Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +16 -0
- chat_template.jinja +7 -0
- config.json +97 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +144 -0
- trainer_state.json +1434 -0
- training_args.bin +3 -0
- video_preprocessor_config.json +86 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|box_end|>": 151649,
|
| 3 |
+
"<|box_start|>": 151648,
|
| 4 |
+
"<|endoftext|>": 151643,
|
| 5 |
+
"<|im_end|>": 151645,
|
| 6 |
+
"<|im_start|>": 151644,
|
| 7 |
+
"<|image_pad|>": 151655,
|
| 8 |
+
"<|object_ref_end|>": 151647,
|
| 9 |
+
"<|object_ref_start|>": 151646,
|
| 10 |
+
"<|quad_end|>": 151651,
|
| 11 |
+
"<|quad_start|>": 151650,
|
| 12 |
+
"<|video_pad|>": 151656,
|
| 13 |
+
"<|vision_end|>": 151653,
|
| 14 |
+
"<|vision_pad|>": 151654,
|
| 15 |
+
"<|vision_start|>": 151652
|
| 16 |
+
}
|
chat_template.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 %}
|
config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2_vl",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"text_config": {
|
| 32 |
+
"architectures": [
|
| 33 |
+
"Qwen2VLForConditionalGeneration"
|
| 34 |
+
],
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"bos_token_id": 151643,
|
| 37 |
+
"eos_token_id": 151645,
|
| 38 |
+
"hidden_act": "silu",
|
| 39 |
+
"hidden_size": 1536,
|
| 40 |
+
"image_token_id": null,
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 8960,
|
| 43 |
+
"max_position_embeddings": 32768,
|
| 44 |
+
"max_window_layers": 28,
|
| 45 |
+
"model_type": "qwen2_vl_text",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 2,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": {
|
| 51 |
+
"mrope_section": [
|
| 52 |
+
16,
|
| 53 |
+
24,
|
| 54 |
+
24
|
| 55 |
+
],
|
| 56 |
+
"rope_type": "default",
|
| 57 |
+
"type": "default"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": 32768,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"use_cache": false,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"video_token_id": null,
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652,
|
| 68 |
+
"vision_token_id": 151654,
|
| 69 |
+
"vocab_size": 151936
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "bfloat16",
|
| 72 |
+
"transformers_version": "4.52.4",
|
| 73 |
+
"use_cache": false,
|
| 74 |
+
"use_sliding_window": false,
|
| 75 |
+
"video_token_id": 151656,
|
| 76 |
+
"vision_config": {
|
| 77 |
+
"depth": 32,
|
| 78 |
+
"embed_dim": 1280,
|
| 79 |
+
"hidden_act": "quick_gelu",
|
| 80 |
+
"hidden_size": 1536,
|
| 81 |
+
"in_channels": 3,
|
| 82 |
+
"in_chans": 3,
|
| 83 |
+
"initializer_range": 0.02,
|
| 84 |
+
"mlp_ratio": 4,
|
| 85 |
+
"model_type": "qwen2_vl",
|
| 86 |
+
"num_heads": 16,
|
| 87 |
+
"patch_size": 14,
|
| 88 |
+
"spatial_merge_size": 2,
|
| 89 |
+
"spatial_patch_size": 14,
|
| 90 |
+
"temporal_patch_size": 2,
|
| 91 |
+
"torch_dtype": "bfloat16"
|
| 92 |
+
},
|
| 93 |
+
"vision_end_token_id": 151653,
|
| 94 |
+
"vision_start_token_id": 151652,
|
| 95 |
+
"vision_token_id": 151654,
|
| 96 |
+
"vocab_size": 151936
|
| 97 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.01,
|
| 10 |
+
"top_k": 1,
|
| 11 |
+
"top_p": 0.001,
|
| 12 |
+
"transformers_version": "4.52.4"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c0f27f2e57cd5f74af5fea9aa1656127709ad927e2550b6c10ff2494f8f146a
|
| 3 |
+
size 4884798456
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"input_data_format": null,
|
| 23 |
+
"max_pixels": 12845056,
|
| 24 |
+
"merge_size": 2,
|
| 25 |
+
"min_pixels": 3136,
|
| 26 |
+
"patch_size": 14,
|
| 27 |
+
"processor_class": "Qwen2VLProcessor",
|
| 28 |
+
"resample": 3,
|
| 29 |
+
"rescale_factor": 0.00392156862745098,
|
| 30 |
+
"return_tensors": null,
|
| 31 |
+
"size": {
|
| 32 |
+
"longest_edge": 12845056,
|
| 33 |
+
"shortest_edge": 3136
|
| 34 |
+
},
|
| 35 |
+
"temporal_patch_size": 2
|
| 36 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
| 3 |
+
size 11420371
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
}
|
| 116 |
+
},
|
| 117 |
+
"additional_special_tokens": [
|
| 118 |
+
"<|im_start|>",
|
| 119 |
+
"<|im_end|>",
|
| 120 |
+
"<|object_ref_start|>",
|
| 121 |
+
"<|object_ref_end|>",
|
| 122 |
+
"<|box_start|>",
|
| 123 |
+
"<|box_end|>",
|
| 124 |
+
"<|quad_start|>",
|
| 125 |
+
"<|quad_end|>",
|
| 126 |
+
"<|vision_start|>",
|
| 127 |
+
"<|vision_end|>",
|
| 128 |
+
"<|vision_pad|>",
|
| 129 |
+
"<|image_pad|>",
|
| 130 |
+
"<|video_pad|>"
|
| 131 |
+
],
|
| 132 |
+
"bos_token": null,
|
| 133 |
+
"clean_up_tokenization_spaces": false,
|
| 134 |
+
"eos_token": "<|im_end|>",
|
| 135 |
+
"errors": "replace",
|
| 136 |
+
"extra_special_tokens": {},
|
| 137 |
+
"model_max_length": 32768,
|
| 138 |
+
"pad_token": "<|endoftext|>",
|
| 139 |
+
"padding_side": "right",
|
| 140 |
+
"processor_class": "Qwen2VLProcessor",
|
| 141 |
+
"split_special_tokens": false,
|
| 142 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 143 |
+
"unk_token": null
|
| 144 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8533333333333334,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004266666666666667,
|
| 14 |
+
"grad_norm": 22.56278419494629,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.003,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008533333333333334,
|
| 21 |
+
"grad_norm": 22.34969711303711,
|
| 22 |
+
"learning_rate": 4.2553191489361707e-08,
|
| 23 |
+
"loss": 1.0007,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0128,
|
| 28 |
+
"grad_norm": 22.497220993041992,
|
| 29 |
+
"learning_rate": 8.510638297872341e-08,
|
| 30 |
+
"loss": 0.9989,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.017066666666666667,
|
| 35 |
+
"grad_norm": 22.301002502441406,
|
| 36 |
+
"learning_rate": 1.276595744680851e-07,
|
| 37 |
+
"loss": 0.9972,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.021333333333333333,
|
| 42 |
+
"grad_norm": 22.443401336669922,
|
| 43 |
+
"learning_rate": 1.7021276595744683e-07,
|
| 44 |
+
"loss": 0.9995,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0256,
|
| 49 |
+
"grad_norm": 22.423526763916016,
|
| 50 |
+
"learning_rate": 2.1276595744680852e-07,
|
| 51 |
+
"loss": 0.9983,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.029866666666666666,
|
| 56 |
+
"grad_norm": 22.28087043762207,
|
| 57 |
+
"learning_rate": 2.553191489361702e-07,
|
| 58 |
+
"loss": 0.9965,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.034133333333333335,
|
| 63 |
+
"grad_norm": 22.648902893066406,
|
| 64 |
+
"learning_rate": 2.9787234042553196e-07,
|
| 65 |
+
"loss": 0.9996,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0384,
|
| 70 |
+
"grad_norm": 21.830528259277344,
|
| 71 |
+
"learning_rate": 3.4042553191489365e-07,
|
| 72 |
+
"loss": 0.9895,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.042666666666666665,
|
| 77 |
+
"grad_norm": 22.060640335083008,
|
| 78 |
+
"learning_rate": 3.8297872340425535e-07,
|
| 79 |
+
"loss": 0.9927,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.046933333333333334,
|
| 84 |
+
"grad_norm": 20.831892013549805,
|
| 85 |
+
"learning_rate": 4.2553191489361704e-07,
|
| 86 |
+
"loss": 0.9694,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0512,
|
| 91 |
+
"grad_norm": 20.609140396118164,
|
| 92 |
+
"learning_rate": 4.6808510638297873e-07,
|
| 93 |
+
"loss": 0.9665,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.055466666666666664,
|
| 98 |
+
"grad_norm": 20.27930450439453,
|
| 99 |
+
"learning_rate": 5.106382978723404e-07,
|
| 100 |
+
"loss": 0.9665,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05973333333333333,
|
| 105 |
+
"grad_norm": 20.32429313659668,
|
| 106 |
+
"learning_rate": 5.531914893617021e-07,
|
| 107 |
+
"loss": 0.9611,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.064,
|
| 112 |
+
"grad_norm": 16.961851119995117,
|
| 113 |
+
"learning_rate": 5.957446808510639e-07,
|
| 114 |
+
"loss": 0.8898,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06826666666666667,
|
| 119 |
+
"grad_norm": 16.51335906982422,
|
| 120 |
+
"learning_rate": 6.382978723404255e-07,
|
| 121 |
+
"loss": 0.8859,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07253333333333334,
|
| 126 |
+
"grad_norm": 16.328777313232422,
|
| 127 |
+
"learning_rate": 6.808510638297873e-07,
|
| 128 |
+
"loss": 0.8805,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0768,
|
| 133 |
+
"grad_norm": 15.942858695983887,
|
| 134 |
+
"learning_rate": 7.234042553191489e-07,
|
| 135 |
+
"loss": 0.8662,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08106666666666666,
|
| 140 |
+
"grad_norm": 15.772059440612793,
|
| 141 |
+
"learning_rate": 7.659574468085107e-07,
|
| 142 |
+
"loss": 0.8618,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08533333333333333,
|
| 147 |
+
"grad_norm": 15.53687858581543,
|
| 148 |
+
"learning_rate": 8.085106382978725e-07,
|
| 149 |
+
"loss": 0.8506,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0896,
|
| 154 |
+
"grad_norm": 10.289249420166016,
|
| 155 |
+
"learning_rate": 8.510638297872341e-07,
|
| 156 |
+
"loss": 0.6896,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09386666666666667,
|
| 161 |
+
"grad_norm": 10.452590942382812,
|
| 162 |
+
"learning_rate": 8.936170212765959e-07,
|
| 163 |
+
"loss": 0.6914,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.09813333333333334,
|
| 168 |
+
"grad_norm": 10.317420959472656,
|
| 169 |
+
"learning_rate": 9.361702127659575e-07,
|
| 170 |
+
"loss": 0.6787,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1024,
|
| 175 |
+
"grad_norm": 9.890551567077637,
|
| 176 |
+
"learning_rate": 9.787234042553193e-07,
|
| 177 |
+
"loss": 0.6696,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10666666666666667,
|
| 182 |
+
"grad_norm": 9.151979446411133,
|
| 183 |
+
"learning_rate": 1.0212765957446809e-06,
|
| 184 |
+
"loss": 0.6481,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.11093333333333333,
|
| 189 |
+
"grad_norm": 8.83176040649414,
|
| 190 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 191 |
+
"loss": 0.6352,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1152,
|
| 196 |
+
"grad_norm": 8.056096076965332,
|
| 197 |
+
"learning_rate": 1.1063829787234042e-06,
|
| 198 |
+
"loss": 0.6139,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.11946666666666667,
|
| 203 |
+
"grad_norm": 8.634873390197754,
|
| 204 |
+
"learning_rate": 1.148936170212766e-06,
|
| 205 |
+
"loss": 0.5139,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.12373333333333333,
|
| 210 |
+
"grad_norm": 6.985842704772949,
|
| 211 |
+
"learning_rate": 1.1914893617021278e-06,
|
| 212 |
+
"loss": 0.4903,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.128,
|
| 217 |
+
"grad_norm": 6.07671594619751,
|
| 218 |
+
"learning_rate": 1.2340425531914894e-06,
|
| 219 |
+
"loss": 0.4741,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.13226666666666667,
|
| 224 |
+
"grad_norm": 5.922327995300293,
|
| 225 |
+
"learning_rate": 1.276595744680851e-06,
|
| 226 |
+
"loss": 0.456,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.13653333333333334,
|
| 231 |
+
"grad_norm": 5.909642696380615,
|
| 232 |
+
"learning_rate": 1.3191489361702128e-06,
|
| 233 |
+
"loss": 0.4431,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1408,
|
| 238 |
+
"grad_norm": 5.159115314483643,
|
| 239 |
+
"learning_rate": 1.3617021276595746e-06,
|
| 240 |
+
"loss": 0.4265,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.14506666666666668,
|
| 245 |
+
"grad_norm": 4.204401016235352,
|
| 246 |
+
"learning_rate": 1.4042553191489364e-06,
|
| 247 |
+
"loss": 0.408,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.14933333333333335,
|
| 252 |
+
"grad_norm": 3.8235232830047607,
|
| 253 |
+
"learning_rate": 1.4468085106382978e-06,
|
| 254 |
+
"loss": 0.3929,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1536,
|
| 259 |
+
"grad_norm": 3.8501057624816895,
|
| 260 |
+
"learning_rate": 1.4893617021276596e-06,
|
| 261 |
+
"loss": 0.3837,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.15786666666666666,
|
| 266 |
+
"grad_norm": 4.0237860679626465,
|
| 267 |
+
"learning_rate": 1.5319148936170214e-06,
|
| 268 |
+
"loss": 0.3512,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.16213333333333332,
|
| 273 |
+
"grad_norm": 4.531589031219482,
|
| 274 |
+
"learning_rate": 1.5744680851063832e-06,
|
| 275 |
+
"loss": 0.3299,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.1664,
|
| 280 |
+
"grad_norm": 4.304875373840332,
|
| 281 |
+
"learning_rate": 1.617021276595745e-06,
|
| 282 |
+
"loss": 0.3179,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.17066666666666666,
|
| 287 |
+
"grad_norm": 3.1829235553741455,
|
| 288 |
+
"learning_rate": 1.6595744680851064e-06,
|
| 289 |
+
"loss": 0.3087,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.17493333333333333,
|
| 294 |
+
"grad_norm": 2.890695810317993,
|
| 295 |
+
"learning_rate": 1.7021276595744682e-06,
|
| 296 |
+
"loss": 0.3009,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1792,
|
| 301 |
+
"grad_norm": 3.62577223777771,
|
| 302 |
+
"learning_rate": 1.74468085106383e-06,
|
| 303 |
+
"loss": 0.2926,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.18346666666666667,
|
| 308 |
+
"grad_norm": 3.2570207118988037,
|
| 309 |
+
"learning_rate": 1.7872340425531918e-06,
|
| 310 |
+
"loss": 0.2857,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.18773333333333334,
|
| 315 |
+
"grad_norm": 2.0917487144470215,
|
| 316 |
+
"learning_rate": 1.8297872340425531e-06,
|
| 317 |
+
"loss": 0.2734,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.192,
|
| 322 |
+
"grad_norm": 2.1430346965789795,
|
| 323 |
+
"learning_rate": 1.872340425531915e-06,
|
| 324 |
+
"loss": 0.2669,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.19626666666666667,
|
| 329 |
+
"grad_norm": 2.666980266571045,
|
| 330 |
+
"learning_rate": 1.9148936170212767e-06,
|
| 331 |
+
"loss": 0.2582,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.20053333333333334,
|
| 336 |
+
"grad_norm": 1.869988203048706,
|
| 337 |
+
"learning_rate": 1.9574468085106385e-06,
|
| 338 |
+
"loss": 0.2517,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2048,
|
| 343 |
+
"grad_norm": 2.069547653198242,
|
| 344 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 345 |
+
"loss": 0.2445,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.20906666666666668,
|
| 350 |
+
"grad_norm": 2.0606069564819336,
|
| 351 |
+
"learning_rate": 2.0425531914893617e-06,
|
| 352 |
+
"loss": 0.238,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.21333333333333335,
|
| 357 |
+
"grad_norm": 1.706727147102356,
|
| 358 |
+
"learning_rate": 2.0851063829787235e-06,
|
| 359 |
+
"loss": 0.2335,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2176,
|
| 364 |
+
"grad_norm": 2.278432846069336,
|
| 365 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 366 |
+
"loss": 0.2308,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.22186666666666666,
|
| 371 |
+
"grad_norm": 1.8908629417419434,
|
| 372 |
+
"learning_rate": 2.170212765957447e-06,
|
| 373 |
+
"loss": 0.2262,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.22613333333333333,
|
| 378 |
+
"grad_norm": 1.949669599533081,
|
| 379 |
+
"learning_rate": 2.2127659574468085e-06,
|
| 380 |
+
"loss": 0.219,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2304,
|
| 385 |
+
"grad_norm": 1.920652151107788,
|
| 386 |
+
"learning_rate": 2.2553191489361703e-06,
|
| 387 |
+
"loss": 0.2162,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.23466666666666666,
|
| 392 |
+
"grad_norm": 2.028974771499634,
|
| 393 |
+
"learning_rate": 2.297872340425532e-06,
|
| 394 |
+
"loss": 0.2121,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.23893333333333333,
|
| 399 |
+
"grad_norm": 1.6449410915374756,
|
| 400 |
+
"learning_rate": 2.340425531914894e-06,
|
| 401 |
+
"loss": 0.2078,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2432,
|
| 406 |
+
"grad_norm": 1.5636619329452515,
|
| 407 |
+
"learning_rate": 2.3829787234042557e-06,
|
| 408 |
+
"loss": 0.2003,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.24746666666666667,
|
| 413 |
+
"grad_norm": 1.9496514797210693,
|
| 414 |
+
"learning_rate": 2.425531914893617e-06,
|
| 415 |
+
"loss": 0.1962,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2517333333333333,
|
| 420 |
+
"grad_norm": 1.6503078937530518,
|
| 421 |
+
"learning_rate": 2.468085106382979e-06,
|
| 422 |
+
"loss": 0.1907,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.256,
|
| 427 |
+
"grad_norm": 1.2683771848678589,
|
| 428 |
+
"learning_rate": 2.5106382978723402e-06,
|
| 429 |
+
"loss": 0.1878,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.26026666666666665,
|
| 434 |
+
"grad_norm": 2.003361701965332,
|
| 435 |
+
"learning_rate": 2.553191489361702e-06,
|
| 436 |
+
"loss": 0.1827,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.26453333333333334,
|
| 441 |
+
"grad_norm": 1.4562724828720093,
|
| 442 |
+
"learning_rate": 2.595744680851064e-06,
|
| 443 |
+
"loss": 0.1817,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2688,
|
| 448 |
+
"grad_norm": 2.4795641899108887,
|
| 449 |
+
"learning_rate": 2.6382978723404256e-06,
|
| 450 |
+
"loss": 0.1787,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2730666666666667,
|
| 455 |
+
"grad_norm": 2.1848199367523193,
|
| 456 |
+
"learning_rate": 2.6808510638297874e-06,
|
| 457 |
+
"loss": 0.1759,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2773333333333333,
|
| 462 |
+
"grad_norm": 1.6162073612213135,
|
| 463 |
+
"learning_rate": 2.7234042553191492e-06,
|
| 464 |
+
"loss": 0.1725,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.2816,
|
| 469 |
+
"grad_norm": 3.0534298419952393,
|
| 470 |
+
"learning_rate": 2.765957446808511e-06,
|
| 471 |
+
"loss": 0.169,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.28586666666666666,
|
| 476 |
+
"grad_norm": 1.6378310918807983,
|
| 477 |
+
"learning_rate": 2.808510638297873e-06,
|
| 478 |
+
"loss": 0.1662,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.29013333333333335,
|
| 483 |
+
"grad_norm": 3.190389394760132,
|
| 484 |
+
"learning_rate": 2.8510638297872346e-06,
|
| 485 |
+
"loss": 0.1638,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2944,
|
| 490 |
+
"grad_norm": 2.222900152206421,
|
| 491 |
+
"learning_rate": 2.8936170212765956e-06,
|
| 492 |
+
"loss": 0.1643,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2986666666666667,
|
| 497 |
+
"grad_norm": 2.720613956451416,
|
| 498 |
+
"learning_rate": 2.9361702127659574e-06,
|
| 499 |
+
"loss": 0.16,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.30293333333333333,
|
| 504 |
+
"grad_norm": 2.4706056118011475,
|
| 505 |
+
"learning_rate": 2.978723404255319e-06,
|
| 506 |
+
"loss": 0.1595,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3072,
|
| 511 |
+
"grad_norm": 1.7160310745239258,
|
| 512 |
+
"learning_rate": 3.021276595744681e-06,
|
| 513 |
+
"loss": 0.1579,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.31146666666666667,
|
| 518 |
+
"grad_norm": 3.9026131629943848,
|
| 519 |
+
"learning_rate": 3.0638297872340428e-06,
|
| 520 |
+
"loss": 0.1548,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3157333333333333,
|
| 525 |
+
"grad_norm": 2.223243236541748,
|
| 526 |
+
"learning_rate": 3.1063829787234046e-06,
|
| 527 |
+
"loss": 0.1571,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.32,
|
| 532 |
+
"grad_norm": 3.901400327682495,
|
| 533 |
+
"learning_rate": 3.1489361702127664e-06,
|
| 534 |
+
"loss": 0.1532,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.32426666666666665,
|
| 539 |
+
"grad_norm": 3.2121057510375977,
|
| 540 |
+
"learning_rate": 3.191489361702128e-06,
|
| 541 |
+
"loss": 0.1535,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.32853333333333334,
|
| 546 |
+
"grad_norm": 2.6652214527130127,
|
| 547 |
+
"learning_rate": 3.23404255319149e-06,
|
| 548 |
+
"loss": 0.1513,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3328,
|
| 553 |
+
"grad_norm": 5.308091640472412,
|
| 554 |
+
"learning_rate": 3.276595744680851e-06,
|
| 555 |
+
"loss": 0.1501,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3370666666666667,
|
| 560 |
+
"grad_norm": 4.369630813598633,
|
| 561 |
+
"learning_rate": 3.3191489361702127e-06,
|
| 562 |
+
"loss": 0.1505,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3413333333333333,
|
| 567 |
+
"grad_norm": 4.927572727203369,
|
| 568 |
+
"learning_rate": 3.3617021276595745e-06,
|
| 569 |
+
"loss": 0.1486,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3456,
|
| 574 |
+
"grad_norm": 3.150054931640625,
|
| 575 |
+
"learning_rate": 3.4042553191489363e-06,
|
| 576 |
+
"loss": 0.1488,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.34986666666666666,
|
| 581 |
+
"grad_norm": 6.687278747558594,
|
| 582 |
+
"learning_rate": 3.446808510638298e-06,
|
| 583 |
+
"loss": 0.1467,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.35413333333333336,
|
| 588 |
+
"grad_norm": 5.45517635345459,
|
| 589 |
+
"learning_rate": 3.48936170212766e-06,
|
| 590 |
+
"loss": 0.1468,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3584,
|
| 595 |
+
"grad_norm": 5.900143623352051,
|
| 596 |
+
"learning_rate": 3.5319148936170217e-06,
|
| 597 |
+
"loss": 0.1457,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3626666666666667,
|
| 602 |
+
"grad_norm": 6.59785795211792,
|
| 603 |
+
"learning_rate": 3.5744680851063835e-06,
|
| 604 |
+
"loss": 0.1479,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.36693333333333333,
|
| 609 |
+
"grad_norm": 3.661660671234131,
|
| 610 |
+
"learning_rate": 3.6170212765957453e-06,
|
| 611 |
+
"loss": 0.1436,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3712,
|
| 616 |
+
"grad_norm": 4.646217346191406,
|
| 617 |
+
"learning_rate": 3.6595744680851063e-06,
|
| 618 |
+
"loss": 0.1431,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.37546666666666667,
|
| 623 |
+
"grad_norm": 3.3780157566070557,
|
| 624 |
+
"learning_rate": 3.702127659574468e-06,
|
| 625 |
+
"loss": 0.1426,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3797333333333333,
|
| 630 |
+
"grad_norm": 4.596078395843506,
|
| 631 |
+
"learning_rate": 3.74468085106383e-06,
|
| 632 |
+
"loss": 0.1422,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.384,
|
| 637 |
+
"grad_norm": 3.384758949279785,
|
| 638 |
+
"learning_rate": 3.7872340425531917e-06,
|
| 639 |
+
"loss": 0.1399,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.38826666666666665,
|
| 644 |
+
"grad_norm": 6.492227077484131,
|
| 645 |
+
"learning_rate": 3.8297872340425535e-06,
|
| 646 |
+
"loss": 0.1408,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.39253333333333335,
|
| 651 |
+
"grad_norm": 4.704247951507568,
|
| 652 |
+
"learning_rate": 3.872340425531915e-06,
|
| 653 |
+
"loss": 0.1392,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3968,
|
| 658 |
+
"grad_norm": 7.741692543029785,
|
| 659 |
+
"learning_rate": 3.914893617021277e-06,
|
| 660 |
+
"loss": 0.1413,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4010666666666667,
|
| 665 |
+
"grad_norm": 8.09485149383545,
|
| 666 |
+
"learning_rate": 3.957446808510639e-06,
|
| 667 |
+
"loss": 0.1433,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.4053333333333333,
|
| 672 |
+
"grad_norm": 2.9961678981781006,
|
| 673 |
+
"learning_rate": 4.000000000000001e-06,
|
| 674 |
+
"loss": 0.1381,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.4096,
|
| 679 |
+
"grad_norm": 4.540401935577393,
|
| 680 |
+
"learning_rate": 4.042553191489362e-06,
|
| 681 |
+
"loss": 0.1376,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.41386666666666666,
|
| 686 |
+
"grad_norm": 4.068235397338867,
|
| 687 |
+
"learning_rate": 4.085106382978723e-06,
|
| 688 |
+
"loss": 0.1369,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.41813333333333336,
|
| 693 |
+
"grad_norm": 3.181708812713623,
|
| 694 |
+
"learning_rate": 4.127659574468085e-06,
|
| 695 |
+
"loss": 0.1352,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4224,
|
| 700 |
+
"grad_norm": 4.561326026916504,
|
| 701 |
+
"learning_rate": 4.170212765957447e-06,
|
| 702 |
+
"loss": 0.1358,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4266666666666667,
|
| 707 |
+
"grad_norm": 3.7372615337371826,
|
| 708 |
+
"learning_rate": 4.212765957446809e-06,
|
| 709 |
+
"loss": 0.1338,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.43093333333333333,
|
| 714 |
+
"grad_norm": 6.206492900848389,
|
| 715 |
+
"learning_rate": 4.255319148936171e-06,
|
| 716 |
+
"loss": 0.1376,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4352,
|
| 721 |
+
"grad_norm": 4.748600006103516,
|
| 722 |
+
"learning_rate": 4.297872340425532e-06,
|
| 723 |
+
"loss": 0.1353,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.43946666666666667,
|
| 728 |
+
"grad_norm": 8.013435363769531,
|
| 729 |
+
"learning_rate": 4.340425531914894e-06,
|
| 730 |
+
"loss": 0.136,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4437333333333333,
|
| 735 |
+
"grad_norm": 7.1991190910339355,
|
| 736 |
+
"learning_rate": 4.382978723404256e-06,
|
| 737 |
+
"loss": 0.137,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.448,
|
| 742 |
+
"grad_norm": 4.625593185424805,
|
| 743 |
+
"learning_rate": 4.425531914893617e-06,
|
| 744 |
+
"loss": 0.1319,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.45226666666666665,
|
| 749 |
+
"grad_norm": 4.910801887512207,
|
| 750 |
+
"learning_rate": 4.468085106382979e-06,
|
| 751 |
+
"loss": 0.134,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.45653333333333335,
|
| 756 |
+
"grad_norm": 6.377923488616943,
|
| 757 |
+
"learning_rate": 4.5106382978723406e-06,
|
| 758 |
+
"loss": 0.1342,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4608,
|
| 763 |
+
"grad_norm": 5.0228986740112305,
|
| 764 |
+
"learning_rate": 4.553191489361702e-06,
|
| 765 |
+
"loss": 0.1343,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4650666666666667,
|
| 770 |
+
"grad_norm": 6.513828754425049,
|
| 771 |
+
"learning_rate": 4.595744680851064e-06,
|
| 772 |
+
"loss": 0.1308,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4693333333333333,
|
| 777 |
+
"grad_norm": 5.182156085968018,
|
| 778 |
+
"learning_rate": 4.638297872340426e-06,
|
| 779 |
+
"loss": 0.1324,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4736,
|
| 784 |
+
"grad_norm": 6.711518287658691,
|
| 785 |
+
"learning_rate": 4.680851063829788e-06,
|
| 786 |
+
"loss": 0.1327,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.47786666666666666,
|
| 791 |
+
"grad_norm": 5.540736198425293,
|
| 792 |
+
"learning_rate": 4.7234042553191496e-06,
|
| 793 |
+
"loss": 0.1316,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.48213333333333336,
|
| 798 |
+
"grad_norm": 5.925957202911377,
|
| 799 |
+
"learning_rate": 4.765957446808511e-06,
|
| 800 |
+
"loss": 0.1302,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4864,
|
| 805 |
+
"grad_norm": 5.579200744628906,
|
| 806 |
+
"learning_rate": 4.808510638297872e-06,
|
| 807 |
+
"loss": 0.131,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.49066666666666664,
|
| 812 |
+
"grad_norm": 4.405421733856201,
|
| 813 |
+
"learning_rate": 4.851063829787234e-06,
|
| 814 |
+
"loss": 0.1296,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.49493333333333334,
|
| 819 |
+
"grad_norm": 5.265398025512695,
|
| 820 |
+
"learning_rate": 4.893617021276596e-06,
|
| 821 |
+
"loss": 0.1291,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.4992,
|
| 826 |
+
"grad_norm": 3.860846519470215,
|
| 827 |
+
"learning_rate": 4.936170212765958e-06,
|
| 828 |
+
"loss": 0.1303,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5034666666666666,
|
| 833 |
+
"grad_norm": 2.226341724395752,
|
| 834 |
+
"learning_rate": 4.9787234042553195e-06,
|
| 835 |
+
"loss": 0.1256,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5077333333333334,
|
| 840 |
+
"grad_norm": 8.795147895812988,
|
| 841 |
+
"learning_rate": 5.0212765957446805e-06,
|
| 842 |
+
"loss": 0.1305,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.512,
|
| 847 |
+
"grad_norm": 4.675596714019775,
|
| 848 |
+
"learning_rate": 5.063829787234042e-06,
|
| 849 |
+
"loss": 0.1295,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5162666666666667,
|
| 854 |
+
"grad_norm": 11.608587265014648,
|
| 855 |
+
"learning_rate": 5.106382978723404e-06,
|
| 856 |
+
"loss": 0.1315,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5205333333333333,
|
| 861 |
+
"grad_norm": 11.548611640930176,
|
| 862 |
+
"learning_rate": 5.148936170212766e-06,
|
| 863 |
+
"loss": 0.1354,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5248,
|
| 868 |
+
"grad_norm": 4.825727462768555,
|
| 869 |
+
"learning_rate": 5.191489361702128e-06,
|
| 870 |
+
"loss": 0.1299,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5290666666666667,
|
| 875 |
+
"grad_norm": 7.2229413986206055,
|
| 876 |
+
"learning_rate": 5.2340425531914895e-06,
|
| 877 |
+
"loss": 0.1306,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5333333333333333,
|
| 882 |
+
"grad_norm": 6.224844932556152,
|
| 883 |
+
"learning_rate": 5.276595744680851e-06,
|
| 884 |
+
"loss": 0.1332,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5376,
|
| 889 |
+
"grad_norm": 5.247742652893066,
|
| 890 |
+
"learning_rate": 5.319148936170213e-06,
|
| 891 |
+
"loss": 0.1277,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5418666666666667,
|
| 896 |
+
"grad_norm": 7.463538646697998,
|
| 897 |
+
"learning_rate": 5.361702127659575e-06,
|
| 898 |
+
"loss": 0.1313,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5461333333333334,
|
| 903 |
+
"grad_norm": 5.209482192993164,
|
| 904 |
+
"learning_rate": 5.404255319148937e-06,
|
| 905 |
+
"loss": 0.1304,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5504,
|
| 910 |
+
"grad_norm": 7.131233215332031,
|
| 911 |
+
"learning_rate": 5.4468085106382985e-06,
|
| 912 |
+
"loss": 0.1283,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5546666666666666,
|
| 917 |
+
"grad_norm": 5.096197128295898,
|
| 918 |
+
"learning_rate": 5.48936170212766e-06,
|
| 919 |
+
"loss": 0.1314,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5589333333333333,
|
| 924 |
+
"grad_norm": 8.022686004638672,
|
| 925 |
+
"learning_rate": 5.531914893617022e-06,
|
| 926 |
+
"loss": 0.1287,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5632,
|
| 931 |
+
"grad_norm": 5.0473175048828125,
|
| 932 |
+
"learning_rate": 5.574468085106384e-06,
|
| 933 |
+
"loss": 0.129,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5674666666666667,
|
| 938 |
+
"grad_norm": 8.857738494873047,
|
| 939 |
+
"learning_rate": 5.617021276595746e-06,
|
| 940 |
+
"loss": 0.1288,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5717333333333333,
|
| 945 |
+
"grad_norm": 5.748481750488281,
|
| 946 |
+
"learning_rate": 5.6595744680851075e-06,
|
| 947 |
+
"loss": 0.1298,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.576,
|
| 952 |
+
"grad_norm": 9.72546100616455,
|
| 953 |
+
"learning_rate": 5.702127659574469e-06,
|
| 954 |
+
"loss": 0.1283,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5802666666666667,
|
| 959 |
+
"grad_norm": 7.091835975646973,
|
| 960 |
+
"learning_rate": 5.744680851063831e-06,
|
| 961 |
+
"loss": 0.1286,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5845333333333333,
|
| 966 |
+
"grad_norm": 10.19481372833252,
|
| 967 |
+
"learning_rate": 5.787234042553191e-06,
|
| 968 |
+
"loss": 0.1311,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5888,
|
| 973 |
+
"grad_norm": 9.936722755432129,
|
| 974 |
+
"learning_rate": 5.829787234042553e-06,
|
| 975 |
+
"loss": 0.1273,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5930666666666666,
|
| 980 |
+
"grad_norm": 5.595465183258057,
|
| 981 |
+
"learning_rate": 5.872340425531915e-06,
|
| 982 |
+
"loss": 0.1242,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5973333333333334,
|
| 987 |
+
"grad_norm": 5.289859771728516,
|
| 988 |
+
"learning_rate": 5.9148936170212766e-06,
|
| 989 |
+
"loss": 0.1242,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6016,
|
| 994 |
+
"grad_norm": 8.406579971313477,
|
| 995 |
+
"learning_rate": 5.957446808510638e-06,
|
| 996 |
+
"loss": 0.1251,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6058666666666667,
|
| 1001 |
+
"grad_norm": 6.704819679260254,
|
| 1002 |
+
"learning_rate": 6e-06,
|
| 1003 |
+
"loss": 0.1255,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6101333333333333,
|
| 1008 |
+
"grad_norm": 9.0625,
|
| 1009 |
+
"learning_rate": 6.042553191489362e-06,
|
| 1010 |
+
"loss": 0.1255,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6144,
|
| 1015 |
+
"grad_norm": 8.436838150024414,
|
| 1016 |
+
"learning_rate": 6.085106382978724e-06,
|
| 1017 |
+
"loss": 0.1247,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.6186666666666667,
|
| 1022 |
+
"grad_norm": 7.0138630867004395,
|
| 1023 |
+
"learning_rate": 6.1276595744680855e-06,
|
| 1024 |
+
"loss": 0.1268,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6229333333333333,
|
| 1029 |
+
"grad_norm": 6.2439117431640625,
|
| 1030 |
+
"learning_rate": 6.170212765957447e-06,
|
| 1031 |
+
"loss": 0.1231,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6272,
|
| 1036 |
+
"grad_norm": 8.84973430633545,
|
| 1037 |
+
"learning_rate": 6.212765957446809e-06,
|
| 1038 |
+
"loss": 0.1255,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.6314666666666666,
|
| 1043 |
+
"grad_norm": 7.984808921813965,
|
| 1044 |
+
"learning_rate": 6.255319148936171e-06,
|
| 1045 |
+
"loss": 0.1238,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6357333333333334,
|
| 1050 |
+
"grad_norm": 6.803660869598389,
|
| 1051 |
+
"learning_rate": 6.297872340425533e-06,
|
| 1052 |
+
"loss": 0.1226,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.64,
|
| 1057 |
+
"grad_norm": 5.848384380340576,
|
| 1058 |
+
"learning_rate": 6.3404255319148945e-06,
|
| 1059 |
+
"loss": 0.1224,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6442666666666667,
|
| 1064 |
+
"grad_norm": 8.635106086730957,
|
| 1065 |
+
"learning_rate": 6.382978723404256e-06,
|
| 1066 |
+
"loss": 0.1232,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6485333333333333,
|
| 1071 |
+
"grad_norm": 7.334502220153809,
|
| 1072 |
+
"learning_rate": 6.425531914893618e-06,
|
| 1073 |
+
"loss": 0.1235,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6528,
|
| 1078 |
+
"grad_norm": 7.256570816040039,
|
| 1079 |
+
"learning_rate": 6.46808510638298e-06,
|
| 1080 |
+
"loss": 0.1235,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6570666666666667,
|
| 1085 |
+
"grad_norm": 6.407953262329102,
|
| 1086 |
+
"learning_rate": 6.510638297872342e-06,
|
| 1087 |
+
"loss": 0.122,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6613333333333333,
|
| 1092 |
+
"grad_norm": 8.223788261413574,
|
| 1093 |
+
"learning_rate": 6.553191489361702e-06,
|
| 1094 |
+
"loss": 0.124,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6656,
|
| 1099 |
+
"grad_norm": 6.739434242248535,
|
| 1100 |
+
"learning_rate": 6.595744680851064e-06,
|
| 1101 |
+
"loss": 0.123,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6698666666666667,
|
| 1106 |
+
"grad_norm": 7.93510103225708,
|
| 1107 |
+
"learning_rate": 6.6382978723404254e-06,
|
| 1108 |
+
"loss": 0.123,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6741333333333334,
|
| 1113 |
+
"grad_norm": 7.154916763305664,
|
| 1114 |
+
"learning_rate": 6.680851063829787e-06,
|
| 1115 |
+
"loss": 0.1221,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6784,
|
| 1120 |
+
"grad_norm": 6.691060543060303,
|
| 1121 |
+
"learning_rate": 6.723404255319149e-06,
|
| 1122 |
+
"loss": 0.1225,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6826666666666666,
|
| 1127 |
+
"grad_norm": 5.641987323760986,
|
| 1128 |
+
"learning_rate": 6.765957446808511e-06,
|
| 1129 |
+
"loss": 0.1208,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6869333333333333,
|
| 1134 |
+
"grad_norm": 7.909478187561035,
|
| 1135 |
+
"learning_rate": 6.808510638297873e-06,
|
| 1136 |
+
"loss": 0.1229,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6912,
|
| 1141 |
+
"grad_norm": 6.212748050689697,
|
| 1142 |
+
"learning_rate": 6.8510638297872344e-06,
|
| 1143 |
+
"loss": 0.1201,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6954666666666667,
|
| 1148 |
+
"grad_norm": 7.641393661499023,
|
| 1149 |
+
"learning_rate": 6.893617021276596e-06,
|
| 1150 |
+
"loss": 0.1215,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6997333333333333,
|
| 1155 |
+
"grad_norm": 6.818618297576904,
|
| 1156 |
+
"learning_rate": 6.936170212765958e-06,
|
| 1157 |
+
"loss": 0.1212,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.704,
|
| 1162 |
+
"grad_norm": 6.080795764923096,
|
| 1163 |
+
"learning_rate": 6.97872340425532e-06,
|
| 1164 |
+
"loss": 0.1204,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7082666666666667,
|
| 1169 |
+
"grad_norm": 5.294103145599365,
|
| 1170 |
+
"learning_rate": 7.021276595744682e-06,
|
| 1171 |
+
"loss": 0.12,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7125333333333334,
|
| 1176 |
+
"grad_norm": 7.565417289733887,
|
| 1177 |
+
"learning_rate": 7.0638297872340434e-06,
|
| 1178 |
+
"loss": 0.1209,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7168,
|
| 1183 |
+
"grad_norm": 6.280045509338379,
|
| 1184 |
+
"learning_rate": 7.106382978723405e-06,
|
| 1185 |
+
"loss": 0.1212,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7210666666666666,
|
| 1190 |
+
"grad_norm": 6.898222923278809,
|
| 1191 |
+
"learning_rate": 7.148936170212767e-06,
|
| 1192 |
+
"loss": 0.1206,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.7253333333333334,
|
| 1197 |
+
"grad_norm": 6.254840850830078,
|
| 1198 |
+
"learning_rate": 7.191489361702129e-06,
|
| 1199 |
+
"loss": 0.1203,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.7296,
|
| 1204 |
+
"grad_norm": 6.527096748352051,
|
| 1205 |
+
"learning_rate": 7.234042553191491e-06,
|
| 1206 |
+
"loss": 0.122,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7338666666666667,
|
| 1211 |
+
"grad_norm": 5.724420070648193,
|
| 1212 |
+
"learning_rate": 7.2765957446808524e-06,
|
| 1213 |
+
"loss": 0.1207,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.7381333333333333,
|
| 1218 |
+
"grad_norm": 6.684255123138428,
|
| 1219 |
+
"learning_rate": 7.3191489361702125e-06,
|
| 1220 |
+
"loss": 0.1219,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7424,
|
| 1225 |
+
"grad_norm": 6.503657341003418,
|
| 1226 |
+
"learning_rate": 7.361702127659574e-06,
|
| 1227 |
+
"loss": 0.1178,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7466666666666667,
|
| 1232 |
+
"grad_norm": 5.723449230194092,
|
| 1233 |
+
"learning_rate": 7.404255319148936e-06,
|
| 1234 |
+
"loss": 0.1199,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7509333333333333,
|
| 1239 |
+
"grad_norm": 4.989058017730713,
|
| 1240 |
+
"learning_rate": 7.446808510638298e-06,
|
| 1241 |
+
"loss": 0.1181,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7552,
|
| 1246 |
+
"grad_norm": 7.475578784942627,
|
| 1247 |
+
"learning_rate": 7.48936170212766e-06,
|
| 1248 |
+
"loss": 0.1221,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.7594666666666666,
|
| 1253 |
+
"grad_norm": 6.384317398071289,
|
| 1254 |
+
"learning_rate": 7.5319148936170215e-06,
|
| 1255 |
+
"loss": 0.1193,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7637333333333334,
|
| 1260 |
+
"grad_norm": 5.993687629699707,
|
| 1261 |
+
"learning_rate": 7.574468085106383e-06,
|
| 1262 |
+
"loss": 0.1197,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.768,
|
| 1267 |
+
"grad_norm": 5.651639938354492,
|
| 1268 |
+
"learning_rate": 7.617021276595745e-06,
|
| 1269 |
+
"loss": 0.118,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.7722666666666667,
|
| 1274 |
+
"grad_norm": 5.343756675720215,
|
| 1275 |
+
"learning_rate": 7.659574468085107e-06,
|
| 1276 |
+
"loss": 0.1191,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7765333333333333,
|
| 1281 |
+
"grad_norm": 3.9733238220214844,
|
| 1282 |
+
"learning_rate": 7.702127659574469e-06,
|
| 1283 |
+
"loss": 0.117,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7808,
|
| 1288 |
+
"grad_norm": 8.402620315551758,
|
| 1289 |
+
"learning_rate": 7.74468085106383e-06,
|
| 1290 |
+
"loss": 0.1235,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7850666666666667,
|
| 1295 |
+
"grad_norm": 8.289787292480469,
|
| 1296 |
+
"learning_rate": 7.787234042553192e-06,
|
| 1297 |
+
"loss": 0.121,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7893333333333333,
|
| 1302 |
+
"grad_norm": 3.6568987369537354,
|
| 1303 |
+
"learning_rate": 7.829787234042554e-06,
|
| 1304 |
+
"loss": 0.1174,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7936,
|
| 1309 |
+
"grad_norm": 11.13115119934082,
|
| 1310 |
+
"learning_rate": 7.872340425531916e-06,
|
| 1311 |
+
"loss": 0.1257,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7978666666666666,
|
| 1316 |
+
"grad_norm": 5.116509914398193,
|
| 1317 |
+
"learning_rate": 7.914893617021278e-06,
|
| 1318 |
+
"loss": 0.1195,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.8021333333333334,
|
| 1323 |
+
"grad_norm": 15.565638542175293,
|
| 1324 |
+
"learning_rate": 7.95744680851064e-06,
|
| 1325 |
+
"loss": 0.1417,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.8064,
|
| 1330 |
+
"grad_norm": 16.17276954650879,
|
| 1331 |
+
"learning_rate": 8.000000000000001e-06,
|
| 1332 |
+
"loss": 0.152,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.8106666666666666,
|
| 1337 |
+
"grad_norm": 6.167568206787109,
|
| 1338 |
+
"learning_rate": 8.042553191489363e-06,
|
| 1339 |
+
"loss": 0.1233,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.8149333333333333,
|
| 1344 |
+
"grad_norm": 12.830926895141602,
|
| 1345 |
+
"learning_rate": 8.085106382978723e-06,
|
| 1346 |
+
"loss": 0.1399,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.8192,
|
| 1351 |
+
"grad_norm": 12.8762845993042,
|
| 1352 |
+
"learning_rate": 8.127659574468085e-06,
|
| 1353 |
+
"loss": 0.1521,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.8234666666666667,
|
| 1358 |
+
"grad_norm": 8.177667617797852,
|
| 1359 |
+
"learning_rate": 8.170212765957447e-06,
|
| 1360 |
+
"loss": 0.1298,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8277333333333333,
|
| 1365 |
+
"grad_norm": 6.849120616912842,
|
| 1366 |
+
"learning_rate": 8.212765957446809e-06,
|
| 1367 |
+
"loss": 0.1287,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.832,
|
| 1372 |
+
"grad_norm": 7.727602481842041,
|
| 1373 |
+
"learning_rate": 8.25531914893617e-06,
|
| 1374 |
+
"loss": 0.1332,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.8362666666666667,
|
| 1379 |
+
"grad_norm": 5.658266067504883,
|
| 1380 |
+
"learning_rate": 8.297872340425532e-06,
|
| 1381 |
+
"loss": 0.1278,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.8405333333333334,
|
| 1386 |
+
"grad_norm": 5.271341800689697,
|
| 1387 |
+
"learning_rate": 8.340425531914894e-06,
|
| 1388 |
+
"loss": 0.1254,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.8448,
|
| 1393 |
+
"grad_norm": 5.509979248046875,
|
| 1394 |
+
"learning_rate": 8.382978723404256e-06,
|
| 1395 |
+
"loss": 0.1283,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8490666666666666,
|
| 1400 |
+
"grad_norm": 4.625118732452393,
|
| 1401 |
+
"learning_rate": 8.425531914893618e-06,
|
| 1402 |
+
"loss": 0.1226,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.8533333333333334,
|
| 1407 |
+
"grad_norm": 5.153396129608154,
|
| 1408 |
+
"learning_rate": 8.46808510638298e-06,
|
| 1409 |
+
"loss": 0.1258,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 1,
|
| 1414 |
+
"max_steps": 2350,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 10,
|
| 1417 |
+
"save_steps": 100,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": false
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 5.269690929618354e+18,
|
| 1431 |
+
"train_batch_size": 8,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d76a75bebf3491ba6c0223c474ab435c114b060370b046e532bc0adfccfd23c6
|
| 3 |
+
size 7761
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_kwargs_names": [
|
| 3 |
+
"do_convert_rgb",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"size_divisor",
|
| 7 |
+
"default_to_square",
|
| 8 |
+
"resample",
|
| 9 |
+
"do_rescale",
|
| 10 |
+
"rescale_factor",
|
| 11 |
+
"do_normalize",
|
| 12 |
+
"image_mean",
|
| 13 |
+
"image_std",
|
| 14 |
+
"do_pad",
|
| 15 |
+
"do_center_crop",
|
| 16 |
+
"crop_size",
|
| 17 |
+
"data_format",
|
| 18 |
+
"input_data_format",
|
| 19 |
+
"device",
|
| 20 |
+
"min_pixels",
|
| 21 |
+
"max_pixels",
|
| 22 |
+
"patch_size",
|
| 23 |
+
"temporal_patch_size",
|
| 24 |
+
"merge_size"
|
| 25 |
+
],
|
| 26 |
+
"crop_size": null,
|
| 27 |
+
"data_format": "channels_first",
|
| 28 |
+
"default_to_square": true,
|
| 29 |
+
"device": null,
|
| 30 |
+
"do_center_crop": null,
|
| 31 |
+
"do_convert_rgb": true,
|
| 32 |
+
"do_normalize": true,
|
| 33 |
+
"do_pad": null,
|
| 34 |
+
"do_rescale": true,
|
| 35 |
+
"do_resize": true,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.48145466,
|
| 38 |
+
0.4578275,
|
| 39 |
+
0.40821073
|
| 40 |
+
],
|
| 41 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 42 |
+
"image_std": [
|
| 43 |
+
0.26862954,
|
| 44 |
+
0.26130258,
|
| 45 |
+
0.27577711
|
| 46 |
+
],
|
| 47 |
+
"input_data_format": null,
|
| 48 |
+
"max_pixels": 12845056,
|
| 49 |
+
"merge_size": 2,
|
| 50 |
+
"min_pixels": 3136,
|
| 51 |
+
"model_valid_processing_keys": [
|
| 52 |
+
"do_convert_rgb",
|
| 53 |
+
"do_resize",
|
| 54 |
+
"size",
|
| 55 |
+
"size_divisor",
|
| 56 |
+
"default_to_square",
|
| 57 |
+
"resample",
|
| 58 |
+
"do_rescale",
|
| 59 |
+
"rescale_factor",
|
| 60 |
+
"do_normalize",
|
| 61 |
+
"image_mean",
|
| 62 |
+
"image_std",
|
| 63 |
+
"do_pad",
|
| 64 |
+
"do_center_crop",
|
| 65 |
+
"crop_size",
|
| 66 |
+
"data_format",
|
| 67 |
+
"input_data_format",
|
| 68 |
+
"device",
|
| 69 |
+
"min_pixels",
|
| 70 |
+
"max_pixels",
|
| 71 |
+
"patch_size",
|
| 72 |
+
"temporal_patch_size",
|
| 73 |
+
"merge_size"
|
| 74 |
+
],
|
| 75 |
+
"patch_size": 14,
|
| 76 |
+
"processor_class": "Qwen2VLProcessor",
|
| 77 |
+
"resample": 3,
|
| 78 |
+
"rescale_factor": 0.00392156862745098,
|
| 79 |
+
"size": {
|
| 80 |
+
"longest_edge": 12845056,
|
| 81 |
+
"shortest_edge": 3136
|
| 82 |
+
},
|
| 83 |
+
"size_divisor": null,
|
| 84 |
+
"temporal_patch_size": 2,
|
| 85 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 86 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|