Upload folder using huggingface_hub
Browse files- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +4 -0
- tokenizer.json +18 -0
- trainer_state.json +381 -105
- training_args.bin +1 -1
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134264397
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93ea301f5724c707d23a8c72827e01f0cdcf129699c4f33780ab23248c4c4620
|
| 3 |
size 134264397
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268514437
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3cc969275e7bdae7c3dd38a542b2421a2ed3e03d2db0eb39ffd4e68f7fea15c
|
| 3 |
size 268514437
|
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 sha256:56a832931926a88f688d3ca860b4a417c281069911bf241f408353622df29f3f
|
| 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 sha256:0bd7b80ec246d44d8b81124b8ba36f2bf12bf8f35c030e50fad44a064bd194e8
|
| 3 |
size 627
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_end|>",
|
| 4 |
+
"<|im_start|>"
|
| 5 |
+
],
|
| 6 |
"bos_token": "<|endoftext|>",
|
| 7 |
"eos_token": "<|endoftext|>",
|
| 8 |
"pad_token": "<|endoftext|>",
|
tokenizer.json
CHANGED
|
@@ -232,6 +232,24 @@
|
|
| 232 |
"rstrip": false,
|
| 233 |
"normalized": true,
|
| 234 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 235 |
}
|
| 236 |
],
|
| 237 |
"normalizer": {
|
|
|
|
| 232 |
"rstrip": false,
|
| 233 |
"normalized": true,
|
| 234 |
"special": false
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"id": 50277,
|
| 238 |
+
"content": "<|im_end|>",
|
| 239 |
+
"single_word": false,
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"normalized": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"id": 50278,
|
| 247 |
+
"content": "<|im_start|>",
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"lstrip": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"special": true
|
| 253 |
}
|
| 254 |
],
|
| 255 |
"normalizer": {
|
trainer_state.json
CHANGED
|
@@ -1,319 +1,595 @@
|
|
| 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": 2e-05,
|
| 14 |
-
"loss":
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
"learning_rate": 2e-05,
|
| 20 |
-
"loss":
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
"learning_rate": 2e-05,
|
| 26 |
-
"loss":
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
"learning_rate": 2e-05,
|
| 32 |
-
"loss":
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
"learning_rate": 2e-05,
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
"learning_rate": 2e-05,
|
| 44 |
-
"loss":
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
"learning_rate": 2e-05,
|
| 50 |
-
"loss":
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
"learning_rate": 2e-05,
|
| 56 |
-
"loss":
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
"learning_rate": 2e-05,
|
| 62 |
-
"loss":
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
"learning_rate": 2e-05,
|
| 68 |
-
"loss": 2.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
"learning_rate": 2e-05,
|
| 74 |
-
"loss": 2.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
"learning_rate": 2e-05,
|
| 80 |
-
"loss": 2.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
"learning_rate": 2e-05,
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
"learning_rate": 2e-05,
|
| 92 |
-
"loss": 2.
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
"learning_rate": 2e-05,
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
"learning_rate": 2e-05,
|
| 104 |
-
"loss":
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
"learning_rate": 2e-05,
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
"learning_rate": 2e-05,
|
| 116 |
-
"loss": 2.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
"learning_rate": 2e-05,
|
| 122 |
-
"loss": 2.
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
"learning_rate": 2e-05,
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
"learning_rate": 2e-05,
|
| 134 |
-
"loss": 2.
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
"learning_rate": 2e-05,
|
| 140 |
-
"loss": 2.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
"learning_rate": 2e-05,
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
"learning_rate": 2e-05,
|
| 152 |
-
"loss":
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
"learning_rate": 2e-05,
|
| 158 |
-
"loss":
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
"learning_rate": 2e-05,
|
| 164 |
-
"loss":
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
"learning_rate": 2e-05,
|
| 170 |
-
"loss":
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
"learning_rate": 2e-05,
|
| 176 |
-
"loss":
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
"learning_rate": 2e-05,
|
| 182 |
-
"loss":
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0.
|
| 187 |
"learning_rate": 2e-05,
|
| 188 |
-
"loss":
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
"learning_rate": 2e-05,
|
| 194 |
-
"loss":
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
"learning_rate": 2e-05,
|
| 200 |
-
"loss":
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
"learning_rate": 2e-05,
|
| 206 |
-
"loss":
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
"learning_rate": 2e-05,
|
| 212 |
-
"loss":
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
"learning_rate": 2e-05,
|
| 218 |
-
"loss":
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
"learning_rate": 2e-05,
|
| 224 |
-
"loss":
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
"learning_rate": 2e-05,
|
| 230 |
-
"loss":
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
"learning_rate": 2e-05,
|
| 236 |
-
"loss": 2.
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
"learning_rate": 2e-05,
|
| 242 |
-
"loss": 2.
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
"learning_rate": 2e-05,
|
| 248 |
-
"loss":
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
"learning_rate": 2e-05,
|
| 254 |
-
"loss": 2.
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
"learning_rate": 2e-05,
|
| 260 |
-
"loss": 2.
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
"learning_rate": 2e-05,
|
| 266 |
-
"loss": 2.
|
| 267 |
"step": 86
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
"learning_rate": 2e-05,
|
| 272 |
-
"loss": 2.
|
| 273 |
"step": 88
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch":
|
| 277 |
"learning_rate": 2e-05,
|
| 278 |
-
"loss": 2.
|
| 279 |
"step": 90
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 283 |
"learning_rate": 2e-05,
|
| 284 |
-
"loss": 2.
|
| 285 |
"step": 92
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch":
|
| 289 |
"learning_rate": 2e-05,
|
| 290 |
-
"loss": 2.
|
| 291 |
"step": 94
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch":
|
| 295 |
"learning_rate": 2e-05,
|
| 296 |
-
"loss":
|
| 297 |
"step": 96
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch":
|
| 301 |
"learning_rate": 2e-05,
|
| 302 |
-
"loss": 2.
|
| 303 |
"step": 98
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
"learning_rate": 2e-05,
|
| 308 |
-
"loss":
|
| 309 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 310 |
}
|
| 311 |
],
|
| 312 |
"logging_steps": 2,
|
| 313 |
-
"max_steps":
|
| 314 |
"num_train_epochs": 3,
|
| 315 |
-
"save_steps":
|
| 316 |
-
"total_flos":
|
| 317 |
"trial_name": null,
|
| 318 |
"trial_params": null
|
| 319 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9825242718446603,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 192,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 2.3248,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
"learning_rate": 2e-05,
|
| 20 |
+
"loss": 2.5426,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.09,
|
| 25 |
"learning_rate": 2e-05,
|
| 26 |
+
"loss": 2.4419,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.12,
|
| 31 |
"learning_rate": 2e-05,
|
| 32 |
+
"loss": 2.7004,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 2.7353,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 2.912,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
"learning_rate": 2e-05,
|
| 50 |
+
"loss": 2.9538,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.25,
|
| 55 |
"learning_rate": 2e-05,
|
| 56 |
+
"loss": 3.8338,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.28,
|
| 61 |
"learning_rate": 2e-05,
|
| 62 |
+
"loss": 2.309,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.31,
|
| 67 |
"learning_rate": 2e-05,
|
| 68 |
+
"loss": 2.3515,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.34,
|
| 73 |
"learning_rate": 2e-05,
|
| 74 |
+
"loss": 2.4006,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.37,
|
| 79 |
"learning_rate": 2e-05,
|
| 80 |
+
"loss": 2.7096,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.4,
|
| 85 |
"learning_rate": 2e-05,
|
| 86 |
+
"loss": 2.7586,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.43,
|
| 91 |
"learning_rate": 2e-05,
|
| 92 |
+
"loss": 2.96,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.47,
|
| 97 |
"learning_rate": 2e-05,
|
| 98 |
+
"loss": 2.9802,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.5,
|
| 103 |
"learning_rate": 2e-05,
|
| 104 |
+
"loss": 4.0495,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.53,
|
| 109 |
"learning_rate": 2e-05,
|
| 110 |
+
"loss": 2.2675,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.56,
|
| 115 |
"learning_rate": 2e-05,
|
| 116 |
+
"loss": 2.5202,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.59,
|
| 121 |
"learning_rate": 2e-05,
|
| 122 |
+
"loss": 2.5992,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.62,
|
| 127 |
"learning_rate": 2e-05,
|
| 128 |
+
"loss": 2.67,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.65,
|
| 133 |
"learning_rate": 2e-05,
|
| 134 |
+
"loss": 2.7912,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.68,
|
| 139 |
"learning_rate": 2e-05,
|
| 140 |
+
"loss": 2.7341,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.71,
|
| 145 |
"learning_rate": 2e-05,
|
| 146 |
+
"loss": 2.8227,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.75,
|
| 151 |
"learning_rate": 2e-05,
|
| 152 |
+
"loss": 3.5357,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.78,
|
| 157 |
"learning_rate": 2e-05,
|
| 158 |
+
"loss": 2.3243,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.81,
|
| 163 |
"learning_rate": 2e-05,
|
| 164 |
+
"loss": 2.4356,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.84,
|
| 169 |
"learning_rate": 2e-05,
|
| 170 |
+
"loss": 2.5515,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.87,
|
| 175 |
"learning_rate": 2e-05,
|
| 176 |
+
"loss": 2.5328,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.9,
|
| 181 |
"learning_rate": 2e-05,
|
| 182 |
+
"loss": 2.6837,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.93,
|
| 187 |
"learning_rate": 2e-05,
|
| 188 |
+
"loss": 2.7156,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.96,
|
| 193 |
"learning_rate": 2e-05,
|
| 194 |
+
"loss": 2.9951,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.99,
|
| 199 |
"learning_rate": 2e-05,
|
| 200 |
+
"loss": 3.4254,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 1.03,
|
| 205 |
"learning_rate": 2e-05,
|
| 206 |
+
"loss": 2.3508,
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.06,
|
| 211 |
"learning_rate": 2e-05,
|
| 212 |
+
"loss": 2.3299,
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 1.09,
|
| 217 |
"learning_rate": 2e-05,
|
| 218 |
+
"loss": 2.4101,
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.12,
|
| 223 |
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 2.5624,
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 1.15,
|
| 229 |
"learning_rate": 2e-05,
|
| 230 |
+
"loss": 2.7489,
|
| 231 |
"step": 74
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 1.18,
|
| 235 |
"learning_rate": 2e-05,
|
| 236 |
+
"loss": 2.6214,
|
| 237 |
"step": 76
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 1.21,
|
| 241 |
"learning_rate": 2e-05,
|
| 242 |
+
"loss": 2.8964,
|
| 243 |
"step": 78
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 1.24,
|
| 247 |
"learning_rate": 2e-05,
|
| 248 |
+
"loss": 3.1998,
|
| 249 |
"step": 80
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 1.27,
|
| 253 |
"learning_rate": 2e-05,
|
| 254 |
+
"loss": 2.5584,
|
| 255 |
"step": 82
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 1.3,
|
| 259 |
"learning_rate": 2e-05,
|
| 260 |
+
"loss": 2.2981,
|
| 261 |
"step": 84
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 1.34,
|
| 265 |
"learning_rate": 2e-05,
|
| 266 |
+
"loss": 2.474,
|
| 267 |
"step": 86
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 1.37,
|
| 271 |
"learning_rate": 2e-05,
|
| 272 |
+
"loss": 2.5068,
|
| 273 |
"step": 88
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 1.4,
|
| 277 |
"learning_rate": 2e-05,
|
| 278 |
+
"loss": 2.627,
|
| 279 |
"step": 90
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 1.43,
|
| 283 |
"learning_rate": 2e-05,
|
| 284 |
+
"loss": 2.6775,
|
| 285 |
"step": 92
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 1.46,
|
| 289 |
"learning_rate": 2e-05,
|
| 290 |
+
"loss": 2.7335,
|
| 291 |
"step": 94
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 1.49,
|
| 295 |
"learning_rate": 2e-05,
|
| 296 |
+
"loss": 3.205,
|
| 297 |
"step": 96
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 1.52,
|
| 301 |
"learning_rate": 2e-05,
|
| 302 |
+
"loss": 2.7354,
|
| 303 |
"step": 98
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 1.55,
|
| 307 |
"learning_rate": 2e-05,
|
| 308 |
+
"loss": 2.2453,
|
| 309 |
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.58,
|
| 313 |
+
"learning_rate": 2e-05,
|
| 314 |
+
"loss": 2.4487,
|
| 315 |
+
"step": 102
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.62,
|
| 319 |
+
"learning_rate": 2e-05,
|
| 320 |
+
"loss": 2.512,
|
| 321 |
+
"step": 104
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.65,
|
| 325 |
+
"learning_rate": 2e-05,
|
| 326 |
+
"loss": 2.655,
|
| 327 |
+
"step": 106
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.68,
|
| 331 |
+
"learning_rate": 2e-05,
|
| 332 |
+
"loss": 2.7735,
|
| 333 |
+
"step": 108
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.71,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 2.7788,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.74,
|
| 343 |
+
"learning_rate": 2e-05,
|
| 344 |
+
"loss": 3.0831,
|
| 345 |
+
"step": 112
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.77,
|
| 349 |
+
"learning_rate": 2e-05,
|
| 350 |
+
"loss": 2.6533,
|
| 351 |
+
"step": 114
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.8,
|
| 355 |
+
"learning_rate": 2e-05,
|
| 356 |
+
"loss": 2.4139,
|
| 357 |
+
"step": 116
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.83,
|
| 361 |
+
"learning_rate": 2e-05,
|
| 362 |
+
"loss": 2.5046,
|
| 363 |
+
"step": 118
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.86,
|
| 367 |
+
"learning_rate": 2e-05,
|
| 368 |
+
"loss": 2.5975,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9,
|
| 373 |
+
"learning_rate": 2e-05,
|
| 374 |
+
"loss": 2.5629,
|
| 375 |
+
"step": 122
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.93,
|
| 379 |
+
"learning_rate": 2e-05,
|
| 380 |
+
"loss": 2.6159,
|
| 381 |
+
"step": 124
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.96,
|
| 385 |
+
"learning_rate": 2e-05,
|
| 386 |
+
"loss": 2.7659,
|
| 387 |
+
"step": 126
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.99,
|
| 391 |
+
"learning_rate": 2e-05,
|
| 392 |
+
"loss": 2.851,
|
| 393 |
+
"step": 128
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.02,
|
| 397 |
+
"learning_rate": 2e-05,
|
| 398 |
+
"loss": 2.4641,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.05,
|
| 403 |
+
"learning_rate": 2e-05,
|
| 404 |
+
"loss": 2.3735,
|
| 405 |
+
"step": 132
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.08,
|
| 409 |
+
"learning_rate": 2e-05,
|
| 410 |
+
"loss": 2.4855,
|
| 411 |
+
"step": 134
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.11,
|
| 415 |
+
"learning_rate": 2e-05,
|
| 416 |
+
"loss": 2.488,
|
| 417 |
+
"step": 136
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.14,
|
| 421 |
+
"learning_rate": 2e-05,
|
| 422 |
+
"loss": 2.6419,
|
| 423 |
+
"step": 138
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.17,
|
| 427 |
+
"learning_rate": 2e-05,
|
| 428 |
+
"loss": 2.6311,
|
| 429 |
+
"step": 140
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.21,
|
| 433 |
+
"learning_rate": 2e-05,
|
| 434 |
+
"loss": 2.7308,
|
| 435 |
+
"step": 142
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.24,
|
| 439 |
+
"learning_rate": 2e-05,
|
| 440 |
+
"loss": 2.7833,
|
| 441 |
+
"step": 144
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.27,
|
| 445 |
+
"learning_rate": 2e-05,
|
| 446 |
+
"loss": 2.5155,
|
| 447 |
+
"step": 146
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.3,
|
| 451 |
+
"learning_rate": 2e-05,
|
| 452 |
+
"loss": 2.2384,
|
| 453 |
+
"step": 148
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.33,
|
| 457 |
+
"learning_rate": 2e-05,
|
| 458 |
+
"loss": 2.5146,
|
| 459 |
+
"step": 150
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.36,
|
| 463 |
+
"learning_rate": 2e-05,
|
| 464 |
+
"loss": 2.4276,
|
| 465 |
+
"step": 152
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.39,
|
| 469 |
+
"learning_rate": 2e-05,
|
| 470 |
+
"loss": 2.4304,
|
| 471 |
+
"step": 154
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.42,
|
| 475 |
+
"learning_rate": 2e-05,
|
| 476 |
+
"loss": 2.5241,
|
| 477 |
+
"step": 156
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.45,
|
| 481 |
+
"learning_rate": 2e-05,
|
| 482 |
+
"loss": 2.6708,
|
| 483 |
+
"step": 158
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.49,
|
| 487 |
+
"learning_rate": 2e-05,
|
| 488 |
+
"loss": 2.7999,
|
| 489 |
+
"step": 160
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.52,
|
| 493 |
+
"learning_rate": 2e-05,
|
| 494 |
+
"loss": 2.5317,
|
| 495 |
+
"step": 162
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.55,
|
| 499 |
+
"learning_rate": 2e-05,
|
| 500 |
+
"loss": 2.3519,
|
| 501 |
+
"step": 164
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.58,
|
| 505 |
+
"learning_rate": 2e-05,
|
| 506 |
+
"loss": 2.4353,
|
| 507 |
+
"step": 166
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.61,
|
| 511 |
+
"learning_rate": 2e-05,
|
| 512 |
+
"loss": 2.254,
|
| 513 |
+
"step": 168
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.64,
|
| 517 |
+
"learning_rate": 2e-05,
|
| 518 |
+
"loss": 2.7192,
|
| 519 |
+
"step": 170
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.67,
|
| 523 |
+
"learning_rate": 2e-05,
|
| 524 |
+
"loss": 2.5182,
|
| 525 |
+
"step": 172
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.7,
|
| 529 |
+
"learning_rate": 2e-05,
|
| 530 |
+
"loss": 2.6026,
|
| 531 |
+
"step": 174
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.73,
|
| 535 |
+
"learning_rate": 2e-05,
|
| 536 |
+
"loss": 2.7313,
|
| 537 |
+
"step": 176
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.77,
|
| 541 |
+
"learning_rate": 2e-05,
|
| 542 |
+
"loss": 2.4888,
|
| 543 |
+
"step": 178
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.8,
|
| 547 |
+
"learning_rate": 2e-05,
|
| 548 |
+
"loss": 2.2595,
|
| 549 |
+
"step": 180
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.83,
|
| 553 |
+
"learning_rate": 2e-05,
|
| 554 |
+
"loss": 2.2564,
|
| 555 |
+
"step": 182
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.86,
|
| 559 |
+
"learning_rate": 2e-05,
|
| 560 |
+
"loss": 2.38,
|
| 561 |
+
"step": 184
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.89,
|
| 565 |
+
"learning_rate": 2e-05,
|
| 566 |
+
"loss": 2.6661,
|
| 567 |
+
"step": 186
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.92,
|
| 571 |
+
"learning_rate": 2e-05,
|
| 572 |
+
"loss": 2.4435,
|
| 573 |
+
"step": 188
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.95,
|
| 577 |
+
"learning_rate": 2e-05,
|
| 578 |
+
"loss": 2.4033,
|
| 579 |
+
"step": 190
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.98,
|
| 583 |
+
"learning_rate": 2e-05,
|
| 584 |
+
"loss": 2.7354,
|
| 585 |
+
"step": 192
|
| 586 |
}
|
| 587 |
],
|
| 588 |
"logging_steps": 2,
|
| 589 |
+
"max_steps": 192,
|
| 590 |
"num_train_epochs": 3,
|
| 591 |
+
"save_steps": 64,
|
| 592 |
+
"total_flos": 5255438541864960.0,
|
| 593 |
"trial_name": null,
|
| 594 |
"trial_params": null
|
| 595 |
}
|
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:dd9f3c299e9abebdd89b9e40c36c9c83893177c6bf92c57a4f83c8e357745fbc
|
| 3 |
size 4027
|