Training in progress, step 5910, 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 sha256:9024feb53e66556dbaa04d03fe297fb927e0204184f1b4086b1b5b8f30f031df
|
| 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 sha256:4eb2566f2d44018b60d54afa56a09d9fcef4a1e246bdf395db745dbd2c4c83ef
|
| 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:b0831391e8371d775f0709c6f4aca632e53c3a4ba8d2febedcd706bb5c6eb2c4
|
| 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": 45.
|
| 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,
|
|
@@ -10628,6 +10628,24 @@
|
|
| 10628 |
"mean_token_accuracy": 0.6537360846996307,
|
| 10629 |
"num_tokens": 21518451.0,
|
| 10630 |
"step": 5900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10631 |
}
|
| 10632 |
],
|
| 10633 |
"logging_steps": 5,
|
|
@@ -10647,7 +10665,7 @@
|
|
| 10647 |
"attributes": {}
|
| 10648 |
}
|
| 10649 |
},
|
| 10650 |
-
"total_flos": 1.
|
| 10651 |
"train_batch_size": 4,
|
| 10652 |
"trial_name": null,
|
| 10653 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10628 |
"mean_token_accuracy": 0.6537360846996307,
|
| 10629 |
"num_tokens": 21518451.0,
|
| 10630 |
"step": 5900
|
| 10631 |
+
},
|
| 10632 |
+
{
|
| 10633 |
+
"epoch": 45.42307692307692,
|
| 10634 |
+
"grad_norm": 0.0,
|
| 10635 |
+
"learning_rate": 2.048e-05,
|
| 10636 |
+
"loss": 1.7311,
|
| 10637 |
+
"mean_token_accuracy": 0.6522845417261124,
|
| 10638 |
+
"num_tokens": 21536579.0,
|
| 10639 |
+
"step": 5905
|
| 10640 |
+
},
|
| 10641 |
+
{
|
| 10642 |
+
"epoch": 45.46153846153846,
|
| 10643 |
+
"grad_norm": 0.0,
|
| 10644 |
+
"learning_rate": 2.0455000000000003e-05,
|
| 10645 |
+
"loss": 1.6915,
|
| 10646 |
+
"mean_token_accuracy": 0.658150565624237,
|
| 10647 |
+
"num_tokens": 21555889.0,
|
| 10648 |
+
"step": 5910
|
| 10649 |
}
|
| 10650 |
],
|
| 10651 |
"logging_steps": 5,
|
|
|
|
| 10665 |
"attributes": {}
|
| 10666 |
}
|
| 10667 |
},
|
| 10668 |
+
"total_flos": 1.0923306633068544e+18,
|
| 10669 |
"train_batch_size": 4,
|
| 10670 |
"trial_name": null,
|
| 10671 |
"trial_params": null
|