Upload folder using huggingface_hub
Browse files- adapter_config.json +1 -1
- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +4 -32
- tokenizer.json +0 -18
- tokenizer_config.json +2 -22
- trainer_state.json +152 -194
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100299853
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bae2073e36bb32cfbba8de769e77f64c03b07ec350b5827681ed7636c12884c1
|
| 3 |
size 100299853
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 200654493
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecbc943d06bb9e8c8a39e4f638b03e0faf3ed5c5c2026eadf7f0c97048905bf6
|
| 3 |
size 200654493
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ecb1da131f28ebbdaed7969d4c7cdc38820701e74de5e10734a014050ce8ad
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d95b72119680d337f83be2a4d08a065f8278279b4937edf5107b5f0d8275c4a5
|
| 3 |
size 627
|
special_tokens_map.json
CHANGED
|
@@ -1,34 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"bos_token": {
|
| 7 |
-
"content": "<|im_start|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"eos_token": {
|
| 14 |
-
"content": "<|im_end|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
-
"pad_token": {
|
| 21 |
-
"content": "<|endoftext|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false
|
| 26 |
-
},
|
| 27 |
-
"unk_token": {
|
| 28 |
-
"content": "<|endoftext|>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false
|
| 33 |
-
}
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer.json
CHANGED
|
@@ -227,24 +227,6 @@
|
|
| 227 |
"rstrip": false,
|
| 228 |
"normalized": true,
|
| 229 |
"special": false
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"id": 50277,
|
| 233 |
-
"content": "<|im_end|>",
|
| 234 |
-
"single_word": false,
|
| 235 |
-
"lstrip": false,
|
| 236 |
-
"rstrip": false,
|
| 237 |
-
"normalized": false,
|
| 238 |
-
"special": true
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"id": 50278,
|
| 242 |
-
"content": "<|im_start|>",
|
| 243 |
-
"single_word": false,
|
| 244 |
-
"lstrip": false,
|
| 245 |
-
"rstrip": false,
|
| 246 |
-
"normalized": false,
|
| 247 |
-
"special": true
|
| 248 |
}
|
| 249 |
],
|
| 250 |
"normalizer": {
|
|
|
|
| 227 |
"rstrip": false,
|
| 228 |
"normalized": true,
|
| 229 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 230 |
}
|
| 231 |
],
|
| 232 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -200,31 +200,11 @@
|
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
| 203 |
-
},
|
| 204 |
-
"50277": {
|
| 205 |
-
"content": "<|im_end|>",
|
| 206 |
-
"lstrip": false,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": false,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": true
|
| 211 |
-
},
|
| 212 |
-
"50278": {
|
| 213 |
-
"content": "<|im_start|>",
|
| 214 |
-
"lstrip": false,
|
| 215 |
-
"normalized": false,
|
| 216 |
-
"rstrip": false,
|
| 217 |
-
"single_word": false,
|
| 218 |
-
"special": true
|
| 219 |
}
|
| 220 |
},
|
| 221 |
-
"
|
| 222 |
-
"<|im_end|>",
|
| 223 |
-
"<|im_start|>"
|
| 224 |
-
],
|
| 225 |
-
"bos_token": "<|im_start|>",
|
| 226 |
"clean_up_tokenization_spaces": true,
|
| 227 |
-
"eos_token": "<|
|
| 228 |
"model_max_length": 1024,
|
| 229 |
"pad_token": "<|endoftext|>",
|
| 230 |
"tokenizer_class": "GPTNeoXTokenizer",
|
|
|
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
}
|
| 204 |
},
|
| 205 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
"clean_up_tokenization_spaces": true,
|
| 207 |
+
"eos_token": "<|endoftext|>",
|
| 208 |
"model_max_length": 1024,
|
| 209 |
"pad_token": "<|endoftext|>",
|
| 210 |
"tokenizer_class": "GPTNeoXTokenizer",
|
trainer_state.json
CHANGED
|
@@ -1,355 +1,313 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss":
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss":
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss":
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss":
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss":
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 1.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 1.
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"learning_rate": 0.
|
| 146 |
-
"loss": 1.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 1.
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 1.
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 1.
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 1.
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 1.
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 1.
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 1.
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 1.
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 1.
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 1.
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 1.
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 1.
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 1.
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 1.
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 1.
|
| 267 |
"step": 86
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 1.
|
| 273 |
"step": 88
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch":
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 1.
|
| 279 |
"step": 90
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 283 |
-
"learning_rate":
|
| 284 |
-
"loss": 1.
|
| 285 |
"step": 92
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch":
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 1.
|
| 291 |
"step": 94
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch":
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 96
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch":
|
| 301 |
-
"learning_rate": 2.
|
| 302 |
-
"loss": 1.
|
| 303 |
"step": 98
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.89,
|
| 307 |
-
"learning_rate": 2.4e-05,
|
| 308 |
-
"loss": 1.8632,
|
| 309 |
-
"step": 100
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.91,
|
| 313 |
-
"learning_rate": 2e-05,
|
| 314 |
-
"loss": 1.881,
|
| 315 |
-
"step": 102
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.93,
|
| 319 |
-
"learning_rate": 1.6000000000000003e-05,
|
| 320 |
-
"loss": 1.7914,
|
| 321 |
-
"step": 104
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.95,
|
| 325 |
-
"learning_rate": 1.2e-05,
|
| 326 |
-
"loss": 1.7627,
|
| 327 |
-
"step": 106
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.96,
|
| 331 |
-
"learning_rate": 8.000000000000001e-06,
|
| 332 |
-
"loss": 1.7977,
|
| 333 |
-
"step": 108
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.98,
|
| 337 |
-
"learning_rate": 4.000000000000001e-06,
|
| 338 |
-
"loss": 1.8781,
|
| 339 |
-
"step": 110
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 1.0,
|
| 343 |
-
"learning_rate": 0.0,
|
| 344 |
-
"loss": 1.7793,
|
| 345 |
-
"step": 112
|
| 346 |
}
|
| 347 |
],
|
| 348 |
"logging_steps": 2,
|
| 349 |
-
"max_steps":
|
| 350 |
-
"num_train_epochs":
|
| 351 |
"save_steps": 500,
|
| 352 |
-
"total_flos": 2.
|
| 353 |
"trial_name": null,
|
| 354 |
"trial_params": null
|
| 355 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.955223880597015,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 99,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 4e-05,
|
| 14 |
+
"loss": 2.0227,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 2.1777,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.18,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 1.5886,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.24,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 1.7764,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.3,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 1.8589,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.36,
|
| 43 |
+
"learning_rate": 0.0001955056179775281,
|
| 44 |
+
"loss": 1.8044,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.42,
|
| 49 |
+
"learning_rate": 0.00019101123595505618,
|
| 50 |
+
"loss": 1.3535,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.48,
|
| 55 |
+
"learning_rate": 0.00018651685393258427,
|
| 56 |
+
"loss": 1.5432,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.54,
|
| 61 |
+
"learning_rate": 0.00018202247191011236,
|
| 62 |
+
"loss": 1.4256,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.6,
|
| 67 |
+
"learning_rate": 0.00017752808988764045,
|
| 68 |
+
"loss": 1.3982,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.66,
|
| 73 |
+
"learning_rate": 0.00017303370786516853,
|
| 74 |
+
"loss": 1.2797,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.72,
|
| 79 |
+
"learning_rate": 0.00016853932584269662,
|
| 80 |
+
"loss": 1.5707,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.78,
|
| 85 |
+
"learning_rate": 0.00016404494382022474,
|
| 86 |
+
"loss": 1.5817,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.84,
|
| 91 |
+
"learning_rate": 0.0001595505617977528,
|
| 92 |
+
"loss": 1.4543,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.9,
|
| 97 |
+
"learning_rate": 0.0001550561797752809,
|
| 98 |
+
"loss": 1.7071,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.96,
|
| 103 |
+
"learning_rate": 0.000150561797752809,
|
| 104 |
+
"loss": 1.8541,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 1.01,
|
| 109 |
+
"learning_rate": 0.0001460674157303371,
|
| 110 |
+
"loss": 2.0083,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 1.07,
|
| 115 |
+
"learning_rate": 0.00014157303370786517,
|
| 116 |
+
"loss": 1.5323,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 1.13,
|
| 121 |
+
"learning_rate": 0.00013707865168539326,
|
| 122 |
+
"loss": 1.6096,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.19,
|
| 127 |
+
"learning_rate": 0.00013258426966292135,
|
| 128 |
+
"loss": 1.7131,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.25,
|
| 133 |
+
"learning_rate": 0.00012808988764044944,
|
| 134 |
+
"loss": 1.5119,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 1.31,
|
| 139 |
+
"learning_rate": 0.00012359550561797752,
|
| 140 |
+
"loss": 1.1917,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 1.37,
|
| 145 |
+
"learning_rate": 0.00011910112359550563,
|
| 146 |
+
"loss": 1.3534,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 1.43,
|
| 151 |
+
"learning_rate": 0.0001146067415730337,
|
| 152 |
+
"loss": 1.2448,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 1.49,
|
| 157 |
+
"learning_rate": 0.0001101123595505618,
|
| 158 |
+
"loss": 1.4007,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 1.55,
|
| 163 |
+
"learning_rate": 0.00010561797752808989,
|
| 164 |
+
"loss": 1.4253,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.61,
|
| 169 |
+
"learning_rate": 0.00010112359550561799,
|
| 170 |
+
"loss": 1.7311,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 1.67,
|
| 175 |
+
"learning_rate": 9.662921348314608e-05,
|
| 176 |
+
"loss": 1.0368,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 1.73,
|
| 181 |
+
"learning_rate": 9.213483146067416e-05,
|
| 182 |
+
"loss": 1.3187,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 1.79,
|
| 187 |
+
"learning_rate": 8.764044943820225e-05,
|
| 188 |
+
"loss": 1.2071,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 1.85,
|
| 193 |
+
"learning_rate": 8.314606741573034e-05,
|
| 194 |
+
"loss": 1.764,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.91,
|
| 199 |
+
"learning_rate": 7.865168539325843e-05,
|
| 200 |
+
"loss": 1.4301,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 1.97,
|
| 205 |
+
"learning_rate": 7.415730337078653e-05,
|
| 206 |
+
"loss": 1.586,
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 2.03,
|
| 211 |
+
"learning_rate": 6.966292134831462e-05,
|
| 212 |
+
"loss": 1.5166,
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 2.09,
|
| 217 |
+
"learning_rate": 6.51685393258427e-05,
|
| 218 |
+
"loss": 1.4832,
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 2.15,
|
| 223 |
+
"learning_rate": 6.067415730337079e-05,
|
| 224 |
+
"loss": 1.3071,
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 2.21,
|
| 229 |
+
"learning_rate": 5.6179775280898885e-05,
|
| 230 |
+
"loss": 1.3457,
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 2.27,
|
| 235 |
+
"learning_rate": 5.168539325842697e-05,
|
| 236 |
+
"loss": 1.1732,
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 2.33,
|
| 241 |
+
"learning_rate": 4.719101123595506e-05,
|
| 242 |
+
"loss": 1.2885,
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 2.39,
|
| 247 |
+
"learning_rate": 4.269662921348315e-05,
|
| 248 |
+
"loss": 1.0507,
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 2.45,
|
| 253 |
+
"learning_rate": 3.8202247191011236e-05,
|
| 254 |
+
"loss": 1.4467,
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 2.51,
|
| 259 |
+
"learning_rate": 3.370786516853933e-05,
|
| 260 |
+
"loss": 1.5236,
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 2.57,
|
| 265 |
+
"learning_rate": 2.9213483146067417e-05,
|
| 266 |
+
"loss": 1.1199,
|
| 267 |
"step": 86
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 2.63,
|
| 271 |
+
"learning_rate": 2.4719101123595505e-05,
|
| 272 |
+
"loss": 1.4098,
|
| 273 |
"step": 88
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 2.69,
|
| 277 |
+
"learning_rate": 2.0224719101123596e-05,
|
| 278 |
+
"loss": 1.2576,
|
| 279 |
"step": 90
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 2.75,
|
| 283 |
+
"learning_rate": 1.5730337078651687e-05,
|
| 284 |
+
"loss": 1.2179,
|
| 285 |
"step": 92
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 2.81,
|
| 289 |
+
"learning_rate": 1.1235955056179776e-05,
|
| 290 |
+
"loss": 1.6813,
|
| 291 |
"step": 94
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 2.87,
|
| 295 |
+
"learning_rate": 6.741573033707865e-06,
|
| 296 |
+
"loss": 1.3637,
|
| 297 |
"step": 96
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 2.93,
|
| 301 |
+
"learning_rate": 2.247191011235955e-06,
|
| 302 |
+
"loss": 1.3635,
|
| 303 |
"step": 98
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
}
|
| 305 |
],
|
| 306 |
"logging_steps": 2,
|
| 307 |
+
"max_steps": 99,
|
| 308 |
+
"num_train_epochs": 3,
|
| 309 |
"save_steps": 500,
|
| 310 |
+
"total_flos": 2.619520731788083e+16,
|
| 311 |
"trial_name": null,
|
| 312 |
"trial_params": null
|
| 313 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:667639befa7411dfffdec199ef1e6179390d304e4531677c185ca673c703bc09
|
| 3 |
size 4027
|