Training in progress, step 6300, 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 sha256:4a9a31fcc283f0be4d0deddf3a16fc73c2b6194d5f9f0b309a28c408e6ca78ee
|
| 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:fc87db8af5d0a3ba63a835f393c4f825ef2dcf646708f6d65bddb7c79c98a9a7
|
| 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:d45514f2bc77fe36313cba07aaa8cac7e5a37a7886351eedb0774d6de3f1701c
|
| 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": 48.
|
| 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,
|
|
@@ -11330,6 +11330,24 @@
|
|
| 11330 |
"mean_token_accuracy": 0.6502360552549362,
|
| 11331 |
"num_tokens": 22938888.0,
|
| 11332 |
"step": 6290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11333 |
}
|
| 11334 |
],
|
| 11335 |
"logging_steps": 5,
|
|
@@ -11349,7 +11367,7 @@
|
|
| 11349 |
"attributes": {}
|
| 11350 |
}
|
| 11351 |
},
|
| 11352 |
-
"total_flos": 1.
|
| 11353 |
"train_batch_size": 4,
|
| 11354 |
"trial_name": null,
|
| 11355 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11330 |
"mean_token_accuracy": 0.6502360552549362,
|
| 11331 |
"num_tokens": 22938888.0,
|
| 11332 |
"step": 6290
|
| 11333 |
+
},
|
| 11334 |
+
{
|
| 11335 |
+
"epoch": 48.42307692307692,
|
| 11336 |
+
"grad_norm": 0.0,
|
| 11337 |
+
"learning_rate": 1.853e-05,
|
| 11338 |
+
"loss": 1.7299,
|
| 11339 |
+
"mean_token_accuracy": 0.649975848197937,
|
| 11340 |
+
"num_tokens": 22957254.0,
|
| 11341 |
+
"step": 6295
|
| 11342 |
+
},
|
| 11343 |
+
{
|
| 11344 |
+
"epoch": 48.46153846153846,
|
| 11345 |
+
"grad_norm": 0.0,
|
| 11346 |
+
"learning_rate": 1.8505e-05,
|
| 11347 |
+
"loss": 1.7488,
|
| 11348 |
+
"mean_token_accuracy": 0.6526569038629532,
|
| 11349 |
+
"num_tokens": 22975073.0,
|
| 11350 |
+
"step": 6300
|
| 11351 |
}
|
| 11352 |
],
|
| 11353 |
"logging_steps": 5,
|
|
|
|
| 11367 |
"attributes": {}
|
| 11368 |
}
|
| 11369 |
},
|
| 11370 |
+
"total_flos": 1.1646094711416422e+18,
|
| 11371 |
"train_batch_size": 4,
|
| 11372 |
"trial_name": null,
|
| 11373 |
"trial_params": null
|