Training in progress, step 10
Browse files- adapter_config.json +1 -1
- adapter_model.safetensors +2 -2
- all_results.json +8 -8
- eval_results.json +4 -4
- special_tokens_map.json +3 -7
- tokenizer.json +2 -2
- tokenizer.model +2 -2
- tokenizer_config.json +12 -1718
- train_results.json +4 -4
- trainer_state.json +622 -622
- training_args.bin +2 -2
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
adapter_model.safetensors
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 sha256:94a9601f3ec6b7f23be4cc5a122306b160ad882f3672262aa641a291af050b33
|
| 3 |
+
size 537953760
|
all_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 1.
|
| 7 |
-
"train_loss":
|
| 8 |
-
"train_runtime":
|
| 9 |
-
"train_samples_per_second":
|
| 10 |
-
"train_steps_per_second": 0.
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
+
"eval_loss": 1.5016273260116577,
|
| 4 |
+
"eval_runtime": 109.2744,
|
| 5 |
+
"eval_samples_per_second": 45.756,
|
| 6 |
+
"eval_steps_per_second": 1.437,
|
| 7 |
+
"train_loss": 1.802713230252266,
|
| 8 |
+
"train_runtime": 3920.872,
|
| 9 |
+
"train_samples_per_second": 4.179,
|
| 10 |
+
"train_steps_per_second": 0.065
|
| 11 |
}
|
eval_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 1.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
+
"eval_loss": 1.5016273260116577,
|
| 4 |
+
"eval_runtime": 109.2744,
|
| 5 |
+
"eval_samples_per_second": 45.756,
|
| 6 |
+
"eval_steps_per_second": 1.437
|
| 7 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<start_of_turn>",
|
| 4 |
-
"<end_of_turn>"
|
| 5 |
-
],
|
| 6 |
"bos_token": {
|
| 7 |
-
"content": "<
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"eos_token": {
|
| 14 |
-
"content": "
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
"pad_token": {
|
| 21 |
-
"content": "
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": false,
|
| 24 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
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:b5ae21df0ad37f3fb2985a0eebc764ad3a518d1ed6fee2dfb39e52e3d8308ac2
|
| 3 |
+
size 1795583
|
tokenizer.model
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
-
"content": "<
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": false,
|
| 9 |
"rstrip": false,
|
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
-
"content": "<
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
|
@@ -19,1739 +19,33 @@
|
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
-
"content": "
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
-
"
|
| 30 |
-
"content": "
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
| 33 |
"rstrip": false,
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
| 36 |
-
},
|
| 37 |
-
"4": {
|
| 38 |
-
"content": "<mask>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": false
|
| 44 |
-
},
|
| 45 |
-
"5": {
|
| 46 |
-
"content": "<2mass>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": false
|
| 52 |
-
},
|
| 53 |
-
"6": {
|
| 54 |
-
"content": "[@BOS@]",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": false
|
| 60 |
-
},
|
| 61 |
-
"7": {
|
| 62 |
-
"content": "<unused0>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": false
|
| 68 |
-
},
|
| 69 |
-
"8": {
|
| 70 |
-
"content": "<unused1>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": false
|
| 76 |
-
},
|
| 77 |
-
"9": {
|
| 78 |
-
"content": "<unused2>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": false
|
| 84 |
-
},
|
| 85 |
-
"10": {
|
| 86 |
-
"content": "<unused3>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": false
|
| 92 |
-
},
|
| 93 |
-
"11": {
|
| 94 |
-
"content": "<unused4>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": false
|
| 100 |
-
},
|
| 101 |
-
"12": {
|
| 102 |
-
"content": "<unused5>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": false
|
| 108 |
-
},
|
| 109 |
-
"13": {
|
| 110 |
-
"content": "<unused6>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": false
|
| 116 |
-
},
|
| 117 |
-
"14": {
|
| 118 |
-
"content": "<unused7>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"15": {
|
| 126 |
-
"content": "<unused8>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"16": {
|
| 134 |
-
"content": "<unused9>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"17": {
|
| 142 |
-
"content": "<unused10>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"18": {
|
| 150 |
-
"content": "<unused11>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"19": {
|
| 158 |
-
"content": "<unused12>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"20": {
|
| 166 |
-
"content": "<unused13>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"21": {
|
| 174 |
-
"content": "<unused14>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
},
|
| 181 |
-
"22": {
|
| 182 |
-
"content": "<unused15>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": false
|
| 188 |
-
},
|
| 189 |
-
"23": {
|
| 190 |
-
"content": "<unused16>",
|
| 191 |
-
"lstrip": false,
|
| 192 |
-
"normalized": false,
|
| 193 |
-
"rstrip": false,
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"special": false
|
| 196 |
-
},
|
| 197 |
-
"24": {
|
| 198 |
-
"content": "<unused17>",
|
| 199 |
-
"lstrip": false,
|
| 200 |
-
"normalized": false,
|
| 201 |
-
"rstrip": false,
|
| 202 |
-
"single_word": false,
|
| 203 |
-
"special": false
|
| 204 |
-
},
|
| 205 |
-
"25": {
|
| 206 |
-
"content": "<unused18>",
|
| 207 |
-
"lstrip": false,
|
| 208 |
-
"normalized": false,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"single_word": false,
|
| 211 |
-
"special": false
|
| 212 |
-
},
|
| 213 |
-
"26": {
|
| 214 |
-
"content": "<unused19>",
|
| 215 |
-
"lstrip": false,
|
| 216 |
-
"normalized": false,
|
| 217 |
-
"rstrip": false,
|
| 218 |
-
"single_word": false,
|
| 219 |
-
"special": false
|
| 220 |
-
},
|
| 221 |
-
"27": {
|
| 222 |
-
"content": "<unused20>",
|
| 223 |
-
"lstrip": false,
|
| 224 |
-
"normalized": false,
|
| 225 |
-
"rstrip": false,
|
| 226 |
-
"single_word": false,
|
| 227 |
-
"special": false
|
| 228 |
-
},
|
| 229 |
-
"28": {
|
| 230 |
-
"content": "<unused21>",
|
| 231 |
-
"lstrip": false,
|
| 232 |
-
"normalized": false,
|
| 233 |
-
"rstrip": false,
|
| 234 |
-
"single_word": false,
|
| 235 |
-
"special": false
|
| 236 |
-
},
|
| 237 |
-
"29": {
|
| 238 |
-
"content": "<unused22>",
|
| 239 |
-
"lstrip": false,
|
| 240 |
-
"normalized": false,
|
| 241 |
-
"rstrip": false,
|
| 242 |
-
"single_word": false,
|
| 243 |
-
"special": false
|
| 244 |
-
},
|
| 245 |
-
"30": {
|
| 246 |
-
"content": "<unused23>",
|
| 247 |
-
"lstrip": false,
|
| 248 |
-
"normalized": false,
|
| 249 |
-
"rstrip": false,
|
| 250 |
-
"single_word": false,
|
| 251 |
-
"special": false
|
| 252 |
-
},
|
| 253 |
-
"31": {
|
| 254 |
-
"content": "<unused24>",
|
| 255 |
-
"lstrip": false,
|
| 256 |
-
"normalized": false,
|
| 257 |
-
"rstrip": false,
|
| 258 |
-
"single_word": false,
|
| 259 |
-
"special": false
|
| 260 |
-
},
|
| 261 |
-
"32": {
|
| 262 |
-
"content": "<unused25>",
|
| 263 |
-
"lstrip": false,
|
| 264 |
-
"normalized": false,
|
| 265 |
-
"rstrip": false,
|
| 266 |
-
"single_word": false,
|
| 267 |
-
"special": false
|
| 268 |
-
},
|
| 269 |
-
"33": {
|
| 270 |
-
"content": "<unused26>",
|
| 271 |
-
"lstrip": false,
|
| 272 |
-
"normalized": false,
|
| 273 |
-
"rstrip": false,
|
| 274 |
-
"single_word": false,
|
| 275 |
-
"special": false
|
| 276 |
-
},
|
| 277 |
-
"34": {
|
| 278 |
-
"content": "<unused27>",
|
| 279 |
-
"lstrip": false,
|
| 280 |
-
"normalized": false,
|
| 281 |
-
"rstrip": false,
|
| 282 |
-
"single_word": false,
|
| 283 |
-
"special": false
|
| 284 |
-
},
|
| 285 |
-
"35": {
|
| 286 |
-
"content": "<unused28>",
|
| 287 |
-
"lstrip": false,
|
| 288 |
-
"normalized": false,
|
| 289 |
-
"rstrip": false,
|
| 290 |
-
"single_word": false,
|
| 291 |
-
"special": false
|
| 292 |
-
},
|
| 293 |
-
"36": {
|
| 294 |
-
"content": "<unused29>",
|
| 295 |
-
"lstrip": false,
|
| 296 |
-
"normalized": false,
|
| 297 |
-
"rstrip": false,
|
| 298 |
-
"single_word": false,
|
| 299 |
-
"special": false
|
| 300 |
-
},
|
| 301 |
-
"37": {
|
| 302 |
-
"content": "<unused30>",
|
| 303 |
-
"lstrip": false,
|
| 304 |
-
"normalized": false,
|
| 305 |
-
"rstrip": false,
|
| 306 |
-
"single_word": false,
|
| 307 |
-
"special": false
|
| 308 |
-
},
|
| 309 |
-
"38": {
|
| 310 |
-
"content": "<unused31>",
|
| 311 |
-
"lstrip": false,
|
| 312 |
-
"normalized": false,
|
| 313 |
-
"rstrip": false,
|
| 314 |
-
"single_word": false,
|
| 315 |
-
"special": false
|
| 316 |
-
},
|
| 317 |
-
"39": {
|
| 318 |
-
"content": "<unused32>",
|
| 319 |
-
"lstrip": false,
|
| 320 |
-
"normalized": false,
|
| 321 |
-
"rstrip": false,
|
| 322 |
-
"single_word": false,
|
| 323 |
-
"special": false
|
| 324 |
-
},
|
| 325 |
-
"40": {
|
| 326 |
-
"content": "<unused33>",
|
| 327 |
-
"lstrip": false,
|
| 328 |
-
"normalized": false,
|
| 329 |
-
"rstrip": false,
|
| 330 |
-
"single_word": false,
|
| 331 |
-
"special": false
|
| 332 |
-
},
|
| 333 |
-
"41": {
|
| 334 |
-
"content": "<unused34>",
|
| 335 |
-
"lstrip": false,
|
| 336 |
-
"normalized": false,
|
| 337 |
-
"rstrip": false,
|
| 338 |
-
"single_word": false,
|
| 339 |
-
"special": false
|
| 340 |
-
},
|
| 341 |
-
"42": {
|
| 342 |
-
"content": "<unused35>",
|
| 343 |
-
"lstrip": false,
|
| 344 |
-
"normalized": false,
|
| 345 |
-
"rstrip": false,
|
| 346 |
-
"single_word": false,
|
| 347 |
-
"special": false
|
| 348 |
-
},
|
| 349 |
-
"43": {
|
| 350 |
-
"content": "<unused36>",
|
| 351 |
-
"lstrip": false,
|
| 352 |
-
"normalized": false,
|
| 353 |
-
"rstrip": false,
|
| 354 |
-
"single_word": false,
|
| 355 |
-
"special": false
|
| 356 |
-
},
|
| 357 |
-
"44": {
|
| 358 |
-
"content": "<unused37>",
|
| 359 |
-
"lstrip": false,
|
| 360 |
-
"normalized": false,
|
| 361 |
-
"rstrip": false,
|
| 362 |
-
"single_word": false,
|
| 363 |
-
"special": false
|
| 364 |
-
},
|
| 365 |
-
"45": {
|
| 366 |
-
"content": "<unused38>",
|
| 367 |
-
"lstrip": false,
|
| 368 |
-
"normalized": false,
|
| 369 |
-
"rstrip": false,
|
| 370 |
-
"single_word": false,
|
| 371 |
-
"special": false
|
| 372 |
-
},
|
| 373 |
-
"46": {
|
| 374 |
-
"content": "<unused39>",
|
| 375 |
-
"lstrip": false,
|
| 376 |
-
"normalized": false,
|
| 377 |
-
"rstrip": false,
|
| 378 |
-
"single_word": false,
|
| 379 |
-
"special": false
|
| 380 |
-
},
|
| 381 |
-
"47": {
|
| 382 |
-
"content": "<unused40>",
|
| 383 |
-
"lstrip": false,
|
| 384 |
-
"normalized": false,
|
| 385 |
-
"rstrip": false,
|
| 386 |
-
"single_word": false,
|
| 387 |
-
"special": false
|
| 388 |
-
},
|
| 389 |
-
"48": {
|
| 390 |
-
"content": "<unused41>",
|
| 391 |
-
"lstrip": false,
|
| 392 |
-
"normalized": false,
|
| 393 |
-
"rstrip": false,
|
| 394 |
-
"single_word": false,
|
| 395 |
-
"special": false
|
| 396 |
-
},
|
| 397 |
-
"49": {
|
| 398 |
-
"content": "<unused42>",
|
| 399 |
-
"lstrip": false,
|
| 400 |
-
"normalized": false,
|
| 401 |
-
"rstrip": false,
|
| 402 |
-
"single_word": false,
|
| 403 |
-
"special": false
|
| 404 |
-
},
|
| 405 |
-
"50": {
|
| 406 |
-
"content": "<unused43>",
|
| 407 |
-
"lstrip": false,
|
| 408 |
-
"normalized": false,
|
| 409 |
-
"rstrip": false,
|
| 410 |
-
"single_word": false,
|
| 411 |
-
"special": false
|
| 412 |
-
},
|
| 413 |
-
"51": {
|
| 414 |
-
"content": "<unused44>",
|
| 415 |
-
"lstrip": false,
|
| 416 |
-
"normalized": false,
|
| 417 |
-
"rstrip": false,
|
| 418 |
-
"single_word": false,
|
| 419 |
-
"special": false
|
| 420 |
-
},
|
| 421 |
-
"52": {
|
| 422 |
-
"content": "<unused45>",
|
| 423 |
-
"lstrip": false,
|
| 424 |
-
"normalized": false,
|
| 425 |
-
"rstrip": false,
|
| 426 |
-
"single_word": false,
|
| 427 |
-
"special": false
|
| 428 |
-
},
|
| 429 |
-
"53": {
|
| 430 |
-
"content": "<unused46>",
|
| 431 |
-
"lstrip": false,
|
| 432 |
-
"normalized": false,
|
| 433 |
-
"rstrip": false,
|
| 434 |
-
"single_word": false,
|
| 435 |
-
"special": false
|
| 436 |
-
},
|
| 437 |
-
"54": {
|
| 438 |
-
"content": "<unused47>",
|
| 439 |
-
"lstrip": false,
|
| 440 |
-
"normalized": false,
|
| 441 |
-
"rstrip": false,
|
| 442 |
-
"single_word": false,
|
| 443 |
-
"special": false
|
| 444 |
-
},
|
| 445 |
-
"55": {
|
| 446 |
-
"content": "<unused48>",
|
| 447 |
-
"lstrip": false,
|
| 448 |
-
"normalized": false,
|
| 449 |
-
"rstrip": false,
|
| 450 |
-
"single_word": false,
|
| 451 |
-
"special": false
|
| 452 |
-
},
|
| 453 |
-
"56": {
|
| 454 |
-
"content": "<unused49>",
|
| 455 |
-
"lstrip": false,
|
| 456 |
-
"normalized": false,
|
| 457 |
-
"rstrip": false,
|
| 458 |
-
"single_word": false,
|
| 459 |
-
"special": false
|
| 460 |
-
},
|
| 461 |
-
"57": {
|
| 462 |
-
"content": "<unused50>",
|
| 463 |
-
"lstrip": false,
|
| 464 |
-
"normalized": false,
|
| 465 |
-
"rstrip": false,
|
| 466 |
-
"single_word": false,
|
| 467 |
-
"special": false
|
| 468 |
-
},
|
| 469 |
-
"58": {
|
| 470 |
-
"content": "<unused51>",
|
| 471 |
-
"lstrip": false,
|
| 472 |
-
"normalized": false,
|
| 473 |
-
"rstrip": false,
|
| 474 |
-
"single_word": false,
|
| 475 |
-
"special": false
|
| 476 |
-
},
|
| 477 |
-
"59": {
|
| 478 |
-
"content": "<unused52>",
|
| 479 |
-
"lstrip": false,
|
| 480 |
-
"normalized": false,
|
| 481 |
-
"rstrip": false,
|
| 482 |
-
"single_word": false,
|
| 483 |
-
"special": false
|
| 484 |
-
},
|
| 485 |
-
"60": {
|
| 486 |
-
"content": "<unused53>",
|
| 487 |
-
"lstrip": false,
|
| 488 |
-
"normalized": false,
|
| 489 |
-
"rstrip": false,
|
| 490 |
-
"single_word": false,
|
| 491 |
-
"special": false
|
| 492 |
-
},
|
| 493 |
-
"61": {
|
| 494 |
-
"content": "<unused54>",
|
| 495 |
-
"lstrip": false,
|
| 496 |
-
"normalized": false,
|
| 497 |
-
"rstrip": false,
|
| 498 |
-
"single_word": false,
|
| 499 |
-
"special": false
|
| 500 |
-
},
|
| 501 |
-
"62": {
|
| 502 |
-
"content": "<unused55>",
|
| 503 |
-
"lstrip": false,
|
| 504 |
-
"normalized": false,
|
| 505 |
-
"rstrip": false,
|
| 506 |
-
"single_word": false,
|
| 507 |
-
"special": false
|
| 508 |
-
},
|
| 509 |
-
"63": {
|
| 510 |
-
"content": "<unused56>",
|
| 511 |
-
"lstrip": false,
|
| 512 |
-
"normalized": false,
|
| 513 |
-
"rstrip": false,
|
| 514 |
-
"single_word": false,
|
| 515 |
-
"special": false
|
| 516 |
-
},
|
| 517 |
-
"64": {
|
| 518 |
-
"content": "<unused57>",
|
| 519 |
-
"lstrip": false,
|
| 520 |
-
"normalized": false,
|
| 521 |
-
"rstrip": false,
|
| 522 |
-
"single_word": false,
|
| 523 |
-
"special": false
|
| 524 |
-
},
|
| 525 |
-
"65": {
|
| 526 |
-
"content": "<unused58>",
|
| 527 |
-
"lstrip": false,
|
| 528 |
-
"normalized": false,
|
| 529 |
-
"rstrip": false,
|
| 530 |
-
"single_word": false,
|
| 531 |
-
"special": false
|
| 532 |
-
},
|
| 533 |
-
"66": {
|
| 534 |
-
"content": "<unused59>",
|
| 535 |
-
"lstrip": false,
|
| 536 |
-
"normalized": false,
|
| 537 |
-
"rstrip": false,
|
| 538 |
-
"single_word": false,
|
| 539 |
-
"special": false
|
| 540 |
-
},
|
| 541 |
-
"67": {
|
| 542 |
-
"content": "<unused60>",
|
| 543 |
-
"lstrip": false,
|
| 544 |
-
"normalized": false,
|
| 545 |
-
"rstrip": false,
|
| 546 |
-
"single_word": false,
|
| 547 |
-
"special": false
|
| 548 |
-
},
|
| 549 |
-
"68": {
|
| 550 |
-
"content": "<unused61>",
|
| 551 |
-
"lstrip": false,
|
| 552 |
-
"normalized": false,
|
| 553 |
-
"rstrip": false,
|
| 554 |
-
"single_word": false,
|
| 555 |
-
"special": false
|
| 556 |
-
},
|
| 557 |
-
"69": {
|
| 558 |
-
"content": "<unused62>",
|
| 559 |
-
"lstrip": false,
|
| 560 |
-
"normalized": false,
|
| 561 |
-
"rstrip": false,
|
| 562 |
-
"single_word": false,
|
| 563 |
-
"special": false
|
| 564 |
-
},
|
| 565 |
-
"70": {
|
| 566 |
-
"content": "<unused63>",
|
| 567 |
-
"lstrip": false,
|
| 568 |
-
"normalized": false,
|
| 569 |
-
"rstrip": false,
|
| 570 |
-
"single_word": false,
|
| 571 |
-
"special": false
|
| 572 |
-
},
|
| 573 |
-
"71": {
|
| 574 |
-
"content": "<unused64>",
|
| 575 |
-
"lstrip": false,
|
| 576 |
-
"normalized": false,
|
| 577 |
-
"rstrip": false,
|
| 578 |
-
"single_word": false,
|
| 579 |
-
"special": false
|
| 580 |
-
},
|
| 581 |
-
"72": {
|
| 582 |
-
"content": "<unused65>",
|
| 583 |
-
"lstrip": false,
|
| 584 |
-
"normalized": false,
|
| 585 |
-
"rstrip": false,
|
| 586 |
-
"single_word": false,
|
| 587 |
-
"special": false
|
| 588 |
-
},
|
| 589 |
-
"73": {
|
| 590 |
-
"content": "<unused66>",
|
| 591 |
-
"lstrip": false,
|
| 592 |
-
"normalized": false,
|
| 593 |
-
"rstrip": false,
|
| 594 |
-
"single_word": false,
|
| 595 |
-
"special": false
|
| 596 |
-
},
|
| 597 |
-
"74": {
|
| 598 |
-
"content": "<unused67>",
|
| 599 |
-
"lstrip": false,
|
| 600 |
-
"normalized": false,
|
| 601 |
-
"rstrip": false,
|
| 602 |
-
"single_word": false,
|
| 603 |
-
"special": false
|
| 604 |
-
},
|
| 605 |
-
"75": {
|
| 606 |
-
"content": "<unused68>",
|
| 607 |
-
"lstrip": false,
|
| 608 |
-
"normalized": false,
|
| 609 |
-
"rstrip": false,
|
| 610 |
-
"single_word": false,
|
| 611 |
-
"special": false
|
| 612 |
-
},
|
| 613 |
-
"76": {
|
| 614 |
-
"content": "<unused69>",
|
| 615 |
-
"lstrip": false,
|
| 616 |
-
"normalized": false,
|
| 617 |
-
"rstrip": false,
|
| 618 |
-
"single_word": false,
|
| 619 |
-
"special": false
|
| 620 |
-
},
|
| 621 |
-
"77": {
|
| 622 |
-
"content": "<unused70>",
|
| 623 |
-
"lstrip": false,
|
| 624 |
-
"normalized": false,
|
| 625 |
-
"rstrip": false,
|
| 626 |
-
"single_word": false,
|
| 627 |
-
"special": false
|
| 628 |
-
},
|
| 629 |
-
"78": {
|
| 630 |
-
"content": "<unused71>",
|
| 631 |
-
"lstrip": false,
|
| 632 |
-
"normalized": false,
|
| 633 |
-
"rstrip": false,
|
| 634 |
-
"single_word": false,
|
| 635 |
-
"special": false
|
| 636 |
-
},
|
| 637 |
-
"79": {
|
| 638 |
-
"content": "<unused72>",
|
| 639 |
-
"lstrip": false,
|
| 640 |
-
"normalized": false,
|
| 641 |
-
"rstrip": false,
|
| 642 |
-
"single_word": false,
|
| 643 |
-
"special": false
|
| 644 |
-
},
|
| 645 |
-
"80": {
|
| 646 |
-
"content": "<unused73>",
|
| 647 |
-
"lstrip": false,
|
| 648 |
-
"normalized": false,
|
| 649 |
-
"rstrip": false,
|
| 650 |
-
"single_word": false,
|
| 651 |
-
"special": false
|
| 652 |
-
},
|
| 653 |
-
"81": {
|
| 654 |
-
"content": "<unused74>",
|
| 655 |
-
"lstrip": false,
|
| 656 |
-
"normalized": false,
|
| 657 |
-
"rstrip": false,
|
| 658 |
-
"single_word": false,
|
| 659 |
-
"special": false
|
| 660 |
-
},
|
| 661 |
-
"82": {
|
| 662 |
-
"content": "<unused75>",
|
| 663 |
-
"lstrip": false,
|
| 664 |
-
"normalized": false,
|
| 665 |
-
"rstrip": false,
|
| 666 |
-
"single_word": false,
|
| 667 |
-
"special": false
|
| 668 |
-
},
|
| 669 |
-
"83": {
|
| 670 |
-
"content": "<unused76>",
|
| 671 |
-
"lstrip": false,
|
| 672 |
-
"normalized": false,
|
| 673 |
-
"rstrip": false,
|
| 674 |
-
"single_word": false,
|
| 675 |
-
"special": false
|
| 676 |
-
},
|
| 677 |
-
"84": {
|
| 678 |
-
"content": "<unused77>",
|
| 679 |
-
"lstrip": false,
|
| 680 |
-
"normalized": false,
|
| 681 |
-
"rstrip": false,
|
| 682 |
-
"single_word": false,
|
| 683 |
-
"special": false
|
| 684 |
-
},
|
| 685 |
-
"85": {
|
| 686 |
-
"content": "<unused78>",
|
| 687 |
-
"lstrip": false,
|
| 688 |
-
"normalized": false,
|
| 689 |
-
"rstrip": false,
|
| 690 |
-
"single_word": false,
|
| 691 |
-
"special": false
|
| 692 |
-
},
|
| 693 |
-
"86": {
|
| 694 |
-
"content": "<unused79>",
|
| 695 |
-
"lstrip": false,
|
| 696 |
-
"normalized": false,
|
| 697 |
-
"rstrip": false,
|
| 698 |
-
"single_word": false,
|
| 699 |
-
"special": false
|
| 700 |
-
},
|
| 701 |
-
"87": {
|
| 702 |
-
"content": "<unused80>",
|
| 703 |
-
"lstrip": false,
|
| 704 |
-
"normalized": false,
|
| 705 |
-
"rstrip": false,
|
| 706 |
-
"single_word": false,
|
| 707 |
-
"special": false
|
| 708 |
-
},
|
| 709 |
-
"88": {
|
| 710 |
-
"content": "<unused81>",
|
| 711 |
-
"lstrip": false,
|
| 712 |
-
"normalized": false,
|
| 713 |
-
"rstrip": false,
|
| 714 |
-
"single_word": false,
|
| 715 |
-
"special": false
|
| 716 |
-
},
|
| 717 |
-
"89": {
|
| 718 |
-
"content": "<unused82>",
|
| 719 |
-
"lstrip": false,
|
| 720 |
-
"normalized": false,
|
| 721 |
-
"rstrip": false,
|
| 722 |
-
"single_word": false,
|
| 723 |
-
"special": false
|
| 724 |
-
},
|
| 725 |
-
"90": {
|
| 726 |
-
"content": "<unused83>",
|
| 727 |
-
"lstrip": false,
|
| 728 |
-
"normalized": false,
|
| 729 |
-
"rstrip": false,
|
| 730 |
-
"single_word": false,
|
| 731 |
-
"special": false
|
| 732 |
-
},
|
| 733 |
-
"91": {
|
| 734 |
-
"content": "<unused84>",
|
| 735 |
-
"lstrip": false,
|
| 736 |
-
"normalized": false,
|
| 737 |
-
"rstrip": false,
|
| 738 |
-
"single_word": false,
|
| 739 |
-
"special": false
|
| 740 |
-
},
|
| 741 |
-
"92": {
|
| 742 |
-
"content": "<unused85>",
|
| 743 |
-
"lstrip": false,
|
| 744 |
-
"normalized": false,
|
| 745 |
-
"rstrip": false,
|
| 746 |
-
"single_word": false,
|
| 747 |
-
"special": false
|
| 748 |
-
},
|
| 749 |
-
"93": {
|
| 750 |
-
"content": "<unused86>",
|
| 751 |
-
"lstrip": false,
|
| 752 |
-
"normalized": false,
|
| 753 |
-
"rstrip": false,
|
| 754 |
-
"single_word": false,
|
| 755 |
-
"special": false
|
| 756 |
-
},
|
| 757 |
-
"94": {
|
| 758 |
-
"content": "<unused87>",
|
| 759 |
-
"lstrip": false,
|
| 760 |
-
"normalized": false,
|
| 761 |
-
"rstrip": false,
|
| 762 |
-
"single_word": false,
|
| 763 |
-
"special": false
|
| 764 |
-
},
|
| 765 |
-
"95": {
|
| 766 |
-
"content": "<unused88>",
|
| 767 |
-
"lstrip": false,
|
| 768 |
-
"normalized": false,
|
| 769 |
-
"rstrip": false,
|
| 770 |
-
"single_word": false,
|
| 771 |
-
"special": false
|
| 772 |
-
},
|
| 773 |
-
"96": {
|
| 774 |
-
"content": "<unused89>",
|
| 775 |
-
"lstrip": false,
|
| 776 |
-
"normalized": false,
|
| 777 |
-
"rstrip": false,
|
| 778 |
-
"single_word": false,
|
| 779 |
-
"special": false
|
| 780 |
-
},
|
| 781 |
-
"97": {
|
| 782 |
-
"content": "<unused90>",
|
| 783 |
-
"lstrip": false,
|
| 784 |
-
"normalized": false,
|
| 785 |
-
"rstrip": false,
|
| 786 |
-
"single_word": false,
|
| 787 |
-
"special": false
|
| 788 |
-
},
|
| 789 |
-
"98": {
|
| 790 |
-
"content": "<unused91>",
|
| 791 |
-
"lstrip": false,
|
| 792 |
-
"normalized": false,
|
| 793 |
-
"rstrip": false,
|
| 794 |
-
"single_word": false,
|
| 795 |
-
"special": false
|
| 796 |
-
},
|
| 797 |
-
"99": {
|
| 798 |
-
"content": "<unused92>",
|
| 799 |
-
"lstrip": false,
|
| 800 |
-
"normalized": false,
|
| 801 |
-
"rstrip": false,
|
| 802 |
-
"single_word": false,
|
| 803 |
-
"special": false
|
| 804 |
-
},
|
| 805 |
-
"100": {
|
| 806 |
-
"content": "<unused93>",
|
| 807 |
-
"lstrip": false,
|
| 808 |
-
"normalized": false,
|
| 809 |
-
"rstrip": false,
|
| 810 |
-
"single_word": false,
|
| 811 |
-
"special": false
|
| 812 |
-
},
|
| 813 |
-
"101": {
|
| 814 |
-
"content": "<unused94>",
|
| 815 |
-
"lstrip": false,
|
| 816 |
-
"normalized": false,
|
| 817 |
-
"rstrip": false,
|
| 818 |
-
"single_word": false,
|
| 819 |
-
"special": false
|
| 820 |
-
},
|
| 821 |
-
"102": {
|
| 822 |
-
"content": "<unused95>",
|
| 823 |
-
"lstrip": false,
|
| 824 |
-
"normalized": false,
|
| 825 |
-
"rstrip": false,
|
| 826 |
-
"single_word": false,
|
| 827 |
-
"special": false
|
| 828 |
-
},
|
| 829 |
-
"103": {
|
| 830 |
-
"content": "<unused96>",
|
| 831 |
-
"lstrip": false,
|
| 832 |
-
"normalized": false,
|
| 833 |
-
"rstrip": false,
|
| 834 |
-
"single_word": false,
|
| 835 |
-
"special": false
|
| 836 |
-
},
|
| 837 |
-
"104": {
|
| 838 |
-
"content": "<unused97>",
|
| 839 |
-
"lstrip": false,
|
| 840 |
-
"normalized": false,
|
| 841 |
-
"rstrip": false,
|
| 842 |
-
"single_word": false,
|
| 843 |
-
"special": false
|
| 844 |
-
},
|
| 845 |
-
"105": {
|
| 846 |
-
"content": "<unused98>",
|
| 847 |
-
"lstrip": false,
|
| 848 |
-
"normalized": false,
|
| 849 |
-
"rstrip": false,
|
| 850 |
-
"single_word": false,
|
| 851 |
-
"special": false
|
| 852 |
-
},
|
| 853 |
-
"106": {
|
| 854 |
-
"content": "<start_of_turn>",
|
| 855 |
-
"lstrip": false,
|
| 856 |
-
"normalized": false,
|
| 857 |
-
"rstrip": false,
|
| 858 |
-
"single_word": false,
|
| 859 |
-
"special": true
|
| 860 |
-
},
|
| 861 |
-
"107": {
|
| 862 |
-
"content": "<end_of_turn>",
|
| 863 |
-
"lstrip": false,
|
| 864 |
-
"normalized": false,
|
| 865 |
-
"rstrip": false,
|
| 866 |
-
"single_word": false,
|
| 867 |
-
"special": true
|
| 868 |
-
},
|
| 869 |
-
"108": {
|
| 870 |
-
"content": "\n",
|
| 871 |
-
"lstrip": false,
|
| 872 |
-
"normalized": false,
|
| 873 |
-
"rstrip": false,
|
| 874 |
-
"single_word": false,
|
| 875 |
-
"special": false
|
| 876 |
-
},
|
| 877 |
-
"109": {
|
| 878 |
-
"content": "\n\n",
|
| 879 |
-
"lstrip": false,
|
| 880 |
-
"normalized": false,
|
| 881 |
-
"rstrip": false,
|
| 882 |
-
"single_word": false,
|
| 883 |
-
"special": false
|
| 884 |
-
},
|
| 885 |
-
"110": {
|
| 886 |
-
"content": "\n\n\n",
|
| 887 |
-
"lstrip": false,
|
| 888 |
-
"normalized": false,
|
| 889 |
-
"rstrip": false,
|
| 890 |
-
"single_word": false,
|
| 891 |
-
"special": false
|
| 892 |
-
},
|
| 893 |
-
"111": {
|
| 894 |
-
"content": "\n\n\n\n",
|
| 895 |
-
"lstrip": false,
|
| 896 |
-
"normalized": false,
|
| 897 |
-
"rstrip": false,
|
| 898 |
-
"single_word": false,
|
| 899 |
-
"special": false
|
| 900 |
-
},
|
| 901 |
-
"112": {
|
| 902 |
-
"content": "\n\n\n\n\n",
|
| 903 |
-
"lstrip": false,
|
| 904 |
-
"normalized": false,
|
| 905 |
-
"rstrip": false,
|
| 906 |
-
"single_word": false,
|
| 907 |
-
"special": false
|
| 908 |
-
},
|
| 909 |
-
"113": {
|
| 910 |
-
"content": "\n\n\n\n\n\n",
|
| 911 |
-
"lstrip": false,
|
| 912 |
-
"normalized": false,
|
| 913 |
-
"rstrip": false,
|
| 914 |
-
"single_word": false,
|
| 915 |
-
"special": false
|
| 916 |
-
},
|
| 917 |
-
"114": {
|
| 918 |
-
"content": "\n\n\n\n\n\n\n",
|
| 919 |
-
"lstrip": false,
|
| 920 |
-
"normalized": false,
|
| 921 |
-
"rstrip": false,
|
| 922 |
-
"single_word": false,
|
| 923 |
-
"special": false
|
| 924 |
-
},
|
| 925 |
-
"115": {
|
| 926 |
-
"content": "\n\n\n\n\n\n\n\n",
|
| 927 |
-
"lstrip": false,
|
| 928 |
-
"normalized": false,
|
| 929 |
-
"rstrip": false,
|
| 930 |
-
"single_word": false,
|
| 931 |
-
"special": false
|
| 932 |
-
},
|
| 933 |
-
"116": {
|
| 934 |
-
"content": "\n\n\n\n\n\n\n\n\n",
|
| 935 |
-
"lstrip": false,
|
| 936 |
-
"normalized": false,
|
| 937 |
-
"rstrip": false,
|
| 938 |
-
"single_word": false,
|
| 939 |
-
"special": false
|
| 940 |
-
},
|
| 941 |
-
"117": {
|
| 942 |
-
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
-
"lstrip": false,
|
| 944 |
-
"normalized": false,
|
| 945 |
-
"rstrip": false,
|
| 946 |
-
"single_word": false,
|
| 947 |
-
"special": false
|
| 948 |
-
},
|
| 949 |
-
"118": {
|
| 950 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
-
"lstrip": false,
|
| 952 |
-
"normalized": false,
|
| 953 |
-
"rstrip": false,
|
| 954 |
-
"single_word": false,
|
| 955 |
-
"special": false
|
| 956 |
-
},
|
| 957 |
-
"119": {
|
| 958 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
-
"lstrip": false,
|
| 960 |
-
"normalized": false,
|
| 961 |
-
"rstrip": false,
|
| 962 |
-
"single_word": false,
|
| 963 |
-
"special": false
|
| 964 |
-
},
|
| 965 |
-
"120": {
|
| 966 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
-
"lstrip": false,
|
| 968 |
-
"normalized": false,
|
| 969 |
-
"rstrip": false,
|
| 970 |
-
"single_word": false,
|
| 971 |
-
"special": false
|
| 972 |
-
},
|
| 973 |
-
"121": {
|
| 974 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
-
"lstrip": false,
|
| 976 |
-
"normalized": false,
|
| 977 |
-
"rstrip": false,
|
| 978 |
-
"single_word": false,
|
| 979 |
-
"special": false
|
| 980 |
-
},
|
| 981 |
-
"122": {
|
| 982 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
-
"lstrip": false,
|
| 984 |
-
"normalized": false,
|
| 985 |
-
"rstrip": false,
|
| 986 |
-
"single_word": false,
|
| 987 |
-
"special": false
|
| 988 |
-
},
|
| 989 |
-
"123": {
|
| 990 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
-
"lstrip": false,
|
| 992 |
-
"normalized": false,
|
| 993 |
-
"rstrip": false,
|
| 994 |
-
"single_word": false,
|
| 995 |
-
"special": false
|
| 996 |
-
},
|
| 997 |
-
"124": {
|
| 998 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
-
"lstrip": false,
|
| 1000 |
-
"normalized": false,
|
| 1001 |
-
"rstrip": false,
|
| 1002 |
-
"single_word": false,
|
| 1003 |
-
"special": false
|
| 1004 |
-
},
|
| 1005 |
-
"125": {
|
| 1006 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
-
"lstrip": false,
|
| 1008 |
-
"normalized": false,
|
| 1009 |
-
"rstrip": false,
|
| 1010 |
-
"single_word": false,
|
| 1011 |
-
"special": false
|
| 1012 |
-
},
|
| 1013 |
-
"126": {
|
| 1014 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
-
"lstrip": false,
|
| 1016 |
-
"normalized": false,
|
| 1017 |
-
"rstrip": false,
|
| 1018 |
-
"single_word": false,
|
| 1019 |
-
"special": false
|
| 1020 |
-
},
|
| 1021 |
-
"127": {
|
| 1022 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1023 |
-
"lstrip": false,
|
| 1024 |
-
"normalized": false,
|
| 1025 |
-
"rstrip": false,
|
| 1026 |
-
"single_word": false,
|
| 1027 |
-
"special": false
|
| 1028 |
-
},
|
| 1029 |
-
"128": {
|
| 1030 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1031 |
-
"lstrip": false,
|
| 1032 |
-
"normalized": false,
|
| 1033 |
-
"rstrip": false,
|
| 1034 |
-
"single_word": false,
|
| 1035 |
-
"special": false
|
| 1036 |
-
},
|
| 1037 |
-
"129": {
|
| 1038 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1039 |
-
"lstrip": false,
|
| 1040 |
-
"normalized": false,
|
| 1041 |
-
"rstrip": false,
|
| 1042 |
-
"single_word": false,
|
| 1043 |
-
"special": false
|
| 1044 |
-
},
|
| 1045 |
-
"130": {
|
| 1046 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1047 |
-
"lstrip": false,
|
| 1048 |
-
"normalized": false,
|
| 1049 |
-
"rstrip": false,
|
| 1050 |
-
"single_word": false,
|
| 1051 |
-
"special": false
|
| 1052 |
-
},
|
| 1053 |
-
"131": {
|
| 1054 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1055 |
-
"lstrip": false,
|
| 1056 |
-
"normalized": false,
|
| 1057 |
-
"rstrip": false,
|
| 1058 |
-
"single_word": false,
|
| 1059 |
-
"special": false
|
| 1060 |
-
},
|
| 1061 |
-
"132": {
|
| 1062 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1063 |
-
"lstrip": false,
|
| 1064 |
-
"normalized": false,
|
| 1065 |
-
"rstrip": false,
|
| 1066 |
-
"single_word": false,
|
| 1067 |
-
"special": false
|
| 1068 |
-
},
|
| 1069 |
-
"133": {
|
| 1070 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1071 |
-
"lstrip": false,
|
| 1072 |
-
"normalized": false,
|
| 1073 |
-
"rstrip": false,
|
| 1074 |
-
"single_word": false,
|
| 1075 |
-
"special": false
|
| 1076 |
-
},
|
| 1077 |
-
"134": {
|
| 1078 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1079 |
-
"lstrip": false,
|
| 1080 |
-
"normalized": false,
|
| 1081 |
-
"rstrip": false,
|
| 1082 |
-
"single_word": false,
|
| 1083 |
-
"special": false
|
| 1084 |
-
},
|
| 1085 |
-
"135": {
|
| 1086 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1087 |
-
"lstrip": false,
|
| 1088 |
-
"normalized": false,
|
| 1089 |
-
"rstrip": false,
|
| 1090 |
-
"single_word": false,
|
| 1091 |
-
"special": false
|
| 1092 |
-
},
|
| 1093 |
-
"136": {
|
| 1094 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1095 |
-
"lstrip": false,
|
| 1096 |
-
"normalized": false,
|
| 1097 |
-
"rstrip": false,
|
| 1098 |
-
"single_word": false,
|
| 1099 |
-
"special": false
|
| 1100 |
-
},
|
| 1101 |
-
"137": {
|
| 1102 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1103 |
-
"lstrip": false,
|
| 1104 |
-
"normalized": false,
|
| 1105 |
-
"rstrip": false,
|
| 1106 |
-
"single_word": false,
|
| 1107 |
-
"special": false
|
| 1108 |
-
},
|
| 1109 |
-
"138": {
|
| 1110 |
-
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1111 |
-
"lstrip": false,
|
| 1112 |
-
"normalized": false,
|
| 1113 |
-
"rstrip": false,
|
| 1114 |
-
"single_word": false,
|
| 1115 |
-
"special": false
|
| 1116 |
-
},
|
| 1117 |
-
"139": {
|
| 1118 |
-
"content": "▁▁",
|
| 1119 |
-
"lstrip": false,
|
| 1120 |
-
"normalized": false,
|
| 1121 |
-
"rstrip": false,
|
| 1122 |
-
"single_word": false,
|
| 1123 |
-
"special": false
|
| 1124 |
-
},
|
| 1125 |
-
"140": {
|
| 1126 |
-
"content": "▁▁▁",
|
| 1127 |
-
"lstrip": false,
|
| 1128 |
-
"normalized": false,
|
| 1129 |
-
"rstrip": false,
|
| 1130 |
-
"single_word": false,
|
| 1131 |
-
"special": false
|
| 1132 |
-
},
|
| 1133 |
-
"141": {
|
| 1134 |
-
"content": "▁▁▁▁",
|
| 1135 |
-
"lstrip": false,
|
| 1136 |
-
"normalized": false,
|
| 1137 |
-
"rstrip": false,
|
| 1138 |
-
"single_word": false,
|
| 1139 |
-
"special": false
|
| 1140 |
-
},
|
| 1141 |
-
"142": {
|
| 1142 |
-
"content": "▁▁▁▁▁",
|
| 1143 |
-
"lstrip": false,
|
| 1144 |
-
"normalized": false,
|
| 1145 |
-
"rstrip": false,
|
| 1146 |
-
"single_word": false,
|
| 1147 |
-
"special": false
|
| 1148 |
-
},
|
| 1149 |
-
"143": {
|
| 1150 |
-
"content": "▁▁▁▁▁▁",
|
| 1151 |
-
"lstrip": false,
|
| 1152 |
-
"normalized": false,
|
| 1153 |
-
"rstrip": false,
|
| 1154 |
-
"single_word": false,
|
| 1155 |
-
"special": false
|
| 1156 |
-
},
|
| 1157 |
-
"144": {
|
| 1158 |
-
"content": "▁▁▁▁▁▁▁",
|
| 1159 |
-
"lstrip": false,
|
| 1160 |
-
"normalized": false,
|
| 1161 |
-
"rstrip": false,
|
| 1162 |
-
"single_word": false,
|
| 1163 |
-
"special": false
|
| 1164 |
-
},
|
| 1165 |
-
"145": {
|
| 1166 |
-
"content": "▁▁▁▁▁▁▁▁",
|
| 1167 |
-
"lstrip": false,
|
| 1168 |
-
"normalized": false,
|
| 1169 |
-
"rstrip": false,
|
| 1170 |
-
"single_word": false,
|
| 1171 |
-
"special": false
|
| 1172 |
-
},
|
| 1173 |
-
"146": {
|
| 1174 |
-
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1175 |
-
"lstrip": false,
|
| 1176 |
-
"normalized": false,
|
| 1177 |
-
"rstrip": false,
|
| 1178 |
-
"single_word": false,
|
| 1179 |
-
"special": false
|
| 1180 |
-
},
|
| 1181 |
-
"147": {
|
| 1182 |
-
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
-
"lstrip": false,
|
| 1184 |
-
"normalized": false,
|
| 1185 |
-
"rstrip": false,
|
| 1186 |
-
"single_word": false,
|
| 1187 |
-
"special": false
|
| 1188 |
-
},
|
| 1189 |
-
"148": {
|
| 1190 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
-
"lstrip": false,
|
| 1192 |
-
"normalized": false,
|
| 1193 |
-
"rstrip": false,
|
| 1194 |
-
"single_word": false,
|
| 1195 |
-
"special": false
|
| 1196 |
-
},
|
| 1197 |
-
"149": {
|
| 1198 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
-
"lstrip": false,
|
| 1200 |
-
"normalized": false,
|
| 1201 |
-
"rstrip": false,
|
| 1202 |
-
"single_word": false,
|
| 1203 |
-
"special": false
|
| 1204 |
-
},
|
| 1205 |
-
"150": {
|
| 1206 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
-
"lstrip": false,
|
| 1208 |
-
"normalized": false,
|
| 1209 |
-
"rstrip": false,
|
| 1210 |
-
"single_word": false,
|
| 1211 |
-
"special": false
|
| 1212 |
-
},
|
| 1213 |
-
"151": {
|
| 1214 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
-
"lstrip": false,
|
| 1216 |
-
"normalized": false,
|
| 1217 |
-
"rstrip": false,
|
| 1218 |
-
"single_word": false,
|
| 1219 |
-
"special": false
|
| 1220 |
-
},
|
| 1221 |
-
"152": {
|
| 1222 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
-
"lstrip": false,
|
| 1224 |
-
"normalized": false,
|
| 1225 |
-
"rstrip": false,
|
| 1226 |
-
"single_word": false,
|
| 1227 |
-
"special": false
|
| 1228 |
-
},
|
| 1229 |
-
"153": {
|
| 1230 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
-
"lstrip": false,
|
| 1232 |
-
"normalized": false,
|
| 1233 |
-
"rstrip": false,
|
| 1234 |
-
"single_word": false,
|
| 1235 |
-
"special": false
|
| 1236 |
-
},
|
| 1237 |
-
"154": {
|
| 1238 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
-
"lstrip": false,
|
| 1240 |
-
"normalized": false,
|
| 1241 |
-
"rstrip": false,
|
| 1242 |
-
"single_word": false,
|
| 1243 |
-
"special": false
|
| 1244 |
-
},
|
| 1245 |
-
"155": {
|
| 1246 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
-
"lstrip": false,
|
| 1248 |
-
"normalized": false,
|
| 1249 |
-
"rstrip": false,
|
| 1250 |
-
"single_word": false,
|
| 1251 |
-
"special": false
|
| 1252 |
-
},
|
| 1253 |
-
"156": {
|
| 1254 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
-
"lstrip": false,
|
| 1256 |
-
"normalized": false,
|
| 1257 |
-
"rstrip": false,
|
| 1258 |
-
"single_word": false,
|
| 1259 |
-
"special": false
|
| 1260 |
-
},
|
| 1261 |
-
"157": {
|
| 1262 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
-
"lstrip": false,
|
| 1264 |
-
"normalized": false,
|
| 1265 |
-
"rstrip": false,
|
| 1266 |
-
"single_word": false,
|
| 1267 |
-
"special": false
|
| 1268 |
-
},
|
| 1269 |
-
"158": {
|
| 1270 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
-
"lstrip": false,
|
| 1272 |
-
"normalized": false,
|
| 1273 |
-
"rstrip": false,
|
| 1274 |
-
"single_word": false,
|
| 1275 |
-
"special": false
|
| 1276 |
-
},
|
| 1277 |
-
"159": {
|
| 1278 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
-
"lstrip": false,
|
| 1280 |
-
"normalized": false,
|
| 1281 |
-
"rstrip": false,
|
| 1282 |
-
"single_word": false,
|
| 1283 |
-
"special": false
|
| 1284 |
-
},
|
| 1285 |
-
"160": {
|
| 1286 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
-
"lstrip": false,
|
| 1288 |
-
"normalized": false,
|
| 1289 |
-
"rstrip": false,
|
| 1290 |
-
"single_word": false,
|
| 1291 |
-
"special": false
|
| 1292 |
-
},
|
| 1293 |
-
"161": {
|
| 1294 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1295 |
-
"lstrip": false,
|
| 1296 |
-
"normalized": false,
|
| 1297 |
-
"rstrip": false,
|
| 1298 |
-
"single_word": false,
|
| 1299 |
-
"special": false
|
| 1300 |
-
},
|
| 1301 |
-
"162": {
|
| 1302 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
-
"lstrip": false,
|
| 1304 |
-
"normalized": false,
|
| 1305 |
-
"rstrip": false,
|
| 1306 |
-
"single_word": false,
|
| 1307 |
-
"special": false
|
| 1308 |
-
},
|
| 1309 |
-
"163": {
|
| 1310 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
-
"lstrip": false,
|
| 1312 |
-
"normalized": false,
|
| 1313 |
-
"rstrip": false,
|
| 1314 |
-
"single_word": false,
|
| 1315 |
-
"special": false
|
| 1316 |
-
},
|
| 1317 |
-
"164": {
|
| 1318 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
-
"lstrip": false,
|
| 1320 |
-
"normalized": false,
|
| 1321 |
-
"rstrip": false,
|
| 1322 |
-
"single_word": false,
|
| 1323 |
-
"special": false
|
| 1324 |
-
},
|
| 1325 |
-
"165": {
|
| 1326 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
-
"lstrip": false,
|
| 1328 |
-
"normalized": false,
|
| 1329 |
-
"rstrip": false,
|
| 1330 |
-
"single_word": false,
|
| 1331 |
-
"special": false
|
| 1332 |
-
},
|
| 1333 |
-
"166": {
|
| 1334 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
-
"lstrip": false,
|
| 1336 |
-
"normalized": false,
|
| 1337 |
-
"rstrip": false,
|
| 1338 |
-
"single_word": false,
|
| 1339 |
-
"special": false
|
| 1340 |
-
},
|
| 1341 |
-
"167": {
|
| 1342 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
-
"lstrip": false,
|
| 1344 |
-
"normalized": false,
|
| 1345 |
-
"rstrip": false,
|
| 1346 |
-
"single_word": false,
|
| 1347 |
-
"special": false
|
| 1348 |
-
},
|
| 1349 |
-
"168": {
|
| 1350 |
-
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1351 |
-
"lstrip": false,
|
| 1352 |
-
"normalized": false,
|
| 1353 |
-
"rstrip": false,
|
| 1354 |
-
"single_word": false,
|
| 1355 |
-
"special": false
|
| 1356 |
-
},
|
| 1357 |
-
"169": {
|
| 1358 |
-
"content": "<table>",
|
| 1359 |
-
"lstrip": false,
|
| 1360 |
-
"normalized": false,
|
| 1361 |
-
"rstrip": false,
|
| 1362 |
-
"single_word": false,
|
| 1363 |
-
"special": false
|
| 1364 |
-
},
|
| 1365 |
-
"170": {
|
| 1366 |
-
"content": "<caption>",
|
| 1367 |
-
"lstrip": false,
|
| 1368 |
-
"normalized": false,
|
| 1369 |
-
"rstrip": false,
|
| 1370 |
-
"single_word": false,
|
| 1371 |
-
"special": false
|
| 1372 |
-
},
|
| 1373 |
-
"171": {
|
| 1374 |
-
"content": "<thead>",
|
| 1375 |
-
"lstrip": false,
|
| 1376 |
-
"normalized": false,
|
| 1377 |
-
"rstrip": false,
|
| 1378 |
-
"single_word": false,
|
| 1379 |
-
"special": false
|
| 1380 |
-
},
|
| 1381 |
-
"172": {
|
| 1382 |
-
"content": "<tbody>",
|
| 1383 |
-
"lstrip": false,
|
| 1384 |
-
"normalized": false,
|
| 1385 |
-
"rstrip": false,
|
| 1386 |
-
"single_word": false,
|
| 1387 |
-
"special": false
|
| 1388 |
-
},
|
| 1389 |
-
"173": {
|
| 1390 |
-
"content": "<tfoot>",
|
| 1391 |
-
"lstrip": false,
|
| 1392 |
-
"normalized": false,
|
| 1393 |
-
"rstrip": false,
|
| 1394 |
-
"single_word": false,
|
| 1395 |
-
"special": false
|
| 1396 |
-
},
|
| 1397 |
-
"174": {
|
| 1398 |
-
"content": "<tr>",
|
| 1399 |
-
"lstrip": false,
|
| 1400 |
-
"normalized": false,
|
| 1401 |
-
"rstrip": false,
|
| 1402 |
-
"single_word": false,
|
| 1403 |
-
"special": false
|
| 1404 |
-
},
|
| 1405 |
-
"175": {
|
| 1406 |
-
"content": "<th>",
|
| 1407 |
-
"lstrip": false,
|
| 1408 |
-
"normalized": false,
|
| 1409 |
-
"rstrip": false,
|
| 1410 |
-
"single_word": false,
|
| 1411 |
-
"special": false
|
| 1412 |
-
},
|
| 1413 |
-
"176": {
|
| 1414 |
-
"content": "<td>",
|
| 1415 |
-
"lstrip": false,
|
| 1416 |
-
"normalized": false,
|
| 1417 |
-
"rstrip": false,
|
| 1418 |
-
"single_word": false,
|
| 1419 |
-
"special": false
|
| 1420 |
-
},
|
| 1421 |
-
"177": {
|
| 1422 |
-
"content": "</table>",
|
| 1423 |
-
"lstrip": false,
|
| 1424 |
-
"normalized": false,
|
| 1425 |
-
"rstrip": false,
|
| 1426 |
-
"single_word": false,
|
| 1427 |
-
"special": false
|
| 1428 |
-
},
|
| 1429 |
-
"178": {
|
| 1430 |
-
"content": "</caption>",
|
| 1431 |
-
"lstrip": false,
|
| 1432 |
-
"normalized": false,
|
| 1433 |
-
"rstrip": false,
|
| 1434 |
-
"single_word": false,
|
| 1435 |
-
"special": false
|
| 1436 |
-
},
|
| 1437 |
-
"179": {
|
| 1438 |
-
"content": "</thead>",
|
| 1439 |
-
"lstrip": false,
|
| 1440 |
-
"normalized": false,
|
| 1441 |
-
"rstrip": false,
|
| 1442 |
-
"single_word": false,
|
| 1443 |
-
"special": false
|
| 1444 |
-
},
|
| 1445 |
-
"180": {
|
| 1446 |
-
"content": "</tbody>",
|
| 1447 |
-
"lstrip": false,
|
| 1448 |
-
"normalized": false,
|
| 1449 |
-
"rstrip": false,
|
| 1450 |
-
"single_word": false,
|
| 1451 |
-
"special": false
|
| 1452 |
-
},
|
| 1453 |
-
"181": {
|
| 1454 |
-
"content": "</tfoot>",
|
| 1455 |
-
"lstrip": false,
|
| 1456 |
-
"normalized": false,
|
| 1457 |
-
"rstrip": false,
|
| 1458 |
-
"single_word": false,
|
| 1459 |
-
"special": false
|
| 1460 |
-
},
|
| 1461 |
-
"182": {
|
| 1462 |
-
"content": "</tr>",
|
| 1463 |
-
"lstrip": false,
|
| 1464 |
-
"normalized": false,
|
| 1465 |
-
"rstrip": false,
|
| 1466 |
-
"single_word": false,
|
| 1467 |
-
"special": false
|
| 1468 |
-
},
|
| 1469 |
-
"183": {
|
| 1470 |
-
"content": "</th>",
|
| 1471 |
-
"lstrip": false,
|
| 1472 |
-
"normalized": false,
|
| 1473 |
-
"rstrip": false,
|
| 1474 |
-
"single_word": false,
|
| 1475 |
-
"special": false
|
| 1476 |
-
},
|
| 1477 |
-
"184": {
|
| 1478 |
-
"content": "</td>",
|
| 1479 |
-
"lstrip": false,
|
| 1480 |
-
"normalized": false,
|
| 1481 |
-
"rstrip": false,
|
| 1482 |
-
"single_word": false,
|
| 1483 |
-
"special": false
|
| 1484 |
-
},
|
| 1485 |
-
"185": {
|
| 1486 |
-
"content": "<h1>",
|
| 1487 |
-
"lstrip": false,
|
| 1488 |
-
"normalized": false,
|
| 1489 |
-
"rstrip": false,
|
| 1490 |
-
"single_word": false,
|
| 1491 |
-
"special": false
|
| 1492 |
-
},
|
| 1493 |
-
"186": {
|
| 1494 |
-
"content": "<h2>",
|
| 1495 |
-
"lstrip": false,
|
| 1496 |
-
"normalized": false,
|
| 1497 |
-
"rstrip": false,
|
| 1498 |
-
"single_word": false,
|
| 1499 |
-
"special": false
|
| 1500 |
-
},
|
| 1501 |
-
"187": {
|
| 1502 |
-
"content": "<h3>",
|
| 1503 |
-
"lstrip": false,
|
| 1504 |
-
"normalized": false,
|
| 1505 |
-
"rstrip": false,
|
| 1506 |
-
"single_word": false,
|
| 1507 |
-
"special": false
|
| 1508 |
-
},
|
| 1509 |
-
"188": {
|
| 1510 |
-
"content": "<h4>",
|
| 1511 |
-
"lstrip": false,
|
| 1512 |
-
"normalized": false,
|
| 1513 |
-
"rstrip": false,
|
| 1514 |
-
"single_word": false,
|
| 1515 |
-
"special": false
|
| 1516 |
-
},
|
| 1517 |
-
"189": {
|
| 1518 |
-
"content": "<h5>",
|
| 1519 |
-
"lstrip": false,
|
| 1520 |
-
"normalized": false,
|
| 1521 |
-
"rstrip": false,
|
| 1522 |
-
"single_word": false,
|
| 1523 |
-
"special": false
|
| 1524 |
-
},
|
| 1525 |
-
"190": {
|
| 1526 |
-
"content": "<h6>",
|
| 1527 |
-
"lstrip": false,
|
| 1528 |
-
"normalized": false,
|
| 1529 |
-
"rstrip": false,
|
| 1530 |
-
"single_word": false,
|
| 1531 |
-
"special": false
|
| 1532 |
-
},
|
| 1533 |
-
"191": {
|
| 1534 |
-
"content": "<blockquote>",
|
| 1535 |
-
"lstrip": false,
|
| 1536 |
-
"normalized": false,
|
| 1537 |
-
"rstrip": false,
|
| 1538 |
-
"single_word": false,
|
| 1539 |
-
"special": false
|
| 1540 |
-
},
|
| 1541 |
-
"192": {
|
| 1542 |
-
"content": "</h1>",
|
| 1543 |
-
"lstrip": false,
|
| 1544 |
-
"normalized": false,
|
| 1545 |
-
"rstrip": false,
|
| 1546 |
-
"single_word": false,
|
| 1547 |
-
"special": false
|
| 1548 |
-
},
|
| 1549 |
-
"193": {
|
| 1550 |
-
"content": "</h2>",
|
| 1551 |
-
"lstrip": false,
|
| 1552 |
-
"normalized": false,
|
| 1553 |
-
"rstrip": false,
|
| 1554 |
-
"single_word": false,
|
| 1555 |
-
"special": false
|
| 1556 |
-
},
|
| 1557 |
-
"194": {
|
| 1558 |
-
"content": "</h3>",
|
| 1559 |
-
"lstrip": false,
|
| 1560 |
-
"normalized": false,
|
| 1561 |
-
"rstrip": false,
|
| 1562 |
-
"single_word": false,
|
| 1563 |
-
"special": false
|
| 1564 |
-
},
|
| 1565 |
-
"195": {
|
| 1566 |
-
"content": "</h4>",
|
| 1567 |
-
"lstrip": false,
|
| 1568 |
-
"normalized": false,
|
| 1569 |
-
"rstrip": false,
|
| 1570 |
-
"single_word": false,
|
| 1571 |
-
"special": false
|
| 1572 |
-
},
|
| 1573 |
-
"196": {
|
| 1574 |
-
"content": "</h5>",
|
| 1575 |
-
"lstrip": false,
|
| 1576 |
-
"normalized": false,
|
| 1577 |
-
"rstrip": false,
|
| 1578 |
-
"single_word": false,
|
| 1579 |
-
"special": false
|
| 1580 |
-
},
|
| 1581 |
-
"197": {
|
| 1582 |
-
"content": "</h6>",
|
| 1583 |
-
"lstrip": false,
|
| 1584 |
-
"normalized": false,
|
| 1585 |
-
"rstrip": false,
|
| 1586 |
-
"single_word": false,
|
| 1587 |
-
"special": false
|
| 1588 |
-
},
|
| 1589 |
-
"198": {
|
| 1590 |
-
"content": "</blockquote>",
|
| 1591 |
-
"lstrip": false,
|
| 1592 |
-
"normalized": false,
|
| 1593 |
-
"rstrip": false,
|
| 1594 |
-
"single_word": false,
|
| 1595 |
-
"special": false
|
| 1596 |
-
},
|
| 1597 |
-
"199": {
|
| 1598 |
-
"content": "<strong>",
|
| 1599 |
-
"lstrip": false,
|
| 1600 |
-
"normalized": false,
|
| 1601 |
-
"rstrip": false,
|
| 1602 |
-
"single_word": false,
|
| 1603 |
-
"special": false
|
| 1604 |
-
},
|
| 1605 |
-
"200": {
|
| 1606 |
-
"content": "<em>",
|
| 1607 |
-
"lstrip": false,
|
| 1608 |
-
"normalized": false,
|
| 1609 |
-
"rstrip": false,
|
| 1610 |
-
"single_word": false,
|
| 1611 |
-
"special": false
|
| 1612 |
-
},
|
| 1613 |
-
"201": {
|
| 1614 |
-
"content": "<b>",
|
| 1615 |
-
"lstrip": false,
|
| 1616 |
-
"normalized": false,
|
| 1617 |
-
"rstrip": false,
|
| 1618 |
-
"single_word": false,
|
| 1619 |
-
"special": false
|
| 1620 |
-
},
|
| 1621 |
-
"202": {
|
| 1622 |
-
"content": "<i>",
|
| 1623 |
-
"lstrip": false,
|
| 1624 |
-
"normalized": false,
|
| 1625 |
-
"rstrip": false,
|
| 1626 |
-
"single_word": false,
|
| 1627 |
-
"special": false
|
| 1628 |
-
},
|
| 1629 |
-
"203": {
|
| 1630 |
-
"content": "<u>",
|
| 1631 |
-
"lstrip": false,
|
| 1632 |
-
"normalized": false,
|
| 1633 |
-
"rstrip": false,
|
| 1634 |
-
"single_word": false,
|
| 1635 |
-
"special": false
|
| 1636 |
-
},
|
| 1637 |
-
"204": {
|
| 1638 |
-
"content": "<s>",
|
| 1639 |
-
"lstrip": false,
|
| 1640 |
-
"normalized": false,
|
| 1641 |
-
"rstrip": false,
|
| 1642 |
-
"single_word": false,
|
| 1643 |
-
"special": false
|
| 1644 |
-
},
|
| 1645 |
-
"205": {
|
| 1646 |
-
"content": "<sub>",
|
| 1647 |
-
"lstrip": false,
|
| 1648 |
-
"normalized": false,
|
| 1649 |
-
"rstrip": false,
|
| 1650 |
-
"single_word": false,
|
| 1651 |
-
"special": false
|
| 1652 |
-
},
|
| 1653 |
-
"206": {
|
| 1654 |
-
"content": "<sup>",
|
| 1655 |
-
"lstrip": false,
|
| 1656 |
-
"normalized": false,
|
| 1657 |
-
"rstrip": false,
|
| 1658 |
-
"single_word": false,
|
| 1659 |
-
"special": false
|
| 1660 |
-
},
|
| 1661 |
-
"207": {
|
| 1662 |
-
"content": "<code>",
|
| 1663 |
-
"lstrip": false,
|
| 1664 |
-
"normalized": false,
|
| 1665 |
-
"rstrip": false,
|
| 1666 |
-
"single_word": false,
|
| 1667 |
-
"special": false
|
| 1668 |
-
},
|
| 1669 |
-
"208": {
|
| 1670 |
-
"content": "</strong>",
|
| 1671 |
-
"lstrip": false,
|
| 1672 |
-
"normalized": false,
|
| 1673 |
-
"rstrip": false,
|
| 1674 |
-
"single_word": false,
|
| 1675 |
-
"special": false
|
| 1676 |
-
},
|
| 1677 |
-
"209": {
|
| 1678 |
-
"content": "</em>",
|
| 1679 |
-
"lstrip": false,
|
| 1680 |
-
"normalized": false,
|
| 1681 |
-
"rstrip": false,
|
| 1682 |
-
"single_word": false,
|
| 1683 |
-
"special": false
|
| 1684 |
-
},
|
| 1685 |
-
"210": {
|
| 1686 |
-
"content": "</b>",
|
| 1687 |
-
"lstrip": false,
|
| 1688 |
-
"normalized": false,
|
| 1689 |
-
"rstrip": false,
|
| 1690 |
-
"single_word": false,
|
| 1691 |
-
"special": false
|
| 1692 |
-
},
|
| 1693 |
-
"211": {
|
| 1694 |
-
"content": "</i>",
|
| 1695 |
-
"lstrip": false,
|
| 1696 |
-
"normalized": false,
|
| 1697 |
-
"rstrip": false,
|
| 1698 |
-
"single_word": false,
|
| 1699 |
-
"special": false
|
| 1700 |
-
},
|
| 1701 |
-
"212": {
|
| 1702 |
-
"content": "</u>",
|
| 1703 |
-
"lstrip": false,
|
| 1704 |
-
"normalized": false,
|
| 1705 |
-
"rstrip": false,
|
| 1706 |
-
"single_word": false,
|
| 1707 |
-
"special": false
|
| 1708 |
-
},
|
| 1709 |
-
"213": {
|
| 1710 |
-
"content": "</s>",
|
| 1711 |
-
"lstrip": false,
|
| 1712 |
-
"normalized": false,
|
| 1713 |
-
"rstrip": false,
|
| 1714 |
-
"single_word": false,
|
| 1715 |
-
"special": false
|
| 1716 |
-
},
|
| 1717 |
-
"214": {
|
| 1718 |
-
"content": "</sub>",
|
| 1719 |
-
"lstrip": false,
|
| 1720 |
-
"normalized": false,
|
| 1721 |
-
"rstrip": false,
|
| 1722 |
-
"single_word": false,
|
| 1723 |
-
"special": false
|
| 1724 |
-
},
|
| 1725 |
-
"215": {
|
| 1726 |
-
"content": "</sup>",
|
| 1727 |
-
"lstrip": false,
|
| 1728 |
-
"normalized": false,
|
| 1729 |
-
"rstrip": false,
|
| 1730 |
-
"single_word": false,
|
| 1731 |
-
"special": false
|
| 1732 |
-
},
|
| 1733 |
-
"216": {
|
| 1734 |
-
"content": "</code>",
|
| 1735 |
-
"lstrip": false,
|
| 1736 |
-
"normalized": false,
|
| 1737 |
-
"rstrip": false,
|
| 1738 |
-
"single_word": false,
|
| 1739 |
-
"special": false
|
| 1740 |
}
|
| 1741 |
},
|
| 1742 |
-
"additional_special_tokens": [
|
| 1743 |
-
|
| 1744 |
-
|
| 1745 |
-
],
|
| 1746 |
-
"bos_token": "<bos>",
|
| 1747 |
-
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
| 1748 |
"clean_up_tokenization_spaces": false,
|
| 1749 |
-
"eos_token": "
|
|
|
|
| 1750 |
"model_max_length": 1000000000000000019884624838656,
|
| 1751 |
-
"pad_token": "
|
| 1752 |
"sp_model_kwargs": {},
|
| 1753 |
"spaces_between_special_tokens": false,
|
| 1754 |
-
"tokenizer_class": "
|
| 1755 |
"unk_token": "<unk>",
|
| 1756 |
"use_default_system_prompt": false
|
| 1757 |
}
|
|
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": false,
|
| 9 |
"rstrip": false,
|
|
|
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
|
|
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
| 33 |
"rstrip": false,
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
}
|
| 37 |
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
|
|
|
|
|
|
|
|
|
| 41 |
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "</s>",
|
| 43 |
+
"legacy": true,
|
| 44 |
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
"sp_model_kwargs": {},
|
| 47 |
"spaces_between_special_tokens": false,
|
| 48 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 49 |
"unk_token": "<unk>",
|
| 50 |
"use_default_system_prompt": false
|
| 51 |
}
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0.33,
|
| 3 |
+
"train_loss": 1.802713230252266,
|
| 4 |
+
"train_runtime": 3920.872,
|
| 5 |
+
"train_samples_per_second": 4.179,
|
| 6 |
+
"train_steps_per_second": 0.065
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "lora_lr/
|
| 4 |
"epoch": 0.327575175943698,
|
| 5 |
"eval_steps": 10,
|
| 6 |
"global_step": 256,
|
|
@@ -10,2011 +10,2011 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
-
"loss":
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.0,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 4.000000000000001e-06,
|
| 22 |
-
"loss":
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 6e-06,
|
| 29 |
-
"loss":
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.01,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 8.000000000000001e-06,
|
| 36 |
-
"loss":
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.01,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
"learning_rate": 1e-05,
|
| 43 |
-
"loss":
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.01,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 1.2e-05,
|
| 50 |
-
"loss":
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.01,
|
| 55 |
-
"grad_norm":
|
| 56 |
"learning_rate": 1.4000000000000001e-05,
|
| 57 |
-
"loss":
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.01,
|
| 62 |
-
"grad_norm":
|
| 63 |
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
-
"loss":
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.01,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 1.8e-05,
|
| 71 |
-
"loss":
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.01,
|
| 76 |
-
"grad_norm": 1.
|
| 77 |
"learning_rate": 2e-05,
|
| 78 |
-
"loss":
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.01,
|
| 83 |
-
"eval_loss":
|
| 84 |
-
"eval_runtime":
|
| 85 |
-
"eval_samples_per_second":
|
| 86 |
-
"eval_steps_per_second": 1.
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.01,
|
| 91 |
-
"grad_norm": 1.
|
| 92 |
"learning_rate": 2.2000000000000003e-05,
|
| 93 |
-
"loss":
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.02,
|
| 98 |
-
"grad_norm":
|
| 99 |
"learning_rate": 2.4e-05,
|
| 100 |
-
"loss":
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.02,
|
| 105 |
-
"grad_norm": 1.
|
| 106 |
"learning_rate": 2.6000000000000002e-05,
|
| 107 |
-
"loss":
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.02,
|
| 112 |
-
"grad_norm": 1.
|
| 113 |
"learning_rate": 2.8000000000000003e-05,
|
| 114 |
-
"loss":
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.02,
|
| 119 |
-
"grad_norm": 1.
|
| 120 |
"learning_rate": 3e-05,
|
| 121 |
-
"loss":
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.02,
|
| 126 |
-
"grad_norm": 1.
|
| 127 |
"learning_rate": 3.2000000000000005e-05,
|
| 128 |
-
"loss":
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.02,
|
| 133 |
-
"grad_norm": 1.
|
| 134 |
"learning_rate": 3.4000000000000007e-05,
|
| 135 |
-
"loss":
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.02,
|
| 140 |
-
"grad_norm": 1.
|
| 141 |
"learning_rate": 3.6e-05,
|
| 142 |
-
"loss":
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.02,
|
| 147 |
-
"grad_norm": 1.
|
| 148 |
"learning_rate": 3.8e-05,
|
| 149 |
-
"loss":
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.03,
|
| 154 |
-
"grad_norm": 1.
|
| 155 |
"learning_rate": 4e-05,
|
| 156 |
-
"loss":
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.03,
|
| 161 |
-
"eval_loss":
|
| 162 |
-
"eval_runtime":
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second": 1.
|
| 165 |
"step": 20
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.03,
|
| 169 |
-
"grad_norm": 1.
|
| 170 |
"learning_rate": 4.2e-05,
|
| 171 |
-
"loss":
|
| 172 |
"step": 21
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 0.03,
|
| 176 |
-
"grad_norm":
|
| 177 |
"learning_rate": 4.4000000000000006e-05,
|
| 178 |
-
"loss":
|
| 179 |
"step": 22
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.03,
|
| 183 |
-
"grad_norm":
|
| 184 |
"learning_rate": 4.600000000000001e-05,
|
| 185 |
-
"loss":
|
| 186 |
"step": 23
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.03,
|
| 190 |
-
"grad_norm":
|
| 191 |
"learning_rate": 4.8e-05,
|
| 192 |
-
"loss":
|
| 193 |
"step": 24
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.03,
|
| 197 |
-
"grad_norm":
|
| 198 |
"learning_rate": 5e-05,
|
| 199 |
-
"loss":
|
| 200 |
"step": 25
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.03,
|
| 204 |
-
"grad_norm":
|
| 205 |
"learning_rate": 5.2000000000000004e-05,
|
| 206 |
-
"loss": 3.
|
| 207 |
"step": 26
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.03,
|
| 211 |
-
"grad_norm":
|
| 212 |
"learning_rate": 5.4000000000000005e-05,
|
| 213 |
-
"loss":
|
| 214 |
"step": 27
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 0.04,
|
| 218 |
-
"grad_norm":
|
| 219 |
"learning_rate": 5.6000000000000006e-05,
|
| 220 |
-
"loss":
|
| 221 |
"step": 28
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.04,
|
| 225 |
-
"grad_norm":
|
| 226 |
"learning_rate": 5.8e-05,
|
| 227 |
-
"loss":
|
| 228 |
"step": 29
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.04,
|
| 232 |
-
"grad_norm":
|
| 233 |
"learning_rate": 6e-05,
|
| 234 |
-
"loss":
|
| 235 |
"step": 30
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.04,
|
| 239 |
-
"eval_loss":
|
| 240 |
-
"eval_runtime":
|
| 241 |
-
"eval_samples_per_second":
|
| 242 |
-
"eval_steps_per_second": 1.
|
| 243 |
"step": 30
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.04,
|
| 247 |
-
"grad_norm": 2.
|
| 248 |
"learning_rate": 6.2e-05,
|
| 249 |
-
"loss":
|
| 250 |
"step": 31
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.04,
|
| 254 |
-
"grad_norm": 1.
|
| 255 |
"learning_rate": 6.400000000000001e-05,
|
| 256 |
-
"loss":
|
| 257 |
"step": 32
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 0.04,
|
| 261 |
-
"grad_norm":
|
| 262 |
"learning_rate": 6.6e-05,
|
| 263 |
-
"loss":
|
| 264 |
"step": 33
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.04,
|
| 268 |
-
"grad_norm":
|
| 269 |
"learning_rate": 6.800000000000001e-05,
|
| 270 |
-
"loss":
|
| 271 |
"step": 34
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.04,
|
| 275 |
-
"grad_norm": 1.
|
| 276 |
"learning_rate": 7e-05,
|
| 277 |
-
"loss":
|
| 278 |
"step": 35
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.05,
|
| 282 |
-
"grad_norm": 1.
|
| 283 |
"learning_rate": 7.2e-05,
|
| 284 |
-
"loss": 2.
|
| 285 |
"step": 36
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.05,
|
| 289 |
-
"grad_norm": 1.
|
| 290 |
"learning_rate": 7.4e-05,
|
| 291 |
-
"loss":
|
| 292 |
"step": 37
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 0.05,
|
| 296 |
-
"grad_norm": 1.
|
| 297 |
"learning_rate": 7.6e-05,
|
| 298 |
-
"loss": 2.
|
| 299 |
"step": 38
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.05,
|
| 303 |
-
"grad_norm": 1.
|
| 304 |
"learning_rate": 7.800000000000001e-05,
|
| 305 |
-
"loss":
|
| 306 |
"step": 39
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.05,
|
| 310 |
-
"grad_norm":
|
| 311 |
"learning_rate": 8e-05,
|
| 312 |
-
"loss":
|
| 313 |
"step": 40
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 0.05,
|
| 317 |
-
"eval_loss":
|
| 318 |
-
"eval_runtime":
|
| 319 |
-
"eval_samples_per_second":
|
| 320 |
-
"eval_steps_per_second": 1.
|
| 321 |
"step": 40
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.05,
|
| 325 |
-
"grad_norm": 0.
|
| 326 |
"learning_rate": 8.2e-05,
|
| 327 |
-
"loss":
|
| 328 |
"step": 41
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 0.05,
|
| 332 |
-
"grad_norm":
|
| 333 |
"learning_rate": 8.4e-05,
|
| 334 |
-
"loss":
|
| 335 |
"step": 42
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 0.06,
|
| 339 |
-
"grad_norm":
|
| 340 |
"learning_rate": 8.6e-05,
|
| 341 |
-
"loss":
|
| 342 |
"step": 43
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 0.06,
|
| 346 |
-
"grad_norm":
|
| 347 |
"learning_rate": 8.800000000000001e-05,
|
| 348 |
-
"loss":
|
| 349 |
"step": 44
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.06,
|
| 353 |
-
"grad_norm":
|
| 354 |
"learning_rate": 9e-05,
|
| 355 |
-
"loss":
|
| 356 |
"step": 45
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.06,
|
| 360 |
-
"grad_norm": 0.
|
| 361 |
"learning_rate": 9.200000000000001e-05,
|
| 362 |
-
"loss":
|
| 363 |
"step": 46
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.06,
|
| 367 |
"grad_norm": 0.5625,
|
| 368 |
"learning_rate": 9.4e-05,
|
| 369 |
-
"loss":
|
| 370 |
"step": 47
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 0.06,
|
| 374 |
-
"grad_norm": 0.
|
| 375 |
"learning_rate": 9.6e-05,
|
| 376 |
-
"loss":
|
| 377 |
"step": 48
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 0.06,
|
| 381 |
-
"grad_norm": 0.
|
| 382 |
"learning_rate": 9.8e-05,
|
| 383 |
-
"loss":
|
| 384 |
"step": 49
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 0.06,
|
| 388 |
-
"grad_norm": 0.
|
| 389 |
"learning_rate": 0.0001,
|
| 390 |
-
"loss":
|
| 391 |
"step": 50
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 0.06,
|
| 395 |
-
"eval_loss":
|
| 396 |
-
"eval_runtime":
|
| 397 |
-
"eval_samples_per_second":
|
| 398 |
-
"eval_steps_per_second": 1.
|
| 399 |
"step": 50
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.07,
|
| 403 |
-
"grad_norm": 0.
|
| 404 |
"learning_rate": 0.00010200000000000001,
|
| 405 |
-
"loss":
|
| 406 |
"step": 51
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"epoch": 0.07,
|
| 410 |
-
"grad_norm": 0.
|
| 411 |
"learning_rate": 0.00010400000000000001,
|
| 412 |
-
"loss":
|
| 413 |
"step": 52
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 0.07,
|
| 417 |
-
"grad_norm": 0.
|
| 418 |
"learning_rate": 0.00010600000000000002,
|
| 419 |
-
"loss":
|
| 420 |
"step": 53
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 0.07,
|
| 424 |
-
"grad_norm": 0.
|
| 425 |
"learning_rate": 0.00010800000000000001,
|
| 426 |
-
"loss":
|
| 427 |
"step": 54
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 0.07,
|
| 431 |
-
"grad_norm":
|
| 432 |
"learning_rate": 0.00011000000000000002,
|
| 433 |
-
"loss":
|
| 434 |
"step": 55
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 0.07,
|
| 438 |
-
"grad_norm": 0.
|
| 439 |
"learning_rate": 0.00011200000000000001,
|
| 440 |
-
"loss":
|
| 441 |
"step": 56
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.07,
|
| 445 |
-
"grad_norm": 0.
|
| 446 |
"learning_rate": 0.00011399999999999999,
|
| 447 |
-
"loss":
|
| 448 |
"step": 57
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 0.07,
|
| 452 |
-
"grad_norm": 0.
|
| 453 |
"learning_rate": 0.000116,
|
| 454 |
-
"loss":
|
| 455 |
"step": 58
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 0.08,
|
| 459 |
-
"grad_norm": 0.
|
| 460 |
"learning_rate": 0.000118,
|
| 461 |
-
"loss":
|
| 462 |
"step": 59
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 0.08,
|
| 466 |
-
"grad_norm": 0.
|
| 467 |
"learning_rate": 0.00012,
|
| 468 |
-
"loss":
|
| 469 |
"step": 60
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 0.08,
|
| 473 |
-
"eval_loss":
|
| 474 |
-
"eval_runtime":
|
| 475 |
-
"eval_samples_per_second":
|
| 476 |
-
"eval_steps_per_second": 1.
|
| 477 |
"step": 60
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.08,
|
| 481 |
-
"grad_norm": 0.
|
| 482 |
"learning_rate": 0.000122,
|
| 483 |
-
"loss":
|
| 484 |
"step": 61
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 0.08,
|
| 488 |
-
"grad_norm": 0.
|
| 489 |
"learning_rate": 0.000124,
|
| 490 |
-
"loss":
|
| 491 |
"step": 62
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 0.08,
|
| 495 |
-
"grad_norm": 0.
|
| 496 |
"learning_rate": 0.000126,
|
| 497 |
-
"loss":
|
| 498 |
"step": 63
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 0.08,
|
| 502 |
-
"grad_norm": 0.
|
| 503 |
"learning_rate": 0.00012800000000000002,
|
| 504 |
-
"loss":
|
| 505 |
"step": 64
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 0.08,
|
| 509 |
-
"grad_norm": 0.
|
| 510 |
"learning_rate": 0.00013000000000000002,
|
| 511 |
-
"loss":
|
| 512 |
"step": 65
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 0.08,
|
| 516 |
-
"grad_norm": 0.
|
| 517 |
"learning_rate": 0.000132,
|
| 518 |
-
"loss":
|
| 519 |
"step": 66
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.09,
|
| 523 |
-
"grad_norm": 0.
|
| 524 |
"learning_rate": 0.000134,
|
| 525 |
-
"loss":
|
| 526 |
"step": 67
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 0.09,
|
| 530 |
-
"grad_norm": 0.
|
| 531 |
"learning_rate": 0.00013600000000000003,
|
| 532 |
-
"loss":
|
| 533 |
"step": 68
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 0.09,
|
| 537 |
-
"grad_norm": 0.
|
| 538 |
"learning_rate": 0.000138,
|
| 539 |
-
"loss":
|
| 540 |
"step": 69
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 0.09,
|
| 544 |
-
"grad_norm": 0.
|
| 545 |
"learning_rate": 0.00014,
|
| 546 |
-
"loss":
|
| 547 |
"step": 70
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 0.09,
|
| 551 |
-
"eval_loss":
|
| 552 |
-
"eval_runtime":
|
| 553 |
-
"eval_samples_per_second":
|
| 554 |
-
"eval_steps_per_second": 1.
|
| 555 |
"step": 70
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.09,
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
"learning_rate": 0.000142,
|
| 561 |
-
"loss":
|
| 562 |
"step": 71
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 0.09,
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
"learning_rate": 0.000144,
|
| 568 |
-
"loss":
|
| 569 |
"step": 72
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 0.09,
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
"learning_rate": 0.000146,
|
| 575 |
-
"loss": 1.
|
| 576 |
"step": 73
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 0.09,
|
| 580 |
-
"grad_norm": 0.
|
| 581 |
"learning_rate": 0.000148,
|
| 582 |
-
"loss":
|
| 583 |
"step": 74
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 0.1,
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
"learning_rate": 0.00015000000000000001,
|
| 589 |
-
"loss":
|
| 590 |
"step": 75
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.1,
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
"learning_rate": 0.000152,
|
| 596 |
-
"loss": 1.
|
| 597 |
"step": 76
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.1,
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
"learning_rate": 0.000154,
|
| 603 |
-
"loss":
|
| 604 |
"step": 77
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 0.1,
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
"learning_rate": 0.00015600000000000002,
|
| 610 |
-
"loss": 1.
|
| 611 |
"step": 78
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.1,
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
"learning_rate": 0.00015800000000000002,
|
| 617 |
-
"loss": 1.
|
| 618 |
"step": 79
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.1,
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
"learning_rate": 0.00016,
|
| 624 |
-
"loss": 1.
|
| 625 |
"step": 80
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.1,
|
| 629 |
-
"eval_loss": 1.
|
| 630 |
-
"eval_runtime":
|
| 631 |
-
"eval_samples_per_second":
|
| 632 |
-
"eval_steps_per_second": 1.
|
| 633 |
"step": 80
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.1,
|
| 637 |
-
"grad_norm": 0.
|
| 638 |
"learning_rate": 0.000162,
|
| 639 |
-
"loss": 1.
|
| 640 |
"step": 81
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 0.1,
|
| 644 |
-
"grad_norm": 0.
|
| 645 |
"learning_rate": 0.000164,
|
| 646 |
-
"loss": 1.
|
| 647 |
"step": 82
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 0.11,
|
| 651 |
-
"grad_norm": 0.
|
| 652 |
"learning_rate": 0.000166,
|
| 653 |
-
"loss": 1.
|
| 654 |
"step": 83
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.11,
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
"learning_rate": 0.000168,
|
| 660 |
-
"loss": 1.
|
| 661 |
"step": 84
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.11,
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
"learning_rate": 0.00017,
|
| 667 |
-
"loss": 1.
|
| 668 |
"step": 85
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.11,
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
"learning_rate": 0.000172,
|
| 674 |
-
"loss": 1.
|
| 675 |
"step": 86
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.11,
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
"learning_rate": 0.000174,
|
| 681 |
-
"loss": 1.
|
| 682 |
"step": 87
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.11,
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
"learning_rate": 0.00017600000000000002,
|
| 688 |
-
"loss": 1.
|
| 689 |
"step": 88
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.11,
|
| 693 |
-
"grad_norm": 0.
|
| 694 |
"learning_rate": 0.00017800000000000002,
|
| 695 |
-
"loss": 1.
|
| 696 |
"step": 89
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 0.12,
|
| 700 |
-
"grad_norm": 0.
|
| 701 |
"learning_rate": 0.00018,
|
| 702 |
-
"loss": 1.
|
| 703 |
"step": 90
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 0.12,
|
| 707 |
-
"eval_loss": 1.
|
| 708 |
-
"eval_runtime":
|
| 709 |
-
"eval_samples_per_second":
|
| 710 |
-
"eval_steps_per_second": 1.
|
| 711 |
"step": 90
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.12,
|
| 715 |
-
"grad_norm": 0.
|
| 716 |
"learning_rate": 0.000182,
|
| 717 |
-
"loss": 1.
|
| 718 |
"step": 91
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.12,
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
"learning_rate": 0.00018400000000000003,
|
| 724 |
-
"loss": 1.
|
| 725 |
"step": 92
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.12,
|
| 729 |
-
"grad_norm": 0.
|
| 730 |
"learning_rate": 0.00018600000000000002,
|
| 731 |
-
"loss":
|
| 732 |
"step": 93
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.12,
|
| 736 |
-
"grad_norm": 0.
|
| 737 |
"learning_rate": 0.000188,
|
| 738 |
-
"loss": 1.
|
| 739 |
"step": 94
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 0.12,
|
| 743 |
-
"grad_norm": 0.
|
| 744 |
"learning_rate": 0.00019,
|
| 745 |
-
"loss": 1.
|
| 746 |
"step": 95
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 0.12,
|
| 750 |
-
"grad_norm": 0.
|
| 751 |
"learning_rate": 0.000192,
|
| 752 |
-
"loss": 1.
|
| 753 |
"step": 96
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.12,
|
| 757 |
-
"grad_norm": 0.
|
| 758 |
"learning_rate": 0.000194,
|
| 759 |
-
"loss": 1.
|
| 760 |
"step": 97
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 0.13,
|
| 764 |
-
"grad_norm": 0.
|
| 765 |
"learning_rate": 0.000196,
|
| 766 |
-
"loss": 1.
|
| 767 |
"step": 98
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 0.13,
|
| 771 |
-
"grad_norm": 0.
|
| 772 |
"learning_rate": 0.00019800000000000002,
|
| 773 |
-
"loss": 1.
|
| 774 |
"step": 99
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 0.13,
|
| 778 |
-
"grad_norm": 0.
|
| 779 |
"learning_rate": 0.0002,
|
| 780 |
-
"loss": 1.
|
| 781 |
"step": 100
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 0.13,
|
| 785 |
-
"eval_loss": 1.
|
| 786 |
-
"eval_runtime":
|
| 787 |
-
"eval_samples_per_second":
|
| 788 |
-
"eval_steps_per_second": 1.
|
| 789 |
"step": 100
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.13,
|
| 793 |
-
"grad_norm": 0.
|
| 794 |
"learning_rate": 0.00019871794871794874,
|
| 795 |
-
"loss": 1.
|
| 796 |
"step": 101
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 0.13,
|
| 800 |
-
"grad_norm": 0.
|
| 801 |
"learning_rate": 0.00019743589743589744,
|
| 802 |
-
"loss": 1.
|
| 803 |
"step": 102
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 0.13,
|
| 807 |
-
"grad_norm": 0.
|
| 808 |
"learning_rate": 0.00019615384615384615,
|
| 809 |
-
"loss": 1.
|
| 810 |
"step": 103
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.13,
|
| 814 |
-
"grad_norm": 0.
|
| 815 |
"learning_rate": 0.00019487179487179487,
|
| 816 |
-
"loss": 1.
|
| 817 |
"step": 104
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 0.13,
|
| 821 |
-
"grad_norm": 0.
|
| 822 |
"learning_rate": 0.0001935897435897436,
|
| 823 |
-
"loss": 1.
|
| 824 |
"step": 105
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.14,
|
| 828 |
-
"grad_norm": 0.
|
| 829 |
"learning_rate": 0.00019230769230769233,
|
| 830 |
-
"loss": 1.
|
| 831 |
"step": 106
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.14,
|
| 835 |
-
"grad_norm": 0.
|
| 836 |
"learning_rate": 0.00019102564102564104,
|
| 837 |
-
"loss": 1.
|
| 838 |
"step": 107
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 0.14,
|
| 842 |
-
"grad_norm": 0.
|
| 843 |
"learning_rate": 0.00018974358974358974,
|
| 844 |
-
"loss": 1.
|
| 845 |
"step": 108
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 0.14,
|
| 849 |
-
"grad_norm": 0.
|
| 850 |
"learning_rate": 0.00018846153846153847,
|
| 851 |
-
"loss": 1.
|
| 852 |
"step": 109
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 0.14,
|
| 856 |
-
"grad_norm": 0.
|
| 857 |
"learning_rate": 0.0001871794871794872,
|
| 858 |
-
"loss": 1.
|
| 859 |
"step": 110
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 0.14,
|
| 863 |
-
"eval_loss": 1.
|
| 864 |
-
"eval_runtime":
|
| 865 |
-
"eval_samples_per_second":
|
| 866 |
-
"eval_steps_per_second": 1.
|
| 867 |
"step": 110
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.14,
|
| 871 |
-
"grad_norm": 0.
|
| 872 |
"learning_rate": 0.0001858974358974359,
|
| 873 |
-
"loss": 1.
|
| 874 |
"step": 111
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 0.14,
|
| 878 |
-
"grad_norm": 0.
|
| 879 |
"learning_rate": 0.00018461538461538463,
|
| 880 |
-
"loss": 1.
|
| 881 |
"step": 112
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 0.14,
|
| 885 |
-
"grad_norm": 0.
|
| 886 |
"learning_rate": 0.00018333333333333334,
|
| 887 |
-
"loss": 1.
|
| 888 |
"step": 113
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 0.15,
|
| 892 |
-
"grad_norm": 0.
|
| 893 |
"learning_rate": 0.00018205128205128207,
|
| 894 |
-
"loss": 1.
|
| 895 |
"step": 114
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 0.15,
|
| 899 |
-
"grad_norm": 0.
|
| 900 |
"learning_rate": 0.00018076923076923077,
|
| 901 |
-
"loss": 1.
|
| 902 |
"step": 115
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 0.15,
|
| 906 |
-
"grad_norm": 0.
|
| 907 |
"learning_rate": 0.0001794871794871795,
|
| 908 |
-
"loss": 1.
|
| 909 |
"step": 116
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.15,
|
| 913 |
-
"grad_norm": 0.
|
| 914 |
"learning_rate": 0.00017820512820512823,
|
| 915 |
-
"loss": 1.
|
| 916 |
"step": 117
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 0.15,
|
| 920 |
-
"grad_norm": 0.
|
| 921 |
"learning_rate": 0.00017692307692307693,
|
| 922 |
-
"loss": 1.
|
| 923 |
"step": 118
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 0.15,
|
| 927 |
-
"grad_norm": 0.
|
| 928 |
"learning_rate": 0.00017564102564102566,
|
| 929 |
-
"loss": 1.
|
| 930 |
"step": 119
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 0.15,
|
| 934 |
-
"grad_norm": 0.
|
| 935 |
"learning_rate": 0.00017435897435897436,
|
| 936 |
-
"loss": 1.
|
| 937 |
"step": 120
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 0.15,
|
| 941 |
-
"eval_loss": 1.
|
| 942 |
-
"eval_runtime":
|
| 943 |
-
"eval_samples_per_second":
|
| 944 |
-
"eval_steps_per_second": 1.
|
| 945 |
"step": 120
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.15,
|
| 949 |
-
"grad_norm": 0.
|
| 950 |
"learning_rate": 0.0001730769230769231,
|
| 951 |
-
"loss": 1.
|
| 952 |
"step": 121
|
| 953 |
},
|
| 954 |
{
|
| 955 |
"epoch": 0.16,
|
| 956 |
-
"grad_norm": 0.
|
| 957 |
"learning_rate": 0.0001717948717948718,
|
| 958 |
-
"loss": 1.
|
| 959 |
"step": 122
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 0.16,
|
| 963 |
-
"grad_norm": 0.
|
| 964 |
"learning_rate": 0.00017051282051282053,
|
| 965 |
-
"loss": 1.
|
| 966 |
"step": 123
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 0.16,
|
| 970 |
-
"grad_norm": 0.
|
| 971 |
"learning_rate": 0.00016923076923076923,
|
| 972 |
-
"loss": 1.
|
| 973 |
"step": 124
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 0.16,
|
| 977 |
-
"grad_norm": 0.
|
| 978 |
"learning_rate": 0.00016794871794871796,
|
| 979 |
-
"loss": 1.
|
| 980 |
"step": 125
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 0.16,
|
| 984 |
-
"grad_norm": 0.
|
| 985 |
"learning_rate": 0.0001666666666666667,
|
| 986 |
-
"loss": 1.
|
| 987 |
"step": 126
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.16,
|
| 991 |
-
"grad_norm": 0.
|
| 992 |
"learning_rate": 0.0001653846153846154,
|
| 993 |
-
"loss": 1.
|
| 994 |
"step": 127
|
| 995 |
},
|
| 996 |
{
|
| 997 |
"epoch": 0.16,
|
| 998 |
-
"grad_norm": 0.
|
| 999 |
"learning_rate": 0.0001641025641025641,
|
| 1000 |
-
"loss": 1.
|
| 1001 |
"step": 128
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 0.17,
|
| 1005 |
-
"grad_norm": 0.
|
| 1006 |
"learning_rate": 0.00016282051282051282,
|
| 1007 |
-
"loss": 1.
|
| 1008 |
"step": 129
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
"epoch": 0.17,
|
| 1012 |
-
"grad_norm": 0.
|
| 1013 |
"learning_rate": 0.00016153846153846155,
|
| 1014 |
-
"loss": 1.
|
| 1015 |
"step": 130
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 0.17,
|
| 1019 |
-
"eval_loss": 1.
|
| 1020 |
-
"eval_runtime":
|
| 1021 |
-
"eval_samples_per_second":
|
| 1022 |
-
"eval_steps_per_second": 1.
|
| 1023 |
"step": 130
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.17,
|
| 1027 |
-
"grad_norm": 0.
|
| 1028 |
"learning_rate": 0.00016025641025641028,
|
| 1029 |
-
"loss": 1.
|
| 1030 |
"step": 131
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
"epoch": 0.17,
|
| 1034 |
-
"grad_norm": 0.
|
| 1035 |
"learning_rate": 0.00015897435897435896,
|
| 1036 |
-
"loss": 1.
|
| 1037 |
"step": 132
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
"epoch": 0.17,
|
| 1041 |
-
"grad_norm": 0.
|
| 1042 |
"learning_rate": 0.0001576923076923077,
|
| 1043 |
-
"loss": 1.
|
| 1044 |
"step": 133
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 0.17,
|
| 1048 |
-
"grad_norm": 0.
|
| 1049 |
"learning_rate": 0.00015641025641025642,
|
| 1050 |
-
"loss": 1.
|
| 1051 |
"step": 134
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 0.17,
|
| 1055 |
-
"grad_norm": 0.
|
| 1056 |
"learning_rate": 0.00015512820512820515,
|
| 1057 |
-
"loss": 1.
|
| 1058 |
"step": 135
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 0.17,
|
| 1062 |
-
"grad_norm": 0.
|
| 1063 |
"learning_rate": 0.00015384615384615385,
|
| 1064 |
-
"loss": 1.
|
| 1065 |
"step": 136
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.18,
|
| 1069 |
-
"grad_norm": 0.
|
| 1070 |
"learning_rate": 0.00015256410256410255,
|
| 1071 |
-
"loss": 1.
|
| 1072 |
"step": 137
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 0.18,
|
| 1076 |
-
"grad_norm": 0.
|
| 1077 |
"learning_rate": 0.00015128205128205128,
|
| 1078 |
-
"loss": 1.
|
| 1079 |
"step": 138
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 0.18,
|
| 1083 |
-
"grad_norm": 0.
|
| 1084 |
"learning_rate": 0.00015000000000000001,
|
| 1085 |
-
"loss": 1.
|
| 1086 |
"step": 139
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 0.18,
|
| 1090 |
-
"grad_norm": 0.
|
| 1091 |
"learning_rate": 0.00014871794871794872,
|
| 1092 |
-
"loss": 1.
|
| 1093 |
"step": 140
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 0.18,
|
| 1097 |
-
"eval_loss": 1.
|
| 1098 |
-
"eval_runtime":
|
| 1099 |
-
"eval_samples_per_second":
|
| 1100 |
-
"eval_steps_per_second": 1.
|
| 1101 |
"step": 140
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 0.18,
|
| 1105 |
-
"grad_norm": 0.
|
| 1106 |
"learning_rate": 0.00014743589743589745,
|
| 1107 |
-
"loss": 1.
|
| 1108 |
"step": 141
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 0.18,
|
| 1112 |
-
"grad_norm": 0.
|
| 1113 |
"learning_rate": 0.00014615384615384615,
|
| 1114 |
-
"loss": 1.
|
| 1115 |
"step": 142
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 0.18,
|
| 1119 |
-
"grad_norm": 0.
|
| 1120 |
"learning_rate": 0.00014487179487179488,
|
| 1121 |
-
"loss": 1.
|
| 1122 |
"step": 143
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 0.18,
|
| 1126 |
-
"grad_norm": 0.
|
| 1127 |
"learning_rate": 0.0001435897435897436,
|
| 1128 |
-
"loss": 1.
|
| 1129 |
"step": 144
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 0.19,
|
| 1133 |
-
"grad_norm": 0.
|
| 1134 |
"learning_rate": 0.0001423076923076923,
|
| 1135 |
-
"loss": 1.
|
| 1136 |
"step": 145
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 0.19,
|
| 1140 |
-
"grad_norm": 0.
|
| 1141 |
"learning_rate": 0.00014102564102564104,
|
| 1142 |
-
"loss": 1.
|
| 1143 |
"step": 146
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.19,
|
| 1147 |
-
"grad_norm": 0.
|
| 1148 |
"learning_rate": 0.00013974358974358974,
|
| 1149 |
-
"loss": 1.
|
| 1150 |
"step": 147
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 0.19,
|
| 1154 |
-
"grad_norm": 0.
|
| 1155 |
"learning_rate": 0.00013846153846153847,
|
| 1156 |
-
"loss": 1.
|
| 1157 |
"step": 148
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 0.19,
|
| 1161 |
-
"grad_norm": 0.
|
| 1162 |
"learning_rate": 0.00013717948717948718,
|
| 1163 |
-
"loss": 1.
|
| 1164 |
"step": 149
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 0.19,
|
| 1168 |
-
"grad_norm": 0.
|
| 1169 |
"learning_rate": 0.0001358974358974359,
|
| 1170 |
-
"loss": 1.
|
| 1171 |
"step": 150
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 0.19,
|
| 1175 |
-
"eval_loss": 1.
|
| 1176 |
-
"eval_runtime":
|
| 1177 |
-
"eval_samples_per_second":
|
| 1178 |
-
"eval_steps_per_second": 1.
|
| 1179 |
"step": 150
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.19,
|
| 1183 |
-
"grad_norm": 0.
|
| 1184 |
"learning_rate": 0.00013461538461538464,
|
| 1185 |
-
"loss": 1.
|
| 1186 |
"step": 151
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 0.19,
|
| 1190 |
-
"grad_norm": 0.
|
| 1191 |
"learning_rate": 0.00013333333333333334,
|
| 1192 |
-
"loss": 1.
|
| 1193 |
"step": 152
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 0.2,
|
| 1197 |
-
"grad_norm": 0.
|
| 1198 |
"learning_rate": 0.00013205128205128204,
|
| 1199 |
-
"loss": 1.
|
| 1200 |
"step": 153
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 0.2,
|
| 1204 |
-
"grad_norm": 0.
|
| 1205 |
"learning_rate": 0.00013076923076923077,
|
| 1206 |
-
"loss": 1.
|
| 1207 |
"step": 154
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
"epoch": 0.2,
|
| 1211 |
-
"grad_norm": 0.
|
| 1212 |
"learning_rate": 0.0001294871794871795,
|
| 1213 |
-
"loss": 1.
|
| 1214 |
"step": 155
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 0.2,
|
| 1218 |
-
"grad_norm": 0.
|
| 1219 |
"learning_rate": 0.00012820512820512823,
|
| 1220 |
-
"loss": 1.
|
| 1221 |
"step": 156
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 0.2,
|
| 1225 |
-
"grad_norm": 0.
|
| 1226 |
"learning_rate": 0.00012692307692307693,
|
| 1227 |
-
"loss": 1.
|
| 1228 |
"step": 157
|
| 1229 |
},
|
| 1230 |
{
|
| 1231 |
"epoch": 0.2,
|
| 1232 |
"grad_norm": 0.251953125,
|
| 1233 |
"learning_rate": 0.00012564102564102564,
|
| 1234 |
-
"loss": 1.
|
| 1235 |
"step": 158
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 0.2,
|
| 1239 |
-
"grad_norm": 0.
|
| 1240 |
"learning_rate": 0.00012435897435897437,
|
| 1241 |
-
"loss": 1.
|
| 1242 |
"step": 159
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 0.2,
|
| 1246 |
-
"grad_norm": 0.
|
| 1247 |
"learning_rate": 0.0001230769230769231,
|
| 1248 |
-
"loss": 1.
|
| 1249 |
"step": 160
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
"epoch": 0.2,
|
| 1253 |
-
"eval_loss": 1.
|
| 1254 |
-
"eval_runtime":
|
| 1255 |
-
"eval_samples_per_second":
|
| 1256 |
-
"eval_steps_per_second": 1.
|
| 1257 |
"step": 160
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.21,
|
| 1261 |
-
"grad_norm": 0.
|
| 1262 |
"learning_rate": 0.00012179487179487179,
|
| 1263 |
-
"loss": 1.
|
| 1264 |
"step": 161
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 0.21,
|
| 1268 |
-
"grad_norm": 0.
|
| 1269 |
"learning_rate": 0.00012051282051282052,
|
| 1270 |
-
"loss": 1.
|
| 1271 |
"step": 162
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 0.21,
|
| 1275 |
-
"grad_norm": 0.
|
| 1276 |
"learning_rate": 0.00011923076923076923,
|
| 1277 |
-
"loss": 1.
|
| 1278 |
"step": 163
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
"epoch": 0.21,
|
| 1282 |
-
"grad_norm": 0.
|
| 1283 |
"learning_rate": 0.00011794871794871796,
|
| 1284 |
-
"loss": 1.
|
| 1285 |
"step": 164
|
| 1286 |
},
|
| 1287 |
{
|
| 1288 |
"epoch": 0.21,
|
| 1289 |
-
"grad_norm": 0.
|
| 1290 |
"learning_rate": 0.00011666666666666668,
|
| 1291 |
-
"loss": 1.
|
| 1292 |
"step": 165
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 0.21,
|
| 1296 |
-
"grad_norm": 0.
|
| 1297 |
"learning_rate": 0.00011538461538461538,
|
| 1298 |
-
"loss": 1.
|
| 1299 |
"step": 166
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.21,
|
| 1303 |
-
"grad_norm": 0.
|
| 1304 |
"learning_rate": 0.0001141025641025641,
|
| 1305 |
-
"loss": 1.
|
| 1306 |
"step": 167
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 0.21,
|
| 1310 |
-
"grad_norm": 0.
|
| 1311 |
"learning_rate": 0.00011282051282051283,
|
| 1312 |
-
"loss": 1.
|
| 1313 |
"step": 168
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 0.22,
|
| 1317 |
-
"grad_norm": 0.
|
| 1318 |
"learning_rate": 0.00011153846153846154,
|
| 1319 |
-
"loss": 1.
|
| 1320 |
"step": 169
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 0.22,
|
| 1324 |
-
"grad_norm": 0.
|
| 1325 |
"learning_rate": 0.00011025641025641027,
|
| 1326 |
-
"loss": 1.
|
| 1327 |
"step": 170
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 0.22,
|
| 1331 |
-
"eval_loss": 1.
|
| 1332 |
-
"eval_runtime":
|
| 1333 |
-
"eval_samples_per_second":
|
| 1334 |
-
"eval_steps_per_second": 1.
|
| 1335 |
"step": 170
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 0.22,
|
| 1339 |
-
"grad_norm": 0.
|
| 1340 |
"learning_rate": 0.00010897435897435896,
|
| 1341 |
-
"loss": 1.
|
| 1342 |
"step": 171
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 0.22,
|
| 1346 |
-
"grad_norm": 0.
|
| 1347 |
"learning_rate": 0.0001076923076923077,
|
| 1348 |
-
"loss": 1.
|
| 1349 |
"step": 172
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 0.22,
|
| 1353 |
-
"grad_norm": 0.
|
| 1354 |
"learning_rate": 0.00010641025641025641,
|
| 1355 |
-
"loss": 1.
|
| 1356 |
"step": 173
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 0.22,
|
| 1360 |
-
"grad_norm": 0.
|
| 1361 |
"learning_rate": 0.00010512820512820514,
|
| 1362 |
-
"loss": 1.
|
| 1363 |
"step": 174
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 0.22,
|
| 1367 |
-
"grad_norm": 0.
|
| 1368 |
"learning_rate": 0.00010384615384615386,
|
| 1369 |
-
"loss": 1.
|
| 1370 |
"step": 175
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 0.23,
|
| 1374 |
-
"grad_norm": 0.
|
| 1375 |
"learning_rate": 0.00010256410256410256,
|
| 1376 |
-
"loss": 1.
|
| 1377 |
"step": 176
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 0.23,
|
| 1381 |
-
"grad_norm": 0.
|
| 1382 |
"learning_rate": 0.00010128205128205129,
|
| 1383 |
-
"loss": 1.
|
| 1384 |
"step": 177
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 0.23,
|
| 1388 |
-
"grad_norm": 0.
|
| 1389 |
"learning_rate": 0.0001,
|
| 1390 |
-
"loss": 1.
|
| 1391 |
"step": 178
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 0.23,
|
| 1395 |
-
"grad_norm": 0.
|
| 1396 |
"learning_rate": 9.871794871794872e-05,
|
| 1397 |
-
"loss": 1.
|
| 1398 |
"step": 179
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 0.23,
|
| 1402 |
-
"grad_norm": 0.
|
| 1403 |
"learning_rate": 9.743589743589744e-05,
|
| 1404 |
-
"loss": 1.
|
| 1405 |
"step": 180
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 0.23,
|
| 1409 |
-
"eval_loss": 1.
|
| 1410 |
-
"eval_runtime":
|
| 1411 |
-
"eval_samples_per_second":
|
| 1412 |
-
"eval_steps_per_second": 1.
|
| 1413 |
"step": 180
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 0.23,
|
| 1417 |
-
"grad_norm": 0.
|
| 1418 |
"learning_rate": 9.615384615384617e-05,
|
| 1419 |
-
"loss": 1.
|
| 1420 |
"step": 181
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 0.23,
|
| 1424 |
-
"grad_norm": 0.
|
| 1425 |
"learning_rate": 9.487179487179487e-05,
|
| 1426 |
-
"loss": 1.
|
| 1427 |
"step": 182
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
"epoch": 0.23,
|
| 1431 |
-
"grad_norm": 0.
|
| 1432 |
"learning_rate": 9.35897435897436e-05,
|
| 1433 |
-
"loss": 1.
|
| 1434 |
"step": 183
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 0.24,
|
| 1438 |
-
"grad_norm": 0.
|
| 1439 |
"learning_rate": 9.230769230769232e-05,
|
| 1440 |
-
"loss": 1.
|
| 1441 |
"step": 184
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 0.24,
|
| 1445 |
-
"grad_norm": 0.
|
| 1446 |
"learning_rate": 9.102564102564103e-05,
|
| 1447 |
-
"loss": 1.
|
| 1448 |
"step": 185
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 0.24,
|
| 1452 |
-
"grad_norm": 0.
|
| 1453 |
"learning_rate": 8.974358974358975e-05,
|
| 1454 |
-
"loss": 1.
|
| 1455 |
"step": 186
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 0.24,
|
| 1459 |
-
"grad_norm": 0.
|
| 1460 |
"learning_rate": 8.846153846153847e-05,
|
| 1461 |
-
"loss": 1.
|
| 1462 |
"step": 187
|
| 1463 |
},
|
| 1464 |
{
|
| 1465 |
"epoch": 0.24,
|
| 1466 |
-
"grad_norm": 0.
|
| 1467 |
"learning_rate": 8.717948717948718e-05,
|
| 1468 |
-
"loss": 1.
|
| 1469 |
"step": 188
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 0.24,
|
| 1473 |
-
"grad_norm": 0.
|
| 1474 |
"learning_rate": 8.58974358974359e-05,
|
| 1475 |
-
"loss": 1.
|
| 1476 |
"step": 189
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 0.24,
|
| 1480 |
-
"grad_norm": 0.
|
| 1481 |
"learning_rate": 8.461538461538461e-05,
|
| 1482 |
-
"loss": 1.
|
| 1483 |
"step": 190
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 0.24,
|
| 1487 |
-
"eval_loss": 1.
|
| 1488 |
-
"eval_runtime":
|
| 1489 |
-
"eval_samples_per_second":
|
| 1490 |
-
"eval_steps_per_second": 1.
|
| 1491 |
"step": 190
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
"epoch": 0.24,
|
| 1495 |
-
"grad_norm": 0.
|
| 1496 |
"learning_rate": 8.333333333333334e-05,
|
| 1497 |
-
"loss": 1.
|
| 1498 |
"step": 191
|
| 1499 |
},
|
| 1500 |
{
|
| 1501 |
"epoch": 0.25,
|
| 1502 |
-
"grad_norm": 0.
|
| 1503 |
"learning_rate": 8.205128205128205e-05,
|
| 1504 |
-
"loss": 1.
|
| 1505 |
"step": 192
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
"epoch": 0.25,
|
| 1509 |
-
"grad_norm": 0.
|
| 1510 |
"learning_rate": 8.076923076923078e-05,
|
| 1511 |
-
"loss": 1.
|
| 1512 |
"step": 193
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
"epoch": 0.25,
|
| 1516 |
-
"grad_norm": 0.
|
| 1517 |
"learning_rate": 7.948717948717948e-05,
|
| 1518 |
-
"loss": 1.
|
| 1519 |
"step": 194
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 0.25,
|
| 1523 |
-
"grad_norm": 0.
|
| 1524 |
"learning_rate": 7.820512820512821e-05,
|
| 1525 |
-
"loss": 1.
|
| 1526 |
"step": 195
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 0.25,
|
| 1530 |
-
"grad_norm": 0.
|
| 1531 |
"learning_rate": 7.692307692307693e-05,
|
| 1532 |
-
"loss": 1.
|
| 1533 |
"step": 196
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 0.25,
|
| 1537 |
-
"grad_norm": 0.
|
| 1538 |
"learning_rate": 7.564102564102564e-05,
|
| 1539 |
-
"loss": 1.
|
| 1540 |
"step": 197
|
| 1541 |
},
|
| 1542 |
{
|
| 1543 |
"epoch": 0.25,
|
| 1544 |
-
"grad_norm": 0.
|
| 1545 |
"learning_rate": 7.435897435897436e-05,
|
| 1546 |
-
"loss": 1.
|
| 1547 |
"step": 198
|
| 1548 |
},
|
| 1549 |
{
|
| 1550 |
"epoch": 0.25,
|
| 1551 |
-
"grad_norm": 0.
|
| 1552 |
"learning_rate": 7.307692307692307e-05,
|
| 1553 |
-
"loss": 1.
|
| 1554 |
"step": 199
|
| 1555 |
},
|
| 1556 |
{
|
| 1557 |
"epoch": 0.26,
|
| 1558 |
-
"grad_norm": 0.
|
| 1559 |
"learning_rate": 7.17948717948718e-05,
|
| 1560 |
-
"loss": 1.
|
| 1561 |
"step": 200
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
"epoch": 0.26,
|
| 1565 |
-
"eval_loss": 1.
|
| 1566 |
-
"eval_runtime":
|
| 1567 |
-
"eval_samples_per_second":
|
| 1568 |
-
"eval_steps_per_second": 1.
|
| 1569 |
"step": 200
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 0.26,
|
| 1573 |
-
"grad_norm": 0.
|
| 1574 |
"learning_rate": 7.051282051282052e-05,
|
| 1575 |
-
"loss": 1.
|
| 1576 |
"step": 201
|
| 1577 |
},
|
| 1578 |
{
|
| 1579 |
"epoch": 0.26,
|
| 1580 |
-
"grad_norm": 0.
|
| 1581 |
"learning_rate": 6.923076923076924e-05,
|
| 1582 |
-
"loss": 1.
|
| 1583 |
"step": 202
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
"epoch": 0.26,
|
| 1587 |
-
"grad_norm": 0.
|
| 1588 |
"learning_rate": 6.794871794871795e-05,
|
| 1589 |
-
"loss": 1.
|
| 1590 |
"step": 203
|
| 1591 |
},
|
| 1592 |
{
|
| 1593 |
"epoch": 0.26,
|
| 1594 |
-
"grad_norm": 0.
|
| 1595 |
"learning_rate": 6.666666666666667e-05,
|
| 1596 |
-
"loss": 1.
|
| 1597 |
"step": 204
|
| 1598 |
},
|
| 1599 |
{
|
| 1600 |
"epoch": 0.26,
|
| 1601 |
-
"grad_norm": 0.
|
| 1602 |
"learning_rate": 6.538461538461539e-05,
|
| 1603 |
-
"loss": 1.
|
| 1604 |
"step": 205
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 0.26,
|
| 1608 |
-
"grad_norm": 0.
|
| 1609 |
"learning_rate": 6.410256410256412e-05,
|
| 1610 |
-
"loss": 1.
|
| 1611 |
"step": 206
|
| 1612 |
},
|
| 1613 |
{
|
| 1614 |
"epoch": 0.26,
|
| 1615 |
-
"grad_norm": 0.
|
| 1616 |
"learning_rate": 6.282051282051282e-05,
|
| 1617 |
-
"loss": 1.
|
| 1618 |
"step": 207
|
| 1619 |
},
|
| 1620 |
{
|
| 1621 |
"epoch": 0.27,
|
| 1622 |
-
"grad_norm": 0.
|
| 1623 |
"learning_rate": 6.153846153846155e-05,
|
| 1624 |
-
"loss": 1.
|
| 1625 |
"step": 208
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
"epoch": 0.27,
|
| 1629 |
-
"grad_norm": 0.
|
| 1630 |
"learning_rate": 6.025641025641026e-05,
|
| 1631 |
-
"loss": 1.
|
| 1632 |
"step": 209
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 0.27,
|
| 1636 |
-
"grad_norm": 0.
|
| 1637 |
"learning_rate": 5.897435897435898e-05,
|
| 1638 |
-
"loss": 1.
|
| 1639 |
"step": 210
|
| 1640 |
},
|
| 1641 |
{
|
| 1642 |
"epoch": 0.27,
|
| 1643 |
-
"eval_loss": 1.
|
| 1644 |
-
"eval_runtime":
|
| 1645 |
-
"eval_samples_per_second":
|
| 1646 |
-
"eval_steps_per_second": 1.
|
| 1647 |
"step": 210
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 0.27,
|
| 1651 |
-
"grad_norm": 0.
|
| 1652 |
"learning_rate": 5.769230769230769e-05,
|
| 1653 |
-
"loss": 1.
|
| 1654 |
"step": 211
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 0.27,
|
| 1658 |
-
"grad_norm": 0.
|
| 1659 |
"learning_rate": 5.6410256410256414e-05,
|
| 1660 |
-
"loss": 1.
|
| 1661 |
"step": 212
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 0.27,
|
| 1665 |
-
"grad_norm": 0.
|
| 1666 |
"learning_rate": 5.512820512820514e-05,
|
| 1667 |
-
"loss": 1.
|
| 1668 |
"step": 213
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 0.27,
|
| 1672 |
-
"grad_norm": 0.
|
| 1673 |
"learning_rate": 5.384615384615385e-05,
|
| 1674 |
-
"loss": 1.
|
| 1675 |
"step": 214
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 0.28,
|
| 1679 |
-
"grad_norm": 0.
|
| 1680 |
"learning_rate": 5.256410256410257e-05,
|
| 1681 |
-
"loss": 1.
|
| 1682 |
"step": 215
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 0.28,
|
| 1686 |
-
"grad_norm": 0.
|
| 1687 |
"learning_rate": 5.128205128205128e-05,
|
| 1688 |
-
"loss": 1.
|
| 1689 |
"step": 216
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 0.28,
|
| 1693 |
-
"grad_norm": 0.
|
| 1694 |
"learning_rate": 5e-05,
|
| 1695 |
-
"loss": 1.
|
| 1696 |
"step": 217
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 0.28,
|
| 1700 |
-
"grad_norm": 0.
|
| 1701 |
"learning_rate": 4.871794871794872e-05,
|
| 1702 |
-
"loss": 1.
|
| 1703 |
"step": 218
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 0.28,
|
| 1707 |
-
"grad_norm": 0.
|
| 1708 |
"learning_rate": 4.7435897435897435e-05,
|
| 1709 |
-
"loss": 1.
|
| 1710 |
"step": 219
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
"epoch": 0.28,
|
| 1714 |
-
"grad_norm": 0.
|
| 1715 |
"learning_rate": 4.615384615384616e-05,
|
| 1716 |
-
"loss": 1.
|
| 1717 |
"step": 220
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
"epoch": 0.28,
|
| 1721 |
-
"eval_loss": 1.
|
| 1722 |
-
"eval_runtime":
|
| 1723 |
-
"eval_samples_per_second":
|
| 1724 |
-
"eval_steps_per_second": 1.
|
| 1725 |
"step": 220
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 0.28,
|
| 1729 |
-
"grad_norm": 0.
|
| 1730 |
"learning_rate": 4.4871794871794874e-05,
|
| 1731 |
-
"loss": 1.
|
| 1732 |
"step": 221
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 0.28,
|
| 1736 |
-
"grad_norm": 0.
|
| 1737 |
"learning_rate": 4.358974358974359e-05,
|
| 1738 |
-
"loss": 1.
|
| 1739 |
"step": 222
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 0.29,
|
| 1743 |
-
"grad_norm": 0.
|
| 1744 |
"learning_rate": 4.230769230769231e-05,
|
| 1745 |
-
"loss": 1.
|
| 1746 |
"step": 223
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 0.29,
|
| 1750 |
-
"grad_norm": 0.
|
| 1751 |
"learning_rate": 4.1025641025641023e-05,
|
| 1752 |
-
"loss": 1.
|
| 1753 |
"step": 224
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 0.29,
|
| 1757 |
-
"grad_norm": 0.
|
| 1758 |
"learning_rate": 3.974358974358974e-05,
|
| 1759 |
-
"loss": 1.
|
| 1760 |
"step": 225
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 0.29,
|
| 1764 |
-
"grad_norm": 0.
|
| 1765 |
"learning_rate": 3.846153846153846e-05,
|
| 1766 |
-
"loss": 1.
|
| 1767 |
"step": 226
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 0.29,
|
| 1771 |
-
"grad_norm": 0.
|
| 1772 |
"learning_rate": 3.717948717948718e-05,
|
| 1773 |
-
"loss": 1.
|
| 1774 |
"step": 227
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 0.29,
|
| 1778 |
-
"grad_norm": 0.
|
| 1779 |
"learning_rate": 3.58974358974359e-05,
|
| 1780 |
-
"loss": 1.
|
| 1781 |
"step": 228
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 0.29,
|
| 1785 |
-
"grad_norm": 0.
|
| 1786 |
"learning_rate": 3.461538461538462e-05,
|
| 1787 |
-
"loss": 1.
|
| 1788 |
"step": 229
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 0.29,
|
| 1792 |
-
"grad_norm": 0.
|
| 1793 |
"learning_rate": 3.3333333333333335e-05,
|
| 1794 |
-
"loss": 1.
|
| 1795 |
"step": 230
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 0.29,
|
| 1799 |
-
"eval_loss": 1.
|
| 1800 |
-
"eval_runtime":
|
| 1801 |
-
"eval_samples_per_second":
|
| 1802 |
-
"eval_steps_per_second": 1.
|
| 1803 |
"step": 230
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 0.3,
|
| 1807 |
-
"grad_norm": 0.
|
| 1808 |
"learning_rate": 3.205128205128206e-05,
|
| 1809 |
-
"loss": 1.
|
| 1810 |
"step": 231
|
| 1811 |
},
|
| 1812 |
{
|
| 1813 |
"epoch": 0.3,
|
| 1814 |
-
"grad_norm": 0.
|
| 1815 |
"learning_rate": 3.0769230769230774e-05,
|
| 1816 |
-
"loss": 1.
|
| 1817 |
"step": 232
|
| 1818 |
},
|
| 1819 |
{
|
| 1820 |
"epoch": 0.3,
|
| 1821 |
-
"grad_norm": 0.
|
| 1822 |
"learning_rate": 2.948717948717949e-05,
|
| 1823 |
-
"loss": 1.
|
| 1824 |
"step": 233
|
| 1825 |
},
|
| 1826 |
{
|
| 1827 |
"epoch": 0.3,
|
| 1828 |
-
"grad_norm": 0.
|
| 1829 |
"learning_rate": 2.8205128205128207e-05,
|
| 1830 |
-
"loss": 1.
|
| 1831 |
"step": 234
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
"epoch": 0.3,
|
| 1835 |
-
"grad_norm": 0.
|
| 1836 |
"learning_rate": 2.6923076923076923e-05,
|
| 1837 |
-
"loss": 1.
|
| 1838 |
"step": 235
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
"epoch": 0.3,
|
| 1842 |
-
"grad_norm": 0.
|
| 1843 |
"learning_rate": 2.564102564102564e-05,
|
| 1844 |
-
"loss": 1.
|
| 1845 |
"step": 236
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 0.3,
|
| 1849 |
-
"grad_norm": 0.
|
| 1850 |
"learning_rate": 2.435897435897436e-05,
|
| 1851 |
-
"loss": 1.
|
| 1852 |
"step": 237
|
| 1853 |
},
|
| 1854 |
{
|
| 1855 |
"epoch": 0.3,
|
| 1856 |
-
"grad_norm": 0.
|
| 1857 |
"learning_rate": 2.307692307692308e-05,
|
| 1858 |
-
"loss": 1.
|
| 1859 |
"step": 238
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
"epoch": 0.31,
|
| 1863 |
-
"grad_norm": 0.
|
| 1864 |
"learning_rate": 2.1794871794871795e-05,
|
| 1865 |
-
"loss": 1.
|
| 1866 |
"step": 239
|
| 1867 |
},
|
| 1868 |
{
|
| 1869 |
"epoch": 0.31,
|
| 1870 |
-
"grad_norm": 0.
|
| 1871 |
"learning_rate": 2.0512820512820512e-05,
|
| 1872 |
-
"loss": 1.
|
| 1873 |
"step": 240
|
| 1874 |
},
|
| 1875 |
{
|
| 1876 |
"epoch": 0.31,
|
| 1877 |
-
"eval_loss": 1.
|
| 1878 |
-
"eval_runtime":
|
| 1879 |
-
"eval_samples_per_second":
|
| 1880 |
-
"eval_steps_per_second": 1.
|
| 1881 |
"step": 240
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 0.31,
|
| 1885 |
-
"grad_norm": 0.
|
| 1886 |
"learning_rate": 1.923076923076923e-05,
|
| 1887 |
-
"loss": 1.
|
| 1888 |
"step": 241
|
| 1889 |
},
|
| 1890 |
{
|
| 1891 |
"epoch": 0.31,
|
| 1892 |
-
"grad_norm": 0.
|
| 1893 |
"learning_rate": 1.794871794871795e-05,
|
| 1894 |
-
"loss": 1.
|
| 1895 |
"step": 242
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
"epoch": 0.31,
|
| 1899 |
-
"grad_norm": 0.
|
| 1900 |
"learning_rate": 1.6666666666666667e-05,
|
| 1901 |
-
"loss": 1.
|
| 1902 |
"step": 243
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 0.31,
|
| 1906 |
-
"grad_norm": 0.
|
| 1907 |
"learning_rate": 1.5384615384615387e-05,
|
| 1908 |
-
"loss": 1.
|
| 1909 |
"step": 244
|
| 1910 |
},
|
| 1911 |
{
|
| 1912 |
"epoch": 0.31,
|
| 1913 |
-
"grad_norm": 0.
|
| 1914 |
"learning_rate": 1.4102564102564104e-05,
|
| 1915 |
-
"loss": 1.
|
| 1916 |
"step": 245
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 0.31,
|
| 1920 |
-
"grad_norm": 0.
|
| 1921 |
"learning_rate": 1.282051282051282e-05,
|
| 1922 |
-
"loss": 1.
|
| 1923 |
"step": 246
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 0.32,
|
| 1927 |
-
"grad_norm": 0.
|
| 1928 |
"learning_rate": 1.153846153846154e-05,
|
| 1929 |
-
"loss": 1.
|
| 1930 |
"step": 247
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 0.32,
|
| 1934 |
-
"grad_norm": 0.
|
| 1935 |
"learning_rate": 1.0256410256410256e-05,
|
| 1936 |
-
"loss": 1.
|
| 1937 |
"step": 248
|
| 1938 |
},
|
| 1939 |
{
|
| 1940 |
"epoch": 0.32,
|
| 1941 |
-
"grad_norm": 0.
|
| 1942 |
"learning_rate": 8.974358974358976e-06,
|
| 1943 |
-
"loss": 1.
|
| 1944 |
"step": 249
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 0.32,
|
| 1948 |
-
"grad_norm": 0.
|
| 1949 |
"learning_rate": 7.692307692307694e-06,
|
| 1950 |
-
"loss": 1.
|
| 1951 |
"step": 250
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 0.32,
|
| 1955 |
-
"eval_loss": 1.
|
| 1956 |
-
"eval_runtime":
|
| 1957 |
-
"eval_samples_per_second":
|
| 1958 |
-
"eval_steps_per_second": 1.
|
| 1959 |
"step": 250
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 0.32,
|
| 1963 |
-
"grad_norm": 0.
|
| 1964 |
"learning_rate": 6.41025641025641e-06,
|
| 1965 |
-
"loss": 1.
|
| 1966 |
"step": 251
|
| 1967 |
},
|
| 1968 |
{
|
| 1969 |
"epoch": 0.32,
|
| 1970 |
-
"grad_norm": 0.
|
| 1971 |
"learning_rate": 5.128205128205128e-06,
|
| 1972 |
-
"loss": 1.
|
| 1973 |
"step": 252
|
| 1974 |
},
|
| 1975 |
{
|
| 1976 |
"epoch": 0.32,
|
| 1977 |
-
"grad_norm": 0.
|
| 1978 |
"learning_rate": 3.846153846153847e-06,
|
| 1979 |
-
"loss": 1.
|
| 1980 |
"step": 253
|
| 1981 |
},
|
| 1982 |
{
|
| 1983 |
"epoch": 0.33,
|
| 1984 |
-
"grad_norm": 0.
|
| 1985 |
"learning_rate": 2.564102564102564e-06,
|
| 1986 |
-
"loss": 1.
|
| 1987 |
"step": 254
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 0.33,
|
| 1991 |
-
"grad_norm": 0.
|
| 1992 |
"learning_rate": 1.282051282051282e-06,
|
| 1993 |
-
"loss": 1.
|
| 1994 |
"step": 255
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 0.33,
|
| 1998 |
-
"grad_norm": 0.
|
| 1999 |
"learning_rate": 0.0,
|
| 2000 |
-
"loss": 1.
|
| 2001 |
"step": 256
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 0.33,
|
| 2005 |
"step": 256,
|
| 2006 |
-
"total_flos": 1.
|
| 2007 |
-
"train_loss":
|
| 2008 |
-
"train_runtime":
|
| 2009 |
-
"train_samples_per_second":
|
| 2010 |
-
"train_steps_per_second": 0.
|
| 2011 |
},
|
| 2012 |
{
|
| 2013 |
"epoch": 0.33,
|
| 2014 |
-
"eval_loss": 1.
|
| 2015 |
-
"eval_runtime":
|
| 2016 |
-
"eval_samples_per_second":
|
| 2017 |
-
"eval_steps_per_second": 1.
|
| 2018 |
"step": 256
|
| 2019 |
}
|
| 2020 |
],
|
|
@@ -2023,7 +2023,7 @@
|
|
| 2023 |
"num_input_tokens_seen": 0,
|
| 2024 |
"num_train_epochs": 1,
|
| 2025 |
"save_steps": 10,
|
| 2026 |
-
"total_flos": 1.
|
| 2027 |
"train_batch_size": 32,
|
| 2028 |
"trial_name": null,
|
| 2029 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.5016273260116577,
|
| 3 |
+
"best_model_checkpoint": "lora_lr/mistralai/Mistral-7B-Instruct-v0.2/unaligned/checkpoint-240",
|
| 4 |
"epoch": 0.327575175943698,
|
| 5 |
"eval_steps": 10,
|
| 6 |
"global_step": 256,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 1.484375,
|
| 14 |
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 3.7421,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 1.4921875,
|
| 21 |
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 3.6136,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0,
|
| 27 |
+
"grad_norm": 1.4140625,
|
| 28 |
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 3.5641,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 1.59375,
|
| 35 |
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 3.8168,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.01,
|
| 41 |
+
"grad_norm": 1.5703125,
|
| 42 |
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 3.7471,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.01,
|
| 48 |
+
"grad_norm": 1.4609375,
|
| 49 |
"learning_rate": 1.2e-05,
|
| 50 |
+
"loss": 3.6939,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.01,
|
| 55 |
+
"grad_norm": 1.5546875,
|
| 56 |
"learning_rate": 1.4000000000000001e-05,
|
| 57 |
+
"loss": 3.5964,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.01,
|
| 62 |
+
"grad_norm": 1.5625,
|
| 63 |
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
+
"loss": 3.7708,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.01,
|
| 69 |
+
"grad_norm": 1.5703125,
|
| 70 |
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 3.7418,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.01,
|
| 76 |
+
"grad_norm": 1.609375,
|
| 77 |
"learning_rate": 2e-05,
|
| 78 |
+
"loss": 3.8394,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.01,
|
| 83 |
+
"eval_loss": 3.672560214996338,
|
| 84 |
+
"eval_runtime": 108.3497,
|
| 85 |
+
"eval_samples_per_second": 46.147,
|
| 86 |
+
"eval_steps_per_second": 1.449,
|
| 87 |
"step": 10
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.01,
|
| 91 |
+
"grad_norm": 1.5078125,
|
| 92 |
"learning_rate": 2.2000000000000003e-05,
|
| 93 |
+
"loss": 3.6075,
|
| 94 |
"step": 11
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.02,
|
| 98 |
+
"grad_norm": 1.4296875,
|
| 99 |
"learning_rate": 2.4e-05,
|
| 100 |
+
"loss": 3.4171,
|
| 101 |
"step": 12
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.02,
|
| 105 |
+
"grad_norm": 1.6484375,
|
| 106 |
"learning_rate": 2.6000000000000002e-05,
|
| 107 |
+
"loss": 3.7848,
|
| 108 |
"step": 13
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.02,
|
| 112 |
+
"grad_norm": 1.6328125,
|
| 113 |
"learning_rate": 2.8000000000000003e-05,
|
| 114 |
+
"loss": 3.7797,
|
| 115 |
"step": 14
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.02,
|
| 119 |
+
"grad_norm": 1.609375,
|
| 120 |
"learning_rate": 3e-05,
|
| 121 |
+
"loss": 3.7132,
|
| 122 |
"step": 15
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.02,
|
| 126 |
+
"grad_norm": 1.5390625,
|
| 127 |
"learning_rate": 3.2000000000000005e-05,
|
| 128 |
+
"loss": 3.5353,
|
| 129 |
"step": 16
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.02,
|
| 133 |
+
"grad_norm": 1.828125,
|
| 134 |
"learning_rate": 3.4000000000000007e-05,
|
| 135 |
+
"loss": 3.687,
|
| 136 |
"step": 17
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.02,
|
| 140 |
+
"grad_norm": 1.65625,
|
| 141 |
"learning_rate": 3.6e-05,
|
| 142 |
+
"loss": 3.4312,
|
| 143 |
"step": 18
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.02,
|
| 147 |
+
"grad_norm": 1.8203125,
|
| 148 |
"learning_rate": 3.8e-05,
|
| 149 |
+
"loss": 3.4971,
|
| 150 |
"step": 19
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.03,
|
| 154 |
+
"grad_norm": 1.875,
|
| 155 |
"learning_rate": 4e-05,
|
| 156 |
+
"loss": 3.3386,
|
| 157 |
"step": 20
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.03,
|
| 161 |
+
"eval_loss": 3.376652240753174,
|
| 162 |
+
"eval_runtime": 108.6461,
|
| 163 |
+
"eval_samples_per_second": 46.021,
|
| 164 |
+
"eval_steps_per_second": 1.445,
|
| 165 |
"step": 20
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.03,
|
| 169 |
+
"grad_norm": 1.9921875,
|
| 170 |
"learning_rate": 4.2e-05,
|
| 171 |
+
"loss": 3.3568,
|
| 172 |
"step": 21
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 0.03,
|
| 176 |
+
"grad_norm": 2.109375,
|
| 177 |
"learning_rate": 4.4000000000000006e-05,
|
| 178 |
+
"loss": 3.3976,
|
| 179 |
"step": 22
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.03,
|
| 183 |
+
"grad_norm": 2.125,
|
| 184 |
"learning_rate": 4.600000000000001e-05,
|
| 185 |
+
"loss": 3.3644,
|
| 186 |
"step": 23
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.03,
|
| 190 |
+
"grad_norm": 2.28125,
|
| 191 |
"learning_rate": 4.8e-05,
|
| 192 |
+
"loss": 3.1825,
|
| 193 |
"step": 24
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.03,
|
| 197 |
+
"grad_norm": 2.421875,
|
| 198 |
"learning_rate": 5e-05,
|
| 199 |
+
"loss": 3.2047,
|
| 200 |
"step": 25
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.03,
|
| 204 |
+
"grad_norm": 2.359375,
|
| 205 |
"learning_rate": 5.2000000000000004e-05,
|
| 206 |
+
"loss": 3.098,
|
| 207 |
"step": 26
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.03,
|
| 211 |
+
"grad_norm": 2.390625,
|
| 212 |
"learning_rate": 5.4000000000000005e-05,
|
| 213 |
+
"loss": 2.9831,
|
| 214 |
"step": 27
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 0.04,
|
| 218 |
+
"grad_norm": 2.359375,
|
| 219 |
"learning_rate": 5.6000000000000006e-05,
|
| 220 |
+
"loss": 2.9573,
|
| 221 |
"step": 28
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.04,
|
| 225 |
+
"grad_norm": 2.609375,
|
| 226 |
"learning_rate": 5.8e-05,
|
| 227 |
+
"loss": 2.9497,
|
| 228 |
"step": 29
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.04,
|
| 232 |
+
"grad_norm": 2.125,
|
| 233 |
"learning_rate": 6e-05,
|
| 234 |
+
"loss": 2.5156,
|
| 235 |
"step": 30
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.04,
|
| 239 |
+
"eval_loss": 2.578493356704712,
|
| 240 |
+
"eval_runtime": 109.4296,
|
| 241 |
+
"eval_samples_per_second": 45.691,
|
| 242 |
+
"eval_steps_per_second": 1.435,
|
| 243 |
"step": 30
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.04,
|
| 247 |
+
"grad_norm": 2.25,
|
| 248 |
"learning_rate": 6.2e-05,
|
| 249 |
+
"loss": 2.6802,
|
| 250 |
"step": 31
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.04,
|
| 254 |
+
"grad_norm": 1.984375,
|
| 255 |
"learning_rate": 6.400000000000001e-05,
|
| 256 |
+
"loss": 2.4563,
|
| 257 |
"step": 32
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 0.04,
|
| 261 |
+
"grad_norm": 2.046875,
|
| 262 |
"learning_rate": 6.6e-05,
|
| 263 |
+
"loss": 2.4709,
|
| 264 |
"step": 33
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.04,
|
| 268 |
+
"grad_norm": 2.046875,
|
| 269 |
"learning_rate": 6.800000000000001e-05,
|
| 270 |
+
"loss": 2.4096,
|
| 271 |
"step": 34
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.04,
|
| 275 |
+
"grad_norm": 1.75,
|
| 276 |
"learning_rate": 7e-05,
|
| 277 |
+
"loss": 2.2541,
|
| 278 |
"step": 35
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.05,
|
| 282 |
+
"grad_norm": 1.78125,
|
| 283 |
"learning_rate": 7.2e-05,
|
| 284 |
+
"loss": 2.1879,
|
| 285 |
"step": 36
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.05,
|
| 289 |
+
"grad_norm": 1.6484375,
|
| 290 |
"learning_rate": 7.4e-05,
|
| 291 |
+
"loss": 2.2291,
|
| 292 |
"step": 37
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 0.05,
|
| 296 |
+
"grad_norm": 1.4140625,
|
| 297 |
"learning_rate": 7.6e-05,
|
| 298 |
+
"loss": 2.028,
|
| 299 |
"step": 38
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.05,
|
| 303 |
+
"grad_norm": 1.1640625,
|
| 304 |
"learning_rate": 7.800000000000001e-05,
|
| 305 |
+
"loss": 1.9569,
|
| 306 |
"step": 39
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.05,
|
| 310 |
+
"grad_norm": 0.9296875,
|
| 311 |
"learning_rate": 8e-05,
|
| 312 |
+
"loss": 1.8834,
|
| 313 |
"step": 40
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 0.05,
|
| 317 |
+
"eval_loss": 1.834492564201355,
|
| 318 |
+
"eval_runtime": 109.4942,
|
| 319 |
+
"eval_samples_per_second": 45.665,
|
| 320 |
+
"eval_steps_per_second": 1.434,
|
| 321 |
"step": 40
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.05,
|
| 325 |
+
"grad_norm": 0.765625,
|
| 326 |
"learning_rate": 8.2e-05,
|
| 327 |
+
"loss": 1.9118,
|
| 328 |
"step": 41
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 0.05,
|
| 332 |
+
"grad_norm": 0.640625,
|
| 333 |
"learning_rate": 8.4e-05,
|
| 334 |
+
"loss": 1.8096,
|
| 335 |
"step": 42
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 0.06,
|
| 339 |
+
"grad_norm": 0.515625,
|
| 340 |
"learning_rate": 8.6e-05,
|
| 341 |
+
"loss": 1.8097,
|
| 342 |
"step": 43
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 0.06,
|
| 346 |
+
"grad_norm": 0.49609375,
|
| 347 |
"learning_rate": 8.800000000000001e-05,
|
| 348 |
+
"loss": 1.7625,
|
| 349 |
"step": 44
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.06,
|
| 353 |
+
"grad_norm": 0.578125,
|
| 354 |
"learning_rate": 9e-05,
|
| 355 |
+
"loss": 1.7719,
|
| 356 |
"step": 45
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.06,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
"learning_rate": 9.200000000000001e-05,
|
| 362 |
+
"loss": 1.7783,
|
| 363 |
"step": 46
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.06,
|
| 367 |
"grad_norm": 0.5625,
|
| 368 |
"learning_rate": 9.4e-05,
|
| 369 |
+
"loss": 1.7888,
|
| 370 |
"step": 47
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 0.06,
|
| 374 |
+
"grad_norm": 0.55078125,
|
| 375 |
"learning_rate": 9.6e-05,
|
| 376 |
+
"loss": 1.7738,
|
| 377 |
"step": 48
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 0.06,
|
| 381 |
+
"grad_norm": 0.5859375,
|
| 382 |
"learning_rate": 9.8e-05,
|
| 383 |
+
"loss": 1.7428,
|
| 384 |
"step": 49
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 0.06,
|
| 388 |
+
"grad_norm": 0.55078125,
|
| 389 |
"learning_rate": 0.0001,
|
| 390 |
+
"loss": 1.7651,
|
| 391 |
"step": 50
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 0.06,
|
| 395 |
+
"eval_loss": 1.744554042816162,
|
| 396 |
+
"eval_runtime": 109.7416,
|
| 397 |
+
"eval_samples_per_second": 45.562,
|
| 398 |
+
"eval_steps_per_second": 1.431,
|
| 399 |
"step": 50
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.07,
|
| 403 |
+
"grad_norm": 0.58984375,
|
| 404 |
"learning_rate": 0.00010200000000000001,
|
| 405 |
+
"loss": 1.8558,
|
| 406 |
"step": 51
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"epoch": 0.07,
|
| 410 |
+
"grad_norm": 0.6171875,
|
| 411 |
"learning_rate": 0.00010400000000000001,
|
| 412 |
+
"loss": 1.7136,
|
| 413 |
"step": 52
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 0.07,
|
| 417 |
+
"grad_norm": 0.6328125,
|
| 418 |
"learning_rate": 0.00010600000000000002,
|
| 419 |
+
"loss": 1.6953,
|
| 420 |
"step": 53
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 0.07,
|
| 424 |
+
"grad_norm": 0.79296875,
|
| 425 |
"learning_rate": 0.00010800000000000001,
|
| 426 |
+
"loss": 1.7225,
|
| 427 |
"step": 54
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 0.07,
|
| 431 |
+
"grad_norm": 0.83203125,
|
| 432 |
"learning_rate": 0.00011000000000000002,
|
| 433 |
+
"loss": 1.6275,
|
| 434 |
"step": 55
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 0.07,
|
| 438 |
+
"grad_norm": 0.84375,
|
| 439 |
"learning_rate": 0.00011200000000000001,
|
| 440 |
+
"loss": 1.6724,
|
| 441 |
"step": 56
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.07,
|
| 445 |
+
"grad_norm": 0.5546875,
|
| 446 |
"learning_rate": 0.00011399999999999999,
|
| 447 |
+
"loss": 1.627,
|
| 448 |
"step": 57
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 0.07,
|
| 452 |
+
"grad_norm": 0.388671875,
|
| 453 |
"learning_rate": 0.000116,
|
| 454 |
+
"loss": 1.6624,
|
| 455 |
"step": 58
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 0.08,
|
| 459 |
+
"grad_norm": 0.34375,
|
| 460 |
"learning_rate": 0.000118,
|
| 461 |
+
"loss": 1.592,
|
| 462 |
"step": 59
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 0.08,
|
| 466 |
+
"grad_norm": 0.306640625,
|
| 467 |
"learning_rate": 0.00012,
|
| 468 |
+
"loss": 1.638,
|
| 469 |
"step": 60
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 0.08,
|
| 473 |
+
"eval_loss": 1.5958868265151978,
|
| 474 |
+
"eval_runtime": 109.6677,
|
| 475 |
+
"eval_samples_per_second": 45.592,
|
| 476 |
+
"eval_steps_per_second": 1.432,
|
| 477 |
"step": 60
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.08,
|
| 481 |
+
"grad_norm": 0.302734375,
|
| 482 |
"learning_rate": 0.000122,
|
| 483 |
+
"loss": 1.5942,
|
| 484 |
"step": 61
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 0.08,
|
| 488 |
+
"grad_norm": 0.30078125,
|
| 489 |
"learning_rate": 0.000124,
|
| 490 |
+
"loss": 1.6169,
|
| 491 |
"step": 62
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 0.08,
|
| 495 |
+
"grad_norm": 0.296875,
|
| 496 |
"learning_rate": 0.000126,
|
| 497 |
+
"loss": 1.6183,
|
| 498 |
"step": 63
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 0.08,
|
| 502 |
+
"grad_norm": 0.3046875,
|
| 503 |
"learning_rate": 0.00012800000000000002,
|
| 504 |
+
"loss": 1.5629,
|
| 505 |
"step": 64
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 0.08,
|
| 509 |
+
"grad_norm": 0.3203125,
|
| 510 |
"learning_rate": 0.00013000000000000002,
|
| 511 |
+
"loss": 1.6236,
|
| 512 |
"step": 65
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 0.08,
|
| 516 |
+
"grad_norm": 0.267578125,
|
| 517 |
"learning_rate": 0.000132,
|
| 518 |
+
"loss": 1.6701,
|
| 519 |
"step": 66
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.09,
|
| 523 |
+
"grad_norm": 0.294921875,
|
| 524 |
"learning_rate": 0.000134,
|
| 525 |
+
"loss": 1.6067,
|
| 526 |
"step": 67
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 0.09,
|
| 530 |
+
"grad_norm": 0.30859375,
|
| 531 |
"learning_rate": 0.00013600000000000003,
|
| 532 |
+
"loss": 1.5935,
|
| 533 |
"step": 68
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 0.09,
|
| 537 |
+
"grad_norm": 0.27734375,
|
| 538 |
"learning_rate": 0.000138,
|
| 539 |
+
"loss": 1.578,
|
| 540 |
"step": 69
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 0.09,
|
| 544 |
+
"grad_norm": 0.26953125,
|
| 545 |
"learning_rate": 0.00014,
|
| 546 |
+
"loss": 1.592,
|
| 547 |
"step": 70
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 0.09,
|
| 551 |
+
"eval_loss": 1.571932077407837,
|
| 552 |
+
"eval_runtime": 109.6303,
|
| 553 |
+
"eval_samples_per_second": 45.608,
|
| 554 |
+
"eval_steps_per_second": 1.432,
|
| 555 |
"step": 70
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.09,
|
| 559 |
+
"grad_norm": 0.28125,
|
| 560 |
"learning_rate": 0.000142,
|
| 561 |
+
"loss": 1.5923,
|
| 562 |
"step": 71
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 0.09,
|
| 566 |
+
"grad_norm": 0.283203125,
|
| 567 |
"learning_rate": 0.000144,
|
| 568 |
+
"loss": 1.5838,
|
| 569 |
"step": 72
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 0.09,
|
| 573 |
+
"grad_norm": 0.26171875,
|
| 574 |
"learning_rate": 0.000146,
|
| 575 |
+
"loss": 1.5646,
|
| 576 |
"step": 73
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 0.09,
|
| 580 |
+
"grad_norm": 0.255859375,
|
| 581 |
"learning_rate": 0.000148,
|
| 582 |
+
"loss": 1.6265,
|
| 583 |
"step": 74
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 0.1,
|
| 587 |
+
"grad_norm": 0.271484375,
|
| 588 |
"learning_rate": 0.00015000000000000001,
|
| 589 |
+
"loss": 1.622,
|
| 590 |
"step": 75
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.1,
|
| 594 |
+
"grad_norm": 0.2373046875,
|
| 595 |
"learning_rate": 0.000152,
|
| 596 |
+
"loss": 1.5504,
|
| 597 |
"step": 76
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.1,
|
| 601 |
+
"grad_norm": 0.267578125,
|
| 602 |
"learning_rate": 0.000154,
|
| 603 |
+
"loss": 1.6184,
|
| 604 |
"step": 77
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 0.1,
|
| 608 |
+
"grad_norm": 0.228515625,
|
| 609 |
"learning_rate": 0.00015600000000000002,
|
| 610 |
+
"loss": 1.5829,
|
| 611 |
"step": 78
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.1,
|
| 615 |
+
"grad_norm": 0.2451171875,
|
| 616 |
"learning_rate": 0.00015800000000000002,
|
| 617 |
+
"loss": 1.5305,
|
| 618 |
"step": 79
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.1,
|
| 622 |
+
"grad_norm": 0.25,
|
| 623 |
"learning_rate": 0.00016,
|
| 624 |
+
"loss": 1.554,
|
| 625 |
"step": 80
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.1,
|
| 629 |
+
"eval_loss": 1.5540077686309814,
|
| 630 |
+
"eval_runtime": 109.5859,
|
| 631 |
+
"eval_samples_per_second": 45.626,
|
| 632 |
+
"eval_steps_per_second": 1.433,
|
| 633 |
"step": 80
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.1,
|
| 637 |
+
"grad_norm": 0.24609375,
|
| 638 |
"learning_rate": 0.000162,
|
| 639 |
+
"loss": 1.5691,
|
| 640 |
"step": 81
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 0.1,
|
| 644 |
+
"grad_norm": 0.2470703125,
|
| 645 |
"learning_rate": 0.000164,
|
| 646 |
+
"loss": 1.542,
|
| 647 |
"step": 82
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 0.11,
|
| 651 |
+
"grad_norm": 0.2431640625,
|
| 652 |
"learning_rate": 0.000166,
|
| 653 |
+
"loss": 1.5844,
|
| 654 |
"step": 83
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.11,
|
| 658 |
+
"grad_norm": 0.2333984375,
|
| 659 |
"learning_rate": 0.000168,
|
| 660 |
+
"loss": 1.5429,
|
| 661 |
"step": 84
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.11,
|
| 665 |
+
"grad_norm": 0.2255859375,
|
| 666 |
"learning_rate": 0.00017,
|
| 667 |
+
"loss": 1.5836,
|
| 668 |
"step": 85
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.11,
|
| 672 |
+
"grad_norm": 0.25390625,
|
| 673 |
"learning_rate": 0.000172,
|
| 674 |
+
"loss": 1.5227,
|
| 675 |
"step": 86
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.11,
|
| 679 |
+
"grad_norm": 0.2412109375,
|
| 680 |
"learning_rate": 0.000174,
|
| 681 |
+
"loss": 1.5495,
|
| 682 |
"step": 87
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.11,
|
| 686 |
+
"grad_norm": 0.21484375,
|
| 687 |
"learning_rate": 0.00017600000000000002,
|
| 688 |
+
"loss": 1.6124,
|
| 689 |
"step": 88
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.11,
|
| 693 |
+
"grad_norm": 0.2470703125,
|
| 694 |
"learning_rate": 0.00017800000000000002,
|
| 695 |
+
"loss": 1.5469,
|
| 696 |
"step": 89
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 0.12,
|
| 700 |
+
"grad_norm": 0.2470703125,
|
| 701 |
"learning_rate": 0.00018,
|
| 702 |
+
"loss": 1.5215,
|
| 703 |
"step": 90
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 0.12,
|
| 707 |
+
"eval_loss": 1.5420269966125488,
|
| 708 |
+
"eval_runtime": 109.6203,
|
| 709 |
+
"eval_samples_per_second": 45.612,
|
| 710 |
+
"eval_steps_per_second": 1.432,
|
| 711 |
"step": 90
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.12,
|
| 715 |
+
"grad_norm": 0.22265625,
|
| 716 |
"learning_rate": 0.000182,
|
| 717 |
+
"loss": 1.5654,
|
| 718 |
"step": 91
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.12,
|
| 722 |
+
"grad_norm": 0.2392578125,
|
| 723 |
"learning_rate": 0.00018400000000000003,
|
| 724 |
+
"loss": 1.494,
|
| 725 |
"step": 92
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.12,
|
| 729 |
+
"grad_norm": 0.216796875,
|
| 730 |
"learning_rate": 0.00018600000000000002,
|
| 731 |
+
"loss": 1.6285,
|
| 732 |
"step": 93
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.12,
|
| 736 |
+
"grad_norm": 0.2451171875,
|
| 737 |
"learning_rate": 0.000188,
|
| 738 |
+
"loss": 1.5177,
|
| 739 |
"step": 94
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 0.12,
|
| 743 |
+
"grad_norm": 0.2177734375,
|
| 744 |
"learning_rate": 0.00019,
|
| 745 |
+
"loss": 1.5659,
|
| 746 |
"step": 95
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 0.12,
|
| 750 |
+
"grad_norm": 0.220703125,
|
| 751 |
"learning_rate": 0.000192,
|
| 752 |
+
"loss": 1.6005,
|
| 753 |
"step": 96
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.12,
|
| 757 |
+
"grad_norm": 0.251953125,
|
| 758 |
"learning_rate": 0.000194,
|
| 759 |
+
"loss": 1.5713,
|
| 760 |
"step": 97
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 0.13,
|
| 764 |
+
"grad_norm": 0.2294921875,
|
| 765 |
"learning_rate": 0.000196,
|
| 766 |
+
"loss": 1.4815,
|
| 767 |
"step": 98
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 0.13,
|
| 771 |
+
"grad_norm": 0.216796875,
|
| 772 |
"learning_rate": 0.00019800000000000002,
|
| 773 |
+
"loss": 1.489,
|
| 774 |
"step": 99
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 0.13,
|
| 778 |
+
"grad_norm": 0.216796875,
|
| 779 |
"learning_rate": 0.0002,
|
| 780 |
+
"loss": 1.497,
|
| 781 |
"step": 100
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 0.13,
|
| 785 |
+
"eval_loss": 1.5331306457519531,
|
| 786 |
+
"eval_runtime": 108.6942,
|
| 787 |
+
"eval_samples_per_second": 46.001,
|
| 788 |
+
"eval_steps_per_second": 1.444,
|
| 789 |
"step": 100
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.13,
|
| 793 |
+
"grad_norm": 0.23046875,
|
| 794 |
"learning_rate": 0.00019871794871794874,
|
| 795 |
+
"loss": 1.4933,
|
| 796 |
"step": 101
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 0.13,
|
| 800 |
+
"grad_norm": 0.23828125,
|
| 801 |
"learning_rate": 0.00019743589743589744,
|
| 802 |
+
"loss": 1.5385,
|
| 803 |
"step": 102
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 0.13,
|
| 807 |
+
"grad_norm": 0.2431640625,
|
| 808 |
"learning_rate": 0.00019615384615384615,
|
| 809 |
+
"loss": 1.5745,
|
| 810 |
"step": 103
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.13,
|
| 814 |
+
"grad_norm": 0.220703125,
|
| 815 |
"learning_rate": 0.00019487179487179487,
|
| 816 |
+
"loss": 1.5485,
|
| 817 |
"step": 104
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 0.13,
|
| 821 |
+
"grad_norm": 0.248046875,
|
| 822 |
"learning_rate": 0.0001935897435897436,
|
| 823 |
+
"loss": 1.5391,
|
| 824 |
"step": 105
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.14,
|
| 828 |
+
"grad_norm": 0.23046875,
|
| 829 |
"learning_rate": 0.00019230769230769233,
|
| 830 |
+
"loss": 1.5649,
|
| 831 |
"step": 106
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.14,
|
| 835 |
+
"grad_norm": 0.212890625,
|
| 836 |
"learning_rate": 0.00019102564102564104,
|
| 837 |
+
"loss": 1.5543,
|
| 838 |
"step": 107
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 0.14,
|
| 842 |
+
"grad_norm": 0.23046875,
|
| 843 |
"learning_rate": 0.00018974358974358974,
|
| 844 |
+
"loss": 1.5377,
|
| 845 |
"step": 108
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 0.14,
|
| 849 |
+
"grad_norm": 0.2314453125,
|
| 850 |
"learning_rate": 0.00018846153846153847,
|
| 851 |
+
"loss": 1.534,
|
| 852 |
"step": 109
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 0.14,
|
| 856 |
+
"grad_norm": 0.2119140625,
|
| 857 |
"learning_rate": 0.0001871794871794872,
|
| 858 |
+
"loss": 1.5583,
|
| 859 |
"step": 110
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 0.14,
|
| 863 |
+
"eval_loss": 1.526591181755066,
|
| 864 |
+
"eval_runtime": 108.4319,
|
| 865 |
+
"eval_samples_per_second": 46.112,
|
| 866 |
+
"eval_steps_per_second": 1.448,
|
| 867 |
"step": 110
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.14,
|
| 871 |
+
"grad_norm": 0.234375,
|
| 872 |
"learning_rate": 0.0001858974358974359,
|
| 873 |
+
"loss": 1.4938,
|
| 874 |
"step": 111
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 0.14,
|
| 878 |
+
"grad_norm": 0.248046875,
|
| 879 |
"learning_rate": 0.00018461538461538463,
|
| 880 |
+
"loss": 1.5327,
|
| 881 |
"step": 112
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 0.14,
|
| 885 |
+
"grad_norm": 0.2294921875,
|
| 886 |
"learning_rate": 0.00018333333333333334,
|
| 887 |
+
"loss": 1.5475,
|
| 888 |
"step": 113
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 0.15,
|
| 892 |
+
"grad_norm": 0.2431640625,
|
| 893 |
"learning_rate": 0.00018205128205128207,
|
| 894 |
+
"loss": 1.5718,
|
| 895 |
"step": 114
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 0.15,
|
| 899 |
+
"grad_norm": 0.23046875,
|
| 900 |
"learning_rate": 0.00018076923076923077,
|
| 901 |
+
"loss": 1.53,
|
| 902 |
"step": 115
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 0.15,
|
| 906 |
+
"grad_norm": 0.2177734375,
|
| 907 |
"learning_rate": 0.0001794871794871795,
|
| 908 |
+
"loss": 1.5675,
|
| 909 |
"step": 116
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.15,
|
| 913 |
+
"grad_norm": 0.2431640625,
|
| 914 |
"learning_rate": 0.00017820512820512823,
|
| 915 |
+
"loss": 1.6159,
|
| 916 |
"step": 117
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 0.15,
|
| 920 |
+
"grad_norm": 0.2119140625,
|
| 921 |
"learning_rate": 0.00017692307692307693,
|
| 922 |
+
"loss": 1.5419,
|
| 923 |
"step": 118
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 0.15,
|
| 927 |
+
"grad_norm": 0.2294921875,
|
| 928 |
"learning_rate": 0.00017564102564102566,
|
| 929 |
+
"loss": 1.4955,
|
| 930 |
"step": 119
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 0.15,
|
| 934 |
+
"grad_norm": 0.2236328125,
|
| 935 |
"learning_rate": 0.00017435897435897436,
|
| 936 |
+
"loss": 1.5639,
|
| 937 |
"step": 120
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 0.15,
|
| 941 |
+
"eval_loss": 1.521650791168213,
|
| 942 |
+
"eval_runtime": 108.8276,
|
| 943 |
+
"eval_samples_per_second": 45.944,
|
| 944 |
+
"eval_steps_per_second": 1.443,
|
| 945 |
"step": 120
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.15,
|
| 949 |
+
"grad_norm": 0.2119140625,
|
| 950 |
"learning_rate": 0.0001730769230769231,
|
| 951 |
+
"loss": 1.5569,
|
| 952 |
"step": 121
|
| 953 |
},
|
| 954 |
{
|
| 955 |
"epoch": 0.16,
|
| 956 |
+
"grad_norm": 0.24609375,
|
| 957 |
"learning_rate": 0.0001717948717948718,
|
| 958 |
+
"loss": 1.527,
|
| 959 |
"step": 122
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 0.16,
|
| 963 |
+
"grad_norm": 0.2197265625,
|
| 964 |
"learning_rate": 0.00017051282051282053,
|
| 965 |
+
"loss": 1.538,
|
| 966 |
"step": 123
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 0.16,
|
| 970 |
+
"grad_norm": 0.26953125,
|
| 971 |
"learning_rate": 0.00016923076923076923,
|
| 972 |
+
"loss": 1.5353,
|
| 973 |
"step": 124
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 0.16,
|
| 977 |
+
"grad_norm": 0.2353515625,
|
| 978 |
"learning_rate": 0.00016794871794871796,
|
| 979 |
+
"loss": 1.5495,
|
| 980 |
"step": 125
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 0.16,
|
| 984 |
+
"grad_norm": 0.2421875,
|
| 985 |
"learning_rate": 0.0001666666666666667,
|
| 986 |
+
"loss": 1.5366,
|
| 987 |
"step": 126
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.16,
|
| 991 |
+
"grad_norm": 0.228515625,
|
| 992 |
"learning_rate": 0.0001653846153846154,
|
| 993 |
+
"loss": 1.5695,
|
| 994 |
"step": 127
|
| 995 |
},
|
| 996 |
{
|
| 997 |
"epoch": 0.16,
|
| 998 |
+
"grad_norm": 0.2314453125,
|
| 999 |
"learning_rate": 0.0001641025641025641,
|
| 1000 |
+
"loss": 1.5112,
|
| 1001 |
"step": 128
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 0.17,
|
| 1005 |
+
"grad_norm": 0.234375,
|
| 1006 |
"learning_rate": 0.00016282051282051282,
|
| 1007 |
+
"loss": 1.5919,
|
| 1008 |
"step": 129
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
"epoch": 0.17,
|
| 1012 |
+
"grad_norm": 0.2216796875,
|
| 1013 |
"learning_rate": 0.00016153846153846155,
|
| 1014 |
+
"loss": 1.5785,
|
| 1015 |
"step": 130
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 0.17,
|
| 1019 |
+
"eval_loss": 1.517764925956726,
|
| 1020 |
+
"eval_runtime": 109.0406,
|
| 1021 |
+
"eval_samples_per_second": 45.854,
|
| 1022 |
+
"eval_steps_per_second": 1.44,
|
| 1023 |
"step": 130
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.17,
|
| 1027 |
+
"grad_norm": 0.248046875,
|
| 1028 |
"learning_rate": 0.00016025641025641028,
|
| 1029 |
+
"loss": 1.5056,
|
| 1030 |
"step": 131
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
"epoch": 0.17,
|
| 1034 |
+
"grad_norm": 0.236328125,
|
| 1035 |
"learning_rate": 0.00015897435897435896,
|
| 1036 |
+
"loss": 1.5427,
|
| 1037 |
"step": 132
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
"epoch": 0.17,
|
| 1041 |
+
"grad_norm": 0.23046875,
|
| 1042 |
"learning_rate": 0.0001576923076923077,
|
| 1043 |
+
"loss": 1.5357,
|
| 1044 |
"step": 133
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 0.17,
|
| 1048 |
+
"grad_norm": 0.21875,
|
| 1049 |
"learning_rate": 0.00015641025641025642,
|
| 1050 |
+
"loss": 1.5671,
|
| 1051 |
"step": 134
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 0.17,
|
| 1055 |
+
"grad_norm": 0.2421875,
|
| 1056 |
"learning_rate": 0.00015512820512820515,
|
| 1057 |
+
"loss": 1.5247,
|
| 1058 |
"step": 135
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 0.17,
|
| 1062 |
+
"grad_norm": 0.2412109375,
|
| 1063 |
"learning_rate": 0.00015384615384615385,
|
| 1064 |
+
"loss": 1.557,
|
| 1065 |
"step": 136
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.18,
|
| 1069 |
+
"grad_norm": 0.26953125,
|
| 1070 |
"learning_rate": 0.00015256410256410255,
|
| 1071 |
+
"loss": 1.5042,
|
| 1072 |
"step": 137
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 0.18,
|
| 1076 |
+
"grad_norm": 0.2373046875,
|
| 1077 |
"learning_rate": 0.00015128205128205128,
|
| 1078 |
+
"loss": 1.5061,
|
| 1079 |
"step": 138
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 0.18,
|
| 1083 |
+
"grad_norm": 0.26953125,
|
| 1084 |
"learning_rate": 0.00015000000000000001,
|
| 1085 |
+
"loss": 1.5608,
|
| 1086 |
"step": 139
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 0.18,
|
| 1090 |
+
"grad_norm": 0.25,
|
| 1091 |
"learning_rate": 0.00014871794871794872,
|
| 1092 |
+
"loss": 1.5235,
|
| 1093 |
"step": 140
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 0.18,
|
| 1097 |
+
"eval_loss": 1.5145833492279053,
|
| 1098 |
+
"eval_runtime": 109.0187,
|
| 1099 |
+
"eval_samples_per_second": 45.864,
|
| 1100 |
+
"eval_steps_per_second": 1.44,
|
| 1101 |
"step": 140
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 0.18,
|
| 1105 |
+
"grad_norm": 0.2314453125,
|
| 1106 |
"learning_rate": 0.00014743589743589745,
|
| 1107 |
+
"loss": 1.5099,
|
| 1108 |
"step": 141
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 0.18,
|
| 1112 |
+
"grad_norm": 0.228515625,
|
| 1113 |
"learning_rate": 0.00014615384615384615,
|
| 1114 |
+
"loss": 1.5413,
|
| 1115 |
"step": 142
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 0.18,
|
| 1119 |
+
"grad_norm": 0.2373046875,
|
| 1120 |
"learning_rate": 0.00014487179487179488,
|
| 1121 |
+
"loss": 1.5383,
|
| 1122 |
"step": 143
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 0.18,
|
| 1126 |
+
"grad_norm": 0.234375,
|
| 1127 |
"learning_rate": 0.0001435897435897436,
|
| 1128 |
+
"loss": 1.5671,
|
| 1129 |
"step": 144
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 0.19,
|
| 1133 |
+
"grad_norm": 0.244140625,
|
| 1134 |
"learning_rate": 0.0001423076923076923,
|
| 1135 |
+
"loss": 1.5102,
|
| 1136 |
"step": 145
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 0.19,
|
| 1140 |
+
"grad_norm": 0.220703125,
|
| 1141 |
"learning_rate": 0.00014102564102564104,
|
| 1142 |
+
"loss": 1.545,
|
| 1143 |
"step": 146
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.19,
|
| 1147 |
+
"grad_norm": 0.228515625,
|
| 1148 |
"learning_rate": 0.00013974358974358974,
|
| 1149 |
+
"loss": 1.5223,
|
| 1150 |
"step": 147
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 0.19,
|
| 1154 |
+
"grad_norm": 0.2275390625,
|
| 1155 |
"learning_rate": 0.00013846153846153847,
|
| 1156 |
+
"loss": 1.433,
|
| 1157 |
"step": 148
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 0.19,
|
| 1161 |
+
"grad_norm": 0.2353515625,
|
| 1162 |
"learning_rate": 0.00013717948717948718,
|
| 1163 |
+
"loss": 1.554,
|
| 1164 |
"step": 149
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 0.19,
|
| 1168 |
+
"grad_norm": 0.2314453125,
|
| 1169 |
"learning_rate": 0.0001358974358974359,
|
| 1170 |
+
"loss": 1.5447,
|
| 1171 |
"step": 150
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 0.19,
|
| 1175 |
+
"eval_loss": 1.5118788480758667,
|
| 1176 |
+
"eval_runtime": 109.1366,
|
| 1177 |
+
"eval_samples_per_second": 45.814,
|
| 1178 |
+
"eval_steps_per_second": 1.439,
|
| 1179 |
"step": 150
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.19,
|
| 1183 |
+
"grad_norm": 0.259765625,
|
| 1184 |
"learning_rate": 0.00013461538461538464,
|
| 1185 |
+
"loss": 1.4771,
|
| 1186 |
"step": 151
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 0.19,
|
| 1190 |
+
"grad_norm": 0.240234375,
|
| 1191 |
"learning_rate": 0.00013333333333333334,
|
| 1192 |
+
"loss": 1.5853,
|
| 1193 |
"step": 152
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 0.2,
|
| 1197 |
+
"grad_norm": 0.2197265625,
|
| 1198 |
"learning_rate": 0.00013205128205128204,
|
| 1199 |
+
"loss": 1.5237,
|
| 1200 |
"step": 153
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 0.2,
|
| 1204 |
+
"grad_norm": 0.2578125,
|
| 1205 |
"learning_rate": 0.00013076923076923077,
|
| 1206 |
+
"loss": 1.4963,
|
| 1207 |
"step": 154
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
"epoch": 0.2,
|
| 1211 |
+
"grad_norm": 0.2373046875,
|
| 1212 |
"learning_rate": 0.0001294871794871795,
|
| 1213 |
+
"loss": 1.5393,
|
| 1214 |
"step": 155
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 0.2,
|
| 1218 |
+
"grad_norm": 0.220703125,
|
| 1219 |
"learning_rate": 0.00012820512820512823,
|
| 1220 |
+
"loss": 1.4725,
|
| 1221 |
"step": 156
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 0.2,
|
| 1225 |
+
"grad_norm": 0.220703125,
|
| 1226 |
"learning_rate": 0.00012692307692307693,
|
| 1227 |
+
"loss": 1.5187,
|
| 1228 |
"step": 157
|
| 1229 |
},
|
| 1230 |
{
|
| 1231 |
"epoch": 0.2,
|
| 1232 |
"grad_norm": 0.251953125,
|
| 1233 |
"learning_rate": 0.00012564102564102564,
|
| 1234 |
+
"loss": 1.5263,
|
| 1235 |
"step": 158
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 0.2,
|
| 1239 |
+
"grad_norm": 0.2470703125,
|
| 1240 |
"learning_rate": 0.00012435897435897437,
|
| 1241 |
+
"loss": 1.5388,
|
| 1242 |
"step": 159
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 0.2,
|
| 1246 |
+
"grad_norm": 0.224609375,
|
| 1247 |
"learning_rate": 0.0001230769230769231,
|
| 1248 |
+
"loss": 1.4606,
|
| 1249 |
"step": 160
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
"epoch": 0.2,
|
| 1253 |
+
"eval_loss": 1.5093975067138672,
|
| 1254 |
+
"eval_runtime": 109.3522,
|
| 1255 |
+
"eval_samples_per_second": 45.724,
|
| 1256 |
+
"eval_steps_per_second": 1.436,
|
| 1257 |
"step": 160
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.21,
|
| 1261 |
+
"grad_norm": 0.2392578125,
|
| 1262 |
"learning_rate": 0.00012179487179487179,
|
| 1263 |
+
"loss": 1.5584,
|
| 1264 |
"step": 161
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 0.21,
|
| 1268 |
+
"grad_norm": 0.224609375,
|
| 1269 |
"learning_rate": 0.00012051282051282052,
|
| 1270 |
+
"loss": 1.4941,
|
| 1271 |
"step": 162
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 0.21,
|
| 1275 |
+
"grad_norm": 0.236328125,
|
| 1276 |
"learning_rate": 0.00011923076923076923,
|
| 1277 |
+
"loss": 1.5283,
|
| 1278 |
"step": 163
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
"epoch": 0.21,
|
| 1282 |
+
"grad_norm": 0.2373046875,
|
| 1283 |
"learning_rate": 0.00011794871794871796,
|
| 1284 |
+
"loss": 1.4864,
|
| 1285 |
"step": 164
|
| 1286 |
},
|
| 1287 |
{
|
| 1288 |
"epoch": 0.21,
|
| 1289 |
+
"grad_norm": 0.24609375,
|
| 1290 |
"learning_rate": 0.00011666666666666668,
|
| 1291 |
+
"loss": 1.4398,
|
| 1292 |
"step": 165
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 0.21,
|
| 1296 |
+
"grad_norm": 0.251953125,
|
| 1297 |
"learning_rate": 0.00011538461538461538,
|
| 1298 |
+
"loss": 1.514,
|
| 1299 |
"step": 166
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.21,
|
| 1303 |
+
"grad_norm": 0.25390625,
|
| 1304 |
"learning_rate": 0.0001141025641025641,
|
| 1305 |
+
"loss": 1.5578,
|
| 1306 |
"step": 167
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 0.21,
|
| 1310 |
+
"grad_norm": 0.2353515625,
|
| 1311 |
"learning_rate": 0.00011282051282051283,
|
| 1312 |
+
"loss": 1.5682,
|
| 1313 |
"step": 168
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 0.22,
|
| 1317 |
+
"grad_norm": 0.23046875,
|
| 1318 |
"learning_rate": 0.00011153846153846154,
|
| 1319 |
+
"loss": 1.4911,
|
| 1320 |
"step": 169
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 0.22,
|
| 1324 |
+
"grad_norm": 0.236328125,
|
| 1325 |
"learning_rate": 0.00011025641025641027,
|
| 1326 |
+
"loss": 1.5906,
|
| 1327 |
"step": 170
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 0.22,
|
| 1331 |
+
"eval_loss": 1.5074635744094849,
|
| 1332 |
+
"eval_runtime": 108.9797,
|
| 1333 |
+
"eval_samples_per_second": 45.88,
|
| 1334 |
+
"eval_steps_per_second": 1.441,
|
| 1335 |
"step": 170
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 0.22,
|
| 1339 |
+
"grad_norm": 0.271484375,
|
| 1340 |
"learning_rate": 0.00010897435897435896,
|
| 1341 |
+
"loss": 1.5266,
|
| 1342 |
"step": 171
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 0.22,
|
| 1346 |
+
"grad_norm": 0.23828125,
|
| 1347 |
"learning_rate": 0.0001076923076923077,
|
| 1348 |
+
"loss": 1.4515,
|
| 1349 |
"step": 172
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 0.22,
|
| 1353 |
+
"grad_norm": 0.2451171875,
|
| 1354 |
"learning_rate": 0.00010641025641025641,
|
| 1355 |
+
"loss": 1.5492,
|
| 1356 |
"step": 173
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 0.22,
|
| 1360 |
+
"grad_norm": 0.2314453125,
|
| 1361 |
"learning_rate": 0.00010512820512820514,
|
| 1362 |
+
"loss": 1.4961,
|
| 1363 |
"step": 174
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 0.22,
|
| 1367 |
+
"grad_norm": 0.2421875,
|
| 1368 |
"learning_rate": 0.00010384615384615386,
|
| 1369 |
+
"loss": 1.5594,
|
| 1370 |
"step": 175
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 0.23,
|
| 1374 |
+
"grad_norm": 0.2275390625,
|
| 1375 |
"learning_rate": 0.00010256410256410256,
|
| 1376 |
+
"loss": 1.5469,
|
| 1377 |
"step": 176
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 0.23,
|
| 1381 |
+
"grad_norm": 0.240234375,
|
| 1382 |
"learning_rate": 0.00010128205128205129,
|
| 1383 |
+
"loss": 1.4925,
|
| 1384 |
"step": 177
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 0.23,
|
| 1388 |
+
"grad_norm": 0.2578125,
|
| 1389 |
"learning_rate": 0.0001,
|
| 1390 |
+
"loss": 1.4808,
|
| 1391 |
"step": 178
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 0.23,
|
| 1395 |
+
"grad_norm": 0.251953125,
|
| 1396 |
"learning_rate": 9.871794871794872e-05,
|
| 1397 |
+
"loss": 1.4963,
|
| 1398 |
"step": 179
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 0.23,
|
| 1402 |
+
"grad_norm": 0.2578125,
|
| 1403 |
"learning_rate": 9.743589743589744e-05,
|
| 1404 |
+
"loss": 1.5397,
|
| 1405 |
"step": 180
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 0.23,
|
| 1409 |
+
"eval_loss": 1.5060302019119263,
|
| 1410 |
+
"eval_runtime": 109.1672,
|
| 1411 |
+
"eval_samples_per_second": 45.801,
|
| 1412 |
+
"eval_steps_per_second": 1.438,
|
| 1413 |
"step": 180
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 0.23,
|
| 1417 |
+
"grad_norm": 0.2451171875,
|
| 1418 |
"learning_rate": 9.615384615384617e-05,
|
| 1419 |
+
"loss": 1.5202,
|
| 1420 |
"step": 181
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 0.23,
|
| 1424 |
+
"grad_norm": 0.2158203125,
|
| 1425 |
"learning_rate": 9.487179487179487e-05,
|
| 1426 |
+
"loss": 1.488,
|
| 1427 |
"step": 182
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
"epoch": 0.23,
|
| 1431 |
+
"grad_norm": 0.25390625,
|
| 1432 |
"learning_rate": 9.35897435897436e-05,
|
| 1433 |
+
"loss": 1.5124,
|
| 1434 |
"step": 183
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 0.24,
|
| 1438 |
+
"grad_norm": 0.2578125,
|
| 1439 |
"learning_rate": 9.230769230769232e-05,
|
| 1440 |
+
"loss": 1.4791,
|
| 1441 |
"step": 184
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 0.24,
|
| 1445 |
+
"grad_norm": 0.2421875,
|
| 1446 |
"learning_rate": 9.102564102564103e-05,
|
| 1447 |
+
"loss": 1.6039,
|
| 1448 |
"step": 185
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 0.24,
|
| 1452 |
+
"grad_norm": 0.2353515625,
|
| 1453 |
"learning_rate": 8.974358974358975e-05,
|
| 1454 |
+
"loss": 1.5389,
|
| 1455 |
"step": 186
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 0.24,
|
| 1459 |
+
"grad_norm": 0.2216796875,
|
| 1460 |
"learning_rate": 8.846153846153847e-05,
|
| 1461 |
+
"loss": 1.5542,
|
| 1462 |
"step": 187
|
| 1463 |
},
|
| 1464 |
{
|
| 1465 |
"epoch": 0.24,
|
| 1466 |
+
"grad_norm": 0.2353515625,
|
| 1467 |
"learning_rate": 8.717948717948718e-05,
|
| 1468 |
+
"loss": 1.5131,
|
| 1469 |
"step": 188
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 0.24,
|
| 1473 |
+
"grad_norm": 0.248046875,
|
| 1474 |
"learning_rate": 8.58974358974359e-05,
|
| 1475 |
+
"loss": 1.5371,
|
| 1476 |
"step": 189
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 0.24,
|
| 1480 |
+
"grad_norm": 0.2392578125,
|
| 1481 |
"learning_rate": 8.461538461538461e-05,
|
| 1482 |
+
"loss": 1.5264,
|
| 1483 |
"step": 190
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 0.24,
|
| 1487 |
+
"eval_loss": 1.5048484802246094,
|
| 1488 |
+
"eval_runtime": 109.1034,
|
| 1489 |
+
"eval_samples_per_second": 45.828,
|
| 1490 |
+
"eval_steps_per_second": 1.439,
|
| 1491 |
"step": 190
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
"epoch": 0.24,
|
| 1495 |
+
"grad_norm": 0.236328125,
|
| 1496 |
"learning_rate": 8.333333333333334e-05,
|
| 1497 |
+
"loss": 1.5295,
|
| 1498 |
"step": 191
|
| 1499 |
},
|
| 1500 |
{
|
| 1501 |
"epoch": 0.25,
|
| 1502 |
+
"grad_norm": 0.2333984375,
|
| 1503 |
"learning_rate": 8.205128205128205e-05,
|
| 1504 |
+
"loss": 1.5677,
|
| 1505 |
"step": 192
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
"epoch": 0.25,
|
| 1509 |
+
"grad_norm": 0.255859375,
|
| 1510 |
"learning_rate": 8.076923076923078e-05,
|
| 1511 |
+
"loss": 1.4473,
|
| 1512 |
"step": 193
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
"epoch": 0.25,
|
| 1516 |
+
"grad_norm": 0.2353515625,
|
| 1517 |
"learning_rate": 7.948717948717948e-05,
|
| 1518 |
+
"loss": 1.5756,
|
| 1519 |
"step": 194
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 0.25,
|
| 1523 |
+
"grad_norm": 0.236328125,
|
| 1524 |
"learning_rate": 7.820512820512821e-05,
|
| 1525 |
+
"loss": 1.4832,
|
| 1526 |
"step": 195
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 0.25,
|
| 1530 |
+
"grad_norm": 0.2294921875,
|
| 1531 |
"learning_rate": 7.692307692307693e-05,
|
| 1532 |
+
"loss": 1.5144,
|
| 1533 |
"step": 196
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 0.25,
|
| 1537 |
+
"grad_norm": 0.248046875,
|
| 1538 |
"learning_rate": 7.564102564102564e-05,
|
| 1539 |
+
"loss": 1.5077,
|
| 1540 |
"step": 197
|
| 1541 |
},
|
| 1542 |
{
|
| 1543 |
"epoch": 0.25,
|
| 1544 |
+
"grad_norm": 0.21875,
|
| 1545 |
"learning_rate": 7.435897435897436e-05,
|
| 1546 |
+
"loss": 1.5042,
|
| 1547 |
"step": 198
|
| 1548 |
},
|
| 1549 |
{
|
| 1550 |
"epoch": 0.25,
|
| 1551 |
+
"grad_norm": 0.22265625,
|
| 1552 |
"learning_rate": 7.307692307692307e-05,
|
| 1553 |
+
"loss": 1.5022,
|
| 1554 |
"step": 199
|
| 1555 |
},
|
| 1556 |
{
|
| 1557 |
"epoch": 0.26,
|
| 1558 |
+
"grad_norm": 0.265625,
|
| 1559 |
"learning_rate": 7.17948717948718e-05,
|
| 1560 |
+
"loss": 1.484,
|
| 1561 |
"step": 200
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
"epoch": 0.26,
|
| 1565 |
+
"eval_loss": 1.503655195236206,
|
| 1566 |
+
"eval_runtime": 117.4418,
|
| 1567 |
+
"eval_samples_per_second": 42.574,
|
| 1568 |
+
"eval_steps_per_second": 1.337,
|
| 1569 |
"step": 200
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 0.26,
|
| 1573 |
+
"grad_norm": 0.2431640625,
|
| 1574 |
"learning_rate": 7.051282051282052e-05,
|
| 1575 |
+
"loss": 1.4973,
|
| 1576 |
"step": 201
|
| 1577 |
},
|
| 1578 |
{
|
| 1579 |
"epoch": 0.26,
|
| 1580 |
+
"grad_norm": 0.2314453125,
|
| 1581 |
"learning_rate": 6.923076923076924e-05,
|
| 1582 |
+
"loss": 1.5267,
|
| 1583 |
"step": 202
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
"epoch": 0.26,
|
| 1587 |
+
"grad_norm": 0.2236328125,
|
| 1588 |
"learning_rate": 6.794871794871795e-05,
|
| 1589 |
+
"loss": 1.5657,
|
| 1590 |
"step": 203
|
| 1591 |
},
|
| 1592 |
{
|
| 1593 |
"epoch": 0.26,
|
| 1594 |
+
"grad_norm": 0.23046875,
|
| 1595 |
"learning_rate": 6.666666666666667e-05,
|
| 1596 |
+
"loss": 1.5184,
|
| 1597 |
"step": 204
|
| 1598 |
},
|
| 1599 |
{
|
| 1600 |
"epoch": 0.26,
|
| 1601 |
+
"grad_norm": 0.23828125,
|
| 1602 |
"learning_rate": 6.538461538461539e-05,
|
| 1603 |
+
"loss": 1.4522,
|
| 1604 |
"step": 205
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 0.26,
|
| 1608 |
+
"grad_norm": 0.2451171875,
|
| 1609 |
"learning_rate": 6.410256410256412e-05,
|
| 1610 |
+
"loss": 1.5309,
|
| 1611 |
"step": 206
|
| 1612 |
},
|
| 1613 |
{
|
| 1614 |
"epoch": 0.26,
|
| 1615 |
+
"grad_norm": 0.2373046875,
|
| 1616 |
"learning_rate": 6.282051282051282e-05,
|
| 1617 |
+
"loss": 1.4503,
|
| 1618 |
"step": 207
|
| 1619 |
},
|
| 1620 |
{
|
| 1621 |
"epoch": 0.27,
|
| 1622 |
+
"grad_norm": 0.2265625,
|
| 1623 |
"learning_rate": 6.153846153846155e-05,
|
| 1624 |
+
"loss": 1.5173,
|
| 1625 |
"step": 208
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
"epoch": 0.27,
|
| 1629 |
+
"grad_norm": 0.275390625,
|
| 1630 |
"learning_rate": 6.025641025641026e-05,
|
| 1631 |
+
"loss": 1.5112,
|
| 1632 |
"step": 209
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 0.27,
|
| 1636 |
+
"grad_norm": 0.234375,
|
| 1637 |
"learning_rate": 5.897435897435898e-05,
|
| 1638 |
+
"loss": 1.5342,
|
| 1639 |
"step": 210
|
| 1640 |
},
|
| 1641 |
{
|
| 1642 |
"epoch": 0.27,
|
| 1643 |
+
"eval_loss": 1.5029850006103516,
|
| 1644 |
+
"eval_runtime": 118.7123,
|
| 1645 |
+
"eval_samples_per_second": 42.119,
|
| 1646 |
+
"eval_steps_per_second": 1.323,
|
| 1647 |
"step": 210
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 0.27,
|
| 1651 |
+
"grad_norm": 0.2333984375,
|
| 1652 |
"learning_rate": 5.769230769230769e-05,
|
| 1653 |
+
"loss": 1.5216,
|
| 1654 |
"step": 211
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 0.27,
|
| 1658 |
+
"grad_norm": 0.2373046875,
|
| 1659 |
"learning_rate": 5.6410256410256414e-05,
|
| 1660 |
+
"loss": 1.5005,
|
| 1661 |
"step": 212
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 0.27,
|
| 1665 |
+
"grad_norm": 0.23046875,
|
| 1666 |
"learning_rate": 5.512820512820514e-05,
|
| 1667 |
+
"loss": 1.5372,
|
| 1668 |
"step": 213
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 0.27,
|
| 1672 |
+
"grad_norm": 0.2353515625,
|
| 1673 |
"learning_rate": 5.384615384615385e-05,
|
| 1674 |
+
"loss": 1.4916,
|
| 1675 |
"step": 214
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 0.28,
|
| 1679 |
+
"grad_norm": 0.232421875,
|
| 1680 |
"learning_rate": 5.256410256410257e-05,
|
| 1681 |
+
"loss": 1.4511,
|
| 1682 |
"step": 215
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 0.28,
|
| 1686 |
+
"grad_norm": 0.251953125,
|
| 1687 |
"learning_rate": 5.128205128205128e-05,
|
| 1688 |
+
"loss": 1.4984,
|
| 1689 |
"step": 216
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 0.28,
|
| 1693 |
+
"grad_norm": 0.275390625,
|
| 1694 |
"learning_rate": 5e-05,
|
| 1695 |
+
"loss": 1.5332,
|
| 1696 |
"step": 217
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 0.28,
|
| 1700 |
+
"grad_norm": 0.2412109375,
|
| 1701 |
"learning_rate": 4.871794871794872e-05,
|
| 1702 |
+
"loss": 1.558,
|
| 1703 |
"step": 218
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 0.28,
|
| 1707 |
+
"grad_norm": 0.255859375,
|
| 1708 |
"learning_rate": 4.7435897435897435e-05,
|
| 1709 |
+
"loss": 1.5057,
|
| 1710 |
"step": 219
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
"epoch": 0.28,
|
| 1714 |
+
"grad_norm": 0.2431640625,
|
| 1715 |
"learning_rate": 4.615384615384616e-05,
|
| 1716 |
+
"loss": 1.5374,
|
| 1717 |
"step": 220
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
"epoch": 0.28,
|
| 1721 |
+
"eval_loss": 1.5021294355392456,
|
| 1722 |
+
"eval_runtime": 120.5989,
|
| 1723 |
+
"eval_samples_per_second": 41.46,
|
| 1724 |
+
"eval_steps_per_second": 1.302,
|
| 1725 |
"step": 220
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 0.28,
|
| 1729 |
+
"grad_norm": 0.26953125,
|
| 1730 |
"learning_rate": 4.4871794871794874e-05,
|
| 1731 |
+
"loss": 1.5332,
|
| 1732 |
"step": 221
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 0.28,
|
| 1736 |
+
"grad_norm": 0.236328125,
|
| 1737 |
"learning_rate": 4.358974358974359e-05,
|
| 1738 |
+
"loss": 1.5205,
|
| 1739 |
"step": 222
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 0.29,
|
| 1743 |
+
"grad_norm": 0.224609375,
|
| 1744 |
"learning_rate": 4.230769230769231e-05,
|
| 1745 |
+
"loss": 1.497,
|
| 1746 |
"step": 223
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 0.29,
|
| 1750 |
+
"grad_norm": 0.22265625,
|
| 1751 |
"learning_rate": 4.1025641025641023e-05,
|
| 1752 |
+
"loss": 1.5158,
|
| 1753 |
"step": 224
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 0.29,
|
| 1757 |
+
"grad_norm": 0.2421875,
|
| 1758 |
"learning_rate": 3.974358974358974e-05,
|
| 1759 |
+
"loss": 1.4847,
|
| 1760 |
"step": 225
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 0.29,
|
| 1764 |
+
"grad_norm": 0.244140625,
|
| 1765 |
"learning_rate": 3.846153846153846e-05,
|
| 1766 |
+
"loss": 1.4456,
|
| 1767 |
"step": 226
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 0.29,
|
| 1771 |
+
"grad_norm": 0.228515625,
|
| 1772 |
"learning_rate": 3.717948717948718e-05,
|
| 1773 |
+
"loss": 1.5334,
|
| 1774 |
"step": 227
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 0.29,
|
| 1778 |
+
"grad_norm": 0.25390625,
|
| 1779 |
"learning_rate": 3.58974358974359e-05,
|
| 1780 |
+
"loss": 1.5238,
|
| 1781 |
"step": 228
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 0.29,
|
| 1785 |
+
"grad_norm": 0.2490234375,
|
| 1786 |
"learning_rate": 3.461538461538462e-05,
|
| 1787 |
+
"loss": 1.4388,
|
| 1788 |
"step": 229
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 0.29,
|
| 1792 |
+
"grad_norm": 0.2353515625,
|
| 1793 |
"learning_rate": 3.3333333333333335e-05,
|
| 1794 |
+
"loss": 1.5555,
|
| 1795 |
"step": 230
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 0.29,
|
| 1799 |
+
"eval_loss": 1.5019102096557617,
|
| 1800 |
+
"eval_runtime": 109.1608,
|
| 1801 |
+
"eval_samples_per_second": 45.804,
|
| 1802 |
+
"eval_steps_per_second": 1.438,
|
| 1803 |
"step": 230
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 0.3,
|
| 1807 |
+
"grad_norm": 0.267578125,
|
| 1808 |
"learning_rate": 3.205128205128206e-05,
|
| 1809 |
+
"loss": 1.5535,
|
| 1810 |
"step": 231
|
| 1811 |
},
|
| 1812 |
{
|
| 1813 |
"epoch": 0.3,
|
| 1814 |
+
"grad_norm": 0.240234375,
|
| 1815 |
"learning_rate": 3.0769230769230774e-05,
|
| 1816 |
+
"loss": 1.4322,
|
| 1817 |
"step": 232
|
| 1818 |
},
|
| 1819 |
{
|
| 1820 |
"epoch": 0.3,
|
| 1821 |
+
"grad_norm": 0.2470703125,
|
| 1822 |
"learning_rate": 2.948717948717949e-05,
|
| 1823 |
+
"loss": 1.471,
|
| 1824 |
"step": 233
|
| 1825 |
},
|
| 1826 |
{
|
| 1827 |
"epoch": 0.3,
|
| 1828 |
+
"grad_norm": 0.25,
|
| 1829 |
"learning_rate": 2.8205128205128207e-05,
|
| 1830 |
+
"loss": 1.5444,
|
| 1831 |
"step": 234
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
"epoch": 0.3,
|
| 1835 |
+
"grad_norm": 0.25,
|
| 1836 |
"learning_rate": 2.6923076923076923e-05,
|
| 1837 |
+
"loss": 1.5331,
|
| 1838 |
"step": 235
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
"epoch": 0.3,
|
| 1842 |
+
"grad_norm": 0.236328125,
|
| 1843 |
"learning_rate": 2.564102564102564e-05,
|
| 1844 |
+
"loss": 1.5355,
|
| 1845 |
"step": 236
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 0.3,
|
| 1849 |
+
"grad_norm": 0.244140625,
|
| 1850 |
"learning_rate": 2.435897435897436e-05,
|
| 1851 |
+
"loss": 1.4883,
|
| 1852 |
"step": 237
|
| 1853 |
},
|
| 1854 |
{
|
| 1855 |
"epoch": 0.3,
|
| 1856 |
+
"grad_norm": 0.263671875,
|
| 1857 |
"learning_rate": 2.307692307692308e-05,
|
| 1858 |
+
"loss": 1.5266,
|
| 1859 |
"step": 238
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
"epoch": 0.31,
|
| 1863 |
+
"grad_norm": 0.2451171875,
|
| 1864 |
"learning_rate": 2.1794871794871795e-05,
|
| 1865 |
+
"loss": 1.5576,
|
| 1866 |
"step": 239
|
| 1867 |
},
|
| 1868 |
{
|
| 1869 |
"epoch": 0.31,
|
| 1870 |
+
"grad_norm": 0.259765625,
|
| 1871 |
"learning_rate": 2.0512820512820512e-05,
|
| 1872 |
+
"loss": 1.5615,
|
| 1873 |
"step": 240
|
| 1874 |
},
|
| 1875 |
{
|
| 1876 |
"epoch": 0.31,
|
| 1877 |
+
"eval_loss": 1.5016273260116577,
|
| 1878 |
+
"eval_runtime": 109.191,
|
| 1879 |
+
"eval_samples_per_second": 45.791,
|
| 1880 |
+
"eval_steps_per_second": 1.438,
|
| 1881 |
"step": 240
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 0.31,
|
| 1885 |
+
"grad_norm": 0.23828125,
|
| 1886 |
"learning_rate": 1.923076923076923e-05,
|
| 1887 |
+
"loss": 1.531,
|
| 1888 |
"step": 241
|
| 1889 |
},
|
| 1890 |
{
|
| 1891 |
"epoch": 0.31,
|
| 1892 |
+
"grad_norm": 0.2470703125,
|
| 1893 |
"learning_rate": 1.794871794871795e-05,
|
| 1894 |
+
"loss": 1.4563,
|
| 1895 |
"step": 242
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
"epoch": 0.31,
|
| 1899 |
+
"grad_norm": 0.24609375,
|
| 1900 |
"learning_rate": 1.6666666666666667e-05,
|
| 1901 |
+
"loss": 1.4773,
|
| 1902 |
"step": 243
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 0.31,
|
| 1906 |
+
"grad_norm": 0.2431640625,
|
| 1907 |
"learning_rate": 1.5384615384615387e-05,
|
| 1908 |
+
"loss": 1.4496,
|
| 1909 |
"step": 244
|
| 1910 |
},
|
| 1911 |
{
|
| 1912 |
"epoch": 0.31,
|
| 1913 |
+
"grad_norm": 0.228515625,
|
| 1914 |
"learning_rate": 1.4102564102564104e-05,
|
| 1915 |
+
"loss": 1.5677,
|
| 1916 |
"step": 245
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 0.31,
|
| 1920 |
+
"grad_norm": 0.2578125,
|
| 1921 |
"learning_rate": 1.282051282051282e-05,
|
| 1922 |
+
"loss": 1.4935,
|
| 1923 |
"step": 246
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 0.32,
|
| 1927 |
+
"grad_norm": 0.2216796875,
|
| 1928 |
"learning_rate": 1.153846153846154e-05,
|
| 1929 |
+
"loss": 1.5357,
|
| 1930 |
"step": 247
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 0.32,
|
| 1934 |
+
"grad_norm": 0.259765625,
|
| 1935 |
"learning_rate": 1.0256410256410256e-05,
|
| 1936 |
+
"loss": 1.5693,
|
| 1937 |
"step": 248
|
| 1938 |
},
|
| 1939 |
{
|
| 1940 |
"epoch": 0.32,
|
| 1941 |
+
"grad_norm": 0.271484375,
|
| 1942 |
"learning_rate": 8.974358974358976e-06,
|
| 1943 |
+
"loss": 1.5037,
|
| 1944 |
"step": 249
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 0.32,
|
| 1948 |
+
"grad_norm": 0.236328125,
|
| 1949 |
"learning_rate": 7.692307692307694e-06,
|
| 1950 |
+
"loss": 1.4786,
|
| 1951 |
"step": 250
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 0.32,
|
| 1955 |
+
"eval_loss": 1.501659631729126,
|
| 1956 |
+
"eval_runtime": 109.1682,
|
| 1957 |
+
"eval_samples_per_second": 45.801,
|
| 1958 |
+
"eval_steps_per_second": 1.438,
|
| 1959 |
"step": 250
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 0.32,
|
| 1963 |
+
"grad_norm": 0.2412109375,
|
| 1964 |
"learning_rate": 6.41025641025641e-06,
|
| 1965 |
+
"loss": 1.5624,
|
| 1966 |
"step": 251
|
| 1967 |
},
|
| 1968 |
{
|
| 1969 |
"epoch": 0.32,
|
| 1970 |
+
"grad_norm": 0.232421875,
|
| 1971 |
"learning_rate": 5.128205128205128e-06,
|
| 1972 |
+
"loss": 1.4851,
|
| 1973 |
"step": 252
|
| 1974 |
},
|
| 1975 |
{
|
| 1976 |
"epoch": 0.32,
|
| 1977 |
+
"grad_norm": 0.2451171875,
|
| 1978 |
"learning_rate": 3.846153846153847e-06,
|
| 1979 |
+
"loss": 1.4184,
|
| 1980 |
"step": 253
|
| 1981 |
},
|
| 1982 |
{
|
| 1983 |
"epoch": 0.33,
|
| 1984 |
+
"grad_norm": 0.2353515625,
|
| 1985 |
"learning_rate": 2.564102564102564e-06,
|
| 1986 |
+
"loss": 1.4701,
|
| 1987 |
"step": 254
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 0.33,
|
| 1991 |
+
"grad_norm": 0.244140625,
|
| 1992 |
"learning_rate": 1.282051282051282e-06,
|
| 1993 |
+
"loss": 1.5079,
|
| 1994 |
"step": 255
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 0.33,
|
| 1998 |
+
"grad_norm": 0.2216796875,
|
| 1999 |
"learning_rate": 0.0,
|
| 2000 |
+
"loss": 1.5386,
|
| 2001 |
"step": 256
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 0.33,
|
| 2005 |
"step": 256,
|
| 2006 |
+
"total_flos": 1.8280284932328653e+17,
|
| 2007 |
+
"train_loss": 1.802713230252266,
|
| 2008 |
+
"train_runtime": 3920.872,
|
| 2009 |
+
"train_samples_per_second": 4.179,
|
| 2010 |
+
"train_steps_per_second": 0.065
|
| 2011 |
},
|
| 2012 |
{
|
| 2013 |
"epoch": 0.33,
|
| 2014 |
+
"eval_loss": 1.5016273260116577,
|
| 2015 |
+
"eval_runtime": 109.2744,
|
| 2016 |
+
"eval_samples_per_second": 45.756,
|
| 2017 |
+
"eval_steps_per_second": 1.437,
|
| 2018 |
"step": 256
|
| 2019 |
}
|
| 2020 |
],
|
|
|
|
| 2023 |
"num_input_tokens_seen": 0,
|
| 2024 |
"num_train_epochs": 1,
|
| 2025 |
"save_steps": 10,
|
| 2026 |
+
"total_flos": 1.8280284932328653e+17,
|
| 2027 |
"train_batch_size": 32,
|
| 2028 |
"trial_name": null,
|
| 2029 |
"trial_params": null
|
training_args.bin
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:bbbcb8df15bb2908ec469fd8d946e91474cbd2b7d05aa4e3329efcd3070a15ed
|
| 3 |
+
size 5240
|