Training in progress, step 6380, 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 sha256:955af6f67ca8d33dbe6e117696b3eccf8ed8fa32fc3cef12f4e3b2104d3a3e44
|
| 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:af4c188164dbed7622eb365870e80c706669ad3322c3d5eb373e741e3aa7484d
|
| 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 sha256:660362feba950dc5951a290bbf6bc4579be5f7c9b2f524a3d8595704d8b82c7f
|
| 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": 49.
|
| 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,
|
|
@@ -11474,6 +11474,24 @@
|
|
| 11474 |
"mean_token_accuracy": 0.6570287615060806,
|
| 11475 |
"num_tokens": 23231145.0,
|
| 11476 |
"step": 6370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11477 |
}
|
| 11478 |
],
|
| 11479 |
"logging_steps": 5,
|
|
@@ -11493,7 +11511,7 @@
|
|
| 11493 |
"attributes": {}
|
| 11494 |
}
|
| 11495 |
},
|
| 11496 |
-
"total_flos": 1.
|
| 11497 |
"train_batch_size": 4,
|
| 11498 |
"trial_name": null,
|
| 11499 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11474 |
"mean_token_accuracy": 0.6570287615060806,
|
| 11475 |
"num_tokens": 23231145.0,
|
| 11476 |
"step": 6370
|
| 11477 |
+
},
|
| 11478 |
+
{
|
| 11479 |
+
"epoch": 49.03846153846154,
|
| 11480 |
+
"grad_norm": 0.0,
|
| 11481 |
+
"learning_rate": 1.813e-05,
|
| 11482 |
+
"loss": 1.7494,
|
| 11483 |
+
"mean_token_accuracy": 0.6495041728019715,
|
| 11484 |
+
"num_tokens": 23249429.0,
|
| 11485 |
+
"step": 6375
|
| 11486 |
+
},
|
| 11487 |
+
{
|
| 11488 |
+
"epoch": 49.07692307692308,
|
| 11489 |
+
"grad_norm": 0.0,
|
| 11490 |
+
"learning_rate": 1.8105e-05,
|
| 11491 |
+
"loss": 1.6628,
|
| 11492 |
+
"mean_token_accuracy": 0.6711469799280166,
|
| 11493 |
+
"num_tokens": 23268600.0,
|
| 11494 |
+
"step": 6380
|
| 11495 |
}
|
| 11496 |
],
|
| 11497 |
"logging_steps": 5,
|
|
|
|
| 11511 |
"attributes": {}
|
| 11512 |
}
|
| 11513 |
},
|
| 11514 |
+
"total_flos": 1.1795129581451674e+18,
|
| 11515 |
"train_batch_size": 4,
|
| 11516 |
"trial_name": null,
|
| 11517 |
"trial_params": null
|