latest training checkpoint
Browse filesnot all the files were pushed to huggingface after training
- adapter_config.json +27 -27
- generation_config.json +9 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -23
- tokenizer.json +2 -2
- tokenizer_config.json +195 -195
- trainer_state.json +563 -0
adapter_config.json
CHANGED
|
@@ -1,28 +1,28 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": false,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layers_pattern": null,
|
| 10 |
-
"layers_to_transform": null,
|
| 11 |
-
"loftq_config": {},
|
| 12 |
-
"lora_alpha": 16,
|
| 13 |
-
"lora_dropout": 0.1,
|
| 14 |
-
"megatron_config": null,
|
| 15 |
-
"megatron_core": "megatron.core",
|
| 16 |
-
"modules_to_save": null,
|
| 17 |
-
"peft_type": "LORA",
|
| 18 |
-
"r": 64,
|
| 19 |
-
"rank_pattern": {},
|
| 20 |
-
"revision": null,
|
| 21 |
-
"target_modules": [
|
| 22 |
-
"v_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
-
"o_proj",
|
| 25 |
-
"q_proj"
|
| 26 |
-
],
|
| 27 |
-
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"q_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.48.1"
|
| 9 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccbfc43bd01ba12dab30c58e7339048877e7ae60f576ce22eb9e47a3e4a95407
|
| 3 |
+
size 35674618
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfddc12c09ed68ce102a9ef57f981c5e4cedd262ad7aee169a63e2dbf351ac69
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31b716b23b3a1c16554a0f288cd041670104f4c187deb0150cab279be98f0445
|
| 3 |
+
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,23 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:253accc92cf719c21724d425d5158ff4ee96a808ba33dbf033067f5df9633eff
|
| 3 |
+
size 12180269
|
tokenizer_config.json
CHANGED
|
@@ -1,195 +1,195 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"151643": {
|
| 7 |
-
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"151644": {
|
| 15 |
-
"content": "<｜User｜>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": false
|
| 21 |
-
},
|
| 22 |
-
"151645": {
|
| 23 |
-
"content": "<｜Assistant｜>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": false
|
| 29 |
-
},
|
| 30 |
-
"151646": {
|
| 31 |
-
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": true
|
| 37 |
-
},
|
| 38 |
-
"151647": {
|
| 39 |
-
"content": "<|EOT|>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": false
|
| 45 |
-
},
|
| 46 |
-
"151648": {
|
| 47 |
-
"content": "<think>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": false,
|
| 50 |
-
"rstrip": false,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": false
|
| 53 |
-
},
|
| 54 |
-
"151649": {
|
| 55 |
-
"content": "</think>",
|
| 56 |
-
"lstrip": false,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"rstrip": false,
|
| 59 |
-
"single_word": false,
|
| 60 |
-
"special": false
|
| 61 |
-
},
|
| 62 |
-
"151650": {
|
| 63 |
-
"content": "<|quad_start|>",
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"normalized": false,
|
| 66 |
-
"rstrip": false,
|
| 67 |
-
"single_word": false,
|
| 68 |
-
"special": true
|
| 69 |
-
},
|
| 70 |
-
"151651": {
|
| 71 |
-
"content": "<|quad_end|>",
|
| 72 |
-
"lstrip": false,
|
| 73 |
-
"normalized": false,
|
| 74 |
-
"rstrip": false,
|
| 75 |
-
"single_word": false,
|
| 76 |
-
"special": true
|
| 77 |
-
},
|
| 78 |
-
"151652": {
|
| 79 |
-
"content": "<|vision_start|>",
|
| 80 |
-
"lstrip": false,
|
| 81 |
-
"normalized": false,
|
| 82 |
-
"rstrip": false,
|
| 83 |
-
"single_word": false,
|
| 84 |
-
"special": true
|
| 85 |
-
},
|
| 86 |
-
"151653": {
|
| 87 |
-
"content": "<|vision_end|>",
|
| 88 |
-
"lstrip": false,
|
| 89 |
-
"normalized": false,
|
| 90 |
-
"rstrip": false,
|
| 91 |
-
"single_word": false,
|
| 92 |
-
"special": true
|
| 93 |
-
},
|
| 94 |
-
"151654": {
|
| 95 |
-
"content": "<|vision_pad|>",
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"normalized": false,
|
| 98 |
-
"rstrip": false,
|
| 99 |
-
"single_word": false,
|
| 100 |
-
"special": true
|
| 101 |
-
},
|
| 102 |
-
"151655": {
|
| 103 |
-
"content": "<|image_pad|>",
|
| 104 |
-
"lstrip": false,
|
| 105 |
-
"normalized": false,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"single_word": false,
|
| 108 |
-
"special": true
|
| 109 |
-
},
|
| 110 |
-
"151656": {
|
| 111 |
-
"content": "<|video_pad|>",
|
| 112 |
-
"lstrip": false,
|
| 113 |
-
"normalized": false,
|
| 114 |
-
"rstrip": false,
|
| 115 |
-
"single_word": false,
|
| 116 |
-
"special": true
|
| 117 |
-
},
|
| 118 |
-
"151657": {
|
| 119 |
-
"content": "<tool_call>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": false,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false,
|
| 124 |
-
"special": false
|
| 125 |
-
},
|
| 126 |
-
"151658": {
|
| 127 |
-
"content": "</tool_call>",
|
| 128 |
-
"lstrip": false,
|
| 129 |
-
"normalized": false,
|
| 130 |
-
"rstrip": false,
|
| 131 |
-
"single_word": false,
|
| 132 |
-
"special": false
|
| 133 |
-
},
|
| 134 |
-
"151659": {
|
| 135 |
-
"content": "<|fim_prefix|>",
|
| 136 |
-
"lstrip": false,
|
| 137 |
-
"normalized": false,
|
| 138 |
-
"rstrip": false,
|
| 139 |
-
"single_word": false,
|
| 140 |
-
"special": false
|
| 141 |
-
},
|
| 142 |
-
"151660": {
|
| 143 |
-
"content": "<|fim_middle|>",
|
| 144 |
-
"lstrip": false,
|
| 145 |
-
"normalized": false,
|
| 146 |
-
"rstrip": false,
|
| 147 |
-
"single_word": false,
|
| 148 |
-
"special": false
|
| 149 |
-
},
|
| 150 |
-
"151661": {
|
| 151 |
-
"content": "<|fim_suffix|>",
|
| 152 |
-
"lstrip": false,
|
| 153 |
-
"normalized": false,
|
| 154 |
-
"rstrip": false,
|
| 155 |
-
"single_word": false,
|
| 156 |
-
"special": false
|
| 157 |
-
},
|
| 158 |
-
"151662": {
|
| 159 |
-
"content": "<|fim_pad|>",
|
| 160 |
-
"lstrip": false,
|
| 161 |
-
"normalized": false,
|
| 162 |
-
"rstrip": false,
|
| 163 |
-
"single_word": false,
|
| 164 |
-
"special": false
|
| 165 |
-
},
|
| 166 |
-
"151663": {
|
| 167 |
-
"content": "<|repo_name|>",
|
| 168 |
-
"lstrip": false,
|
| 169 |
-
"normalized": false,
|
| 170 |
-
"rstrip": false,
|
| 171 |
-
"single_word": false,
|
| 172 |
-
"special": false
|
| 173 |
-
},
|
| 174 |
-
"151664": {
|
| 175 |
-
"content": "<|file_sep|>",
|
| 176 |
-
"lstrip": false,
|
| 177 |
-
"normalized": false,
|
| 178 |
-
"rstrip": false,
|
| 179 |
-
"single_word": false,
|
| 180 |
-
"special": false
|
| 181 |
-
}
|
| 182 |
-
},
|
| 183 |
-
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 185 |
-
"clean_up_tokenization_spaces": false,
|
| 186 |
-
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
-
"extra_special_tokens": {},
|
| 188 |
-
"legacy": true,
|
| 189 |
-
"model_max_length": 16384,
|
| 190 |
-
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
-
"sp_model_kwargs": {},
|
| 192 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
-
"unk_token": null,
|
| 194 |
-
"use_default_system_prompt": false
|
| 195 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,563 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.695652173913043,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 70,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06956521739130435,
|
| 13 |
+
"grad_norm": 0.027621353045105934,
|
| 14 |
+
"learning_rate": 1.9989930665413148e-05,
|
| 15 |
+
"loss": 0.6357,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1391304347826087,
|
| 20 |
+
"grad_norm": 0.027610378339886665,
|
| 21 |
+
"learning_rate": 1.9959742939952393e-05,
|
| 22 |
+
"loss": 0.6181,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.20869565217391303,
|
| 27 |
+
"grad_norm": 0.029305126518011093,
|
| 28 |
+
"learning_rate": 1.990949761767935e-05,
|
| 29 |
+
"loss": 0.642,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2782608695652174,
|
| 34 |
+
"grad_norm": 0.028681788593530655,
|
| 35 |
+
"learning_rate": 1.98392958859863e-05,
|
| 36 |
+
"loss": 0.646,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.34782608695652173,
|
| 41 |
+
"grad_norm": 0.028845500200986862,
|
| 42 |
+
"learning_rate": 1.9749279121818235e-05,
|
| 43 |
+
"loss": 0.6416,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41739130434782606,
|
| 48 |
+
"grad_norm": 0.03184295445680618,
|
| 49 |
+
"learning_rate": 1.9639628606958535e-05,
|
| 50 |
+
"loss": 0.6625,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.48695652173913045,
|
| 55 |
+
"grad_norm": 0.030502479523420334,
|
| 56 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 57 |
+
"loss": 0.645,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5565217391304348,
|
| 62 |
+
"grad_norm": 0.030076082795858383,
|
| 63 |
+
"learning_rate": 1.9362348706397374e-05,
|
| 64 |
+
"loss": 0.6285,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.6260869565217392,
|
| 69 |
+
"grad_norm": 0.032947439700365067,
|
| 70 |
+
"learning_rate": 1.919527772551451e-05,
|
| 71 |
+
"loss": 0.6641,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6956521739130435,
|
| 76 |
+
"grad_norm": 0.03192123770713806,
|
| 77 |
+
"learning_rate": 1.900968867902419e-05,
|
| 78 |
+
"loss": 0.6508,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.7652173913043478,
|
| 83 |
+
"grad_norm": 0.0321270152926445,
|
| 84 |
+
"learning_rate": 1.880595531856738e-05,
|
| 85 |
+
"loss": 0.6436,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8347826086956521,
|
| 90 |
+
"grad_norm": 0.03189520537853241,
|
| 91 |
+
"learning_rate": 1.8584487936018663e-05,
|
| 92 |
+
"loss": 0.6653,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.9043478260869565,
|
| 97 |
+
"grad_norm": 0.03357314690947533,
|
| 98 |
+
"learning_rate": 1.834573253721303e-05,
|
| 99 |
+
"loss": 0.636,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.9739130434782609,
|
| 104 |
+
"grad_norm": 0.031242311000823975,
|
| 105 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 106 |
+
"loss": 0.6537,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0,
|
| 111 |
+
"grad_norm": 0.03731789439916611,
|
| 112 |
+
"learning_rate": 1.78183148246803e-05,
|
| 113 |
+
"loss": 0.6894,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0,
|
| 118 |
+
"eval_loss": 0.6298047304153442,
|
| 119 |
+
"eval_runtime": 2.6261,
|
| 120 |
+
"eval_samples_per_second": 1.523,
|
| 121 |
+
"eval_steps_per_second": 1.523,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0695652173913044,
|
| 126 |
+
"grad_norm": 0.0358547680079937,
|
| 127 |
+
"learning_rate": 1.7530714660036112e-05,
|
| 128 |
+
"loss": 0.6516,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.1391304347826088,
|
| 133 |
+
"grad_norm": 0.0324733592569828,
|
| 134 |
+
"learning_rate": 1.7227948638273918e-05,
|
| 135 |
+
"loss": 0.6244,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.208695652173913,
|
| 140 |
+
"grad_norm": 0.03361370787024498,
|
| 141 |
+
"learning_rate": 1.691062648986865e-05,
|
| 142 |
+
"loss": 0.6417,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.2782608695652173,
|
| 147 |
+
"grad_norm": 0.033928435295820236,
|
| 148 |
+
"learning_rate": 1.657938725939713e-05,
|
| 149 |
+
"loss": 0.6601,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.3478260869565217,
|
| 154 |
+
"grad_norm": 0.03608125448226929,
|
| 155 |
+
"learning_rate": 1.6234898018587336e-05,
|
| 156 |
+
"loss": 0.6532,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.4173913043478261,
|
| 161 |
+
"grad_norm": 0.03397082909941673,
|
| 162 |
+
"learning_rate": 1.5877852522924733e-05,
|
| 163 |
+
"loss": 0.6205,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.4869565217391305,
|
| 168 |
+
"grad_norm": 0.03406910225749016,
|
| 169 |
+
"learning_rate": 1.5508969814521026e-05,
|
| 170 |
+
"loss": 0.6256,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.5565217391304347,
|
| 175 |
+
"grad_norm": 0.034135762602090836,
|
| 176 |
+
"learning_rate": 1.5128992774059063e-05,
|
| 177 |
+
"loss": 0.6332,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.626086956521739,
|
| 182 |
+
"grad_norm": 0.03473026305437088,
|
| 183 |
+
"learning_rate": 1.4738686624729987e-05,
|
| 184 |
+
"loss": 0.6561,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.6956521739130435,
|
| 189 |
+
"grad_norm": 0.03459230437874794,
|
| 190 |
+
"learning_rate": 1.4338837391175582e-05,
|
| 191 |
+
"loss": 0.6391,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.7652173913043478,
|
| 196 |
+
"grad_norm": 0.0341939777135849,
|
| 197 |
+
"learning_rate": 1.3930250316539237e-05,
|
| 198 |
+
"loss": 0.6393,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.8347826086956522,
|
| 203 |
+
"grad_norm": 0.03445998951792717,
|
| 204 |
+
"learning_rate": 1.3513748240813429e-05,
|
| 205 |
+
"loss": 0.6429,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.9043478260869566,
|
| 210 |
+
"grad_norm": 0.03501657024025917,
|
| 211 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 212 |
+
"loss": 0.6483,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.973913043478261,
|
| 217 |
+
"grad_norm": 0.03379024565219879,
|
| 218 |
+
"learning_rate": 1.2660368455666752e-05,
|
| 219 |
+
"loss": 0.6247,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.0,
|
| 224 |
+
"grad_norm": 0.034777939319610596,
|
| 225 |
+
"learning_rate": 1.2225209339563144e-05,
|
| 226 |
+
"loss": 0.6324,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.0,
|
| 231 |
+
"eval_loss": 0.620289146900177,
|
| 232 |
+
"eval_runtime": 2.6255,
|
| 233 |
+
"eval_samples_per_second": 1.524,
|
| 234 |
+
"eval_steps_per_second": 1.524,
|
| 235 |
+
"step": 30
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.0695652173913044,
|
| 239 |
+
"grad_norm": 0.035359956324100494,
|
| 240 |
+
"learning_rate": 1.1785568947986368e-05,
|
| 241 |
+
"loss": 0.6416,
|
| 242 |
+
"step": 31
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.139130434782609,
|
| 246 |
+
"grad_norm": 0.03541162610054016,
|
| 247 |
+
"learning_rate": 1.1342332658176556e-05,
|
| 248 |
+
"loss": 0.6432,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.208695652173913,
|
| 253 |
+
"grad_norm": 0.03285665437579155,
|
| 254 |
+
"learning_rate": 1.0896393089034336e-05,
|
| 255 |
+
"loss": 0.6128,
|
| 256 |
+
"step": 33
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.2782608695652176,
|
| 260 |
+
"grad_norm": 0.03517802432179451,
|
| 261 |
+
"learning_rate": 1.044864830350515e-05,
|
| 262 |
+
"loss": 0.6557,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.3478260869565215,
|
| 267 |
+
"grad_norm": 0.03373734652996063,
|
| 268 |
+
"learning_rate": 1e-05,
|
| 269 |
+
"loss": 0.6298,
|
| 270 |
+
"step": 35
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.417391304347826,
|
| 274 |
+
"grad_norm": 0.0340682752430439,
|
| 275 |
+
"learning_rate": 9.551351696494854e-06,
|
| 276 |
+
"loss": 0.6192,
|
| 277 |
+
"step": 36
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.4869565217391303,
|
| 281 |
+
"grad_norm": 0.03553012013435364,
|
| 282 |
+
"learning_rate": 9.103606910965666e-06,
|
| 283 |
+
"loss": 0.637,
|
| 284 |
+
"step": 37
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.5565217391304347,
|
| 288 |
+
"grad_norm": 0.036372989416122437,
|
| 289 |
+
"learning_rate": 8.657667341823449e-06,
|
| 290 |
+
"loss": 0.6286,
|
| 291 |
+
"step": 38
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.626086956521739,
|
| 295 |
+
"grad_norm": 0.03410479426383972,
|
| 296 |
+
"learning_rate": 8.214431052013636e-06,
|
| 297 |
+
"loss": 0.602,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.6956521739130435,
|
| 302 |
+
"grad_norm": 0.035654351115226746,
|
| 303 |
+
"learning_rate": 7.774790660436857e-06,
|
| 304 |
+
"loss": 0.6282,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.765217391304348,
|
| 309 |
+
"grad_norm": 0.03418293967843056,
|
| 310 |
+
"learning_rate": 7.33963154433325e-06,
|
| 311 |
+
"loss": 0.6384,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.8347826086956522,
|
| 316 |
+
"grad_norm": 0.035010650753974915,
|
| 317 |
+
"learning_rate": 6.909830056250527e-06,
|
| 318 |
+
"loss": 0.6232,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.9043478260869566,
|
| 323 |
+
"grad_norm": 0.03416571021080017,
|
| 324 |
+
"learning_rate": 6.486251759186573e-06,
|
| 325 |
+
"loss": 0.6533,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.973913043478261,
|
| 330 |
+
"grad_norm": 0.03395598754286766,
|
| 331 |
+
"learning_rate": 6.069749683460765e-06,
|
| 332 |
+
"loss": 0.6205,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.0,
|
| 337 |
+
"grad_norm": 0.0333721823990345,
|
| 338 |
+
"learning_rate": 5.66116260882442e-06,
|
| 339 |
+
"loss": 0.6163,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.0,
|
| 344 |
+
"eval_loss": 0.6122885942459106,
|
| 345 |
+
"eval_runtime": 2.6295,
|
| 346 |
+
"eval_samples_per_second": 1.521,
|
| 347 |
+
"eval_steps_per_second": 1.521,
|
| 348 |
+
"step": 45
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.0695652173913044,
|
| 352 |
+
"grad_norm": 0.033700425177812576,
|
| 353 |
+
"learning_rate": 5.2613133752700145e-06,
|
| 354 |
+
"loss": 0.6408,
|
| 355 |
+
"step": 46
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 3.139130434782609,
|
| 359 |
+
"grad_norm": 0.03324361890554428,
|
| 360 |
+
"learning_rate": 4.87100722594094e-06,
|
| 361 |
+
"loss": 0.62,
|
| 362 |
+
"step": 47
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.208695652173913,
|
| 366 |
+
"grad_norm": 0.03405730798840523,
|
| 367 |
+
"learning_rate": 4.491030185478976e-06,
|
| 368 |
+
"loss": 0.6257,
|
| 369 |
+
"step": 48
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.2782608695652176,
|
| 373 |
+
"grad_norm": 0.03492354601621628,
|
| 374 |
+
"learning_rate": 4.12214747707527e-06,
|
| 375 |
+
"loss": 0.6349,
|
| 376 |
+
"step": 49
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 3.3478260869565215,
|
| 380 |
+
"grad_norm": 0.034349583089351654,
|
| 381 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 382 |
+
"loss": 0.6282,
|
| 383 |
+
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.417391304347826,
|
| 387 |
+
"grad_norm": 0.03548488765954971,
|
| 388 |
+
"learning_rate": 3.4206127406028744e-06,
|
| 389 |
+
"loss": 0.6427,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.4869565217391303,
|
| 394 |
+
"grad_norm": 0.03456812724471092,
|
| 395 |
+
"learning_rate": 3.089373510131354e-06,
|
| 396 |
+
"loss": 0.62,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 3.5565217391304347,
|
| 401 |
+
"grad_norm": 0.03488166257739067,
|
| 402 |
+
"learning_rate": 2.7720513617260857e-06,
|
| 403 |
+
"loss": 0.6263,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.626086956521739,
|
| 408 |
+
"grad_norm": 0.0336606539785862,
|
| 409 |
+
"learning_rate": 2.469285339963892e-06,
|
| 410 |
+
"loss": 0.63,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.6956521739130435,
|
| 415 |
+
"grad_norm": 0.03267661854624748,
|
| 416 |
+
"learning_rate": 2.1816851753197023e-06,
|
| 417 |
+
"loss": 0.6297,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 3.765217391304348,
|
| 422 |
+
"grad_norm": 0.0337102934718132,
|
| 423 |
+
"learning_rate": 1.9098300562505266e-06,
|
| 424 |
+
"loss": 0.5945,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.8347826086956522,
|
| 429 |
+
"grad_norm": 0.035517044365406036,
|
| 430 |
+
"learning_rate": 1.6542674627869738e-06,
|
| 431 |
+
"loss": 0.6343,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.9043478260869566,
|
| 436 |
+
"grad_norm": 0.03479280695319176,
|
| 437 |
+
"learning_rate": 1.4155120639813392e-06,
|
| 438 |
+
"loss": 0.6163,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.973913043478261,
|
| 443 |
+
"grad_norm": 0.035013146698474884,
|
| 444 |
+
"learning_rate": 1.19404468143262e-06,
|
| 445 |
+
"loss": 0.6114,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.0,
|
| 450 |
+
"grad_norm": 0.03396342694759369,
|
| 451 |
+
"learning_rate": 9.903113209758098e-07,
|
| 452 |
+
"loss": 0.6191,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.0,
|
| 457 |
+
"eval_loss": 0.609683632850647,
|
| 458 |
+
"eval_runtime": 2.6229,
|
| 459 |
+
"eval_samples_per_second": 1.525,
|
| 460 |
+
"eval_steps_per_second": 1.525,
|
| 461 |
+
"step": 60
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.069565217391304,
|
| 465 |
+
"grad_norm": 0.03345245122909546,
|
| 466 |
+
"learning_rate": 8.047222744854943e-07,
|
| 467 |
+
"loss": 0.6416,
|
| 468 |
+
"step": 61
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 4.139130434782609,
|
| 472 |
+
"grad_norm": 0.03468826040625572,
|
| 473 |
+
"learning_rate": 6.37651293602628e-07,
|
| 474 |
+
"loss": 0.6269,
|
| 475 |
+
"step": 62
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 4.208695652173913,
|
| 479 |
+
"grad_norm": 0.031891003251075745,
|
| 480 |
+
"learning_rate": 4.894348370484648e-07,
|
| 481 |
+
"loss": 0.6147,
|
| 482 |
+
"step": 63
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.278260869565218,
|
| 486 |
+
"grad_norm": 0.033924877643585205,
|
| 487 |
+
"learning_rate": 3.603713930414676e-07,
|
| 488 |
+
"loss": 0.611,
|
| 489 |
+
"step": 64
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.3478260869565215,
|
| 493 |
+
"grad_norm": 0.033348944038152695,
|
| 494 |
+
"learning_rate": 2.507208781817638e-07,
|
| 495 |
+
"loss": 0.6372,
|
| 496 |
+
"step": 65
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 4.417391304347826,
|
| 500 |
+
"grad_norm": 0.03544296696782112,
|
| 501 |
+
"learning_rate": 1.6070411401370335e-07,
|
| 502 |
+
"loss": 0.6176,
|
| 503 |
+
"step": 66
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.48695652173913,
|
| 507 |
+
"grad_norm": 0.03346049040555954,
|
| 508 |
+
"learning_rate": 9.0502382320653e-08,
|
| 509 |
+
"loss": 0.6282,
|
| 510 |
+
"step": 67
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 4.556521739130435,
|
| 514 |
+
"grad_norm": 0.03482738509774208,
|
| 515 |
+
"learning_rate": 4.025706004760932e-08,
|
| 516 |
+
"loss": 0.6432,
|
| 517 |
+
"step": 68
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 4.626086956521739,
|
| 521 |
+
"grad_norm": 0.03497692570090294,
|
| 522 |
+
"learning_rate": 1.0069334586854106e-08,
|
| 523 |
+
"loss": 0.6121,
|
| 524 |
+
"step": 69
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.695652173913043,
|
| 528 |
+
"grad_norm": 0.034334901720285416,
|
| 529 |
+
"learning_rate": 0.0,
|
| 530 |
+
"loss": 0.6054,
|
| 531 |
+
"step": 70
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 4.695652173913043,
|
| 535 |
+
"eval_loss": 0.609480619430542,
|
| 536 |
+
"eval_runtime": 2.628,
|
| 537 |
+
"eval_samples_per_second": 1.522,
|
| 538 |
+
"eval_steps_per_second": 1.522,
|
| 539 |
+
"step": 70
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"logging_steps": 1,
|
| 543 |
+
"max_steps": 70,
|
| 544 |
+
"num_input_tokens_seen": 0,
|
| 545 |
+
"num_train_epochs": 5,
|
| 546 |
+
"save_steps": 500,
|
| 547 |
+
"stateful_callbacks": {
|
| 548 |
+
"TrainerControl": {
|
| 549 |
+
"args": {
|
| 550 |
+
"should_epoch_stop": false,
|
| 551 |
+
"should_evaluate": false,
|
| 552 |
+
"should_log": false,
|
| 553 |
+
"should_save": true,
|
| 554 |
+
"should_training_stop": true
|
| 555 |
+
},
|
| 556 |
+
"attributes": {}
|
| 557 |
+
}
|
| 558 |
+
},
|
| 559 |
+
"total_flos": 1.657443415228416e+17,
|
| 560 |
+
"train_batch_size": 1,
|
| 561 |
+
"trial_name": null,
|
| 562 |
+
"trial_params": null
|
| 563 |
+
}
|