Training in progress, step 6990, 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 sha256:938817135f3c58bc5a11f38eaf13b52cd98d0403d4f9ca60c8b9ec624c32f15f
|
| 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 sha256:5c5b26016da5926617c54a811aa27cad28beaacda5c67c04b037b8c67c38f2cd
|
| 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:d88f01624b564231b133214414df0e71cc532e47710fb26c20bec9fa91d0bc5a
|
| 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": 53.
|
| 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,
|
|
@@ -12572,6 +12572,24 @@
|
|
| 12572 |
"mean_token_accuracy": 0.6556006103754044,
|
| 12573 |
"num_tokens": 25455960.0,
|
| 12574 |
"step": 6980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12575 |
}
|
| 12576 |
],
|
| 12577 |
"logging_steps": 5,
|
|
@@ -12591,7 +12609,7 @@
|
|
| 12591 |
"attributes": {}
|
| 12592 |
}
|
| 12593 |
},
|
| 12594 |
-
"total_flos": 1.
|
| 12595 |
"train_batch_size": 4,
|
| 12596 |
"trial_name": null,
|
| 12597 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12572 |
"mean_token_accuracy": 0.6556006103754044,
|
| 12573 |
"num_tokens": 25455960.0,
|
| 12574 |
"step": 6980
|
| 12575 |
+
},
|
| 12576 |
+
{
|
| 12577 |
+
"epoch": 53.73076923076923,
|
| 12578 |
+
"grad_norm": 0.0,
|
| 12579 |
+
"learning_rate": 1.508e-05,
|
| 12580 |
+
"loss": 1.7452,
|
| 12581 |
+
"mean_token_accuracy": 0.6496385037899017,
|
| 12582 |
+
"num_tokens": 25474285.0,
|
| 12583 |
+
"step": 6985
|
| 12584 |
+
},
|
| 12585 |
+
{
|
| 12586 |
+
"epoch": 53.76923076923077,
|
| 12587 |
+
"grad_norm": 0.0,
|
| 12588 |
+
"learning_rate": 1.5054999999999999e-05,
|
| 12589 |
+
"loss": 1.7495,
|
| 12590 |
+
"mean_token_accuracy": 0.6455465704202652,
|
| 12591 |
+
"num_tokens": 25492111.0,
|
| 12592 |
+
"step": 6990
|
| 12593 |
}
|
| 12594 |
],
|
| 12595 |
"logging_steps": 5,
|
|
|
|
| 12609 |
"attributes": {}
|
| 12610 |
}
|
| 12611 |
},
|
| 12612 |
+
"total_flos": 1.2925702202130432e+18,
|
| 12613 |
"train_batch_size": 4,
|
| 12614 |
"trial_name": null,
|
| 12615 |
"trial_params": null
|