Training in progress, step 6480, 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 sha256:3b702dd5702cff4459e260d063d5f27e858bbbf79e5ca3e229be18ac80c003db
|
| 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 sha256:63f58ea6990c9253a2a81629bc3fbe878bf8c0d75bd2d7223397e10a1f077ef9
|
| 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 sha256:6dc9824fb4513b90f37b248c6c324b588cd09924ce55c260d82e33ec18ad651f
|
| 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": 49.
|
| 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,
|
|
@@ -11654,6 +11654,24 @@
|
|
| 11654 |
"mean_token_accuracy": 0.639831280708313,
|
| 11655 |
"num_tokens": 23596069.0,
|
| 11656 |
"step": 6470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11657 |
}
|
| 11658 |
],
|
| 11659 |
"logging_steps": 5,
|
|
@@ -11673,7 +11691,7 @@
|
|
| 11673 |
"attributes": {}
|
| 11674 |
}
|
| 11675 |
},
|
| 11676 |
-
"total_flos": 1.
|
| 11677 |
"train_batch_size": 4,
|
| 11678 |
"trial_name": null,
|
| 11679 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11654 |
"mean_token_accuracy": 0.639831280708313,
|
| 11655 |
"num_tokens": 23596069.0,
|
| 11656 |
"step": 6470
|
| 11657 |
+
},
|
| 11658 |
+
{
|
| 11659 |
+
"epoch": 49.80769230769231,
|
| 11660 |
+
"grad_norm": 0.0,
|
| 11661 |
+
"learning_rate": 1.7630000000000002e-05,
|
| 11662 |
+
"loss": 1.8093,
|
| 11663 |
+
"mean_token_accuracy": 0.6422061920166016,
|
| 11664 |
+
"num_tokens": 23612951.0,
|
| 11665 |
+
"step": 6475
|
| 11666 |
+
},
|
| 11667 |
+
{
|
| 11668 |
+
"epoch": 49.84615384615385,
|
| 11669 |
+
"grad_norm": 0.0,
|
| 11670 |
+
"learning_rate": 1.7605000000000002e-05,
|
| 11671 |
+
"loss": 1.7392,
|
| 11672 |
+
"mean_token_accuracy": 0.6497550249099732,
|
| 11673 |
+
"num_tokens": 23632333.0,
|
| 11674 |
+
"step": 6480
|
| 11675 |
}
|
| 11676 |
],
|
| 11677 |
"logging_steps": 5,
|
|
|
|
| 11691 |
"attributes": {}
|
| 11692 |
}
|
| 11693 |
},
|
| 11694 |
+
"total_flos": 1.1980348631123558e+18,
|
| 11695 |
"train_batch_size": 4,
|
| 11696 |
"trial_name": null,
|
| 11697 |
"trial_params": null
|