005099547419458e-06,
+      "loss": 0.7034,
+      "step": 102
+    },
+    {
+      "epoch": 0.37242937853107344,
+      "grad_norm": 1.5038951264951017,
+      "learning_rate": 3.979692616967543e-06,
+      "loss": 0.6837,
+      "step": 103
+    },
+    {
+      "epoch": 0.37604519774011297,
+      "grad_norm": 1.4157220265249935,
+      "learning_rate": 3.9540482420327845e-06,
+      "loss": 0.6875,
+      "step": 104
+    },
+    {
+      "epoch": 0.37966101694915255,
+      "grad_norm": 1.4737148597287204,
+      "learning_rate": 3.9281705377369814e-06,
+      "loss": 0.6901,
+      "step": 105
+    },
+    {
+      "epoch": 0.3832768361581921,
+      "grad_norm": 1.4677149428122727,
+      "learning_rate": 3.902063656644012e-06,
+      "loss": 0.6792,
+      "step": 106
+    },
+    {
+      "epoch": 0.38689265536723166,
+      "grad_norm": 1.3434999781262245,
+      "learning_rate": 3.875731788093478e-06,
+      "loss": 0.6876,
+      "step": 107
+    },
+    {
+      "epoch": 0.3905084745762712,
+      "grad_norm": 1.4987089091978376,
+      "learning_rate": 3.84917915752845e-06,
+      "loss": 0.6761,
+      "step": 108
+    },
+    {
+      "epoch": 0.3941242937853107,
+      "grad_norm": 1.508794866255814,
+      "learning_rate": 3.8224100258174066e-06,
+      "loss": 0.6838,
+      "step": 109
+    },
+    {
+      "epoch": 0.3977401129943503,
+      "grad_norm": 1.4688146101109116,
+      "learning_rate": 3.795428688570505e-06,
+      "loss": 0.684,
+      "step": 110
+    },
+    {
+      "epoch": 0.40135593220338983,
+      "grad_norm": 1.4606514616212791,
+      "learning_rate": 3.7682394754502687e-06,
+      "loss": 0.6824,
+      "step": 111
+    },
+    {
+      "epoch": 0.40497175141242936,
+      "grad_norm": 1.4096709625800348,
+      "learning_rate": 3.7408467494768104e-06,
+      "loss": 0.6969,
+      "step": 112
+    },
+    {
+      "epoch": 0.40858757062146894,
+      "grad_norm": 1.418524365345472,
+      "learning_rate": 3.7132549063277033e-06,
+      "loss": 0.7097,
+      "step": 113
+    },
+    {
+      "epoch": 0.41220338983050847,
+      "grad_norm": 1.5410281672091906,
+      "learning_rate": 3.685468373632613e-06,
+      "loss": 0.6746,
+      "step": 114
+    },
+    {
+      "epoch": 0.415819209039548,
+      "grad_norm": 1.3641313015018903,
+      "learning_rate": 3.657491610262802e-06,
+      "loss": 0.6448,
+      "step": 115
+    },
+    {
+      "epoch": 0.4194350282485876,
+      "grad_norm": 1.3041765820835833,
+      "learning_rate": 3.6293291056156178e-06,
+      "loss": 0.6819,
+      "step": 116
+    },
+    {
+      "epoch": 0.4230508474576271,
+      "grad_norm": 1.506905844856063,
+      "learning_rate": 3.600985378894086e-06,
+      "loss": 0.6876,
+      "step": 117
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.376689012221553,
+      "learning_rate": 3.572464978381719e-06,
+      "loss": 0.684,
+      "step": 118
+    },
+    {
+      "epoch": 0.4302824858757062,
+      "grad_norm": 1.340240336011346,
+      "learning_rate": 3.5437724807126583e-06,
+      "loss": 0.6505,
+      "step": 119
+    },
+    {
+      "epoch": 0.43389830508474575,
+      "grad_norm": 1.325670474835959,
+      "learning_rate": 3.514912490137268e-06,
+      "loss": 0.6357,
+      "step": 120
+    },
+    {
+      "epoch": 0.43751412429378533,
+      "grad_norm": 1.2967281789427187,
+      "learning_rate": 3.4858896377832966e-06,
+      "loss": 0.6716,
+      "step": 121
+    },
+    {
+      "epoch": 0.44112994350282486,
+      "grad_norm": 1.4289334076188702,
+      "learning_rate": 3.4567085809127247e-06,
+      "loss": 0.6749,
+      "step": 122
+    },
+    {
+      "epoch": 0.4447457627118644,
+      "grad_norm": 1.4006278853440177,
+      "learning_rate": 3.42737400217442e-06,
+      "loss": 0.6675,
+      "step": 123
+    },
+    {
+      "epoch": 0.448361581920904,
+      "grad_norm": 1.4903303746050145,
+      "learning_rate": 3.397890608852718e-06,
+      "loss": 0.6795,
+      "step": 124
+    },
+    {
+      "epoch": 0.4519774011299435,
+      "grad_norm": 1.5237327914091412,
+      "learning_rate": 3.3682631321120507e-06,
+      "loss": 0.6834,
+      "step": 125
+    },
+    {
+      "epoch": 0.45559322033898303,
+      "grad_norm": 1.375637272974929,
+      "learning_rate": 3.3384963262377434e-06,
+      "loss": 0.6546,
+      "step": 126
+    },
+    {
+      "epoch": 0.4592090395480226,
+      "grad_norm": 1.4010303116849099,
+      "learning_rate": 3.3085949678730953e-06,
+      "loss": 0.6687,
+      "step": 127
+    },
+    {
+      "epoch": 0.46282485875706214,
+      "grad_norm": 1.3723912301345371,
+      "learning_rate": 3.278563855252885e-06,
+      "loss": 0.6927,
+      "step": 128
+    },
+    {
+      "epoch": 0.46644067796610167,
+      "grad_norm": 1.4580226139492987,
+      "learning_rate": 3.248407807433396e-06,
+      "loss": 0.6843,
+      "step": 129
+    },
+    {
+      "epoch": 0.47005649717514125,
+      "grad_norm": 1.5657029406507326,
+      "learning_rate": 3.2181316635191125e-06,
+      "loss": 0.6639,
+      "step": 130
+    },
+    {
+      "epoch": 0.4736723163841808,
+      "grad_norm": 1.5943610613148829,
+      "learning_rate": 3.1877402818861954e-06,
+      "loss": 0.6655,
+      "step": 131
+    },
+    {
+      "epoch": 0.47728813559322036,
+      "grad_norm": 1.398551732301804,
+      "learning_rate": 3.157238539402862e-06,
+      "loss": 0.6648,
+      "step": 132
+    },
+    {
+      "epoch": 0.4809039548022599,
+      "grad_norm": 1.3527863119261647,
+      "learning_rate": 3.1266313306468018e-06,
+      "loss": 0.6793,
+      "step": 133
+    },
+    {
+      "epoch": 0.4845197740112994,
+      "grad_norm": 1.4133737666494006,
+      "learning_rate": 3.095923567119748e-06,
+      "loss": 0.6808,
+      "step": 134
+    },
+    {
+      "epoch": 0.488135593220339,
+      "grad_norm": 1.3489274410441074,
+      "learning_rate": 3.0651201764593375e-06,
+      "loss": 0.669,
+      "step": 135
+    },
+    {
+      "epoch": 0.49175141242937853,
+      "grad_norm": 1.4710077216567483,
+      "learning_rate": 3.034226101648377e-06,
+      "loss": 0.6685,
+      "step": 136
+    },
+    {
+      "epoch": 0.49536723163841806,
+      "grad_norm": 1.4143201023235143,
+      "learning_rate": 3.0032463002216504e-06,
+      "loss": 0.6803,
+      "step": 137
+    },
+    {
+      "epoch": 0.49898305084745764,
+      "grad_norm": 1.350434140774409,
+      "learning_rate": 2.972185743470386e-06,
+      "loss": 0.6293,
+      "step": 138
+    },
+    {
+      "epoch": 0.5025988700564972,
+      "grad_norm": 1.4061918089975518,
+      "learning_rate": 2.941049415644522e-06,
+      "loss": 0.6981,
+      "step": 139
+    },
+    {
+      "epoch": 0.5062146892655367,
+      "grad_norm": 1.4466820101061297,
+      "learning_rate": 2.909842313152888e-06,
+      "loss": 0.6738,
+      "step": 140
+    },
+    {
+      "epoch": 0.5098305084745762,
+      "grad_norm": 1.5124850873525673,
+      "learning_rate": 2.878569443761442e-06,
+      "loss": 0.7131,
+      "step": 141
+    },
+    {
+      "epoch": 0.5134463276836159,
+      "grad_norm": 1.4743009883750753,
+      "learning_rate": 2.847235825789673e-06,
+      "loss": 0.7016,
+      "step": 142
+    },
+    {
+      "epoch": 0.5170621468926554,
+      "grad_norm": 1.3586041525935764,
+      "learning_rate": 2.8158464873053236e-06,
+      "loss": 0.6724,
+      "step": 143
+    },
+    {
+      "epoch": 0.5206779661016949,
+      "grad_norm": 1.4996529158631906,
+      "learning_rate": 2.784406465317538e-06,
+      "loss": 0.6662,
+      "step": 144
+    },
+    {
+      "epoch": 0.5242937853107345,
+      "grad_norm": 1.4671966292049852,
+      "learning_rate": 2.752920804968581e-06,
+      "loss": 0.6631,
+      "step": 145
+    },
+    {
+      "epoch": 0.527909604519774,
+      "grad_norm": 1.444812582502839,
+      "learning_rate": 2.7213945587242507e-06,
+      "loss": 0.6513,
+      "step": 146
+    },
+    {
+      "epoch": 0.5315254237288135,
+      "grad_norm": 1.3053540444757412,
+      "learning_rate": 2.689832785563116e-06,
+      "loss": 0.6555,
+      "step": 147
+    },
+    {
+      "epoch": 0.5351412429378531,
+      "grad_norm": 1.314006962084444,
+      "learning_rate": 2.658240550164704e-06,
+      "loss": 0.6661,
+      "step": 148
+    },
+    {
+      "epoch": 0.5387570621468927,
+      "grad_norm": 1.4304673510029906,
+      "learning_rate": 2.626622922096782e-06,
+      "loss": 0.6621,
+      "step": 149
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 1.4876534124839516,
+      "learning_rate": 2.5949849750018486e-06,
+      "loss": 0.6758,
+      "step": 150
+    },
+    {
+      "epoch": 0.5459887005649717,
+      "grad_norm": 1.3200607589115334,
+      "learning_rate": 2.56333178578297e-06,
+      "loss": 0.6559,
+      "step": 151
+    },
+    {
+      "epoch": 0.5496045197740113,
+      "grad_norm": 1.3240990359086642,
+      "learning_rate": 2.5316684337891005e-06,
+      "loss": 0.6232,
+      "step": 152
+    },
+    {
+      "epoch": 0.5532203389830509,
+      "grad_norm": 1.3124913285203368,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6373,
+      "step": 153
+    },
+    {
+      "epoch": 0.5568361581920904,
+      "grad_norm": 1.3981996964149215,
+      "learning_rate": 2.4683315662109003e-06,
+      "loss": 0.6779,
+      "step": 154
+    },
+    {
+      "epoch": 0.56045197740113,
+      "grad_norm": 1.3816310911971024,
+      "learning_rate": 2.436668214217031e-06,
+      "loss": 0.654,
+      "step": 155
+    },
+    {
+      "epoch": 0.5640677966101695,
+      "grad_norm": 1.263049809743652,
+      "learning_rate": 2.4050150249981522e-06,
+      "loss": 0.6625,
+      "step": 156
+    },
+    {
+      "epoch": 0.567683615819209,
+      "grad_norm": 1.3247706606665524,
+      "learning_rate": 2.3733770779032185e-06,
+      "loss": 0.6862,
+      "step": 157
+    },
+    {
+      "epoch": 0.5712994350282485,
+      "grad_norm": 1.3384592393063528,
+      "learning_rate": 2.341759449835297e-06,
+      "loss": 0.669,
+      "step": 158
+    },
+    {
+      "epoch": 0.5749152542372882,
+      "grad_norm": 1.3084651079974374,
+      "learning_rate": 2.310167214436885e-06,
+      "loss": 0.6389,
+      "step": 159
+    },
+    {
+      "epoch": 0.5785310734463277,
+      "grad_norm": 1.3374680724124108,
+      "learning_rate": 2.27860544127575e-06,
+      "loss": 0.6472,
+      "step": 160
+    },
+    {
+      "epoch": 0.5821468926553672,
+      "grad_norm": 1.3122640789722633,
+      "learning_rate": 2.24707919503142e-06,
+      "loss": 0.6579,
+      "step": 161
+    },
+    {
+      "epoch": 0.5857627118644068,
+      "grad_norm": 1.4412496554625216,
+      "learning_rate": 2.2155935346824634e-06,
+      "loss": 0.6481,
+      "step": 162
+    },
+    {
+      "epoch": 0.5893785310734463,
+      "grad_norm": 1.3863338838498946,
+      "learning_rate": 2.1841535126946777e-06,
+      "loss": 0.6535,
+      "step": 163
+    },
+    {
+      "epoch": 0.5929943502824859,
+      "grad_norm": 1.345502076046215,
+      "learning_rate": 2.1527641742103282e-06,
+      "loss": 0.6707,
+      "step": 164
+    },
+    {
+      "epoch": 0.5966101694915255,
+      "grad_norm": 1.3847319032734033,
+      "learning_rate": 2.1214305562385592e-06,
+      "loss": 0.6663,
+      "step": 165
+    },
+    {
+      "epoch": 0.600225988700565,
+      "grad_norm": 1.430665603476504,
+      "learning_rate": 2.0901576868471125e-06,
+      "loss": 0.6747,
+      "step": 166
+    },
+    {
+      "epoch": 0.6038418079096045,
+      "grad_norm": 1.353261054674096,
+      "learning_rate": 2.05895058435548e-06,
+      "loss": 0.6512,
+      "step": 167
+    },
+    {
+      "epoch": 0.607457627118644,
+      "grad_norm": 1.2859249411363938,
+      "learning_rate": 2.0278142565296153e-06,
+      "loss": 0.6324,
+      "step": 168
+    },
+    {
+      "epoch": 0.6110734463276836,
+      "grad_norm": 1.4013926433738113,
+      "learning_rate": 1.9967536997783495e-06,
+      "loss": 0.6679,
+      "step": 169
+    },
+    {
+      "epoch": 0.6146892655367232,
+      "grad_norm": 1.3862043238014647,
+      "learning_rate": 1.9657738983516227e-06,
+      "loss": 0.6729,
+      "step": 170
+    },
+    {
+      "epoch": 0.6183050847457627,
+      "grad_norm": 1.3586507239524463,
+      "learning_rate": 1.934879823540663e-06,
+      "loss": 0.6493,
+      "step": 171
+    },
+    {
+      "epoch": 0.6219209039548023,
+      "grad_norm": 1.3297630157555045,
+      "learning_rate": 1.9040764328802523e-06,
+      "loss": 0.6398,
+      "step": 172
+    },
+    {
+      "epoch": 0.6255367231638418,
+      "grad_norm": 1.3817085459115725,
+      "learning_rate": 1.8733686693531986e-06,
+      "loss": 0.6582,
+      "step": 173
+    },
+    {
+      "epoch": 0.6291525423728813,
+      "grad_norm": 1.3202548993972594,
+      "learning_rate": 1.842761460597138e-06,
+      "loss": 0.6532,
+      "step": 174
+    },
+    {
+      "epoch": 0.632768361581921,
+      "grad_norm": 1.3288961390749972,
+      "learning_rate": 1.812259718113805e-06,
+      "loss": 0.6603,
+      "step": 175
+    },
+    {
+      "epoch": 0.6363841807909605,
+      "grad_norm": 1.329943461477084,
+      "learning_rate": 1.7818683364808883e-06,
+      "loss": 0.658,
+      "step": 176
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3692273444745175,
+      "learning_rate": 1.7515921925666053e-06,
+      "loss": 0.6317,
+      "step": 177
+    },
+    {
+      "epoch": 0.6436158192090395,
+      "grad_norm": 1.421706203526152,
+      "learning_rate": 1.7214361447471156e-06,
+      "loss": 0.677,
+      "step": 178
+    },
+    {
+      "epoch": 0.6472316384180791,
+      "grad_norm": 1.3083895534561967,
+      "learning_rate": 1.6914050321269049e-06,
+      "loss": 0.6736,
+      "step": 179
+    },
+    {
+      "epoch": 0.6508474576271186,
+      "grad_norm": 1.3408157323699283,
+      "learning_rate": 1.6615036737622574e-06,
+      "loss": 0.6802,
+      "step": 180
+    },
+    {
+      "epoch": 0.6544632768361582,
+      "grad_norm": 1.2866436449644132,
+      "learning_rate": 1.6317368678879497e-06,
+      "loss": 0.646,
+      "step": 181
+    },
+    {
+      "epoch": 0.6580790960451978,
+      "grad_norm": 1.4469309073814418,
+      "learning_rate": 1.6021093911472825e-06,
+      "loss": 0.6502,
+      "step": 182
+    },
+    {
+      "epoch": 0.6616949152542373,
+      "grad_norm": 1.3285438490415578,
+      "learning_rate": 1.572625997825581e-06,
+      "loss": 0.6392,
+      "step": 183
+    },
+    {
+      "epoch": 0.6653107344632768,
+      "grad_norm": 1.3767595914556963,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.6478,
+      "step": 184
+    },
+    {
+      "epoch": 0.6689265536723163,
+      "grad_norm": 1.3913230479527472,
+      "learning_rate": 1.5141103622167042e-06,
+      "loss": 0.6624,
+      "step": 185
+    },
+    {
+      "epoch": 0.672542372881356,
+      "grad_norm": 1.3717018869154762,
+      "learning_rate": 1.4850875098627326e-06,
+      "loss": 0.6519,
+      "step": 186
+    },
+    {
+      "epoch": 0.6761581920903955,
+      "grad_norm": 1.3411020703523342,
+      "learning_rate": 1.456227519287343e-06,
+      "loss": 0.6382,
+      "step": 187
+    },
+    {
+      "epoch": 0.679774011299435,
+      "grad_norm": 1.238291654237968,
+      "learning_rate": 1.4275350216182824e-06,
+      "loss": 0.6391,
+      "step": 188
+    },
+    {
+      "epoch": 0.6833898305084746,
+      "grad_norm": 1.374517850534095,
+      "learning_rate": 1.3990146211059141e-06,
+      "loss": 0.6456,
+      "step": 189
+    },
+    {
+      "epoch": 0.6870056497175141,
+      "grad_norm": 1.306148052181935,
+      "learning_rate": 1.3706708943843822e-06,
+      "loss": 0.6441,
+      "step": 190
+    },
+    {
+      "epoch": 0.6906214689265536,
+      "grad_norm": 1.3876372946236282,
+      "learning_rate": 1.3425083897371983e-06,
+      "loss": 0.6603,
+      "step": 191
+    },
+    {
+      "epoch": 0.6942372881355933,
+      "grad_norm": 1.3904204488306329,
+      "learning_rate": 1.3145316263673874e-06,
+      "loss": 0.6721,
+      "step": 192
+    },
+    {
+      "epoch": 0.6978531073446328,
+      "grad_norm": 1.510808405530817,
+      "learning_rate": 1.286745093672298e-06,
+      "loss": 0.649,
+      "step": 193
+    },
+    {
+      "epoch": 0.7014689265536723,
+      "grad_norm": 1.4312145193748698,
+      "learning_rate": 1.2591532505231906e-06,
+      "loss": 0.6573,
+      "step": 194
+    },
+    {
+      "epoch": 0.7050847457627119,
+      "grad_norm": 1.4024105046257231,
+      "learning_rate": 1.2317605245497324e-06,
+      "loss": 0.6727,
+      "step": 195
+    },
+    {
+      "epoch": 0.7087005649717514,
+      "grad_norm": 1.3505688502581619,
+      "learning_rate": 1.204571311429496e-06,
+      "loss": 0.6131,
+      "step": 196
+    },
+    {
+      "epoch": 0.7123163841807909,
+      "grad_norm": 1.319472329102849,
+      "learning_rate": 1.1775899741825947e-06,
+      "loss": 0.6434,
+      "step": 197
+    },
+    {
+      "epoch": 0.7159322033898305,
+      "grad_norm": 1.5152192403656248,
+      "learning_rate": 1.1508208424715511e-06,
+      "loss": 0.656,
+      "step": 198
+    },
+    {
+      "epoch": 0.7195480225988701,
+      "grad_norm": 1.6136474853206006,
+      "learning_rate": 1.1242682119065217e-06,
+      "loss": 0.6613,
+      "step": 199
+    },
+    {
+      "epoch": 0.7231638418079096,
+      "grad_norm": 1.312425015581362,
+      "learning_rate": 1.0979363433559892e-06,
+      "loss": 0.6577,
+      "step": 200
+    },
+    {
+      "epoch": 0.7267796610169491,
+      "grad_norm": 1.3953598075891687,
+      "learning_rate": 1.0718294622630188e-06,
+      "loss": 0.6905,
+      "step": 201
+    },
+    {
+      "epoch": 0.7303954802259887,
+      "grad_norm": 1.372903007290825,
+      "learning_rate": 1.045951757967215e-06,
+      "loss": 0.6448,
+      "step": 202
+    },
+    {
+      "epoch": 0.7340112994350283,
+      "grad_norm": 1.4652703276389691,
+      "learning_rate": 1.0203073830324566e-06,
+      "loss": 0.6395,
+      "step": 203
+    },
+    {
+      "epoch": 0.7376271186440678,
+      "grad_norm": 1.366422271732463,
+      "learning_rate": 9.949004525805423e-07,
+      "loss": 0.6148,
+      "step": 204
+    },
+    {
+      "epoch": 0.7412429378531074,
+      "grad_norm": 1.2886663538886012,
+      "learning_rate": 9.697350436308428e-07,
+      "loss": 0.6322,
+      "step": 205
+    },
+    {
+      "epoch": 0.7448587570621469,
+      "grad_norm": 1.3574509449302405,
+      "learning_rate": 9.448151944460657e-07,
+      "loss": 0.6835,
+      "step": 206
+    },
+    {
+      "epoch": 0.7484745762711864,
+      "grad_norm": 1.393654049362733,
+      "learning_rate": 9.201449038842403e-07,
+      "loss": 0.6713,
+      "step": 207
+    },
+    {
+      "epoch": 0.7520903954802259,
+      "grad_norm": 1.3962653237548226,
+      "learning_rate": 8.957281307570254e-07,
+      "loss": 0.6349,
+      "step": 208
+    },
+    {
+      "epoch": 0.7557062146892656,
+      "grad_norm": 1.2716349996486196,
+      "learning_rate": 8.71568793194445e-07,
+      "loss": 0.6395,
+      "step": 209
+    },
+    {
+      "epoch": 0.7593220338983051,
+      "grad_norm": 1.3461355380403557,
+      "learning_rate": 8.476707680161486e-07,
+      "loss": 0.6566,
+      "step": 210
+    },
+    {
+      "epoch": 0.7629378531073446,
+      "grad_norm": 1.3005123962225364,
+      "learning_rate": 8.240378901093035e-07,
+      "loss": 0.6498,
+      "step": 211
+    },
+    {
+      "epoch": 0.7665536723163842,
+      "grad_norm": 1.2709444859864987,
+      "learning_rate": 8.006739518132179e-07,
+      "loss": 0.6702,
+      "step": 212
+    },
+    {
+      "epoch": 0.7701694915254237,
+      "grad_norm": 1.3327493213768535,
+      "learning_rate": 7.775827023107835e-07,
+      "loss": 0.6403,
+      "step": 213
+    },
+    {
+      "epoch": 0.7737853107344633,
+      "grad_norm": 1.4047092975707265,
+      "learning_rate": 7.547678470268526e-07,
+      "loss": 0.6492,
+      "step": 214
+    },
+    {
+      "epoch": 0.7774011299435029,
+      "grad_norm": 1.383631976222337,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.6289,
+      "step": 215
+    },
+    {
+      "epoch": 0.7810169491525424,
+      "grad_norm": 1.2567546465681303,
+      "learning_rate": 7.099819184631929e-07,
+      "loss": 0.6393,
+      "step": 216
+    },
+    {
+      "epoch": 0.7846327683615819,
+      "grad_norm": 1.2354895441269147,
+      "learning_rate": 6.880180319272006e-07,
+      "loss": 0.6429,
+      "step": 217
+    },
+    {
+      "epoch": 0.7882485875706214,
+      "grad_norm": 1.3478465932161185,
+      "learning_rate": 6.663449119439358e-07,
+      "loss": 0.6652,
+      "step": 218
+    },
+    {
+      "epoch": 0.791864406779661,
+      "grad_norm": 1.3094969549541247,
+      "learning_rate": 6.449660363727236e-07,
+      "loss": 0.6424,
+      "step": 219
+    },
+    {
+      "epoch": 0.7954802259887006,
+      "grad_norm": 1.385053278123551,
+      "learning_rate": 6.238848358558439e-07,
+      "loss": 0.6409,
+      "step": 220
+    },
+    {
+      "epoch": 0.7990960451977401,
+      "grad_norm": 1.3349840769877994,
+      "learning_rate": 6.031046932680229e-07,
+      "loss": 0.6815,
+      "step": 221
+    },
+    {
+      "epoch": 0.8027118644067797,
+      "grad_norm": 1.4435164246937722,
+      "learning_rate": 5.826289431735832e-07,
+      "loss": 0.6489,
+      "step": 222
+    },
+    {
+      "epoch": 0.8063276836158192,
+      "grad_norm": 1.3356172924249725,
+      "learning_rate": 5.624608712913531e-07,
+      "loss": 0.6298,
+      "step": 223
+    },
+    {
+      "epoch": 0.8099435028248587,
+      "grad_norm": 1.2977048398488058,
+      "learning_rate": 5.426037139674117e-07,
+      "loss": 0.6509,
+      "step": 224
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 1.3774919529523362,
+      "learning_rate": 5.23060657655754e-07,
+      "loss": 0.6573,
+      "step": 225
+    },
+    {
+      "epoch": 0.8171751412429379,
+      "grad_norm": 1.3410009004205188,
+      "learning_rate": 5.038348384069663e-07,
+      "loss": 0.633,
+      "step": 226
+    },
+    {
+      "epoch": 0.8207909604519774,
+      "grad_norm": 1.2928727452886148,
+      "learning_rate": 4.84929341364988e-07,
+      "loss": 0.6754,
+      "step": 227
+    },
+    {
+      "epoch": 0.8244067796610169,
+      "grad_norm": 1.358332904803305,
+      "learning_rate": 4.6634720027204093e-07,
+      "loss": 0.6614,
+      "step": 228
+    },
+    {
+      "epoch": 0.8280225988700565,
+      "grad_norm": 1.4907573288328078,
+      "learning_rate": 4.480913969818099e-07,
+      "loss": 0.6281,
+      "step": 229
+    },
+    {
+      "epoch": 0.831638418079096,
+      "grad_norm": 1.3392158203262607,
+      "learning_rate": 4.3016486098094667e-07,
+      "loss": 0.6161,
+      "step": 230
+    },
+    {
+      "epoch": 0.8352542372881356,
+      "grad_norm": 1.2444012140753318,
+      "learning_rate": 4.125704689189819e-07,
+      "loss": 0.6247,
+      "step": 231
+    },
+    {
+      "epoch": 0.8388700564971752,
+      "grad_norm": 1.4784447467052926,
+      "learning_rate": 3.953110441467073e-07,
+      "loss": 0.6586,
+      "step": 232
+    },
+    {
+      "epoch": 0.8424858757062147,
+      "grad_norm": 1.366997421968513,
+      "learning_rate": 3.7838935626312246e-07,
+      "loss": 0.6463,
+      "step": 233
+    },
+    {
+      "epoch": 0.8461016949152542,
+      "grad_norm": 1.4541952821449111,
+      "learning_rate": 3.6180812067099477e-07,
+      "loss": 0.6726,
+      "step": 234
+    },
+    {
+      "epoch": 0.8497175141242937,
+      "grad_norm": 1.3494835181921292,
+      "learning_rate": 3.455699981411259e-07,
+      "loss": 0.6378,
+      "step": 235
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.3091535029497192,
+      "learning_rate": 3.296775943853789e-07,
+      "loss": 0.6381,
+      "step": 236
+    },
+    {
+      "epoch": 0.8569491525423729,
+      "grad_norm": 1.292004503291086,
+      "learning_rate": 3.141334596385448e-07,
+      "loss": 0.6361,
+      "step": 237
+    },
+    {
+      "epoch": 0.8605649717514124,
+      "grad_norm": 1.3072359435785652,
+      "learning_rate": 2.9894008824910726e-07,
+      "loss": 0.6311,
+      "step": 238
+    },
+    {
+      "epoch": 0.864180790960452,
+      "grad_norm": 1.3418443898914727,
+      "learning_rate": 2.840999182789797e-07,
+      "loss": 0.6584,
+      "step": 239
+    },
+    {
+      "epoch": 0.8677966101694915,
+      "grad_norm": 1.3790407833555425,
+      "learning_rate": 2.696153311122704e-07,
+      "loss": 0.6275,
+      "step": 240
+    },
+    {
+      "epoch": 0.871412429378531,
+      "grad_norm": 1.3668643411134043,
+      "learning_rate": 2.5548865107314606e-07,
+      "loss": 0.6574,
+      "step": 241
+    },
+    {
+      "epoch": 0.8750282485875707,
+      "grad_norm": 1.267748779732102,
+      "learning_rate": 2.4172214505285006e-07,
+      "loss": 0.6394,
+      "step": 242
+    },
+    {
+      "epoch": 0.8786440677966102,
+      "grad_norm": 1.2912726516960031,
+      "learning_rate": 2.2831802214593774e-07,
+      "loss": 0.6352,
+      "step": 243
+    },
+    {
+      "epoch": 0.8822598870056497,
+      "grad_norm": 1.3408535402209096,
+      "learning_rate": 2.1527843329578328e-07,
+      "loss": 0.6332,
+      "step": 244
+    },
+    {
+      "epoch": 0.8858757062146893,
+      "grad_norm": 1.369964120309017,
+      "learning_rate": 2.026054709494235e-07,
+      "loss": 0.6488,
+      "step": 245
+    },
+    {
+      "epoch": 0.8894915254237288,
+      "grad_norm": 1.2985394908560597,
+      "learning_rate": 1.9030116872178317e-07,
+      "loss": 0.6268,
+      "step": 246
+    },
+    {
+      "epoch": 0.8931073446327683,
+      "grad_norm": 1.2695253299944342,
+      "learning_rate": 1.7836750106934475e-07,
+      "loss": 0.6098,
+      "step": 247
+    },
+    {
+      "epoch": 0.896723163841808,
+      "grad_norm": 1.2614680998276686,
+      "learning_rate": 1.6680638297330854e-07,
+      "loss": 0.6328,
+      "step": 248
+    },
+    {
+      "epoch": 0.9003389830508475,
+      "grad_norm": 1.3022416023187458,
+      "learning_rate": 1.5561966963229925e-07,
+      "loss": 0.6353,
+      "step": 249
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 1.3192179782937912,
+      "learning_rate": 1.448091561646628e-07,
+      "loss": 0.6212,
+      "step": 250
+    },
+    {
+      "epoch": 0.9075706214689265,
+      "grad_norm": 1.391821357807215,
+      "learning_rate": 1.3437657732040783e-07,
+      "loss": 0.6581,
+      "step": 251
+    },
+    {
+      "epoch": 0.9111864406779661,
+      "grad_norm": 1.348097897319632,
+      "learning_rate": 1.243236072028317e-07,
+      "loss": 0.6483,
+      "step": 252
+    },
+    {
+      "epoch": 0.9148022598870057,
+      "grad_norm": 1.3327973766461398,
+      "learning_rate": 1.1465185899987797e-07,
+      "loss": 0.6688,
+      "step": 253
+    },
+    {
+      "epoch": 0.9184180790960452,
+      "grad_norm": 1.3050936769777537,
+      "learning_rate": 1.0536288472527162e-07,
+      "loss": 0.6702,
+      "step": 254
+    },
+    {
+      "epoch": 0.9220338983050848,
+      "grad_norm": 1.3816378424721178,
+      "learning_rate": 9.645817496946902e-08,
+      "loss": 0.663,
+      "step": 255
+    },
+    {
+      "epoch": 0.9256497175141243,
+      "grad_norm": 1.3585454766173655,
+      "learning_rate": 8.79391586604636e-08,
+      "loss": 0.64,
+      "step": 256
+    },
+    {
+      "epoch": 0.9292655367231638,
+      "grad_norm": 1.3292531553316056,
+      "learning_rate": 7.980720283448957e-08,
+      "loss": 0.6335,
+      "step": 257
+    },
+    {
+      "epoch": 0.9328813559322033,
+      "grad_norm": 1.2599441985317357,
+      "learning_rate": 7.206361241665266e-08,
+      "loss": 0.6403,
+      "step": 258
+    },
+    {
+      "epoch": 0.936497175141243,
+      "grad_norm": 1.3958906990596642,
+      "learning_rate": 6.470963001153268e-08,
+      "loss": 0.6383,
+      "step": 259
+    },
+    {
+      "epoch": 0.9401129943502825,
+      "grad_norm": 1.295975911169058,
+      "learning_rate": 5.774643570378296e-08,
+      "loss": 0.6485,
+      "step": 260
+    },
+    {
+      "epoch": 0.943728813559322,
+      "grad_norm": 1.247115424184442,
+      "learning_rate": 5.117514686876379e-08,
+      "loss": 0.6479,
+      "step": 261
+    },
+    {
+      "epoch": 0.9473446327683616,
+      "grad_norm": 1.2578135030925344,
+      "learning_rate": 4.4996817993239464e-08,
+      "loss": 0.6363,
+      "step": 262
+    },
+    {
+      "epoch": 0.9509604519774011,
+      "grad_norm": 1.2567862444318008,
+      "learning_rate": 3.9212440506164465e-08,
+      "loss": 0.6417,
+      "step": 263
+    },
+    {
+      "epoch": 0.9545762711864407,
+      "grad_norm": 1.2972287074987505,
+      "learning_rate": 3.382294261959157e-08,
+      "loss": 0.676,
+      "step": 264
+    },
+    {
+      "epoch": 0.9581920903954803,
+      "grad_norm": 1.3028064182497767,
+      "learning_rate": 2.8829189179721552e-08,
+      "loss": 0.6502,
+      "step": 265
+    },
+    {
+      "epoch": 0.9618079096045198,
+      "grad_norm": 1.3401154575841365,
+      "learning_rate": 2.423198152812306e-08,
+      "loss": 0.6271,
+      "step": 266
+    },
+    {
+      "epoch": 0.9654237288135593,
+      "grad_norm": 1.332097876741386,
+      "learning_rate": 2.0032057373142453e-08,
+      "loss": 0.6312,
+      "step": 267
+    },
+    {
+      "epoch": 0.9690395480225988,
+      "grad_norm": 1.2752118722459802,
+      "learning_rate": 1.6230090671524312e-08,
+      "loss": 0.6313,
+      "step": 268
+    },
+    {
+      "epoch": 0.9726553672316384,
+      "grad_norm": 1.315897104629199,
+      "learning_rate": 1.2826691520262114e-08,
+      "loss": 0.6328,
+      "step": 269
+    },
+    {
+      "epoch": 0.976271186440678,
+      "grad_norm": 1.341142823473401,
+      "learning_rate": 9.822406058697665e-09,
+      "loss": 0.6247,
+      "step": 270
+    },
+    {
+      "epoch": 0.9798870056497175,
+      "grad_norm": 1.3751891651375663,
+      "learning_rate": 7.217716380881479e-09,
+      "loss": 0.6185,
+      "step": 271
+    },
+    {
+      "epoch": 0.9835028248587571,
+      "grad_norm": 1.2993917620171413,
+      "learning_rate": 5.0130404582127144e-09,
+      "loss": 0.6308,
+      "step": 272
+    },
+    {
+      "epoch": 0.9871186440677966,
+      "grad_norm": 1.306024529686539,
+      "learning_rate": 3.208732072368104e-09,
+      "loss": 0.6383,
+      "step": 273
+    },
+    {
+      "epoch": 0.9907344632768361,
+      "grad_norm": 1.3213672912672132,
+      "learning_rate": 1.8050807585293095e-09,
+      "loss": 0.6559,
+      "step": 274
+    },
+    {
+      "epoch": 0.9943502824858758,
+      "grad_norm": 1.3174616601564904,
+      "learning_rate": 8.023117589237017e-10,
+      "loss": 0.6701,
+      "step": 275
+    },
+    {
+      "epoch": 0.9979661016949153,
+      "grad_norm": 1.3624163578590245,
+      "learning_rate": 2.0058598667854755e-10,
+      "loss": 0.6445,
+      "step": 276
+    },
+    {
+      "epoch": 0.9979661016949153,
+      "step": 276,
+      "total_flos": 100810460790784.0,
+      "train_loss": 0.7222011056931122,
+      "train_runtime": 4200.972,
+      "train_samples_per_second": 8.426,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 100810460790784.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8081d36af7666efbbea8a1a5dfc6f1fe62fea15eb052b8fa0784c445637107
+size 7544