Training in progress, step 3620, 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:aed281a2fb073c071c751f93d934e8bad3ba7c3b1c23177cf89be43f6bbcb081
|
| 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 sha256:381de39310edde377dc65240c671c92903568f7aaea05fa19d31767760e09359
|
| 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:aea04d860ce3fddd3576e58c7e33423046769edb6b16eba880ed5ccfc052ad22
|
| 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": 27.
|
| 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,
|
|
@@ -6506,6 +6506,24 @@
|
|
| 6506 |
"mean_token_accuracy": 0.6439048200845718,
|
| 6507 |
"num_tokens": 13165594.0,
|
| 6508 |
"step": 3610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6509 |
}
|
| 6510 |
],
|
| 6511 |
"logging_steps": 5,
|
|
@@ -6525,7 +6543,7 @@
|
|
| 6525 |
"attributes": {}
|
| 6526 |
}
|
| 6527 |
},
|
| 6528 |
-
"total_flos": 6.
|
| 6529 |
"train_batch_size": 4,
|
| 6530 |
"trial_name": null,
|
| 6531 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6506 |
"mean_token_accuracy": 0.6439048200845718,
|
| 6507 |
"num_tokens": 13165594.0,
|
| 6508 |
"step": 3610
|
| 6509 |
+
},
|
| 6510 |
+
{
|
| 6511 |
+
"epoch": 27.807692307692307,
|
| 6512 |
+
"grad_norm": 0.0,
|
| 6513 |
+
"learning_rate": 3.193e-05,
|
| 6514 |
+
"loss": 1.6987,
|
| 6515 |
+
"mean_token_accuracy": 0.6610940158367157,
|
| 6516 |
+
"num_tokens": 13183929.0,
|
| 6517 |
+
"step": 3615
|
| 6518 |
+
},
|
| 6519 |
+
{
|
| 6520 |
+
"epoch": 27.846153846153847,
|
| 6521 |
+
"grad_norm": 0.0,
|
| 6522 |
+
"learning_rate": 3.1905e-05,
|
| 6523 |
+
"loss": 1.8453,
|
| 6524 |
+
"mean_token_accuracy": 0.6301412254571914,
|
| 6525 |
+
"num_tokens": 13200878.0,
|
| 6526 |
+
"step": 3620
|
| 6527 |
}
|
| 6528 |
],
|
| 6529 |
"logging_steps": 5,
|
|
|
|
| 6543 |
"attributes": {}
|
| 6544 |
}
|
| 6545 |
},
|
| 6546 |
+
"total_flos": 6.68861123014656e+17,
|
| 6547 |
"train_batch_size": 4,
|
| 6548 |
"trial_name": null,
|
| 6549 |
"trial_params": null
|