Training in progress, step 78
Browse files- .gitattributes +1 -0
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- merges.txt +0 -0
- runs/Mar20_08-29-07_15a89ed742b0/events.out.tfevents.1773995368.15a89ed742b0.1167.0 +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- trainer_log.jsonl +79 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 16,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"target_parameters": null,
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"trainable_token_indices": null,
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_qalora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a80c0e1e541134d6511babf116893319412f0bc09454befab1810da3032d321
|
| 3 |
+
size 14766952
|
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 |
+
}
|
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 %}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/Mar20_08-29-07_15a89ed742b0/events.out.tfevents.1773995368.15a89ed742b0.1167.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ab821cc0e401f801748abb671f3ada38b30bdf4dc633ddb79f5c98aa7ed2be0
|
| 3 |
+
size 25134
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 78, "loss": 1.269, "lr": 0.0, "epoch": 0.039603960396039604, "percentage": 1.28, "elapsed_time": "0:00:24", "remaining_time": "0:31:35"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 78, "loss": 1.3028, "lr": 8.333333333333333e-07, "epoch": 0.07920792079207921, "percentage": 2.56, "elapsed_time": "0:00:45", "remaining_time": "0:28:45"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 78, "loss": 1.3045, "lr": 1.6666666666666667e-06, "epoch": 0.1188118811881188, "percentage": 3.85, "elapsed_time": "0:01:09", "remaining_time": "0:28:55"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 78, "loss": 1.1862, "lr": 2.5e-06, "epoch": 0.15841584158415842, "percentage": 5.13, "elapsed_time": "0:01:37", "remaining_time": "0:30:05"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 78, "loss": 1.2881, "lr": 3.3333333333333333e-06, "epoch": 0.19801980198019803, "percentage": 6.41, "elapsed_time": "0:02:03", "remaining_time": "0:30:07"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 78, "loss": 1.2305, "lr": 4.166666666666667e-06, "epoch": 0.2376237623762376, "percentage": 7.69, "elapsed_time": "0:02:30", "remaining_time": "0:30:03"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 78, "loss": 1.2752, "lr": 5e-06, "epoch": 0.27722772277227725, "percentage": 8.97, "elapsed_time": "0:02:51", "remaining_time": "0:28:55"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 78, "loss": 1.2844, "lr": 4.997620553954645e-06, "epoch": 0.31683168316831684, "percentage": 10.26, "elapsed_time": "0:03:17", "remaining_time": "0:28:44"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 78, "loss": 1.2924, "lr": 4.990486745229364e-06, "epoch": 0.3564356435643564, "percentage": 11.54, "elapsed_time": "0:03:40", "remaining_time": "0:28:08"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 78, "loss": 1.3115, "lr": 4.978612153434527e-06, "epoch": 0.39603960396039606, "percentage": 12.82, "elapsed_time": "0:04:02", "remaining_time": "0:27:29"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 78, "loss": 1.2923, "lr": 4.962019382530521e-06, "epoch": 0.43564356435643564, "percentage": 14.1, "elapsed_time": "0:04:30", "remaining_time": "0:27:26"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 78, "loss": 1.1861, "lr": 4.9407400177998335e-06, "epoch": 0.4752475247524752, "percentage": 15.38, "elapsed_time": "0:04:54", "remaining_time": "0:27:02"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 78, "loss": 1.2729, "lr": 4.914814565722671e-06, "epoch": 0.5148514851485149, "percentage": 16.67, "elapsed_time": "0:05:16", "remaining_time": "0:26:22"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 78, "loss": 1.1916, "lr": 4.884292376870567e-06, "epoch": 0.5544554455445545, "percentage": 17.95, "elapsed_time": "0:05:40", "remaining_time": "0:25:55"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 78, "loss": 1.2383, "lr": 4.849231551964771e-06, "epoch": 0.594059405940594, "percentage": 19.23, "elapsed_time": "0:06:07", "remaining_time": "0:25:42"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 78, "loss": 1.2663, "lr": 4.809698831278217e-06, "epoch": 0.6336633663366337, "percentage": 20.51, "elapsed_time": "0:06:34", "remaining_time": "0:25:27"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 78, "loss": 1.3337, "lr": 4.765769467591626e-06, "epoch": 0.6732673267326733, "percentage": 21.79, "elapsed_time": "0:06:56", "remaining_time": "0:24:55"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 78, "loss": 1.2452, "lr": 4.717527082945555e-06, "epoch": 0.7128712871287128, "percentage": 23.08, "elapsed_time": "0:07:24", "remaining_time": "0:24:41"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 78, "loss": 1.2692, "lr": 4.665063509461098e-06, "epoch": 0.7524752475247525, "percentage": 24.36, "elapsed_time": "0:07:49", "remaining_time": "0:24:18"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 78, "loss": 1.3198, "lr": 4.608478614532215e-06, "epoch": 0.7920792079207921, "percentage": 25.64, "elapsed_time": "0:08:13", "remaining_time": "0:23:49"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 78, "loss": 1.2443, "lr": 4.54788011072248e-06, "epoch": 0.8316831683168316, "percentage": 26.92, "elapsed_time": "0:08:35", "remaining_time": "0:23:19"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 78, "loss": 1.2804, "lr": 4.4833833507280884e-06, "epoch": 0.8712871287128713, "percentage": 28.21, "elapsed_time": "0:09:02", "remaining_time": "0:22:59"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 78, "loss": 1.2601, "lr": 4.415111107797445e-06, "epoch": 0.9108910891089109, "percentage": 29.49, "elapsed_time": "0:09:28", "remaining_time": "0:22:39"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 78, "loss": 1.318, "lr": 4.34319334202531e-06, "epoch": 0.9504950495049505, "percentage": 30.77, "elapsed_time": "0:09:53", "remaining_time": "0:22:14"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 78, "loss": 1.3144, "lr": 4.267766952966369e-06, "epoch": 0.9900990099009901, "percentage": 32.05, "elapsed_time": "0:10:18", "remaining_time": "0:21:52"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 78, "loss": 1.3198, "lr": 4.188975519039151e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:10:27", "remaining_time": "0:20:54"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 78, "loss": 1.2992, "lr": 4.106969024216348e-06, "epoch": 1.0396039603960396, "percentage": 34.62, "elapsed_time": "0:10:51", "remaining_time": "0:20:30"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 78, "loss": 1.2664, "lr": 4.021903572521802e-06, "epoch": 1.0792079207920793, "percentage": 35.9, "elapsed_time": "0:11:18", "remaining_time": "0:20:11"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 78, "loss": 1.2829, "lr": 3.933941090877615e-06, "epoch": 1.118811881188119, "percentage": 37.18, "elapsed_time": "0:11:43", "remaining_time": "0:19:49"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 78, "loss": 1.2943, "lr": 3.8432490208670605e-06, "epoch": 1.1584158415841583, "percentage": 38.46, "elapsed_time": "0:12:06", "remaining_time": "0:19:22"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 1.304, "lr": 3.7500000000000005e-06, "epoch": 1.198019801980198, "percentage": 39.74, "elapsed_time": "0:12:33", "remaining_time": "0:19:03"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 1.2328, "lr": 3.654371533087586e-06, "epoch": 1.2376237623762376, "percentage": 41.03, "elapsed_time": "0:12:57", "remaining_time": "0:18:38"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 1.2158, "lr": 3.556545654351749e-06, "epoch": 1.2772277227722773, "percentage": 42.31, "elapsed_time": "0:13:24", "remaining_time": "0:18:17"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 1.299, "lr": 3.4567085809127247e-06, "epoch": 1.316831683168317, "percentage": 43.59, "elapsed_time": "0:13:49", "remaining_time": "0:17:52"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 1.2121, "lr": 3.3550503583141726e-06, "epoch": 1.3564356435643563, "percentage": 44.87, "elapsed_time": "0:14:14", "remaining_time": "0:17:29"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 1.2247, "lr": 3.2517644987606827e-06, "epoch": 1.396039603960396, "percentage": 46.15, "elapsed_time": "0:14:44", "remaining_time": "0:17:12"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 1.2627, "lr": 3.147047612756302e-06, "epoch": 1.4356435643564356, "percentage": 47.44, "elapsed_time": "0:15:11", "remaining_time": "0:16:49"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 1.2729, "lr": 3.0410990348452572e-06, "epoch": 1.4752475247524752, "percentage": 48.72, "elapsed_time": "0:15:31", "remaining_time": "0:16:20"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 1.2694, "lr": 2.9341204441673267e-06, "epoch": 1.5148514851485149, "percentage": 50.0, "elapsed_time": "0:15:53", "remaining_time": "0:15:53"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 1.2964, "lr": 2.82631548055013e-06, "epoch": 1.5544554455445545, "percentage": 51.28, "elapsed_time": "0:16:17", "remaining_time": "0:15:28"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 1.2762, "lr": 2.717889356869146e-06, "epoch": 1.5940594059405941, "percentage": 52.56, "elapsed_time": "0:16:38", "remaining_time": "0:15:01"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 1.2774, "lr": 2.6090484684133406e-06, "epoch": 1.6336633663366338, "percentage": 53.85, "elapsed_time": "0:17:00", "remaining_time": "0:14:35"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 1.2428, "lr": 2.5e-06, "epoch": 1.6732673267326734, "percentage": 55.13, "elapsed_time": "0:17:28", "remaining_time": "0:14:13"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 1.262, "lr": 2.3909515315866606e-06, "epoch": 1.7128712871287128, "percentage": 56.41, "elapsed_time": "0:17:54", "remaining_time": "0:13:49"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 1.2404, "lr": 2.2821106431308546e-06, "epoch": 1.7524752475247525, "percentage": 57.69, "elapsed_time": "0:18:20", "remaining_time": "0:13:27"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 1.3111, "lr": 2.173684519449872e-06, "epoch": 1.7920792079207921, "percentage": 58.97, "elapsed_time": "0:18:47", "remaining_time": "0:13:04"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 1.1982, "lr": 2.0658795558326745e-06, "epoch": 1.8316831683168315, "percentage": 60.26, "elapsed_time": "0:19:12", "remaining_time": "0:12:40"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 1.1989, "lr": 1.958900965154743e-06, "epoch": 1.8712871287128712, "percentage": 61.54, "elapsed_time": "0:19:39", "remaining_time": "0:12:17"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 1.291, "lr": 1.852952387243698e-06, "epoch": 1.9108910891089108, "percentage": 62.82, "elapsed_time": "0:20:05", "remaining_time": "0:11:53"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 1.3128, "lr": 1.7482355012393177e-06, "epoch": 1.9504950495049505, "percentage": 64.1, "elapsed_time": "0:20:31", "remaining_time": "0:11:29"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 1.2365, "lr": 1.6449496416858285e-06, "epoch": 1.99009900990099, "percentage": 65.38, "elapsed_time": "0:20:58", "remaining_time": "0:11:06"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 1.3676, "lr": 1.5432914190872757e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:21:05", "remaining_time": "0:10:32"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.246, "lr": 1.443454345648252e-06, "epoch": 2.0396039603960396, "percentage": 67.95, "elapsed_time": "0:21:29", "remaining_time": "0:10:08"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 78, "loss": 1.2763, "lr": 1.3456284669124159e-06, "epoch": 2.0792079207920793, "percentage": 69.23, "elapsed_time": "0:21:57", "remaining_time": "0:09:45"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 78, "loss": 1.2776, "lr": 1.2500000000000007e-06, "epoch": 2.118811881188119, "percentage": 70.51, "elapsed_time": "0:22:22", "remaining_time": "0:09:21"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 78, "loss": 1.3065, "lr": 1.1567509791329402e-06, "epoch": 2.1584158415841586, "percentage": 71.79, "elapsed_time": "0:22:48", "remaining_time": "0:08:57"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 78, "loss": 1.2373, "lr": 1.0660589091223854e-06, "epoch": 2.198019801980198, "percentage": 73.08, "elapsed_time": "0:23:14", "remaining_time": "0:08:33"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 78, "loss": 1.3325, "lr": 9.780964274781984e-07, "epoch": 2.237623762376238, "percentage": 74.36, "elapsed_time": "0:23:36", "remaining_time": "0:08:08"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 78, "loss": 1.2723, "lr": 8.930309757836517e-07, "epoch": 2.2772277227722775, "percentage": 75.64, "elapsed_time": "0:23:57", "remaining_time": "0:07:42"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 78, "loss": 1.293, "lr": 8.110244809608494e-07, "epoch": 2.3168316831683167, "percentage": 76.92, "elapsed_time": "0:24:22", "remaining_time": "0:07:18"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 78, "loss": 1.2768, "lr": 7.322330470336314e-07, "epoch": 2.3564356435643563, "percentage": 78.21, "elapsed_time": "0:24:47", "remaining_time": "0:06:54"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 78, "loss": 1.1868, "lr": 6.568066579746901e-07, "epoch": 2.396039603960396, "percentage": 79.49, "elapsed_time": "0:25:13", "remaining_time": "0:06:30"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 78, "loss": 1.2964, "lr": 5.848888922025553e-07, "epoch": 2.4356435643564356, "percentage": 80.77, "elapsed_time": "0:25:36", "remaining_time": "0:06:05"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 78, "loss": 1.2803, "lr": 5.166166492719124e-07, "epoch": 2.4752475247524752, "percentage": 82.05, "elapsed_time": "0:26:01", "remaining_time": "0:05:41"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 78, "loss": 1.2622, "lr": 4.5211988927752026e-07, "epoch": 2.514851485148515, "percentage": 83.33, "elapsed_time": "0:26:22", "remaining_time": "0:05:16"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 78, "loss": 1.2723, "lr": 3.915213854677863e-07, "epoch": 2.5544554455445545, "percentage": 84.62, "elapsed_time": "0:26:48", "remaining_time": "0:04:52"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 78, "loss": 1.2719, "lr": 3.3493649053890325e-07, "epoch": 2.594059405940594, "percentage": 85.9, "elapsed_time": "0:27:15", "remaining_time": "0:04:28"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 78, "loss": 1.1842, "lr": 2.8247291705444575e-07, "epoch": 2.633663366336634, "percentage": 87.18, "elapsed_time": "0:27:41", "remaining_time": "0:04:04"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 78, "loss": 1.2481, "lr": 2.3423053240837518e-07, "epoch": 2.6732673267326734, "percentage": 88.46, "elapsed_time": "0:28:09", "remaining_time": "0:03:40"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 78, "loss": 1.2355, "lr": 1.9030116872178317e-07, "epoch": 2.7128712871287126, "percentage": 89.74, "elapsed_time": "0:28:36", "remaining_time": "0:03:16"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 78, "loss": 1.2041, "lr": 1.507684480352292e-07, "epoch": 2.7524752475247523, "percentage": 91.03, "elapsed_time": "0:29:00", "remaining_time": "0:02:51"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 78, "loss": 1.2795, "lr": 1.1570762312943295e-07, "epoch": 2.792079207920792, "percentage": 92.31, "elapsed_time": "0:29:21", "remaining_time": "0:02:26"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 78, "loss": 1.2717, "lr": 8.518543427732951e-08, "epoch": 2.8316831683168315, "percentage": 93.59, "elapsed_time": "0:29:43", "remaining_time": "0:02:02"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 78, "loss": 1.2322, "lr": 5.92599822001666e-08, "epoch": 2.871287128712871, "percentage": 94.87, "elapsed_time": "0:30:06", "remaining_time": "0:01:37"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 78, "loss": 1.2791, "lr": 3.798061746947995e-08, "epoch": 2.910891089108911, "percentage": 96.15, "elapsed_time": "0:30:31", "remaining_time": "0:01:13"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 78, "loss": 1.2509, "lr": 2.1387846565474047e-08, "epoch": 2.9504950495049505, "percentage": 97.44, "elapsed_time": "0:30:58", "remaining_time": "0:00:48"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 78, "loss": 1.2535, "lr": 9.513254770636138e-09, "epoch": 2.99009900990099, "percentage": 98.72, "elapsed_time": "0:31:26", "remaining_time": "0:00:24"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 78, "loss": 1.2348, "lr": 2.3794460453555046e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:31:35", "remaining_time": "0:00:00"}
|
| 79 |
+
{"current_steps": 78, "total_steps": 78, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:31:37", "remaining_time": "0:00:00"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d867c35b946144b4e32767f7e72efa41cb33ed5d01d2ea28e00ad4e4c484ae17
|
| 3 |
+
size 6353
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|