Add files using upload-large-folder tool
Browse files- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/added_tokens.json +24 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/chat_template.jinja +7 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/preprocessor_config.json +29 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/special_tokens_map.json +31 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/tokenizer_config.json +208 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/trainer_state.json +1434 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/added_tokens.json +24 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/chat_template.jinja +7 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/merges.txt +0 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/preprocessor_config.json +29 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/special_tokens_map.json +31 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/tokenizer_config.json +208 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/trainer_state.json +2134 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/vocab.json +0 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/added_tokens.json +24 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/merges.txt +0 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/vocab.json +0 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-500/merges.txt +0 -0
- experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-500/vocab.json +0 -0
- experiments/Qwen2_5vl_3B_multilayer_distill_AOP_pooling_all_12_10_h100_4_Classifier_Layer12_V5_i_ret_bsz128/special_tokens_map.json +31 -0
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/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 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/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 %}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2_5_VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 1003520,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"max_pixels": 1003520,
|
| 26 |
+
"min_pixels": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/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 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-200/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": 0.2081165452653486,
|
| 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": 0.001040582726326743,
|
| 14 |
+
"grad_norm": 3.268874406814575,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.6993,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002081165452653486,
|
| 21 |
+
"grad_norm": 3.8206846714019775,
|
| 22 |
+
"learning_rate": 5e-06,
|
| 23 |
+
"loss": 0.815,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.003121748178980229,
|
| 28 |
+
"grad_norm": 3.077709436416626,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"loss": 0.758,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.004162330905306972,
|
| 35 |
+
"grad_norm": 2.903688430786133,
|
| 36 |
+
"learning_rate": 1.5e-05,
|
| 37 |
+
"loss": 0.6332,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.005202913631633715,
|
| 42 |
+
"grad_norm": 2.8597545623779297,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.7086,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.006243496357960458,
|
| 49 |
+
"grad_norm": 3.6181485652923584,
|
| 50 |
+
"learning_rate": 2.5e-05,
|
| 51 |
+
"loss": 0.8511,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.007284079084287201,
|
| 56 |
+
"grad_norm": 5.016982555389404,
|
| 57 |
+
"learning_rate": 3e-05,
|
| 58 |
+
"loss": 1.0901,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.008324661810613945,
|
| 63 |
+
"grad_norm": 2.217885971069336,
|
| 64 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 65 |
+
"loss": 0.5426,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.009365244536940686,
|
| 70 |
+
"grad_norm": 2.0818731784820557,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.4986,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01040582726326743,
|
| 77 |
+
"grad_norm": 1.9352552890777588,
|
| 78 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 79 |
+
"loss": 0.5358,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.011446409989594173,
|
| 84 |
+
"grad_norm": 3.7815799713134766,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 0.877,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.012486992715920915,
|
| 91 |
+
"grad_norm": 2.989179849624634,
|
| 92 |
+
"learning_rate": 5.5e-05,
|
| 93 |
+
"loss": 0.6389,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.013527575442247659,
|
| 98 |
+
"grad_norm": 3.6533756256103516,
|
| 99 |
+
"learning_rate": 6e-05,
|
| 100 |
+
"loss": 0.7697,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.014568158168574402,
|
| 105 |
+
"grad_norm": 2.5273356437683105,
|
| 106 |
+
"learning_rate": 6.500000000000001e-05,
|
| 107 |
+
"loss": 0.4582,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.015608740894901144,
|
| 112 |
+
"grad_norm": 2.0315494537353516,
|
| 113 |
+
"learning_rate": 7.000000000000001e-05,
|
| 114 |
+
"loss": 0.4683,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.01664932362122789,
|
| 119 |
+
"grad_norm": 1.3862802982330322,
|
| 120 |
+
"learning_rate": 7.5e-05,
|
| 121 |
+
"loss": 0.401,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01768990634755463,
|
| 126 |
+
"grad_norm": 3.2270781993865967,
|
| 127 |
+
"learning_rate": 8e-05,
|
| 128 |
+
"loss": 0.6733,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.018730489073881373,
|
| 133 |
+
"grad_norm": 2.966115713119507,
|
| 134 |
+
"learning_rate": 8.5e-05,
|
| 135 |
+
"loss": 0.6105,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.019771071800208116,
|
| 140 |
+
"grad_norm": 2.720820188522339,
|
| 141 |
+
"learning_rate": 8.999999999999999e-05,
|
| 142 |
+
"loss": 0.5462,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.02081165452653486,
|
| 147 |
+
"grad_norm": 2.2214956283569336,
|
| 148 |
+
"learning_rate": 9.5e-05,
|
| 149 |
+
"loss": 0.5125,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.021852237252861603,
|
| 154 |
+
"grad_norm": 2.2020890712738037,
|
| 155 |
+
"learning_rate": 0.0001,
|
| 156 |
+
"loss": 0.4953,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.022892819979188347,
|
| 161 |
+
"grad_norm": 2.2625033855438232,
|
| 162 |
+
"learning_rate": 0.000105,
|
| 163 |
+
"loss": 0.5628,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.023933402705515087,
|
| 168 |
+
"grad_norm": 2.223475933074951,
|
| 169 |
+
"learning_rate": 0.00011,
|
| 170 |
+
"loss": 0.5667,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.02497398543184183,
|
| 175 |
+
"grad_norm": 2.982874631881714,
|
| 176 |
+
"learning_rate": 0.000115,
|
| 177 |
+
"loss": 0.6645,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.026014568158168574,
|
| 182 |
+
"grad_norm": 2.5550947189331055,
|
| 183 |
+
"learning_rate": 0.00012,
|
| 184 |
+
"loss": 0.4668,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.027055150884495317,
|
| 189 |
+
"grad_norm": 2.805063486099243,
|
| 190 |
+
"learning_rate": 0.000125,
|
| 191 |
+
"loss": 0.5205,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.02809573361082206,
|
| 196 |
+
"grad_norm": 1.7745788097381592,
|
| 197 |
+
"learning_rate": 0.00013000000000000002,
|
| 198 |
+
"loss": 0.3622,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.029136316337148804,
|
| 203 |
+
"grad_norm": 1.6776342391967773,
|
| 204 |
+
"learning_rate": 0.000135,
|
| 205 |
+
"loss": 0.3641,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.030176899063475548,
|
| 210 |
+
"grad_norm": 2.4569647312164307,
|
| 211 |
+
"learning_rate": 0.00014000000000000001,
|
| 212 |
+
"loss": 0.5263,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.031217481789802288,
|
| 217 |
+
"grad_norm": 1.2685638666152954,
|
| 218 |
+
"learning_rate": 0.000145,
|
| 219 |
+
"loss": 0.3199,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.03225806451612903,
|
| 224 |
+
"grad_norm": 1.3093715906143188,
|
| 225 |
+
"learning_rate": 0.00015,
|
| 226 |
+
"loss": 0.4389,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.03329864724245578,
|
| 231 |
+
"grad_norm": 1.643606185913086,
|
| 232 |
+
"learning_rate": 0.000155,
|
| 233 |
+
"loss": 0.3973,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.03433922996878252,
|
| 238 |
+
"grad_norm": 1.27973473072052,
|
| 239 |
+
"learning_rate": 0.00016,
|
| 240 |
+
"loss": 0.3601,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.03537981269510926,
|
| 245 |
+
"grad_norm": 1.3652054071426392,
|
| 246 |
+
"learning_rate": 0.000165,
|
| 247 |
+
"loss": 0.4557,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.036420395421436005,
|
| 252 |
+
"grad_norm": 1.2647119760513306,
|
| 253 |
+
"learning_rate": 0.00017,
|
| 254 |
+
"loss": 0.3723,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.037460978147762745,
|
| 259 |
+
"grad_norm": 1.2717779874801636,
|
| 260 |
+
"learning_rate": 0.000175,
|
| 261 |
+
"loss": 0.3429,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.03850156087408949,
|
| 266 |
+
"grad_norm": 1.7270296812057495,
|
| 267 |
+
"learning_rate": 0.00017999999999999998,
|
| 268 |
+
"loss": 0.4089,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.03954214360041623,
|
| 273 |
+
"grad_norm": 1.5404200553894043,
|
| 274 |
+
"learning_rate": 0.000185,
|
| 275 |
+
"loss": 0.3764,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.04058272632674298,
|
| 280 |
+
"grad_norm": 1.1958752870559692,
|
| 281 |
+
"learning_rate": 0.00019,
|
| 282 |
+
"loss": 0.375,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.04162330905306972,
|
| 287 |
+
"grad_norm": 1.4304900169372559,
|
| 288 |
+
"learning_rate": 0.00019500000000000002,
|
| 289 |
+
"loss": 0.3802,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.04266389177939646,
|
| 294 |
+
"grad_norm": 1.654426097869873,
|
| 295 |
+
"learning_rate": 0.0002,
|
| 296 |
+
"loss": 0.2566,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.043704474505723206,
|
| 301 |
+
"grad_norm": 1.7565494775772095,
|
| 302 |
+
"learning_rate": 0.000205,
|
| 303 |
+
"loss": 0.3105,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.044745057232049947,
|
| 308 |
+
"grad_norm": 2.055324077606201,
|
| 309 |
+
"learning_rate": 0.00021,
|
| 310 |
+
"loss": 0.3233,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.045785639958376693,
|
| 315 |
+
"grad_norm": 1.283117651939392,
|
| 316 |
+
"learning_rate": 0.000215,
|
| 317 |
+
"loss": 0.3023,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.046826222684703434,
|
| 322 |
+
"grad_norm": 1.292840838432312,
|
| 323 |
+
"learning_rate": 0.00022,
|
| 324 |
+
"loss": 0.2821,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.047866805411030174,
|
| 329 |
+
"grad_norm": 1.0345746278762817,
|
| 330 |
+
"learning_rate": 0.00022500000000000002,
|
| 331 |
+
"loss": 0.2539,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.04890738813735692,
|
| 336 |
+
"grad_norm": 1.0240848064422607,
|
| 337 |
+
"learning_rate": 0.00023,
|
| 338 |
+
"loss": 0.3298,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.04994797086368366,
|
| 343 |
+
"grad_norm": 1.7957828044891357,
|
| 344 |
+
"learning_rate": 0.000235,
|
| 345 |
+
"loss": 0.205,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.05098855359001041,
|
| 350 |
+
"grad_norm": 1.3810360431671143,
|
| 351 |
+
"learning_rate": 0.00024,
|
| 352 |
+
"loss": 0.2919,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.05202913631633715,
|
| 357 |
+
"grad_norm": 0.8331364393234253,
|
| 358 |
+
"learning_rate": 0.000245,
|
| 359 |
+
"loss": 0.1943,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.053069719042663895,
|
| 364 |
+
"grad_norm": 1.213149070739746,
|
| 365 |
+
"learning_rate": 0.00025,
|
| 366 |
+
"loss": 0.3011,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.054110301768990635,
|
| 371 |
+
"grad_norm": 0.9544571042060852,
|
| 372 |
+
"learning_rate": 0.000255,
|
| 373 |
+
"loss": 0.3511,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.055150884495317375,
|
| 378 |
+
"grad_norm": 0.9204476475715637,
|
| 379 |
+
"learning_rate": 0.00026000000000000003,
|
| 380 |
+
"loss": 0.2048,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.05619146722164412,
|
| 385 |
+
"grad_norm": 1.7272144556045532,
|
| 386 |
+
"learning_rate": 0.00026500000000000004,
|
| 387 |
+
"loss": 0.2715,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.05723204994797086,
|
| 392 |
+
"grad_norm": 0.891767680644989,
|
| 393 |
+
"learning_rate": 0.00027,
|
| 394 |
+
"loss": 0.2116,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.05827263267429761,
|
| 399 |
+
"grad_norm": 0.8020220398902893,
|
| 400 |
+
"learning_rate": 0.000275,
|
| 401 |
+
"loss": 0.2101,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.05931321540062435,
|
| 406 |
+
"grad_norm": 1.2897636890411377,
|
| 407 |
+
"learning_rate": 0.00028000000000000003,
|
| 408 |
+
"loss": 0.242,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.060353798126951096,
|
| 413 |
+
"grad_norm": 2.2333452701568604,
|
| 414 |
+
"learning_rate": 0.000285,
|
| 415 |
+
"loss": 0.3461,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.061394380853277836,
|
| 420 |
+
"grad_norm": 1.124709963798523,
|
| 421 |
+
"learning_rate": 0.00029,
|
| 422 |
+
"loss": 0.1709,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.062434963579604576,
|
| 427 |
+
"grad_norm": 0.7170735001564026,
|
| 428 |
+
"learning_rate": 0.000295,
|
| 429 |
+
"loss": 0.1954,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.06347554630593132,
|
| 434 |
+
"grad_norm": 1.3257620334625244,
|
| 435 |
+
"learning_rate": 0.0003,
|
| 436 |
+
"loss": 0.2816,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.06451612903225806,
|
| 441 |
+
"grad_norm": 0.7642104029655457,
|
| 442 |
+
"learning_rate": 0.000305,
|
| 443 |
+
"loss": 0.1788,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.06555671175858481,
|
| 448 |
+
"grad_norm": 0.9636558890342712,
|
| 449 |
+
"learning_rate": 0.00031,
|
| 450 |
+
"loss": 0.2138,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.06659729448491156,
|
| 455 |
+
"grad_norm": 0.7231699228286743,
|
| 456 |
+
"learning_rate": 0.000315,
|
| 457 |
+
"loss": 0.19,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.06763787721123829,
|
| 462 |
+
"grad_norm": 0.9044433236122131,
|
| 463 |
+
"learning_rate": 0.00032,
|
| 464 |
+
"loss": 0.1863,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.06867845993756504,
|
| 469 |
+
"grad_norm": 0.6787164807319641,
|
| 470 |
+
"learning_rate": 0.00032500000000000004,
|
| 471 |
+
"loss": 0.1615,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.06971904266389178,
|
| 476 |
+
"grad_norm": 0.6610997915267944,
|
| 477 |
+
"learning_rate": 0.00033,
|
| 478 |
+
"loss": 0.1777,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.07075962539021852,
|
| 483 |
+
"grad_norm": 0.8359801173210144,
|
| 484 |
+
"learning_rate": 0.000335,
|
| 485 |
+
"loss": 0.238,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.07180020811654526,
|
| 490 |
+
"grad_norm": 0.7294996976852417,
|
| 491 |
+
"learning_rate": 0.00034,
|
| 492 |
+
"loss": 0.2018,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.07284079084287201,
|
| 497 |
+
"grad_norm": 0.7325947880744934,
|
| 498 |
+
"learning_rate": 0.000345,
|
| 499 |
+
"loss": 0.1372,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.07388137356919876,
|
| 504 |
+
"grad_norm": 0.7132765650749207,
|
| 505 |
+
"learning_rate": 0.00035,
|
| 506 |
+
"loss": 0.1951,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.07492195629552549,
|
| 511 |
+
"grad_norm": 1.1800177097320557,
|
| 512 |
+
"learning_rate": 0.000355,
|
| 513 |
+
"loss": 0.2546,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.07596253902185224,
|
| 518 |
+
"grad_norm": 1.0050599575042725,
|
| 519 |
+
"learning_rate": 0.00035999999999999997,
|
| 520 |
+
"loss": 0.189,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.07700312174817898,
|
| 525 |
+
"grad_norm": 0.7532162070274353,
|
| 526 |
+
"learning_rate": 0.000365,
|
| 527 |
+
"loss": 0.1276,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.07804370447450572,
|
| 532 |
+
"grad_norm": 0.8199287056922913,
|
| 533 |
+
"learning_rate": 0.00037,
|
| 534 |
+
"loss": 0.2116,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.07908428720083246,
|
| 539 |
+
"grad_norm": 0.8740005493164062,
|
| 540 |
+
"learning_rate": 0.000375,
|
| 541 |
+
"loss": 0.1754,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.08012486992715921,
|
| 546 |
+
"grad_norm": 0.6971861124038696,
|
| 547 |
+
"learning_rate": 0.00038,
|
| 548 |
+
"loss": 0.1799,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.08116545265348596,
|
| 553 |
+
"grad_norm": 0.6992635726928711,
|
| 554 |
+
"learning_rate": 0.00038500000000000003,
|
| 555 |
+
"loss": 0.1663,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.08220603537981269,
|
| 560 |
+
"grad_norm": 0.8527954816818237,
|
| 561 |
+
"learning_rate": 0.00039000000000000005,
|
| 562 |
+
"loss": 0.1676,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.08324661810613944,
|
| 567 |
+
"grad_norm": 0.7233165502548218,
|
| 568 |
+
"learning_rate": 0.000395,
|
| 569 |
+
"loss": 0.1635,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.08428720083246619,
|
| 574 |
+
"grad_norm": 1.2006125450134277,
|
| 575 |
+
"learning_rate": 0.0004,
|
| 576 |
+
"loss": 0.1902,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.08532778355879292,
|
| 581 |
+
"grad_norm": 0.6341950297355652,
|
| 582 |
+
"learning_rate": 0.00040500000000000003,
|
| 583 |
+
"loss": 0.1396,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.08636836628511967,
|
| 588 |
+
"grad_norm": 0.670028030872345,
|
| 589 |
+
"learning_rate": 0.00041,
|
| 590 |
+
"loss": 0.162,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.08740894901144641,
|
| 595 |
+
"grad_norm": 0.6362585425376892,
|
| 596 |
+
"learning_rate": 0.000415,
|
| 597 |
+
"loss": 0.155,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.08844953173777315,
|
| 602 |
+
"grad_norm": 0.7975156307220459,
|
| 603 |
+
"learning_rate": 0.00042,
|
| 604 |
+
"loss": 0.1264,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.08949011446409989,
|
| 609 |
+
"grad_norm": 0.5603007078170776,
|
| 610 |
+
"learning_rate": 0.000425,
|
| 611 |
+
"loss": 0.1505,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.09053069719042664,
|
| 616 |
+
"grad_norm": 0.515308141708374,
|
| 617 |
+
"learning_rate": 0.00043,
|
| 618 |
+
"loss": 0.1364,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.09157127991675339,
|
| 623 |
+
"grad_norm": 0.6081110239028931,
|
| 624 |
+
"learning_rate": 0.000435,
|
| 625 |
+
"loss": 0.1428,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.09261186264308012,
|
| 630 |
+
"grad_norm": 0.5383463501930237,
|
| 631 |
+
"learning_rate": 0.00044,
|
| 632 |
+
"loss": 0.1293,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.09365244536940687,
|
| 637 |
+
"grad_norm": 0.659436047077179,
|
| 638 |
+
"learning_rate": 0.00044500000000000003,
|
| 639 |
+
"loss": 0.1475,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.09469302809573361,
|
| 644 |
+
"grad_norm": 0.5411190390586853,
|
| 645 |
+
"learning_rate": 0.00045000000000000004,
|
| 646 |
+
"loss": 0.1408,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.09573361082206035,
|
| 651 |
+
"grad_norm": 0.6518479585647583,
|
| 652 |
+
"learning_rate": 0.000455,
|
| 653 |
+
"loss": 0.1576,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.0967741935483871,
|
| 658 |
+
"grad_norm": 0.5494299530982971,
|
| 659 |
+
"learning_rate": 0.00046,
|
| 660 |
+
"loss": 0.1099,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.09781477627471384,
|
| 665 |
+
"grad_norm": 0.8132746815681458,
|
| 666 |
+
"learning_rate": 0.000465,
|
| 667 |
+
"loss": 0.1636,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.09885535900104059,
|
| 672 |
+
"grad_norm": 0.5652503371238708,
|
| 673 |
+
"learning_rate": 0.00047,
|
| 674 |
+
"loss": 0.1595,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.09989594172736732,
|
| 679 |
+
"grad_norm": 0.61795973777771,
|
| 680 |
+
"learning_rate": 0.000475,
|
| 681 |
+
"loss": 0.0745,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.10093652445369407,
|
| 686 |
+
"grad_norm": 0.4944301247596741,
|
| 687 |
+
"learning_rate": 0.00048,
|
| 688 |
+
"loss": 0.1406,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.10197710718002082,
|
| 693 |
+
"grad_norm": 0.5052417516708374,
|
| 694 |
+
"learning_rate": 0.00048499999999999997,
|
| 695 |
+
"loss": 0.104,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.10301768990634755,
|
| 700 |
+
"grad_norm": 0.46198371052742004,
|
| 701 |
+
"learning_rate": 0.00049,
|
| 702 |
+
"loss": 0.0883,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.1040582726326743,
|
| 707 |
+
"grad_norm": 0.6346387267112732,
|
| 708 |
+
"learning_rate": 0.000495,
|
| 709 |
+
"loss": 0.154,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.10509885535900104,
|
| 714 |
+
"grad_norm": 0.4819563925266266,
|
| 715 |
+
"learning_rate": 0.0005,
|
| 716 |
+
"loss": 0.1454,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.10613943808532779,
|
| 721 |
+
"grad_norm": 0.44754841923713684,
|
| 722 |
+
"learning_rate": 0.0004994444444444445,
|
| 723 |
+
"loss": 0.0742,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.10718002081165452,
|
| 728 |
+
"grad_norm": 0.3852291703224182,
|
| 729 |
+
"learning_rate": 0.0004988888888888889,
|
| 730 |
+
"loss": 0.063,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.10822060353798127,
|
| 735 |
+
"grad_norm": 0.572284460067749,
|
| 736 |
+
"learning_rate": 0.0004983333333333334,
|
| 737 |
+
"loss": 0.1434,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.10926118626430802,
|
| 742 |
+
"grad_norm": 0.402413934469223,
|
| 743 |
+
"learning_rate": 0.0004977777777777778,
|
| 744 |
+
"loss": 0.0897,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.11030176899063475,
|
| 749 |
+
"grad_norm": 0.5178724527359009,
|
| 750 |
+
"learning_rate": 0.0004972222222222222,
|
| 751 |
+
"loss": 0.0991,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1113423517169615,
|
| 756 |
+
"grad_norm": 0.5298802852630615,
|
| 757 |
+
"learning_rate": 0.0004966666666666666,
|
| 758 |
+
"loss": 0.1265,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.11238293444328824,
|
| 763 |
+
"grad_norm": 0.5106524229049683,
|
| 764 |
+
"learning_rate": 0.0004961111111111111,
|
| 765 |
+
"loss": 0.076,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.11342351716961499,
|
| 770 |
+
"grad_norm": 0.4718921482563019,
|
| 771 |
+
"learning_rate": 0.0004955555555555556,
|
| 772 |
+
"loss": 0.0927,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.11446409989594172,
|
| 777 |
+
"grad_norm": 0.4144158661365509,
|
| 778 |
+
"learning_rate": 0.000495,
|
| 779 |
+
"loss": 0.1075,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.11550468262226847,
|
| 784 |
+
"grad_norm": 0.44835594296455383,
|
| 785 |
+
"learning_rate": 0.0004944444444444445,
|
| 786 |
+
"loss": 0.1093,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.11654526534859522,
|
| 791 |
+
"grad_norm": 0.6650722622871399,
|
| 792 |
+
"learning_rate": 0.0004938888888888889,
|
| 793 |
+
"loss": 0.1082,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.11758584807492195,
|
| 798 |
+
"grad_norm": 0.40712565183639526,
|
| 799 |
+
"learning_rate": 0.0004933333333333334,
|
| 800 |
+
"loss": 0.0622,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.1186264308012487,
|
| 805 |
+
"grad_norm": 0.5961405634880066,
|
| 806 |
+
"learning_rate": 0.0004927777777777777,
|
| 807 |
+
"loss": 0.1041,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.11966701352757544,
|
| 812 |
+
"grad_norm": 0.4379814863204956,
|
| 813 |
+
"learning_rate": 0.0004922222222222222,
|
| 814 |
+
"loss": 0.1172,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.12070759625390219,
|
| 819 |
+
"grad_norm": 0.4038859009742737,
|
| 820 |
+
"learning_rate": 0.0004916666666666666,
|
| 821 |
+
"loss": 0.083,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.12174817898022892,
|
| 826 |
+
"grad_norm": 0.49663108587265015,
|
| 827 |
+
"learning_rate": 0.0004911111111111111,
|
| 828 |
+
"loss": 0.0732,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.12278876170655567,
|
| 833 |
+
"grad_norm": 0.34757199883461,
|
| 834 |
+
"learning_rate": 0.0004905555555555556,
|
| 835 |
+
"loss": 0.0946,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.12382934443288242,
|
| 840 |
+
"grad_norm": 0.421332448720932,
|
| 841 |
+
"learning_rate": 0.00049,
|
| 842 |
+
"loss": 0.0856,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.12486992715920915,
|
| 847 |
+
"grad_norm": 0.41452690958976746,
|
| 848 |
+
"learning_rate": 0.0004894444444444445,
|
| 849 |
+
"loss": 0.1235,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.1259105098855359,
|
| 854 |
+
"grad_norm": 0.6133429408073425,
|
| 855 |
+
"learning_rate": 0.0004888888888888889,
|
| 856 |
+
"loss": 0.1004,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.12695109261186263,
|
| 861 |
+
"grad_norm": 0.4711684286594391,
|
| 862 |
+
"learning_rate": 0.0004883333333333333,
|
| 863 |
+
"loss": 0.0944,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.1279916753381894,
|
| 868 |
+
"grad_norm": 0.4512624144554138,
|
| 869 |
+
"learning_rate": 0.0004877777777777778,
|
| 870 |
+
"loss": 0.1027,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.12903225806451613,
|
| 875 |
+
"grad_norm": 0.42018765211105347,
|
| 876 |
+
"learning_rate": 0.0004872222222222222,
|
| 877 |
+
"loss": 0.1185,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.13007284079084286,
|
| 882 |
+
"grad_norm": 0.49484384059906006,
|
| 883 |
+
"learning_rate": 0.0004866666666666667,
|
| 884 |
+
"loss": 0.0782,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.13111342351716962,
|
| 889 |
+
"grad_norm": 0.4003879427909851,
|
| 890 |
+
"learning_rate": 0.0004861111111111111,
|
| 891 |
+
"loss": 0.087,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.13215400624349635,
|
| 896 |
+
"grad_norm": 0.5285933017730713,
|
| 897 |
+
"learning_rate": 0.0004855555555555556,
|
| 898 |
+
"loss": 0.078,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.1331945889698231,
|
| 903 |
+
"grad_norm": 0.3752761781215668,
|
| 904 |
+
"learning_rate": 0.00048499999999999997,
|
| 905 |
+
"loss": 0.0792,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.13423517169614985,
|
| 910 |
+
"grad_norm": 0.3410363495349884,
|
| 911 |
+
"learning_rate": 0.00048444444444444446,
|
| 912 |
+
"loss": 0.1107,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.13527575442247658,
|
| 917 |
+
"grad_norm": 0.38146358728408813,
|
| 918 |
+
"learning_rate": 0.0004838888888888889,
|
| 919 |
+
"loss": 0.0894,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.13631633714880334,
|
| 924 |
+
"grad_norm": 0.5861756801605225,
|
| 925 |
+
"learning_rate": 0.00048333333333333334,
|
| 926 |
+
"loss": 0.1187,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.13735691987513007,
|
| 931 |
+
"grad_norm": 0.7138178944587708,
|
| 932 |
+
"learning_rate": 0.0004827777777777778,
|
| 933 |
+
"loss": 0.1242,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.1383975026014568,
|
| 938 |
+
"grad_norm": 0.3060092031955719,
|
| 939 |
+
"learning_rate": 0.0004822222222222222,
|
| 940 |
+
"loss": 0.0721,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.13943808532778357,
|
| 945 |
+
"grad_norm": 0.32948216795921326,
|
| 946 |
+
"learning_rate": 0.0004816666666666667,
|
| 947 |
+
"loss": 0.0814,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1404786680541103,
|
| 952 |
+
"grad_norm": 0.2897670865058899,
|
| 953 |
+
"learning_rate": 0.0004811111111111111,
|
| 954 |
+
"loss": 0.0728,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.14151925078043703,
|
| 959 |
+
"grad_norm": 0.32715317606925964,
|
| 960 |
+
"learning_rate": 0.0004805555555555556,
|
| 961 |
+
"loss": 0.083,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.1425598335067638,
|
| 966 |
+
"grad_norm": 0.28751736879348755,
|
| 967 |
+
"learning_rate": 0.00048,
|
| 968 |
+
"loss": 0.0619,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.14360041623309053,
|
| 973 |
+
"grad_norm": 0.3826645612716675,
|
| 974 |
+
"learning_rate": 0.00047944444444444445,
|
| 975 |
+
"loss": 0.1057,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.14464099895941726,
|
| 980 |
+
"grad_norm": 0.4589000642299652,
|
| 981 |
+
"learning_rate": 0.0004788888888888889,
|
| 982 |
+
"loss": 0.1138,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.14568158168574402,
|
| 987 |
+
"grad_norm": 0.4404071569442749,
|
| 988 |
+
"learning_rate": 0.0004783333333333333,
|
| 989 |
+
"loss": 0.0824,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.14672216441207075,
|
| 994 |
+
"grad_norm": 0.4857710301876068,
|
| 995 |
+
"learning_rate": 0.0004777777777777778,
|
| 996 |
+
"loss": 0.0744,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.14776274713839752,
|
| 1001 |
+
"grad_norm": 0.34489718079566956,
|
| 1002 |
+
"learning_rate": 0.00047722222222222225,
|
| 1003 |
+
"loss": 0.0556,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.14880332986472425,
|
| 1008 |
+
"grad_norm": 0.3448956310749054,
|
| 1009 |
+
"learning_rate": 0.0004766666666666667,
|
| 1010 |
+
"loss": 0.064,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.14984391259105098,
|
| 1015 |
+
"grad_norm": 0.3096216917037964,
|
| 1016 |
+
"learning_rate": 0.0004761111111111111,
|
| 1017 |
+
"loss": 0.0816,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.15088449531737774,
|
| 1022 |
+
"grad_norm": 0.4213986396789551,
|
| 1023 |
+
"learning_rate": 0.00047555555555555556,
|
| 1024 |
+
"loss": 0.1041,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.15192507804370448,
|
| 1029 |
+
"grad_norm": 0.2673068046569824,
|
| 1030 |
+
"learning_rate": 0.000475,
|
| 1031 |
+
"loss": 0.0836,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.1529656607700312,
|
| 1036 |
+
"grad_norm": 0.35139915347099304,
|
| 1037 |
+
"learning_rate": 0.00047444444444444444,
|
| 1038 |
+
"loss": 0.0866,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.15400624349635797,
|
| 1043 |
+
"grad_norm": 0.3168632388114929,
|
| 1044 |
+
"learning_rate": 0.00047388888888888893,
|
| 1045 |
+
"loss": 0.0693,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.1550468262226847,
|
| 1050 |
+
"grad_norm": 0.3259681761264801,
|
| 1051 |
+
"learning_rate": 0.00047333333333333336,
|
| 1052 |
+
"loss": 0.0525,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.15608740894901144,
|
| 1057 |
+
"grad_norm": 0.44802430272102356,
|
| 1058 |
+
"learning_rate": 0.0004727777777777778,
|
| 1059 |
+
"loss": 0.0938,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.1571279916753382,
|
| 1064 |
+
"grad_norm": 0.2723800241947174,
|
| 1065 |
+
"learning_rate": 0.00047222222222222224,
|
| 1066 |
+
"loss": 0.0637,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.15816857440166493,
|
| 1071 |
+
"grad_norm": 0.33274656534194946,
|
| 1072 |
+
"learning_rate": 0.0004716666666666667,
|
| 1073 |
+
"loss": 0.0776,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.15920915712799166,
|
| 1078 |
+
"grad_norm": 0.41862592101097107,
|
| 1079 |
+
"learning_rate": 0.0004711111111111111,
|
| 1080 |
+
"loss": 0.0979,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.16024973985431842,
|
| 1085 |
+
"grad_norm": 0.35577768087387085,
|
| 1086 |
+
"learning_rate": 0.00047055555555555555,
|
| 1087 |
+
"loss": 0.0414,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.16129032258064516,
|
| 1092 |
+
"grad_norm": 0.32270193099975586,
|
| 1093 |
+
"learning_rate": 0.00047,
|
| 1094 |
+
"loss": 0.101,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.16233090530697192,
|
| 1099 |
+
"grad_norm": 0.2666638493537903,
|
| 1100 |
+
"learning_rate": 0.0004694444444444445,
|
| 1101 |
+
"loss": 0.0689,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.16337148803329865,
|
| 1106 |
+
"grad_norm": 0.20294290781021118,
|
| 1107 |
+
"learning_rate": 0.0004688888888888889,
|
| 1108 |
+
"loss": 0.0533,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.16441207075962538,
|
| 1113 |
+
"grad_norm": 0.3359270989894867,
|
| 1114 |
+
"learning_rate": 0.00046833333333333335,
|
| 1115 |
+
"loss": 0.0817,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.16545265348595214,
|
| 1120 |
+
"grad_norm": 0.44312432408332825,
|
| 1121 |
+
"learning_rate": 0.0004677777777777778,
|
| 1122 |
+
"loss": 0.0862,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.16649323621227888,
|
| 1127 |
+
"grad_norm": 0.24581390619277954,
|
| 1128 |
+
"learning_rate": 0.0004672222222222222,
|
| 1129 |
+
"loss": 0.0585,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1675338189386056,
|
| 1134 |
+
"grad_norm": 0.25939878821372986,
|
| 1135 |
+
"learning_rate": 0.00046666666666666666,
|
| 1136 |
+
"loss": 0.0737,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.16857440166493237,
|
| 1141 |
+
"grad_norm": 0.212020605802536,
|
| 1142 |
+
"learning_rate": 0.0004661111111111111,
|
| 1143 |
+
"loss": 0.0487,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.1696149843912591,
|
| 1148 |
+
"grad_norm": 0.30007174611091614,
|
| 1149 |
+
"learning_rate": 0.0004655555555555556,
|
| 1150 |
+
"loss": 0.0695,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.17065556711758584,
|
| 1155 |
+
"grad_norm": 0.2842208445072174,
|
| 1156 |
+
"learning_rate": 0.000465,
|
| 1157 |
+
"loss": 0.0612,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.1716961498439126,
|
| 1162 |
+
"grad_norm": 0.2660129964351654,
|
| 1163 |
+
"learning_rate": 0.00046444444444444446,
|
| 1164 |
+
"loss": 0.0557,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.17273673257023933,
|
| 1169 |
+
"grad_norm": 0.3331991732120514,
|
| 1170 |
+
"learning_rate": 0.0004638888888888889,
|
| 1171 |
+
"loss": 0.0676,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.17377731529656607,
|
| 1176 |
+
"grad_norm": 0.2525298297405243,
|
| 1177 |
+
"learning_rate": 0.00046333333333333334,
|
| 1178 |
+
"loss": 0.0552,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.17481789802289283,
|
| 1183 |
+
"grad_norm": 0.2903599739074707,
|
| 1184 |
+
"learning_rate": 0.0004627777777777778,
|
| 1185 |
+
"loss": 0.0823,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.17585848074921956,
|
| 1190 |
+
"grad_norm": 0.25501200556755066,
|
| 1191 |
+
"learning_rate": 0.0004622222222222222,
|
| 1192 |
+
"loss": 0.0529,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.1768990634755463,
|
| 1197 |
+
"grad_norm": 0.27259787917137146,
|
| 1198 |
+
"learning_rate": 0.0004616666666666667,
|
| 1199 |
+
"loss": 0.0635,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.17793964620187305,
|
| 1204 |
+
"grad_norm": 0.22791972756385803,
|
| 1205 |
+
"learning_rate": 0.00046111111111111114,
|
| 1206 |
+
"loss": 0.0608,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.17898022892819979,
|
| 1211 |
+
"grad_norm": 0.40977853536605835,
|
| 1212 |
+
"learning_rate": 0.0004605555555555556,
|
| 1213 |
+
"loss": 0.0907,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.18002081165452655,
|
| 1218 |
+
"grad_norm": 0.27355197072029114,
|
| 1219 |
+
"learning_rate": 0.00046,
|
| 1220 |
+
"loss": 0.0688,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.18106139438085328,
|
| 1225 |
+
"grad_norm": 0.223897784948349,
|
| 1226 |
+
"learning_rate": 0.00045944444444444445,
|
| 1227 |
+
"loss": 0.0376,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.18210197710718,
|
| 1232 |
+
"grad_norm": 0.3418944180011749,
|
| 1233 |
+
"learning_rate": 0.0004588888888888889,
|
| 1234 |
+
"loss": 0.0483,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.18314255983350677,
|
| 1239 |
+
"grad_norm": 0.22283855080604553,
|
| 1240 |
+
"learning_rate": 0.0004583333333333333,
|
| 1241 |
+
"loss": 0.0602,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.1841831425598335,
|
| 1246 |
+
"grad_norm": 0.260822594165802,
|
| 1247 |
+
"learning_rate": 0.0004577777777777778,
|
| 1248 |
+
"loss": 0.0681,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.18522372528616024,
|
| 1253 |
+
"grad_norm": 0.2648361921310425,
|
| 1254 |
+
"learning_rate": 0.0004572222222222222,
|
| 1255 |
+
"loss": 0.064,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.186264308012487,
|
| 1260 |
+
"grad_norm": 0.28108835220336914,
|
| 1261 |
+
"learning_rate": 0.0004566666666666667,
|
| 1262 |
+
"loss": 0.0664,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.18730489073881373,
|
| 1267 |
+
"grad_norm": 0.3026326298713684,
|
| 1268 |
+
"learning_rate": 0.0004561111111111111,
|
| 1269 |
+
"loss": 0.0653,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.18834547346514047,
|
| 1274 |
+
"grad_norm": 0.24034692347049713,
|
| 1275 |
+
"learning_rate": 0.00045555555555555556,
|
| 1276 |
+
"loss": 0.0653,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.18938605619146723,
|
| 1281 |
+
"grad_norm": 0.2587687075138092,
|
| 1282 |
+
"learning_rate": 0.000455,
|
| 1283 |
+
"loss": 0.066,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.19042663891779396,
|
| 1288 |
+
"grad_norm": 0.44995367527008057,
|
| 1289 |
+
"learning_rate": 0.00045444444444444444,
|
| 1290 |
+
"loss": 0.0697,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.1914672216441207,
|
| 1295 |
+
"grad_norm": 0.29801756143569946,
|
| 1296 |
+
"learning_rate": 0.00045388888888888893,
|
| 1297 |
+
"loss": 0.068,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.19250780437044746,
|
| 1302 |
+
"grad_norm": 0.2797435224056244,
|
| 1303 |
+
"learning_rate": 0.0004533333333333333,
|
| 1304 |
+
"loss": 0.0704,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.1935483870967742,
|
| 1309 |
+
"grad_norm": 0.21289293467998505,
|
| 1310 |
+
"learning_rate": 0.0004527777777777778,
|
| 1311 |
+
"loss": 0.0476,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.19458896982310095,
|
| 1316 |
+
"grad_norm": 0.2547968029975891,
|
| 1317 |
+
"learning_rate": 0.00045222222222222224,
|
| 1318 |
+
"loss": 0.0669,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.19562955254942768,
|
| 1323 |
+
"grad_norm": 0.21561963856220245,
|
| 1324 |
+
"learning_rate": 0.0004516666666666667,
|
| 1325 |
+
"loss": 0.0687,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.19667013527575442,
|
| 1330 |
+
"grad_norm": 0.24872778356075287,
|
| 1331 |
+
"learning_rate": 0.0004511111111111111,
|
| 1332 |
+
"loss": 0.0539,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.19771071800208118,
|
| 1337 |
+
"grad_norm": 0.2251560389995575,
|
| 1338 |
+
"learning_rate": 0.00045055555555555555,
|
| 1339 |
+
"loss": 0.0631,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.1987513007284079,
|
| 1344 |
+
"grad_norm": 0.3262229263782501,
|
| 1345 |
+
"learning_rate": 0.00045000000000000004,
|
| 1346 |
+
"loss": 0.0906,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.19979188345473464,
|
| 1351 |
+
"grad_norm": 0.25986504554748535,
|
| 1352 |
+
"learning_rate": 0.0004494444444444444,
|
| 1353 |
+
"loss": 0.0424,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.2008324661810614,
|
| 1358 |
+
"grad_norm": 0.279202938079834,
|
| 1359 |
+
"learning_rate": 0.0004488888888888889,
|
| 1360 |
+
"loss": 0.0603,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.20187304890738814,
|
| 1365 |
+
"grad_norm": 0.24421726167201996,
|
| 1366 |
+
"learning_rate": 0.0004483333333333333,
|
| 1367 |
+
"loss": 0.0545,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.20291363163371487,
|
| 1372 |
+
"grad_norm": 0.23044031858444214,
|
| 1373 |
+
"learning_rate": 0.0004477777777777778,
|
| 1374 |
+
"loss": 0.0582,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.20395421436004163,
|
| 1379 |
+
"grad_norm": 0.3058019280433655,
|
| 1380 |
+
"learning_rate": 0.0004472222222222222,
|
| 1381 |
+
"loss": 0.071,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.20499479708636836,
|
| 1386 |
+
"grad_norm": 0.32619190216064453,
|
| 1387 |
+
"learning_rate": 0.00044666666666666666,
|
| 1388 |
+
"loss": 0.0625,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.2060353798126951,
|
| 1393 |
+
"grad_norm": 0.2773308753967285,
|
| 1394 |
+
"learning_rate": 0.00044611111111111115,
|
| 1395 |
+
"loss": 0.0496,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.20707596253902186,
|
| 1400 |
+
"grad_norm": 0.19181455671787262,
|
| 1401 |
+
"learning_rate": 0.00044555555555555554,
|
| 1402 |
+
"loss": 0.0424,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.2081165452653486,
|
| 1407 |
+
"grad_norm": 0.3275878131389618,
|
| 1408 |
+
"learning_rate": 0.00044500000000000003,
|
| 1409 |
+
"loss": 0.0505,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 1,
|
| 1414 |
+
"max_steps": 1000,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 2,
|
| 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": 0.0,
|
| 1431 |
+
"train_batch_size": 256,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/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 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/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 %}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2_5_VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 1003520,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"max_pixels": 1003520,
|
| 26 |
+
"min_pixels": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/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 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,2134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.31217481789802287,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001040582726326743,
|
| 14 |
+
"grad_norm": 3.268874406814575,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.6993,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002081165452653486,
|
| 21 |
+
"grad_norm": 3.8206846714019775,
|
| 22 |
+
"learning_rate": 5e-06,
|
| 23 |
+
"loss": 0.815,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.003121748178980229,
|
| 28 |
+
"grad_norm": 3.077709436416626,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"loss": 0.758,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.004162330905306972,
|
| 35 |
+
"grad_norm": 2.903688430786133,
|
| 36 |
+
"learning_rate": 1.5e-05,
|
| 37 |
+
"loss": 0.6332,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.005202913631633715,
|
| 42 |
+
"grad_norm": 2.8597545623779297,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.7086,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.006243496357960458,
|
| 49 |
+
"grad_norm": 3.6181485652923584,
|
| 50 |
+
"learning_rate": 2.5e-05,
|
| 51 |
+
"loss": 0.8511,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.007284079084287201,
|
| 56 |
+
"grad_norm": 5.016982555389404,
|
| 57 |
+
"learning_rate": 3e-05,
|
| 58 |
+
"loss": 1.0901,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.008324661810613945,
|
| 63 |
+
"grad_norm": 2.217885971069336,
|
| 64 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 65 |
+
"loss": 0.5426,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.009365244536940686,
|
| 70 |
+
"grad_norm": 2.0818731784820557,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.4986,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01040582726326743,
|
| 77 |
+
"grad_norm": 1.9352552890777588,
|
| 78 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 79 |
+
"loss": 0.5358,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.011446409989594173,
|
| 84 |
+
"grad_norm": 3.7815799713134766,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 0.877,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.012486992715920915,
|
| 91 |
+
"grad_norm": 2.989179849624634,
|
| 92 |
+
"learning_rate": 5.5e-05,
|
| 93 |
+
"loss": 0.6389,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.013527575442247659,
|
| 98 |
+
"grad_norm": 3.6533756256103516,
|
| 99 |
+
"learning_rate": 6e-05,
|
| 100 |
+
"loss": 0.7697,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.014568158168574402,
|
| 105 |
+
"grad_norm": 2.5273356437683105,
|
| 106 |
+
"learning_rate": 6.500000000000001e-05,
|
| 107 |
+
"loss": 0.4582,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.015608740894901144,
|
| 112 |
+
"grad_norm": 2.0315494537353516,
|
| 113 |
+
"learning_rate": 7.000000000000001e-05,
|
| 114 |
+
"loss": 0.4683,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.01664932362122789,
|
| 119 |
+
"grad_norm": 1.3862802982330322,
|
| 120 |
+
"learning_rate": 7.5e-05,
|
| 121 |
+
"loss": 0.401,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01768990634755463,
|
| 126 |
+
"grad_norm": 3.2270781993865967,
|
| 127 |
+
"learning_rate": 8e-05,
|
| 128 |
+
"loss": 0.6733,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.018730489073881373,
|
| 133 |
+
"grad_norm": 2.966115713119507,
|
| 134 |
+
"learning_rate": 8.5e-05,
|
| 135 |
+
"loss": 0.6105,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.019771071800208116,
|
| 140 |
+
"grad_norm": 2.720820188522339,
|
| 141 |
+
"learning_rate": 8.999999999999999e-05,
|
| 142 |
+
"loss": 0.5462,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.02081165452653486,
|
| 147 |
+
"grad_norm": 2.2214956283569336,
|
| 148 |
+
"learning_rate": 9.5e-05,
|
| 149 |
+
"loss": 0.5125,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.021852237252861603,
|
| 154 |
+
"grad_norm": 2.2020890712738037,
|
| 155 |
+
"learning_rate": 0.0001,
|
| 156 |
+
"loss": 0.4953,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.022892819979188347,
|
| 161 |
+
"grad_norm": 2.2625033855438232,
|
| 162 |
+
"learning_rate": 0.000105,
|
| 163 |
+
"loss": 0.5628,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.023933402705515087,
|
| 168 |
+
"grad_norm": 2.223475933074951,
|
| 169 |
+
"learning_rate": 0.00011,
|
| 170 |
+
"loss": 0.5667,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.02497398543184183,
|
| 175 |
+
"grad_norm": 2.982874631881714,
|
| 176 |
+
"learning_rate": 0.000115,
|
| 177 |
+
"loss": 0.6645,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.026014568158168574,
|
| 182 |
+
"grad_norm": 2.5550947189331055,
|
| 183 |
+
"learning_rate": 0.00012,
|
| 184 |
+
"loss": 0.4668,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.027055150884495317,
|
| 189 |
+
"grad_norm": 2.805063486099243,
|
| 190 |
+
"learning_rate": 0.000125,
|
| 191 |
+
"loss": 0.5205,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.02809573361082206,
|
| 196 |
+
"grad_norm": 1.7745788097381592,
|
| 197 |
+
"learning_rate": 0.00013000000000000002,
|
| 198 |
+
"loss": 0.3622,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.029136316337148804,
|
| 203 |
+
"grad_norm": 1.6776342391967773,
|
| 204 |
+
"learning_rate": 0.000135,
|
| 205 |
+
"loss": 0.3641,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.030176899063475548,
|
| 210 |
+
"grad_norm": 2.4569647312164307,
|
| 211 |
+
"learning_rate": 0.00014000000000000001,
|
| 212 |
+
"loss": 0.5263,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.031217481789802288,
|
| 217 |
+
"grad_norm": 1.2685638666152954,
|
| 218 |
+
"learning_rate": 0.000145,
|
| 219 |
+
"loss": 0.3199,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.03225806451612903,
|
| 224 |
+
"grad_norm": 1.3093715906143188,
|
| 225 |
+
"learning_rate": 0.00015,
|
| 226 |
+
"loss": 0.4389,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.03329864724245578,
|
| 231 |
+
"grad_norm": 1.643606185913086,
|
| 232 |
+
"learning_rate": 0.000155,
|
| 233 |
+
"loss": 0.3973,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.03433922996878252,
|
| 238 |
+
"grad_norm": 1.27973473072052,
|
| 239 |
+
"learning_rate": 0.00016,
|
| 240 |
+
"loss": 0.3601,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.03537981269510926,
|
| 245 |
+
"grad_norm": 1.3652054071426392,
|
| 246 |
+
"learning_rate": 0.000165,
|
| 247 |
+
"loss": 0.4557,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.036420395421436005,
|
| 252 |
+
"grad_norm": 1.2647119760513306,
|
| 253 |
+
"learning_rate": 0.00017,
|
| 254 |
+
"loss": 0.3723,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.037460978147762745,
|
| 259 |
+
"grad_norm": 1.2717779874801636,
|
| 260 |
+
"learning_rate": 0.000175,
|
| 261 |
+
"loss": 0.3429,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.03850156087408949,
|
| 266 |
+
"grad_norm": 1.7270296812057495,
|
| 267 |
+
"learning_rate": 0.00017999999999999998,
|
| 268 |
+
"loss": 0.4089,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.03954214360041623,
|
| 273 |
+
"grad_norm": 1.5404200553894043,
|
| 274 |
+
"learning_rate": 0.000185,
|
| 275 |
+
"loss": 0.3764,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.04058272632674298,
|
| 280 |
+
"grad_norm": 1.1958752870559692,
|
| 281 |
+
"learning_rate": 0.00019,
|
| 282 |
+
"loss": 0.375,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.04162330905306972,
|
| 287 |
+
"grad_norm": 1.4304900169372559,
|
| 288 |
+
"learning_rate": 0.00019500000000000002,
|
| 289 |
+
"loss": 0.3802,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.04266389177939646,
|
| 294 |
+
"grad_norm": 1.654426097869873,
|
| 295 |
+
"learning_rate": 0.0002,
|
| 296 |
+
"loss": 0.2566,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.043704474505723206,
|
| 301 |
+
"grad_norm": 1.7565494775772095,
|
| 302 |
+
"learning_rate": 0.000205,
|
| 303 |
+
"loss": 0.3105,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.044745057232049947,
|
| 308 |
+
"grad_norm": 2.055324077606201,
|
| 309 |
+
"learning_rate": 0.00021,
|
| 310 |
+
"loss": 0.3233,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.045785639958376693,
|
| 315 |
+
"grad_norm": 1.283117651939392,
|
| 316 |
+
"learning_rate": 0.000215,
|
| 317 |
+
"loss": 0.3023,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.046826222684703434,
|
| 322 |
+
"grad_norm": 1.292840838432312,
|
| 323 |
+
"learning_rate": 0.00022,
|
| 324 |
+
"loss": 0.2821,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.047866805411030174,
|
| 329 |
+
"grad_norm": 1.0345746278762817,
|
| 330 |
+
"learning_rate": 0.00022500000000000002,
|
| 331 |
+
"loss": 0.2539,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.04890738813735692,
|
| 336 |
+
"grad_norm": 1.0240848064422607,
|
| 337 |
+
"learning_rate": 0.00023,
|
| 338 |
+
"loss": 0.3298,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.04994797086368366,
|
| 343 |
+
"grad_norm": 1.7957828044891357,
|
| 344 |
+
"learning_rate": 0.000235,
|
| 345 |
+
"loss": 0.205,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.05098855359001041,
|
| 350 |
+
"grad_norm": 1.3810360431671143,
|
| 351 |
+
"learning_rate": 0.00024,
|
| 352 |
+
"loss": 0.2919,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.05202913631633715,
|
| 357 |
+
"grad_norm": 0.8331364393234253,
|
| 358 |
+
"learning_rate": 0.000245,
|
| 359 |
+
"loss": 0.1943,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.053069719042663895,
|
| 364 |
+
"grad_norm": 1.213149070739746,
|
| 365 |
+
"learning_rate": 0.00025,
|
| 366 |
+
"loss": 0.3011,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.054110301768990635,
|
| 371 |
+
"grad_norm": 0.9544571042060852,
|
| 372 |
+
"learning_rate": 0.000255,
|
| 373 |
+
"loss": 0.3511,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.055150884495317375,
|
| 378 |
+
"grad_norm": 0.9204476475715637,
|
| 379 |
+
"learning_rate": 0.00026000000000000003,
|
| 380 |
+
"loss": 0.2048,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.05619146722164412,
|
| 385 |
+
"grad_norm": 1.7272144556045532,
|
| 386 |
+
"learning_rate": 0.00026500000000000004,
|
| 387 |
+
"loss": 0.2715,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.05723204994797086,
|
| 392 |
+
"grad_norm": 0.891767680644989,
|
| 393 |
+
"learning_rate": 0.00027,
|
| 394 |
+
"loss": 0.2116,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.05827263267429761,
|
| 399 |
+
"grad_norm": 0.8020220398902893,
|
| 400 |
+
"learning_rate": 0.000275,
|
| 401 |
+
"loss": 0.2101,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.05931321540062435,
|
| 406 |
+
"grad_norm": 1.2897636890411377,
|
| 407 |
+
"learning_rate": 0.00028000000000000003,
|
| 408 |
+
"loss": 0.242,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.060353798126951096,
|
| 413 |
+
"grad_norm": 2.2333452701568604,
|
| 414 |
+
"learning_rate": 0.000285,
|
| 415 |
+
"loss": 0.3461,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.061394380853277836,
|
| 420 |
+
"grad_norm": 1.124709963798523,
|
| 421 |
+
"learning_rate": 0.00029,
|
| 422 |
+
"loss": 0.1709,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.062434963579604576,
|
| 427 |
+
"grad_norm": 0.7170735001564026,
|
| 428 |
+
"learning_rate": 0.000295,
|
| 429 |
+
"loss": 0.1954,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.06347554630593132,
|
| 434 |
+
"grad_norm": 1.3257620334625244,
|
| 435 |
+
"learning_rate": 0.0003,
|
| 436 |
+
"loss": 0.2816,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.06451612903225806,
|
| 441 |
+
"grad_norm": 0.7642104029655457,
|
| 442 |
+
"learning_rate": 0.000305,
|
| 443 |
+
"loss": 0.1788,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.06555671175858481,
|
| 448 |
+
"grad_norm": 0.9636558890342712,
|
| 449 |
+
"learning_rate": 0.00031,
|
| 450 |
+
"loss": 0.2138,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.06659729448491156,
|
| 455 |
+
"grad_norm": 0.7231699228286743,
|
| 456 |
+
"learning_rate": 0.000315,
|
| 457 |
+
"loss": 0.19,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.06763787721123829,
|
| 462 |
+
"grad_norm": 0.9044433236122131,
|
| 463 |
+
"learning_rate": 0.00032,
|
| 464 |
+
"loss": 0.1863,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.06867845993756504,
|
| 469 |
+
"grad_norm": 0.6787164807319641,
|
| 470 |
+
"learning_rate": 0.00032500000000000004,
|
| 471 |
+
"loss": 0.1615,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.06971904266389178,
|
| 476 |
+
"grad_norm": 0.6610997915267944,
|
| 477 |
+
"learning_rate": 0.00033,
|
| 478 |
+
"loss": 0.1777,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.07075962539021852,
|
| 483 |
+
"grad_norm": 0.8359801173210144,
|
| 484 |
+
"learning_rate": 0.000335,
|
| 485 |
+
"loss": 0.238,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.07180020811654526,
|
| 490 |
+
"grad_norm": 0.7294996976852417,
|
| 491 |
+
"learning_rate": 0.00034,
|
| 492 |
+
"loss": 0.2018,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.07284079084287201,
|
| 497 |
+
"grad_norm": 0.7325947880744934,
|
| 498 |
+
"learning_rate": 0.000345,
|
| 499 |
+
"loss": 0.1372,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.07388137356919876,
|
| 504 |
+
"grad_norm": 0.7132765650749207,
|
| 505 |
+
"learning_rate": 0.00035,
|
| 506 |
+
"loss": 0.1951,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.07492195629552549,
|
| 511 |
+
"grad_norm": 1.1800177097320557,
|
| 512 |
+
"learning_rate": 0.000355,
|
| 513 |
+
"loss": 0.2546,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.07596253902185224,
|
| 518 |
+
"grad_norm": 1.0050599575042725,
|
| 519 |
+
"learning_rate": 0.00035999999999999997,
|
| 520 |
+
"loss": 0.189,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.07700312174817898,
|
| 525 |
+
"grad_norm": 0.7532162070274353,
|
| 526 |
+
"learning_rate": 0.000365,
|
| 527 |
+
"loss": 0.1276,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.07804370447450572,
|
| 532 |
+
"grad_norm": 0.8199287056922913,
|
| 533 |
+
"learning_rate": 0.00037,
|
| 534 |
+
"loss": 0.2116,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.07908428720083246,
|
| 539 |
+
"grad_norm": 0.8740005493164062,
|
| 540 |
+
"learning_rate": 0.000375,
|
| 541 |
+
"loss": 0.1754,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.08012486992715921,
|
| 546 |
+
"grad_norm": 0.6971861124038696,
|
| 547 |
+
"learning_rate": 0.00038,
|
| 548 |
+
"loss": 0.1799,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.08116545265348596,
|
| 553 |
+
"grad_norm": 0.6992635726928711,
|
| 554 |
+
"learning_rate": 0.00038500000000000003,
|
| 555 |
+
"loss": 0.1663,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.08220603537981269,
|
| 560 |
+
"grad_norm": 0.8527954816818237,
|
| 561 |
+
"learning_rate": 0.00039000000000000005,
|
| 562 |
+
"loss": 0.1676,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.08324661810613944,
|
| 567 |
+
"grad_norm": 0.7233165502548218,
|
| 568 |
+
"learning_rate": 0.000395,
|
| 569 |
+
"loss": 0.1635,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.08428720083246619,
|
| 574 |
+
"grad_norm": 1.2006125450134277,
|
| 575 |
+
"learning_rate": 0.0004,
|
| 576 |
+
"loss": 0.1902,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.08532778355879292,
|
| 581 |
+
"grad_norm": 0.6341950297355652,
|
| 582 |
+
"learning_rate": 0.00040500000000000003,
|
| 583 |
+
"loss": 0.1396,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.08636836628511967,
|
| 588 |
+
"grad_norm": 0.670028030872345,
|
| 589 |
+
"learning_rate": 0.00041,
|
| 590 |
+
"loss": 0.162,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.08740894901144641,
|
| 595 |
+
"grad_norm": 0.6362585425376892,
|
| 596 |
+
"learning_rate": 0.000415,
|
| 597 |
+
"loss": 0.155,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.08844953173777315,
|
| 602 |
+
"grad_norm": 0.7975156307220459,
|
| 603 |
+
"learning_rate": 0.00042,
|
| 604 |
+
"loss": 0.1264,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.08949011446409989,
|
| 609 |
+
"grad_norm": 0.5603007078170776,
|
| 610 |
+
"learning_rate": 0.000425,
|
| 611 |
+
"loss": 0.1505,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.09053069719042664,
|
| 616 |
+
"grad_norm": 0.515308141708374,
|
| 617 |
+
"learning_rate": 0.00043,
|
| 618 |
+
"loss": 0.1364,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.09157127991675339,
|
| 623 |
+
"grad_norm": 0.6081110239028931,
|
| 624 |
+
"learning_rate": 0.000435,
|
| 625 |
+
"loss": 0.1428,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.09261186264308012,
|
| 630 |
+
"grad_norm": 0.5383463501930237,
|
| 631 |
+
"learning_rate": 0.00044,
|
| 632 |
+
"loss": 0.1293,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.09365244536940687,
|
| 637 |
+
"grad_norm": 0.659436047077179,
|
| 638 |
+
"learning_rate": 0.00044500000000000003,
|
| 639 |
+
"loss": 0.1475,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.09469302809573361,
|
| 644 |
+
"grad_norm": 0.5411190390586853,
|
| 645 |
+
"learning_rate": 0.00045000000000000004,
|
| 646 |
+
"loss": 0.1408,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.09573361082206035,
|
| 651 |
+
"grad_norm": 0.6518479585647583,
|
| 652 |
+
"learning_rate": 0.000455,
|
| 653 |
+
"loss": 0.1576,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.0967741935483871,
|
| 658 |
+
"grad_norm": 0.5494299530982971,
|
| 659 |
+
"learning_rate": 0.00046,
|
| 660 |
+
"loss": 0.1099,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.09781477627471384,
|
| 665 |
+
"grad_norm": 0.8132746815681458,
|
| 666 |
+
"learning_rate": 0.000465,
|
| 667 |
+
"loss": 0.1636,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.09885535900104059,
|
| 672 |
+
"grad_norm": 0.5652503371238708,
|
| 673 |
+
"learning_rate": 0.00047,
|
| 674 |
+
"loss": 0.1595,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.09989594172736732,
|
| 679 |
+
"grad_norm": 0.61795973777771,
|
| 680 |
+
"learning_rate": 0.000475,
|
| 681 |
+
"loss": 0.0745,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.10093652445369407,
|
| 686 |
+
"grad_norm": 0.4944301247596741,
|
| 687 |
+
"learning_rate": 0.00048,
|
| 688 |
+
"loss": 0.1406,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.10197710718002082,
|
| 693 |
+
"grad_norm": 0.5052417516708374,
|
| 694 |
+
"learning_rate": 0.00048499999999999997,
|
| 695 |
+
"loss": 0.104,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.10301768990634755,
|
| 700 |
+
"grad_norm": 0.46198371052742004,
|
| 701 |
+
"learning_rate": 0.00049,
|
| 702 |
+
"loss": 0.0883,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.1040582726326743,
|
| 707 |
+
"grad_norm": 0.6346387267112732,
|
| 708 |
+
"learning_rate": 0.000495,
|
| 709 |
+
"loss": 0.154,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.10509885535900104,
|
| 714 |
+
"grad_norm": 0.4819563925266266,
|
| 715 |
+
"learning_rate": 0.0005,
|
| 716 |
+
"loss": 0.1454,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.10613943808532779,
|
| 721 |
+
"grad_norm": 0.44754841923713684,
|
| 722 |
+
"learning_rate": 0.0004994444444444445,
|
| 723 |
+
"loss": 0.0742,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.10718002081165452,
|
| 728 |
+
"grad_norm": 0.3852291703224182,
|
| 729 |
+
"learning_rate": 0.0004988888888888889,
|
| 730 |
+
"loss": 0.063,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.10822060353798127,
|
| 735 |
+
"grad_norm": 0.572284460067749,
|
| 736 |
+
"learning_rate": 0.0004983333333333334,
|
| 737 |
+
"loss": 0.1434,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.10926118626430802,
|
| 742 |
+
"grad_norm": 0.402413934469223,
|
| 743 |
+
"learning_rate": 0.0004977777777777778,
|
| 744 |
+
"loss": 0.0897,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.11030176899063475,
|
| 749 |
+
"grad_norm": 0.5178724527359009,
|
| 750 |
+
"learning_rate": 0.0004972222222222222,
|
| 751 |
+
"loss": 0.0991,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1113423517169615,
|
| 756 |
+
"grad_norm": 0.5298802852630615,
|
| 757 |
+
"learning_rate": 0.0004966666666666666,
|
| 758 |
+
"loss": 0.1265,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.11238293444328824,
|
| 763 |
+
"grad_norm": 0.5106524229049683,
|
| 764 |
+
"learning_rate": 0.0004961111111111111,
|
| 765 |
+
"loss": 0.076,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.11342351716961499,
|
| 770 |
+
"grad_norm": 0.4718921482563019,
|
| 771 |
+
"learning_rate": 0.0004955555555555556,
|
| 772 |
+
"loss": 0.0927,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.11446409989594172,
|
| 777 |
+
"grad_norm": 0.4144158661365509,
|
| 778 |
+
"learning_rate": 0.000495,
|
| 779 |
+
"loss": 0.1075,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.11550468262226847,
|
| 784 |
+
"grad_norm": 0.44835594296455383,
|
| 785 |
+
"learning_rate": 0.0004944444444444445,
|
| 786 |
+
"loss": 0.1093,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.11654526534859522,
|
| 791 |
+
"grad_norm": 0.6650722622871399,
|
| 792 |
+
"learning_rate": 0.0004938888888888889,
|
| 793 |
+
"loss": 0.1082,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.11758584807492195,
|
| 798 |
+
"grad_norm": 0.40712565183639526,
|
| 799 |
+
"learning_rate": 0.0004933333333333334,
|
| 800 |
+
"loss": 0.0622,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.1186264308012487,
|
| 805 |
+
"grad_norm": 0.5961405634880066,
|
| 806 |
+
"learning_rate": 0.0004927777777777777,
|
| 807 |
+
"loss": 0.1041,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.11966701352757544,
|
| 812 |
+
"grad_norm": 0.4379814863204956,
|
| 813 |
+
"learning_rate": 0.0004922222222222222,
|
| 814 |
+
"loss": 0.1172,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.12070759625390219,
|
| 819 |
+
"grad_norm": 0.4038859009742737,
|
| 820 |
+
"learning_rate": 0.0004916666666666666,
|
| 821 |
+
"loss": 0.083,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.12174817898022892,
|
| 826 |
+
"grad_norm": 0.49663108587265015,
|
| 827 |
+
"learning_rate": 0.0004911111111111111,
|
| 828 |
+
"loss": 0.0732,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.12278876170655567,
|
| 833 |
+
"grad_norm": 0.34757199883461,
|
| 834 |
+
"learning_rate": 0.0004905555555555556,
|
| 835 |
+
"loss": 0.0946,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.12382934443288242,
|
| 840 |
+
"grad_norm": 0.421332448720932,
|
| 841 |
+
"learning_rate": 0.00049,
|
| 842 |
+
"loss": 0.0856,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.12486992715920915,
|
| 847 |
+
"grad_norm": 0.41452690958976746,
|
| 848 |
+
"learning_rate": 0.0004894444444444445,
|
| 849 |
+
"loss": 0.1235,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.1259105098855359,
|
| 854 |
+
"grad_norm": 0.6133429408073425,
|
| 855 |
+
"learning_rate": 0.0004888888888888889,
|
| 856 |
+
"loss": 0.1004,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.12695109261186263,
|
| 861 |
+
"grad_norm": 0.4711684286594391,
|
| 862 |
+
"learning_rate": 0.0004883333333333333,
|
| 863 |
+
"loss": 0.0944,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.1279916753381894,
|
| 868 |
+
"grad_norm": 0.4512624144554138,
|
| 869 |
+
"learning_rate": 0.0004877777777777778,
|
| 870 |
+
"loss": 0.1027,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.12903225806451613,
|
| 875 |
+
"grad_norm": 0.42018765211105347,
|
| 876 |
+
"learning_rate": 0.0004872222222222222,
|
| 877 |
+
"loss": 0.1185,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.13007284079084286,
|
| 882 |
+
"grad_norm": 0.49484384059906006,
|
| 883 |
+
"learning_rate": 0.0004866666666666667,
|
| 884 |
+
"loss": 0.0782,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.13111342351716962,
|
| 889 |
+
"grad_norm": 0.4003879427909851,
|
| 890 |
+
"learning_rate": 0.0004861111111111111,
|
| 891 |
+
"loss": 0.087,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.13215400624349635,
|
| 896 |
+
"grad_norm": 0.5285933017730713,
|
| 897 |
+
"learning_rate": 0.0004855555555555556,
|
| 898 |
+
"loss": 0.078,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.1331945889698231,
|
| 903 |
+
"grad_norm": 0.3752761781215668,
|
| 904 |
+
"learning_rate": 0.00048499999999999997,
|
| 905 |
+
"loss": 0.0792,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.13423517169614985,
|
| 910 |
+
"grad_norm": 0.3410363495349884,
|
| 911 |
+
"learning_rate": 0.00048444444444444446,
|
| 912 |
+
"loss": 0.1107,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.13527575442247658,
|
| 917 |
+
"grad_norm": 0.38146358728408813,
|
| 918 |
+
"learning_rate": 0.0004838888888888889,
|
| 919 |
+
"loss": 0.0894,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.13631633714880334,
|
| 924 |
+
"grad_norm": 0.5861756801605225,
|
| 925 |
+
"learning_rate": 0.00048333333333333334,
|
| 926 |
+
"loss": 0.1187,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.13735691987513007,
|
| 931 |
+
"grad_norm": 0.7138178944587708,
|
| 932 |
+
"learning_rate": 0.0004827777777777778,
|
| 933 |
+
"loss": 0.1242,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.1383975026014568,
|
| 938 |
+
"grad_norm": 0.3060092031955719,
|
| 939 |
+
"learning_rate": 0.0004822222222222222,
|
| 940 |
+
"loss": 0.0721,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.13943808532778357,
|
| 945 |
+
"grad_norm": 0.32948216795921326,
|
| 946 |
+
"learning_rate": 0.0004816666666666667,
|
| 947 |
+
"loss": 0.0814,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1404786680541103,
|
| 952 |
+
"grad_norm": 0.2897670865058899,
|
| 953 |
+
"learning_rate": 0.0004811111111111111,
|
| 954 |
+
"loss": 0.0728,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.14151925078043703,
|
| 959 |
+
"grad_norm": 0.32715317606925964,
|
| 960 |
+
"learning_rate": 0.0004805555555555556,
|
| 961 |
+
"loss": 0.083,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.1425598335067638,
|
| 966 |
+
"grad_norm": 0.28751736879348755,
|
| 967 |
+
"learning_rate": 0.00048,
|
| 968 |
+
"loss": 0.0619,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.14360041623309053,
|
| 973 |
+
"grad_norm": 0.3826645612716675,
|
| 974 |
+
"learning_rate": 0.00047944444444444445,
|
| 975 |
+
"loss": 0.1057,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.14464099895941726,
|
| 980 |
+
"grad_norm": 0.4589000642299652,
|
| 981 |
+
"learning_rate": 0.0004788888888888889,
|
| 982 |
+
"loss": 0.1138,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.14568158168574402,
|
| 987 |
+
"grad_norm": 0.4404071569442749,
|
| 988 |
+
"learning_rate": 0.0004783333333333333,
|
| 989 |
+
"loss": 0.0824,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.14672216441207075,
|
| 994 |
+
"grad_norm": 0.4857710301876068,
|
| 995 |
+
"learning_rate": 0.0004777777777777778,
|
| 996 |
+
"loss": 0.0744,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.14776274713839752,
|
| 1001 |
+
"grad_norm": 0.34489718079566956,
|
| 1002 |
+
"learning_rate": 0.00047722222222222225,
|
| 1003 |
+
"loss": 0.0556,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.14880332986472425,
|
| 1008 |
+
"grad_norm": 0.3448956310749054,
|
| 1009 |
+
"learning_rate": 0.0004766666666666667,
|
| 1010 |
+
"loss": 0.064,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.14984391259105098,
|
| 1015 |
+
"grad_norm": 0.3096216917037964,
|
| 1016 |
+
"learning_rate": 0.0004761111111111111,
|
| 1017 |
+
"loss": 0.0816,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.15088449531737774,
|
| 1022 |
+
"grad_norm": 0.4213986396789551,
|
| 1023 |
+
"learning_rate": 0.00047555555555555556,
|
| 1024 |
+
"loss": 0.1041,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.15192507804370448,
|
| 1029 |
+
"grad_norm": 0.2673068046569824,
|
| 1030 |
+
"learning_rate": 0.000475,
|
| 1031 |
+
"loss": 0.0836,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.1529656607700312,
|
| 1036 |
+
"grad_norm": 0.35139915347099304,
|
| 1037 |
+
"learning_rate": 0.00047444444444444444,
|
| 1038 |
+
"loss": 0.0866,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.15400624349635797,
|
| 1043 |
+
"grad_norm": 0.3168632388114929,
|
| 1044 |
+
"learning_rate": 0.00047388888888888893,
|
| 1045 |
+
"loss": 0.0693,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.1550468262226847,
|
| 1050 |
+
"grad_norm": 0.3259681761264801,
|
| 1051 |
+
"learning_rate": 0.00047333333333333336,
|
| 1052 |
+
"loss": 0.0525,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.15608740894901144,
|
| 1057 |
+
"grad_norm": 0.44802430272102356,
|
| 1058 |
+
"learning_rate": 0.0004727777777777778,
|
| 1059 |
+
"loss": 0.0938,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.1571279916753382,
|
| 1064 |
+
"grad_norm": 0.2723800241947174,
|
| 1065 |
+
"learning_rate": 0.00047222222222222224,
|
| 1066 |
+
"loss": 0.0637,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.15816857440166493,
|
| 1071 |
+
"grad_norm": 0.33274656534194946,
|
| 1072 |
+
"learning_rate": 0.0004716666666666667,
|
| 1073 |
+
"loss": 0.0776,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.15920915712799166,
|
| 1078 |
+
"grad_norm": 0.41862592101097107,
|
| 1079 |
+
"learning_rate": 0.0004711111111111111,
|
| 1080 |
+
"loss": 0.0979,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.16024973985431842,
|
| 1085 |
+
"grad_norm": 0.35577768087387085,
|
| 1086 |
+
"learning_rate": 0.00047055555555555555,
|
| 1087 |
+
"loss": 0.0414,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.16129032258064516,
|
| 1092 |
+
"grad_norm": 0.32270193099975586,
|
| 1093 |
+
"learning_rate": 0.00047,
|
| 1094 |
+
"loss": 0.101,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.16233090530697192,
|
| 1099 |
+
"grad_norm": 0.2666638493537903,
|
| 1100 |
+
"learning_rate": 0.0004694444444444445,
|
| 1101 |
+
"loss": 0.0689,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.16337148803329865,
|
| 1106 |
+
"grad_norm": 0.20294290781021118,
|
| 1107 |
+
"learning_rate": 0.0004688888888888889,
|
| 1108 |
+
"loss": 0.0533,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.16441207075962538,
|
| 1113 |
+
"grad_norm": 0.3359270989894867,
|
| 1114 |
+
"learning_rate": 0.00046833333333333335,
|
| 1115 |
+
"loss": 0.0817,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.16545265348595214,
|
| 1120 |
+
"grad_norm": 0.44312432408332825,
|
| 1121 |
+
"learning_rate": 0.0004677777777777778,
|
| 1122 |
+
"loss": 0.0862,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.16649323621227888,
|
| 1127 |
+
"grad_norm": 0.24581390619277954,
|
| 1128 |
+
"learning_rate": 0.0004672222222222222,
|
| 1129 |
+
"loss": 0.0585,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1675338189386056,
|
| 1134 |
+
"grad_norm": 0.25939878821372986,
|
| 1135 |
+
"learning_rate": 0.00046666666666666666,
|
| 1136 |
+
"loss": 0.0737,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.16857440166493237,
|
| 1141 |
+
"grad_norm": 0.212020605802536,
|
| 1142 |
+
"learning_rate": 0.0004661111111111111,
|
| 1143 |
+
"loss": 0.0487,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.1696149843912591,
|
| 1148 |
+
"grad_norm": 0.30007174611091614,
|
| 1149 |
+
"learning_rate": 0.0004655555555555556,
|
| 1150 |
+
"loss": 0.0695,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.17065556711758584,
|
| 1155 |
+
"grad_norm": 0.2842208445072174,
|
| 1156 |
+
"learning_rate": 0.000465,
|
| 1157 |
+
"loss": 0.0612,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.1716961498439126,
|
| 1162 |
+
"grad_norm": 0.2660129964351654,
|
| 1163 |
+
"learning_rate": 0.00046444444444444446,
|
| 1164 |
+
"loss": 0.0557,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.17273673257023933,
|
| 1169 |
+
"grad_norm": 0.3331991732120514,
|
| 1170 |
+
"learning_rate": 0.0004638888888888889,
|
| 1171 |
+
"loss": 0.0676,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.17377731529656607,
|
| 1176 |
+
"grad_norm": 0.2525298297405243,
|
| 1177 |
+
"learning_rate": 0.00046333333333333334,
|
| 1178 |
+
"loss": 0.0552,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.17481789802289283,
|
| 1183 |
+
"grad_norm": 0.2903599739074707,
|
| 1184 |
+
"learning_rate": 0.0004627777777777778,
|
| 1185 |
+
"loss": 0.0823,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.17585848074921956,
|
| 1190 |
+
"grad_norm": 0.25501200556755066,
|
| 1191 |
+
"learning_rate": 0.0004622222222222222,
|
| 1192 |
+
"loss": 0.0529,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.1768990634755463,
|
| 1197 |
+
"grad_norm": 0.27259787917137146,
|
| 1198 |
+
"learning_rate": 0.0004616666666666667,
|
| 1199 |
+
"loss": 0.0635,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.17793964620187305,
|
| 1204 |
+
"grad_norm": 0.22791972756385803,
|
| 1205 |
+
"learning_rate": 0.00046111111111111114,
|
| 1206 |
+
"loss": 0.0608,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.17898022892819979,
|
| 1211 |
+
"grad_norm": 0.40977853536605835,
|
| 1212 |
+
"learning_rate": 0.0004605555555555556,
|
| 1213 |
+
"loss": 0.0907,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.18002081165452655,
|
| 1218 |
+
"grad_norm": 0.27355197072029114,
|
| 1219 |
+
"learning_rate": 0.00046,
|
| 1220 |
+
"loss": 0.0688,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.18106139438085328,
|
| 1225 |
+
"grad_norm": 0.223897784948349,
|
| 1226 |
+
"learning_rate": 0.00045944444444444445,
|
| 1227 |
+
"loss": 0.0376,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.18210197710718,
|
| 1232 |
+
"grad_norm": 0.3418944180011749,
|
| 1233 |
+
"learning_rate": 0.0004588888888888889,
|
| 1234 |
+
"loss": 0.0483,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.18314255983350677,
|
| 1239 |
+
"grad_norm": 0.22283855080604553,
|
| 1240 |
+
"learning_rate": 0.0004583333333333333,
|
| 1241 |
+
"loss": 0.0602,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.1841831425598335,
|
| 1246 |
+
"grad_norm": 0.260822594165802,
|
| 1247 |
+
"learning_rate": 0.0004577777777777778,
|
| 1248 |
+
"loss": 0.0681,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.18522372528616024,
|
| 1253 |
+
"grad_norm": 0.2648361921310425,
|
| 1254 |
+
"learning_rate": 0.0004572222222222222,
|
| 1255 |
+
"loss": 0.064,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.186264308012487,
|
| 1260 |
+
"grad_norm": 0.28108835220336914,
|
| 1261 |
+
"learning_rate": 0.0004566666666666667,
|
| 1262 |
+
"loss": 0.0664,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.18730489073881373,
|
| 1267 |
+
"grad_norm": 0.3026326298713684,
|
| 1268 |
+
"learning_rate": 0.0004561111111111111,
|
| 1269 |
+
"loss": 0.0653,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.18834547346514047,
|
| 1274 |
+
"grad_norm": 0.24034692347049713,
|
| 1275 |
+
"learning_rate": 0.00045555555555555556,
|
| 1276 |
+
"loss": 0.0653,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.18938605619146723,
|
| 1281 |
+
"grad_norm": 0.2587687075138092,
|
| 1282 |
+
"learning_rate": 0.000455,
|
| 1283 |
+
"loss": 0.066,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.19042663891779396,
|
| 1288 |
+
"grad_norm": 0.44995367527008057,
|
| 1289 |
+
"learning_rate": 0.00045444444444444444,
|
| 1290 |
+
"loss": 0.0697,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.1914672216441207,
|
| 1295 |
+
"grad_norm": 0.29801756143569946,
|
| 1296 |
+
"learning_rate": 0.00045388888888888893,
|
| 1297 |
+
"loss": 0.068,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.19250780437044746,
|
| 1302 |
+
"grad_norm": 0.2797435224056244,
|
| 1303 |
+
"learning_rate": 0.0004533333333333333,
|
| 1304 |
+
"loss": 0.0704,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.1935483870967742,
|
| 1309 |
+
"grad_norm": 0.21289293467998505,
|
| 1310 |
+
"learning_rate": 0.0004527777777777778,
|
| 1311 |
+
"loss": 0.0476,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.19458896982310095,
|
| 1316 |
+
"grad_norm": 0.2547968029975891,
|
| 1317 |
+
"learning_rate": 0.00045222222222222224,
|
| 1318 |
+
"loss": 0.0669,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.19562955254942768,
|
| 1323 |
+
"grad_norm": 0.21561963856220245,
|
| 1324 |
+
"learning_rate": 0.0004516666666666667,
|
| 1325 |
+
"loss": 0.0687,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.19667013527575442,
|
| 1330 |
+
"grad_norm": 0.24872778356075287,
|
| 1331 |
+
"learning_rate": 0.0004511111111111111,
|
| 1332 |
+
"loss": 0.0539,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.19771071800208118,
|
| 1337 |
+
"grad_norm": 0.2251560389995575,
|
| 1338 |
+
"learning_rate": 0.00045055555555555555,
|
| 1339 |
+
"loss": 0.0631,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.1987513007284079,
|
| 1344 |
+
"grad_norm": 0.3262229263782501,
|
| 1345 |
+
"learning_rate": 0.00045000000000000004,
|
| 1346 |
+
"loss": 0.0906,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.19979188345473464,
|
| 1351 |
+
"grad_norm": 0.25986504554748535,
|
| 1352 |
+
"learning_rate": 0.0004494444444444444,
|
| 1353 |
+
"loss": 0.0424,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.2008324661810614,
|
| 1358 |
+
"grad_norm": 0.279202938079834,
|
| 1359 |
+
"learning_rate": 0.0004488888888888889,
|
| 1360 |
+
"loss": 0.0603,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.20187304890738814,
|
| 1365 |
+
"grad_norm": 0.24421726167201996,
|
| 1366 |
+
"learning_rate": 0.0004483333333333333,
|
| 1367 |
+
"loss": 0.0545,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.20291363163371487,
|
| 1372 |
+
"grad_norm": 0.23044031858444214,
|
| 1373 |
+
"learning_rate": 0.0004477777777777778,
|
| 1374 |
+
"loss": 0.0582,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.20395421436004163,
|
| 1379 |
+
"grad_norm": 0.3058019280433655,
|
| 1380 |
+
"learning_rate": 0.0004472222222222222,
|
| 1381 |
+
"loss": 0.071,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.20499479708636836,
|
| 1386 |
+
"grad_norm": 0.32619190216064453,
|
| 1387 |
+
"learning_rate": 0.00044666666666666666,
|
| 1388 |
+
"loss": 0.0625,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.2060353798126951,
|
| 1393 |
+
"grad_norm": 0.2773308753967285,
|
| 1394 |
+
"learning_rate": 0.00044611111111111115,
|
| 1395 |
+
"loss": 0.0496,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.20707596253902186,
|
| 1400 |
+
"grad_norm": 0.19181455671787262,
|
| 1401 |
+
"learning_rate": 0.00044555555555555554,
|
| 1402 |
+
"loss": 0.0424,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.2081165452653486,
|
| 1407 |
+
"grad_norm": 0.3275878131389618,
|
| 1408 |
+
"learning_rate": 0.00044500000000000003,
|
| 1409 |
+
"loss": 0.0505,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.20915712799167535,
|
| 1414 |
+
"grad_norm": 0.2280910611152649,
|
| 1415 |
+
"learning_rate": 0.0004444444444444444,
|
| 1416 |
+
"loss": 0.0526,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.21019771071800208,
|
| 1421 |
+
"grad_norm": 0.21952077746391296,
|
| 1422 |
+
"learning_rate": 0.0004438888888888889,
|
| 1423 |
+
"loss": 0.0581,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.21123829344432882,
|
| 1428 |
+
"grad_norm": 0.2316325306892395,
|
| 1429 |
+
"learning_rate": 0.00044333333333333334,
|
| 1430 |
+
"loss": 0.0587,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.21227887617065558,
|
| 1435 |
+
"grad_norm": 0.2537364363670349,
|
| 1436 |
+
"learning_rate": 0.0004427777777777778,
|
| 1437 |
+
"loss": 0.0557,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.2133194588969823,
|
| 1442 |
+
"grad_norm": 0.24439412355422974,
|
| 1443 |
+
"learning_rate": 0.00044222222222222227,
|
| 1444 |
+
"loss": 0.0333,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.21436004162330904,
|
| 1449 |
+
"grad_norm": 0.21104027330875397,
|
| 1450 |
+
"learning_rate": 0.00044166666666666665,
|
| 1451 |
+
"loss": 0.0643,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.2154006243496358,
|
| 1456 |
+
"grad_norm": 0.2639058232307434,
|
| 1457 |
+
"learning_rate": 0.00044111111111111114,
|
| 1458 |
+
"loss": 0.0443,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.21644120707596254,
|
| 1463 |
+
"grad_norm": 0.19854490458965302,
|
| 1464 |
+
"learning_rate": 0.0004405555555555555,
|
| 1465 |
+
"loss": 0.0402,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.21748178980228927,
|
| 1470 |
+
"grad_norm": 0.49617311358451843,
|
| 1471 |
+
"learning_rate": 0.00044,
|
| 1472 |
+
"loss": 0.0668,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.21852237252861603,
|
| 1477 |
+
"grad_norm": 0.2171219140291214,
|
| 1478 |
+
"learning_rate": 0.0004394444444444445,
|
| 1479 |
+
"loss": 0.0531,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.21956295525494277,
|
| 1484 |
+
"grad_norm": 0.21126677095890045,
|
| 1485 |
+
"learning_rate": 0.0004388888888888889,
|
| 1486 |
+
"loss": 0.0618,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.2206035379812695,
|
| 1491 |
+
"grad_norm": 0.22313550114631653,
|
| 1492 |
+
"learning_rate": 0.0004383333333333334,
|
| 1493 |
+
"loss": 0.0381,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.22164412070759626,
|
| 1498 |
+
"grad_norm": 0.22066129744052887,
|
| 1499 |
+
"learning_rate": 0.00043777777777777776,
|
| 1500 |
+
"loss": 0.0516,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.222684703433923,
|
| 1505 |
+
"grad_norm": 0.19753003120422363,
|
| 1506 |
+
"learning_rate": 0.00043722222222222225,
|
| 1507 |
+
"loss": 0.0472,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.22372528616024975,
|
| 1512 |
+
"grad_norm": 0.20395542681217194,
|
| 1513 |
+
"learning_rate": 0.00043666666666666664,
|
| 1514 |
+
"loss": 0.0384,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.2247658688865765,
|
| 1519 |
+
"grad_norm": 0.25114142894744873,
|
| 1520 |
+
"learning_rate": 0.00043611111111111113,
|
| 1521 |
+
"loss": 0.0557,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.22580645161290322,
|
| 1526 |
+
"grad_norm": 0.3654433786869049,
|
| 1527 |
+
"learning_rate": 0.0004355555555555555,
|
| 1528 |
+
"loss": 0.0476,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.22684703433922998,
|
| 1533 |
+
"grad_norm": 0.22211597859859467,
|
| 1534 |
+
"learning_rate": 0.000435,
|
| 1535 |
+
"loss": 0.0515,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.2278876170655567,
|
| 1540 |
+
"grad_norm": 0.24841049313545227,
|
| 1541 |
+
"learning_rate": 0.0004344444444444445,
|
| 1542 |
+
"loss": 0.0662,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.22892819979188345,
|
| 1547 |
+
"grad_norm": 0.2204892486333847,
|
| 1548 |
+
"learning_rate": 0.0004338888888888889,
|
| 1549 |
+
"loss": 0.0568,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.2299687825182102,
|
| 1554 |
+
"grad_norm": 0.2373652160167694,
|
| 1555 |
+
"learning_rate": 0.00043333333333333337,
|
| 1556 |
+
"loss": 0.0492,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.23100936524453694,
|
| 1561 |
+
"grad_norm": 0.26821693778038025,
|
| 1562 |
+
"learning_rate": 0.00043277777777777775,
|
| 1563 |
+
"loss": 0.0572,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.23204994797086367,
|
| 1568 |
+
"grad_norm": 0.23499903082847595,
|
| 1569 |
+
"learning_rate": 0.00043222222222222224,
|
| 1570 |
+
"loss": 0.0443,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.23309053069719043,
|
| 1575 |
+
"grad_norm": 0.2623459994792938,
|
| 1576 |
+
"learning_rate": 0.0004316666666666667,
|
| 1577 |
+
"loss": 0.0493,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.23413111342351717,
|
| 1582 |
+
"grad_norm": 0.23820453882217407,
|
| 1583 |
+
"learning_rate": 0.0004311111111111111,
|
| 1584 |
+
"loss": 0.0462,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.2351716961498439,
|
| 1589 |
+
"grad_norm": 0.196584090590477,
|
| 1590 |
+
"learning_rate": 0.0004305555555555556,
|
| 1591 |
+
"loss": 0.0442,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.23621227887617066,
|
| 1596 |
+
"grad_norm": 0.26306819915771484,
|
| 1597 |
+
"learning_rate": 0.00043,
|
| 1598 |
+
"loss": 0.0564,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.2372528616024974,
|
| 1603 |
+
"grad_norm": 0.2611851096153259,
|
| 1604 |
+
"learning_rate": 0.0004294444444444445,
|
| 1605 |
+
"loss": 0.0452,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.23829344432882413,
|
| 1610 |
+
"grad_norm": 0.21443575620651245,
|
| 1611 |
+
"learning_rate": 0.00042888888888888886,
|
| 1612 |
+
"loss": 0.0543,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.2393340270551509,
|
| 1617 |
+
"grad_norm": 0.30607742071151733,
|
| 1618 |
+
"learning_rate": 0.00042833333333333335,
|
| 1619 |
+
"loss": 0.0499,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.24037460978147762,
|
| 1624 |
+
"grad_norm": 0.29146668314933777,
|
| 1625 |
+
"learning_rate": 0.0004277777777777778,
|
| 1626 |
+
"loss": 0.0588,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.24141519250780438,
|
| 1631 |
+
"grad_norm": 0.18191011250019073,
|
| 1632 |
+
"learning_rate": 0.00042722222222222223,
|
| 1633 |
+
"loss": 0.0435,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.24245577523413112,
|
| 1638 |
+
"grad_norm": 0.184339240193367,
|
| 1639 |
+
"learning_rate": 0.0004266666666666667,
|
| 1640 |
+
"loss": 0.0324,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.24349635796045785,
|
| 1645 |
+
"grad_norm": 0.23122777044773102,
|
| 1646 |
+
"learning_rate": 0.0004261111111111111,
|
| 1647 |
+
"loss": 0.0343,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.2445369406867846,
|
| 1652 |
+
"grad_norm": 0.20807258784770966,
|
| 1653 |
+
"learning_rate": 0.0004255555555555556,
|
| 1654 |
+
"loss": 0.0522,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.24557752341311134,
|
| 1659 |
+
"grad_norm": 0.19972191751003265,
|
| 1660 |
+
"learning_rate": 0.000425,
|
| 1661 |
+
"loss": 0.0529,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.24661810613943808,
|
| 1666 |
+
"grad_norm": 0.21919365227222443,
|
| 1667 |
+
"learning_rate": 0.00042444444444444447,
|
| 1668 |
+
"loss": 0.0406,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.24765868886576484,
|
| 1673 |
+
"grad_norm": 0.2519589960575104,
|
| 1674 |
+
"learning_rate": 0.0004238888888888889,
|
| 1675 |
+
"loss": 0.0571,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.24869927159209157,
|
| 1680 |
+
"grad_norm": 0.1512586921453476,
|
| 1681 |
+
"learning_rate": 0.00042333333333333334,
|
| 1682 |
+
"loss": 0.0368,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.2497398543184183,
|
| 1687 |
+
"grad_norm": 0.20062124729156494,
|
| 1688 |
+
"learning_rate": 0.0004227777777777778,
|
| 1689 |
+
"loss": 0.0428,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.25078043704474506,
|
| 1694 |
+
"grad_norm": 0.2119806557893753,
|
| 1695 |
+
"learning_rate": 0.0004222222222222222,
|
| 1696 |
+
"loss": 0.0592,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.2518210197710718,
|
| 1701 |
+
"grad_norm": 0.3062295615673065,
|
| 1702 |
+
"learning_rate": 0.0004216666666666667,
|
| 1703 |
+
"loss": 0.0613,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.25286160249739853,
|
| 1708 |
+
"grad_norm": 0.21827293932437897,
|
| 1709 |
+
"learning_rate": 0.0004211111111111111,
|
| 1710 |
+
"loss": 0.0531,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.25390218522372526,
|
| 1715 |
+
"grad_norm": 0.2759004235267639,
|
| 1716 |
+
"learning_rate": 0.0004205555555555556,
|
| 1717 |
+
"loss": 0.0561,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.25494276795005205,
|
| 1722 |
+
"grad_norm": 0.1976407915353775,
|
| 1723 |
+
"learning_rate": 0.00042,
|
| 1724 |
+
"loss": 0.0374,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.2559833506763788,
|
| 1729 |
+
"grad_norm": 0.2423432171344757,
|
| 1730 |
+
"learning_rate": 0.00041944444444444445,
|
| 1731 |
+
"loss": 0.049,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.2570239334027055,
|
| 1736 |
+
"grad_norm": 0.20555488765239716,
|
| 1737 |
+
"learning_rate": 0.0004188888888888889,
|
| 1738 |
+
"loss": 0.0518,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.25806451612903225,
|
| 1743 |
+
"grad_norm": 0.21792030334472656,
|
| 1744 |
+
"learning_rate": 0.00041833333333333333,
|
| 1745 |
+
"loss": 0.0452,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.259105098855359,
|
| 1750 |
+
"grad_norm": 0.2850765883922577,
|
| 1751 |
+
"learning_rate": 0.0004177777777777778,
|
| 1752 |
+
"loss": 0.0602,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.2601456815816857,
|
| 1757 |
+
"grad_norm": 0.18359482288360596,
|
| 1758 |
+
"learning_rate": 0.0004172222222222222,
|
| 1759 |
+
"loss": 0.0331,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.2611862643080125,
|
| 1764 |
+
"grad_norm": 0.2370993047952652,
|
| 1765 |
+
"learning_rate": 0.0004166666666666667,
|
| 1766 |
+
"loss": 0.0568,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.26222684703433924,
|
| 1771 |
+
"grad_norm": 0.20278838276863098,
|
| 1772 |
+
"learning_rate": 0.00041611111111111113,
|
| 1773 |
+
"loss": 0.0542,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.26326742976066597,
|
| 1778 |
+
"grad_norm": 0.21301935613155365,
|
| 1779 |
+
"learning_rate": 0.00041555555555555557,
|
| 1780 |
+
"loss": 0.0514,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.2643080124869927,
|
| 1785 |
+
"grad_norm": 0.1811857521533966,
|
| 1786 |
+
"learning_rate": 0.000415,
|
| 1787 |
+
"loss": 0.0406,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.26534859521331944,
|
| 1792 |
+
"grad_norm": 0.22240598499774933,
|
| 1793 |
+
"learning_rate": 0.00041444444444444444,
|
| 1794 |
+
"loss": 0.0558,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.2663891779396462,
|
| 1799 |
+
"grad_norm": 0.19993361830711365,
|
| 1800 |
+
"learning_rate": 0.0004138888888888889,
|
| 1801 |
+
"loss": 0.0507,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.26742976066597296,
|
| 1806 |
+
"grad_norm": 0.2210732102394104,
|
| 1807 |
+
"learning_rate": 0.0004133333333333333,
|
| 1808 |
+
"loss": 0.0464,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.2684703433922997,
|
| 1813 |
+
"grad_norm": 0.24159833788871765,
|
| 1814 |
+
"learning_rate": 0.0004127777777777778,
|
| 1815 |
+
"loss": 0.0506,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.2695109261186264,
|
| 1820 |
+
"grad_norm": 0.19818955659866333,
|
| 1821 |
+
"learning_rate": 0.00041222222222222224,
|
| 1822 |
+
"loss": 0.0583,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.27055150884495316,
|
| 1827 |
+
"grad_norm": 0.34667930006980896,
|
| 1828 |
+
"learning_rate": 0.0004116666666666667,
|
| 1829 |
+
"loss": 0.0844,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.2715920915712799,
|
| 1834 |
+
"grad_norm": 0.2061154991388321,
|
| 1835 |
+
"learning_rate": 0.0004111111111111111,
|
| 1836 |
+
"loss": 0.0361,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.2726326742976067,
|
| 1841 |
+
"grad_norm": 0.3629634380340576,
|
| 1842 |
+
"learning_rate": 0.00041055555555555555,
|
| 1843 |
+
"loss": 0.0399,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.2736732570239334,
|
| 1848 |
+
"grad_norm": 0.22805607318878174,
|
| 1849 |
+
"learning_rate": 0.00041,
|
| 1850 |
+
"loss": 0.0665,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.27471383975026015,
|
| 1855 |
+
"grad_norm": 0.3538663983345032,
|
| 1856 |
+
"learning_rate": 0.00040944444444444443,
|
| 1857 |
+
"loss": 0.0564,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.2757544224765869,
|
| 1862 |
+
"grad_norm": 0.21005156636238098,
|
| 1863 |
+
"learning_rate": 0.0004088888888888889,
|
| 1864 |
+
"loss": 0.0513,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.2767950052029136,
|
| 1869 |
+
"grad_norm": 0.1628667265176773,
|
| 1870 |
+
"learning_rate": 0.00040833333333333336,
|
| 1871 |
+
"loss": 0.041,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.2778355879292404,
|
| 1876 |
+
"grad_norm": 0.1788283884525299,
|
| 1877 |
+
"learning_rate": 0.0004077777777777778,
|
| 1878 |
+
"loss": 0.0332,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.27887617065556713,
|
| 1883 |
+
"grad_norm": 0.2412905991077423,
|
| 1884 |
+
"learning_rate": 0.00040722222222222223,
|
| 1885 |
+
"loss": 0.0612,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.27991675338189387,
|
| 1890 |
+
"grad_norm": 0.14978761970996857,
|
| 1891 |
+
"learning_rate": 0.00040666666666666667,
|
| 1892 |
+
"loss": 0.0313,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.2809573361082206,
|
| 1897 |
+
"grad_norm": 0.1715932935476303,
|
| 1898 |
+
"learning_rate": 0.0004061111111111111,
|
| 1899 |
+
"loss": 0.0363,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.28199791883454733,
|
| 1904 |
+
"grad_norm": 0.20580480992794037,
|
| 1905 |
+
"learning_rate": 0.00040555555555555554,
|
| 1906 |
+
"loss": 0.038,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.28303850156087407,
|
| 1911 |
+
"grad_norm": 0.31613650918006897,
|
| 1912 |
+
"learning_rate": 0.00040500000000000003,
|
| 1913 |
+
"loss": 0.0456,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.28407908428720086,
|
| 1918 |
+
"grad_norm": 0.4305758476257324,
|
| 1919 |
+
"learning_rate": 0.00040444444444444447,
|
| 1920 |
+
"loss": 0.0853,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.2851196670135276,
|
| 1925 |
+
"grad_norm": 0.23432056605815887,
|
| 1926 |
+
"learning_rate": 0.0004038888888888889,
|
| 1927 |
+
"loss": 0.0565,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.2861602497398543,
|
| 1932 |
+
"grad_norm": 0.19864040613174438,
|
| 1933 |
+
"learning_rate": 0.00040333333333333334,
|
| 1934 |
+
"loss": 0.0434,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.28720083246618106,
|
| 1939 |
+
"grad_norm": 0.16542665660381317,
|
| 1940 |
+
"learning_rate": 0.0004027777777777778,
|
| 1941 |
+
"loss": 0.0412,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.2882414151925078,
|
| 1946 |
+
"grad_norm": 0.2191186547279358,
|
| 1947 |
+
"learning_rate": 0.0004022222222222222,
|
| 1948 |
+
"loss": 0.0331,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.2892819979188345,
|
| 1953 |
+
"grad_norm": 0.18664966523647308,
|
| 1954 |
+
"learning_rate": 0.00040166666666666665,
|
| 1955 |
+
"loss": 0.048,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.2903225806451613,
|
| 1960 |
+
"grad_norm": 0.2270483821630478,
|
| 1961 |
+
"learning_rate": 0.0004011111111111111,
|
| 1962 |
+
"loss": 0.0377,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.29136316337148804,
|
| 1967 |
+
"grad_norm": 0.24307194352149963,
|
| 1968 |
+
"learning_rate": 0.0004005555555555556,
|
| 1969 |
+
"loss": 0.0348,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.2924037460978148,
|
| 1974 |
+
"grad_norm": 0.2359393984079361,
|
| 1975 |
+
"learning_rate": 0.0004,
|
| 1976 |
+
"loss": 0.0544,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.2934443288241415,
|
| 1981 |
+
"grad_norm": 0.18014176189899445,
|
| 1982 |
+
"learning_rate": 0.00039944444444444446,
|
| 1983 |
+
"loss": 0.0511,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.29448491155046824,
|
| 1988 |
+
"grad_norm": 0.1786079704761505,
|
| 1989 |
+
"learning_rate": 0.0003988888888888889,
|
| 1990 |
+
"loss": 0.0423,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.29552549427679503,
|
| 1995 |
+
"grad_norm": 0.21372316777706146,
|
| 1996 |
+
"learning_rate": 0.00039833333333333333,
|
| 1997 |
+
"loss": 0.0376,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.29656607700312176,
|
| 2002 |
+
"grad_norm": 0.18096502125263214,
|
| 2003 |
+
"learning_rate": 0.00039777777777777777,
|
| 2004 |
+
"loss": 0.0403,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.2976066597294485,
|
| 2009 |
+
"grad_norm": 0.2152777463197708,
|
| 2010 |
+
"learning_rate": 0.0003972222222222222,
|
| 2011 |
+
"loss": 0.0479,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.29864724245577523,
|
| 2016 |
+
"grad_norm": 0.2060365378856659,
|
| 2017 |
+
"learning_rate": 0.0003966666666666667,
|
| 2018 |
+
"loss": 0.0421,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.29968782518210196,
|
| 2023 |
+
"grad_norm": 0.15571239590644836,
|
| 2024 |
+
"learning_rate": 0.00039611111111111113,
|
| 2025 |
+
"loss": 0.0358,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.3007284079084287,
|
| 2030 |
+
"grad_norm": 0.16673770546913147,
|
| 2031 |
+
"learning_rate": 0.00039555555555555557,
|
| 2032 |
+
"loss": 0.0327,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.3017689906347555,
|
| 2037 |
+
"grad_norm": 0.25307971239089966,
|
| 2038 |
+
"learning_rate": 0.000395,
|
| 2039 |
+
"loss": 0.0521,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.3028095733610822,
|
| 2044 |
+
"grad_norm": 0.21981365978717804,
|
| 2045 |
+
"learning_rate": 0.00039444444444444444,
|
| 2046 |
+
"loss": 0.0506,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.30385015608740895,
|
| 2051 |
+
"grad_norm": 0.21614228188991547,
|
| 2052 |
+
"learning_rate": 0.00039388888888888893,
|
| 2053 |
+
"loss": 0.0499,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.3048907388137357,
|
| 2058 |
+
"grad_norm": 0.18407006561756134,
|
| 2059 |
+
"learning_rate": 0.0003933333333333333,
|
| 2060 |
+
"loss": 0.0401,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.3059313215400624,
|
| 2065 |
+
"grad_norm": 0.17395204305648804,
|
| 2066 |
+
"learning_rate": 0.0003927777777777778,
|
| 2067 |
+
"loss": 0.043,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.30697190426638915,
|
| 2072 |
+
"grad_norm": 0.21453210711479187,
|
| 2073 |
+
"learning_rate": 0.00039222222222222225,
|
| 2074 |
+
"loss": 0.0543,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.30801248699271594,
|
| 2079 |
+
"grad_norm": 0.15130619704723358,
|
| 2080 |
+
"learning_rate": 0.0003916666666666667,
|
| 2081 |
+
"loss": 0.0315,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.3090530697190427,
|
| 2086 |
+
"grad_norm": 0.15348005294799805,
|
| 2087 |
+
"learning_rate": 0.0003911111111111111,
|
| 2088 |
+
"loss": 0.0441,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.3100936524453694,
|
| 2093 |
+
"grad_norm": 0.14079153537750244,
|
| 2094 |
+
"learning_rate": 0.00039055555555555556,
|
| 2095 |
+
"loss": 0.0408,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.31113423517169614,
|
| 2100 |
+
"grad_norm": 0.20261019468307495,
|
| 2101 |
+
"learning_rate": 0.00039000000000000005,
|
| 2102 |
+
"loss": 0.0494,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.31217481789802287,
|
| 2107 |
+
"grad_norm": 0.1492331326007843,
|
| 2108 |
+
"learning_rate": 0.00038944444444444443,
|
| 2109 |
+
"loss": 0.0349,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
}
|
| 2112 |
+
],
|
| 2113 |
+
"logging_steps": 1,
|
| 2114 |
+
"max_steps": 1000,
|
| 2115 |
+
"num_input_tokens_seen": 0,
|
| 2116 |
+
"num_train_epochs": 2,
|
| 2117 |
+
"save_steps": 100,
|
| 2118 |
+
"stateful_callbacks": {
|
| 2119 |
+
"TrainerControl": {
|
| 2120 |
+
"args": {
|
| 2121 |
+
"should_epoch_stop": false,
|
| 2122 |
+
"should_evaluate": false,
|
| 2123 |
+
"should_log": false,
|
| 2124 |
+
"should_save": true,
|
| 2125 |
+
"should_training_stop": false
|
| 2126 |
+
},
|
| 2127 |
+
"attributes": {}
|
| 2128 |
+
}
|
| 2129 |
+
},
|
| 2130 |
+
"total_flos": 0.0,
|
| 2131 |
+
"train_batch_size": 256,
|
| 2132 |
+
"trial_name": null,
|
| 2133 |
+
"trial_params": null
|
| 2134 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/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 |
+
}
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-400/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_add_distill_0.2_0.6_11_23_Classifier_Layer12_ImgText_V5_i_ret/checkpoint-500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/Qwen2_5vl_3B_multilayer_distill_AOP_pooling_all_12_10_h100_4_Classifier_Layer12_V5_i_ret_bsz128/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 |
+
}
|