Training in progress, step 5820, 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 sha256:725648f2284683493539cbb939f3de9b903a985d7bb5e75b85cae0505feb64cf
|
| 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 sha256:2e687fdab59affaa70a9d00bc127cd636b6444186cdc671fb1fc8608aa09802a
|
| 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 sha256:81e9a94beb680fc43bbb4b333217bc8af5b2569591e11910fe38fd535506b314
|
| 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": 44.
|
| 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,
|
|
@@ -10466,6 +10466,24 @@
|
|
| 10466 |
"mean_token_accuracy": 0.6378259479999542,
|
| 10467 |
"num_tokens": 21188876.0,
|
| 10468 |
"step": 5810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10469 |
}
|
| 10470 |
],
|
| 10471 |
"logging_steps": 5,
|
|
@@ -10485,7 +10503,7 @@
|
|
| 10485 |
"attributes": {}
|
| 10486 |
}
|
| 10487 |
},
|
| 10488 |
-
"total_flos": 1.
|
| 10489 |
"train_batch_size": 4,
|
| 10490 |
"trial_name": null,
|
| 10491 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10466 |
"mean_token_accuracy": 0.6378259479999542,
|
| 10467 |
"num_tokens": 21188876.0,
|
| 10468 |
"step": 5810
|
| 10469 |
+
},
|
| 10470 |
+
{
|
| 10471 |
+
"epoch": 44.73076923076923,
|
| 10472 |
+
"grad_norm": 0.0,
|
| 10473 |
+
"learning_rate": 2.093e-05,
|
| 10474 |
+
"loss": 1.7046,
|
| 10475 |
+
"mean_token_accuracy": 0.6647377282381057,
|
| 10476 |
+
"num_tokens": 21207312.0,
|
| 10477 |
+
"step": 5815
|
| 10478 |
+
},
|
| 10479 |
+
{
|
| 10480 |
+
"epoch": 44.76923076923077,
|
| 10481 |
+
"grad_norm": 0.0,
|
| 10482 |
+
"learning_rate": 2.0905000000000004e-05,
|
| 10483 |
+
"loss": 1.7338,
|
| 10484 |
+
"mean_token_accuracy": 0.6526555448770524,
|
| 10485 |
+
"num_tokens": 21225855.0,
|
| 10486 |
+
"step": 5820
|
| 10487 |
}
|
| 10488 |
],
|
| 10489 |
"logging_steps": 5,
|
|
|
|
| 10503 |
"attributes": {}
|
| 10504 |
}
|
| 10505 |
},
|
| 10506 |
+
"total_flos": 1.0755756526790246e+18,
|
| 10507 |
"train_batch_size": 4,
|
| 10508 |
"trial_name": null,
|
| 10509 |
"trial_params": null
|