Training in progress, step 160, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3429aa4e9d0b104a4d73558a4967ca925c2d104f441f9ab9a79006096b3bec06
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49e8fede81b14e004a1d3d4e6cef6e5b34d5d88e4c79773a2ddaf03a370f7ad6
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00aa0db240bbcd40d674164b6ae9f2b5ecd77caed110d866f9a18dde96c3efef
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -278,6 +278,24 @@
|
|
| 278 |
"mean_token_accuracy": 0.651939743757248,
|
| 279 |
"num_tokens": 546439.0,
|
| 280 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 281 |
}
|
| 282 |
],
|
| 283 |
"logging_steps": 5,
|
|
@@ -297,7 +315,7 @@
|
|
| 297 |
"attributes": {}
|
| 298 |
}
|
| 299 |
},
|
| 300 |
-
"total_flos": 2.
|
| 301 |
"train_batch_size": 4,
|
| 302 |
"trial_name": null,
|
| 303 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.2307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 278 |
"mean_token_accuracy": 0.651939743757248,
|
| 279 |
"num_tokens": 546439.0,
|
| 280 |
"step": 150
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.1923076923076923,
|
| 284 |
+
"grad_norm": 0.0,
|
| 285 |
+
"learning_rate": 4.923e-05,
|
| 286 |
+
"loss": 1.7413,
|
| 287 |
+
"mean_token_accuracy": 0.6526101022958756,
|
| 288 |
+
"num_tokens": 564750.0,
|
| 289 |
+
"step": 155
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.2307692307692308,
|
| 293 |
+
"grad_norm": 0.0,
|
| 294 |
+
"learning_rate": 4.9205e-05,
|
| 295 |
+
"loss": 1.7649,
|
| 296 |
+
"mean_token_accuracy": 0.6482356518507004,
|
| 297 |
+
"num_tokens": 582901.0,
|
| 298 |
+
"step": 160
|
| 299 |
}
|
| 300 |
],
|
| 301 |
"logging_steps": 5,
|
|
|
|
| 315 |
"attributes": {}
|
| 316 |
}
|
| 317 |
},
|
| 318 |
+
"total_flos": 2.944352854130688e+16,
|
| 319 |
"train_batch_size": 4,
|
| 320 |
"trial_name": null,
|
| 321 |
"trial_params": null
|