Training in progress, step 1420, 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 sha256:51ab43356ccd53c4e90051460d55e77fd022c75a52f8500a519f17b3126274be
|
| 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 sha256:63b85af8c900b6fb251e7e8d1dc6788b4098ef39dc38c30aba8462a6d5d63296
|
| 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 sha256:50916987429f1d66ef06cadcc03a6146e3c419036bad4400fc91bbdd260bea34
|
| 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": 10.
|
| 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,
|
|
@@ -2546,6 +2546,24 @@
|
|
| 2546 |
"mean_token_accuracy": 0.6493318378925323,
|
| 2547 |
"num_tokens": 5143608.0,
|
| 2548 |
"step": 1410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2549 |
}
|
| 2550 |
],
|
| 2551 |
"logging_steps": 5,
|
|
@@ -2565,7 +2583,7 @@
|
|
| 2565 |
"attributes": {}
|
| 2566 |
}
|
| 2567 |
},
|
| 2568 |
-
"total_flos": 2.
|
| 2569 |
"train_batch_size": 4,
|
| 2570 |
"trial_name": null,
|
| 2571 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2546 |
"mean_token_accuracy": 0.6493318378925323,
|
| 2547 |
"num_tokens": 5143608.0,
|
| 2548 |
"step": 1410
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 10.884615384615385,
|
| 2552 |
+
"grad_norm": 0.0,
|
| 2553 |
+
"learning_rate": 4.2930000000000004e-05,
|
| 2554 |
+
"loss": 1.7568,
|
| 2555 |
+
"mean_token_accuracy": 0.6470446825027466,
|
| 2556 |
+
"num_tokens": 5161679.0,
|
| 2557 |
+
"step": 1415
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 10.923076923076923,
|
| 2561 |
+
"grad_norm": 0.0,
|
| 2562 |
+
"learning_rate": 4.2905000000000003e-05,
|
| 2563 |
+
"loss": 1.7742,
|
| 2564 |
+
"mean_token_accuracy": 0.6468683093786239,
|
| 2565 |
+
"num_tokens": 5179282.0,
|
| 2566 |
+
"step": 1420
|
| 2567 |
}
|
| 2568 |
],
|
| 2569 |
"logging_steps": 5,
|
|
|
|
| 2583 |
"attributes": {}
|
| 2584 |
}
|
| 2585 |
},
|
| 2586 |
+
"total_flos": 2.6239158957293568e+17,
|
| 2587 |
"train_batch_size": 4,
|
| 2588 |
"trial_name": null,
|
| 2589 |
"trial_params": null
|