Training in progress, step 5360, 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:a0633812921489b54e92aa6a67d59e626dbfe403c2b441af76423f43089a2922
|
| 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 sha256:6a97706a34d1357aaf2a87408f07c3cffba5245ffe1c71447942bb1b4d7378b8
|
| 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 sha256:144e2bbda71ede76c3c8c022636400050fde6f2150fec6140ce30050d2baddfe
|
| 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,
|
|
@@ -9638,6 +9638,24 @@
|
|
| 9638 |
"mean_token_accuracy": 0.6491418421268463,
|
| 9639 |
"num_tokens": 19512018.0,
|
| 9640 |
"step": 5350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9641 |
}
|
| 9642 |
],
|
| 9643 |
"logging_steps": 5,
|
|
@@ -9657,7 +9675,7 @@
|
|
| 9657 |
"attributes": {}
|
| 9658 |
}
|
| 9659 |
},
|
| 9660 |
-
"total_flos": 9.
|
| 9661 |
"train_batch_size": 4,
|
| 9662 |
"trial_name": null,
|
| 9663 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9638 |
"mean_token_accuracy": 0.6491418421268463,
|
| 9639 |
"num_tokens": 19512018.0,
|
| 9640 |
"step": 5350
|
| 9641 |
+
},
|
| 9642 |
+
{
|
| 9643 |
+
"epoch": 41.19230769230769,
|
| 9644 |
+
"grad_norm": 0.0,
|
| 9645 |
+
"learning_rate": 2.3230000000000003e-05,
|
| 9646 |
+
"loss": 1.757,
|
| 9647 |
+
"mean_token_accuracy": 0.6469480991363525,
|
| 9648 |
+
"num_tokens": 19529637.0,
|
| 9649 |
+
"step": 5355
|
| 9650 |
+
},
|
| 9651 |
+
{
|
| 9652 |
+
"epoch": 41.23076923076923,
|
| 9653 |
+
"grad_norm": 0.0,
|
| 9654 |
+
"learning_rate": 2.3205000000000002e-05,
|
| 9655 |
+
"loss": 1.7163,
|
| 9656 |
+
"mean_token_accuracy": 0.6563492953777313,
|
| 9657 |
+
"num_tokens": 19548075.0,
|
| 9658 |
+
"step": 5360
|
| 9659 |
}
|
| 9660 |
],
|
| 9661 |
"logging_steps": 5,
|
|
|
|
| 9675 |
"attributes": {}
|
| 9676 |
}
|
| 9677 |
},
|
| 9678 |
+
"total_flos": 9.905187754922803e+17,
|
| 9679 |
"train_batch_size": 4,
|
| 9680 |
"trial_name": null,
|
| 9681 |
"trial_params": null
|