Training in progress, step 5260, 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 sha256:42c2695fe72ef60429928d70a1d022b3c070dc3a4fdfb7840ae6cb4c72ed540f
|
| 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 sha256:726b4992208d943933a33d4264fc812d370e77e0fce285f3fc7a4909de93ae92
|
| 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 sha256:9819b065ea7c4a90e5b8cbcf58df1e3d3e835b31f0c36bc45461b4a38788cadc
|
| 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": 40.
|
| 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,
|
|
@@ -9458,6 +9458,24 @@
|
|
| 9458 |
"mean_token_accuracy": 0.6454941630363464,
|
| 9459 |
"num_tokens": 19142899.0,
|
| 9460 |
"step": 5250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9461 |
}
|
| 9462 |
],
|
| 9463 |
"logging_steps": 5,
|
|
@@ -9477,7 +9495,7 @@
|
|
| 9477 |
"attributes": {}
|
| 9478 |
}
|
| 9479 |
},
|
| 9480 |
-
"total_flos": 9.
|
| 9481 |
"train_batch_size": 4,
|
| 9482 |
"trial_name": null,
|
| 9483 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9458 |
"mean_token_accuracy": 0.6454941630363464,
|
| 9459 |
"num_tokens": 19142899.0,
|
| 9460 |
"step": 5250
|
| 9461 |
+
},
|
| 9462 |
+
{
|
| 9463 |
+
"epoch": 40.42307692307692,
|
| 9464 |
+
"grad_norm": 0.0,
|
| 9465 |
+
"learning_rate": 2.373e-05,
|
| 9466 |
+
"loss": 1.7409,
|
| 9467 |
+
"mean_token_accuracy": 0.6469170600175858,
|
| 9468 |
+
"num_tokens": 19161441.0,
|
| 9469 |
+
"step": 5255
|
| 9470 |
+
},
|
| 9471 |
+
{
|
| 9472 |
+
"epoch": 40.46153846153846,
|
| 9473 |
+
"grad_norm": 0.0,
|
| 9474 |
+
"learning_rate": 2.3705e-05,
|
| 9475 |
+
"loss": 1.7284,
|
| 9476 |
+
"mean_token_accuracy": 0.6500023663043976,
|
| 9477 |
+
"num_tokens": 19179916.0,
|
| 9478 |
+
"step": 5260
|
| 9479 |
}
|
| 9480 |
],
|
| 9481 |
"logging_steps": 5,
|
|
|
|
| 9495 |
"attributes": {}
|
| 9496 |
}
|
| 9497 |
},
|
| 9498 |
+
"total_flos": 9.718654013920051e+17,
|
| 9499 |
"train_batch_size": 4,
|
| 9500 |
"trial_name": null,
|
| 9501 |
"trial_params": null
|