Training in progress, step 5370, 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 sha256:7b0181ef0e385337635a873918672280eab759c8ffbf74f87e21b401d32d4c58
|
| 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:fc7d3f3ae0ff0cf365ce37e41177fc6aa2f13fb7022030297e59ace311e9c400
|
| 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 sha256:4dc0eed2f4e276f4189c150e6dd79f9f763caf4e7a8f2e3d8716b920e01214d5
|
| 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": 41.
|
| 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,
|
|
@@ -9656,6 +9656,24 @@
|
|
| 9656 |
"mean_token_accuracy": 0.6563492953777313,
|
| 9657 |
"num_tokens": 19548075.0,
|
| 9658 |
"step": 5360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9659 |
}
|
| 9660 |
],
|
| 9661 |
"logging_steps": 5,
|
|
@@ -9675,7 +9693,7 @@
|
|
| 9675 |
"attributes": {}
|
| 9676 |
}
|
| 9677 |
},
|
| 9678 |
-
"total_flos": 9.
|
| 9679 |
"train_batch_size": 4,
|
| 9680 |
"trial_name": null,
|
| 9681 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9656 |
"mean_token_accuracy": 0.6563492953777313,
|
| 9657 |
"num_tokens": 19548075.0,
|
| 9658 |
"step": 5360
|
| 9659 |
+
},
|
| 9660 |
+
{
|
| 9661 |
+
"epoch": 41.26923076923077,
|
| 9662 |
+
"grad_norm": 0.0,
|
| 9663 |
+
"learning_rate": 2.318e-05,
|
| 9664 |
+
"loss": 1.8052,
|
| 9665 |
+
"mean_token_accuracy": 0.6417810708284378,
|
| 9666 |
+
"num_tokens": 19565579.0,
|
| 9667 |
+
"step": 5365
|
| 9668 |
+
},
|
| 9669 |
+
{
|
| 9670 |
+
"epoch": 41.30769230769231,
|
| 9671 |
+
"grad_norm": 0.0,
|
| 9672 |
+
"learning_rate": 2.3155e-05,
|
| 9673 |
+
"loss": 1.703,
|
| 9674 |
+
"mean_token_accuracy": 0.6617189884185791,
|
| 9675 |
+
"num_tokens": 19584102.0,
|
| 9676 |
+
"step": 5370
|
| 9677 |
}
|
| 9678 |
],
|
| 9679 |
"logging_steps": 5,
|
|
|
|
| 9693 |
"attributes": {}
|
| 9694 |
}
|
| 9695 |
},
|
| 9696 |
+
"total_flos": 9.923190134523494e+17,
|
| 9697 |
"train_batch_size": 4,
|
| 9698 |
"trial_name": null,
|
| 9699 |
"trial_params": null
|