Training in progress, step 1430, 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:be15b1b6adcfb2f6f42d909ab91234fb1caae5211a822babe777efa6c58d96d5
|
| 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 sha256:5982b205268d47d68ae0658f676446e5ebe8443f550e22845d55c2d859c65a30
|
| 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 sha256:83457607e82dd77fd3b5efd1f1ea95d51b8d997b1ac76221b6e57e7d569ea1be
|
| 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,
|
|
@@ -2564,6 +2564,24 @@
|
|
| 2564 |
"mean_token_accuracy": 0.6468683093786239,
|
| 2565 |
"num_tokens": 5179282.0,
|
| 2566 |
"step": 1420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2567 |
}
|
| 2568 |
],
|
| 2569 |
"logging_steps": 5,
|
|
@@ -2583,7 +2601,7 @@
|
|
| 2583 |
"attributes": {}
|
| 2584 |
}
|
| 2585 |
},
|
| 2586 |
-
"total_flos": 2.
|
| 2587 |
"train_batch_size": 4,
|
| 2588 |
"trial_name": null,
|
| 2589 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2564 |
"mean_token_accuracy": 0.6468683093786239,
|
| 2565 |
"num_tokens": 5179282.0,
|
| 2566 |
"step": 1420
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 10.961538461538462,
|
| 2570 |
+
"grad_norm": 0.0,
|
| 2571 |
+
"learning_rate": 4.288e-05,
|
| 2572 |
+
"loss": 1.6856,
|
| 2573 |
+
"mean_token_accuracy": 0.6599813520908355,
|
| 2574 |
+
"num_tokens": 5197538.0,
|
| 2575 |
+
"step": 1425
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 11.0,
|
| 2579 |
+
"grad_norm": 0.0,
|
| 2580 |
+
"learning_rate": 4.2855e-05,
|
| 2581 |
+
"loss": 1.7956,
|
| 2582 |
+
"mean_token_accuracy": 0.642606571316719,
|
| 2583 |
+
"num_tokens": 5215155.0,
|
| 2584 |
+
"step": 1430
|
| 2585 |
}
|
| 2586 |
],
|
| 2587 |
"logging_steps": 5,
|
|
|
|
| 2601 |
"attributes": {}
|
| 2602 |
}
|
| 2603 |
},
|
| 2604 |
+
"total_flos": 2.6420595887702016e+17,
|
| 2605 |
"train_batch_size": 4,
|
| 2606 |
"trial_name": null,
|
| 2607 |
"trial_params": null
|