Model save
Browse files- README.md +7 -15
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- num_examples=100/llava-v1.5-13b_1.0/adapter_config.json +3 -3
- num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors +1 -1
- num_examples=100/llava-v1.5-13b_1.0/training_args.bin +1 -1
- trainer_state.json +355 -1195
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,27 +1,19 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
tags:
|
| 4 |
-
- liuhaotian/llava-v1.5-13b_10.0
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: liuhaotian/llava-v1.5-13b
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [liuhaotian/llava-v1.5-
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- eval_loss: 0.0004
|
| 20 |
-
- eval_runtime: 27.6221
|
| 21 |
-
- eval_samples_per_second: 15.386
|
| 22 |
-
- eval_steps_per_second: 0.507
|
| 23 |
-
- epoch: 9.0
|
| 24 |
-
- step: 126
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -45,13 +37,13 @@ The following hyperparameters were used during training:
|
|
| 45 |
- eval_batch_size: 4
|
| 46 |
- seed: 42
|
| 47 |
- distributed_type: multi-GPU
|
| 48 |
-
- num_devices:
|
| 49 |
-
- total_train_batch_size:
|
| 50 |
-
- total_eval_batch_size:
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: cosine
|
| 53 |
- lr_scheduler_warmup_ratio: 0.03
|
| 54 |
-
- num_epochs:
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
base_model: liuhaotian/llava-v1.5-13b
|
| 6 |
model-index:
|
| 7 |
+
- name: llava_13b_exact_location_name_synthetic
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# llava_13b_exact_location_name_synthetic
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 37 |
- eval_batch_size: 4
|
| 38 |
- seed: 42
|
| 39 |
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 4
|
| 41 |
+
- total_train_batch_size: 16
|
| 42 |
+
- total_eval_batch_size: 16
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.03
|
| 46 |
+
- num_epochs: 20.0
|
| 47 |
|
| 48 |
### Framework versions
|
| 49 |
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"k_proj",
|
|
|
|
| 24 |
"v_proj",
|
| 25 |
-
"q_proj",
|
| 26 |
"down_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
"v_proj",
|
|
|
|
| 27 |
"down_proj",
|
|
|
|
| 28 |
"o_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1001466944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3e154e3e8fb9c55fc0612cde2e1743fc1b2ee777c5ec1c8d7b454f88057371
|
| 3 |
size 1001466944
|
num_examples=100/llava-v1.5-13b_1.0/adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"k_proj",
|
|
|
|
| 24 |
"v_proj",
|
| 25 |
-
"q_proj",
|
| 26 |
"down_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
"v_proj",
|
|
|
|
| 27 |
"down_proj",
|
|
|
|
| 28 |
"o_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1001466944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3e154e3e8fb9c55fc0612cde2e1743fc1b2ee777c5ec1c8d7b454f88057371
|
| 3 |
size 1001466944
|
num_examples=100/llava-v1.5-13b_1.0/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa90b394534132b7b403551766766cdfe27216265cc6d0e380d159dcb58549e3
|
| 3 |
size 6840
|
trainer_state.json
CHANGED
|
@@ -3,1787 +3,947 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss":
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
"learning_rate": 0.0002,
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
"learning_rate": 0.0002,
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
"learning_rate": 0.0002,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
"learning_rate": 0.0002,
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
"learning_rate": 0.0002,
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
"learning_rate": 0.0002,
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
"learning_rate": 0.0002,
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
"learning_rate": 0.0002,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
"learning_rate": 0.0002,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
"learning_rate": 0.0002,
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
"learning_rate": 0.0002,
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
"learning_rate": 0.0002,
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
"learning_rate": 0.0002,
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
"learning_rate": 0.0002,
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
"learning_rate": 0.0002,
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"eval_loss": 0.
|
| 182 |
-
"eval_runtime":
|
| 183 |
-
"eval_samples_per_second": 15.
|
| 184 |
"eval_steps_per_second": 0.509,
|
| 185 |
"step": 28
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch":
|
| 189 |
"learning_rate": 0.0002,
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 29
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
"learning_rate": 0.0002,
|
| 196 |
-
"loss": 0.
|
| 197 |
"step": 30
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch":
|
| 201 |
"learning_rate": 0.0002,
|
| 202 |
-
"loss": 0.
|
| 203 |
"step": 31
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
"learning_rate": 0.0002,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 32
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
"learning_rate": 0.0002,
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 33
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
"learning_rate": 0.0002,
|
| 220 |
-
"loss": 0.
|
| 221 |
"step": 34
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
"learning_rate": 0.0002,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 35
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch":
|
| 231 |
"learning_rate": 0.0002,
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 36
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
"learning_rate": 0.0002,
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 37
|
| 240 |
},
|
| 241 |
{
|
| 242 |
-
"epoch":
|
| 243 |
"learning_rate": 0.0002,
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 38
|
| 246 |
},
|
| 247 |
{
|
| 248 |
-
"epoch":
|
| 249 |
"learning_rate": 0.0002,
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 39
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch":
|
| 255 |
"learning_rate": 0.0002,
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 40
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"epoch":
|
| 261 |
"learning_rate": 0.0002,
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 41
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
"learning_rate": 0.0002,
|
| 268 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 269 |
"step": 42
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch":
|
| 273 |
"learning_rate": 0.0002,
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 43
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
"learning_rate": 0.0002,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 44
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
"learning_rate": 0.0002,
|
| 286 |
-
"loss": 0.
|
| 287 |
"step": 45
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"epoch":
|
| 291 |
"learning_rate": 0.0002,
|
| 292 |
-
"loss": 0.
|
| 293 |
"step": 46
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch":
|
| 297 |
"learning_rate": 0.0002,
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 47
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch":
|
| 303 |
"learning_rate": 0.0002,
|
| 304 |
-
"loss": 0.
|
| 305 |
"step": 48
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch":
|
| 309 |
"learning_rate": 0.0002,
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 49
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch":
|
| 315 |
"learning_rate": 0.0002,
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 50
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
"learning_rate": 0.0002,
|
| 322 |
-
"loss": 0.
|
| 323 |
"step": 51
|
| 324 |
},
|
| 325 |
{
|
| 326 |
-
"epoch":
|
| 327 |
"learning_rate": 0.0002,
|
| 328 |
-
"loss": 0.
|
| 329 |
"step": 52
|
| 330 |
},
|
| 331 |
{
|
| 332 |
-
"epoch":
|
| 333 |
"learning_rate": 0.0002,
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 53
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch":
|
| 339 |
"learning_rate": 0.0002,
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 54
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"epoch":
|
| 345 |
"learning_rate": 0.0002,
|
| 346 |
-
"loss": 0.
|
| 347 |
"step": 55
|
| 348 |
},
|
| 349 |
{
|
| 350 |
-
"epoch":
|
| 351 |
"learning_rate": 0.0002,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 56
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch":
|
| 357 |
-
"eval_loss": 0.
|
| 358 |
-
"eval_runtime":
|
| 359 |
-
"eval_samples_per_second": 15.
|
| 360 |
-
"eval_steps_per_second": 0.
|
| 361 |
"step": 56
|
| 362 |
},
|
| 363 |
{
|
| 364 |
-
"epoch":
|
| 365 |
"learning_rate": 0.0002,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 57
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch":
|
| 371 |
"learning_rate": 0.0002,
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 58
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch":
|
| 377 |
"learning_rate": 0.0002,
|
| 378 |
-
"loss": 0.
|
| 379 |
"step": 59
|
| 380 |
},
|
| 381 |
{
|
| 382 |
-
"epoch":
|
| 383 |
"learning_rate": 0.0002,
|
| 384 |
-
"loss": 0.
|
| 385 |
"step": 60
|
| 386 |
},
|
| 387 |
{
|
| 388 |
-
"epoch":
|
| 389 |
"learning_rate": 0.0002,
|
| 390 |
-
"loss": 0.
|
| 391 |
"step": 61
|
| 392 |
},
|
| 393 |
{
|
| 394 |
-
"epoch":
|
| 395 |
"learning_rate": 0.0002,
|
| 396 |
-
"loss": 0.
|
| 397 |
"step": 62
|
| 398 |
},
|
| 399 |
{
|
| 400 |
-
"epoch":
|
| 401 |
"learning_rate": 0.0002,
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 63
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch":
|
| 407 |
"learning_rate": 0.0002,
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 64
|
| 410 |
},
|
| 411 |
{
|
| 412 |
-
"epoch":
|
| 413 |
"learning_rate": 0.0002,
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 65
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
"learning_rate": 0.0002,
|
| 420 |
-
"loss": 0.
|
| 421 |
"step": 66
|
| 422 |
},
|
| 423 |
{
|
| 424 |
-
"epoch":
|
| 425 |
"learning_rate": 0.0002,
|
| 426 |
-
"loss": 0.
|
| 427 |
"step": 67
|
| 428 |
},
|
| 429 |
{
|
| 430 |
-
"epoch":
|
| 431 |
"learning_rate": 0.0002,
|
| 432 |
-
"loss": 0.
|
| 433 |
"step": 68
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch":
|
| 437 |
"learning_rate": 0.0002,
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 69
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch":
|
| 443 |
"learning_rate": 0.0002,
|
| 444 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 445 |
"step": 70
|
| 446 |
},
|
| 447 |
{
|
| 448 |
-
"epoch":
|
| 449 |
"learning_rate": 0.0002,
|
| 450 |
-
"loss": 0.
|
| 451 |
"step": 71
|
| 452 |
},
|
| 453 |
{
|
| 454 |
-
"epoch":
|
| 455 |
"learning_rate": 0.0002,
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 72
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch":
|
| 461 |
"learning_rate": 0.0002,
|
| 462 |
-
"loss": 0.
|
| 463 |
"step": 73
|
| 464 |
},
|
| 465 |
{
|
| 466 |
-
"epoch":
|
| 467 |
"learning_rate": 0.0002,
|
| 468 |
-
"loss": 0.
|
| 469 |
"step": 74
|
| 470 |
},
|
| 471 |
{
|
| 472 |
-
"epoch":
|
| 473 |
"learning_rate": 0.0002,
|
| 474 |
-
"loss": 0.
|
| 475 |
"step": 75
|
| 476 |
},
|
| 477 |
{
|
| 478 |
-
"epoch":
|
| 479 |
"learning_rate": 0.0002,
|
| 480 |
-
"loss": 0.
|
| 481 |
"step": 76
|
| 482 |
},
|
| 483 |
{
|
| 484 |
-
"epoch":
|
| 485 |
"learning_rate": 0.0002,
|
| 486 |
-
"loss": 0.
|
| 487 |
"step": 77
|
| 488 |
},
|
| 489 |
{
|
| 490 |
-
"epoch":
|
| 491 |
"learning_rate": 0.0002,
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 78
|
| 494 |
},
|
| 495 |
{
|
| 496 |
-
"epoch":
|
| 497 |
"learning_rate": 0.0002,
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 79
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
"learning_rate": 0.0002,
|
| 504 |
-
"loss": 0.
|
| 505 |
"step": 80
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch":
|
| 509 |
"learning_rate": 0.0002,
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 81
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
"learning_rate": 0.0002,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 82
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch":
|
| 521 |
"learning_rate": 0.0002,
|
| 522 |
-
"loss": 0.
|
| 523 |
"step": 83
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch":
|
| 527 |
"learning_rate": 0.0002,
|
| 528 |
-
"loss": 0.
|
| 529 |
"step": 84
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch":
|
| 533 |
-
"eval_loss": 0.
|
| 534 |
-
"eval_runtime":
|
| 535 |
-
"eval_samples_per_second": 15.
|
| 536 |
-
"eval_steps_per_second": 0.
|
| 537 |
"step": 84
|
| 538 |
},
|
| 539 |
{
|
| 540 |
-
"epoch":
|
| 541 |
"learning_rate": 0.0002,
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 85
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch":
|
| 547 |
"learning_rate": 0.0002,
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 86
|
| 550 |
},
|
| 551 |
{
|
| 552 |
-
"epoch":
|
| 553 |
"learning_rate": 0.0002,
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 87
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch":
|
| 559 |
"learning_rate": 0.0002,
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 88
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch":
|
| 565 |
"learning_rate": 0.0002,
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 89
|
| 568 |
},
|
| 569 |
{
|
| 570 |
-
"epoch":
|
| 571 |
"learning_rate": 0.0002,
|
| 572 |
-
"loss": 0.
|
| 573 |
"step": 90
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"epoch":
|
| 577 |
"learning_rate": 0.0002,
|
| 578 |
-
"loss": 0.
|
| 579 |
"step": 91
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"epoch":
|
| 583 |
"learning_rate": 0.0002,
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 92
|
| 586 |
},
|
| 587 |
{
|
| 588 |
-
"epoch":
|
| 589 |
"learning_rate": 0.0002,
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 93
|
| 592 |
},
|
| 593 |
{
|
| 594 |
-
"epoch":
|
| 595 |
"learning_rate": 0.0002,
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 94
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
"learning_rate": 0.0002,
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 95
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch":
|
| 607 |
"learning_rate": 0.0002,
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 96
|
| 610 |
},
|
| 611 |
{
|
| 612 |
-
"epoch":
|
| 613 |
"learning_rate": 0.0002,
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 97
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"epoch":
|
| 619 |
"learning_rate": 0.0002,
|
| 620 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 621 |
"step": 98
|
| 622 |
},
|
| 623 |
{
|
| 624 |
-
"epoch":
|
| 625 |
"learning_rate": 0.0002,
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 99
|
| 628 |
},
|
| 629 |
{
|
| 630 |
-
"epoch":
|
| 631 |
"learning_rate": 0.0002,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 100
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch":
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 101
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
"learning_rate": 0.0002,
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 102
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
"learning_rate": 0.0002,
|
| 650 |
-
"loss": 0.
|
| 651 |
"step": 103
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch":
|
| 655 |
"learning_rate": 0.0002,
|
| 656 |
-
"loss": 0.
|
| 657 |
"step": 104
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch":
|
| 661 |
"learning_rate": 0.0002,
|
| 662 |
-
"loss": 0.
|
| 663 |
"step": 105
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch":
|
| 667 |
"learning_rate": 0.0002,
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 106
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch":
|
| 673 |
"learning_rate": 0.0002,
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 107
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch":
|
| 679 |
"learning_rate": 0.0002,
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 108
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 685 |
"learning_rate": 0.0002,
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 109
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch":
|
| 691 |
"learning_rate": 0.0002,
|
| 692 |
-
"loss": 0.
|
| 693 |
"step": 110
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch":
|
| 697 |
"learning_rate": 0.0002,
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 111
|
| 700 |
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 4.0,
|
| 703 |
-
"learning_rate": 0.0002,
|
| 704 |
-
"loss": 0.0055,
|
| 705 |
-
"step": 112
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"epoch": 4.0,
|
| 709 |
-
"eval_loss": 0.006369821261614561,
|
| 710 |
-
"eval_runtime": 55.1727,
|
| 711 |
-
"eval_samples_per_second": 15.714,
|
| 712 |
-
"eval_steps_per_second": 0.507,
|
| 713 |
-
"step": 112
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 4.04,
|
| 717 |
-
"learning_rate": 0.0002,
|
| 718 |
-
"loss": 0.0069,
|
| 719 |
-
"step": 113
|
| 720 |
-
},
|
| 721 |
-
{
|
| 722 |
-
"epoch": 4.07,
|
| 723 |
-
"learning_rate": 0.0002,
|
| 724 |
-
"loss": 0.0044,
|
| 725 |
-
"step": 114
|
| 726 |
-
},
|
| 727 |
-
{
|
| 728 |
-
"epoch": 4.11,
|
| 729 |
-
"learning_rate": 0.0002,
|
| 730 |
-
"loss": 0.0034,
|
| 731 |
-
"step": 115
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 4.14,
|
| 735 |
-
"learning_rate": 0.0002,
|
| 736 |
-
"loss": 0.004,
|
| 737 |
-
"step": 116
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 4.18,
|
| 741 |
-
"learning_rate": 0.0002,
|
| 742 |
-
"loss": 0.0049,
|
| 743 |
-
"step": 117
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 4.21,
|
| 747 |
-
"learning_rate": 0.0002,
|
| 748 |
-
"loss": 0.0048,
|
| 749 |
-
"step": 118
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 4.25,
|
| 753 |
-
"learning_rate": 0.0002,
|
| 754 |
-
"loss": 0.0122,
|
| 755 |
-
"step": 119
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 4.29,
|
| 759 |
-
"learning_rate": 0.0002,
|
| 760 |
-
"loss": 0.0052,
|
| 761 |
-
"step": 120
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 4.32,
|
| 765 |
-
"learning_rate": 0.0002,
|
| 766 |
-
"loss": 0.005,
|
| 767 |
-
"step": 121
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 4.36,
|
| 771 |
-
"learning_rate": 0.0002,
|
| 772 |
-
"loss": 0.006,
|
| 773 |
-
"step": 122
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 4.39,
|
| 777 |
-
"learning_rate": 0.0002,
|
| 778 |
-
"loss": 0.0059,
|
| 779 |
-
"step": 123
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 4.43,
|
| 783 |
-
"learning_rate": 0.0002,
|
| 784 |
-
"loss": 0.0027,
|
| 785 |
-
"step": 124
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 4.46,
|
| 789 |
-
"learning_rate": 0.0002,
|
| 790 |
-
"loss": 0.0025,
|
| 791 |
-
"step": 125
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 4.5,
|
| 795 |
-
"learning_rate": 0.0002,
|
| 796 |
-
"loss": 0.004,
|
| 797 |
-
"step": 126
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 4.54,
|
| 801 |
-
"learning_rate": 0.0002,
|
| 802 |
-
"loss": 0.0033,
|
| 803 |
-
"step": 127
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 4.57,
|
| 807 |
-
"learning_rate": 0.0002,
|
| 808 |
-
"loss": 0.0024,
|
| 809 |
-
"step": 128
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 4.61,
|
| 813 |
-
"learning_rate": 0.0002,
|
| 814 |
-
"loss": 0.0034,
|
| 815 |
-
"step": 129
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 4.64,
|
| 819 |
-
"learning_rate": 0.0002,
|
| 820 |
-
"loss": 0.0051,
|
| 821 |
-
"step": 130
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 4.68,
|
| 825 |
-
"learning_rate": 0.0002,
|
| 826 |
-
"loss": 0.0025,
|
| 827 |
-
"step": 131
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 4.71,
|
| 831 |
-
"learning_rate": 0.0002,
|
| 832 |
-
"loss": 0.0039,
|
| 833 |
-
"step": 132
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 4.75,
|
| 837 |
-
"learning_rate": 0.0002,
|
| 838 |
-
"loss": 0.005,
|
| 839 |
-
"step": 133
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 4.79,
|
| 843 |
-
"learning_rate": 0.0002,
|
| 844 |
-
"loss": 0.0013,
|
| 845 |
-
"step": 134
|
| 846 |
-
},
|
| 847 |
-
{
|
| 848 |
-
"epoch": 4.82,
|
| 849 |
-
"learning_rate": 0.0002,
|
| 850 |
-
"loss": 0.0041,
|
| 851 |
-
"step": 135
|
| 852 |
-
},
|
| 853 |
-
{
|
| 854 |
-
"epoch": 4.86,
|
| 855 |
-
"learning_rate": 0.0002,
|
| 856 |
-
"loss": 0.0045,
|
| 857 |
-
"step": 136
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 4.89,
|
| 861 |
-
"learning_rate": 0.0002,
|
| 862 |
-
"loss": 0.0037,
|
| 863 |
-
"step": 137
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 4.93,
|
| 867 |
-
"learning_rate": 0.0002,
|
| 868 |
-
"loss": 0.0045,
|
| 869 |
-
"step": 138
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"epoch": 4.96,
|
| 873 |
-
"learning_rate": 0.0002,
|
| 874 |
-
"loss": 0.0029,
|
| 875 |
-
"step": 139
|
| 876 |
-
},
|
| 877 |
-
{
|
| 878 |
-
"epoch": 5.0,
|
| 879 |
-
"learning_rate": 0.0002,
|
| 880 |
-
"loss": 0.0023,
|
| 881 |
-
"step": 140
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 5.0,
|
| 885 |
-
"eval_loss": 0.0037152974400669336,
|
| 886 |
-
"eval_runtime": 55.1887,
|
| 887 |
-
"eval_samples_per_second": 15.71,
|
| 888 |
-
"eval_steps_per_second": 0.507,
|
| 889 |
-
"step": 140
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 5.04,
|
| 893 |
-
"learning_rate": 0.0002,
|
| 894 |
-
"loss": 0.001,
|
| 895 |
-
"step": 141
|
| 896 |
-
},
|
| 897 |
-
{
|
| 898 |
-
"epoch": 5.07,
|
| 899 |
-
"learning_rate": 0.0002,
|
| 900 |
-
"loss": 0.0036,
|
| 901 |
-
"step": 142
|
| 902 |
-
},
|
| 903 |
-
{
|
| 904 |
-
"epoch": 5.11,
|
| 905 |
-
"learning_rate": 0.0002,
|
| 906 |
-
"loss": 0.0031,
|
| 907 |
-
"step": 143
|
| 908 |
-
},
|
| 909 |
-
{
|
| 910 |
-
"epoch": 5.14,
|
| 911 |
-
"learning_rate": 0.0002,
|
| 912 |
-
"loss": 0.0085,
|
| 913 |
-
"step": 144
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"epoch": 5.18,
|
| 917 |
-
"learning_rate": 0.0002,
|
| 918 |
-
"loss": 0.0053,
|
| 919 |
-
"step": 145
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 5.21,
|
| 923 |
-
"learning_rate": 0.0002,
|
| 924 |
-
"loss": 0.004,
|
| 925 |
-
"step": 146
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 5.25,
|
| 929 |
-
"learning_rate": 0.0002,
|
| 930 |
-
"loss": 0.0057,
|
| 931 |
-
"step": 147
|
| 932 |
-
},
|
| 933 |
-
{
|
| 934 |
-
"epoch": 5.29,
|
| 935 |
-
"learning_rate": 0.0002,
|
| 936 |
-
"loss": 0.0057,
|
| 937 |
-
"step": 148
|
| 938 |
-
},
|
| 939 |
-
{
|
| 940 |
-
"epoch": 5.32,
|
| 941 |
-
"learning_rate": 0.0002,
|
| 942 |
-
"loss": 0.0046,
|
| 943 |
-
"step": 149
|
| 944 |
-
},
|
| 945 |
-
{
|
| 946 |
-
"epoch": 5.36,
|
| 947 |
-
"learning_rate": 0.0002,
|
| 948 |
-
"loss": 0.003,
|
| 949 |
-
"step": 150
|
| 950 |
-
},
|
| 951 |
-
{
|
| 952 |
-
"epoch": 5.39,
|
| 953 |
-
"learning_rate": 0.0002,
|
| 954 |
-
"loss": 0.0019,
|
| 955 |
-
"step": 151
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 5.43,
|
| 959 |
-
"learning_rate": 0.0002,
|
| 960 |
-
"loss": 0.0043,
|
| 961 |
-
"step": 152
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 5.46,
|
| 965 |
-
"learning_rate": 0.0002,
|
| 966 |
-
"loss": 0.0019,
|
| 967 |
-
"step": 153
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 5.5,
|
| 971 |
-
"learning_rate": 0.0002,
|
| 972 |
-
"loss": 0.0094,
|
| 973 |
-
"step": 154
|
| 974 |
-
},
|
| 975 |
-
{
|
| 976 |
-
"epoch": 5.54,
|
| 977 |
-
"learning_rate": 0.0002,
|
| 978 |
-
"loss": 0.0033,
|
| 979 |
-
"step": 155
|
| 980 |
-
},
|
| 981 |
-
{
|
| 982 |
-
"epoch": 5.57,
|
| 983 |
-
"learning_rate": 0.0002,
|
| 984 |
-
"loss": 0.0028,
|
| 985 |
-
"step": 156
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 5.61,
|
| 989 |
-
"learning_rate": 0.0002,
|
| 990 |
-
"loss": 0.0013,
|
| 991 |
-
"step": 157
|
| 992 |
-
},
|
| 993 |
-
{
|
| 994 |
-
"epoch": 5.64,
|
| 995 |
-
"learning_rate": 0.0002,
|
| 996 |
-
"loss": 0.0073,
|
| 997 |
-
"step": 158
|
| 998 |
-
},
|
| 999 |
-
{
|
| 1000 |
-
"epoch": 5.68,
|
| 1001 |
-
"learning_rate": 0.0002,
|
| 1002 |
-
"loss": 0.0054,
|
| 1003 |
-
"step": 159
|
| 1004 |
-
},
|
| 1005 |
-
{
|
| 1006 |
-
"epoch": 5.71,
|
| 1007 |
-
"learning_rate": 0.0002,
|
| 1008 |
-
"loss": 0.0066,
|
| 1009 |
-
"step": 160
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 5.75,
|
| 1013 |
-
"learning_rate": 0.0002,
|
| 1014 |
-
"loss": 0.0019,
|
| 1015 |
-
"step": 161
|
| 1016 |
-
},
|
| 1017 |
-
{
|
| 1018 |
-
"epoch": 5.79,
|
| 1019 |
-
"learning_rate": 0.0002,
|
| 1020 |
-
"loss": 0.0014,
|
| 1021 |
-
"step": 162
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"epoch": 5.82,
|
| 1025 |
-
"learning_rate": 0.0002,
|
| 1026 |
-
"loss": 0.0026,
|
| 1027 |
-
"step": 163
|
| 1028 |
-
},
|
| 1029 |
-
{
|
| 1030 |
-
"epoch": 5.86,
|
| 1031 |
-
"learning_rate": 0.0002,
|
| 1032 |
-
"loss": 0.0016,
|
| 1033 |
-
"step": 164
|
| 1034 |
-
},
|
| 1035 |
-
{
|
| 1036 |
-
"epoch": 5.89,
|
| 1037 |
-
"learning_rate": 0.0002,
|
| 1038 |
-
"loss": 0.0022,
|
| 1039 |
-
"step": 165
|
| 1040 |
-
},
|
| 1041 |
-
{
|
| 1042 |
-
"epoch": 5.93,
|
| 1043 |
-
"learning_rate": 0.0002,
|
| 1044 |
-
"loss": 0.0077,
|
| 1045 |
-
"step": 166
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 5.96,
|
| 1049 |
-
"learning_rate": 0.0002,
|
| 1050 |
-
"loss": 0.0054,
|
| 1051 |
-
"step": 167
|
| 1052 |
-
},
|
| 1053 |
-
{
|
| 1054 |
-
"epoch": 6.0,
|
| 1055 |
-
"learning_rate": 0.0002,
|
| 1056 |
-
"loss": 0.0049,
|
| 1057 |
-
"step": 168
|
| 1058 |
-
},
|
| 1059 |
-
{
|
| 1060 |
-
"epoch": 6.0,
|
| 1061 |
-
"eval_loss": 0.003725806251168251,
|
| 1062 |
-
"eval_runtime": 55.2317,
|
| 1063 |
-
"eval_samples_per_second": 15.698,
|
| 1064 |
-
"eval_steps_per_second": 0.507,
|
| 1065 |
-
"step": 168
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 6.04,
|
| 1069 |
-
"learning_rate": 0.0002,
|
| 1070 |
-
"loss": 0.0037,
|
| 1071 |
-
"step": 169
|
| 1072 |
-
},
|
| 1073 |
-
{
|
| 1074 |
-
"epoch": 6.07,
|
| 1075 |
-
"learning_rate": 0.0002,
|
| 1076 |
-
"loss": 0.0022,
|
| 1077 |
-
"step": 170
|
| 1078 |
-
},
|
| 1079 |
-
{
|
| 1080 |
-
"epoch": 6.11,
|
| 1081 |
-
"learning_rate": 0.0002,
|
| 1082 |
-
"loss": 0.0021,
|
| 1083 |
-
"step": 171
|
| 1084 |
-
},
|
| 1085 |
-
{
|
| 1086 |
-
"epoch": 6.14,
|
| 1087 |
-
"learning_rate": 0.0002,
|
| 1088 |
-
"loss": 0.0045,
|
| 1089 |
-
"step": 172
|
| 1090 |
-
},
|
| 1091 |
-
{
|
| 1092 |
-
"epoch": 6.18,
|
| 1093 |
-
"learning_rate": 0.0002,
|
| 1094 |
-
"loss": 0.0026,
|
| 1095 |
-
"step": 173
|
| 1096 |
-
},
|
| 1097 |
-
{
|
| 1098 |
-
"epoch": 6.21,
|
| 1099 |
-
"learning_rate": 0.0002,
|
| 1100 |
-
"loss": 0.0026,
|
| 1101 |
-
"step": 174
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 6.25,
|
| 1105 |
-
"learning_rate": 0.0002,
|
| 1106 |
-
"loss": 0.005,
|
| 1107 |
-
"step": 175
|
| 1108 |
-
},
|
| 1109 |
-
{
|
| 1110 |
-
"epoch": 6.29,
|
| 1111 |
-
"learning_rate": 0.0002,
|
| 1112 |
-
"loss": 0.0048,
|
| 1113 |
-
"step": 176
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"epoch": 6.32,
|
| 1117 |
-
"learning_rate": 0.0002,
|
| 1118 |
-
"loss": 0.0066,
|
| 1119 |
-
"step": 177
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 6.36,
|
| 1123 |
-
"learning_rate": 0.0002,
|
| 1124 |
-
"loss": 0.0028,
|
| 1125 |
-
"step": 178
|
| 1126 |
-
},
|
| 1127 |
-
{
|
| 1128 |
-
"epoch": 6.39,
|
| 1129 |
-
"learning_rate": 0.0002,
|
| 1130 |
-
"loss": 0.006,
|
| 1131 |
-
"step": 179
|
| 1132 |
-
},
|
| 1133 |
-
{
|
| 1134 |
-
"epoch": 6.43,
|
| 1135 |
-
"learning_rate": 0.0002,
|
| 1136 |
-
"loss": 0.0008,
|
| 1137 |
-
"step": 180
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 6.46,
|
| 1141 |
-
"learning_rate": 0.0002,
|
| 1142 |
-
"loss": 0.0037,
|
| 1143 |
-
"step": 181
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 6.5,
|
| 1147 |
-
"learning_rate": 0.0002,
|
| 1148 |
-
"loss": 0.0051,
|
| 1149 |
-
"step": 182
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"epoch": 6.54,
|
| 1153 |
-
"learning_rate": 0.0002,
|
| 1154 |
-
"loss": 0.0028,
|
| 1155 |
-
"step": 183
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"epoch": 6.57,
|
| 1159 |
-
"learning_rate": 0.0002,
|
| 1160 |
-
"loss": 0.0064,
|
| 1161 |
-
"step": 184
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 6.61,
|
| 1165 |
-
"learning_rate": 0.0002,
|
| 1166 |
-
"loss": 0.0025,
|
| 1167 |
-
"step": 185
|
| 1168 |
-
},
|
| 1169 |
-
{
|
| 1170 |
-
"epoch": 6.64,
|
| 1171 |
-
"learning_rate": 0.0002,
|
| 1172 |
-
"loss": 0.0025,
|
| 1173 |
-
"step": 186
|
| 1174 |
-
},
|
| 1175 |
-
{
|
| 1176 |
-
"epoch": 6.68,
|
| 1177 |
-
"learning_rate": 0.0002,
|
| 1178 |
-
"loss": 0.0043,
|
| 1179 |
-
"step": 187
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 6.71,
|
| 1183 |
-
"learning_rate": 0.0002,
|
| 1184 |
-
"loss": 0.0017,
|
| 1185 |
-
"step": 188
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 6.75,
|
| 1189 |
-
"learning_rate": 0.0002,
|
| 1190 |
-
"loss": 0.002,
|
| 1191 |
-
"step": 189
|
| 1192 |
-
},
|
| 1193 |
-
{
|
| 1194 |
-
"epoch": 6.79,
|
| 1195 |
-
"learning_rate": 0.0002,
|
| 1196 |
-
"loss": 0.0009,
|
| 1197 |
-
"step": 190
|
| 1198 |
-
},
|
| 1199 |
-
{
|
| 1200 |
-
"epoch": 6.82,
|
| 1201 |
-
"learning_rate": 0.0002,
|
| 1202 |
-
"loss": 0.0018,
|
| 1203 |
-
"step": 191
|
| 1204 |
-
},
|
| 1205 |
-
{
|
| 1206 |
-
"epoch": 6.86,
|
| 1207 |
-
"learning_rate": 0.0002,
|
| 1208 |
-
"loss": 0.0037,
|
| 1209 |
-
"step": 192
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 6.89,
|
| 1213 |
-
"learning_rate": 0.0002,
|
| 1214 |
-
"loss": 0.0013,
|
| 1215 |
-
"step": 193
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 6.93,
|
| 1219 |
-
"learning_rate": 0.0002,
|
| 1220 |
-
"loss": 0.002,
|
| 1221 |
-
"step": 194
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 6.96,
|
| 1225 |
-
"learning_rate": 0.0002,
|
| 1226 |
-
"loss": 0.002,
|
| 1227 |
-
"step": 195
|
| 1228 |
-
},
|
| 1229 |
-
{
|
| 1230 |
-
"epoch": 7.0,
|
| 1231 |
-
"learning_rate": 0.0002,
|
| 1232 |
-
"loss": 0.0009,
|
| 1233 |
-
"step": 196
|
| 1234 |
-
},
|
| 1235 |
-
{
|
| 1236 |
-
"epoch": 7.0,
|
| 1237 |
-
"eval_loss": 0.0015701488591730595,
|
| 1238 |
-
"eval_runtime": 55.1955,
|
| 1239 |
-
"eval_samples_per_second": 15.708,
|
| 1240 |
-
"eval_steps_per_second": 0.507,
|
| 1241 |
-
"step": 196
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 7.04,
|
| 1245 |
-
"learning_rate": 0.0002,
|
| 1246 |
-
"loss": 0.0016,
|
| 1247 |
-
"step": 197
|
| 1248 |
-
},
|
| 1249 |
-
{
|
| 1250 |
-
"epoch": 7.07,
|
| 1251 |
-
"learning_rate": 0.0002,
|
| 1252 |
-
"loss": 0.0018,
|
| 1253 |
-
"step": 198
|
| 1254 |
-
},
|
| 1255 |
-
{
|
| 1256 |
-
"epoch": 7.11,
|
| 1257 |
-
"learning_rate": 0.0002,
|
| 1258 |
-
"loss": 0.0015,
|
| 1259 |
-
"step": 199
|
| 1260 |
-
},
|
| 1261 |
-
{
|
| 1262 |
-
"epoch": 7.14,
|
| 1263 |
-
"learning_rate": 0.0002,
|
| 1264 |
-
"loss": 0.0016,
|
| 1265 |
-
"step": 200
|
| 1266 |
-
},
|
| 1267 |
-
{
|
| 1268 |
-
"epoch": 7.18,
|
| 1269 |
-
"learning_rate": 0.0002,
|
| 1270 |
-
"loss": 0.0014,
|
| 1271 |
-
"step": 201
|
| 1272 |
-
},
|
| 1273 |
-
{
|
| 1274 |
-
"epoch": 7.21,
|
| 1275 |
-
"learning_rate": 0.0002,
|
| 1276 |
-
"loss": 0.0032,
|
| 1277 |
-
"step": 202
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 7.25,
|
| 1281 |
-
"learning_rate": 0.0002,
|
| 1282 |
-
"loss": 0.0006,
|
| 1283 |
-
"step": 203
|
| 1284 |
-
},
|
| 1285 |
-
{
|
| 1286 |
-
"epoch": 7.29,
|
| 1287 |
-
"learning_rate": 0.0002,
|
| 1288 |
-
"loss": 0.0018,
|
| 1289 |
-
"step": 204
|
| 1290 |
-
},
|
| 1291 |
-
{
|
| 1292 |
-
"epoch": 7.32,
|
| 1293 |
-
"learning_rate": 0.0002,
|
| 1294 |
-
"loss": 0.0005,
|
| 1295 |
-
"step": 205
|
| 1296 |
-
},
|
| 1297 |
-
{
|
| 1298 |
-
"epoch": 7.36,
|
| 1299 |
-
"learning_rate": 0.0002,
|
| 1300 |
-
"loss": 0.0024,
|
| 1301 |
-
"step": 206
|
| 1302 |
-
},
|
| 1303 |
-
{
|
| 1304 |
-
"epoch": 7.39,
|
| 1305 |
-
"learning_rate": 0.0002,
|
| 1306 |
-
"loss": 0.0027,
|
| 1307 |
-
"step": 207
|
| 1308 |
-
},
|
| 1309 |
-
{
|
| 1310 |
-
"epoch": 7.43,
|
| 1311 |
-
"learning_rate": 0.0002,
|
| 1312 |
-
"loss": 0.0005,
|
| 1313 |
-
"step": 208
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 7.46,
|
| 1317 |
-
"learning_rate": 0.0002,
|
| 1318 |
-
"loss": 0.0056,
|
| 1319 |
-
"step": 209
|
| 1320 |
-
},
|
| 1321 |
-
{
|
| 1322 |
-
"epoch": 7.5,
|
| 1323 |
-
"learning_rate": 0.0002,
|
| 1324 |
-
"loss": 0.0015,
|
| 1325 |
-
"step": 210
|
| 1326 |
-
},
|
| 1327 |
-
{
|
| 1328 |
-
"epoch": 7.54,
|
| 1329 |
-
"learning_rate": 0.0002,
|
| 1330 |
-
"loss": 0.0019,
|
| 1331 |
-
"step": 211
|
| 1332 |
-
},
|
| 1333 |
-
{
|
| 1334 |
-
"epoch": 7.57,
|
| 1335 |
-
"learning_rate": 0.0002,
|
| 1336 |
-
"loss": 0.0014,
|
| 1337 |
-
"step": 212
|
| 1338 |
-
},
|
| 1339 |
-
{
|
| 1340 |
-
"epoch": 7.61,
|
| 1341 |
-
"learning_rate": 0.0002,
|
| 1342 |
-
"loss": 0.0009,
|
| 1343 |
-
"step": 213
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 7.64,
|
| 1347 |
-
"learning_rate": 0.0002,
|
| 1348 |
-
"loss": 0.0017,
|
| 1349 |
-
"step": 214
|
| 1350 |
-
},
|
| 1351 |
-
{
|
| 1352 |
-
"epoch": 7.68,
|
| 1353 |
-
"learning_rate": 0.0002,
|
| 1354 |
-
"loss": 0.0037,
|
| 1355 |
-
"step": 215
|
| 1356 |
-
},
|
| 1357 |
-
{
|
| 1358 |
-
"epoch": 7.71,
|
| 1359 |
-
"learning_rate": 0.0002,
|
| 1360 |
-
"loss": 0.0009,
|
| 1361 |
-
"step": 216
|
| 1362 |
-
},
|
| 1363 |
-
{
|
| 1364 |
-
"epoch": 7.75,
|
| 1365 |
-
"learning_rate": 0.0002,
|
| 1366 |
-
"loss": 0.0021,
|
| 1367 |
-
"step": 217
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 7.79,
|
| 1371 |
-
"learning_rate": 0.0002,
|
| 1372 |
-
"loss": 0.0024,
|
| 1373 |
-
"step": 218
|
| 1374 |
-
},
|
| 1375 |
-
{
|
| 1376 |
-
"epoch": 7.82,
|
| 1377 |
-
"learning_rate": 0.0002,
|
| 1378 |
-
"loss": 0.002,
|
| 1379 |
-
"step": 219
|
| 1380 |
-
},
|
| 1381 |
-
{
|
| 1382 |
-
"epoch": 7.86,
|
| 1383 |
-
"learning_rate": 0.0002,
|
| 1384 |
-
"loss": 0.0011,
|
| 1385 |
-
"step": 220
|
| 1386 |
-
},
|
| 1387 |
-
{
|
| 1388 |
-
"epoch": 7.89,
|
| 1389 |
-
"learning_rate": 0.0002,
|
| 1390 |
-
"loss": 0.002,
|
| 1391 |
-
"step": 221
|
| 1392 |
-
},
|
| 1393 |
-
{
|
| 1394 |
-
"epoch": 7.93,
|
| 1395 |
-
"learning_rate": 0.0002,
|
| 1396 |
-
"loss": 0.0042,
|
| 1397 |
-
"step": 222
|
| 1398 |
-
},
|
| 1399 |
-
{
|
| 1400 |
-
"epoch": 7.96,
|
| 1401 |
-
"learning_rate": 0.0002,
|
| 1402 |
-
"loss": 0.0046,
|
| 1403 |
-
"step": 223
|
| 1404 |
-
},
|
| 1405 |
{
|
| 1406 |
"epoch": 8.0,
|
| 1407 |
"learning_rate": 0.0002,
|
| 1408 |
-
"loss": 0.
|
| 1409 |
-
"step":
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 8.0,
|
| 1413 |
-
"eval_loss": 0.
|
| 1414 |
-
"eval_runtime":
|
| 1415 |
-
"eval_samples_per_second": 15.
|
| 1416 |
-
"eval_steps_per_second": 0.
|
| 1417 |
-
"step":
|
| 1418 |
-
},
|
| 1419 |
-
{
|
| 1420 |
-
"epoch": 8.04,
|
| 1421 |
-
"learning_rate": 0.0002,
|
| 1422 |
-
"loss": 0.0005,
|
| 1423 |
-
"step": 225
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 8.07,
|
| 1427 |
"learning_rate": 0.0002,
|
| 1428 |
"loss": 0.0007,
|
| 1429 |
-
"step":
|
| 1430 |
-
},
|
| 1431 |
-
{
|
| 1432 |
-
"epoch": 8.11,
|
| 1433 |
-
"learning_rate": 0.0002,
|
| 1434 |
-
"loss": 0.003,
|
| 1435 |
-
"step": 227
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 8.14,
|
| 1439 |
"learning_rate": 0.0002,
|
| 1440 |
-
"loss": 0.
|
| 1441 |
-
"step":
|
| 1442 |
-
},
|
| 1443 |
-
{
|
| 1444 |
-
"epoch": 8.18,
|
| 1445 |
-
"learning_rate": 0.0002,
|
| 1446 |
-
"loss": 0.0023,
|
| 1447 |
-
"step": 229
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
"epoch": 8.21,
|
| 1451 |
"learning_rate": 0.0002,
|
| 1452 |
-
"loss": 0.
|
| 1453 |
-
"step":
|
| 1454 |
-
},
|
| 1455 |
-
{
|
| 1456 |
-
"epoch": 8.25,
|
| 1457 |
-
"learning_rate": 0.0002,
|
| 1458 |
-
"loss": 0.0018,
|
| 1459 |
-
"step": 231
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 8.29,
|
| 1463 |
"learning_rate": 0.0002,
|
| 1464 |
-
"loss": 0.
|
| 1465 |
-
"step":
|
| 1466 |
-
},
|
| 1467 |
-
{
|
| 1468 |
-
"epoch": 8.32,
|
| 1469 |
-
"learning_rate": 0.0002,
|
| 1470 |
-
"loss": 0.001,
|
| 1471 |
-
"step": 233
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 8.36,
|
| 1475 |
"learning_rate": 0.0002,
|
| 1476 |
-
"loss": 0.
|
| 1477 |
-
"step":
|
| 1478 |
-
},
|
| 1479 |
-
{
|
| 1480 |
-
"epoch": 8.39,
|
| 1481 |
-
"learning_rate": 0.0002,
|
| 1482 |
-
"loss": 0.0022,
|
| 1483 |
-
"step": 235
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 8.43,
|
| 1487 |
"learning_rate": 0.0002,
|
| 1488 |
-
"loss": 0.
|
| 1489 |
-
"step":
|
| 1490 |
-
},
|
| 1491 |
-
{
|
| 1492 |
-
"epoch": 8.46,
|
| 1493 |
-
"learning_rate": 0.0002,
|
| 1494 |
-
"loss": 0.0006,
|
| 1495 |
-
"step": 237
|
| 1496 |
},
|
| 1497 |
{
|
| 1498 |
"epoch": 8.5,
|
| 1499 |
"learning_rate": 0.0002,
|
| 1500 |
-
"loss": 0.
|
| 1501 |
-
"step":
|
| 1502 |
-
},
|
| 1503 |
-
{
|
| 1504 |
-
"epoch": 8.54,
|
| 1505 |
-
"learning_rate": 0.0002,
|
| 1506 |
-
"loss": 0.0016,
|
| 1507 |
-
"step": 239
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 8.57,
|
| 1511 |
"learning_rate": 0.0002,
|
| 1512 |
-
"loss": 0.
|
| 1513 |
-
"step":
|
| 1514 |
-
},
|
| 1515 |
-
{
|
| 1516 |
-
"epoch": 8.61,
|
| 1517 |
-
"learning_rate": 0.0002,
|
| 1518 |
-
"loss": 0.0011,
|
| 1519 |
-
"step": 241
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 8.64,
|
| 1523 |
"learning_rate": 0.0002,
|
| 1524 |
-
"loss": 0.
|
| 1525 |
-
"step":
|
| 1526 |
-
},
|
| 1527 |
-
{
|
| 1528 |
-
"epoch": 8.68,
|
| 1529 |
-
"learning_rate": 0.0002,
|
| 1530 |
-
"loss": 0.0013,
|
| 1531 |
-
"step": 243
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 8.71,
|
| 1535 |
"learning_rate": 0.0002,
|
| 1536 |
-
"loss": 0.
|
| 1537 |
-
"step":
|
| 1538 |
-
},
|
| 1539 |
-
{
|
| 1540 |
-
"epoch": 8.75,
|
| 1541 |
-
"learning_rate": 0.0002,
|
| 1542 |
-
"loss": 0.0005,
|
| 1543 |
-
"step": 245
|
| 1544 |
},
|
| 1545 |
{
|
| 1546 |
"epoch": 8.79,
|
| 1547 |
"learning_rate": 0.0002,
|
| 1548 |
-
"loss": 0.
|
| 1549 |
-
"step":
|
| 1550 |
-
},
|
| 1551 |
-
{
|
| 1552 |
-
"epoch": 8.82,
|
| 1553 |
-
"learning_rate": 0.0002,
|
| 1554 |
-
"loss": 0.0026,
|
| 1555 |
-
"step": 247
|
| 1556 |
},
|
| 1557 |
{
|
| 1558 |
"epoch": 8.86,
|
| 1559 |
"learning_rate": 0.0002,
|
| 1560 |
-
"loss": 0.
|
| 1561 |
-
"step":
|
| 1562 |
-
},
|
| 1563 |
-
{
|
| 1564 |
-
"epoch": 8.89,
|
| 1565 |
-
"learning_rate": 0.0002,
|
| 1566 |
-
"loss": 0.0012,
|
| 1567 |
-
"step": 249
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
"epoch": 8.93,
|
| 1571 |
"learning_rate": 0.0002,
|
| 1572 |
-
"loss": 0.
|
| 1573 |
-
"step":
|
| 1574 |
-
},
|
| 1575 |
-
{
|
| 1576 |
-
"epoch": 8.96,
|
| 1577 |
-
"learning_rate": 0.0002,
|
| 1578 |
-
"loss": 0.0011,
|
| 1579 |
-
"step": 251
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 9.0,
|
| 1583 |
"learning_rate": 0.0002,
|
| 1584 |
-
"loss": 0.
|
| 1585 |
-
"step":
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 9.0,
|
| 1589 |
-
"eval_loss": 0.
|
| 1590 |
-
"eval_runtime":
|
| 1591 |
-
"eval_samples_per_second": 15.
|
| 1592 |
-
"eval_steps_per_second": 0.
|
| 1593 |
-
"step":
|
| 1594 |
-
},
|
| 1595 |
-
{
|
| 1596 |
-
"epoch": 9.04,
|
| 1597 |
-
"learning_rate": 0.0002,
|
| 1598 |
-
"loss": 0.0019,
|
| 1599 |
-
"step": 253
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
"epoch": 9.07,
|
| 1603 |
"learning_rate": 0.0002,
|
| 1604 |
-
"loss": 0.001,
|
| 1605 |
-
"step": 254
|
| 1606 |
-
},
|
| 1607 |
-
{
|
| 1608 |
-
"epoch": 9.11,
|
| 1609 |
-
"learning_rate": 0.0002,
|
| 1610 |
"loss": 0.0004,
|
| 1611 |
-
"step":
|
| 1612 |
},
|
| 1613 |
{
|
| 1614 |
"epoch": 9.14,
|
| 1615 |
"learning_rate": 0.0002,
|
| 1616 |
-
"loss": 0.
|
| 1617 |
-
"step":
|
| 1618 |
-
},
|
| 1619 |
-
{
|
| 1620 |
-
"epoch": 9.18,
|
| 1621 |
-
"learning_rate": 0.0002,
|
| 1622 |
-
"loss": 0.0022,
|
| 1623 |
-
"step": 257
|
| 1624 |
},
|
| 1625 |
{
|
| 1626 |
"epoch": 9.21,
|
| 1627 |
"learning_rate": 0.0002,
|
| 1628 |
-
"loss": 0.
|
| 1629 |
-
"step":
|
| 1630 |
-
},
|
| 1631 |
-
{
|
| 1632 |
-
"epoch": 9.25,
|
| 1633 |
-
"learning_rate": 0.0002,
|
| 1634 |
-
"loss": 0.0013,
|
| 1635 |
-
"step": 259
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 9.29,
|
| 1639 |
"learning_rate": 0.0002,
|
| 1640 |
-
"loss": 0.
|
| 1641 |
-
"step":
|
| 1642 |
-
},
|
| 1643 |
-
{
|
| 1644 |
-
"epoch": 9.32,
|
| 1645 |
-
"learning_rate": 0.0002,
|
| 1646 |
-
"loss": 0.0028,
|
| 1647 |
-
"step": 261
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 9.36,
|
| 1651 |
"learning_rate": 0.0002,
|
| 1652 |
-
"loss": 0.
|
| 1653 |
-
"step":
|
| 1654 |
-
},
|
| 1655 |
-
{
|
| 1656 |
-
"epoch": 9.39,
|
| 1657 |
-
"learning_rate": 0.0002,
|
| 1658 |
-
"loss": 0.0006,
|
| 1659 |
-
"step": 263
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 9.43,
|
| 1663 |
"learning_rate": 0.0002,
|
| 1664 |
-
"loss": 0.
|
| 1665 |
-
"step":
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 9.46,
|
| 1669 |
-
"learning_rate": 0.0002,
|
| 1670 |
-
"loss": 0.001,
|
| 1671 |
-
"step": 265
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 9.5,
|
| 1675 |
"learning_rate": 0.0002,
|
| 1676 |
-
"loss": 0.
|
| 1677 |
-
"step":
|
| 1678 |
-
},
|
| 1679 |
-
{
|
| 1680 |
-
"epoch": 9.54,
|
| 1681 |
-
"learning_rate": 0.0002,
|
| 1682 |
-
"loss": 0.0008,
|
| 1683 |
-
"step": 267
|
| 1684 |
},
|
| 1685 |
{
|
| 1686 |
"epoch": 9.57,
|
| 1687 |
"learning_rate": 0.0002,
|
| 1688 |
-
"loss": 0.
|
| 1689 |
-
"step":
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 9.61,
|
| 1693 |
-
"learning_rate": 0.0002,
|
| 1694 |
-
"loss": 0.0012,
|
| 1695 |
-
"step": 269
|
| 1696 |
},
|
| 1697 |
{
|
| 1698 |
"epoch": 9.64,
|
| 1699 |
"learning_rate": 0.0002,
|
| 1700 |
-
"loss": 0.
|
| 1701 |
-
"step":
|
| 1702 |
-
},
|
| 1703 |
-
{
|
| 1704 |
-
"epoch": 9.68,
|
| 1705 |
-
"learning_rate": 0.0002,
|
| 1706 |
-
"loss": 0.0033,
|
| 1707 |
-
"step": 271
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 9.71,
|
| 1711 |
"learning_rate": 0.0002,
|
| 1712 |
-
"loss": 0.
|
| 1713 |
-
"step":
|
| 1714 |
-
},
|
| 1715 |
-
{
|
| 1716 |
-
"epoch": 9.75,
|
| 1717 |
-
"learning_rate": 0.0002,
|
| 1718 |
-
"loss": 0.0019,
|
| 1719 |
-
"step": 273
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 9.79,
|
| 1723 |
"learning_rate": 0.0002,
|
| 1724 |
-
"loss": 0.
|
| 1725 |
-
"step":
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"epoch": 9.82,
|
| 1729 |
-
"learning_rate": 0.0002,
|
| 1730 |
-
"loss": 0.0045,
|
| 1731 |
-
"step": 275
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
"epoch": 9.86,
|
| 1735 |
"learning_rate": 0.0002,
|
| 1736 |
-
"loss": 0.
|
| 1737 |
-
"step":
|
| 1738 |
-
},
|
| 1739 |
-
{
|
| 1740 |
-
"epoch": 9.89,
|
| 1741 |
-
"learning_rate": 0.0002,
|
| 1742 |
-
"loss": 0.0039,
|
| 1743 |
-
"step": 277
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 9.93,
|
| 1747 |
"learning_rate": 0.0002,
|
| 1748 |
-
"loss": 0.
|
| 1749 |
-
"step":
|
| 1750 |
-
},
|
| 1751 |
-
{
|
| 1752 |
-
"epoch": 9.96,
|
| 1753 |
-
"learning_rate": 0.0002,
|
| 1754 |
-
"loss": 0.0035,
|
| 1755 |
-
"step": 279
|
| 1756 |
},
|
| 1757 |
{
|
| 1758 |
"epoch": 10.0,
|
| 1759 |
"learning_rate": 0.0002,
|
| 1760 |
-
"loss": 0.
|
| 1761 |
-
"step":
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
"epoch": 10.0,
|
| 1765 |
-
"eval_loss": 0.
|
| 1766 |
-
"eval_runtime":
|
| 1767 |
-
"eval_samples_per_second": 15.
|
| 1768 |
-
"eval_steps_per_second": 0.
|
| 1769 |
-
"step":
|
| 1770 |
},
|
| 1771 |
{
|
| 1772 |
"epoch": 10.0,
|
| 1773 |
-
"step":
|
| 1774 |
-
"total_flos":
|
| 1775 |
-
"train_loss": 0.
|
| 1776 |
-
"train_runtime":
|
| 1777 |
-
"train_samples_per_second":
|
| 1778 |
-
"train_steps_per_second": 0.
|
| 1779 |
}
|
| 1780 |
],
|
| 1781 |
"logging_steps": 1.0,
|
| 1782 |
-
"max_steps":
|
| 1783 |
"num_input_tokens_seen": 0,
|
| 1784 |
"num_train_epochs": 10,
|
| 1785 |
"save_steps": 50000,
|
| 1786 |
-
"total_flos":
|
| 1787 |
"train_batch_size": 4,
|
| 1788 |
"trial_name": null,
|
| 1789 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 140,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
+
"loss": 1.4966,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 8.613531161467861e-05,
|
| 20 |
+
"loss": 1.0914,
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.21,
|
| 25 |
+
"learning_rate": 0.00013652123889719707,
|
| 26 |
+
"loss": 1.1815,
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.29,
|
| 31 |
+
"learning_rate": 0.00017227062322935723,
|
| 32 |
+
"loss": 1.1374,
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.36,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 1.0049,
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.43,
|
| 43 |
+
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 0.9757,
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.5,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.9526,
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.57,
|
| 55 |
+
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 0.8746,
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.64,
|
| 61 |
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.7538,
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.71,
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 0.7817,
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.79,
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 0.7263,
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.86,
|
| 79 |
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.6033,
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.93,
|
| 85 |
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.582,
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 1.0,
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.4256,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_loss": 0.3590076267719269,
|
| 98 |
+
"eval_runtime": 27.2669,
|
| 99 |
+
"eval_samples_per_second": 15.587,
|
| 100 |
+
"eval_steps_per_second": 0.513,
|
| 101 |
"step": 14
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 1.07,
|
| 105 |
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.2531,
|
| 107 |
"step": 15
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 1.14,
|
| 111 |
"learning_rate": 0.0002,
|
| 112 |
+
"loss": 0.3431,
|
| 113 |
"step": 16
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 1.21,
|
| 117 |
"learning_rate": 0.0002,
|
| 118 |
+
"loss": 0.2548,
|
| 119 |
"step": 17
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 1.29,
|
| 123 |
"learning_rate": 0.0002,
|
| 124 |
+
"loss": 0.2814,
|
| 125 |
"step": 18
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 1.36,
|
| 129 |
"learning_rate": 0.0002,
|
| 130 |
+
"loss": 0.1958,
|
| 131 |
"step": 19
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 1.43,
|
| 135 |
"learning_rate": 0.0002,
|
| 136 |
+
"loss": 0.2286,
|
| 137 |
"step": 20
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.5,
|
| 141 |
"learning_rate": 0.0002,
|
| 142 |
+
"loss": 0.2332,
|
| 143 |
"step": 21
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 1.57,
|
| 147 |
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.1755,
|
| 149 |
"step": 22
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 1.64,
|
| 153 |
"learning_rate": 0.0002,
|
| 154 |
+
"loss": 0.1312,
|
| 155 |
"step": 23
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 1.71,
|
| 159 |
"learning_rate": 0.0002,
|
| 160 |
+
"loss": 0.0845,
|
| 161 |
"step": 24
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 1.79,
|
| 165 |
"learning_rate": 0.0002,
|
| 166 |
+
"loss": 0.1214,
|
| 167 |
"step": 25
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 1.86,
|
| 171 |
"learning_rate": 0.0002,
|
| 172 |
+
"loss": 0.0884,
|
| 173 |
"step": 26
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 1.93,
|
| 177 |
"learning_rate": 0.0002,
|
| 178 |
+
"loss": 0.1381,
|
| 179 |
"step": 27
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
"learning_rate": 0.0002,
|
| 184 |
+
"loss": 0.0643,
|
| 185 |
"step": 28
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 2.0,
|
| 189 |
+
"eval_loss": 0.07109997421503067,
|
| 190 |
+
"eval_runtime": 27.4843,
|
| 191 |
+
"eval_samples_per_second": 15.463,
|
| 192 |
"eval_steps_per_second": 0.509,
|
| 193 |
"step": 28
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 2.07,
|
| 197 |
"learning_rate": 0.0002,
|
| 198 |
+
"loss": 0.0533,
|
| 199 |
"step": 29
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 2.14,
|
| 203 |
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.0566,
|
| 205 |
"step": 30
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 2.21,
|
| 209 |
"learning_rate": 0.0002,
|
| 210 |
+
"loss": 0.0457,
|
| 211 |
"step": 31
|
| 212 |
},
|
| 213 |
{
|
| 214 |
+
"epoch": 2.29,
|
| 215 |
"learning_rate": 0.0002,
|
| 216 |
+
"loss": 0.041,
|
| 217 |
"step": 32
|
| 218 |
},
|
| 219 |
{
|
| 220 |
+
"epoch": 2.36,
|
| 221 |
"learning_rate": 0.0002,
|
| 222 |
+
"loss": 0.0447,
|
| 223 |
"step": 33
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 2.43,
|
| 227 |
"learning_rate": 0.0002,
|
| 228 |
+
"loss": 0.0206,
|
| 229 |
"step": 34
|
| 230 |
},
|
| 231 |
{
|
| 232 |
+
"epoch": 2.5,
|
| 233 |
"learning_rate": 0.0002,
|
| 234 |
+
"loss": 0.0221,
|
| 235 |
"step": 35
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 2.57,
|
| 239 |
"learning_rate": 0.0002,
|
| 240 |
+
"loss": 0.0541,
|
| 241 |
"step": 36
|
| 242 |
},
|
| 243 |
{
|
| 244 |
+
"epoch": 2.64,
|
| 245 |
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.0274,
|
| 247 |
"step": 37
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 2.71,
|
| 251 |
"learning_rate": 0.0002,
|
| 252 |
+
"loss": 0.0169,
|
| 253 |
"step": 38
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 2.79,
|
| 257 |
"learning_rate": 0.0002,
|
| 258 |
+
"loss": 0.0358,
|
| 259 |
"step": 39
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 2.86,
|
| 263 |
"learning_rate": 0.0002,
|
| 264 |
+
"loss": 0.0375,
|
| 265 |
"step": 40
|
| 266 |
},
|
| 267 |
{
|
| 268 |
+
"epoch": 2.93,
|
| 269 |
"learning_rate": 0.0002,
|
| 270 |
+
"loss": 0.0233,
|
| 271 |
"step": 41
|
| 272 |
},
|
| 273 |
{
|
| 274 |
+
"epoch": 3.0,
|
| 275 |
"learning_rate": 0.0002,
|
| 276 |
+
"loss": 0.0114,
|
| 277 |
+
"step": 42
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.0,
|
| 281 |
+
"eval_loss": 0.01424238458275795,
|
| 282 |
+
"eval_runtime": 27.4614,
|
| 283 |
+
"eval_samples_per_second": 15.476,
|
| 284 |
+
"eval_steps_per_second": 0.51,
|
| 285 |
"step": 42
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 3.07,
|
| 289 |
"learning_rate": 0.0002,
|
| 290 |
+
"loss": 0.0095,
|
| 291 |
"step": 43
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 3.14,
|
| 295 |
"learning_rate": 0.0002,
|
| 296 |
+
"loss": 0.0093,
|
| 297 |
"step": 44
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 3.21,
|
| 301 |
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.0068,
|
| 303 |
"step": 45
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 3.29,
|
| 307 |
"learning_rate": 0.0002,
|
| 308 |
+
"loss": 0.0069,
|
| 309 |
"step": 46
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 3.36,
|
| 313 |
"learning_rate": 0.0002,
|
| 314 |
+
"loss": 0.0067,
|
| 315 |
"step": 47
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 3.43,
|
| 319 |
"learning_rate": 0.0002,
|
| 320 |
+
"loss": 0.0161,
|
| 321 |
"step": 48
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 3.5,
|
| 325 |
"learning_rate": 0.0002,
|
| 326 |
+
"loss": 0.0123,
|
| 327 |
"step": 49
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 3.57,
|
| 331 |
"learning_rate": 0.0002,
|
| 332 |
+
"loss": 0.0074,
|
| 333 |
"step": 50
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 3.64,
|
| 337 |
"learning_rate": 0.0002,
|
| 338 |
+
"loss": 0.0052,
|
| 339 |
"step": 51
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 3.71,
|
| 343 |
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.0088,
|
| 345 |
"step": 52
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 3.79,
|
| 349 |
"learning_rate": 0.0002,
|
| 350 |
+
"loss": 0.0147,
|
| 351 |
"step": 53
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 3.86,
|
| 355 |
"learning_rate": 0.0002,
|
| 356 |
+
"loss": 0.008,
|
| 357 |
"step": 54
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 3.93,
|
| 361 |
"learning_rate": 0.0002,
|
| 362 |
+
"loss": 0.0062,
|
| 363 |
"step": 55
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 4.0,
|
| 367 |
"learning_rate": 0.0002,
|
| 368 |
+
"loss": 0.0089,
|
| 369 |
"step": 56
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 4.0,
|
| 373 |
+
"eval_loss": 0.006587002892047167,
|
| 374 |
+
"eval_runtime": 27.6072,
|
| 375 |
+
"eval_samples_per_second": 15.395,
|
| 376 |
+
"eval_steps_per_second": 0.507,
|
| 377 |
"step": 56
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 4.07,
|
| 381 |
"learning_rate": 0.0002,
|
| 382 |
+
"loss": 0.0047,
|
| 383 |
"step": 57
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 4.14,
|
| 387 |
"learning_rate": 0.0002,
|
| 388 |
+
"loss": 0.0043,
|
| 389 |
"step": 58
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 4.21,
|
| 393 |
"learning_rate": 0.0002,
|
| 394 |
+
"loss": 0.0061,
|
| 395 |
"step": 59
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 4.29,
|
| 399 |
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.0036,
|
| 401 |
"step": 60
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 4.36,
|
| 405 |
"learning_rate": 0.0002,
|
| 406 |
+
"loss": 0.0019,
|
| 407 |
"step": 61
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 4.43,
|
| 411 |
"learning_rate": 0.0002,
|
| 412 |
+
"loss": 0.0032,
|
| 413 |
"step": 62
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 4.5,
|
| 417 |
"learning_rate": 0.0002,
|
| 418 |
+
"loss": 0.0056,
|
| 419 |
"step": 63
|
| 420 |
},
|
| 421 |
{
|
| 422 |
+
"epoch": 4.57,
|
| 423 |
"learning_rate": 0.0002,
|
| 424 |
+
"loss": 0.0063,
|
| 425 |
"step": 64
|
| 426 |
},
|
| 427 |
{
|
| 428 |
+
"epoch": 4.64,
|
| 429 |
"learning_rate": 0.0002,
|
| 430 |
+
"loss": 0.002,
|
| 431 |
"step": 65
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 4.71,
|
| 435 |
"learning_rate": 0.0002,
|
| 436 |
+
"loss": 0.0057,
|
| 437 |
"step": 66
|
| 438 |
},
|
| 439 |
{
|
| 440 |
+
"epoch": 4.79,
|
| 441 |
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.0031,
|
| 443 |
"step": 67
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 4.86,
|
| 447 |
"learning_rate": 0.0002,
|
| 448 |
+
"loss": 0.0065,
|
| 449 |
"step": 68
|
| 450 |
},
|
| 451 |
{
|
| 452 |
+
"epoch": 4.93,
|
| 453 |
"learning_rate": 0.0002,
|
| 454 |
+
"loss": 0.0022,
|
| 455 |
"step": 69
|
| 456 |
},
|
| 457 |
{
|
| 458 |
+
"epoch": 5.0,
|
| 459 |
"learning_rate": 0.0002,
|
| 460 |
+
"loss": 0.0021,
|
| 461 |
+
"step": 70
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.0,
|
| 465 |
+
"eval_loss": 0.0026798362378031015,
|
| 466 |
+
"eval_runtime": 27.5909,
|
| 467 |
+
"eval_samples_per_second": 15.404,
|
| 468 |
+
"eval_steps_per_second": 0.507,
|
| 469 |
"step": 70
|
| 470 |
},
|
| 471 |
{
|
| 472 |
+
"epoch": 5.07,
|
| 473 |
"learning_rate": 0.0002,
|
| 474 |
+
"loss": 0.0009,
|
| 475 |
"step": 71
|
| 476 |
},
|
| 477 |
{
|
| 478 |
+
"epoch": 5.14,
|
| 479 |
"learning_rate": 0.0002,
|
| 480 |
+
"loss": 0.0013,
|
| 481 |
"step": 72
|
| 482 |
},
|
| 483 |
{
|
| 484 |
+
"epoch": 5.21,
|
| 485 |
"learning_rate": 0.0002,
|
| 486 |
+
"loss": 0.0024,
|
| 487 |
"step": 73
|
| 488 |
},
|
| 489 |
{
|
| 490 |
+
"epoch": 5.29,
|
| 491 |
"learning_rate": 0.0002,
|
| 492 |
+
"loss": 0.0011,
|
| 493 |
"step": 74
|
| 494 |
},
|
| 495 |
{
|
| 496 |
+
"epoch": 5.36,
|
| 497 |
"learning_rate": 0.0002,
|
| 498 |
+
"loss": 0.0008,
|
| 499 |
"step": 75
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 5.43,
|
| 503 |
"learning_rate": 0.0002,
|
| 504 |
+
"loss": 0.0019,
|
| 505 |
"step": 76
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 5.5,
|
| 509 |
"learning_rate": 0.0002,
|
| 510 |
+
"loss": 0.0009,
|
| 511 |
"step": 77
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 5.57,
|
| 515 |
"learning_rate": 0.0002,
|
| 516 |
+
"loss": 0.0016,
|
| 517 |
"step": 78
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 5.64,
|
| 521 |
"learning_rate": 0.0002,
|
| 522 |
+
"loss": 0.0021,
|
| 523 |
"step": 79
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"epoch": 5.71,
|
| 527 |
"learning_rate": 0.0002,
|
| 528 |
+
"loss": 0.0017,
|
| 529 |
"step": 80
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 5.79,
|
| 533 |
"learning_rate": 0.0002,
|
| 534 |
+
"loss": 0.0028,
|
| 535 |
"step": 81
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 5.86,
|
| 539 |
"learning_rate": 0.0002,
|
| 540 |
+
"loss": 0.0028,
|
| 541 |
"step": 82
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 5.93,
|
| 545 |
"learning_rate": 0.0002,
|
| 546 |
+
"loss": 0.0013,
|
| 547 |
"step": 83
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 6.0,
|
| 551 |
"learning_rate": 0.0002,
|
| 552 |
+
"loss": 0.0012,
|
| 553 |
"step": 84
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 6.0,
|
| 557 |
+
"eval_loss": 0.0026673530228435993,
|
| 558 |
+
"eval_runtime": 27.6491,
|
| 559 |
+
"eval_samples_per_second": 15.371,
|
| 560 |
+
"eval_steps_per_second": 0.506,
|
| 561 |
"step": 84
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 6.07,
|
| 565 |
"learning_rate": 0.0002,
|
| 566 |
+
"loss": 0.0027,
|
| 567 |
"step": 85
|
| 568 |
},
|
| 569 |
{
|
| 570 |
+
"epoch": 6.14,
|
| 571 |
"learning_rate": 0.0002,
|
| 572 |
+
"loss": 0.0037,
|
| 573 |
"step": 86
|
| 574 |
},
|
| 575 |
{
|
| 576 |
+
"epoch": 6.21,
|
| 577 |
"learning_rate": 0.0002,
|
| 578 |
+
"loss": 0.0022,
|
| 579 |
"step": 87
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"epoch": 6.29,
|
| 583 |
"learning_rate": 0.0002,
|
| 584 |
+
"loss": 0.002,
|
| 585 |
"step": 88
|
| 586 |
},
|
| 587 |
{
|
| 588 |
+
"epoch": 6.36,
|
| 589 |
"learning_rate": 0.0002,
|
| 590 |
+
"loss": 0.0004,
|
| 591 |
"step": 89
|
| 592 |
},
|
| 593 |
{
|
| 594 |
+
"epoch": 6.43,
|
| 595 |
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.0009,
|
| 597 |
"step": 90
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 6.5,
|
| 601 |
"learning_rate": 0.0002,
|
| 602 |
+
"loss": 0.0009,
|
| 603 |
"step": 91
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 6.57,
|
| 607 |
"learning_rate": 0.0002,
|
| 608 |
+
"loss": 0.0014,
|
| 609 |
"step": 92
|
| 610 |
},
|
| 611 |
{
|
| 612 |
+
"epoch": 6.64,
|
| 613 |
"learning_rate": 0.0002,
|
| 614 |
+
"loss": 0.0014,
|
| 615 |
"step": 93
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"epoch": 6.71,
|
| 619 |
"learning_rate": 0.0002,
|
| 620 |
+
"loss": 0.002,
|
| 621 |
"step": 94
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 6.79,
|
| 625 |
"learning_rate": 0.0002,
|
| 626 |
+
"loss": 0.001,
|
| 627 |
"step": 95
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 6.86,
|
| 631 |
"learning_rate": 0.0002,
|
| 632 |
+
"loss": 0.0005,
|
| 633 |
"step": 96
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 6.93,
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.0031,
|
| 639 |
"step": 97
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 7.0,
|
| 643 |
"learning_rate": 0.0002,
|
| 644 |
+
"loss": 0.0008,
|
| 645 |
+
"step": 98
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 7.0,
|
| 649 |
+
"eval_loss": 0.0014789514243602753,
|
| 650 |
+
"eval_runtime": 27.6117,
|
| 651 |
+
"eval_samples_per_second": 15.392,
|
| 652 |
+
"eval_steps_per_second": 0.507,
|
| 653 |
"step": 98
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 7.07,
|
| 657 |
"learning_rate": 0.0002,
|
| 658 |
+
"loss": 0.0005,
|
| 659 |
"step": 99
|
| 660 |
},
|
| 661 |
{
|
| 662 |
+
"epoch": 7.14,
|
| 663 |
"learning_rate": 0.0002,
|
| 664 |
+
"loss": 0.0003,
|
| 665 |
"step": 100
|
| 666 |
},
|
| 667 |
{
|
| 668 |
+
"epoch": 7.21,
|
| 669 |
"learning_rate": 0.0002,
|
| 670 |
+
"loss": 0.0011,
|
| 671 |
"step": 101
|
| 672 |
},
|
| 673 |
{
|
| 674 |
+
"epoch": 7.29,
|
| 675 |
"learning_rate": 0.0002,
|
| 676 |
+
"loss": 0.0005,
|
| 677 |
"step": 102
|
| 678 |
},
|
| 679 |
{
|
| 680 |
+
"epoch": 7.36,
|
| 681 |
"learning_rate": 0.0002,
|
| 682 |
+
"loss": 0.0005,
|
| 683 |
"step": 103
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 7.43,
|
| 687 |
"learning_rate": 0.0002,
|
| 688 |
+
"loss": 0.0003,
|
| 689 |
"step": 104
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 7.5,
|
| 693 |
"learning_rate": 0.0002,
|
| 694 |
+
"loss": 0.0004,
|
| 695 |
"step": 105
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 7.57,
|
| 699 |
"learning_rate": 0.0002,
|
| 700 |
+
"loss": 0.0003,
|
| 701 |
"step": 106
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 7.64,
|
| 705 |
"learning_rate": 0.0002,
|
| 706 |
+
"loss": 0.002,
|
| 707 |
"step": 107
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 7.71,
|
| 711 |
"learning_rate": 0.0002,
|
| 712 |
+
"loss": 0.001,
|
| 713 |
"step": 108
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 7.79,
|
| 717 |
"learning_rate": 0.0002,
|
| 718 |
+
"loss": 0.0005,
|
| 719 |
"step": 109
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"epoch": 7.86,
|
| 723 |
"learning_rate": 0.0002,
|
| 724 |
+
"loss": 0.0025,
|
| 725 |
"step": 110
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 7.93,
|
| 729 |
"learning_rate": 0.0002,
|
| 730 |
+
"loss": 0.0005,
|
| 731 |
"step": 111
|
| 732 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 733 |
{
|
| 734 |
"epoch": 8.0,
|
| 735 |
"learning_rate": 0.0002,
|
| 736 |
+
"loss": 0.0002,
|
| 737 |
+
"step": 112
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 8.0,
|
| 741 |
+
"eval_loss": 0.0006328822346404195,
|
| 742 |
+
"eval_runtime": 27.661,
|
| 743 |
+
"eval_samples_per_second": 15.365,
|
| 744 |
+
"eval_steps_per_second": 0.506,
|
| 745 |
+
"step": 112
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 8.07,
|
| 749 |
"learning_rate": 0.0002,
|
| 750 |
"loss": 0.0007,
|
| 751 |
+
"step": 113
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 8.14,
|
| 755 |
"learning_rate": 0.0002,
|
| 756 |
+
"loss": 0.0002,
|
| 757 |
+
"step": 114
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 8.21,
|
| 761 |
"learning_rate": 0.0002,
|
| 762 |
+
"loss": 0.0002,
|
| 763 |
+
"step": 115
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 8.29,
|
| 767 |
"learning_rate": 0.0002,
|
| 768 |
+
"loss": 0.0002,
|
| 769 |
+
"step": 116
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 8.36,
|
| 773 |
"learning_rate": 0.0002,
|
| 774 |
+
"loss": 0.0005,
|
| 775 |
+
"step": 117
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 8.43,
|
| 779 |
"learning_rate": 0.0002,
|
| 780 |
+
"loss": 0.0002,
|
| 781 |
+
"step": 118
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 8.5,
|
| 785 |
"learning_rate": 0.0002,
|
| 786 |
+
"loss": 0.0007,
|
| 787 |
+
"step": 119
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 8.57,
|
| 791 |
"learning_rate": 0.0002,
|
| 792 |
+
"loss": 0.0002,
|
| 793 |
+
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 8.64,
|
| 797 |
"learning_rate": 0.0002,
|
| 798 |
+
"loss": 0.0025,
|
| 799 |
+
"step": 121
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 800 |
},
|
| 801 |
{
|
| 802 |
"epoch": 8.71,
|
| 803 |
"learning_rate": 0.0002,
|
| 804 |
+
"loss": 0.0008,
|
| 805 |
+
"step": 122
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"epoch": 8.79,
|
| 809 |
"learning_rate": 0.0002,
|
| 810 |
+
"loss": 0.0012,
|
| 811 |
+
"step": 123
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 8.86,
|
| 815 |
"learning_rate": 0.0002,
|
| 816 |
+
"loss": 0.0002,
|
| 817 |
+
"step": 124
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 8.93,
|
| 821 |
"learning_rate": 0.0002,
|
| 822 |
+
"loss": 0.0003,
|
| 823 |
+
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 824 |
},
|
| 825 |
{
|
| 826 |
"epoch": 9.0,
|
| 827 |
"learning_rate": 0.0002,
|
| 828 |
+
"loss": 0.0002,
|
| 829 |
+
"step": 126
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 9.0,
|
| 833 |
+
"eval_loss": 0.0004491883155424148,
|
| 834 |
+
"eval_runtime": 27.6221,
|
| 835 |
+
"eval_samples_per_second": 15.386,
|
| 836 |
+
"eval_steps_per_second": 0.507,
|
| 837 |
+
"step": 126
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 9.07,
|
| 841 |
"learning_rate": 0.0002,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 842 |
"loss": 0.0004,
|
| 843 |
+
"step": 127
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 9.14,
|
| 847 |
"learning_rate": 0.0002,
|
| 848 |
+
"loss": 0.0001,
|
| 849 |
+
"step": 128
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 9.21,
|
| 853 |
"learning_rate": 0.0002,
|
| 854 |
+
"loss": 0.0001,
|
| 855 |
+
"step": 129
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 9.29,
|
| 859 |
"learning_rate": 0.0002,
|
| 860 |
+
"loss": 0.0003,
|
| 861 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 9.36,
|
| 865 |
"learning_rate": 0.0002,
|
| 866 |
+
"loss": 0.0011,
|
| 867 |
+
"step": 131
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 9.43,
|
| 871 |
"learning_rate": 0.0002,
|
| 872 |
+
"loss": 0.0002,
|
| 873 |
+
"step": 132
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 9.5,
|
| 877 |
"learning_rate": 0.0002,
|
| 878 |
+
"loss": 0.0002,
|
| 879 |
+
"step": 133
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 9.57,
|
| 883 |
"learning_rate": 0.0002,
|
| 884 |
+
"loss": 0.0007,
|
| 885 |
+
"step": 134
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 9.64,
|
| 889 |
"learning_rate": 0.0002,
|
| 890 |
+
"loss": 0.0022,
|
| 891 |
+
"step": 135
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 9.71,
|
| 895 |
"learning_rate": 0.0002,
|
| 896 |
+
"loss": 0.0016,
|
| 897 |
+
"step": 136
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 9.79,
|
| 901 |
"learning_rate": 0.0002,
|
| 902 |
+
"loss": 0.0001,
|
| 903 |
+
"step": 137
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 9.86,
|
| 907 |
"learning_rate": 0.0002,
|
| 908 |
+
"loss": 0.0001,
|
| 909 |
+
"step": 138
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 9.93,
|
| 913 |
"learning_rate": 0.0002,
|
| 914 |
+
"loss": 0.0003,
|
| 915 |
+
"step": 139
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 10.0,
|
| 919 |
"learning_rate": 0.0002,
|
| 920 |
+
"loss": 0.0005,
|
| 921 |
+
"step": 140
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 10.0,
|
| 925 |
+
"eval_loss": 0.00029718142468482256,
|
| 926 |
+
"eval_runtime": 27.6542,
|
| 927 |
+
"eval_samples_per_second": 15.368,
|
| 928 |
+
"eval_steps_per_second": 0.506,
|
| 929 |
+
"step": 140
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 10.0,
|
| 933 |
+
"step": 140,
|
| 934 |
+
"total_flos": 4.2897933864638874e+17,
|
| 935 |
+
"train_loss": 0.11377025729951648,
|
| 936 |
+
"train_runtime": 2129.3536,
|
| 937 |
+
"train_samples_per_second": 1.996,
|
| 938 |
+
"train_steps_per_second": 0.066
|
| 939 |
}
|
| 940 |
],
|
| 941 |
"logging_steps": 1.0,
|
| 942 |
+
"max_steps": 140,
|
| 943 |
"num_input_tokens_seen": 0,
|
| 944 |
"num_train_epochs": 10,
|
| 945 |
"save_steps": 50000,
|
| 946 |
+
"total_flos": 4.2897933864638874e+17,
|
| 947 |
"train_batch_size": 4,
|
| 948 |
"trial_name": null,
|
| 949 |
"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 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa90b394534132b7b403551766766cdfe27216265cc6d0e380d159dcb58549e3
|
| 3 |
size 6840
|