Hugging Face's logo

JamesK2W
/
viewsuite-checkpoints

Safetensors
Model card Files
xet
Community
JamesK2W commited on
Commit
b460692
·
verified ·
1 Parent(s): 5b28bed

upload folder model

Browse files
Files changed (24) hide show
  1. iter4_sft/README.md +61 -0
  2. iter4_sft/added_tokens.json +24 -0
  3. iter4_sft/all_results.json +8 -0
  4. iter4_sft/chat_template.jinja +7 -0
  5. iter4_sft/config.json +134 -0
  6. iter4_sft/generation_config.json +11 -0
  7. iter4_sft/merges.txt +0 -0
  8. iter4_sft/model-00001-of-00004.safetensors +3 -0
  9. iter4_sft/model-00002-of-00004.safetensors +3 -0
  10. iter4_sft/model-00003-of-00004.safetensors +3 -0
  11. iter4_sft/model-00004-of-00004.safetensors +3 -0
  12. iter4_sft/model.safetensors.index.json +737 -0
  13. iter4_sft/preprocessor_config.json +39 -0
  14. iter4_sft/sft.log +0 -0
  15. iter4_sft/sft_config.yaml +39 -0
  16. iter4_sft/special_tokens_map.json +31 -0
  17. iter4_sft/tokenizer_config.json +209 -0
  18. iter4_sft/train_results.json +8 -0
  19. iter4_sft/trainer_log.jsonl +364 -0
  20. iter4_sft/trainer_state.json +2584 -0
  21. iter4_sft/training_args.bin +3 -0
  22. iter4_sft/training_loss.png +0 -0
  23. iter4_sft/video_preprocessor_config.json +45 -0
  24. iter4_sft/vocab.json +0 -0
iter4_sft/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-VL-7B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: model
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # model
18
+
19
+ This model is a fine-tuned version of [/mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_4/rl/verl_checkpoints/global_step_100/actor/huggingface](https://huggingface.co//mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_4/rl/verl_checkpoints/global_step_100/actor/huggingface) on the multi_turn_action_gen, the forward_dynamics and the action_gen datasets.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.56.1
59
+ - Pytorch 2.8.0+cu128
60
+ - Datasets 4.0.0
61
+ - Tokenizers 0.22.2
iter4_sft/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
iter4_sft/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 50754799140864.0,
4
+ "train_loss": 0.09636665488652289,
5
+ "train_runtime": 845.3624,
6
+ "train_samples_per_second": 6.855,
7
+ "train_steps_per_second": 0.429
8
+ }
iter4_sft/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
iter4_sft/config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "_name_or_path": "/mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_1/rl/verl_checkpoints/global_step_50/actor/huggingface",
34
+ "architectures": [
35
+ "Qwen2_5_VLForConditionalGeneration"
36
+ ],
37
+ "attention_dropout": 0.0,
38
+ "dtype": "float32",
39
+ "eos_token_id": 151645,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 3584,
42
+ "image_token_id": null,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 18944,
45
+ "layer_types": [
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention"
74
+ ],
75
+ "max_position_embeddings": 128000,
76
+ "max_window_layers": 28,
77
+ "model_type": "qwen2_5_vl_text",
78
+ "num_attention_heads": 28,
79
+ "num_hidden_layers": 28,
80
+ "num_key_value_heads": 4,
81
+ "pad_token_id": 151643,
82
+ "rms_norm_eps": 1e-06,
83
+ "rope_scaling": {
84
+ "mrope_section": [
85
+ 16,
86
+ 24,
87
+ 24
88
+ ],
89
+ "rope_type": "default",
90
+ "type": "default"
91
+ },
92
+ "rope_theta": 1000000.0,
93
+ "sliding_window": null,
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "video_token_id": null,
97
+ "vision_token_id": 151654,
98
+ "vocab_size": 152064
99
+ },
100
+ "tie_word_embeddings": false,
101
+ "transformers_version": "4.56.1",
102
+ "use_cache": false,
103
+ "use_sliding_window": false,
104
+ "video_token_id": 151656,
105
+ "vision_config": {
106
+ "depth": 32,
107
+ "dtype": "float32",
108
+ "fullatt_block_indexes": [
109
+ 7,
110
+ 15,
111
+ 23,
112
+ 31
113
+ ],
114
+ "hidden_act": "silu",
115
+ "hidden_size": 1280,
116
+ "in_channels": 3,
117
+ "in_chans": 3,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3420,
120
+ "model_type": "qwen2_5_vl",
121
+ "num_heads": 16,
122
+ "out_hidden_size": 3584,
123
+ "patch_size": 14,
124
+ "spatial_merge_size": 2,
125
+ "spatial_patch_size": 14,
126
+ "temporal_patch_size": 2,
127
+ "tokens_per_second": 2,
128
+ "window_size": 112
129
+ },
130
+ "vision_end_token_id": 151653,
131
+ "vision_start_token_id": 151652,
132
+ "vision_token_id": 151654,
133
+ "vocab_size": 152064
134
+ }
iter4_sft/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 1e-06,
10
+ "transformers_version": "4.56.1"
11
+ }
iter4_sft/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
iter4_sft/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fe2113dc9788bc34af0d4be5f9d15fd4a88a2a3595ab9561ca55f267fcb143
3
+ size 4968243304
iter4_sft/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076c149cdb054a8e93b4724657987b6ebd660a3f85a8891358900272e4c4f507
3
+ size 4991495816
iter4_sft/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815623f817a05e9c15816122ef0ef5d366b9387d4ffc9561ff88fcc1de1cd623
3
+ size 4932751040
iter4_sft/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34637701b00724de851c7452079263ec60bbf717c9eabea0193ecfd3a96f50e0
3
+ size 1691924384
iter4_sft/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 848896,
4
+ "total_size": 16584333312
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
iter4_sft/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessor",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2_5_VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
iter4_sft/sft.log ADDED
The diff for this file is too large to render. See raw diff
 
iter4_sft/sft_config.yaml ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: /mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_4/rl/verl_checkpoints/global_step_100/actor/huggingface
3
+ image_max_pixels: 262144
4
+ video_max_pixels: 16384
5
+ trust_remote_code: true
6
+
7
+ ### method
8
+ stage: sft
9
+ do_train: true
10
+ finetuning_type: full
11
+ deepspeed: /home/ubuntu/projects/viewsuite/ViewSuite/iterative_training/configs/sft/ds_z3_config.json
12
+
13
+ ### dataset
14
+ dataset: multi_turn_action_gen,forward_dynamics,action_gen
15
+ dataset_dir: /mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_4/sft/sft_data
16
+ template: qwen2_vl
17
+ cutoff_len: 25000
18
+ preprocessing_num_workers: 4
19
+ dataloader_num_workers: 1
20
+
21
+ ### output
22
+ output_dir: /mnt/disk1/exps/verl_vagen/iterative_ppo_sft/iteration_4/sft/model
23
+ plot_loss: true
24
+ overwrite_output_dir: true
25
+ save_only_model: true
26
+ report_to: wandb
27
+
28
+ ### train
29
+ per_device_train_batch_size: 1
30
+ gradient_accumulation_steps: 2
31
+ num_train_epochs: 1
32
+ learning_rate: 2e-05
33
+ logging_steps: 1
34
+ save_steps: 100
35
+ lr_scheduler_type: cosine
36
+ warmup_ratio: 0.1
37
+ bf16: true
38
+ ddp_timeout: 180000000
39
+ use_fast_tokenizer: false
iter4_sft/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
iter4_sft/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
iter4_sft/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 50754799140864.0,
4
+ "train_loss": 0.09636665488652289,
5
+ "train_runtime": 845.3624,
6
+ "train_samples_per_second": 6.855,
7
+ "train_steps_per_second": 0.429
8
+ }
iter4_sft/trainer_log.jsonl ADDED
@@ -0,0 +1,364 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 363, "loss": 0.0852, "lr": 0.0, "epoch": 0.002758620689655172, "percentage": 0.28, "elapsed_time": "0:00:08", "remaining_time": "0:49:36"}
2
+ {"current_steps": 2, "total_steps": 363, "loss": 0.1171, "lr": 5.405405405405406e-07, "epoch": 0.005517241379310344, "percentage": 0.55, "elapsed_time": "0:00:10", "remaining_time": "0:32:09"}
3
+ {"current_steps": 3, "total_steps": 363, "loss": 0.1201, "lr": 1.0810810810810812e-06, "epoch": 0.008275862068965517, "percentage": 0.83, "elapsed_time": "0:00:13", "remaining_time": "0:26:00"}
4
+ {"current_steps": 4, "total_steps": 363, "loss": 0.0976, "lr": 1.6216216216216219e-06, "epoch": 0.011034482758620689, "percentage": 1.1, "elapsed_time": "0:00:15", "remaining_time": "0:23:03"}
5
+ {"current_steps": 5, "total_steps": 363, "loss": 0.1046, "lr": 2.1621621621621623e-06, "epoch": 0.013793103448275862, "percentage": 1.38, "elapsed_time": "0:00:17", "remaining_time": "0:20:46"}
6
+ {"current_steps": 6, "total_steps": 363, "loss": 0.0609, "lr": 2.702702702702703e-06, "epoch": 0.016551724137931035, "percentage": 1.65, "elapsed_time": "0:00:19", "remaining_time": "0:19:12"}
7
+ {"current_steps": 7, "total_steps": 363, "loss": 0.081, "lr": 3.2432432432432437e-06, "epoch": 0.019310344827586208, "percentage": 1.93, "elapsed_time": "0:00:21", "remaining_time": "0:18:12"}
8
+ {"current_steps": 8, "total_steps": 363, "loss": 0.1121, "lr": 3.7837837837837844e-06, "epoch": 0.022068965517241378, "percentage": 2.2, "elapsed_time": "0:00:23", "remaining_time": "0:17:16"}
9
+ {"current_steps": 9, "total_steps": 363, "loss": 0.1125, "lr": 4.324324324324325e-06, "epoch": 0.02482758620689655, "percentage": 2.48, "elapsed_time": "0:00:25", "remaining_time": "0:16:41"}
10
+ {"current_steps": 10, "total_steps": 363, "loss": 0.0724, "lr": 4.864864864864866e-06, "epoch": 0.027586206896551724, "percentage": 2.75, "elapsed_time": "0:00:27", "remaining_time": "0:16:06"}
11
+ {"current_steps": 11, "total_steps": 363, "loss": 0.1475, "lr": 5.405405405405406e-06, "epoch": 0.030344827586206897, "percentage": 3.03, "elapsed_time": "0:00:29", "remaining_time": "0:15:40"}
12
+ {"current_steps": 12, "total_steps": 363, "loss": 0.0974, "lr": 5.945945945945947e-06, "epoch": 0.03310344827586207, "percentage": 3.31, "elapsed_time": "0:00:31", "remaining_time": "0:15:20"}
13
+ {"current_steps": 13, "total_steps": 363, "loss": 0.0597, "lr": 6.486486486486487e-06, "epoch": 0.03586206896551724, "percentage": 3.58, "elapsed_time": "0:00:33", "remaining_time": "0:15:04"}
14
+ {"current_steps": 14, "total_steps": 363, "loss": 0.0778, "lr": 7.027027027027028e-06, "epoch": 0.038620689655172416, "percentage": 3.86, "elapsed_time": "0:00:35", "remaining_time": "0:14:46"}
15
+ {"current_steps": 15, "total_steps": 363, "loss": 0.0955, "lr": 7.567567567567569e-06, "epoch": 0.041379310344827586, "percentage": 4.13, "elapsed_time": "0:00:37", "remaining_time": "0:14:31"}
16
+ {"current_steps": 16, "total_steps": 363, "loss": 0.0869, "lr": 8.108108108108109e-06, "epoch": 0.044137931034482755, "percentage": 4.41, "elapsed_time": "0:00:39", "remaining_time": "0:14:16"}
17
+ {"current_steps": 17, "total_steps": 363, "loss": 0.0807, "lr": 8.64864864864865e-06, "epoch": 0.04689655172413793, "percentage": 4.68, "elapsed_time": "0:00:41", "remaining_time": "0:14:00"}
18
+ {"current_steps": 18, "total_steps": 363, "loss": 0.0665, "lr": 9.189189189189191e-06, "epoch": 0.0496551724137931, "percentage": 4.96, "elapsed_time": "0:00:43", "remaining_time": "0:13:46"}
19
+ {"current_steps": 19, "total_steps": 363, "loss": 0.0868, "lr": 9.729729729729732e-06, "epoch": 0.05241379310344828, "percentage": 5.23, "elapsed_time": "0:00:45", "remaining_time": "0:13:38"}
20
+ {"current_steps": 20, "total_steps": 363, "loss": 0.0736, "lr": 1.027027027027027e-05, "epoch": 0.05517241379310345, "percentage": 5.51, "elapsed_time": "0:00:47", "remaining_time": "0:13:28"}
21
+ {"current_steps": 21, "total_steps": 363, "loss": 0.079, "lr": 1.0810810810810812e-05, "epoch": 0.057931034482758624, "percentage": 5.79, "elapsed_time": "0:00:48", "remaining_time": "0:13:17"}
22
+ {"current_steps": 22, "total_steps": 363, "loss": 0.0437, "lr": 1.1351351351351352e-05, "epoch": 0.060689655172413794, "percentage": 6.06, "elapsed_time": "0:00:51", "remaining_time": "0:13:10"}
23
+ {"current_steps": 23, "total_steps": 363, "loss": 0.0905, "lr": 1.1891891891891894e-05, "epoch": 0.06344827586206897, "percentage": 6.34, "elapsed_time": "0:00:53", "remaining_time": "0:13:04"}
24
+ {"current_steps": 24, "total_steps": 363, "loss": 0.1024, "lr": 1.2432432432432433e-05, "epoch": 0.06620689655172414, "percentage": 6.61, "elapsed_time": "0:00:55", "remaining_time": "0:12:58"}
25
+ {"current_steps": 25, "total_steps": 363, "loss": 0.0701, "lr": 1.2972972972972975e-05, "epoch": 0.06896551724137931, "percentage": 6.89, "elapsed_time": "0:00:56", "remaining_time": "0:12:49"}
26
+ {"current_steps": 26, "total_steps": 363, "loss": 0.0748, "lr": 1.3513513513513515e-05, "epoch": 0.07172413793103448, "percentage": 7.16, "elapsed_time": "0:00:58", "remaining_time": "0:12:40"}
27
+ {"current_steps": 27, "total_steps": 363, "loss": 0.101, "lr": 1.4054054054054055e-05, "epoch": 0.07448275862068965, "percentage": 7.44, "elapsed_time": "0:01:00", "remaining_time": "0:12:34"}
28
+ {"current_steps": 28, "total_steps": 363, "loss": 0.0918, "lr": 1.4594594594594596e-05, "epoch": 0.07724137931034483, "percentage": 7.71, "elapsed_time": "0:01:02", "remaining_time": "0:12:29"}
29
+ {"current_steps": 29, "total_steps": 363, "loss": 0.0915, "lr": 1.5135135135135138e-05, "epoch": 0.08, "percentage": 7.99, "elapsed_time": "0:01:04", "remaining_time": "0:12:26"}
30
+ {"current_steps": 30, "total_steps": 363, "loss": 0.1025, "lr": 1.5675675675675676e-05, "epoch": 0.08275862068965517, "percentage": 8.26, "elapsed_time": "0:01:07", "remaining_time": "0:12:27"}
31
+ {"current_steps": 31, "total_steps": 363, "loss": 0.1059, "lr": 1.6216216216216218e-05, "epoch": 0.08551724137931034, "percentage": 8.54, "elapsed_time": "0:01:09", "remaining_time": "0:12:25"}
32
+ {"current_steps": 32, "total_steps": 363, "loss": 0.0677, "lr": 1.6756756756756757e-05, "epoch": 0.08827586206896551, "percentage": 8.82, "elapsed_time": "0:01:11", "remaining_time": "0:12:20"}
33
+ {"current_steps": 33, "total_steps": 363, "loss": 0.0894, "lr": 1.72972972972973e-05, "epoch": 0.0910344827586207, "percentage": 9.09, "elapsed_time": "0:01:13", "remaining_time": "0:12:15"}
34
+ {"current_steps": 34, "total_steps": 363, "loss": 0.1158, "lr": 1.783783783783784e-05, "epoch": 0.09379310344827586, "percentage": 9.37, "elapsed_time": "0:01:15", "remaining_time": "0:12:13"}
35
+ {"current_steps": 35, "total_steps": 363, "loss": 0.0924, "lr": 1.8378378378378383e-05, "epoch": 0.09655172413793103, "percentage": 9.64, "elapsed_time": "0:01:18", "remaining_time": "0:12:11"}
36
+ {"current_steps": 36, "total_steps": 363, "loss": 0.0978, "lr": 1.891891891891892e-05, "epoch": 0.0993103448275862, "percentage": 9.92, "elapsed_time": "0:01:19", "remaining_time": "0:12:06"}
37
+ {"current_steps": 37, "total_steps": 363, "loss": 0.1327, "lr": 1.9459459459459463e-05, "epoch": 0.10206896551724139, "percentage": 10.19, "elapsed_time": "0:01:22", "remaining_time": "0:12:06"}
38
+ {"current_steps": 38, "total_steps": 363, "loss": 0.095, "lr": 2e-05, "epoch": 0.10482758620689656, "percentage": 10.47, "elapsed_time": "0:01:24", "remaining_time": "0:12:02"}
39
+ {"current_steps": 39, "total_steps": 363, "loss": 0.0706, "lr": 1.9999535665248e-05, "epoch": 0.10758620689655173, "percentage": 10.74, "elapsed_time": "0:01:26", "remaining_time": "0:12:00"}
40
+ {"current_steps": 40, "total_steps": 363, "loss": 0.1205, "lr": 1.999814270411335e-05, "epoch": 0.1103448275862069, "percentage": 11.02, "elapsed_time": "0:01:29", "remaining_time": "0:11:58"}
41
+ {"current_steps": 41, "total_steps": 363, "loss": 0.0896, "lr": 1.99958212459561e-05, "epoch": 0.11310344827586206, "percentage": 11.29, "elapsed_time": "0:01:31", "remaining_time": "0:11:57"}
42
+ {"current_steps": 42, "total_steps": 363, "loss": 0.1012, "lr": 1.9992571506362997e-05, "epoch": 0.11586206896551725, "percentage": 11.57, "elapsed_time": "0:01:33", "remaining_time": "0:11:53"}
43
+ {"current_steps": 43, "total_steps": 363, "loss": 0.1087, "lr": 1.9988393787127444e-05, "epoch": 0.11862068965517242, "percentage": 11.85, "elapsed_time": "0:01:35", "remaining_time": "0:11:52"}
44
+ {"current_steps": 44, "total_steps": 363, "loss": 0.1382, "lr": 1.9983288476221482e-05, "epoch": 0.12137931034482759, "percentage": 12.12, "elapsed_time": "0:01:38", "remaining_time": "0:11:50"}
45
+ {"current_steps": 45, "total_steps": 363, "loss": 0.0538, "lr": 1.9977256047759765e-05, "epoch": 0.12413793103448276, "percentage": 12.4, "elapsed_time": "0:01:40", "remaining_time": "0:11:47"}
46
+ {"current_steps": 46, "total_steps": 363, "loss": 0.0855, "lr": 1.9970297061955533e-05, "epoch": 0.12689655172413794, "percentage": 12.67, "elapsed_time": "0:01:42", "remaining_time": "0:11:44"}
47
+ {"current_steps": 47, "total_steps": 363, "loss": 0.1386, "lr": 1.9962412165068575e-05, "epoch": 0.1296551724137931, "percentage": 12.95, "elapsed_time": "0:01:44", "remaining_time": "0:11:40"}
48
+ {"current_steps": 48, "total_steps": 363, "loss": 0.0961, "lr": 1.9953602089345215e-05, "epoch": 0.13241379310344828, "percentage": 13.22, "elapsed_time": "0:01:46", "remaining_time": "0:11:38"}
49
+ {"current_steps": 49, "total_steps": 363, "loss": 0.0857, "lr": 1.9943867652950323e-05, "epoch": 0.13517241379310344, "percentage": 13.5, "elapsed_time": "0:01:48", "remaining_time": "0:11:36"}
50
+ {"current_steps": 50, "total_steps": 363, "loss": 0.0563, "lr": 1.9933209759891318e-05, "epoch": 0.13793103448275862, "percentage": 13.77, "elapsed_time": "0:01:50", "remaining_time": "0:11:32"}
51
+ {"current_steps": 51, "total_steps": 363, "loss": 0.108, "lr": 1.9921629399934224e-05, "epoch": 0.1406896551724138, "percentage": 14.05, "elapsed_time": "0:01:52", "remaining_time": "0:11:28"}
52
+ {"current_steps": 52, "total_steps": 363, "loss": 0.1289, "lr": 1.9909127648511758e-05, "epoch": 0.14344827586206896, "percentage": 14.33, "elapsed_time": "0:01:54", "remaining_time": "0:11:26"}
53
+ {"current_steps": 53, "total_steps": 363, "loss": 0.0615, "lr": 1.989570566662345e-05, "epoch": 0.14620689655172414, "percentage": 14.6, "elapsed_time": "0:01:56", "remaining_time": "0:11:20"}
54
+ {"current_steps": 54, "total_steps": 363, "loss": 0.0559, "lr": 1.9881364700727827e-05, "epoch": 0.1489655172413793, "percentage": 14.88, "elapsed_time": "0:01:58", "remaining_time": "0:11:17"}
55
+ {"current_steps": 55, "total_steps": 363, "loss": 0.0512, "lr": 1.986610608262665e-05, "epoch": 0.15172413793103448, "percentage": 15.15, "elapsed_time": "0:02:00", "remaining_time": "0:11:14"}
56
+ {"current_steps": 56, "total_steps": 363, "loss": 0.1492, "lr": 1.9849931229341258e-05, "epoch": 0.15448275862068966, "percentage": 15.43, "elapsed_time": "0:02:02", "remaining_time": "0:11:11"}
57
+ {"current_steps": 57, "total_steps": 363, "loss": 0.1277, "lr": 1.9832841642980948e-05, "epoch": 0.15724137931034482, "percentage": 15.7, "elapsed_time": "0:02:04", "remaining_time": "0:11:07"}
58
+ {"current_steps": 58, "total_steps": 363, "loss": 0.1266, "lr": 1.981483891060348e-05, "epoch": 0.16, "percentage": 15.98, "elapsed_time": "0:02:06", "remaining_time": "0:11:04"}
59
+ {"current_steps": 59, "total_steps": 363, "loss": 0.095, "lr": 1.979592470406772e-05, "epoch": 0.16275862068965516, "percentage": 16.25, "elapsed_time": "0:02:07", "remaining_time": "0:10:59"}
60
+ {"current_steps": 60, "total_steps": 363, "loss": 0.0602, "lr": 1.9776100779878344e-05, "epoch": 0.16551724137931034, "percentage": 16.53, "elapsed_time": "0:02:09", "remaining_time": "0:10:54"}
61
+ {"current_steps": 61, "total_steps": 363, "loss": 0.0597, "lr": 1.9755368979022734e-05, "epoch": 0.16827586206896553, "percentage": 16.8, "elapsed_time": "0:02:11", "remaining_time": "0:10:51"}
62
+ {"current_steps": 62, "total_steps": 363, "loss": 0.0902, "lr": 1.9733731226800016e-05, "epoch": 0.17103448275862068, "percentage": 17.08, "elapsed_time": "0:02:13", "remaining_time": "0:10:48"}
63
+ {"current_steps": 63, "total_steps": 363, "loss": 0.0851, "lr": 1.9711189532642244e-05, "epoch": 0.17379310344827587, "percentage": 17.36, "elapsed_time": "0:02:15", "remaining_time": "0:10:44"}
64
+ {"current_steps": 64, "total_steps": 363, "loss": 0.1022, "lr": 1.9687745989927823e-05, "epoch": 0.17655172413793102, "percentage": 17.63, "elapsed_time": "0:02:17", "remaining_time": "0:10:40"}
65
+ {"current_steps": 65, "total_steps": 363, "loss": 0.1402, "lr": 1.9663402775787066e-05, "epoch": 0.1793103448275862, "percentage": 17.91, "elapsed_time": "0:02:18", "remaining_time": "0:10:36"}
66
+ {"current_steps": 66, "total_steps": 363, "loss": 0.0595, "lr": 1.9638162150900028e-05, "epoch": 0.1820689655172414, "percentage": 18.18, "elapsed_time": "0:02:20", "remaining_time": "0:10:32"}
67
+ {"current_steps": 67, "total_steps": 363, "loss": 0.1526, "lr": 1.961202645928658e-05, "epoch": 0.18482758620689654, "percentage": 18.46, "elapsed_time": "0:02:22", "remaining_time": "0:10:29"}
68
+ {"current_steps": 68, "total_steps": 363, "loss": 0.1149, "lr": 1.9584998128088686e-05, "epoch": 0.18758620689655173, "percentage": 18.73, "elapsed_time": "0:02:24", "remaining_time": "0:10:25"}
69
+ {"current_steps": 69, "total_steps": 363, "loss": 0.1724, "lr": 1.955707966734505e-05, "epoch": 0.19034482758620688, "percentage": 19.01, "elapsed_time": "0:02:25", "remaining_time": "0:10:21"}
70
+ {"current_steps": 70, "total_steps": 363, "loss": 0.1357, "lr": 1.9528273669757974e-05, "epoch": 0.19310344827586207, "percentage": 19.28, "elapsed_time": "0:02:27", "remaining_time": "0:10:17"}
71
+ {"current_steps": 71, "total_steps": 363, "loss": 0.1289, "lr": 1.9498582810452607e-05, "epoch": 0.19586206896551725, "percentage": 19.56, "elapsed_time": "0:02:29", "remaining_time": "0:10:15"}
72
+ {"current_steps": 72, "total_steps": 363, "loss": 0.1201, "lr": 1.9468009846728515e-05, "epoch": 0.1986206896551724, "percentage": 19.83, "elapsed_time": "0:02:31", "remaining_time": "0:10:11"}
73
+ {"current_steps": 73, "total_steps": 363, "loss": 0.1343, "lr": 1.9436557617803594e-05, "epoch": 0.2013793103448276, "percentage": 20.11, "elapsed_time": "0:02:32", "remaining_time": "0:10:07"}
74
+ {"current_steps": 74, "total_steps": 363, "loss": 0.1014, "lr": 1.9404229044550432e-05, "epoch": 0.20413793103448277, "percentage": 20.39, "elapsed_time": "0:02:34", "remaining_time": "0:10:04"}
75
+ {"current_steps": 75, "total_steps": 363, "loss": 0.08, "lr": 1.9371027129225042e-05, "epoch": 0.20689655172413793, "percentage": 20.66, "elapsed_time": "0:02:37", "remaining_time": "0:10:03"}
76
+ {"current_steps": 76, "total_steps": 363, "loss": 0.0664, "lr": 1.9336954955188042e-05, "epoch": 0.2096551724137931, "percentage": 20.94, "elapsed_time": "0:02:39", "remaining_time": "0:10:01"}
77
+ {"current_steps": 77, "total_steps": 363, "loss": 0.1228, "lr": 1.9302015686618328e-05, "epoch": 0.21241379310344827, "percentage": 21.21, "elapsed_time": "0:02:41", "remaining_time": "0:09:59"}
78
+ {"current_steps": 78, "total_steps": 363, "loss": 0.1181, "lr": 1.9266212568219223e-05, "epoch": 0.21517241379310345, "percentage": 21.49, "elapsed_time": "0:02:44", "remaining_time": "0:09:59"}
79
+ {"current_steps": 79, "total_steps": 363, "loss": 0.1593, "lr": 1.9229548924917146e-05, "epoch": 0.21793103448275863, "percentage": 21.76, "elapsed_time": "0:02:47", "remaining_time": "0:10:00"}
80
+ {"current_steps": 80, "total_steps": 363, "loss": 0.1068, "lr": 1.9192028161552848e-05, "epoch": 0.2206896551724138, "percentage": 22.04, "elapsed_time": "0:02:49", "remaining_time": "0:09:59"}
81
+ {"current_steps": 81, "total_steps": 363, "loss": 0.1395, "lr": 1.915365376256519e-05, "epoch": 0.22344827586206897, "percentage": 22.31, "elapsed_time": "0:02:51", "remaining_time": "0:09:57"}
82
+ {"current_steps": 82, "total_steps": 363, "loss": 0.1322, "lr": 1.9114429291667583e-05, "epoch": 0.22620689655172413, "percentage": 22.59, "elapsed_time": "0:02:53", "remaining_time": "0:09:54"}
83
+ {"current_steps": 83, "total_steps": 363, "loss": 0.1298, "lr": 1.9074358391517026e-05, "epoch": 0.2289655172413793, "percentage": 22.87, "elapsed_time": "0:02:55", "remaining_time": "0:09:51"}
84
+ {"current_steps": 84, "total_steps": 363, "loss": 0.1375, "lr": 1.9033444783375806e-05, "epoch": 0.2317241379310345, "percentage": 23.14, "elapsed_time": "0:02:57", "remaining_time": "0:09:49"}
85
+ {"current_steps": 85, "total_steps": 363, "loss": 0.1454, "lr": 1.8991692266765947e-05, "epoch": 0.23448275862068965, "percentage": 23.42, "elapsed_time": "0:02:59", "remaining_time": "0:09:47"}
86
+ {"current_steps": 86, "total_steps": 363, "loss": 0.1004, "lr": 1.8949104719116334e-05, "epoch": 0.23724137931034484, "percentage": 23.69, "elapsed_time": "0:03:01", "remaining_time": "0:09:45"}
87
+ {"current_steps": 87, "total_steps": 363, "loss": 0.0729, "lr": 1.8905686095402648e-05, "epoch": 0.24, "percentage": 23.97, "elapsed_time": "0:03:04", "remaining_time": "0:09:45"}
88
+ {"current_steps": 88, "total_steps": 363, "loss": 0.1219, "lr": 1.886144042778006e-05, "epoch": 0.24275862068965517, "percentage": 24.24, "elapsed_time": "0:03:07", "remaining_time": "0:09:45"}
89
+ {"current_steps": 89, "total_steps": 363, "loss": 0.1277, "lr": 1.881637182520879e-05, "epoch": 0.24551724137931036, "percentage": 24.52, "elapsed_time": "0:03:09", "remaining_time": "0:09:44"}
90
+ {"current_steps": 90, "total_steps": 363, "loss": 0.133, "lr": 1.8770484473072518e-05, "epoch": 0.2482758620689655, "percentage": 24.79, "elapsed_time": "0:03:12", "remaining_time": "0:09:42"}
91
+ {"current_steps": 91, "total_steps": 363, "loss": 0.1271, "lr": 1.87237826327897e-05, "epoch": 0.25103448275862067, "percentage": 25.07, "elapsed_time": "0:03:14", "remaining_time": "0:09:40"}
92
+ {"current_steps": 92, "total_steps": 363, "loss": 0.1337, "lr": 1.8676270641417824e-05, "epoch": 0.2537931034482759, "percentage": 25.34, "elapsed_time": "0:03:16", "remaining_time": "0:09:38"}
93
+ {"current_steps": 93, "total_steps": 363, "loss": 0.1188, "lr": 1.8627952911250632e-05, "epoch": 0.25655172413793104, "percentage": 25.62, "elapsed_time": "0:03:18", "remaining_time": "0:09:36"}
94
+ {"current_steps": 94, "total_steps": 363, "loss": 0.09, "lr": 1.857883392940837e-05, "epoch": 0.2593103448275862, "percentage": 25.9, "elapsed_time": "0:03:20", "remaining_time": "0:09:33"}
95
+ {"current_steps": 95, "total_steps": 363, "loss": 0.1084, "lr": 1.85289182574211e-05, "epoch": 0.2620689655172414, "percentage": 26.17, "elapsed_time": "0:03:22", "remaining_time": "0:09:30"}
96
+ {"current_steps": 96, "total_steps": 363, "loss": 0.1003, "lr": 1.847821053080505e-05, "epoch": 0.26482758620689656, "percentage": 26.45, "elapsed_time": "0:03:24", "remaining_time": "0:09:28"}
97
+ {"current_steps": 97, "total_steps": 363, "loss": 0.0747, "lr": 1.8426715458632154e-05, "epoch": 0.2675862068965517, "percentage": 26.72, "elapsed_time": "0:03:26", "remaining_time": "0:09:26"}
98
+ {"current_steps": 98, "total_steps": 363, "loss": 0.1513, "lr": 1.8374437823092726e-05, "epoch": 0.27034482758620687, "percentage": 27.0, "elapsed_time": "0:03:28", "remaining_time": "0:09:23"}
99
+ {"current_steps": 99, "total_steps": 363, "loss": 0.088, "lr": 1.832138247905135e-05, "epoch": 0.2731034482758621, "percentage": 27.27, "elapsed_time": "0:03:30", "remaining_time": "0:09:20"}
100
+ {"current_steps": 100, "total_steps": 363, "loss": 0.0617, "lr": 1.8267554353596027e-05, "epoch": 0.27586206896551724, "percentage": 27.55, "elapsed_time": "0:03:32", "remaining_time": "0:09:17"}
101
+ {"current_steps": 101, "total_steps": 363, "loss": 0.0809, "lr": 1.8212958445580623e-05, "epoch": 0.2786206896551724, "percentage": 27.82, "elapsed_time": "0:03:59", "remaining_time": "0:10:21"}
102
+ {"current_steps": 102, "total_steps": 363, "loss": 0.0987, "lr": 1.815759982516061e-05, "epoch": 0.2813793103448276, "percentage": 28.1, "elapsed_time": "0:04:01", "remaining_time": "0:10:18"}
103
+ {"current_steps": 103, "total_steps": 363, "loss": 0.1055, "lr": 1.8101483633322255e-05, "epoch": 0.28413793103448276, "percentage": 28.37, "elapsed_time": "0:04:03", "remaining_time": "0:10:14"}
104
+ {"current_steps": 104, "total_steps": 363, "loss": 0.12, "lr": 1.8044615081405153e-05, "epoch": 0.2868965517241379, "percentage": 28.65, "elapsed_time": "0:04:05", "remaining_time": "0:10:12"}
105
+ {"current_steps": 105, "total_steps": 363, "loss": 0.1293, "lr": 1.7986999450618295e-05, "epoch": 0.2896551724137931, "percentage": 28.93, "elapsed_time": "0:04:07", "remaining_time": "0:10:08"}
106
+ {"current_steps": 106, "total_steps": 363, "loss": 0.0945, "lr": 1.7928642091549616e-05, "epoch": 0.2924137931034483, "percentage": 29.2, "elapsed_time": "0:04:09", "remaining_time": "0:10:05"}
107
+ {"current_steps": 107, "total_steps": 363, "loss": 0.1124, "lr": 1.7869548423669075e-05, "epoch": 0.29517241379310344, "percentage": 29.48, "elapsed_time": "0:04:11", "remaining_time": "0:10:01"}
108
+ {"current_steps": 108, "total_steps": 363, "loss": 0.1182, "lr": 1.7809723934825405e-05, "epoch": 0.2979310344827586, "percentage": 29.75, "elapsed_time": "0:04:13", "remaining_time": "0:09:58"}
109
+ {"current_steps": 109, "total_steps": 363, "loss": 0.0857, "lr": 1.7749174180736443e-05, "epoch": 0.3006896551724138, "percentage": 30.03, "elapsed_time": "0:04:15", "remaining_time": "0:09:54"}
110
+ {"current_steps": 110, "total_steps": 363, "loss": 0.0781, "lr": 1.768790478447319e-05, "epoch": 0.30344827586206896, "percentage": 30.3, "elapsed_time": "0:04:16", "remaining_time": "0:09:50"}
111
+ {"current_steps": 111, "total_steps": 363, "loss": 0.0713, "lr": 1.762592143593764e-05, "epoch": 0.3062068965517241, "percentage": 30.58, "elapsed_time": "0:04:18", "remaining_time": "0:09:47"}
112
+ {"current_steps": 112, "total_steps": 363, "loss": 0.1301, "lr": 1.756322989133434e-05, "epoch": 0.30896551724137933, "percentage": 30.85, "elapsed_time": "0:04:20", "remaining_time": "0:09:43"}
113
+ {"current_steps": 113, "total_steps": 363, "loss": 0.0681, "lr": 1.749983597263586e-05, "epoch": 0.3117241379310345, "percentage": 31.13, "elapsed_time": "0:04:22", "remaining_time": "0:09:40"}
114
+ {"current_steps": 114, "total_steps": 363, "loss": 0.1331, "lr": 1.7435745567042096e-05, "epoch": 0.31448275862068964, "percentage": 31.4, "elapsed_time": "0:04:24", "remaining_time": "0:09:37"}
115
+ {"current_steps": 115, "total_steps": 363, "loss": 0.0604, "lr": 1.737096462643357e-05, "epoch": 0.31724137931034485, "percentage": 31.68, "elapsed_time": "0:04:25", "remaining_time": "0:09:33"}
116
+ {"current_steps": 116, "total_steps": 363, "loss": 0.1494, "lr": 1.730549916681868e-05, "epoch": 0.32, "percentage": 31.96, "elapsed_time": "0:04:27", "remaining_time": "0:09:30"}
117
+ {"current_steps": 117, "total_steps": 363, "loss": 0.1092, "lr": 1.723935526777502e-05, "epoch": 0.32275862068965516, "percentage": 32.23, "elapsed_time": "0:04:29", "remaining_time": "0:09:26"}
118
+ {"current_steps": 118, "total_steps": 363, "loss": 0.1082, "lr": 1.717253907188477e-05, "epoch": 0.3255172413793103, "percentage": 32.51, "elapsed_time": "0:04:31", "remaining_time": "0:09:23"}
119
+ {"current_steps": 119, "total_steps": 363, "loss": 0.1703, "lr": 1.7105056784164295e-05, "epoch": 0.32827586206896553, "percentage": 32.78, "elapsed_time": "0:04:33", "remaining_time": "0:09:20"}
120
+ {"current_steps": 120, "total_steps": 363, "loss": 0.1303, "lr": 1.7036914671487854e-05, "epoch": 0.3310344827586207, "percentage": 33.06, "elapsed_time": "0:04:34", "remaining_time": "0:09:16"}
121
+ {"current_steps": 121, "total_steps": 363, "loss": 0.1077, "lr": 1.6968119062005644e-05, "epoch": 0.33379310344827584, "percentage": 33.33, "elapsed_time": "0:04:36", "remaining_time": "0:09:13"}
122
+ {"current_steps": 122, "total_steps": 363, "loss": 0.0924, "lr": 1.689867634455612e-05, "epoch": 0.33655172413793105, "percentage": 33.61, "elapsed_time": "0:04:38", "remaining_time": "0:09:10"}
123
+ {"current_steps": 123, "total_steps": 363, "loss": 0.1221, "lr": 1.682859296807268e-05, "epoch": 0.3393103448275862, "percentage": 33.88, "elapsed_time": "0:04:40", "remaining_time": "0:09:07"}
124
+ {"current_steps": 124, "total_steps": 363, "loss": 0.1106, "lr": 1.675787544098477e-05, "epoch": 0.34206896551724136, "percentage": 34.16, "elapsed_time": "0:04:42", "remaining_time": "0:09:04"}
125
+ {"current_steps": 125, "total_steps": 363, "loss": 0.1122, "lr": 1.6686530330613472e-05, "epoch": 0.3448275862068966, "percentage": 34.44, "elapsed_time": "0:04:44", "remaining_time": "0:09:02"}
126
+ {"current_steps": 126, "total_steps": 363, "loss": 0.087, "lr": 1.661456426256161e-05, "epoch": 0.34758620689655173, "percentage": 34.71, "elapsed_time": "0:04:47", "remaining_time": "0:08:59"}
127
+ {"current_steps": 127, "total_steps": 363, "loss": 0.087, "lr": 1.6541983920098462e-05, "epoch": 0.3503448275862069, "percentage": 34.99, "elapsed_time": "0:04:49", "remaining_time": "0:08:57"}
128
+ {"current_steps": 128, "total_steps": 363, "loss": 0.1254, "lr": 1.6468796043539082e-05, "epoch": 0.35310344827586204, "percentage": 35.26, "elapsed_time": "0:04:51", "remaining_time": "0:08:54"}
129
+ {"current_steps": 129, "total_steps": 363, "loss": 0.0498, "lr": 1.639500742961838e-05, "epoch": 0.35586206896551725, "percentage": 35.54, "elapsed_time": "0:04:53", "remaining_time": "0:08:51"}
130
+ {"current_steps": 130, "total_steps": 363, "loss": 0.077, "lr": 1.6320624930859905e-05, "epoch": 0.3586206896551724, "percentage": 35.81, "elapsed_time": "0:04:54", "remaining_time": "0:08:48"}
131
+ {"current_steps": 131, "total_steps": 363, "loss": 0.0352, "lr": 1.6245655454939474e-05, "epoch": 0.36137931034482756, "percentage": 36.09, "elapsed_time": "0:04:56", "remaining_time": "0:08:45"}
132
+ {"current_steps": 132, "total_steps": 363, "loss": 0.1228, "lr": 1.6170105964043698e-05, "epoch": 0.3641379310344828, "percentage": 36.36, "elapsed_time": "0:04:58", "remaining_time": "0:08:41"}
133
+ {"current_steps": 133, "total_steps": 363, "loss": 0.1799, "lr": 1.6093983474223392e-05, "epoch": 0.36689655172413793, "percentage": 36.64, "elapsed_time": "0:05:00", "remaining_time": "0:08:39"}
134
+ {"current_steps": 134, "total_steps": 363, "loss": 0.1088, "lr": 1.6017295054742045e-05, "epoch": 0.3696551724137931, "percentage": 36.91, "elapsed_time": "0:05:02", "remaining_time": "0:08:37"}
135
+ {"current_steps": 135, "total_steps": 363, "loss": 0.0722, "lr": 1.5940047827419305e-05, "epoch": 0.3724137931034483, "percentage": 37.19, "elapsed_time": "0:05:05", "remaining_time": "0:08:35"}
136
+ {"current_steps": 136, "total_steps": 363, "loss": 0.0902, "lr": 1.5862248965969604e-05, "epoch": 0.37517241379310345, "percentage": 37.47, "elapsed_time": "0:05:07", "remaining_time": "0:08:33"}
137
+ {"current_steps": 137, "total_steps": 363, "loss": 0.0763, "lr": 1.5783905695335947e-05, "epoch": 0.3779310344827586, "percentage": 37.74, "elapsed_time": "0:05:09", "remaining_time": "0:08:30"}
138
+ {"current_steps": 138, "total_steps": 363, "loss": 0.0582, "lr": 1.570502529101896e-05, "epoch": 0.38068965517241377, "percentage": 38.02, "elapsed_time": "0:05:11", "remaining_time": "0:08:27"}
139
+ {"current_steps": 139, "total_steps": 363, "loss": 0.1131, "lr": 1.5625615078401244e-05, "epoch": 0.383448275862069, "percentage": 38.29, "elapsed_time": "0:05:13", "remaining_time": "0:08:24"}
140
+ {"current_steps": 140, "total_steps": 363, "loss": 0.1319, "lr": 1.5545682432067068e-05, "epoch": 0.38620689655172413, "percentage": 38.57, "elapsed_time": "0:05:14", "remaining_time": "0:08:21"}
141
+ {"current_steps": 141, "total_steps": 363, "loss": 0.1232, "lr": 1.5465234775117538e-05, "epoch": 0.3889655172413793, "percentage": 38.84, "elapsed_time": "0:05:16", "remaining_time": "0:08:18"}
142
+ {"current_steps": 142, "total_steps": 363, "loss": 0.1537, "lr": 1.5384279578481223e-05, "epoch": 0.3917241379310345, "percentage": 39.12, "elapsed_time": "0:05:18", "remaining_time": "0:08:15"}
143
+ {"current_steps": 143, "total_steps": 363, "loss": 0.1161, "lr": 1.5302824360220352e-05, "epoch": 0.39448275862068966, "percentage": 39.39, "elapsed_time": "0:05:20", "remaining_time": "0:08:13"}
144
+ {"current_steps": 144, "total_steps": 363, "loss": 0.1054, "lr": 1.522087668483264e-05, "epoch": 0.3972413793103448, "percentage": 39.67, "elapsed_time": "0:05:22", "remaining_time": "0:08:10"}
145
+ {"current_steps": 145, "total_steps": 363, "loss": 0.072, "lr": 1.5138444162548791e-05, "epoch": 0.4, "percentage": 39.94, "elapsed_time": "0:05:24", "remaining_time": "0:08:07"}
146
+ {"current_steps": 146, "total_steps": 363, "loss": 0.1956, "lr": 1.5055534448625766e-05, "epoch": 0.4027586206896552, "percentage": 40.22, "elapsed_time": "0:05:26", "remaining_time": "0:08:04"}
147
+ {"current_steps": 147, "total_steps": 363, "loss": 0.1163, "lr": 1.4972155242635853e-05, "epoch": 0.40551724137931033, "percentage": 40.5, "elapsed_time": "0:05:28", "remaining_time": "0:08:02"}
148
+ {"current_steps": 148, "total_steps": 363, "loss": 0.1588, "lr": 1.488831428775164e-05, "epoch": 0.40827586206896554, "percentage": 40.77, "elapsed_time": "0:05:30", "remaining_time": "0:08:00"}
149
+ {"current_steps": 149, "total_steps": 363, "loss": 0.0874, "lr": 1.4804019370026927e-05, "epoch": 0.4110344827586207, "percentage": 41.05, "elapsed_time": "0:05:32", "remaining_time": "0:07:57"}
150
+ {"current_steps": 150, "total_steps": 363, "loss": 0.1225, "lr": 1.4719278317673655e-05, "epoch": 0.41379310344827586, "percentage": 41.32, "elapsed_time": "0:05:35", "remaining_time": "0:07:56"}
151
+ {"current_steps": 151, "total_steps": 363, "loss": 0.0628, "lr": 1.4634099000334932e-05, "epoch": 0.416551724137931, "percentage": 41.6, "elapsed_time": "0:05:37", "remaining_time": "0:07:53"}
152
+ {"current_steps": 152, "total_steps": 363, "loss": 0.1119, "lr": 1.4548489328354197e-05, "epoch": 0.4193103448275862, "percentage": 41.87, "elapsed_time": "0:05:39", "remaining_time": "0:07:50"}
153
+ {"current_steps": 153, "total_steps": 363, "loss": 0.1371, "lr": 1.4462457252040606e-05, "epoch": 0.4220689655172414, "percentage": 42.15, "elapsed_time": "0:05:41", "remaining_time": "0:07:48"}
154
+ {"current_steps": 154, "total_steps": 363, "loss": 0.0715, "lr": 1.437601076093073e-05, "epoch": 0.42482758620689653, "percentage": 42.42, "elapsed_time": "0:05:43", "remaining_time": "0:07:45"}
155
+ {"current_steps": 155, "total_steps": 363, "loss": 0.0671, "lr": 1.4289157883046567e-05, "epoch": 0.42758620689655175, "percentage": 42.7, "elapsed_time": "0:05:45", "remaining_time": "0:07:43"}
156
+ {"current_steps": 156, "total_steps": 363, "loss": 0.0937, "lr": 1.420190668415002e-05, "epoch": 0.4303448275862069, "percentage": 42.98, "elapsed_time": "0:05:47", "remaining_time": "0:07:40"}
157
+ {"current_steps": 157, "total_steps": 363, "loss": 0.1114, "lr": 1.4114265266993847e-05, "epoch": 0.43310344827586206, "percentage": 43.25, "elapsed_time": "0:05:49", "remaining_time": "0:07:38"}
158
+ {"current_steps": 158, "total_steps": 363, "loss": 0.1388, "lr": 1.4026241770569198e-05, "epoch": 0.43586206896551727, "percentage": 43.53, "elapsed_time": "0:05:51", "remaining_time": "0:07:36"}
159
+ {"current_steps": 159, "total_steps": 363, "loss": 0.0862, "lr": 1.3937844369349736e-05, "epoch": 0.4386206896551724, "percentage": 43.8, "elapsed_time": "0:05:53", "remaining_time": "0:07:34"}
160
+ {"current_steps": 160, "total_steps": 363, "loss": 0.0752, "lr": 1.3849081272532545e-05, "epoch": 0.4413793103448276, "percentage": 44.08, "elapsed_time": "0:05:56", "remaining_time": "0:07:32"}
161
+ {"current_steps": 161, "total_steps": 363, "loss": 0.1456, "lr": 1.375996072327573e-05, "epoch": 0.44413793103448274, "percentage": 44.35, "elapsed_time": "0:05:59", "remaining_time": "0:07:30"}
162
+ {"current_steps": 162, "total_steps": 363, "loss": 0.109, "lr": 1.3670490997932922e-05, "epoch": 0.44689655172413795, "percentage": 44.63, "elapsed_time": "0:06:01", "remaining_time": "0:07:28"}
163
+ {"current_steps": 163, "total_steps": 363, "loss": 0.1144, "lr": 1.3580680405284666e-05, "epoch": 0.4496551724137931, "percentage": 44.9, "elapsed_time": "0:06:03", "remaining_time": "0:07:25"}
164
+ {"current_steps": 164, "total_steps": 363, "loss": 0.0838, "lr": 1.3490537285766809e-05, "epoch": 0.45241379310344826, "percentage": 45.18, "elapsed_time": "0:06:04", "remaining_time": "0:07:22"}
165
+ {"current_steps": 165, "total_steps": 363, "loss": 0.1309, "lr": 1.3400070010695966e-05, "epoch": 0.45517241379310347, "percentage": 45.45, "elapsed_time": "0:06:06", "remaining_time": "0:07:20"}
166
+ {"current_steps": 166, "total_steps": 363, "loss": 0.1336, "lr": 1.3309286981492084e-05, "epoch": 0.4579310344827586, "percentage": 45.73, "elapsed_time": "0:06:09", "remaining_time": "0:07:17"}
167
+ {"current_steps": 167, "total_steps": 363, "loss": 0.0878, "lr": 1.3218196628898232e-05, "epoch": 0.4606896551724138, "percentage": 46.01, "elapsed_time": "0:06:11", "remaining_time": "0:07:15"}
168
+ {"current_steps": 168, "total_steps": 363, "loss": 0.0866, "lr": 1.3126807412197666e-05, "epoch": 0.463448275862069, "percentage": 46.28, "elapsed_time": "0:06:13", "remaining_time": "0:07:13"}
169
+ {"current_steps": 169, "total_steps": 363, "loss": 0.0863, "lr": 1.3035127818428239e-05, "epoch": 0.46620689655172415, "percentage": 46.56, "elapsed_time": "0:06:15", "remaining_time": "0:07:10"}
170
+ {"current_steps": 170, "total_steps": 363, "loss": 0.1393, "lr": 1.2943166361594242e-05, "epoch": 0.4689655172413793, "percentage": 46.83, "elapsed_time": "0:06:17", "remaining_time": "0:07:08"}
171
+ {"current_steps": 171, "total_steps": 363, "loss": 0.1762, "lr": 1.2850931581875723e-05, "epoch": 0.47172413793103446, "percentage": 47.11, "elapsed_time": "0:06:19", "remaining_time": "0:07:06"}
172
+ {"current_steps": 172, "total_steps": 363, "loss": 0.0599, "lr": 1.275843204483539e-05, "epoch": 0.47448275862068967, "percentage": 47.38, "elapsed_time": "0:06:21", "remaining_time": "0:07:03"}
173
+ {"current_steps": 173, "total_steps": 363, "loss": 0.0938, "lr": 1.2665676340623172e-05, "epoch": 0.4772413793103448, "percentage": 47.66, "elapsed_time": "0:06:23", "remaining_time": "0:07:00"}
174
+ {"current_steps": 174, "total_steps": 363, "loss": 0.098, "lr": 1.2572673083178448e-05, "epoch": 0.48, "percentage": 47.93, "elapsed_time": "0:06:25", "remaining_time": "0:06:58"}
175
+ {"current_steps": 175, "total_steps": 363, "loss": 0.0936, "lr": 1.2479430909430109e-05, "epoch": 0.4827586206896552, "percentage": 48.21, "elapsed_time": "0:06:27", "remaining_time": "0:06:55"}
176
+ {"current_steps": 176, "total_steps": 363, "loss": 0.1279, "lr": 1.2385958478494487e-05, "epoch": 0.48551724137931035, "percentage": 48.48, "elapsed_time": "0:06:29", "remaining_time": "0:06:53"}
177
+ {"current_steps": 177, "total_steps": 363, "loss": 0.0783, "lr": 1.2292264470871183e-05, "epoch": 0.4882758620689655, "percentage": 48.76, "elapsed_time": "0:06:31", "remaining_time": "0:06:51"}
178
+ {"current_steps": 178, "total_steps": 363, "loss": 0.0525, "lr": 1.2198357587636958e-05, "epoch": 0.4910344827586207, "percentage": 49.04, "elapsed_time": "0:06:33", "remaining_time": "0:06:48"}
179
+ {"current_steps": 179, "total_steps": 363, "loss": 0.0978, "lr": 1.2104246549637683e-05, "epoch": 0.49379310344827587, "percentage": 49.31, "elapsed_time": "0:06:35", "remaining_time": "0:06:46"}
180
+ {"current_steps": 180, "total_steps": 363, "loss": 0.0963, "lr": 1.2009940096678451e-05, "epoch": 0.496551724137931, "percentage": 49.59, "elapsed_time": "0:06:37", "remaining_time": "0:06:44"}
181
+ {"current_steps": 181, "total_steps": 363, "loss": 0.1092, "lr": 1.1915446986711953e-05, "epoch": 0.4993103448275862, "percentage": 49.86, "elapsed_time": "0:06:39", "remaining_time": "0:06:42"}
182
+ {"current_steps": 182, "total_steps": 363, "loss": 0.0667, "lr": 1.1820775995025147e-05, "epoch": 0.5020689655172413, "percentage": 50.14, "elapsed_time": "0:06:42", "remaining_time": "0:06:39"}
183
+ {"current_steps": 183, "total_steps": 363, "loss": 0.0882, "lr": 1.172593591342432e-05, "epoch": 0.5048275862068966, "percentage": 50.41, "elapsed_time": "0:06:44", "remaining_time": "0:06:37"}
184
+ {"current_steps": 184, "total_steps": 363, "loss": 0.0865, "lr": 1.1630935549418627e-05, "epoch": 0.5075862068965518, "percentage": 50.69, "elapsed_time": "0:06:46", "remaining_time": "0:06:34"}
185
+ {"current_steps": 185, "total_steps": 363, "loss": 0.1353, "lr": 1.1535783725402163e-05, "epoch": 0.5103448275862069, "percentage": 50.96, "elapsed_time": "0:06:48", "remaining_time": "0:06:32"}
186
+ {"current_steps": 186, "total_steps": 363, "loss": 0.1393, "lr": 1.1440489277834645e-05, "epoch": 0.5131034482758621, "percentage": 51.24, "elapsed_time": "0:06:50", "remaining_time": "0:06:30"}
187
+ {"current_steps": 187, "total_steps": 363, "loss": 0.1169, "lr": 1.134506105642081e-05, "epoch": 0.5158620689655172, "percentage": 51.52, "elapsed_time": "0:06:52", "remaining_time": "0:06:28"}
188
+ {"current_steps": 188, "total_steps": 363, "loss": 0.1241, "lr": 1.1249507923288563e-05, "epoch": 0.5186206896551724, "percentage": 51.79, "elapsed_time": "0:06:55", "remaining_time": "0:06:26"}
189
+ {"current_steps": 189, "total_steps": 363, "loss": 0.0945, "lr": 1.115383875216598e-05, "epoch": 0.5213793103448275, "percentage": 52.07, "elapsed_time": "0:06:58", "remaining_time": "0:06:25"}
190
+ {"current_steps": 190, "total_steps": 363, "loss": 0.0791, "lr": 1.105806242755723e-05, "epoch": 0.5241379310344828, "percentage": 52.34, "elapsed_time": "0:07:00", "remaining_time": "0:06:23"}
191
+ {"current_steps": 191, "total_steps": 363, "loss": 0.0995, "lr": 1.0962187843917498e-05, "epoch": 0.526896551724138, "percentage": 52.62, "elapsed_time": "0:07:03", "remaining_time": "0:06:21"}
192
+ {"current_steps": 192, "total_steps": 363, "loss": 0.0978, "lr": 1.0866223904826992e-05, "epoch": 0.5296551724137931, "percentage": 52.89, "elapsed_time": "0:07:05", "remaining_time": "0:06:19"}
193
+ {"current_steps": 193, "total_steps": 363, "loss": 0.0654, "lr": 1.0770179522164079e-05, "epoch": 0.5324137931034483, "percentage": 53.17, "elapsed_time": "0:07:08", "remaining_time": "0:06:17"}
194
+ {"current_steps": 194, "total_steps": 363, "loss": 0.0795, "lr": 1.0674063615277681e-05, "epoch": 0.5351724137931034, "percentage": 53.44, "elapsed_time": "0:07:10", "remaining_time": "0:06:14"}
195
+ {"current_steps": 195, "total_steps": 363, "loss": 0.0722, "lr": 1.0577885110158959e-05, "epoch": 0.5379310344827586, "percentage": 53.72, "elapsed_time": "0:07:12", "remaining_time": "0:06:12"}
196
+ {"current_steps": 196, "total_steps": 363, "loss": 0.1059, "lr": 1.0481652938612374e-05, "epoch": 0.5406896551724137, "percentage": 53.99, "elapsed_time": "0:07:14", "remaining_time": "0:06:10"}
197
+ {"current_steps": 197, "total_steps": 363, "loss": 0.1007, "lr": 1.0385376037426227e-05, "epoch": 0.543448275862069, "percentage": 54.27, "elapsed_time": "0:07:16", "remaining_time": "0:06:07"}
198
+ {"current_steps": 198, "total_steps": 363, "loss": 0.0997, "lr": 1.0289063347542727e-05, "epoch": 0.5462068965517242, "percentage": 54.55, "elapsed_time": "0:07:18", "remaining_time": "0:06:05"}
199
+ {"current_steps": 199, "total_steps": 363, "loss": 0.1803, "lr": 1.0192723813227672e-05, "epoch": 0.5489655172413793, "percentage": 54.82, "elapsed_time": "0:07:20", "remaining_time": "0:06:03"}
200
+ {"current_steps": 200, "total_steps": 363, "loss": 0.1275, "lr": 1.0096366381239808e-05, "epoch": 0.5517241379310345, "percentage": 55.1, "elapsed_time": "0:07:22", "remaining_time": "0:06:00"}
201
+ {"current_steps": 201, "total_steps": 363, "loss": 0.0784, "lr": 1e-05, "epoch": 0.5544827586206896, "percentage": 55.37, "elapsed_time": "0:07:50", "remaining_time": "0:06:18"}
202
+ {"current_steps": 202, "total_steps": 363, "loss": 0.0884, "lr": 9.903633618760195e-06, "epoch": 0.5572413793103448, "percentage": 55.65, "elapsed_time": "0:07:52", "remaining_time": "0:06:16"}
203
+ {"current_steps": 203, "total_steps": 363, "loss": 0.0852, "lr": 9.807276186772335e-06, "epoch": 0.56, "percentage": 55.92, "elapsed_time": "0:07:54", "remaining_time": "0:06:14"}
204
+ {"current_steps": 204, "total_steps": 363, "loss": 0.0528, "lr": 9.710936652457276e-06, "epoch": 0.5627586206896552, "percentage": 56.2, "elapsed_time": "0:07:56", "remaining_time": "0:06:11"}
205
+ {"current_steps": 205, "total_steps": 363, "loss": 0.1213, "lr": 9.614623962573776e-06, "epoch": 0.5655172413793104, "percentage": 56.47, "elapsed_time": "0:07:59", "remaining_time": "0:06:09"}
206
+ {"current_steps": 206, "total_steps": 363, "loss": 0.0813, "lr": 9.518347061387629e-06, "epoch": 0.5682758620689655, "percentage": 56.75, "elapsed_time": "0:08:00", "remaining_time": "0:06:06"}
207
+ {"current_steps": 207, "total_steps": 363, "loss": 0.1114, "lr": 9.422114889841045e-06, "epoch": 0.5710344827586207, "percentage": 57.02, "elapsed_time": "0:08:02", "remaining_time": "0:06:03"}
208
+ {"current_steps": 208, "total_steps": 363, "loss": 0.1072, "lr": 9.325936384722322e-06, "epoch": 0.5737931034482758, "percentage": 57.3, "elapsed_time": "0:08:05", "remaining_time": "0:06:01"}
209
+ {"current_steps": 209, "total_steps": 363, "loss": 0.0629, "lr": 9.229820477835926e-06, "epoch": 0.576551724137931, "percentage": 57.58, "elapsed_time": "0:08:07", "remaining_time": "0:05:59"}
210
+ {"current_steps": 210, "total_steps": 363, "loss": 0.0798, "lr": 9.133776095173015e-06, "epoch": 0.5793103448275863, "percentage": 57.85, "elapsed_time": "0:08:09", "remaining_time": "0:05:56"}
211
+ {"current_steps": 211, "total_steps": 363, "loss": 0.0832, "lr": 9.037812156082503e-06, "epoch": 0.5820689655172414, "percentage": 58.13, "elapsed_time": "0:08:11", "remaining_time": "0:05:54"}
212
+ {"current_steps": 212, "total_steps": 363, "loss": 0.0912, "lr": 8.941937572442773e-06, "epoch": 0.5848275862068966, "percentage": 58.4, "elapsed_time": "0:08:14", "remaining_time": "0:05:51"}
213
+ {"current_steps": 213, "total_steps": 363, "loss": 0.0757, "lr": 8.846161247834024e-06, "epoch": 0.5875862068965517, "percentage": 58.68, "elapsed_time": "0:08:16", "remaining_time": "0:05:49"}
214
+ {"current_steps": 214, "total_steps": 363, "loss": 0.0607, "lr": 8.750492076711439e-06, "epoch": 0.5903448275862069, "percentage": 58.95, "elapsed_time": "0:08:18", "remaining_time": "0:05:47"}
215
+ {"current_steps": 215, "total_steps": 363, "loss": 0.1315, "lr": 8.654938943579194e-06, "epoch": 0.593103448275862, "percentage": 59.23, "elapsed_time": "0:08:20", "remaining_time": "0:05:44"}
216
+ {"current_steps": 216, "total_steps": 363, "loss": 0.1015, "lr": 8.55951072216536e-06, "epoch": 0.5958620689655172, "percentage": 59.5, "elapsed_time": "0:08:22", "remaining_time": "0:05:42"}
217
+ {"current_steps": 217, "total_steps": 363, "loss": 0.083, "lr": 8.464216274597839e-06, "epoch": 0.5986206896551725, "percentage": 59.78, "elapsed_time": "0:08:24", "remaining_time": "0:05:39"}
218
+ {"current_steps": 218, "total_steps": 363, "loss": 0.144, "lr": 8.369064450581374e-06, "epoch": 0.6013793103448276, "percentage": 60.06, "elapsed_time": "0:08:26", "remaining_time": "0:05:36"}
219
+ {"current_steps": 219, "total_steps": 363, "loss": 0.1187, "lr": 8.274064086575682e-06, "epoch": 0.6041379310344828, "percentage": 60.33, "elapsed_time": "0:08:27", "remaining_time": "0:05:33"}
220
+ {"current_steps": 220, "total_steps": 363, "loss": 0.101, "lr": 8.179224004974857e-06, "epoch": 0.6068965517241379, "percentage": 60.61, "elapsed_time": "0:08:29", "remaining_time": "0:05:31"}
221
+ {"current_steps": 221, "total_steps": 363, "loss": 0.0562, "lr": 8.084553013288048e-06, "epoch": 0.6096551724137931, "percentage": 60.88, "elapsed_time": "0:08:31", "remaining_time": "0:05:28"}
222
+ {"current_steps": 222, "total_steps": 363, "loss": 0.1144, "lr": 7.990059903321554e-06, "epoch": 0.6124137931034482, "percentage": 61.16, "elapsed_time": "0:08:33", "remaining_time": "0:05:26"}
223
+ {"current_steps": 223, "total_steps": 363, "loss": 0.0431, "lr": 7.89575345036232e-06, "epoch": 0.6151724137931035, "percentage": 61.43, "elapsed_time": "0:08:35", "remaining_time": "0:05:23"}
224
+ {"current_steps": 224, "total_steps": 363, "loss": 0.1239, "lr": 7.801642412363042e-06, "epoch": 0.6179310344827587, "percentage": 61.71, "elapsed_time": "0:08:37", "remaining_time": "0:05:21"}
225
+ {"current_steps": 225, "total_steps": 363, "loss": 0.0861, "lr": 7.707735529128819e-06, "epoch": 0.6206896551724138, "percentage": 61.98, "elapsed_time": "0:08:39", "remaining_time": "0:05:18"}
226
+ {"current_steps": 226, "total_steps": 363, "loss": 0.0939, "lr": 7.614041521505517e-06, "epoch": 0.623448275862069, "percentage": 62.26, "elapsed_time": "0:08:41", "remaining_time": "0:05:16"}
227
+ {"current_steps": 227, "total_steps": 363, "loss": 0.0961, "lr": 7.520569090569894e-06, "epoch": 0.6262068965517241, "percentage": 62.53, "elapsed_time": "0:08:43", "remaining_time": "0:05:13"}
228
+ {"current_steps": 228, "total_steps": 363, "loss": 0.1141, "lr": 7.427326916821557e-06, "epoch": 0.6289655172413793, "percentage": 62.81, "elapsed_time": "0:08:45", "remaining_time": "0:05:11"}
229
+ {"current_steps": 229, "total_steps": 363, "loss": 0.0631, "lr": 7.3343236593768295e-06, "epoch": 0.6317241379310344, "percentage": 63.09, "elapsed_time": "0:08:47", "remaining_time": "0:05:08"}
230
+ {"current_steps": 230, "total_steps": 363, "loss": 0.0607, "lr": 7.24156795516461e-06, "epoch": 0.6344827586206897, "percentage": 63.36, "elapsed_time": "0:08:49", "remaining_time": "0:05:05"}
231
+ {"current_steps": 231, "total_steps": 363, "loss": 0.1243, "lr": 7.149068418124281e-06, "epoch": 0.6372413793103449, "percentage": 63.64, "elapsed_time": "0:08:51", "remaining_time": "0:05:03"}
232
+ {"current_steps": 232, "total_steps": 363, "loss": 0.1154, "lr": 7.056833638405762e-06, "epoch": 0.64, "percentage": 63.91, "elapsed_time": "0:08:53", "remaining_time": "0:05:01"}
233
+ {"current_steps": 233, "total_steps": 363, "loss": 0.0782, "lr": 6.964872181571765e-06, "epoch": 0.6427586206896552, "percentage": 64.19, "elapsed_time": "0:08:55", "remaining_time": "0:04:58"}
234
+ {"current_steps": 234, "total_steps": 363, "loss": 0.1088, "lr": 6.87319258780234e-06, "epoch": 0.6455172413793103, "percentage": 64.46, "elapsed_time": "0:08:56", "remaining_time": "0:04:55"}
235
+ {"current_steps": 235, "total_steps": 363, "loss": 0.0635, "lr": 6.781803371101774e-06, "epoch": 0.6482758620689655, "percentage": 64.74, "elapsed_time": "0:08:58", "remaining_time": "0:04:53"}
236
+ {"current_steps": 236, "total_steps": 363, "loss": 0.065, "lr": 6.690713018507917e-06, "epoch": 0.6510344827586206, "percentage": 65.01, "elapsed_time": "0:09:00", "remaining_time": "0:04:50"}
237
+ {"current_steps": 237, "total_steps": 363, "loss": 0.0941, "lr": 6.599929989304034e-06, "epoch": 0.6537931034482759, "percentage": 65.29, "elapsed_time": "0:09:02", "remaining_time": "0:04:48"}
238
+ {"current_steps": 238, "total_steps": 363, "loss": 0.1049, "lr": 6.509462714233194e-06, "epoch": 0.6565517241379311, "percentage": 65.56, "elapsed_time": "0:09:04", "remaining_time": "0:04:45"}
239
+ {"current_steps": 239, "total_steps": 363, "loss": 0.0795, "lr": 6.419319594715338e-06, "epoch": 0.6593103448275862, "percentage": 65.84, "elapsed_time": "0:09:06", "remaining_time": "0:04:43"}
240
+ {"current_steps": 240, "total_steps": 363, "loss": 0.1389, "lr": 6.32950900206708e-06, "epoch": 0.6620689655172414, "percentage": 66.12, "elapsed_time": "0:09:08", "remaining_time": "0:04:40"}
241
+ {"current_steps": 241, "total_steps": 363, "loss": 0.0904, "lr": 6.240039276724273e-06, "epoch": 0.6648275862068965, "percentage": 66.39, "elapsed_time": "0:09:10", "remaining_time": "0:04:38"}
242
+ {"current_steps": 242, "total_steps": 363, "loss": 0.0988, "lr": 6.150918727467455e-06, "epoch": 0.6675862068965517, "percentage": 66.67, "elapsed_time": "0:09:12", "remaining_time": "0:04:36"}
243
+ {"current_steps": 243, "total_steps": 363, "loss": 0.0887, "lr": 6.062155630650265e-06, "epoch": 0.670344827586207, "percentage": 66.94, "elapsed_time": "0:09:13", "remaining_time": "0:04:33"}
244
+ {"current_steps": 244, "total_steps": 363, "loss": 0.0406, "lr": 5.973758229430806e-06, "epoch": 0.6731034482758621, "percentage": 67.22, "elapsed_time": "0:09:16", "remaining_time": "0:04:31"}
245
+ {"current_steps": 245, "total_steps": 363, "loss": 0.0613, "lr": 5.8857347330061545e-06, "epoch": 0.6758620689655173, "percentage": 67.49, "elapsed_time": "0:09:18", "remaining_time": "0:04:28"}
246
+ {"current_steps": 246, "total_steps": 363, "loss": 0.0621, "lr": 5.798093315849984e-06, "epoch": 0.6786206896551724, "percentage": 67.77, "elapsed_time": "0:09:19", "remaining_time": "0:04:26"}
247
+ {"current_steps": 247, "total_steps": 363, "loss": 0.135, "lr": 5.7108421169534376e-06, "epoch": 0.6813793103448276, "percentage": 68.04, "elapsed_time": "0:09:21", "remaining_time": "0:04:23"}
248
+ {"current_steps": 248, "total_steps": 363, "loss": 0.0912, "lr": 5.623989239069275e-06, "epoch": 0.6841379310344827, "percentage": 68.32, "elapsed_time": "0:09:23", "remaining_time": "0:04:21"}
249
+ {"current_steps": 249, "total_steps": 363, "loss": 0.0481, "lr": 5.5375427479593945e-06, "epoch": 0.6868965517241379, "percentage": 68.6, "elapsed_time": "0:09:25", "remaining_time": "0:04:18"}
250
+ {"current_steps": 250, "total_steps": 363, "loss": 0.0915, "lr": 5.451510671645806e-06, "epoch": 0.6896551724137931, "percentage": 68.87, "elapsed_time": "0:09:27", "remaining_time": "0:04:16"}
251
+ {"current_steps": 251, "total_steps": 363, "loss": 0.0932, "lr": 5.3659009996650704e-06, "epoch": 0.6924137931034483, "percentage": 69.15, "elapsed_time": "0:09:29", "remaining_time": "0:04:14"}
252
+ {"current_steps": 252, "total_steps": 363, "loss": 0.1258, "lr": 5.280721682326349e-06, "epoch": 0.6951724137931035, "percentage": 69.42, "elapsed_time": "0:09:31", "remaining_time": "0:04:11"}
253
+ {"current_steps": 253, "total_steps": 363, "loss": 0.136, "lr": 5.195980629973077e-06, "epoch": 0.6979310344827586, "percentage": 69.7, "elapsed_time": "0:09:33", "remaining_time": "0:04:09"}
254
+ {"current_steps": 254, "total_steps": 363, "loss": 0.0744, "lr": 5.111685712248364e-06, "epoch": 0.7006896551724138, "percentage": 69.97, "elapsed_time": "0:09:35", "remaining_time": "0:04:06"}
255
+ {"current_steps": 255, "total_steps": 363, "loss": 0.1436, "lr": 5.02784475736415e-06, "epoch": 0.7034482758620689, "percentage": 70.25, "elapsed_time": "0:09:37", "remaining_time": "0:04:04"}
256
+ {"current_steps": 256, "total_steps": 363, "loss": 0.0864, "lr": 4.944465551374238e-06, "epoch": 0.7062068965517241, "percentage": 70.52, "elapsed_time": "0:09:39", "remaining_time": "0:04:02"}
257
+ {"current_steps": 257, "total_steps": 363, "loss": 0.0931, "lr": 4.861555837451213e-06, "epoch": 0.7089655172413794, "percentage": 70.8, "elapsed_time": "0:09:41", "remaining_time": "0:03:59"}
258
+ {"current_steps": 258, "total_steps": 363, "loss": 0.1589, "lr": 4.779123315167362e-06, "epoch": 0.7117241379310345, "percentage": 71.07, "elapsed_time": "0:09:42", "remaining_time": "0:03:57"}
259
+ {"current_steps": 259, "total_steps": 363, "loss": 0.075, "lr": 4.6971756397796506e-06, "epoch": 0.7144827586206897, "percentage": 71.35, "elapsed_time": "0:09:44", "remaining_time": "0:03:54"}
260
+ {"current_steps": 260, "total_steps": 363, "loss": 0.0423, "lr": 4.61572042151878e-06, "epoch": 0.7172413793103448, "percentage": 71.63, "elapsed_time": "0:09:46", "remaining_time": "0:03:52"}
261
+ {"current_steps": 261, "total_steps": 363, "loss": 0.0538, "lr": 4.534765224882463e-06, "epoch": 0.72, "percentage": 71.9, "elapsed_time": "0:09:48", "remaining_time": "0:03:49"}
262
+ {"current_steps": 262, "total_steps": 363, "loss": 0.0591, "lr": 4.4543175679329345e-06, "epoch": 0.7227586206896551, "percentage": 72.18, "elapsed_time": "0:09:50", "remaining_time": "0:03:47"}
263
+ {"current_steps": 263, "total_steps": 363, "loss": 0.0965, "lr": 4.37438492159876e-06, "epoch": 0.7255172413793104, "percentage": 72.45, "elapsed_time": "0:09:52", "remaining_time": "0:03:45"}
264
+ {"current_steps": 264, "total_steps": 363, "loss": 0.0383, "lr": 4.294974708981041e-06, "epoch": 0.7282758620689656, "percentage": 72.73, "elapsed_time": "0:09:54", "remaining_time": "0:03:42"}
265
+ {"current_steps": 265, "total_steps": 363, "loss": 0.0952, "lr": 4.216094304664056e-06, "epoch": 0.7310344827586207, "percentage": 73.0, "elapsed_time": "0:09:56", "remaining_time": "0:03:40"}
266
+ {"current_steps": 266, "total_steps": 363, "loss": 0.0687, "lr": 4.1377510340304e-06, "epoch": 0.7337931034482759, "percentage": 73.28, "elapsed_time": "0:09:58", "remaining_time": "0:03:38"}
267
+ {"current_steps": 267, "total_steps": 363, "loss": 0.1397, "lr": 4.059952172580694e-06, "epoch": 0.736551724137931, "percentage": 73.55, "elapsed_time": "0:09:59", "remaining_time": "0:03:35"}
268
+ {"current_steps": 268, "total_steps": 363, "loss": 0.1271, "lr": 3.982704945257957e-06, "epoch": 0.7393103448275862, "percentage": 73.83, "elapsed_time": "0:10:01", "remaining_time": "0:03:33"}
269
+ {"current_steps": 269, "total_steps": 363, "loss": 0.0736, "lr": 3.9060165257766116e-06, "epoch": 0.7420689655172413, "percentage": 74.1, "elapsed_time": "0:10:03", "remaining_time": "0:03:30"}
270
+ {"current_steps": 270, "total_steps": 363, "loss": 0.1243, "lr": 3.829894035956306e-06, "epoch": 0.7448275862068966, "percentage": 74.38, "elapsed_time": "0:10:05", "remaining_time": "0:03:28"}
271
+ {"current_steps": 271, "total_steps": 363, "loss": 0.0971, "lr": 3.754344545060529e-06, "epoch": 0.7475862068965518, "percentage": 74.66, "elapsed_time": "0:10:06", "remaining_time": "0:03:26"}
272
+ {"current_steps": 272, "total_steps": 363, "loss": 0.1226, "lr": 3.6793750691400996e-06, "epoch": 0.7503448275862069, "percentage": 74.93, "elapsed_time": "0:10:08", "remaining_time": "0:03:23"}
273
+ {"current_steps": 273, "total_steps": 363, "loss": 0.0573, "lr": 3.604992570381621e-06, "epoch": 0.7531034482758621, "percentage": 75.21, "elapsed_time": "0:10:10", "remaining_time": "0:03:21"}
274
+ {"current_steps": 274, "total_steps": 363, "loss": 0.0357, "lr": 3.5312039564609203e-06, "epoch": 0.7558620689655172, "percentage": 75.48, "elapsed_time": "0:10:12", "remaining_time": "0:03:19"}
275
+ {"current_steps": 275, "total_steps": 363, "loss": 0.0841, "lr": 3.458016079901544e-06, "epoch": 0.7586206896551724, "percentage": 75.76, "elapsed_time": "0:10:14", "remaining_time": "0:03:16"}
276
+ {"current_steps": 276, "total_steps": 363, "loss": 0.0749, "lr": 3.3854357374383905e-06, "epoch": 0.7613793103448275, "percentage": 76.03, "elapsed_time": "0:10:16", "remaining_time": "0:03:14"}
277
+ {"current_steps": 277, "total_steps": 363, "loss": 0.1234, "lr": 3.313469669386532e-06, "epoch": 0.7641379310344828, "percentage": 76.31, "elapsed_time": "0:10:18", "remaining_time": "0:03:12"}
278
+ {"current_steps": 278, "total_steps": 363, "loss": 0.0752, "lr": 3.242124559015234e-06, "epoch": 0.766896551724138, "percentage": 76.58, "elapsed_time": "0:10:20", "remaining_time": "0:03:09"}
279
+ {"current_steps": 279, "total_steps": 363, "loss": 0.0991, "lr": 3.171407031927325e-06, "epoch": 0.7696551724137931, "percentage": 76.86, "elapsed_time": "0:10:22", "remaining_time": "0:03:07"}
280
+ {"current_steps": 280, "total_steps": 363, "loss": 0.109, "lr": 3.101323655443882e-06, "epoch": 0.7724137931034483, "percentage": 77.13, "elapsed_time": "0:10:24", "remaining_time": "0:03:05"}
281
+ {"current_steps": 281, "total_steps": 363, "loss": 0.0599, "lr": 3.0318809379943594e-06, "epoch": 0.7751724137931034, "percentage": 77.41, "elapsed_time": "0:10:26", "remaining_time": "0:03:02"}
282
+ {"current_steps": 282, "total_steps": 363, "loss": 0.0641, "lr": 2.9630853285121506e-06, "epoch": 0.7779310344827586, "percentage": 77.69, "elapsed_time": "0:10:28", "remaining_time": "0:03:00"}
283
+ {"current_steps": 283, "total_steps": 363, "loss": 0.0909, "lr": 2.8949432158357083e-06, "epoch": 0.7806896551724138, "percentage": 77.96, "elapsed_time": "0:10:30", "remaining_time": "0:02:58"}
284
+ {"current_steps": 284, "total_steps": 363, "loss": 0.1223, "lr": 2.8274609281152322e-06, "epoch": 0.783448275862069, "percentage": 78.24, "elapsed_time": "0:10:32", "remaining_time": "0:02:55"}
285
+ {"current_steps": 285, "total_steps": 363, "loss": 0.087, "lr": 2.7606447322249876e-06, "epoch": 0.7862068965517242, "percentage": 78.51, "elapsed_time": "0:10:33", "remaining_time": "0:02:53"}
286
+ {"current_steps": 286, "total_steps": 363, "loss": 0.1002, "lr": 2.694500833181323e-06, "epoch": 0.7889655172413793, "percentage": 78.79, "elapsed_time": "0:10:35", "remaining_time": "0:02:51"}
287
+ {"current_steps": 287, "total_steps": 363, "loss": 0.0915, "lr": 2.629035373566433e-06, "epoch": 0.7917241379310345, "percentage": 79.06, "elapsed_time": "0:10:37", "remaining_time": "0:02:48"}
288
+ {"current_steps": 288, "total_steps": 363, "loss": 0.0555, "lr": 2.5642544329579088e-06, "epoch": 0.7944827586206896, "percentage": 79.34, "elapsed_time": "0:10:39", "remaining_time": "0:02:46"}
289
+ {"current_steps": 289, "total_steps": 363, "loss": 0.0555, "lr": 2.500164027364147e-06, "epoch": 0.7972413793103448, "percentage": 79.61, "elapsed_time": "0:10:41", "remaining_time": "0:02:44"}
290
+ {"current_steps": 290, "total_steps": 363, "loss": 0.104, "lr": 2.4367701086656625e-06, "epoch": 0.8, "percentage": 79.89, "elapsed_time": "0:10:43", "remaining_time": "0:02:41"}
291
+ {"current_steps": 291, "total_steps": 363, "loss": 0.0936, "lr": 2.374078564062364e-06, "epoch": 0.8027586206896552, "percentage": 80.17, "elapsed_time": "0:10:45", "remaining_time": "0:02:39"}
292
+ {"current_steps": 292, "total_steps": 363, "loss": 0.0898, "lr": 2.312095215526814e-06, "epoch": 0.8055172413793104, "percentage": 80.44, "elapsed_time": "0:10:46", "remaining_time": "0:02:37"}
293
+ {"current_steps": 293, "total_steps": 363, "loss": 0.073, "lr": 2.2508258192635614e-06, "epoch": 0.8082758620689655, "percentage": 80.72, "elapsed_time": "0:10:48", "remaining_time": "0:02:34"}
294
+ {"current_steps": 294, "total_steps": 363, "loss": 0.0675, "lr": 2.190276065174596e-06, "epoch": 0.8110344827586207, "percentage": 80.99, "elapsed_time": "0:10:50", "remaining_time": "0:02:32"}
295
+ {"current_steps": 295, "total_steps": 363, "loss": 0.0871, "lr": 2.130451576330925e-06, "epoch": 0.8137931034482758, "percentage": 81.27, "elapsed_time": "0:10:52", "remaining_time": "0:02:30"}
296
+ {"current_steps": 296, "total_steps": 363, "loss": 0.075, "lr": 2.0713579084503877e-06, "epoch": 0.8165517241379311, "percentage": 81.54, "elapsed_time": "0:10:54", "remaining_time": "0:02:28"}
297
+ {"current_steps": 297, "total_steps": 363, "loss": 0.0726, "lr": 2.0130005493817063e-06, "epoch": 0.8193103448275862, "percentage": 81.82, "elapsed_time": "0:10:56", "remaining_time": "0:02:25"}
298
+ {"current_steps": 298, "total_steps": 363, "loss": 0.0585, "lr": 1.9553849185948514e-06, "epoch": 0.8220689655172414, "percentage": 82.09, "elapsed_time": "0:10:58", "remaining_time": "0:02:23"}
299
+ {"current_steps": 299, "total_steps": 363, "loss": 0.1192, "lr": 1.8985163666777473e-06, "epoch": 0.8248275862068966, "percentage": 82.37, "elapsed_time": "0:10:59", "remaining_time": "0:02:21"}
300
+ {"current_steps": 300, "total_steps": 363, "loss": 0.0639, "lr": 1.8424001748393905e-06, "epoch": 0.8275862068965517, "percentage": 82.64, "elapsed_time": "0:11:01", "remaining_time": "0:02:18"}
301
+ {"current_steps": 301, "total_steps": 363, "loss": 0.0644, "lr": 1.7870415544193808e-06, "epoch": 0.8303448275862069, "percentage": 82.92, "elapsed_time": "0:11:29", "remaining_time": "0:02:22"}
302
+ {"current_steps": 302, "total_steps": 363, "loss": 0.0806, "lr": 1.7324456464039751e-06, "epoch": 0.833103448275862, "percentage": 83.2, "elapsed_time": "0:11:31", "remaining_time": "0:02:19"}
303
+ {"current_steps": 303, "total_steps": 363, "loss": 0.1166, "lr": 1.6786175209486565e-06, "epoch": 0.8358620689655173, "percentage": 83.47, "elapsed_time": "0:11:33", "remaining_time": "0:02:17"}
304
+ {"current_steps": 304, "total_steps": 363, "loss": 0.0883, "lr": 1.6255621769072805e-06, "epoch": 0.8386206896551724, "percentage": 83.75, "elapsed_time": "0:11:35", "remaining_time": "0:02:15"}
305
+ {"current_steps": 305, "total_steps": 363, "loss": 0.105, "lr": 1.5732845413678477e-06, "epoch": 0.8413793103448276, "percentage": 84.02, "elapsed_time": "0:11:37", "remaining_time": "0:02:12"}
306
+ {"current_steps": 306, "total_steps": 363, "loss": 0.0618, "lr": 1.521789469194952e-06, "epoch": 0.8441379310344828, "percentage": 84.3, "elapsed_time": "0:11:39", "remaining_time": "0:02:10"}
307
+ {"current_steps": 307, "total_steps": 363, "loss": 0.0992, "lr": 1.4710817425789015e-06, "epoch": 0.8468965517241379, "percentage": 84.57, "elapsed_time": "0:11:41", "remaining_time": "0:02:07"}
308
+ {"current_steps": 308, "total_steps": 363, "loss": 0.0458, "lr": 1.4211660705916286e-06, "epoch": 0.8496551724137931, "percentage": 84.85, "elapsed_time": "0:11:43", "remaining_time": "0:02:05"}
309
+ {"current_steps": 309, "total_steps": 363, "loss": 0.0516, "lr": 1.372047088749372e-06, "epoch": 0.8524137931034482, "percentage": 85.12, "elapsed_time": "0:11:45", "remaining_time": "0:02:03"}
310
+ {"current_steps": 310, "total_steps": 363, "loss": 0.1156, "lr": 1.3237293585821786e-06, "epoch": 0.8551724137931035, "percentage": 85.4, "elapsed_time": "0:11:46", "remaining_time": "0:02:00"}
311
+ {"current_steps": 311, "total_steps": 363, "loss": 0.1332, "lr": 1.2762173672102996e-06, "epoch": 0.8579310344827586, "percentage": 85.67, "elapsed_time": "0:11:48", "remaining_time": "0:01:58"}
312
+ {"current_steps": 312, "total_steps": 363, "loss": 0.0735, "lr": 1.2295155269274827e-06, "epoch": 0.8606896551724138, "percentage": 85.95, "elapsed_time": "0:11:50", "remaining_time": "0:01:56"}
313
+ {"current_steps": 313, "total_steps": 363, "loss": 0.0825, "lr": 1.1836281747912125e-06, "epoch": 0.863448275862069, "percentage": 86.23, "elapsed_time": "0:11:52", "remaining_time": "0:01:53"}
314
+ {"current_steps": 314, "total_steps": 363, "loss": 0.0945, "lr": 1.1385595722199438e-06, "epoch": 0.8662068965517241, "percentage": 86.5, "elapsed_time": "0:11:54", "remaining_time": "0:01:51"}
315
+ {"current_steps": 315, "total_steps": 363, "loss": 0.0761, "lr": 1.094313904597355e-06, "epoch": 0.8689655172413793, "percentage": 86.78, "elapsed_time": "0:11:56", "remaining_time": "0:01:49"}
316
+ {"current_steps": 316, "total_steps": 363, "loss": 0.1104, "lr": 1.0508952808836682e-06, "epoch": 0.8717241379310345, "percentage": 87.05, "elapsed_time": "0:11:58", "remaining_time": "0:01:46"}
317
+ {"current_steps": 317, "total_steps": 363, "loss": 0.137, "lr": 1.0083077332340563e-06, "epoch": 0.8744827586206897, "percentage": 87.33, "elapsed_time": "0:12:00", "remaining_time": "0:01:44"}
318
+ {"current_steps": 318, "total_steps": 363, "loss": 0.1395, "lr": 9.665552166241965e-07, "epoch": 0.8772413793103448, "percentage": 87.6, "elapsed_time": "0:12:01", "remaining_time": "0:01:42"}
319
+ {"current_steps": 319, "total_steps": 363, "loss": 0.1331, "lr": 9.256416084829778e-07, "epoch": 0.88, "percentage": 87.88, "elapsed_time": "0:12:03", "remaining_time": "0:01:39"}
320
+ {"current_steps": 320, "total_steps": 363, "loss": 0.1077, "lr": 8.855707083324183e-07, "epoch": 0.8827586206896552, "percentage": 88.15, "elapsed_time": "0:12:05", "remaining_time": "0:01:37"}
321
+ {"current_steps": 321, "total_steps": 363, "loss": 0.0638, "lr": 8.46346237434813e-07, "epoch": 0.8855172413793103, "percentage": 88.43, "elapsed_time": "0:12:07", "remaining_time": "0:01:35"}
322
+ {"current_steps": 322, "total_steps": 363, "loss": 0.0515, "lr": 8.079718384471557e-07, "epoch": 0.8882758620689655, "percentage": 88.71, "elapsed_time": "0:12:09", "remaining_time": "0:01:32"}
323
+ {"current_steps": 323, "total_steps": 363, "loss": 0.0623, "lr": 7.704510750828542e-07, "epoch": 0.8910344827586207, "percentage": 88.98, "elapsed_time": "0:12:11", "remaining_time": "0:01:30"}
324
+ {"current_steps": 324, "total_steps": 363, "loss": 0.0516, "lr": 7.337874317807803e-07, "epoch": 0.8937931034482759, "percentage": 89.26, "elapsed_time": "0:12:13", "remaining_time": "0:01:28"}
325
+ {"current_steps": 325, "total_steps": 363, "loss": 0.0612, "lr": 6.979843133816744e-07, "epoch": 0.896551724137931, "percentage": 89.53, "elapsed_time": "0:12:15", "remaining_time": "0:01:25"}
326
+ {"current_steps": 326, "total_steps": 363, "loss": 0.0333, "lr": 6.630450448119618e-07, "epoch": 0.8993103448275862, "percentage": 89.81, "elapsed_time": "0:12:17", "remaining_time": "0:01:23"}
327
+ {"current_steps": 327, "total_steps": 363, "loss": 0.0953, "lr": 6.289728707749609e-07, "epoch": 0.9020689655172414, "percentage": 90.08, "elapsed_time": "0:12:19", "remaining_time": "0:01:21"}
328
+ {"current_steps": 328, "total_steps": 363, "loss": 0.0893, "lr": 5.957709554495683e-07, "epoch": 0.9048275862068965, "percentage": 90.36, "elapsed_time": "0:12:21", "remaining_time": "0:01:19"}
329
+ {"current_steps": 329, "total_steps": 363, "loss": 0.0423, "lr": 5.634423821964074e-07, "epoch": 0.9075862068965517, "percentage": 90.63, "elapsed_time": "0:12:24", "remaining_time": "0:01:16"}
330
+ {"current_steps": 330, "total_steps": 363, "loss": 0.1055, "lr": 5.319901532714877e-07, "epoch": 0.9103448275862069, "percentage": 90.91, "elapsed_time": "0:12:26", "remaining_time": "0:01:14"}
331
+ {"current_steps": 331, "total_steps": 363, "loss": 0.1232, "lr": 5.014171895473929e-07, "epoch": 0.9131034482758621, "percentage": 91.18, "elapsed_time": "0:12:29", "remaining_time": "0:01:12"}
332
+ {"current_steps": 332, "total_steps": 363, "loss": 0.076, "lr": 4.717263302420283e-07, "epoch": 0.9158620689655173, "percentage": 91.46, "elapsed_time": "0:12:32", "remaining_time": "0:01:10"}
333
+ {"current_steps": 333, "total_steps": 363, "loss": 0.0835, "lr": 4.429203326549525e-07, "epoch": 0.9186206896551724, "percentage": 91.74, "elapsed_time": "0:12:34", "remaining_time": "0:01:08"}
334
+ {"current_steps": 334, "total_steps": 363, "loss": 0.0734, "lr": 4.150018719113147e-07, "epoch": 0.9213793103448276, "percentage": 92.01, "elapsed_time": "0:12:37", "remaining_time": "0:01:05"}
335
+ {"current_steps": 335, "total_steps": 363, "loss": 0.0768, "lr": 3.8797354071342443e-07, "epoch": 0.9241379310344827, "percentage": 92.29, "elapsed_time": "0:12:38", "remaining_time": "0:01:03"}
336
+ {"current_steps": 336, "total_steps": 363, "loss": 0.1027, "lr": 3.618378490999719e-07, "epoch": 0.926896551724138, "percentage": 92.56, "elapsed_time": "0:12:40", "remaining_time": "0:01:01"}
337
+ {"current_steps": 337, "total_steps": 363, "loss": 0.1176, "lr": 3.365972242129378e-07, "epoch": 0.9296551724137931, "percentage": 92.84, "elapsed_time": "0:12:42", "remaining_time": "0:00:58"}
338
+ {"current_steps": 338, "total_steps": 363, "loss": 0.068, "lr": 3.122540100721794e-07, "epoch": 0.9324137931034483, "percentage": 93.11, "elapsed_time": "0:12:44", "remaining_time": "0:00:56"}
339
+ {"current_steps": 339, "total_steps": 363, "loss": 0.0826, "lr": 2.888104673577574e-07, "epoch": 0.9351724137931035, "percentage": 93.39, "elapsed_time": "0:12:46", "remaining_time": "0:00:54"}
340
+ {"current_steps": 340, "total_steps": 363, "loss": 0.1094, "lr": 2.66268773199988e-07, "epoch": 0.9379310344827586, "percentage": 93.66, "elapsed_time": "0:12:47", "remaining_time": "0:00:51"}
341
+ {"current_steps": 341, "total_steps": 363, "loss": 0.1397, "lr": 2.4463102097726843e-07, "epoch": 0.9406896551724138, "percentage": 93.94, "elapsed_time": "0:12:49", "remaining_time": "0:00:49"}
342
+ {"current_steps": 342, "total_steps": 363, "loss": 0.0883, "lr": 2.2389922012165944e-07, "epoch": 0.9434482758620689, "percentage": 94.21, "elapsed_time": "0:12:51", "remaining_time": "0:00:47"}
343
+ {"current_steps": 343, "total_steps": 363, "loss": 0.0537, "lr": 2.0407529593228114e-07, "epoch": 0.9462068965517242, "percentage": 94.49, "elapsed_time": "0:12:52", "remaining_time": "0:00:45"}
344
+ {"current_steps": 344, "total_steps": 363, "loss": 0.0841, "lr": 1.8516108939651945e-07, "epoch": 0.9489655172413793, "percentage": 94.77, "elapsed_time": "0:12:54", "remaining_time": "0:00:42"}
345
+ {"current_steps": 345, "total_steps": 363, "loss": 0.1278, "lr": 1.6715835701905604e-07, "epoch": 0.9517241379310345, "percentage": 95.04, "elapsed_time": "0:12:56", "remaining_time": "0:00:40"}
346
+ {"current_steps": 346, "total_steps": 363, "loss": 0.062, "lr": 1.5006877065874338e-07, "epoch": 0.9544827586206897, "percentage": 95.32, "elapsed_time": "0:12:58", "remaining_time": "0:00:38"}
347
+ {"current_steps": 347, "total_steps": 363, "loss": 0.1123, "lr": 1.3389391737335112e-07, "epoch": 0.9572413793103448, "percentage": 95.59, "elapsed_time": "0:13:00", "remaining_time": "0:00:35"}
348
+ {"current_steps": 348, "total_steps": 363, "loss": 0.0859, "lr": 1.1863529927217731e-07, "epoch": 0.96, "percentage": 95.87, "elapsed_time": "0:13:02", "remaining_time": "0:00:33"}
349
+ {"current_steps": 349, "total_steps": 363, "loss": 0.0664, "lr": 1.0429433337655115e-07, "epoch": 0.9627586206896551, "percentage": 96.14, "elapsed_time": "0:13:04", "remaining_time": "0:00:31"}
350
+ {"current_steps": 350, "total_steps": 363, "loss": 0.0978, "lr": 9.08723514882437e-08, "epoch": 0.9655172413793104, "percentage": 96.42, "elapsed_time": "0:13:06", "remaining_time": "0:00:29"}
351
+ {"current_steps": 351, "total_steps": 363, "loss": 0.082, "lr": 7.837060006577801e-08, "epoch": 0.9682758620689655, "percentage": 96.69, "elapsed_time": "0:13:09", "remaining_time": "0:00:26"}
352
+ {"current_steps": 352, "total_steps": 363, "loss": 0.0937, "lr": 6.679024010868617e-08, "epoch": 0.9710344827586207, "percentage": 96.97, "elapsed_time": "0:13:11", "remaining_time": "0:00:24"}
353
+ {"current_steps": 353, "total_steps": 363, "loss": 0.0944, "lr": 5.6132347049679955e-08, "epoch": 0.9737931034482759, "percentage": 97.25, "elapsed_time": "0:13:14", "remaining_time": "0:00:22"}
354
+ {"current_steps": 354, "total_steps": 363, "loss": 0.0373, "lr": 4.639791065478738e-08, "epoch": 0.976551724137931, "percentage": 97.52, "elapsed_time": "0:13:16", "remaining_time": "0:00:20"}
355
+ {"current_steps": 355, "total_steps": 363, "loss": 0.0938, "lr": 3.758783493142737e-08, "epoch": 0.9793103448275862, "percentage": 97.8, "elapsed_time": "0:13:18", "remaining_time": "0:00:18"}
356
+ {"current_steps": 356, "total_steps": 363, "loss": 0.1083, "lr": 2.9702938044468e-08, "epoch": 0.9820689655172414, "percentage": 98.07, "elapsed_time": "0:13:20", "remaining_time": "0:00:15"}
357
+ {"current_steps": 357, "total_steps": 363, "loss": 0.0667, "lr": 2.274395224023618e-08, "epoch": 0.9848275862068966, "percentage": 98.35, "elapsed_time": "0:13:22", "remaining_time": "0:00:13"}
358
+ {"current_steps": 358, "total_steps": 363, "loss": 0.0907, "lr": 1.671152377852092e-08, "epoch": 0.9875862068965517, "percentage": 98.62, "elapsed_time": "0:13:24", "remaining_time": "0:00:11"}
359
+ {"current_steps": 359, "total_steps": 363, "loss": 0.0937, "lr": 1.1606212872559142e-08, "epoch": 0.9903448275862069, "percentage": 98.9, "elapsed_time": "0:13:26", "remaining_time": "0:00:08"}
360
+ {"current_steps": 360, "total_steps": 363, "loss": 0.0863, "lr": 7.42849363700282e-09, "epoch": 0.993103448275862, "percentage": 99.17, "elapsed_time": "0:13:28", "remaining_time": "0:00:06"}
361
+ {"current_steps": 361, "total_steps": 363, "loss": 0.0593, "lr": 4.178754043898669e-09, "epoch": 0.9958620689655172, "percentage": 99.45, "elapsed_time": "0:13:30", "remaining_time": "0:00:04"}
362
+ {"current_steps": 362, "total_steps": 363, "loss": 0.0859, "lr": 1.8572958866514e-09, "epoch": 0.9986206896551724, "percentage": 99.72, "elapsed_time": "0:13:31", "remaining_time": "0:00:02"}
363
+ {"current_steps": 363, "total_steps": 363, "loss": 0.0658, "lr": 4.643347520005836e-10, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:13:32", "remaining_time": "0:00:00"}
364
+ {"current_steps": 363, "total_steps": 363, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:14:02", "remaining_time": "0:00:00"}
iter4_sft/trainer_state.json ADDED
@@ -0,0 +1,2584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 363,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002758620689655172,
14
+ "grad_norm": 2.2012167823201163,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.0852,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.005517241379310344,
21
+ "grad_norm": 2.684327612345962,
22
+ "learning_rate": 5.405405405405406e-07,
23
+ "loss": 0.1171,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.008275862068965517,
28
+ "grad_norm": 2.922848494791373,
29
+ "learning_rate": 1.0810810810810812e-06,
30
+ "loss": 0.1201,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.011034482758620689,
35
+ "grad_norm": 2.923985908786216,
36
+ "learning_rate": 1.6216216216216219e-06,
37
+ "loss": 0.0976,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.013793103448275862,
42
+ "grad_norm": 1.2724240051553533,
43
+ "learning_rate": 2.1621621621621623e-06,
44
+ "loss": 0.1046,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.016551724137931035,
49
+ "grad_norm": 1.673019205535178,
50
+ "learning_rate": 2.702702702702703e-06,
51
+ "loss": 0.0609,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.019310344827586208,
56
+ "grad_norm": 2.504855019369174,
57
+ "learning_rate": 3.2432432432432437e-06,
58
+ "loss": 0.081,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.022068965517241378,
63
+ "grad_norm": 1.878885411504625,
64
+ "learning_rate": 3.7837837837837844e-06,
65
+ "loss": 0.1121,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.02482758620689655,
70
+ "grad_norm": 2.653287813889321,
71
+ "learning_rate": 4.324324324324325e-06,
72
+ "loss": 0.1125,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.027586206896551724,
77
+ "grad_norm": 1.7453919996030804,
78
+ "learning_rate": 4.864864864864866e-06,
79
+ "loss": 0.0724,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.030344827586206897,
84
+ "grad_norm": 3.333638766021421,
85
+ "learning_rate": 5.405405405405406e-06,
86
+ "loss": 0.1475,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.03310344827586207,
91
+ "grad_norm": 2.292734722563975,
92
+ "learning_rate": 5.945945945945947e-06,
93
+ "loss": 0.0974,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.03586206896551724,
98
+ "grad_norm": 1.099049620799708,
99
+ "learning_rate": 6.486486486486487e-06,
100
+ "loss": 0.0597,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.038620689655172416,
105
+ "grad_norm": 1.727408246250002,
106
+ "learning_rate": 7.027027027027028e-06,
107
+ "loss": 0.0778,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.041379310344827586,
112
+ "grad_norm": 1.761342077131181,
113
+ "learning_rate": 7.567567567567569e-06,
114
+ "loss": 0.0955,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.044137931034482755,
119
+ "grad_norm": 1.9277700023635902,
120
+ "learning_rate": 8.108108108108109e-06,
121
+ "loss": 0.0869,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.04689655172413793,
126
+ "grad_norm": 1.568808525211501,
127
+ "learning_rate": 8.64864864864865e-06,
128
+ "loss": 0.0807,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0496551724137931,
133
+ "grad_norm": 1.3523306531543753,
134
+ "learning_rate": 9.189189189189191e-06,
135
+ "loss": 0.0665,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.05241379310344828,
140
+ "grad_norm": 1.7180837689557336,
141
+ "learning_rate": 9.729729729729732e-06,
142
+ "loss": 0.0868,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.05517241379310345,
147
+ "grad_norm": 1.5131863973051378,
148
+ "learning_rate": 1.027027027027027e-05,
149
+ "loss": 0.0736,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.057931034482758624,
154
+ "grad_norm": 1.6815268723910783,
155
+ "learning_rate": 1.0810810810810812e-05,
156
+ "loss": 0.079,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.060689655172413794,
161
+ "grad_norm": 1.4834028913829107,
162
+ "learning_rate": 1.1351351351351352e-05,
163
+ "loss": 0.0437,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.06344827586206897,
168
+ "grad_norm": 2.1417510445007792,
169
+ "learning_rate": 1.1891891891891894e-05,
170
+ "loss": 0.0905,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.06620689655172414,
175
+ "grad_norm": 1.7871991104284883,
176
+ "learning_rate": 1.2432432432432433e-05,
177
+ "loss": 0.1024,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.06896551724137931,
182
+ "grad_norm": 2.0156063129423485,
183
+ "learning_rate": 1.2972972972972975e-05,
184
+ "loss": 0.0701,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.07172413793103448,
189
+ "grad_norm": 1.9160557707810737,
190
+ "learning_rate": 1.3513513513513515e-05,
191
+ "loss": 0.0748,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.07448275862068965,
196
+ "grad_norm": 2.000911025201981,
197
+ "learning_rate": 1.4054054054054055e-05,
198
+ "loss": 0.101,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.07724137931034483,
203
+ "grad_norm": 2.115047269982351,
204
+ "learning_rate": 1.4594594594594596e-05,
205
+ "loss": 0.0918,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.08,
210
+ "grad_norm": 1.8098326272573262,
211
+ "learning_rate": 1.5135135135135138e-05,
212
+ "loss": 0.0915,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.08275862068965517,
217
+ "grad_norm": 2.1207994498886764,
218
+ "learning_rate": 1.5675675675675676e-05,
219
+ "loss": 0.1025,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.08551724137931034,
224
+ "grad_norm": 2.171868532095742,
225
+ "learning_rate": 1.6216216216216218e-05,
226
+ "loss": 0.1059,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.08827586206896551,
231
+ "grad_norm": 1.6943229112776936,
232
+ "learning_rate": 1.6756756756756757e-05,
233
+ "loss": 0.0677,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.0910344827586207,
238
+ "grad_norm": 1.994899794317826,
239
+ "learning_rate": 1.72972972972973e-05,
240
+ "loss": 0.0894,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.09379310344827586,
245
+ "grad_norm": 2.3711691862715907,
246
+ "learning_rate": 1.783783783783784e-05,
247
+ "loss": 0.1158,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.09655172413793103,
252
+ "grad_norm": 1.9877327316155244,
253
+ "learning_rate": 1.8378378378378383e-05,
254
+ "loss": 0.0924,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0993103448275862,
259
+ "grad_norm": 2.0641113315593898,
260
+ "learning_rate": 1.891891891891892e-05,
261
+ "loss": 0.0978,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.10206896551724139,
266
+ "grad_norm": 2.5636633454788593,
267
+ "learning_rate": 1.9459459459459463e-05,
268
+ "loss": 0.1327,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.10482758620689656,
273
+ "grad_norm": 2.3262721461116396,
274
+ "learning_rate": 2e-05,
275
+ "loss": 0.095,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.10758620689655173,
280
+ "grad_norm": 2.0685116596847832,
281
+ "learning_rate": 1.9999535665248e-05,
282
+ "loss": 0.0706,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.1103448275862069,
287
+ "grad_norm": 2.5954824427417007,
288
+ "learning_rate": 1.999814270411335e-05,
289
+ "loss": 0.1205,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.11310344827586206,
294
+ "grad_norm": 2.144122161715886,
295
+ "learning_rate": 1.99958212459561e-05,
296
+ "loss": 0.0896,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.11586206896551725,
301
+ "grad_norm": 1.9322201299634434,
302
+ "learning_rate": 1.9992571506362997e-05,
303
+ "loss": 0.1012,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.11862068965517242,
308
+ "grad_norm": 2.075048476162322,
309
+ "learning_rate": 1.9988393787127444e-05,
310
+ "loss": 0.1087,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.12137931034482759,
315
+ "grad_norm": 2.259726318820954,
316
+ "learning_rate": 1.9983288476221482e-05,
317
+ "loss": 0.1382,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.12413793103448276,
322
+ "grad_norm": 1.360664005910794,
323
+ "learning_rate": 1.9977256047759765e-05,
324
+ "loss": 0.0538,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.12689655172413794,
329
+ "grad_norm": 1.6435792074598727,
330
+ "learning_rate": 1.9970297061955533e-05,
331
+ "loss": 0.0855,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.1296551724137931,
336
+ "grad_norm": 2.3601345815092483,
337
+ "learning_rate": 1.9962412165068575e-05,
338
+ "loss": 0.1386,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.13241379310344828,
343
+ "grad_norm": 1.7105484837560168,
344
+ "learning_rate": 1.9953602089345215e-05,
345
+ "loss": 0.0961,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.13517241379310344,
350
+ "grad_norm": 1.6496292161975452,
351
+ "learning_rate": 1.9943867652950323e-05,
352
+ "loss": 0.0857,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.13793103448275862,
357
+ "grad_norm": 1.2468755808496865,
358
+ "learning_rate": 1.9933209759891318e-05,
359
+ "loss": 0.0563,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.1406896551724138,
364
+ "grad_norm": 2.0793413384987183,
365
+ "learning_rate": 1.9921629399934224e-05,
366
+ "loss": 0.108,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.14344827586206896,
371
+ "grad_norm": 2.0093677538398524,
372
+ "learning_rate": 1.9909127648511758e-05,
373
+ "loss": 0.1289,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.14620689655172414,
378
+ "grad_norm": 1.2736371995174656,
379
+ "learning_rate": 1.989570566662345e-05,
380
+ "loss": 0.0615,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.1489655172413793,
385
+ "grad_norm": 1.5368399292599437,
386
+ "learning_rate": 1.9881364700727827e-05,
387
+ "loss": 0.0559,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.15172413793103448,
392
+ "grad_norm": 1.6143124587473046,
393
+ "learning_rate": 1.986610608262665e-05,
394
+ "loss": 0.0512,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.15448275862068966,
399
+ "grad_norm": 2.0640396297545323,
400
+ "learning_rate": 1.9849931229341258e-05,
401
+ "loss": 0.1492,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.15724137931034482,
406
+ "grad_norm": 1.9321341515451917,
407
+ "learning_rate": 1.9832841642980948e-05,
408
+ "loss": 0.1277,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.16,
413
+ "grad_norm": 3.5565020190489753,
414
+ "learning_rate": 1.981483891060348e-05,
415
+ "loss": 0.1266,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.16275862068965516,
420
+ "grad_norm": 1.6731150384360727,
421
+ "learning_rate": 1.979592470406772e-05,
422
+ "loss": 0.095,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.16551724137931034,
427
+ "grad_norm": 1.3348447458614452,
428
+ "learning_rate": 1.9776100779878344e-05,
429
+ "loss": 0.0602,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.16827586206896553,
434
+ "grad_norm": 1.211440894700164,
435
+ "learning_rate": 1.9755368979022734e-05,
436
+ "loss": 0.0597,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.17103448275862068,
441
+ "grad_norm": 2.045395762464389,
442
+ "learning_rate": 1.9733731226800016e-05,
443
+ "loss": 0.0902,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.17379310344827587,
448
+ "grad_norm": 1.681889406229311,
449
+ "learning_rate": 1.9711189532642244e-05,
450
+ "loss": 0.0851,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.17655172413793102,
455
+ "grad_norm": 2.156485405646681,
456
+ "learning_rate": 1.9687745989927823e-05,
457
+ "loss": 0.1022,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.1793103448275862,
462
+ "grad_norm": 2.2694346385487765,
463
+ "learning_rate": 1.9663402775787066e-05,
464
+ "loss": 0.1402,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.1820689655172414,
469
+ "grad_norm": 2.2102729735649502,
470
+ "learning_rate": 1.9638162150900028e-05,
471
+ "loss": 0.0595,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.18482758620689654,
476
+ "grad_norm": 2.4808367225986023,
477
+ "learning_rate": 1.961202645928658e-05,
478
+ "loss": 0.1526,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.18758620689655173,
483
+ "grad_norm": 2.125991623159161,
484
+ "learning_rate": 1.9584998128088686e-05,
485
+ "loss": 0.1149,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.19034482758620688,
490
+ "grad_norm": 3.5959738930248553,
491
+ "learning_rate": 1.955707966734505e-05,
492
+ "loss": 0.1724,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.19310344827586207,
497
+ "grad_norm": 2.217349082976429,
498
+ "learning_rate": 1.9528273669757974e-05,
499
+ "loss": 0.1357,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.19586206896551725,
504
+ "grad_norm": 2.9019793725624288,
505
+ "learning_rate": 1.9498582810452607e-05,
506
+ "loss": 0.1289,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.1986206896551724,
511
+ "grad_norm": 2.677822777383495,
512
+ "learning_rate": 1.9468009846728515e-05,
513
+ "loss": 0.1201,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.2013793103448276,
518
+ "grad_norm": 2.1904068713477693,
519
+ "learning_rate": 1.9436557617803594e-05,
520
+ "loss": 0.1343,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.20413793103448277,
525
+ "grad_norm": 1.9333752870288448,
526
+ "learning_rate": 1.9404229044550432e-05,
527
+ "loss": 0.1014,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.20689655172413793,
532
+ "grad_norm": 1.2594973301567354,
533
+ "learning_rate": 1.9371027129225042e-05,
534
+ "loss": 0.08,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.2096551724137931,
539
+ "grad_norm": 1.1588871349219974,
540
+ "learning_rate": 1.9336954955188042e-05,
541
+ "loss": 0.0664,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.21241379310344827,
546
+ "grad_norm": 2.424390700582275,
547
+ "learning_rate": 1.9302015686618328e-05,
548
+ "loss": 0.1228,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.21517241379310345,
553
+ "grad_norm": 1.839851381331024,
554
+ "learning_rate": 1.9266212568219223e-05,
555
+ "loss": 0.1181,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.21793103448275863,
560
+ "grad_norm": 2.9112052255264627,
561
+ "learning_rate": 1.9229548924917146e-05,
562
+ "loss": 0.1593,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.2206896551724138,
567
+ "grad_norm": 2.6573066473445124,
568
+ "learning_rate": 1.9192028161552848e-05,
569
+ "loss": 0.1068,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.22344827586206897,
574
+ "grad_norm": 2.228711734634549,
575
+ "learning_rate": 1.915365376256519e-05,
576
+ "loss": 0.1395,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.22620689655172413,
581
+ "grad_norm": 2.1487793287842463,
582
+ "learning_rate": 1.9114429291667583e-05,
583
+ "loss": 0.1322,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.2289655172413793,
588
+ "grad_norm": 1.418589529134045,
589
+ "learning_rate": 1.9074358391517026e-05,
590
+ "loss": 0.1298,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.2317241379310345,
595
+ "grad_norm": 1.6184969490675134,
596
+ "learning_rate": 1.9033444783375806e-05,
597
+ "loss": 0.1375,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.23448275862068965,
602
+ "grad_norm": 2.636414425888468,
603
+ "learning_rate": 1.8991692266765947e-05,
604
+ "loss": 0.1454,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.23724137931034484,
609
+ "grad_norm": 1.5999297559125214,
610
+ "learning_rate": 1.8949104719116334e-05,
611
+ "loss": 0.1004,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.24,
616
+ "grad_norm": 1.7047937938863038,
617
+ "learning_rate": 1.8905686095402648e-05,
618
+ "loss": 0.0729,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.24275862068965517,
623
+ "grad_norm": 2.213860086801788,
624
+ "learning_rate": 1.886144042778006e-05,
625
+ "loss": 0.1219,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.24551724137931036,
630
+ "grad_norm": 1.9830213856101813,
631
+ "learning_rate": 1.881637182520879e-05,
632
+ "loss": 0.1277,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.2482758620689655,
637
+ "grad_norm": 2.1526995896994543,
638
+ "learning_rate": 1.8770484473072518e-05,
639
+ "loss": 0.133,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.25103448275862067,
644
+ "grad_norm": 5.615536299423343,
645
+ "learning_rate": 1.87237826327897e-05,
646
+ "loss": 0.1271,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.2537931034482759,
651
+ "grad_norm": 2.9892624763616213,
652
+ "learning_rate": 1.8676270641417824e-05,
653
+ "loss": 0.1337,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.25655172413793104,
658
+ "grad_norm": 1.7670570813048203,
659
+ "learning_rate": 1.8627952911250632e-05,
660
+ "loss": 0.1188,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.2593103448275862,
665
+ "grad_norm": 1.8832817735619782,
666
+ "learning_rate": 1.857883392940837e-05,
667
+ "loss": 0.09,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.2620689655172414,
672
+ "grad_norm": 2.2995757188920964,
673
+ "learning_rate": 1.85289182574211e-05,
674
+ "loss": 0.1084,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.26482758620689656,
679
+ "grad_norm": 2.268436925129853,
680
+ "learning_rate": 1.847821053080505e-05,
681
+ "loss": 0.1003,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.2675862068965517,
686
+ "grad_norm": 1.8417005302085403,
687
+ "learning_rate": 1.8426715458632154e-05,
688
+ "loss": 0.0747,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.27034482758620687,
693
+ "grad_norm": 2.497572736496612,
694
+ "learning_rate": 1.8374437823092726e-05,
695
+ "loss": 0.1513,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.2731034482758621,
700
+ "grad_norm": 2.0212629509138766,
701
+ "learning_rate": 1.832138247905135e-05,
702
+ "loss": 0.088,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.27586206896551724,
707
+ "grad_norm": 1.806243660764203,
708
+ "learning_rate": 1.8267554353596027e-05,
709
+ "loss": 0.0617,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2786206896551724,
714
+ "grad_norm": 1.43840041921586,
715
+ "learning_rate": 1.8212958445580623e-05,
716
+ "loss": 0.0809,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.2813793103448276,
721
+ "grad_norm": 1.5624416473825227,
722
+ "learning_rate": 1.815759982516061e-05,
723
+ "loss": 0.0987,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.28413793103448276,
728
+ "grad_norm": 1.3722413173440258,
729
+ "learning_rate": 1.8101483633322255e-05,
730
+ "loss": 0.1055,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.2868965517241379,
735
+ "grad_norm": 1.5055322976041905,
736
+ "learning_rate": 1.8044615081405153e-05,
737
+ "loss": 0.12,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.2896551724137931,
742
+ "grad_norm": 1.9238100509571232,
743
+ "learning_rate": 1.7986999450618295e-05,
744
+ "loss": 0.1293,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.2924137931034483,
749
+ "grad_norm": 1.4169309751550185,
750
+ "learning_rate": 1.7928642091549616e-05,
751
+ "loss": 0.0945,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.29517241379310344,
756
+ "grad_norm": 1.7127369268478376,
757
+ "learning_rate": 1.7869548423669075e-05,
758
+ "loss": 0.1124,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.2979310344827586,
763
+ "grad_norm": 1.859903898855105,
764
+ "learning_rate": 1.7809723934825405e-05,
765
+ "loss": 0.1182,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.3006896551724138,
770
+ "grad_norm": 1.4775939025780847,
771
+ "learning_rate": 1.7749174180736443e-05,
772
+ "loss": 0.0857,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.30344827586206896,
777
+ "grad_norm": 1.4354799536836982,
778
+ "learning_rate": 1.768790478447319e-05,
779
+ "loss": 0.0781,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.3062068965517241,
784
+ "grad_norm": 1.0273549786544405,
785
+ "learning_rate": 1.762592143593764e-05,
786
+ "loss": 0.0713,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.30896551724137933,
791
+ "grad_norm": 1.9640486386494376,
792
+ "learning_rate": 1.756322989133434e-05,
793
+ "loss": 0.1301,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.3117241379310345,
798
+ "grad_norm": 1.7089277562540073,
799
+ "learning_rate": 1.749983597263586e-05,
800
+ "loss": 0.0681,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.31448275862068964,
805
+ "grad_norm": 1.9429869321530793,
806
+ "learning_rate": 1.7435745567042096e-05,
807
+ "loss": 0.1331,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.31724137931034485,
812
+ "grad_norm": 1.26536650090277,
813
+ "learning_rate": 1.737096462643357e-05,
814
+ "loss": 0.0604,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.32,
819
+ "grad_norm": 2.087216494160791,
820
+ "learning_rate": 1.730549916681868e-05,
821
+ "loss": 0.1494,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.32275862068965516,
826
+ "grad_norm": 1.9975034441736954,
827
+ "learning_rate": 1.723935526777502e-05,
828
+ "loss": 0.1092,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.3255172413793103,
833
+ "grad_norm": 2.038235893575754,
834
+ "learning_rate": 1.717253907188477e-05,
835
+ "loss": 0.1082,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.32827586206896553,
840
+ "grad_norm": 3.3184113391653396,
841
+ "learning_rate": 1.7105056784164295e-05,
842
+ "loss": 0.1703,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.3310344827586207,
847
+ "grad_norm": 2.0270058507038966,
848
+ "learning_rate": 1.7036914671487854e-05,
849
+ "loss": 0.1303,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.33379310344827584,
854
+ "grad_norm": 1.8154593381383104,
855
+ "learning_rate": 1.6968119062005644e-05,
856
+ "loss": 0.1077,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.33655172413793105,
861
+ "grad_norm": 1.2350092975243878,
862
+ "learning_rate": 1.689867634455612e-05,
863
+ "loss": 0.0924,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.3393103448275862,
868
+ "grad_norm": 1.792900391384705,
869
+ "learning_rate": 1.682859296807268e-05,
870
+ "loss": 0.1221,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.34206896551724136,
875
+ "grad_norm": 1.9404357508554042,
876
+ "learning_rate": 1.675787544098477e-05,
877
+ "loss": 0.1106,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.3448275862068966,
882
+ "grad_norm": 1.7814508590384097,
883
+ "learning_rate": 1.6686530330613472e-05,
884
+ "loss": 0.1122,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.34758620689655173,
889
+ "grad_norm": 1.53815702992395,
890
+ "learning_rate": 1.661456426256161e-05,
891
+ "loss": 0.087,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.3503448275862069,
896
+ "grad_norm": 1.9077349161199095,
897
+ "learning_rate": 1.6541983920098462e-05,
898
+ "loss": 0.087,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.35310344827586204,
903
+ "grad_norm": 2.2996250559408704,
904
+ "learning_rate": 1.6468796043539082e-05,
905
+ "loss": 0.1254,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.35586206896551725,
910
+ "grad_norm": 1.2031295382564096,
911
+ "learning_rate": 1.639500742961838e-05,
912
+ "loss": 0.0498,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.3586206896551724,
917
+ "grad_norm": 1.3436281870681093,
918
+ "learning_rate": 1.6320624930859905e-05,
919
+ "loss": 0.077,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.36137931034482756,
924
+ "grad_norm": 0.6314939772663396,
925
+ "learning_rate": 1.6245655454939474e-05,
926
+ "loss": 0.0352,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.3641379310344828,
931
+ "grad_norm": 2.420910473317855,
932
+ "learning_rate": 1.6170105964043698e-05,
933
+ "loss": 0.1228,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.36689655172413793,
938
+ "grad_norm": 2.80050435155021,
939
+ "learning_rate": 1.6093983474223392e-05,
940
+ "loss": 0.1799,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.3696551724137931,
945
+ "grad_norm": 1.9733179937634817,
946
+ "learning_rate": 1.6017295054742045e-05,
947
+ "loss": 0.1088,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.3724137931034483,
952
+ "grad_norm": 0.8866446082715613,
953
+ "learning_rate": 1.5940047827419305e-05,
954
+ "loss": 0.0722,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.37517241379310345,
959
+ "grad_norm": 1.4747083716633578,
960
+ "learning_rate": 1.5862248965969604e-05,
961
+ "loss": 0.0902,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.3779310344827586,
966
+ "grad_norm": 1.203872871772734,
967
+ "learning_rate": 1.5783905695335947e-05,
968
+ "loss": 0.0763,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.38068965517241377,
973
+ "grad_norm": 1.295759494638433,
974
+ "learning_rate": 1.570502529101896e-05,
975
+ "loss": 0.0582,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.383448275862069,
980
+ "grad_norm": 2.082719193654199,
981
+ "learning_rate": 1.5625615078401244e-05,
982
+ "loss": 0.1131,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.38620689655172413,
987
+ "grad_norm": 2.4303248947365046,
988
+ "learning_rate": 1.5545682432067068e-05,
989
+ "loss": 0.1319,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.3889655172413793,
994
+ "grad_norm": 2.308746027421277,
995
+ "learning_rate": 1.5465234775117538e-05,
996
+ "loss": 0.1232,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.3917241379310345,
1001
+ "grad_norm": 2.9364629760972907,
1002
+ "learning_rate": 1.5384279578481223e-05,
1003
+ "loss": 0.1537,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.39448275862068966,
1008
+ "grad_norm": 1.8350345374035169,
1009
+ "learning_rate": 1.5302824360220352e-05,
1010
+ "loss": 0.1161,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.3972413793103448,
1015
+ "grad_norm": 1.8562459888809821,
1016
+ "learning_rate": 1.522087668483264e-05,
1017
+ "loss": 0.1054,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.4,
1022
+ "grad_norm": 2.2050577332052317,
1023
+ "learning_rate": 1.5138444162548791e-05,
1024
+ "loss": 0.072,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.4027586206896552,
1029
+ "grad_norm": 2.576862971551694,
1030
+ "learning_rate": 1.5055534448625766e-05,
1031
+ "loss": 0.1956,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.40551724137931033,
1036
+ "grad_norm": 2.526412596716041,
1037
+ "learning_rate": 1.4972155242635853e-05,
1038
+ "loss": 0.1163,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.40827586206896554,
1043
+ "grad_norm": 2.4122326865926325,
1044
+ "learning_rate": 1.488831428775164e-05,
1045
+ "loss": 0.1588,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.4110344827586207,
1050
+ "grad_norm": 1.5900334279122388,
1051
+ "learning_rate": 1.4804019370026927e-05,
1052
+ "loss": 0.0874,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.41379310344827586,
1057
+ "grad_norm": 2.2583849148863284,
1058
+ "learning_rate": 1.4719278317673655e-05,
1059
+ "loss": 0.1225,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.416551724137931,
1064
+ "grad_norm": 1.5043786808378643,
1065
+ "learning_rate": 1.4634099000334932e-05,
1066
+ "loss": 0.0628,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.4193103448275862,
1071
+ "grad_norm": 2.6867593671378707,
1072
+ "learning_rate": 1.4548489328354197e-05,
1073
+ "loss": 0.1119,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.4220689655172414,
1078
+ "grad_norm": 1.892183158003583,
1079
+ "learning_rate": 1.4462457252040606e-05,
1080
+ "loss": 0.1371,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.42482758620689653,
1085
+ "grad_norm": 0.7376897959603039,
1086
+ "learning_rate": 1.437601076093073e-05,
1087
+ "loss": 0.0715,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.42758620689655175,
1092
+ "grad_norm": 1.2313754414547655,
1093
+ "learning_rate": 1.4289157883046567e-05,
1094
+ "loss": 0.0671,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.4303448275862069,
1099
+ "grad_norm": 2.443959323743539,
1100
+ "learning_rate": 1.420190668415002e-05,
1101
+ "loss": 0.0937,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.43310344827586206,
1106
+ "grad_norm": 1.8279711072151712,
1107
+ "learning_rate": 1.4114265266993847e-05,
1108
+ "loss": 0.1114,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.43586206896551727,
1113
+ "grad_norm": 2.722814716999782,
1114
+ "learning_rate": 1.4026241770569198e-05,
1115
+ "loss": 0.1388,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.4386206896551724,
1120
+ "grad_norm": 2.522323402694141,
1121
+ "learning_rate": 1.3937844369349736e-05,
1122
+ "loss": 0.0862,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.4413793103448276,
1127
+ "grad_norm": 1.0652613518383625,
1128
+ "learning_rate": 1.3849081272532545e-05,
1129
+ "loss": 0.0752,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.44413793103448274,
1134
+ "grad_norm": 2.6542750874407335,
1135
+ "learning_rate": 1.375996072327573e-05,
1136
+ "loss": 0.1456,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.44689655172413795,
1141
+ "grad_norm": 1.8544625800539327,
1142
+ "learning_rate": 1.3670490997932922e-05,
1143
+ "loss": 0.109,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.4496551724137931,
1148
+ "grad_norm": 1.9735546120483556,
1149
+ "learning_rate": 1.3580680405284666e-05,
1150
+ "loss": 0.1144,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.45241379310344826,
1155
+ "grad_norm": 1.2177687301571833,
1156
+ "learning_rate": 1.3490537285766809e-05,
1157
+ "loss": 0.0838,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.45517241379310347,
1162
+ "grad_norm": 2.866049013585789,
1163
+ "learning_rate": 1.3400070010695966e-05,
1164
+ "loss": 0.1309,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.4579310344827586,
1169
+ "grad_norm": 1.7714947880406966,
1170
+ "learning_rate": 1.3309286981492084e-05,
1171
+ "loss": 0.1336,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.4606896551724138,
1176
+ "grad_norm": 2.3528937198669966,
1177
+ "learning_rate": 1.3218196628898232e-05,
1178
+ "loss": 0.0878,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.463448275862069,
1183
+ "grad_norm": 1.32763797639713,
1184
+ "learning_rate": 1.3126807412197666e-05,
1185
+ "loss": 0.0866,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.46620689655172415,
1190
+ "grad_norm": 1.0489060017302254,
1191
+ "learning_rate": 1.3035127818428239e-05,
1192
+ "loss": 0.0863,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.4689655172413793,
1197
+ "grad_norm": 1.4769228384530726,
1198
+ "learning_rate": 1.2943166361594242e-05,
1199
+ "loss": 0.1393,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.47172413793103446,
1204
+ "grad_norm": 1.9367121483246261,
1205
+ "learning_rate": 1.2850931581875723e-05,
1206
+ "loss": 0.1762,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.47448275862068967,
1211
+ "grad_norm": 1.5440366202640854,
1212
+ "learning_rate": 1.275843204483539e-05,
1213
+ "loss": 0.0599,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.4772413793103448,
1218
+ "grad_norm": 1.691410284752133,
1219
+ "learning_rate": 1.2665676340623172e-05,
1220
+ "loss": 0.0938,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.48,
1225
+ "grad_norm": 1.2010801724859,
1226
+ "learning_rate": 1.2572673083178448e-05,
1227
+ "loss": 0.098,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.4827586206896552,
1232
+ "grad_norm": 2.223070626201405,
1233
+ "learning_rate": 1.2479430909430109e-05,
1234
+ "loss": 0.0936,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.48551724137931035,
1239
+ "grad_norm": 2.1176352077764107,
1240
+ "learning_rate": 1.2385958478494487e-05,
1241
+ "loss": 0.1279,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.4882758620689655,
1246
+ "grad_norm": 1.3628256498935367,
1247
+ "learning_rate": 1.2292264470871183e-05,
1248
+ "loss": 0.0783,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.4910344827586207,
1253
+ "grad_norm": 1.064266823164612,
1254
+ "learning_rate": 1.2198357587636958e-05,
1255
+ "loss": 0.0525,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.49379310344827587,
1260
+ "grad_norm": 2.00945904980985,
1261
+ "learning_rate": 1.2104246549637683e-05,
1262
+ "loss": 0.0978,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.496551724137931,
1267
+ "grad_norm": 1.3141391526330848,
1268
+ "learning_rate": 1.2009940096678451e-05,
1269
+ "loss": 0.0963,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.4993103448275862,
1274
+ "grad_norm": 1.6531005740449383,
1275
+ "learning_rate": 1.1915446986711953e-05,
1276
+ "loss": 0.1092,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.5020689655172413,
1281
+ "grad_norm": 1.4945974838001637,
1282
+ "learning_rate": 1.1820775995025147e-05,
1283
+ "loss": 0.0667,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.5048275862068966,
1288
+ "grad_norm": 1.3762608443334923,
1289
+ "learning_rate": 1.172593591342432e-05,
1290
+ "loss": 0.0882,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.5075862068965518,
1295
+ "grad_norm": 1.5415877422060749,
1296
+ "learning_rate": 1.1630935549418627e-05,
1297
+ "loss": 0.0865,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.5103448275862069,
1302
+ "grad_norm": 2.0042018778537622,
1303
+ "learning_rate": 1.1535783725402163e-05,
1304
+ "loss": 0.1353,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.5131034482758621,
1309
+ "grad_norm": 2.6818407651740266,
1310
+ "learning_rate": 1.1440489277834645e-05,
1311
+ "loss": 0.1393,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.5158620689655172,
1316
+ "grad_norm": 2.3807831512162374,
1317
+ "learning_rate": 1.134506105642081e-05,
1318
+ "loss": 0.1169,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.5186206896551724,
1323
+ "grad_norm": 2.202610904326787,
1324
+ "learning_rate": 1.1249507923288563e-05,
1325
+ "loss": 0.1241,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.5213793103448275,
1330
+ "grad_norm": 1.8110167173727552,
1331
+ "learning_rate": 1.115383875216598e-05,
1332
+ "loss": 0.0945,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.5241379310344828,
1337
+ "grad_norm": 1.2395129394737805,
1338
+ "learning_rate": 1.105806242755723e-05,
1339
+ "loss": 0.0791,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.526896551724138,
1344
+ "grad_norm": 2.269164321603063,
1345
+ "learning_rate": 1.0962187843917498e-05,
1346
+ "loss": 0.0995,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.5296551724137931,
1351
+ "grad_norm": 2.1091615955126217,
1352
+ "learning_rate": 1.0866223904826992e-05,
1353
+ "loss": 0.0978,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.5324137931034483,
1358
+ "grad_norm": 1.1661181979597077,
1359
+ "learning_rate": 1.0770179522164079e-05,
1360
+ "loss": 0.0654,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.5351724137931034,
1365
+ "grad_norm": 1.529220319087916,
1366
+ "learning_rate": 1.0674063615277681e-05,
1367
+ "loss": 0.0795,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.5379310344827586,
1372
+ "grad_norm": 1.61462843303553,
1373
+ "learning_rate": 1.0577885110158959e-05,
1374
+ "loss": 0.0722,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.5406896551724137,
1379
+ "grad_norm": 1.0229094996985268,
1380
+ "learning_rate": 1.0481652938612374e-05,
1381
+ "loss": 0.1059,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.543448275862069,
1386
+ "grad_norm": 1.8905308810375994,
1387
+ "learning_rate": 1.0385376037426227e-05,
1388
+ "loss": 0.1007,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.5462068965517242,
1393
+ "grad_norm": 1.4659160591839386,
1394
+ "learning_rate": 1.0289063347542727e-05,
1395
+ "loss": 0.0997,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.5489655172413793,
1400
+ "grad_norm": 3.3227958982974637,
1401
+ "learning_rate": 1.0192723813227672e-05,
1402
+ "loss": 0.1803,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.5517241379310345,
1407
+ "grad_norm": 1.963767479554977,
1408
+ "learning_rate": 1.0096366381239808e-05,
1409
+ "loss": 0.1275,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.5544827586206896,
1414
+ "grad_norm": 1.6295769776645304,
1415
+ "learning_rate": 1e-05,
1416
+ "loss": 0.0784,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.5572413793103448,
1421
+ "grad_norm": 2.440021613726331,
1422
+ "learning_rate": 9.903633618760195e-06,
1423
+ "loss": 0.0884,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.56,
1428
+ "grad_norm": 1.4242019780978539,
1429
+ "learning_rate": 9.807276186772335e-06,
1430
+ "loss": 0.0852,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.5627586206896552,
1435
+ "grad_norm": 0.9963914089293635,
1436
+ "learning_rate": 9.710936652457276e-06,
1437
+ "loss": 0.0528,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.5655172413793104,
1442
+ "grad_norm": 2.0171601668683863,
1443
+ "learning_rate": 9.614623962573776e-06,
1444
+ "loss": 0.1213,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.5682758620689655,
1449
+ "grad_norm": 1.8302600165169711,
1450
+ "learning_rate": 9.518347061387629e-06,
1451
+ "loss": 0.0813,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.5710344827586207,
1456
+ "grad_norm": 2.135574797850369,
1457
+ "learning_rate": 9.422114889841045e-06,
1458
+ "loss": 0.1114,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.5737931034482758,
1463
+ "grad_norm": 1.856147430619363,
1464
+ "learning_rate": 9.325936384722322e-06,
1465
+ "loss": 0.1072,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.576551724137931,
1470
+ "grad_norm": 1.3734175489711284,
1471
+ "learning_rate": 9.229820477835926e-06,
1472
+ "loss": 0.0629,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.5793103448275863,
1477
+ "grad_norm": 1.4955582653472665,
1478
+ "learning_rate": 9.133776095173015e-06,
1479
+ "loss": 0.0798,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.5820689655172414,
1484
+ "grad_norm": 2.2098641671152075,
1485
+ "learning_rate": 9.037812156082503e-06,
1486
+ "loss": 0.0832,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.5848275862068966,
1491
+ "grad_norm": 2.1234204791453446,
1492
+ "learning_rate": 8.941937572442773e-06,
1493
+ "loss": 0.0912,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.5875862068965517,
1498
+ "grad_norm": 1.7048969824409477,
1499
+ "learning_rate": 8.846161247834024e-06,
1500
+ "loss": 0.0757,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.5903448275862069,
1505
+ "grad_norm": 1.2386625705533991,
1506
+ "learning_rate": 8.750492076711439e-06,
1507
+ "loss": 0.0607,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.593103448275862,
1512
+ "grad_norm": 2.4577783979073518,
1513
+ "learning_rate": 8.654938943579194e-06,
1514
+ "loss": 0.1315,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.5958620689655172,
1519
+ "grad_norm": 1.7822551401830198,
1520
+ "learning_rate": 8.55951072216536e-06,
1521
+ "loss": 0.1015,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.5986206896551725,
1526
+ "grad_norm": 1.627034418887004,
1527
+ "learning_rate": 8.464216274597839e-06,
1528
+ "loss": 0.083,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.6013793103448276,
1533
+ "grad_norm": 2.4236805021780907,
1534
+ "learning_rate": 8.369064450581374e-06,
1535
+ "loss": 0.144,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.6041379310344828,
1540
+ "grad_norm": 2.0852606023844547,
1541
+ "learning_rate": 8.274064086575682e-06,
1542
+ "loss": 0.1187,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.6068965517241379,
1547
+ "grad_norm": 1.554124619394613,
1548
+ "learning_rate": 8.179224004974857e-06,
1549
+ "loss": 0.101,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.6096551724137931,
1554
+ "grad_norm": 1.0086858963161975,
1555
+ "learning_rate": 8.084553013288048e-06,
1556
+ "loss": 0.0562,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.6124137931034482,
1561
+ "grad_norm": 1.744957411692858,
1562
+ "learning_rate": 7.990059903321554e-06,
1563
+ "loss": 0.1144,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.6151724137931035,
1568
+ "grad_norm": 1.115741854823727,
1569
+ "learning_rate": 7.89575345036232e-06,
1570
+ "loss": 0.0431,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.6179310344827587,
1575
+ "grad_norm": 2.4048467960954523,
1576
+ "learning_rate": 7.801642412363042e-06,
1577
+ "loss": 0.1239,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.6206896551724138,
1582
+ "grad_norm": 1.7045994682708523,
1583
+ "learning_rate": 7.707735529128819e-06,
1584
+ "loss": 0.0861,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.623448275862069,
1589
+ "grad_norm": 1.5844433019812807,
1590
+ "learning_rate": 7.614041521505517e-06,
1591
+ "loss": 0.0939,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.6262068965517241,
1596
+ "grad_norm": 1.817274462365455,
1597
+ "learning_rate": 7.520569090569894e-06,
1598
+ "loss": 0.0961,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.6289655172413793,
1603
+ "grad_norm": 2.169489761841419,
1604
+ "learning_rate": 7.427326916821557e-06,
1605
+ "loss": 0.1141,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.6317241379310344,
1610
+ "grad_norm": 1.2611061121212517,
1611
+ "learning_rate": 7.3343236593768295e-06,
1612
+ "loss": 0.0631,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.6344827586206897,
1617
+ "grad_norm": 1.4981316942094398,
1618
+ "learning_rate": 7.24156795516461e-06,
1619
+ "loss": 0.0607,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.6372413793103449,
1624
+ "grad_norm": 1.889688470210782,
1625
+ "learning_rate": 7.149068418124281e-06,
1626
+ "loss": 0.1243,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.64,
1631
+ "grad_norm": 1.6091621479461797,
1632
+ "learning_rate": 7.056833638405762e-06,
1633
+ "loss": 0.1154,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.6427586206896552,
1638
+ "grad_norm": 1.7584988460897566,
1639
+ "learning_rate": 6.964872181571765e-06,
1640
+ "loss": 0.0782,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.6455172413793103,
1645
+ "grad_norm": 1.9608264553670172,
1646
+ "learning_rate": 6.87319258780234e-06,
1647
+ "loss": 0.1088,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.6482758620689655,
1652
+ "grad_norm": 1.1583598512074385,
1653
+ "learning_rate": 6.781803371101774e-06,
1654
+ "loss": 0.0635,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.6510344827586206,
1659
+ "grad_norm": 1.5744270190667782,
1660
+ "learning_rate": 6.690713018507917e-06,
1661
+ "loss": 0.065,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.6537931034482759,
1666
+ "grad_norm": 2.0489496115781147,
1667
+ "learning_rate": 6.599929989304034e-06,
1668
+ "loss": 0.0941,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.6565517241379311,
1673
+ "grad_norm": 1.3833240601648478,
1674
+ "learning_rate": 6.509462714233194e-06,
1675
+ "loss": 0.1049,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.6593103448275862,
1680
+ "grad_norm": 1.105761243006651,
1681
+ "learning_rate": 6.419319594715338e-06,
1682
+ "loss": 0.0795,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.6620689655172414,
1687
+ "grad_norm": 2.2243011538195323,
1688
+ "learning_rate": 6.32950900206708e-06,
1689
+ "loss": 0.1389,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.6648275862068965,
1694
+ "grad_norm": 1.6204675243320001,
1695
+ "learning_rate": 6.240039276724273e-06,
1696
+ "loss": 0.0904,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.6675862068965517,
1701
+ "grad_norm": 1.7416445698806022,
1702
+ "learning_rate": 6.150918727467455e-06,
1703
+ "loss": 0.0988,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.670344827586207,
1708
+ "grad_norm": 1.5865476897173794,
1709
+ "learning_rate": 6.062155630650265e-06,
1710
+ "loss": 0.0887,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.6731034482758621,
1715
+ "grad_norm": 1.0908181878235528,
1716
+ "learning_rate": 5.973758229430806e-06,
1717
+ "loss": 0.0406,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.6758620689655173,
1722
+ "grad_norm": 1.2409267373149415,
1723
+ "learning_rate": 5.8857347330061545e-06,
1724
+ "loss": 0.0613,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.6786206896551724,
1729
+ "grad_norm": 1.5366160191792417,
1730
+ "learning_rate": 5.798093315849984e-06,
1731
+ "loss": 0.0621,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.6813793103448276,
1736
+ "grad_norm": 2.401971583677582,
1737
+ "learning_rate": 5.7108421169534376e-06,
1738
+ "loss": 0.135,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.6841379310344827,
1743
+ "grad_norm": 1.7382959732076737,
1744
+ "learning_rate": 5.623989239069275e-06,
1745
+ "loss": 0.0912,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.6868965517241379,
1750
+ "grad_norm": 1.1164138593496515,
1751
+ "learning_rate": 5.5375427479593945e-06,
1752
+ "loss": 0.0481,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.6896551724137931,
1757
+ "grad_norm": 1.9207044725285578,
1758
+ "learning_rate": 5.451510671645806e-06,
1759
+ "loss": 0.0915,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.6924137931034483,
1764
+ "grad_norm": 1.4554330468757273,
1765
+ "learning_rate": 5.3659009996650704e-06,
1766
+ "loss": 0.0932,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.6951724137931035,
1771
+ "grad_norm": 1.5637751353358034,
1772
+ "learning_rate": 5.280721682326349e-06,
1773
+ "loss": 0.1258,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.6979310344827586,
1778
+ "grad_norm": 1.6864022667103549,
1779
+ "learning_rate": 5.195980629973077e-06,
1780
+ "loss": 0.136,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.7006896551724138,
1785
+ "grad_norm": 1.5424417657042435,
1786
+ "learning_rate": 5.111685712248364e-06,
1787
+ "loss": 0.0744,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.7034482758620689,
1792
+ "grad_norm": 2.4152541945255965,
1793
+ "learning_rate": 5.02784475736415e-06,
1794
+ "loss": 0.1436,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.7062068965517241,
1799
+ "grad_norm": 1.8800510082119968,
1800
+ "learning_rate": 4.944465551374238e-06,
1801
+ "loss": 0.0864,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.7089655172413794,
1806
+ "grad_norm": 1.6391965299287088,
1807
+ "learning_rate": 4.861555837451213e-06,
1808
+ "loss": 0.0931,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.7117241379310345,
1813
+ "grad_norm": 2.1164230178199688,
1814
+ "learning_rate": 4.779123315167362e-06,
1815
+ "loss": 0.1589,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.7144827586206897,
1820
+ "grad_norm": 2.1736287568680615,
1821
+ "learning_rate": 4.6971756397796506e-06,
1822
+ "loss": 0.075,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.7172413793103448,
1827
+ "grad_norm": 0.981201558647046,
1828
+ "learning_rate": 4.61572042151878e-06,
1829
+ "loss": 0.0423,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.72,
1834
+ "grad_norm": 1.2068505093305162,
1835
+ "learning_rate": 4.534765224882463e-06,
1836
+ "loss": 0.0538,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.7227586206896551,
1841
+ "grad_norm": 0.9541230040360105,
1842
+ "learning_rate": 4.4543175679329345e-06,
1843
+ "loss": 0.0591,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.7255172413793104,
1848
+ "grad_norm": 1.7162320823485342,
1849
+ "learning_rate": 4.37438492159876e-06,
1850
+ "loss": 0.0965,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.7282758620689656,
1855
+ "grad_norm": 1.184768855122373,
1856
+ "learning_rate": 4.294974708981041e-06,
1857
+ "loss": 0.0383,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.7310344827586207,
1862
+ "grad_norm": 1.5098290827125584,
1863
+ "learning_rate": 4.216094304664056e-06,
1864
+ "loss": 0.0952,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.7337931034482759,
1869
+ "grad_norm": 1.3641276614652302,
1870
+ "learning_rate": 4.1377510340304e-06,
1871
+ "loss": 0.0687,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.736551724137931,
1876
+ "grad_norm": 1.9886328182742048,
1877
+ "learning_rate": 4.059952172580694e-06,
1878
+ "loss": 0.1397,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.7393103448275862,
1883
+ "grad_norm": 2.0623334755221494,
1884
+ "learning_rate": 3.982704945257957e-06,
1885
+ "loss": 0.1271,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.7420689655172413,
1890
+ "grad_norm": 2.027142606530138,
1891
+ "learning_rate": 3.9060165257766116e-06,
1892
+ "loss": 0.0736,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.7448275862068966,
1897
+ "grad_norm": 1.8884432574197467,
1898
+ "learning_rate": 3.829894035956306e-06,
1899
+ "loss": 0.1243,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.7475862068965518,
1904
+ "grad_norm": 1.5259208901463874,
1905
+ "learning_rate": 3.754344545060529e-06,
1906
+ "loss": 0.0971,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.7503448275862069,
1911
+ "grad_norm": 1.454648528529707,
1912
+ "learning_rate": 3.6793750691400996e-06,
1913
+ "loss": 0.1226,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.7531034482758621,
1918
+ "grad_norm": 1.1852288533881499,
1919
+ "learning_rate": 3.604992570381621e-06,
1920
+ "loss": 0.0573,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.7558620689655172,
1925
+ "grad_norm": 0.9888790128432269,
1926
+ "learning_rate": 3.5312039564609203e-06,
1927
+ "loss": 0.0357,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.7586206896551724,
1932
+ "grad_norm": 1.9227683916123242,
1933
+ "learning_rate": 3.458016079901544e-06,
1934
+ "loss": 0.0841,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.7613793103448275,
1939
+ "grad_norm": 1.6925865088399465,
1940
+ "learning_rate": 3.3854357374383905e-06,
1941
+ "loss": 0.0749,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.7641379310344828,
1946
+ "grad_norm": 2.482457504595889,
1947
+ "learning_rate": 3.313469669386532e-06,
1948
+ "loss": 0.1234,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.766896551724138,
1953
+ "grad_norm": 1.2830007481095762,
1954
+ "learning_rate": 3.242124559015234e-06,
1955
+ "loss": 0.0752,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.7696551724137931,
1960
+ "grad_norm": 2.0768576257082114,
1961
+ "learning_rate": 3.171407031927325e-06,
1962
+ "loss": 0.0991,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.7724137931034483,
1967
+ "grad_norm": 1.8987466668093202,
1968
+ "learning_rate": 3.101323655443882e-06,
1969
+ "loss": 0.109,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.7751724137931034,
1974
+ "grad_norm": 1.6001709673447158,
1975
+ "learning_rate": 3.0318809379943594e-06,
1976
+ "loss": 0.0599,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.7779310344827586,
1981
+ "grad_norm": 1.309542383665605,
1982
+ "learning_rate": 2.9630853285121506e-06,
1983
+ "loss": 0.0641,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.7806896551724138,
1988
+ "grad_norm": 1.5565630583605414,
1989
+ "learning_rate": 2.8949432158357083e-06,
1990
+ "loss": 0.0909,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.783448275862069,
1995
+ "grad_norm": 1.2776706094735155,
1996
+ "learning_rate": 2.8274609281152322e-06,
1997
+ "loss": 0.1223,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.7862068965517242,
2002
+ "grad_norm": 1.6300368148462467,
2003
+ "learning_rate": 2.7606447322249876e-06,
2004
+ "loss": 0.087,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.7889655172413793,
2009
+ "grad_norm": 1.5096693670735182,
2010
+ "learning_rate": 2.694500833181323e-06,
2011
+ "loss": 0.1002,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.7917241379310345,
2016
+ "grad_norm": 1.719399247233759,
2017
+ "learning_rate": 2.629035373566433e-06,
2018
+ "loss": 0.0915,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.7944827586206896,
2023
+ "grad_norm": 1.1425139227274304,
2024
+ "learning_rate": 2.5642544329579088e-06,
2025
+ "loss": 0.0555,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.7972413793103448,
2030
+ "grad_norm": 1.2082856945935607,
2031
+ "learning_rate": 2.500164027364147e-06,
2032
+ "loss": 0.0555,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.8,
2037
+ "grad_norm": 2.028172728126609,
2038
+ "learning_rate": 2.4367701086656625e-06,
2039
+ "loss": 0.104,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.8027586206896552,
2044
+ "grad_norm": 1.498164820422529,
2045
+ "learning_rate": 2.374078564062364e-06,
2046
+ "loss": 0.0936,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.8055172413793104,
2051
+ "grad_norm": 1.3254283577777912,
2052
+ "learning_rate": 2.312095215526814e-06,
2053
+ "loss": 0.0898,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.8082758620689655,
2058
+ "grad_norm": 1.3758428200048072,
2059
+ "learning_rate": 2.2508258192635614e-06,
2060
+ "loss": 0.073,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.8110344827586207,
2065
+ "grad_norm": 1.2825112587820704,
2066
+ "learning_rate": 2.190276065174596e-06,
2067
+ "loss": 0.0675,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.8137931034482758,
2072
+ "grad_norm": 1.704844614821693,
2073
+ "learning_rate": 2.130451576330925e-06,
2074
+ "loss": 0.0871,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.8165517241379311,
2079
+ "grad_norm": 1.8236093781558738,
2080
+ "learning_rate": 2.0713579084503877e-06,
2081
+ "loss": 0.075,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.8193103448275862,
2086
+ "grad_norm": 1.7159210186184939,
2087
+ "learning_rate": 2.0130005493817063e-06,
2088
+ "loss": 0.0726,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.8220689655172414,
2093
+ "grad_norm": 1.5402879375212146,
2094
+ "learning_rate": 1.9553849185948514e-06,
2095
+ "loss": 0.0585,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.8248275862068966,
2100
+ "grad_norm": 2.088587364963122,
2101
+ "learning_rate": 1.8985163666777473e-06,
2102
+ "loss": 0.1192,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.8275862068965517,
2107
+ "grad_norm": 1.385102288521542,
2108
+ "learning_rate": 1.8424001748393905e-06,
2109
+ "loss": 0.0639,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.8303448275862069,
2114
+ "grad_norm": 1.199103692035072,
2115
+ "learning_rate": 1.7870415544193808e-06,
2116
+ "loss": 0.0644,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.833103448275862,
2121
+ "grad_norm": 1.576550399440244,
2122
+ "learning_rate": 1.7324456464039751e-06,
2123
+ "loss": 0.0806,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.8358620689655173,
2128
+ "grad_norm": 1.9033469567963237,
2129
+ "learning_rate": 1.6786175209486565e-06,
2130
+ "loss": 0.1166,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.8386206896551724,
2135
+ "grad_norm": 1.5481679752062283,
2136
+ "learning_rate": 1.6255621769072805e-06,
2137
+ "loss": 0.0883,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.8413793103448276,
2142
+ "grad_norm": 1.7374538978001977,
2143
+ "learning_rate": 1.5732845413678477e-06,
2144
+ "loss": 0.105,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.8441379310344828,
2149
+ "grad_norm": 1.3465892642582866,
2150
+ "learning_rate": 1.521789469194952e-06,
2151
+ "loss": 0.0618,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.8468965517241379,
2156
+ "grad_norm": 2.312489005340463,
2157
+ "learning_rate": 1.4710817425789015e-06,
2158
+ "loss": 0.0992,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.8496551724137931,
2163
+ "grad_norm": 1.1318530850342379,
2164
+ "learning_rate": 1.4211660705916286e-06,
2165
+ "loss": 0.0458,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.8524137931034482,
2170
+ "grad_norm": 1.5063935617388766,
2171
+ "learning_rate": 1.372047088749372e-06,
2172
+ "loss": 0.0516,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.8551724137931035,
2177
+ "grad_norm": 1.4001415457936668,
2178
+ "learning_rate": 1.3237293585821786e-06,
2179
+ "loss": 0.1156,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.8579310344827586,
2184
+ "grad_norm": 2.487040806365276,
2185
+ "learning_rate": 1.2762173672102996e-06,
2186
+ "loss": 0.1332,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.8606896551724138,
2191
+ "grad_norm": 1.514447174356807,
2192
+ "learning_rate": 1.2295155269274827e-06,
2193
+ "loss": 0.0735,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.863448275862069,
2198
+ "grad_norm": 1.9664878278885487,
2199
+ "learning_rate": 1.1836281747912125e-06,
2200
+ "loss": 0.0825,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.8662068965517241,
2205
+ "grad_norm": 1.7248118984472842,
2206
+ "learning_rate": 1.1385595722199438e-06,
2207
+ "loss": 0.0945,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.8689655172413793,
2212
+ "grad_norm": 1.232176840002336,
2213
+ "learning_rate": 1.094313904597355e-06,
2214
+ "loss": 0.0761,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.8717241379310345,
2219
+ "grad_norm": 2.3846939660082636,
2220
+ "learning_rate": 1.0508952808836682e-06,
2221
+ "loss": 0.1104,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.8744827586206897,
2226
+ "grad_norm": 1.5107849502345858,
2227
+ "learning_rate": 1.0083077332340563e-06,
2228
+ "loss": 0.137,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.8772413793103448,
2233
+ "grad_norm": 2.5218758909483077,
2234
+ "learning_rate": 9.665552166241965e-07,
2235
+ "loss": 0.1395,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.88,
2240
+ "grad_norm": 1.913603235284768,
2241
+ "learning_rate": 9.256416084829778e-07,
2242
+ "loss": 0.1331,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.8827586206896552,
2247
+ "grad_norm": 2.4049905043471806,
2248
+ "learning_rate": 8.855707083324183e-07,
2249
+ "loss": 0.1077,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.8855172413793103,
2254
+ "grad_norm": 1.108589495662786,
2255
+ "learning_rate": 8.46346237434813e-07,
2256
+ "loss": 0.0638,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.8882758620689655,
2261
+ "grad_norm": 1.222025656507595,
2262
+ "learning_rate": 8.079718384471557e-07,
2263
+ "loss": 0.0515,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.8910344827586207,
2268
+ "grad_norm": 1.6319377780473996,
2269
+ "learning_rate": 7.704510750828542e-07,
2270
+ "loss": 0.0623,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.8937931034482759,
2275
+ "grad_norm": 1.402983153361783,
2276
+ "learning_rate": 7.337874317807803e-07,
2277
+ "loss": 0.0516,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.896551724137931,
2282
+ "grad_norm": 1.4500270750731776,
2283
+ "learning_rate": 6.979843133816744e-07,
2284
+ "loss": 0.0612,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.8993103448275862,
2289
+ "grad_norm": 1.095211249638046,
2290
+ "learning_rate": 6.630450448119618e-07,
2291
+ "loss": 0.0333,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.9020689655172414,
2296
+ "grad_norm": 1.8925065532997027,
2297
+ "learning_rate": 6.289728707749609e-07,
2298
+ "loss": 0.0953,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.9048275862068965,
2303
+ "grad_norm": 1.747624078137272,
2304
+ "learning_rate": 5.957709554495683e-07,
2305
+ "loss": 0.0893,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.9075862068965517,
2310
+ "grad_norm": 0.9113610050884592,
2311
+ "learning_rate": 5.634423821964074e-07,
2312
+ "loss": 0.0423,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.9103448275862069,
2317
+ "grad_norm": 1.6463257868897792,
2318
+ "learning_rate": 5.319901532714877e-07,
2319
+ "loss": 0.1055,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.9131034482758621,
2324
+ "grad_norm": 1.84950657136513,
2325
+ "learning_rate": 5.014171895473929e-07,
2326
+ "loss": 0.1232,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.9158620689655173,
2331
+ "grad_norm": 1.5561236996647523,
2332
+ "learning_rate": 4.717263302420283e-07,
2333
+ "loss": 0.076,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.9186206896551724,
2338
+ "grad_norm": 1.2285714349711996,
2339
+ "learning_rate": 4.429203326549525e-07,
2340
+ "loss": 0.0835,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.9213793103448276,
2345
+ "grad_norm": 2.8092718918728288,
2346
+ "learning_rate": 4.150018719113147e-07,
2347
+ "loss": 0.0734,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.9241379310344827,
2352
+ "grad_norm": 1.766273016183224,
2353
+ "learning_rate": 3.8797354071342443e-07,
2354
+ "loss": 0.0768,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.926896551724138,
2359
+ "grad_norm": 2.1729531887535285,
2360
+ "learning_rate": 3.618378490999719e-07,
2361
+ "loss": 0.1027,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.9296551724137931,
2366
+ "grad_norm": 1.7482937409483954,
2367
+ "learning_rate": 3.365972242129378e-07,
2368
+ "loss": 0.1176,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.9324137931034483,
2373
+ "grad_norm": 1.2860014321281648,
2374
+ "learning_rate": 3.122540100721794e-07,
2375
+ "loss": 0.068,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.9351724137931035,
2380
+ "grad_norm": 1.8682982161376196,
2381
+ "learning_rate": 2.888104673577574e-07,
2382
+ "loss": 0.0826,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.9379310344827586,
2387
+ "grad_norm": 2.1192579972688548,
2388
+ "learning_rate": 2.66268773199988e-07,
2389
+ "loss": 0.1094,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.9406896551724138,
2394
+ "grad_norm": 1.812620322889224,
2395
+ "learning_rate": 2.4463102097726843e-07,
2396
+ "loss": 0.1397,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.9434482758620689,
2401
+ "grad_norm": 1.55323368762906,
2402
+ "learning_rate": 2.2389922012165944e-07,
2403
+ "loss": 0.0883,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.9462068965517242,
2408
+ "grad_norm": 1.3537994599803411,
2409
+ "learning_rate": 2.0407529593228114e-07,
2410
+ "loss": 0.0537,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.9489655172413793,
2415
+ "grad_norm": 1.9963802514280435,
2416
+ "learning_rate": 1.8516108939651945e-07,
2417
+ "loss": 0.0841,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.9517241379310345,
2422
+ "grad_norm": 1.9489250790151131,
2423
+ "learning_rate": 1.6715835701905604e-07,
2424
+ "loss": 0.1278,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.9544827586206897,
2429
+ "grad_norm": 1.208403698921063,
2430
+ "learning_rate": 1.5006877065874338e-07,
2431
+ "loss": 0.062,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.9572413793103448,
2436
+ "grad_norm": 1.9902454269295837,
2437
+ "learning_rate": 1.3389391737335112e-07,
2438
+ "loss": 0.1123,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.96,
2443
+ "grad_norm": 1.5549649154456184,
2444
+ "learning_rate": 1.1863529927217731e-07,
2445
+ "loss": 0.0859,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.9627586206896551,
2450
+ "grad_norm": 1.5672800792400794,
2451
+ "learning_rate": 1.0429433337655115e-07,
2452
+ "loss": 0.0664,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.9655172413793104,
2457
+ "grad_norm": 1.980266389039632,
2458
+ "learning_rate": 9.08723514882437e-08,
2459
+ "loss": 0.0978,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.9682758620689655,
2464
+ "grad_norm": 1.924180909114094,
2465
+ "learning_rate": 7.837060006577801e-08,
2466
+ "loss": 0.082,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.9710344827586207,
2471
+ "grad_norm": 1.360244814652006,
2472
+ "learning_rate": 6.679024010868617e-08,
2473
+ "loss": 0.0937,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.9737931034482759,
2478
+ "grad_norm": 1.3638474049460683,
2479
+ "learning_rate": 5.6132347049679955e-08,
2480
+ "loss": 0.0944,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.976551724137931,
2485
+ "grad_norm": 1.0043906816455541,
2486
+ "learning_rate": 4.639791065478738e-08,
2487
+ "loss": 0.0373,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.9793103448275862,
2492
+ "grad_norm": 1.3136551040176567,
2493
+ "learning_rate": 3.758783493142737e-08,
2494
+ "loss": 0.0938,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.9820689655172414,
2499
+ "grad_norm": 1.2330770172633143,
2500
+ "learning_rate": 2.9702938044468e-08,
2501
+ "loss": 0.1083,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.9848275862068966,
2506
+ "grad_norm": 1.4318266541987408,
2507
+ "learning_rate": 2.274395224023618e-08,
2508
+ "loss": 0.0667,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.9875862068965517,
2513
+ "grad_norm": 1.4889881534099365,
2514
+ "learning_rate": 1.671152377852092e-08,
2515
+ "loss": 0.0907,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.9903448275862069,
2520
+ "grad_norm": 1.9950572073445185,
2521
+ "learning_rate": 1.1606212872559142e-08,
2522
+ "loss": 0.0937,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.993103448275862,
2527
+ "grad_norm": 1.2536334792292063,
2528
+ "learning_rate": 7.42849363700282e-09,
2529
+ "loss": 0.0863,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.9958620689655172,
2534
+ "grad_norm": 1.2816200143172458,
2535
+ "learning_rate": 4.178754043898669e-09,
2536
+ "loss": 0.0593,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.9986206896551724,
2541
+ "grad_norm": 0.7637431538197891,
2542
+ "learning_rate": 1.8572958866514e-09,
2543
+ "loss": 0.0859,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 1.0,
2548
+ "grad_norm": 2.3907025925168472,
2549
+ "learning_rate": 4.643347520005836e-10,
2550
+ "loss": 0.0658,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 1.0,
2555
+ "step": 363,
2556
+ "total_flos": 50754799140864.0,
2557
+ "train_loss": 0.09636665488652289,
2558
+ "train_runtime": 845.3624,
2559
+ "train_samples_per_second": 6.855,
2560
+ "train_steps_per_second": 0.429
2561
+ }
2562
+ ],
2563
+ "logging_steps": 1,
2564
+ "max_steps": 363,
2565
+ "num_input_tokens_seen": 0,
2566
+ "num_train_epochs": 1,
2567
+ "save_steps": 100,
2568
+ "stateful_callbacks": {
2569
+ "TrainerControl": {
2570
+ "args": {
2571
+ "should_epoch_stop": false,
2572
+ "should_evaluate": false,
2573
+ "should_log": false,
2574
+ "should_save": true,
2575
+ "should_training_stop": true
2576
+ },
2577
+ "attributes": {}
2578
+ }
2579
+ },
2580
+ "total_flos": 50754799140864.0,
2581
+ "train_batch_size": 1,
2582
+ "trial_name": null,
2583
+ "trial_params": null
2584
+ }
iter4_sft/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ecef1a19e50720dda9589d091e84f25baab62d44fa0582bb6351c6765912dc
3
+ size 8273
iter4_sft/training_loss.png ADDED
iter4_sft/video_preprocessor_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "pad_size": null,
32
+ "patch_size": 14,
33
+ "processor_class": "Qwen2_5_VLProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "return_metadata": false,
37
+ "size": {
38
+ "longest_edge": 12845056,
39
+ "shortest_edge": 3136
40
+ },
41
+ "size_divisor": null,
42
+ "temporal_patch_size": 2,
43
+ "video_metadata": null,
44
+ "video_processor_type": "Qwen2VLVideoProcessor"
45
+ }
iter4_sft/vocab.json ADDED
The diff for this file is too large to render. See raw diff