Training in progress, step 2470, 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 sha256:97758d64fed3826776aac0d51d71f8bcd85f441350353d1d52e16b8b8effb717
|
| 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 sha256:938cb363993415df831d0696cb1749770d00074a6c8f893e26c9fcf7c0c33216
|
| 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 sha256:882352bc8ab8704ba0240ad44ec9f6a43a3cc9f3bd98edbd2c261cfd49179506
|
| 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":
|
| 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,
|
|
@@ -4436,6 +4436,24 @@
|
|
| 4436 |
"mean_token_accuracy": 0.6640833884477615,
|
| 4437 |
"num_tokens": 8970281.0,
|
| 4438 |
"step": 2460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4439 |
}
|
| 4440 |
],
|
| 4441 |
"logging_steps": 5,
|
|
@@ -4455,7 +4473,7 @@
|
|
| 4455 |
"attributes": {}
|
| 4456 |
}
|
| 4457 |
},
|
| 4458 |
-
"total_flos": 4.
|
| 4459 |
"train_batch_size": 4,
|
| 4460 |
"trial_name": null,
|
| 4461 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4436 |
"mean_token_accuracy": 0.6640833884477615,
|
| 4437 |
"num_tokens": 8970281.0,
|
| 4438 |
"step": 2460
|
| 4439 |
+
},
|
| 4440 |
+
{
|
| 4441 |
+
"epoch": 18.96153846153846,
|
| 4442 |
+
"grad_norm": 0.0,
|
| 4443 |
+
"learning_rate": 3.7680000000000005e-05,
|
| 4444 |
+
"loss": 1.6164,
|
| 4445 |
+
"mean_token_accuracy": 0.6714823067188262,
|
| 4446 |
+
"num_tokens": 8989804.0,
|
| 4447 |
+
"step": 2465
|
| 4448 |
+
},
|
| 4449 |
+
{
|
| 4450 |
+
"epoch": 19.0,
|
| 4451 |
+
"grad_norm": 0.0,
|
| 4452 |
+
"learning_rate": 3.7655000000000005e-05,
|
| 4453 |
+
"loss": 1.8069,
|
| 4454 |
+
"mean_token_accuracy": 0.634514644742012,
|
| 4455 |
+
"num_tokens": 9007995.0,
|
| 4456 |
+
"step": 2470
|
| 4457 |
}
|
| 4458 |
],
|
| 4459 |
"logging_steps": 5,
|
|
|
|
| 4473 |
"attributes": {}
|
| 4474 |
}
|
| 4475 |
},
|
| 4476 |
+
"total_flos": 4.56513862311936e+17,
|
| 4477 |
"train_batch_size": 4,
|
| 4478 |
"trial_name": null,
|
| 4479 |
"trial_params": null
|