Training in progress, step 5350, 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:e39ea3aff04dc94f7ac1df62c34093691c1efc59bf44b2a29fb7fe05d87d2a75
|
| 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 sha256:877bd12164c5249e9c0c9105a917855fece2ae3ded8e839102024d66c96fab2d
|
| 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:f77e49ea49484f48357a81675af9528623fdbd628ff873b942066c198b7ee153
|
| 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,
|
|
@@ -9620,6 +9620,24 @@
|
|
| 9620 |
"mean_token_accuracy": 0.6670808821916581,
|
| 9621 |
"num_tokens": 19474660.0,
|
| 9622 |
"step": 5340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9623 |
}
|
| 9624 |
],
|
| 9625 |
"logging_steps": 5,
|
|
@@ -9639,7 +9657,7 @@
|
|
| 9639 |
"attributes": {}
|
| 9640 |
}
|
| 9641 |
},
|
| 9642 |
-
"total_flos": 9.
|
| 9643 |
"train_batch_size": 4,
|
| 9644 |
"trial_name": null,
|
| 9645 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9620 |
"mean_token_accuracy": 0.6670808821916581,
|
| 9621 |
"num_tokens": 19474660.0,
|
| 9622 |
"step": 5340
|
| 9623 |
+
},
|
| 9624 |
+
{
|
| 9625 |
+
"epoch": 41.11538461538461,
|
| 9626 |
+
"grad_norm": 0.0,
|
| 9627 |
+
"learning_rate": 2.328e-05,
|
| 9628 |
+
"loss": 1.7063,
|
| 9629 |
+
"mean_token_accuracy": 0.6591937988996506,
|
| 9630 |
+
"num_tokens": 19493457.0,
|
| 9631 |
+
"step": 5345
|
| 9632 |
+
},
|
| 9633 |
+
{
|
| 9634 |
+
"epoch": 41.15384615384615,
|
| 9635 |
+
"grad_norm": 0.0,
|
| 9636 |
+
"learning_rate": 2.3255e-05,
|
| 9637 |
+
"loss": 1.7488,
|
| 9638 |
+
"mean_token_accuracy": 0.6491418421268463,
|
| 9639 |
+
"num_tokens": 19512018.0,
|
| 9640 |
+
"step": 5350
|
| 9641 |
}
|
| 9642 |
],
|
| 9643 |
"logging_steps": 5,
|
|
|
|
| 9657 |
"attributes": {}
|
| 9658 |
}
|
| 9659 |
},
|
| 9660 |
+
"total_flos": 9.88637718946775e+17,
|
| 9661 |
"train_batch_size": 4,
|
| 9662 |
"trial_name": null,
|
| 9663 |
"trial_params": null
|