Commit
•
1a17623
1
Parent(s):
2fab1cf
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +653 -7
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/queen")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/queen")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1v5o4ijc/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2apdiv6y) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2apdiv6y/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -35,7 +35,7 @@
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
|
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.11.3",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss":
|
|
|
|
| 1 |
+
{"eval_loss": 1.775342345237732, "eval_runtime": 3.9684, "eval_samples_per_second": 21.923, "eval_steps_per_second": 2.772, "epoch": 12.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78164ec45551b127583fec5e4a0f6928dd1f4f77a75658bc2052260c3e93c6dc
|
| 3 |
size 497764120
|
optimizer.pt
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:c05aaab90d8caa0c02fb32e76686034b0a99f484a4537df99993a9ff56a1cd41
|
| 3 |
+
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eecd5d268e5f975f932bf34dff98dd7e71a2e51f68b094f2ebc1800a6bd5a0f4
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fe9cc5f8604aa97b538fc3054764ff7cb9b030361ac3a1e8a39c4ddce759080
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:066420211cafaee663c00dce05f0eac5d610fd3a9b179d73be449c25b47fdfdc
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "output/queen/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -184,11 +184,657 @@
|
|
| 184 |
"eval_samples_per_second": 22.039,
|
| 185 |
"eval_steps_per_second": 2.784,
|
| 186 |
"step": 136
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187 |
}
|
| 188 |
],
|
| 189 |
-
"max_steps":
|
| 190 |
-
"num_train_epochs":
|
| 191 |
-
"total_flos":
|
| 192 |
"trial_name": null,
|
| 193 |
"trial_params": null
|
| 194 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.775342345237732,
|
| 3 |
+
"best_model_checkpoint": "output/queen/checkpoint-621",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"global_step": 621,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 184 |
"eval_samples_per_second": 22.039,
|
| 185 |
"eval_steps_per_second": 2.784,
|
| 186 |
"step": 136
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0,
|
| 190 |
+
"eval_loss": 2.222139835357666,
|
| 191 |
+
"eval_runtime": 3.7161,
|
| 192 |
+
"eval_samples_per_second": 23.412,
|
| 193 |
+
"eval_steps_per_second": 2.96,
|
| 194 |
+
"step": 138
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.03,
|
| 198 |
+
"learning_rate": 0.00013691577939766304,
|
| 199 |
+
"loss": 2.3223,
|
| 200 |
+
"step": 140
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.1,
|
| 204 |
+
"learning_rate": 0.00013374528334456193,
|
| 205 |
+
"loss": 2.4227,
|
| 206 |
+
"step": 145
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.17,
|
| 210 |
+
"learning_rate": 0.00012721317115188912,
|
| 211 |
+
"loss": 2.3956,
|
| 212 |
+
"step": 150
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.25,
|
| 216 |
+
"learning_rate": 0.00011765651179294606,
|
| 217 |
+
"loss": 2.3273,
|
| 218 |
+
"step": 155
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.32,
|
| 222 |
+
"learning_rate": 0.0001055684464238085,
|
| 223 |
+
"loss": 2.4048,
|
| 224 |
+
"step": 160
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.39,
|
| 228 |
+
"learning_rate": 9.157274139492967e-05,
|
| 229 |
+
"loss": 2.4168,
|
| 230 |
+
"step": 165
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.46,
|
| 234 |
+
"learning_rate": 7.639160076306266e-05,
|
| 235 |
+
"loss": 2.4496,
|
| 236 |
+
"step": 170
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.54,
|
| 240 |
+
"learning_rate": 6.0808399236937385e-05,
|
| 241 |
+
"loss": 2.0669,
|
| 242 |
+
"step": 175
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.61,
|
| 246 |
+
"learning_rate": 4.5627258605070364e-05,
|
| 247 |
+
"loss": 2.2692,
|
| 248 |
+
"step": 180
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.68,
|
| 252 |
+
"learning_rate": 3.1631553576191535e-05,
|
| 253 |
+
"loss": 2.1242,
|
| 254 |
+
"step": 185
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.75,
|
| 258 |
+
"learning_rate": 1.954348820705391e-05,
|
| 259 |
+
"loss": 2.3064,
|
| 260 |
+
"step": 190
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.83,
|
| 264 |
+
"learning_rate": 9.986828848110892e-06,
|
| 265 |
+
"loss": 2.146,
|
| 266 |
+
"step": 195
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.9,
|
| 270 |
+
"learning_rate": 3.454716655438096e-06,
|
| 271 |
+
"loss": 2.3787,
|
| 272 |
+
"step": 200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.97,
|
| 276 |
+
"learning_rate": 2.8422060233695394e-07,
|
| 277 |
+
"loss": 2.2533,
|
| 278 |
+
"step": 205
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.0,
|
| 282 |
+
"eval_loss": 2.043508768081665,
|
| 283 |
+
"eval_runtime": 3.8679,
|
| 284 |
+
"eval_samples_per_second": 22.493,
|
| 285 |
+
"eval_steps_per_second": 2.844,
|
| 286 |
+
"step": 207
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.04,
|
| 290 |
+
"learning_rate": 6.389441019077102e-07,
|
| 291 |
+
"loss": 2.1995,
|
| 292 |
+
"step": 210
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.12,
|
| 296 |
+
"learning_rate": 4.500582770777967e-06,
|
| 297 |
+
"loss": 2.2239,
|
| 298 |
+
"step": 215
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.19,
|
| 302 |
+
"learning_rate": 1.166986896886688e-05,
|
| 303 |
+
"loss": 2.1124,
|
| 304 |
+
"step": 220
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.26,
|
| 308 |
+
"learning_rate": 2.177685437520025e-05,
|
| 309 |
+
"loss": 2.2442,
|
| 310 |
+
"step": 225
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.33,
|
| 314 |
+
"learning_rate": 3.4300000000000014e-05,
|
| 315 |
+
"loss": 2.0765,
|
| 316 |
+
"step": 230
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.41,
|
| 320 |
+
"learning_rate": 4.859308855339902e-05,
|
| 321 |
+
"loss": 2.042,
|
| 322 |
+
"step": 235
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.48,
|
| 326 |
+
"learning_rate": 6.391857044318346e-05,
|
| 327 |
+
"loss": 2.0462,
|
| 328 |
+
"step": 240
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.55,
|
| 332 |
+
"learning_rate": 7.948562268689874e-05,
|
| 333 |
+
"loss": 1.9776,
|
| 334 |
+
"step": 245
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 3.62,
|
| 338 |
+
"learning_rate": 9.449095682862937e-05,
|
| 339 |
+
"loss": 2.1824,
|
| 340 |
+
"step": 250
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.7,
|
| 344 |
+
"learning_rate": 0.0001081602700970798,
|
| 345 |
+
"loss": 1.996,
|
| 346 |
+
"step": 255
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.77,
|
| 350 |
+
"learning_rate": 0.00011978820084915117,
|
| 351 |
+
"loss": 2.1329,
|
| 352 |
+
"step": 260
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 3.84,
|
| 356 |
+
"learning_rate": 0.00012877472652481797,
|
| 357 |
+
"loss": 2.1854,
|
| 358 |
+
"step": 265
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.91,
|
| 362 |
+
"learning_rate": 0.00013465612591205902,
|
| 363 |
+
"loss": 1.8201,
|
| 364 |
+
"step": 270
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 3.99,
|
| 368 |
+
"learning_rate": 0.00013712890801216552,
|
| 369 |
+
"loss": 1.8969,
|
| 370 |
+
"step": 275
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.0,
|
| 374 |
+
"eval_loss": 1.9531660079956055,
|
| 375 |
+
"eval_runtime": 3.8382,
|
| 376 |
+
"eval_samples_per_second": 22.667,
|
| 377 |
+
"eval_steps_per_second": 2.866,
|
| 378 |
+
"step": 276
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.06,
|
| 382 |
+
"learning_rate": 0.0001360654727320747,
|
| 383 |
+
"loss": 1.817,
|
| 384 |
+
"step": 280
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.13,
|
| 388 |
+
"learning_rate": 0.0001315206952832741,
|
| 389 |
+
"loss": 1.6319,
|
| 390 |
+
"step": 285
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.2,
|
| 394 |
+
"learning_rate": 0.00012372909452021153,
|
| 395 |
+
"loss": 1.7738,
|
| 396 |
+
"step": 290
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 4.28,
|
| 400 |
+
"learning_rate": 0.00011309273133714503,
|
| 401 |
+
"loss": 1.7757,
|
| 402 |
+
"step": 295
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.35,
|
| 406 |
+
"learning_rate": 0.0001001604615883571,
|
| 407 |
+
"loss": 1.9699,
|
| 408 |
+
"step": 300
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.42,
|
| 412 |
+
"learning_rate": 8.5599614119113e-05,
|
| 413 |
+
"loss": 1.9681,
|
| 414 |
+
"step": 305
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.49,
|
| 418 |
+
"learning_rate": 7.016155537292879e-05,
|
| 419 |
+
"loss": 1.9245,
|
| 420 |
+
"step": 310
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.57,
|
| 424 |
+
"learning_rate": 5.464291750458938e-05,
|
| 425 |
+
"loss": 1.7497,
|
| 426 |
+
"step": 315
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.64,
|
| 430 |
+
"learning_rate": 3.98444906994169e-05,
|
| 431 |
+
"loss": 1.7975,
|
| 432 |
+
"step": 320
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.71,
|
| 436 |
+
"learning_rate": 2.6529900930537204e-05,
|
| 437 |
+
"loss": 1.6675,
|
| 438 |
+
"step": 325
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.78,
|
| 442 |
+
"learning_rate": 1.5386205457676833e-05,
|
| 443 |
+
"loss": 1.9876,
|
| 444 |
+
"step": 330
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.86,
|
| 448 |
+
"learning_rate": 6.988439412050469e-06,
|
| 449 |
+
"loss": 1.691,
|
| 450 |
+
"step": 335
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 4.93,
|
| 454 |
+
"learning_rate": 1.7699429285993718e-06,
|
| 455 |
+
"loss": 1.8689,
|
| 456 |
+
"step": 340
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5.0,
|
| 460 |
+
"learning_rate": 0.0,
|
| 461 |
+
"loss": 1.9327,
|
| 462 |
+
"step": 345
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.0,
|
| 466 |
+
"eval_loss": 1.8510653972625732,
|
| 467 |
+
"eval_runtime": 3.8275,
|
| 468 |
+
"eval_samples_per_second": 22.73,
|
| 469 |
+
"eval_steps_per_second": 2.874,
|
| 470 |
+
"step": 345
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.07,
|
| 474 |
+
"learning_rate": 1.7699429285993566e-06,
|
| 475 |
+
"loss": 1.5991,
|
| 476 |
+
"step": 350
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.14,
|
| 480 |
+
"learning_rate": 6.988439412050431e-06,
|
| 481 |
+
"loss": 1.6155,
|
| 482 |
+
"step": 355
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.22,
|
| 486 |
+
"learning_rate": 1.538620545767678e-05,
|
| 487 |
+
"loss": 1.6707,
|
| 488 |
+
"step": 360
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.29,
|
| 492 |
+
"learning_rate": 2.6529900930537035e-05,
|
| 493 |
+
"loss": 1.7262,
|
| 494 |
+
"step": 365
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.36,
|
| 498 |
+
"learning_rate": 3.984449069941682e-05,
|
| 499 |
+
"loss": 1.7087,
|
| 500 |
+
"step": 370
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.43,
|
| 504 |
+
"learning_rate": 5.4642917504589295e-05,
|
| 505 |
+
"loss": 1.7766,
|
| 506 |
+
"step": 375
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.51,
|
| 510 |
+
"learning_rate": 7.016155537292883e-05,
|
| 511 |
+
"loss": 1.5992,
|
| 512 |
+
"step": 380
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.58,
|
| 516 |
+
"learning_rate": 8.559961411911291e-05,
|
| 517 |
+
"loss": 1.6561,
|
| 518 |
+
"step": 385
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.65,
|
| 522 |
+
"learning_rate": 0.00010016046158835702,
|
| 523 |
+
"loss": 1.6108,
|
| 524 |
+
"step": 390
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 5.72,
|
| 528 |
+
"learning_rate": 0.00011309273133714504,
|
| 529 |
+
"loss": 1.6236,
|
| 530 |
+
"step": 395
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 5.8,
|
| 534 |
+
"learning_rate": 0.0001237290945202115,
|
| 535 |
+
"loss": 1.6319,
|
| 536 |
+
"step": 400
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 5.87,
|
| 540 |
+
"learning_rate": 0.00013152069528327408,
|
| 541 |
+
"loss": 1.4268,
|
| 542 |
+
"step": 405
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 5.94,
|
| 546 |
+
"learning_rate": 0.00013606547273207472,
|
| 547 |
+
"loss": 1.7278,
|
| 548 |
+
"step": 410
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.0,
|
| 552 |
+
"eval_loss": 1.8254233598709106,
|
| 553 |
+
"eval_runtime": 3.854,
|
| 554 |
+
"eval_samples_per_second": 22.574,
|
| 555 |
+
"eval_steps_per_second": 2.854,
|
| 556 |
+
"step": 414
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 6.01,
|
| 560 |
+
"learning_rate": 0.00013712890801216552,
|
| 561 |
+
"loss": 1.8762,
|
| 562 |
+
"step": 415
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 6.09,
|
| 566 |
+
"learning_rate": 0.00013465612591205902,
|
| 567 |
+
"loss": 1.4495,
|
| 568 |
+
"step": 420
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 6.16,
|
| 572 |
+
"learning_rate": 0.00012877472652481797,
|
| 573 |
+
"loss": 1.5224,
|
| 574 |
+
"step": 425
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.23,
|
| 578 |
+
"learning_rate": 0.00011978820084915123,
|
| 579 |
+
"loss": 1.5038,
|
| 580 |
+
"step": 430
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 6.3,
|
| 584 |
+
"learning_rate": 0.00010816027009708009,
|
| 585 |
+
"loss": 1.4097,
|
| 586 |
+
"step": 435
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 6.38,
|
| 590 |
+
"learning_rate": 9.449095682862935e-05,
|
| 591 |
+
"loss": 1.3203,
|
| 592 |
+
"step": 440
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 6.45,
|
| 596 |
+
"learning_rate": 7.948562268689883e-05,
|
| 597 |
+
"loss": 1.3634,
|
| 598 |
+
"step": 445
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 6.52,
|
| 602 |
+
"learning_rate": 6.39185704431838e-05,
|
| 603 |
+
"loss": 1.4181,
|
| 604 |
+
"step": 450
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.59,
|
| 608 |
+
"learning_rate": 4.859308855339899e-05,
|
| 609 |
+
"loss": 1.5025,
|
| 610 |
+
"step": 455
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 6.67,
|
| 614 |
+
"learning_rate": 3.429999999999998e-05,
|
| 615 |
+
"loss": 1.5881,
|
| 616 |
+
"step": 460
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 6.74,
|
| 620 |
+
"learning_rate": 2.1776854375200487e-05,
|
| 621 |
+
"loss": 1.5042,
|
| 622 |
+
"step": 465
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 6.81,
|
| 626 |
+
"learning_rate": 1.1669868968866859e-05,
|
| 627 |
+
"loss": 1.4229,
|
| 628 |
+
"step": 470
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 6.88,
|
| 632 |
+
"learning_rate": 4.500582770777952e-06,
|
| 633 |
+
"loss": 1.5551,
|
| 634 |
+
"step": 475
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 6.96,
|
| 638 |
+
"learning_rate": 6.389441019077407e-07,
|
| 639 |
+
"loss": 1.6253,
|
| 640 |
+
"step": 480
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 7.0,
|
| 644 |
+
"eval_loss": 1.787222146987915,
|
| 645 |
+
"eval_runtime": 3.8357,
|
| 646 |
+
"eval_samples_per_second": 22.681,
|
| 647 |
+
"eval_steps_per_second": 2.868,
|
| 648 |
+
"step": 483
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 7.03,
|
| 652 |
+
"learning_rate": 2.8422060233696156e-07,
|
| 653 |
+
"loss": 1.5683,
|
| 654 |
+
"step": 485
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 7.1,
|
| 658 |
+
"learning_rate": 3.4547166554380356e-06,
|
| 659 |
+
"loss": 1.1749,
|
| 660 |
+
"step": 490
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.17,
|
| 664 |
+
"learning_rate": 9.986828848110785e-06,
|
| 665 |
+
"loss": 1.2655,
|
| 666 |
+
"step": 495
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.25,
|
| 670 |
+
"learning_rate": 1.9543488207053935e-05,
|
| 671 |
+
"loss": 1.3456,
|
| 672 |
+
"step": 500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 7.32,
|
| 676 |
+
"learning_rate": 3.163155357619136e-05,
|
| 677 |
+
"loss": 1.2074,
|
| 678 |
+
"step": 505
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 7.39,
|
| 682 |
+
"learning_rate": 4.5627258605070174e-05,
|
| 683 |
+
"loss": 1.3068,
|
| 684 |
+
"step": 510
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 7.46,
|
| 688 |
+
"learning_rate": 6.080839923693748e-05,
|
| 689 |
+
"loss": 1.1119,
|
| 690 |
+
"step": 515
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 7.54,
|
| 694 |
+
"learning_rate": 7.639160076306239e-05,
|
| 695 |
+
"loss": 1.3026,
|
| 696 |
+
"step": 520
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 7.61,
|
| 700 |
+
"learning_rate": 9.15727413949297e-05,
|
| 701 |
+
"loss": 1.4164,
|
| 702 |
+
"step": 525
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 7.68,
|
| 706 |
+
"learning_rate": 0.00010556844642380854,
|
| 707 |
+
"loss": 1.6188,
|
| 708 |
+
"step": 530
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 7.75,
|
| 712 |
+
"learning_rate": 0.00011765651179294598,
|
| 713 |
+
"loss": 1.438,
|
| 714 |
+
"step": 535
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 7.83,
|
| 718 |
+
"learning_rate": 0.00012721317115188917,
|
| 719 |
+
"loss": 1.267,
|
| 720 |
+
"step": 540
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 7.9,
|
| 724 |
+
"learning_rate": 0.00013374528334456193,
|
| 725 |
+
"loss": 1.2976,
|
| 726 |
+
"step": 545
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 7.97,
|
| 730 |
+
"learning_rate": 0.00013691577939766304,
|
| 731 |
+
"loss": 1.4411,
|
| 732 |
+
"step": 550
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.0,
|
| 736 |
+
"eval_loss": 1.795061707496643,
|
| 737 |
+
"eval_runtime": 3.8467,
|
| 738 |
+
"eval_samples_per_second": 22.617,
|
| 739 |
+
"eval_steps_per_second": 2.86,
|
| 740 |
+
"step": 552
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 8.04,
|
| 744 |
+
"learning_rate": 0.0001365610558980923,
|
| 745 |
+
"loss": 1.266,
|
| 746 |
+
"step": 555
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.12,
|
| 750 |
+
"learning_rate": 0.000132699417229222,
|
| 751 |
+
"loss": 1.2792,
|
| 752 |
+
"step": 560
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.19,
|
| 756 |
+
"learning_rate": 0.0001255301310311332,
|
| 757 |
+
"loss": 1.2561,
|
| 758 |
+
"step": 565
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.26,
|
| 762 |
+
"learning_rate": 0.00011542314562479977,
|
| 763 |
+
"loss": 1.2462,
|
| 764 |
+
"step": 570
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.33,
|
| 768 |
+
"learning_rate": 0.00010289999999999993,
|
| 769 |
+
"loss": 1.2013,
|
| 770 |
+
"step": 575
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.41,
|
| 774 |
+
"learning_rate": 8.860691144660113e-05,
|
| 775 |
+
"loss": 1.2052,
|
| 776 |
+
"step": 580
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.48,
|
| 780 |
+
"learning_rate": 7.328142955681657e-05,
|
| 781 |
+
"loss": 1.3885,
|
| 782 |
+
"step": 585
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.55,
|
| 786 |
+
"learning_rate": 5.771437731310106e-05,
|
| 787 |
+
"loss": 1.0822,
|
| 788 |
+
"step": 590
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 8.62,
|
| 792 |
+
"learning_rate": 4.270904317137078e-05,
|
| 793 |
+
"loss": 1.3064,
|
| 794 |
+
"step": 595
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.7,
|
| 798 |
+
"learning_rate": 2.9039729902920224e-05,
|
| 799 |
+
"loss": 1.2009,
|
| 800 |
+
"step": 600
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.77,
|
| 804 |
+
"learning_rate": 1.7411799150848703e-05,
|
| 805 |
+
"loss": 1.2057,
|
| 806 |
+
"step": 605
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 8.84,
|
| 810 |
+
"learning_rate": 8.425273475182102e-06,
|
| 811 |
+
"loss": 1.1498,
|
| 812 |
+
"step": 610
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 8.91,
|
| 816 |
+
"learning_rate": 2.5438740879410024e-06,
|
| 817 |
+
"loss": 1.0197,
|
| 818 |
+
"step": 615
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 8.99,
|
| 822 |
+
"learning_rate": 7.109198783448199e-08,
|
| 823 |
+
"loss": 1.1622,
|
| 824 |
+
"step": 620
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.0,
|
| 828 |
+
"eval_loss": 1.775342345237732,
|
| 829 |
+
"eval_runtime": 3.8327,
|
| 830 |
+
"eval_samples_per_second": 22.699,
|
| 831 |
+
"eval_steps_per_second": 2.87,
|
| 832 |
+
"step": 621
|
| 833 |
}
|
| 834 |
],
|
| 835 |
+
"max_steps": 828,
|
| 836 |
+
"num_train_epochs": 12,
|
| 837 |
+
"total_flos": 642778398720000.0,
|
| 838 |
"trial_name": null,
|
| 839 |
"trial_params": null
|
| 840 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27f7066b415f01cd40fe79d9609a25d25e2e5ba0f11a92fd67adab5753419b6f
|
| 3 |
+
size 2863
|