Model save
Browse files- README.md +6 -7
- adapter_config.json +5 -1
- adapter_model.safetensors +2 -2
- all_results.json +8 -8
- eval_results.json +4 -4
- mm_projector.bin +1 -1
- train_results.json +4 -4
- trainer_state.json +374 -374
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,11 +2,10 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- generated_from_trainer
|
| 7 |
base_model: mistralai/Mistral-7B-v0.1
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
model-index:
|
| 11 |
- name: tmp
|
| 12 |
results: []
|
|
@@ -17,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# tmp
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 1.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -38,7 +37,7 @@ More information needed
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate:
|
| 42 |
- train_batch_size: 32
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
|
@@ -48,14 +47,14 @@ The following hyperparameters were used during training:
|
|
| 48 |
- total_eval_batch_size: 16
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: cosine
|
| 51 |
-
- lr_scheduler_warmup_ratio: 0.
|
| 52 |
- num_epochs: 1
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
-
| 1.
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
datasets:
|
| 8 |
+
- generator
|
| 9 |
model-index:
|
| 10 |
- name: tmp
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# tmp
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0098
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
- train_batch_size: 32
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
|
|
|
| 47 |
- total_eval_batch_size: 16
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 51 |
- num_epochs: 1
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.0177 | 1.0 | 907 | 1.0098 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -19,9 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
| 22 |
"down_proj",
|
| 23 |
"up_proj",
|
| 24 |
-
"gate_proj"
|
|
|
|
|
|
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM"
|
| 27 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"o_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
"down_proj",
|
| 25 |
"up_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
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:b0ad77b42e5d13440fb676453174ba04bc3d3f30e684a4f2f749df64038744b2
|
| 3 |
+
size 83946192
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 6440,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"train_loss": 1.
|
| 9 |
-
"train_runtime":
|
| 10 |
"train_samples": 58034,
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.0098061561584473,
|
| 4 |
+
"eval_runtime": 480.2819,
|
| 5 |
"eval_samples": 6440,
|
| 6 |
+
"eval_samples_per_second": 13.409,
|
| 7 |
+
"eval_steps_per_second": 0.839,
|
| 8 |
+
"train_loss": 1.0062879709056614,
|
| 9 |
+
"train_runtime": 14623.7103,
|
| 10 |
"train_samples": 58034,
|
| 11 |
+
"train_samples_per_second": 3.968,
|
| 12 |
+
"train_steps_per_second": 0.062
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 6440,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.0098061561584473,
|
| 4 |
+
"eval_runtime": 480.2819,
|
| 5 |
"eval_samples": 6440,
|
| 6 |
+
"eval_samples_per_second": 13.409,
|
| 7 |
+
"eval_steps_per_second": 0.839
|
| 8 |
}
|
mm_projector.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16795126
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c038acdf4f04ada424a48b4442868db8539473c8c209cbfe06568c76a52bc3
|
| 3 |
size 16795126
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 58034,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.0062879709056614,
|
| 4 |
+
"train_runtime": 14623.7103,
|
| 5 |
"train_samples": 58034,
|
| 6 |
+
"train_samples_per_second": 3.968,
|
| 7 |
+
"train_steps_per_second": 0.062
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -10,1112 +10,1112 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.02,
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.02,
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.03,
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.03,
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.04,
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss":
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.04,
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.05,
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.06,
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.06,
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.07,
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.07,
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.08,
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.08,
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.09,
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 1.
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.09,
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.1,
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.1,
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 1.
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.11,
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 100
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.12,
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss":
|
| 141 |
"step": 105
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.12,
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 110
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.13,
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss":
|
| 153 |
"step": 115
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.13,
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 120
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.14,
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 125
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.14,
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 130
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.15,
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 135
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.15,
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 1.
|
| 183 |
"step": 140
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.16,
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 145
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.17,
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 1.
|
| 195 |
"step": 150
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.17,
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 155
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.18,
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 160
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.18,
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 1.
|
| 213 |
"step": 165
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.19,
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 170
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.19,
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 1.
|
| 225 |
"step": 175
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.2,
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 180
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.2,
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 1.
|
| 237 |
"step": 185
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 0.21,
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 1.
|
| 243 |
"step": 190
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.21,
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 1.
|
| 249 |
"step": 195
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.22,
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 1.
|
| 255 |
"step": 200
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.23,
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 1.
|
| 261 |
"step": 205
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.23,
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 210
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.24,
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 1.
|
| 273 |
"step": 215
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.24,
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 1.
|
| 279 |
"step": 220
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.25,
|
| 283 |
-
"learning_rate":
|
| 284 |
-
"loss": 1.
|
| 285 |
"step": 225
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.25,
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss":
|
| 291 |
"step": 230
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.26,
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 235
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.26,
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss":
|
| 303 |
"step": 240
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.27,
|
| 307 |
-
"learning_rate":
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 245
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.28,
|
| 313 |
-
"learning_rate":
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 250
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.28,
|
| 319 |
-
"learning_rate":
|
| 320 |
-
"loss": 1.
|
| 321 |
"step": 255
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.29,
|
| 325 |
-
"learning_rate":
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 260
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.29,
|
| 331 |
-
"learning_rate":
|
| 332 |
-
"loss": 1.
|
| 333 |
"step": 265
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.3,
|
| 337 |
-
"learning_rate":
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 270
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.3,
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 1.
|
| 345 |
"step": 275
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.31,
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 1.
|
| 351 |
"step": 280
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.31,
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss": 1.
|
| 357 |
"step": 285
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.32,
|
| 361 |
-
"learning_rate":
|
| 362 |
-
"loss": 0.
|
| 363 |
"step": 290
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.33,
|
| 367 |
-
"learning_rate":
|
| 368 |
-
"loss": 0.
|
| 369 |
"step": 295
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 0.33,
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss": 0.
|
| 375 |
"step": 300
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 0.34,
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 305
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.34,
|
| 385 |
-
"learning_rate":
|
| 386 |
-
"loss": 1.
|
| 387 |
"step": 310
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.35,
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"loss": 1.
|
| 393 |
"step": 315
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.35,
|
| 397 |
-
"learning_rate":
|
| 398 |
-
"loss": 1.
|
| 399 |
"step": 320
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.36,
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 1.
|
| 405 |
"step": 325
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.36,
|
| 409 |
-
"learning_rate":
|
| 410 |
-
"loss":
|
| 411 |
"step": 330
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 0.37,
|
| 415 |
-
"learning_rate":
|
| 416 |
-
"loss": 1.
|
| 417 |
"step": 335
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.37,
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss": 1.
|
| 423 |
"step": 340
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.38,
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss":
|
| 429 |
"step": 345
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.39,
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 1.
|
| 435 |
"step": 350
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.39,
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss": 1.
|
| 441 |
"step": 355
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.4,
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 1.
|
| 447 |
"step": 360
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.4,
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 365
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.41,
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 1.
|
| 459 |
"step": 370
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.41,
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 1.
|
| 465 |
"step": 375
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.42,
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 380
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.42,
|
| 475 |
-
"learning_rate":
|
| 476 |
-
"loss": 1.
|
| 477 |
"step": 385
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.43,
|
| 481 |
-
"learning_rate":
|
| 482 |
-
"loss": 1.
|
| 483 |
"step": 390
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.44,
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 395
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.44,
|
| 493 |
-
"learning_rate":
|
| 494 |
-
"loss": 0.
|
| 495 |
"step": 400
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 0.45,
|
| 499 |
-
"learning_rate":
|
| 500 |
-
"loss": 1.
|
| 501 |
"step": 405
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 0.45,
|
| 505 |
-
"learning_rate":
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 410
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 0.46,
|
| 511 |
-
"learning_rate":
|
| 512 |
-
"loss": 1.
|
| 513 |
"step": 415
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.46,
|
| 517 |
-
"learning_rate":
|
| 518 |
-
"loss": 1.
|
| 519 |
"step": 420
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.47,
|
| 523 |
-
"learning_rate":
|
| 524 |
-
"loss": 1.
|
| 525 |
"step": 425
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.47,
|
| 529 |
-
"learning_rate":
|
| 530 |
-
"loss": 1.
|
| 531 |
"step": 430
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 0.48,
|
| 535 |
-
"learning_rate":
|
| 536 |
-
"loss": 1.
|
| 537 |
"step": 435
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 0.49,
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 440
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 0.49,
|
| 547 |
-
"learning_rate":
|
| 548 |
-
"loss": 1.
|
| 549 |
"step": 445
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 0.5,
|
| 553 |
-
"learning_rate":
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 450
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.5,
|
| 559 |
-
"learning_rate":
|
| 560 |
-
"loss":
|
| 561 |
"step": 455
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.51,
|
| 565 |
-
"learning_rate":
|
| 566 |
-
"loss": 1.
|
| 567 |
"step": 460
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.51,
|
| 571 |
-
"learning_rate":
|
| 572 |
-
"loss": 1.
|
| 573 |
"step": 465
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.52,
|
| 577 |
-
"learning_rate":
|
| 578 |
-
"loss": 1.
|
| 579 |
"step": 470
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.52,
|
| 583 |
-
"learning_rate":
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 475
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.53,
|
| 589 |
-
"learning_rate":
|
| 590 |
-
"loss":
|
| 591 |
"step": 480
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.53,
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 1.
|
| 597 |
"step": 485
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.54,
|
| 601 |
-
"learning_rate":
|
| 602 |
-
"loss": 1.
|
| 603 |
"step": 490
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.55,
|
| 607 |
-
"learning_rate":
|
| 608 |
-
"loss": 1.
|
| 609 |
"step": 495
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.55,
|
| 613 |
-
"learning_rate":
|
| 614 |
-
"loss": 1.
|
| 615 |
"step": 500
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.56,
|
| 619 |
-
"learning_rate":
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 505
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.56,
|
| 625 |
-
"learning_rate":
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 510
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.57,
|
| 631 |
-
"learning_rate":
|
| 632 |
-
"loss": 1.
|
| 633 |
"step": 515
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.57,
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 1.
|
| 639 |
"step": 520
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.58,
|
| 643 |
-
"learning_rate":
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 525
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 0.58,
|
| 649 |
-
"learning_rate":
|
| 650 |
-
"loss":
|
| 651 |
"step": 530
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 0.59,
|
| 655 |
-
"learning_rate":
|
| 656 |
-
"loss":
|
| 657 |
"step": 535
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.6,
|
| 661 |
-
"learning_rate":
|
| 662 |
-
"loss": 1.
|
| 663 |
"step": 540
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 0.6,
|
| 667 |
-
"learning_rate":
|
| 668 |
-
"loss":
|
| 669 |
"step": 545
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.61,
|
| 673 |
-
"learning_rate":
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 550
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.61,
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 555
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 0.62,
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 560
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 0.62,
|
| 691 |
-
"learning_rate":
|
| 692 |
-
"loss": 1.
|
| 693 |
"step": 565
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 0.63,
|
| 697 |
-
"learning_rate":
|
| 698 |
-
"loss": 1.
|
| 699 |
"step": 570
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.63,
|
| 703 |
-
"learning_rate":
|
| 704 |
-
"loss": 1.
|
| 705 |
"step": 575
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.64,
|
| 709 |
-
"learning_rate": 6.
|
| 710 |
-
"loss": 1.
|
| 711 |
"step": 580
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.64,
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 585
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.65,
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss":
|
| 723 |
"step": 590
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.66,
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 595
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.66,
|
| 733 |
-
"learning_rate":
|
| 734 |
-
"loss": 1.
|
| 735 |
"step": 600
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.67,
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 605
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.67,
|
| 745 |
-
"learning_rate": 5.
|
| 746 |
-
"loss":
|
| 747 |
"step": 610
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.68,
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 1.
|
| 753 |
"step": 615
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.68,
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 1.
|
| 759 |
"step": 620
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.69,
|
| 763 |
-
"learning_rate":
|
| 764 |
-
"loss": 1.
|
| 765 |
"step": 625
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.69,
|
| 769 |
-
"learning_rate":
|
| 770 |
-
"loss": 1.
|
| 771 |
"step": 630
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 0.7,
|
| 775 |
-
"learning_rate":
|
| 776 |
-
"loss": 1.
|
| 777 |
"step": 635
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 0.71,
|
| 781 |
-
"learning_rate": 4.
|
| 782 |
-
"loss": 1.
|
| 783 |
"step": 640
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.71,
|
| 787 |
-
"learning_rate": 4.
|
| 788 |
-
"loss": 1.
|
| 789 |
"step": 645
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.72,
|
| 793 |
-
"learning_rate":
|
| 794 |
-
"loss": 1.
|
| 795 |
"step": 650
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 0.72,
|
| 799 |
-
"learning_rate":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 655
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 0.73,
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss":
|
| 807 |
"step": 660
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 0.73,
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"loss": 1.
|
| 813 |
"step": 665
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 0.74,
|
| 817 |
-
"learning_rate": 3.
|
| 818 |
-
"loss": 1.
|
| 819 |
"step": 670
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 0.74,
|
| 823 |
-
"learning_rate": 3.
|
| 824 |
-
"loss":
|
| 825 |
"step": 675
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 0.75,
|
| 829 |
-
"learning_rate": 3.
|
| 830 |
-
"loss": 0.
|
| 831 |
"step": 680
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.76,
|
| 835 |
-
"learning_rate":
|
| 836 |
-
"loss": 0.
|
| 837 |
"step": 685
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 0.76,
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 1.
|
| 843 |
"step": 690
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.77,
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 695
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.77,
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 1.
|
| 855 |
"step": 700
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.78,
|
| 859 |
-
"learning_rate": 2.
|
| 860 |
-
"loss":
|
| 861 |
"step": 705
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.78,
|
| 865 |
-
"learning_rate": 2.
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 710
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.79,
|
| 871 |
-
"learning_rate": 2.
|
| 872 |
-
"loss": 1.
|
| 873 |
"step": 715
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.79,
|
| 877 |
-
"learning_rate": 2.
|
| 878 |
-
"loss": 1.
|
| 879 |
"step": 720
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.8,
|
| 883 |
-
"learning_rate": 2.
|
| 884 |
-
"loss":
|
| 885 |
"step": 725
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.8,
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 730
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.81,
|
| 895 |
-
"learning_rate":
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 735
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.82,
|
| 901 |
-
"learning_rate": 1.
|
| 902 |
-
"loss":
|
| 903 |
"step": 740
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.82,
|
| 907 |
-
"learning_rate": 1.
|
| 908 |
-
"loss": 0.
|
| 909 |
"step": 745
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.83,
|
| 913 |
-
"learning_rate": 1.
|
| 914 |
-
"loss": 1.
|
| 915 |
"step": 750
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 0.83,
|
| 919 |
-
"learning_rate": 1.
|
| 920 |
-
"loss":
|
| 921 |
"step": 755
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 0.84,
|
| 925 |
-
"learning_rate": 1.
|
| 926 |
-
"loss": 1.
|
| 927 |
"step": 760
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 0.84,
|
| 931 |
-
"learning_rate": 1.
|
| 932 |
-
"loss": 1.
|
| 933 |
"step": 765
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 0.85,
|
| 937 |
-
"learning_rate": 1.
|
| 938 |
-
"loss": 1.
|
| 939 |
"step": 770
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.85,
|
| 943 |
-
"learning_rate": 1.
|
| 944 |
-
"loss": 1.
|
| 945 |
"step": 775
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.86,
|
| 949 |
-
"learning_rate": 1.
|
| 950 |
-
"loss": 1.
|
| 951 |
"step": 780
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 0.87,
|
| 955 |
-
"learning_rate":
|
| 956 |
-
"loss": 1.
|
| 957 |
"step": 785
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 0.87,
|
| 961 |
-
"learning_rate":
|
| 962 |
-
"loss": 0.
|
| 963 |
"step": 790
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 0.88,
|
| 967 |
-
"learning_rate":
|
| 968 |
-
"loss": 1.
|
| 969 |
"step": 795
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 0.88,
|
| 973 |
-
"learning_rate":
|
| 974 |
-
"loss": 0.
|
| 975 |
"step": 800
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 0.89,
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"loss": 1.
|
| 981 |
"step": 805
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.89,
|
| 985 |
-
"learning_rate":
|
| 986 |
-
"loss": 1.
|
| 987 |
"step": 810
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.9,
|
| 991 |
-
"learning_rate":
|
| 992 |
-
"loss": 1.
|
| 993 |
"step": 815
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.9,
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 820
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.91,
|
| 1003 |
-
"learning_rate": 4.
|
| 1004 |
-
"loss": 1.
|
| 1005 |
"step": 825
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.92,
|
| 1009 |
-
"learning_rate":
|
| 1010 |
-
"loss": 1.
|
| 1011 |
"step": 830
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.92,
|
| 1015 |
-
"learning_rate": 3.
|
| 1016 |
-
"loss":
|
| 1017 |
"step": 835
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.93,
|
| 1021 |
-
"learning_rate":
|
| 1022 |
-
"loss": 1.
|
| 1023 |
"step": 840
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.93,
|
| 1027 |
-
"learning_rate": 2.
|
| 1028 |
-
"loss": 0.
|
| 1029 |
"step": 845
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.94,
|
| 1033 |
-
"learning_rate": 2.
|
| 1034 |
-
"loss": 1.
|
| 1035 |
"step": 850
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.94,
|
| 1039 |
-
"learning_rate": 1.
|
| 1040 |
-
"loss": 1.
|
| 1041 |
"step": 855
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.95,
|
| 1045 |
-
"learning_rate": 1.
|
| 1046 |
-
"loss": 1.
|
| 1047 |
"step": 860
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 0.95,
|
| 1051 |
-
"learning_rate": 1.
|
| 1052 |
-
"loss": 0.
|
| 1053 |
"step": 865
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 0.96,
|
| 1057 |
-
"learning_rate":
|
| 1058 |
-
"loss":
|
| 1059 |
"step": 870
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 0.96,
|
| 1063 |
-
"learning_rate":
|
| 1064 |
-
"loss":
|
| 1065 |
"step": 875
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.97,
|
| 1069 |
-
"learning_rate":
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 880
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 0.98,
|
| 1075 |
-
"learning_rate": 3.
|
| 1076 |
-
"loss": 0.
|
| 1077 |
"step": 885
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 0.98,
|
| 1081 |
-
"learning_rate":
|
| 1082 |
-
"loss": 1.
|
| 1083 |
"step": 890
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 0.99,
|
| 1087 |
-
"learning_rate":
|
| 1088 |
-
"loss": 1.
|
| 1089 |
"step": 895
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 0.99,
|
| 1093 |
-
"learning_rate": 3.
|
| 1094 |
-
"loss":
|
| 1095 |
"step": 900
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 1.0,
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
-
"loss": 1.
|
| 1101 |
"step": 905
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 1.0,
|
| 1105 |
-
"eval_loss": 1.
|
| 1106 |
-
"eval_runtime":
|
| 1107 |
-
"eval_samples_per_second":
|
| 1108 |
-
"eval_steps_per_second": 0.
|
| 1109 |
"step": 907
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
"epoch": 1.0,
|
| 1113 |
"step": 907,
|
| 1114 |
-
"total_flos": 5.
|
| 1115 |
-
"train_loss": 1.
|
| 1116 |
-
"train_runtime":
|
| 1117 |
-
"train_samples_per_second":
|
| 1118 |
-
"train_steps_per_second": 0.
|
| 1119 |
}
|
| 1120 |
],
|
| 1121 |
"logging_steps": 5,
|
|
@@ -1123,7 +1123,7 @@
|
|
| 1123 |
"num_input_tokens_seen": 0,
|
| 1124 |
"num_train_epochs": 1,
|
| 1125 |
"save_steps": 100,
|
| 1126 |
-
"total_flos": 5.
|
| 1127 |
"train_batch_size": 32,
|
| 1128 |
"trial_name": null,
|
| 1129 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 7.142857142857143e-07,
|
| 14 |
+
"loss": 1.0707,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 20 |
+
"loss": 1.0883,
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 26 |
+
"loss": 1.0538,
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 32 |
+
"loss": 1.0773,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 38 |
+
"loss": 1.057,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.785714285714286e-05,
|
| 44 |
+
"loss": 1.046,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 1.9999744523980044e-05,
|
| 50 |
+
"loss": 1.0391,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 1.9996870568665825e-05,
|
| 56 |
+
"loss": 1.0144,
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 1.9990804233834707e-05,
|
| 62 |
+
"loss": 1.0181,
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 1.9981547456697224e-05,
|
| 68 |
+
"loss": 1.0307,
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 1.996910319329303e-05,
|
| 74 |
+
"loss": 1.0375,
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 1.995347541754689e-05,
|
| 80 |
+
"loss": 1.0107,
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 1.993466911999968e-05,
|
| 86 |
+
"loss": 1.0326,
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 1.9912690306214705e-05,
|
| 92 |
+
"loss": 1.03,
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.08,
|
| 97 |
+
"learning_rate": 1.988754599485991e-05,
|
| 98 |
+
"loss": 1.0201,
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 1.9859244215466525e-05,
|
| 104 |
+
"loss": 1.0059,
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.09,
|
| 109 |
+
"learning_rate": 1.982779400586497e-05,
|
| 110 |
+
"loss": 1.0111,
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 1.9793205409298696e-05,
|
| 116 |
+
"loss": 0.988,
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.1,
|
| 121 |
+
"learning_rate": 1.975548947121702e-05,
|
| 122 |
+
"loss": 1.0176,
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 1.9714658235747888e-05,
|
| 128 |
+
"loss": 1.0027,
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.11,
|
| 133 |
+
"learning_rate": 1.9670724741851737e-05,
|
| 134 |
+
"loss": 1.0196,
|
| 135 |
"step": 100
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.12,
|
| 139 |
+
"learning_rate": 1.9623703019157637e-05,
|
| 140 |
+
"loss": 1.0006,
|
| 141 |
"step": 105
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.12,
|
| 145 |
+
"learning_rate": 1.9573608083483124e-05,
|
| 146 |
+
"loss": 0.9745,
|
| 147 |
"step": 110
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.13,
|
| 151 |
+
"learning_rate": 1.9520455932039074e-05,
|
| 152 |
+
"loss": 1.0004,
|
| 153 |
"step": 115
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 1.9464263538321176e-05,
|
| 158 |
+
"loss": 1.0367,
|
| 159 |
"step": 120
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.14,
|
| 163 |
+
"learning_rate": 1.9405048846689668e-05,
|
| 164 |
+
"loss": 0.9981,
|
| 165 |
"step": 125
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 1.9342830766639013e-05,
|
| 170 |
+
"loss": 0.9896,
|
| 171 |
"step": 130
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.15,
|
| 175 |
+
"learning_rate": 1.927762916675938e-05,
|
| 176 |
+
"loss": 1.0117,
|
| 177 |
"step": 135
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 1.9209464868391863e-05,
|
| 182 |
+
"loss": 1.0193,
|
| 183 |
"step": 140
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.16,
|
| 187 |
+
"learning_rate": 1.9138359638979423e-05,
|
| 188 |
+
"loss": 0.9941,
|
| 189 |
"step": 145
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.17,
|
| 193 |
+
"learning_rate": 1.9064336185115718e-05,
|
| 194 |
+
"loss": 1.01,
|
| 195 |
"step": 150
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 1.8987418145294045e-05,
|
| 200 |
+
"loss": 0.9847,
|
| 201 |
"step": 155
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.18,
|
| 205 |
+
"learning_rate": 1.8907630082358657e-05,
|
| 206 |
+
"loss": 1.0326,
|
| 207 |
"step": 160
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.18,
|
| 211 |
+
"learning_rate": 1.8824997475660925e-05,
|
| 212 |
+
"loss": 1.0172,
|
| 213 |
"step": 165
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.19,
|
| 217 |
+
"learning_rate": 1.8739546712922805e-05,
|
| 218 |
+
"loss": 0.996,
|
| 219 |
"step": 170
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.19,
|
| 223 |
+
"learning_rate": 1.865130508181026e-05,
|
| 224 |
+
"loss": 1.0048,
|
| 225 |
"step": 175
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.2,
|
| 229 |
+
"learning_rate": 1.8560300761219246e-05,
|
| 230 |
+
"loss": 0.9907,
|
| 231 |
"step": 180
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.2,
|
| 235 |
+
"learning_rate": 1.8466562812277146e-05,
|
| 236 |
+
"loss": 1.0163,
|
| 237 |
"step": 185
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 0.21,
|
| 241 |
+
"learning_rate": 1.8370121169062436e-05,
|
| 242 |
+
"loss": 1.0111,
|
| 243 |
"step": 190
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.21,
|
| 247 |
+
"learning_rate": 1.8271006629045618e-05,
|
| 248 |
+
"loss": 1.0038,
|
| 249 |
"step": 195
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.22,
|
| 253 |
+
"learning_rate": 1.8169250843254397e-05,
|
| 254 |
+
"loss": 1.0324,
|
| 255 |
"step": 200
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.23,
|
| 259 |
+
"learning_rate": 1.8064886306166326e-05,
|
| 260 |
+
"loss": 1.0097,
|
| 261 |
"step": 205
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.23,
|
| 265 |
+
"learning_rate": 1.795794634533208e-05,
|
| 266 |
+
"loss": 0.9967,
|
| 267 |
"step": 210
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.24,
|
| 271 |
+
"learning_rate": 1.7848465110732713e-05,
|
| 272 |
+
"loss": 1.0042,
|
| 273 |
"step": 215
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.24,
|
| 277 |
+
"learning_rate": 1.7736477563874274e-05,
|
| 278 |
+
"loss": 1.0252,
|
| 279 |
"step": 220
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.25,
|
| 283 |
+
"learning_rate": 1.7622019466623265e-05,
|
| 284 |
+
"loss": 1.0163,
|
| 285 |
"step": 225
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 1.7505127369786524e-05,
|
| 290 |
+
"loss": 0.9979,
|
| 291 |
"step": 230
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.26,
|
| 295 |
+
"learning_rate": 1.7385838601439193e-05,
|
| 296 |
+
"loss": 1.0124,
|
| 297 |
"step": 235
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.26,
|
| 301 |
+
"learning_rate": 1.72641912550044e-05,
|
| 302 |
+
"loss": 0.9971,
|
| 303 |
"step": 240
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.27,
|
| 307 |
+
"learning_rate": 1.7140224177088638e-05,
|
| 308 |
+
"loss": 0.9959,
|
| 309 |
"step": 245
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.28,
|
| 313 |
+
"learning_rate": 1.7013976955076534e-05,
|
| 314 |
+
"loss": 0.9944,
|
| 315 |
"step": 250
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.28,
|
| 319 |
+
"learning_rate": 1.6885489904489113e-05,
|
| 320 |
+
"loss": 1.0211,
|
| 321 |
"step": 255
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.29,
|
| 325 |
+
"learning_rate": 1.6754804056109528e-05,
|
| 326 |
+
"loss": 0.9932,
|
| 327 |
"step": 260
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.29,
|
| 331 |
+
"learning_rate": 1.6621961142880368e-05,
|
| 332 |
+
"loss": 1.0241,
|
| 333 |
"step": 265
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.3,
|
| 337 |
+
"learning_rate": 1.6487003586576755e-05,
|
| 338 |
+
"loss": 0.9861,
|
| 339 |
"step": 270
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.3,
|
| 343 |
+
"learning_rate": 1.6349974484259452e-05,
|
| 344 |
+
"loss": 1.0314,
|
| 345 |
"step": 275
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.31,
|
| 349 |
+
"learning_rate": 1.6210917594512355e-05,
|
| 350 |
+
"loss": 1.0052,
|
| 351 |
"step": 280
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.31,
|
| 355 |
+
"learning_rate": 1.6069877323468713e-05,
|
| 356 |
+
"loss": 1.0184,
|
| 357 |
"step": 285
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.32,
|
| 361 |
+
"learning_rate": 1.5926898710630562e-05,
|
| 362 |
+
"loss": 0.9924,
|
| 363 |
"step": 290
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.33,
|
| 367 |
+
"learning_rate": 1.5782027414485906e-05,
|
| 368 |
+
"loss": 0.9744,
|
| 369 |
"step": 295
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 0.33,
|
| 373 |
+
"learning_rate": 1.5635309697928244e-05,
|
| 374 |
+
"loss": 0.9718,
|
| 375 |
"step": 300
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 0.34,
|
| 379 |
+
"learning_rate": 1.5486792413483057e-05,
|
| 380 |
+
"loss": 0.9897,
|
| 381 |
"step": 305
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.34,
|
| 385 |
+
"learning_rate": 1.5336522988346047e-05,
|
| 386 |
+
"loss": 1.0158,
|
| 387 |
"step": 310
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.35,
|
| 391 |
+
"learning_rate": 1.5184549409237806e-05,
|
| 392 |
+
"loss": 1.0233,
|
| 393 |
"step": 315
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.35,
|
| 397 |
+
"learning_rate": 1.503092020707985e-05,
|
| 398 |
+
"loss": 1.0142,
|
| 399 |
"step": 320
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.36,
|
| 403 |
+
"learning_rate": 1.4875684441496883e-05,
|
| 404 |
+
"loss": 1.0037,
|
| 405 |
"step": 325
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.36,
|
| 409 |
+
"learning_rate": 1.4718891685150151e-05,
|
| 410 |
+
"loss": 0.9973,
|
| 411 |
"step": 330
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 0.37,
|
| 415 |
+
"learning_rate": 1.456059200790706e-05,
|
| 416 |
+
"loss": 1.0046,
|
| 417 |
"step": 335
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.37,
|
| 421 |
+
"learning_rate": 1.4400835960851938e-05,
|
| 422 |
+
"loss": 1.0032,
|
| 423 |
"step": 340
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.38,
|
| 427 |
+
"learning_rate": 1.4239674560143168e-05,
|
| 428 |
+
"loss": 0.9965,
|
| 429 |
"step": 345
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.39,
|
| 433 |
+
"learning_rate": 1.407715927072181e-05,
|
| 434 |
+
"loss": 1.0034,
|
| 435 |
"step": 350
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.39,
|
| 439 |
+
"learning_rate": 1.3913341989876876e-05,
|
| 440 |
+
"loss": 1.0264,
|
| 441 |
"step": 355
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.4,
|
| 445 |
+
"learning_rate": 1.3748275030672569e-05,
|
| 446 |
+
"loss": 1.0017,
|
| 447 |
"step": 360
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.4,
|
| 451 |
+
"learning_rate": 1.3582011105242734e-05,
|
| 452 |
+
"loss": 0.9878,
|
| 453 |
"step": 365
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.41,
|
| 457 |
+
"learning_rate": 1.341460330795789e-05,
|
| 458 |
+
"loss": 1.0051,
|
| 459 |
"step": 370
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.41,
|
| 463 |
+
"learning_rate": 1.3246105098470166e-05,
|
| 464 |
+
"loss": 1.0036,
|
| 465 |
"step": 375
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.42,
|
| 469 |
+
"learning_rate": 1.3076570284641625e-05,
|
| 470 |
+
"loss": 0.9857,
|
| 471 |
"step": 380
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.42,
|
| 475 |
+
"learning_rate": 1.2906053005361366e-05,
|
| 476 |
+
"loss": 1.0268,
|
| 477 |
"step": 385
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.43,
|
| 481 |
+
"learning_rate": 1.273460771325693e-05,
|
| 482 |
+
"loss": 1.0209,
|
| 483 |
"step": 390
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.44,
|
| 487 |
+
"learning_rate": 1.2562289157305514e-05,
|
| 488 |
+
"loss": 0.9882,
|
| 489 |
"step": 395
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.44,
|
| 493 |
+
"learning_rate": 1.238915236535054e-05,
|
| 494 |
+
"loss": 0.9885,
|
| 495 |
"step": 400
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 0.45,
|
| 499 |
+
"learning_rate": 1.2215252626529197e-05,
|
| 500 |
+
"loss": 1.0106,
|
| 501 |
"step": 405
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 0.45,
|
| 505 |
+
"learning_rate": 1.2040645473616496e-05,
|
| 506 |
+
"loss": 0.9831,
|
| 507 |
"step": 410
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 0.46,
|
| 511 |
+
"learning_rate": 1.1865386665291591e-05,
|
| 512 |
+
"loss": 1.0113,
|
| 513 |
"step": 415
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.46,
|
| 517 |
+
"learning_rate": 1.1689532168331877e-05,
|
| 518 |
+
"loss": 1.001,
|
| 519 |
"step": 420
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.47,
|
| 523 |
+
"learning_rate": 1.151313813974071e-05,
|
| 524 |
+
"loss": 1.0121,
|
| 525 |
"step": 425
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.47,
|
| 529 |
+
"learning_rate": 1.1336260908814335e-05,
|
| 530 |
+
"loss": 1.0086,
|
| 531 |
"step": 430
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 0.48,
|
| 535 |
+
"learning_rate": 1.1158956959153808e-05,
|
| 536 |
+
"loss": 1.0244,
|
| 537 |
"step": 435
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 0.49,
|
| 541 |
+
"learning_rate": 1.0981282910627646e-05,
|
| 542 |
+
"loss": 0.992,
|
| 543 |
"step": 440
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 0.49,
|
| 547 |
+
"learning_rate": 1.0803295501290954e-05,
|
| 548 |
+
"loss": 1.0017,
|
| 549 |
"step": 445
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 0.5,
|
| 553 |
+
"learning_rate": 1.062505156926681e-05,
|
| 554 |
+
"loss": 0.9844,
|
| 555 |
"step": 450
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.5,
|
| 559 |
+
"learning_rate": 1.0446608034595718e-05,
|
| 560 |
+
"loss": 0.9988,
|
| 561 |
"step": 455
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.51,
|
| 565 |
+
"learning_rate": 1.0268021881058858e-05,
|
| 566 |
+
"loss": 1.01,
|
| 567 |
"step": 460
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.51,
|
| 571 |
+
"learning_rate": 1.0089350137981022e-05,
|
| 572 |
+
"loss": 1.0094,
|
| 573 |
"step": 465
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.52,
|
| 577 |
+
"learning_rate": 9.910649862018981e-06,
|
| 578 |
+
"loss": 1.0195,
|
| 579 |
"step": 470
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.52,
|
| 583 |
+
"learning_rate": 9.731978118941143e-06,
|
| 584 |
+
"loss": 0.9931,
|
| 585 |
"step": 475
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.53,
|
| 589 |
+
"learning_rate": 9.553391965404287e-06,
|
| 590 |
+
"loss": 0.9998,
|
| 591 |
"step": 480
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.53,
|
| 595 |
+
"learning_rate": 9.374948430733191e-06,
|
| 596 |
+
"loss": 1.0168,
|
| 597 |
"step": 485
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.54,
|
| 601 |
+
"learning_rate": 9.196704498709049e-06,
|
| 602 |
+
"loss": 1.0121,
|
| 603 |
"step": 490
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.55,
|
| 607 |
+
"learning_rate": 9.018717089372356e-06,
|
| 608 |
+
"loss": 1.0011,
|
| 609 |
"step": 495
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.55,
|
| 613 |
+
"learning_rate": 8.841043040846192e-06,
|
| 614 |
+
"loss": 1.0001,
|
| 615 |
"step": 500
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.56,
|
| 619 |
+
"learning_rate": 8.663739091185668e-06,
|
| 620 |
+
"loss": 0.9908,
|
| 621 |
"step": 505
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.56,
|
| 625 |
+
"learning_rate": 8.486861860259294e-06,
|
| 626 |
+
"loss": 0.9903,
|
| 627 |
"step": 510
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.57,
|
| 631 |
+
"learning_rate": 8.310467831668128e-06,
|
| 632 |
+
"loss": 1.0138,
|
| 633 |
"step": 515
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.57,
|
| 637 |
+
"learning_rate": 8.134613334708412e-06,
|
| 638 |
+
"loss": 1.0015,
|
| 639 |
"step": 520
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.58,
|
| 643 |
+
"learning_rate": 7.959354526383502e-06,
|
| 644 |
+
"loss": 0.9801,
|
| 645 |
"step": 525
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 0.58,
|
| 649 |
+
"learning_rate": 7.784747373470806e-06,
|
| 650 |
+
"loss": 0.9955,
|
| 651 |
"step": 530
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 0.59,
|
| 655 |
+
"learning_rate": 7.610847634649459e-06,
|
| 656 |
+
"loss": 0.9947,
|
| 657 |
"step": 535
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.6,
|
| 661 |
+
"learning_rate": 7.43771084269449e-06,
|
| 662 |
+
"loss": 1.0037,
|
| 663 |
"step": 540
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 0.6,
|
| 667 |
+
"learning_rate": 7.2653922867430725e-06,
|
| 668 |
+
"loss": 0.9997,
|
| 669 |
"step": 545
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.61,
|
| 673 |
+
"learning_rate": 7.093946994638638e-06,
|
| 674 |
+
"loss": 0.9735,
|
| 675 |
"step": 550
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.61,
|
| 679 |
+
"learning_rate": 6.923429715358377e-06,
|
| 680 |
+
"loss": 0.9877,
|
| 681 |
"step": 555
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 0.62,
|
| 685 |
+
"learning_rate": 6.753894901529834e-06,
|
| 686 |
+
"loss": 0.9884,
|
| 687 |
"step": 560
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 0.62,
|
| 691 |
+
"learning_rate": 6.585396692042113e-06,
|
| 692 |
+
"loss": 1.0122,
|
| 693 |
"step": 565
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 0.63,
|
| 697 |
+
"learning_rate": 6.417988894757267e-06,
|
| 698 |
+
"loss": 1.0112,
|
| 699 |
"step": 570
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.63,
|
| 703 |
+
"learning_rate": 6.251724969327435e-06,
|
| 704 |
+
"loss": 1.0007,
|
| 705 |
"step": 575
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.64,
|
| 709 |
+
"learning_rate": 6.086658010123125e-06,
|
| 710 |
+
"loss": 1.0037,
|
| 711 |
"step": 580
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.64,
|
| 715 |
+
"learning_rate": 5.9228407292781945e-06,
|
| 716 |
+
"loss": 0.9924,
|
| 717 |
"step": 585
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.65,
|
| 721 |
+
"learning_rate": 5.760325439856833e-06,
|
| 722 |
+
"loss": 0.9994,
|
| 723 |
"step": 590
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.66,
|
| 727 |
+
"learning_rate": 5.599164039148066e-06,
|
| 728 |
+
"loss": 0.9928,
|
| 729 |
"step": 595
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.66,
|
| 733 |
+
"learning_rate": 5.4394079920929425e-06,
|
| 734 |
+
"loss": 1.023,
|
| 735 |
"step": 600
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.67,
|
| 739 |
+
"learning_rate": 5.281108314849851e-06,
|
| 740 |
+
"loss": 0.9677,
|
| 741 |
"step": 605
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.67,
|
| 745 |
+
"learning_rate": 5.124315558503122e-06,
|
| 746 |
+
"loss": 0.9957,
|
| 747 |
"step": 610
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.68,
|
| 751 |
+
"learning_rate": 4.96907979292015e-06,
|
| 752 |
+
"loss": 1.013,
|
| 753 |
"step": 615
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.68,
|
| 757 |
+
"learning_rate": 4.815450590762203e-06,
|
| 758 |
+
"loss": 1.0111,
|
| 759 |
"step": 620
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.69,
|
| 763 |
+
"learning_rate": 4.663477011653955e-06,
|
| 764 |
+
"loss": 1.0065,
|
| 765 |
"step": 625
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.69,
|
| 769 |
+
"learning_rate": 4.513207586516943e-06,
|
| 770 |
+
"loss": 1.021,
|
| 771 |
"step": 630
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 0.7,
|
| 775 |
+
"learning_rate": 4.36469030207176e-06,
|
| 776 |
+
"loss": 1.0109,
|
| 777 |
"step": 635
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 0.71,
|
| 781 |
+
"learning_rate": 4.217972585514095e-06,
|
| 782 |
+
"loss": 1.0366,
|
| 783 |
"step": 640
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.71,
|
| 787 |
+
"learning_rate": 4.0731012893694435e-06,
|
| 788 |
+
"loss": 1.0129,
|
| 789 |
"step": 645
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.72,
|
| 793 |
+
"learning_rate": 3.930122676531287e-06,
|
| 794 |
+
"loss": 1.0044,
|
| 795 |
"step": 650
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 0.72,
|
| 799 |
+
"learning_rate": 3.7890824054876452e-06,
|
| 800 |
+
"loss": 0.9931,
|
| 801 |
"step": 655
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 0.73,
|
| 805 |
+
"learning_rate": 3.6500255157405504e-06,
|
| 806 |
+
"loss": 0.9962,
|
| 807 |
"step": 660
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 0.73,
|
| 811 |
+
"learning_rate": 3.5129964134232464e-06,
|
| 812 |
+
"loss": 1.006,
|
| 813 |
"step": 665
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 0.74,
|
| 817 |
+
"learning_rate": 3.378038857119632e-06,
|
| 818 |
+
"loss": 1.0132,
|
| 819 |
"step": 670
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 0.74,
|
| 823 |
+
"learning_rate": 3.2451959438904735e-06,
|
| 824 |
+
"loss": 0.9996,
|
| 825 |
"step": 675
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 0.75,
|
| 829 |
+
"learning_rate": 3.11451009551089e-06,
|
| 830 |
+
"loss": 0.9911,
|
| 831 |
"step": 680
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.76,
|
| 835 |
+
"learning_rate": 2.9860230449234705e-06,
|
| 836 |
+
"loss": 0.9906,
|
| 837 |
"step": 685
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 0.76,
|
| 841 |
+
"learning_rate": 2.859775822911366e-06,
|
| 842 |
+
"loss": 1.0027,
|
| 843 |
"step": 690
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.77,
|
| 847 |
+
"learning_rate": 2.7358087449955996e-06,
|
| 848 |
+
"loss": 0.988,
|
| 849 |
"step": 695
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.77,
|
| 853 |
+
"learning_rate": 2.6141613985608093e-06,
|
| 854 |
+
"loss": 1.0035,
|
| 855 |
"step": 700
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.78,
|
| 859 |
+
"learning_rate": 2.494872630213476e-06,
|
| 860 |
+
"loss": 0.9979,
|
| 861 |
"step": 705
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.78,
|
| 865 |
+
"learning_rate": 2.3779805333767403e-06,
|
| 866 |
+
"loss": 0.99,
|
| 867 |
"step": 710
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.79,
|
| 871 |
+
"learning_rate": 2.263522436125729e-06,
|
| 872 |
+
"loss": 1.0214,
|
| 873 |
"step": 715
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.79,
|
| 877 |
+
"learning_rate": 2.151534889267287e-06,
|
| 878 |
+
"loss": 1.0037,
|
| 879 |
"step": 720
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.8,
|
| 883 |
+
"learning_rate": 2.042053654667925e-06,
|
| 884 |
+
"loss": 0.9984,
|
| 885 |
"step": 725
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.8,
|
| 889 |
+
"learning_rate": 1.9351136938336777e-06,
|
| 890 |
+
"loss": 0.994,
|
| 891 |
"step": 730
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.81,
|
| 895 |
+
"learning_rate": 1.830749156745607e-06,
|
| 896 |
+
"loss": 0.989,
|
| 897 |
"step": 735
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.82,
|
| 901 |
+
"learning_rate": 1.7289933709543848e-06,
|
| 902 |
+
"loss": 0.9995,
|
| 903 |
"step": 740
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.82,
|
| 907 |
+
"learning_rate": 1.6298788309375646e-06,
|
| 908 |
+
"loss": 0.9884,
|
| 909 |
"step": 745
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.83,
|
| 913 |
+
"learning_rate": 1.5334371877228604e-06,
|
| 914 |
+
"loss": 1.0202,
|
| 915 |
"step": 750
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 0.83,
|
| 919 |
+
"learning_rate": 1.4396992387807574e-06,
|
| 920 |
+
"loss": 0.9982,
|
| 921 |
"step": 755
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 0.84,
|
| 925 |
+
"learning_rate": 1.3486949181897435e-06,
|
| 926 |
+
"loss": 1.0206,
|
| 927 |
"step": 760
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 0.84,
|
| 931 |
+
"learning_rate": 1.2604532870771968e-06,
|
| 932 |
+
"loss": 1.0057,
|
| 933 |
"step": 765
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 0.85,
|
| 937 |
+
"learning_rate": 1.1750025243390783e-06,
|
| 938 |
+
"loss": 1.0007,
|
| 939 |
"step": 770
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.85,
|
| 943 |
+
"learning_rate": 1.092369917641345e-06,
|
| 944 |
+
"loss": 1.0193,
|
| 945 |
"step": 775
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.86,
|
| 949 |
+
"learning_rate": 1.0125818547059584e-06,
|
| 950 |
+
"loss": 1.0146,
|
| 951 |
"step": 780
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 0.87,
|
| 955 |
+
"learning_rate": 9.356638148842856e-07,
|
| 956 |
+
"loss": 1.0104,
|
| 957 |
"step": 785
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 0.87,
|
| 961 |
+
"learning_rate": 8.616403610205814e-07,
|
| 962 |
+
"loss": 0.982,
|
| 963 |
"step": 790
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 0.88,
|
| 967 |
+
"learning_rate": 7.905351316081377e-07,
|
| 968 |
+
"loss": 1.0158,
|
| 969 |
"step": 795
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 0.88,
|
| 973 |
+
"learning_rate": 7.223708332406187e-07,
|
| 974 |
+
"loss": 0.9883,
|
| 975 |
"step": 800
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 0.89,
|
| 979 |
+
"learning_rate": 6.571692333609892e-07,
|
| 980 |
+
"loss": 1.0272,
|
| 981 |
"step": 805
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.89,
|
| 985 |
+
"learning_rate": 5.949511533103336e-07,
|
| 986 |
+
"loss": 1.0191,
|
| 987 |
"step": 810
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.9,
|
| 991 |
+
"learning_rate": 5.357364616788263e-07,
|
| 992 |
+
"loss": 1.0136,
|
| 993 |
"step": 815
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.9,
|
| 997 |
+
"learning_rate": 4.795440679609298e-07,
|
| 998 |
+
"loss": 0.9857,
|
| 999 |
"step": 820
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.91,
|
| 1003 |
+
"learning_rate": 4.263919165168762e-07,
|
| 1004 |
+
"loss": 1.0191,
|
| 1005 |
"step": 825
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.92,
|
| 1009 |
+
"learning_rate": 3.7629698084236665e-07,
|
| 1010 |
+
"loss": 1.0163,
|
| 1011 |
"step": 830
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.92,
|
| 1015 |
+
"learning_rate": 3.29275258148265e-07,
|
| 1016 |
+
"loss": 0.9955,
|
| 1017 |
"step": 835
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.93,
|
| 1021 |
+
"learning_rate": 2.8534176425211166e-07,
|
| 1022 |
+
"loss": 1.0113,
|
| 1023 |
"step": 840
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.93,
|
| 1027 |
+
"learning_rate": 2.44510528782983e-07,
|
| 1028 |
+
"loss": 0.9853,
|
| 1029 |
"step": 845
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.94,
|
| 1033 |
+
"learning_rate": 2.0679459070130693e-07,
|
| 1034 |
+
"loss": 1.0027,
|
| 1035 |
"step": 850
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.94,
|
| 1039 |
+
"learning_rate": 1.722059941350329e-07,
|
| 1040 |
+
"loss": 1.0057,
|
| 1041 |
"step": 855
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.95,
|
| 1045 |
+
"learning_rate": 1.4075578453347504e-07,
|
| 1046 |
+
"loss": 1.007,
|
| 1047 |
"step": 860
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 0.95,
|
| 1051 |
+
"learning_rate": 1.1245400514009352e-07,
|
| 1052 |
+
"loss": 0.9815,
|
| 1053 |
"step": 865
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 0.96,
|
| 1057 |
+
"learning_rate": 8.730969378529575e-08,
|
| 1058 |
+
"loss": 0.9968,
|
| 1059 |
"step": 870
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 0.96,
|
| 1063 |
+
"learning_rate": 6.533088000032273e-08,
|
| 1064 |
+
"loss": 0.9971,
|
| 1065 |
"step": 875
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.97,
|
| 1069 |
+
"learning_rate": 4.652458245311242e-08,
|
| 1070 |
+
"loss": 0.9909,
|
| 1071 |
"step": 880
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 0.98,
|
| 1075 |
+
"learning_rate": 3.089680670697148e-08,
|
| 1076 |
+
"loss": 0.9916,
|
| 1077 |
"step": 885
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 0.98,
|
| 1081 |
+
"learning_rate": 1.8452543302776016e-08,
|
| 1082 |
+
"loss": 1.0153,
|
| 1083 |
"step": 890
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 0.99,
|
| 1087 |
+
"learning_rate": 9.195766165295272e-09,
|
| 1088 |
+
"loss": 1.01,
|
| 1089 |
"step": 895
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 0.99,
|
| 1093 |
+
"learning_rate": 3.129431334175648e-09,
|
| 1094 |
+
"loss": 0.9951,
|
| 1095 |
"step": 900
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 1.0,
|
| 1099 |
+
"learning_rate": 2.5547601995912216e-10,
|
| 1100 |
+
"loss": 1.0177,
|
| 1101 |
"step": 905
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 1.0,
|
| 1105 |
+
"eval_loss": 1.0098061561584473,
|
| 1106 |
+
"eval_runtime": 480.371,
|
| 1107 |
+
"eval_samples_per_second": 13.406,
|
| 1108 |
+
"eval_steps_per_second": 0.839,
|
| 1109 |
"step": 907
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
"epoch": 1.0,
|
| 1113 |
"step": 907,
|
| 1114 |
+
"total_flos": 5.321288023160127e+18,
|
| 1115 |
+
"train_loss": 1.0062879709056614,
|
| 1116 |
+
"train_runtime": 14623.7103,
|
| 1117 |
+
"train_samples_per_second": 3.968,
|
| 1118 |
+
"train_steps_per_second": 0.062
|
| 1119 |
}
|
| 1120 |
],
|
| 1121 |
"logging_steps": 5,
|
|
|
|
| 1123 |
"num_input_tokens_seen": 0,
|
| 1124 |
"num_train_epochs": 1,
|
| 1125 |
"save_steps": 100,
|
| 1126 |
+
"total_flos": 5.321288023160127e+18,
|
| 1127 |
"train_batch_size": 32,
|
| 1128 |
"trial_name": null,
|
| 1129 |
"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 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:625e24da9ccb9aabc6f68ca9c127cb0d58ea844c14e98bf605e748cc9d6b1bd3
|
| 3 |
size 4792
|