Training in progress, step 300, 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 sha256:575371e3a04b985b27f6fc3d359bc5b8e6218f8db508f32ba6a15782667cab61
|
| 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 sha256:486bfff40aa9ab46f2ec17284b015caaff8f169fe1b3a0c440e83b55898d0708
|
| 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 sha256:479a04f68c66bee1de11b23d01dd4a9e91c4d2f736fa60c001d8e3c4aa526794
|
| 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": 2.
|
| 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,
|
|
@@ -530,6 +530,24 @@
|
|
| 530 |
"mean_token_accuracy": 0.6483366042375565,
|
| 531 |
"num_tokens": 1059633.0,
|
| 532 |
"step": 290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 533 |
}
|
| 534 |
],
|
| 535 |
"logging_steps": 5,
|
|
@@ -549,7 +567,7 @@
|
|
| 549 |
"attributes": {}
|
| 550 |
}
|
| 551 |
},
|
| 552 |
-
"total_flos": 5.
|
| 553 |
"train_batch_size": 4,
|
| 554 |
"trial_name": null,
|
| 555 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.3076923076923075,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 530 |
"mean_token_accuracy": 0.6483366042375565,
|
| 531 |
"num_tokens": 1059633.0,
|
| 532 |
"step": 290
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.269230769230769,
|
| 536 |
+
"grad_norm": 0.0,
|
| 537 |
+
"learning_rate": 4.8530000000000005e-05,
|
| 538 |
+
"loss": 1.6675,
|
| 539 |
+
"mean_token_accuracy": 0.6683109492063523,
|
| 540 |
+
"num_tokens": 1078768.0,
|
| 541 |
+
"step": 295
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.3076923076923075,
|
| 545 |
+
"grad_norm": 0.0,
|
| 546 |
+
"learning_rate": 4.8505e-05,
|
| 547 |
+
"loss": 1.7856,
|
| 548 |
+
"mean_token_accuracy": 0.6457105249166488,
|
| 549 |
+
"num_tokens": 1096433.0,
|
| 550 |
+
"step": 300
|
| 551 |
}
|
| 552 |
],
|
| 553 |
"logging_steps": 5,
|
|
|
|
| 567 |
"attributes": {}
|
| 568 |
}
|
| 569 |
},
|
| 570 |
+
"total_flos": 5.553411785146368e+16,
|
| 571 |
"train_batch_size": 4,
|
| 572 |
"trial_name": null,
|
| 573 |
"trial_params": null
|