Training in progress, step 1440, 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:bdf0ccec84ccdf8d9ec87a4284f888bc5b3f01b1a9e7fe8447d56e6242acef3c
|
| 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 sha256:9b9960649b6dfea5f1f6f5642a72a38b2900a023333a3f2232095293dbb80bd7
|
| 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 sha256:96702c5c2baf928ebec769b10f312fb6ff86741cdf03a62117e935e503086a5c
|
| 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": 11.
|
| 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,
|
|
@@ -2582,6 +2582,24 @@
|
|
| 2582 |
"mean_token_accuracy": 0.642606571316719,
|
| 2583 |
"num_tokens": 5215155.0,
|
| 2584 |
"step": 1430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2585 |
}
|
| 2586 |
],
|
| 2587 |
"logging_steps": 5,
|
|
@@ -2601,7 +2619,7 @@
|
|
| 2601 |
"attributes": {}
|
| 2602 |
}
|
| 2603 |
},
|
| 2604 |
-
"total_flos": 2.
|
| 2605 |
"train_batch_size": 4,
|
| 2606 |
"trial_name": null,
|
| 2607 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2582 |
"mean_token_accuracy": 0.642606571316719,
|
| 2583 |
"num_tokens": 5215155.0,
|
| 2584 |
"step": 1430
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 11.038461538461538,
|
| 2588 |
+
"grad_norm": 0.0,
|
| 2589 |
+
"learning_rate": 4.283e-05,
|
| 2590 |
+
"loss": 1.7845,
|
| 2591 |
+
"mean_token_accuracy": 0.6424670696258545,
|
| 2592 |
+
"num_tokens": 5232784.0,
|
| 2593 |
+
"step": 1435
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 11.076923076923077,
|
| 2597 |
+
"grad_norm": 0.0,
|
| 2598 |
+
"learning_rate": 4.2805e-05,
|
| 2599 |
+
"loss": 1.7199,
|
| 2600 |
+
"mean_token_accuracy": 0.6572603791952133,
|
| 2601 |
+
"num_tokens": 5250874.0,
|
| 2602 |
+
"step": 1440
|
| 2603 |
}
|
| 2604 |
],
|
| 2605 |
"logging_steps": 5,
|
|
|
|
| 2619 |
"attributes": {}
|
| 2620 |
}
|
| 2621 |
},
|
| 2622 |
+
"total_flos": 2.659884135727104e+17,
|
| 2623 |
"train_batch_size": 4,
|
| 2624 |
"trial_name": null,
|
| 2625 |
"trial_params": null
|