Training in progress, step 7020, 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 sha256:855e5db550d699fb83d972848f941eb00608c3b7831d680a6b735f3b3e1125d6
|
| 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 sha256:9b50bc24580f69c5941b3707540a4b50917a20a5ad9e067a5b7b7c9ca25832ca
|
| 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 sha256:6debd41af189b61de2c81fd185989d887f3d52f5557e96e348a3c558a2df88e6
|
| 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":
|
| 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,
|
|
@@ -12626,6 +12626,24 @@
|
|
| 12626 |
"mean_token_accuracy": 0.6465475499629975,
|
| 12627 |
"num_tokens": 25564683.0,
|
| 12628 |
"step": 7010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12629 |
}
|
| 12630 |
],
|
| 12631 |
"logging_steps": 5,
|
|
@@ -12645,7 +12663,7 @@
|
|
| 12645 |
"attributes": {}
|
| 12646 |
}
|
| 12647 |
},
|
| 12648 |
-
"total_flos": 1.
|
| 12649 |
"train_batch_size": 4,
|
| 12650 |
"trial_name": null,
|
| 12651 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12626 |
"mean_token_accuracy": 0.6465475499629975,
|
| 12627 |
"num_tokens": 25564683.0,
|
| 12628 |
"step": 7010
|
| 12629 |
+
},
|
| 12630 |
+
{
|
| 12631 |
+
"epoch": 53.96153846153846,
|
| 12632 |
+
"grad_norm": 0.0,
|
| 12633 |
+
"learning_rate": 1.493e-05,
|
| 12634 |
+
"loss": 1.7459,
|
| 12635 |
+
"mean_token_accuracy": 0.6489285141229629,
|
| 12636 |
+
"num_tokens": 25582903.0,
|
| 12637 |
+
"step": 7015
|
| 12638 |
+
},
|
| 12639 |
+
{
|
| 12640 |
+
"epoch": 54.0,
|
| 12641 |
+
"grad_norm": 0.0,
|
| 12642 |
+
"learning_rate": 1.4904999999999999e-05,
|
| 12643 |
+
"loss": 1.6906,
|
| 12644 |
+
"mean_token_accuracy": 0.6570352196693421,
|
| 12645 |
+
"num_tokens": 25601670.0,
|
| 12646 |
+
"step": 7020
|
| 12647 |
}
|
| 12648 |
],
|
| 12649 |
"logging_steps": 5,
|
|
|
|
| 12663 |
"attributes": {}
|
| 12664 |
}
|
| 12665 |
},
|
| 12666 |
+
"total_flos": 1.298095575723049e+18,
|
| 12667 |
"train_batch_size": 4,
|
| 12668 |
"trial_name": null,
|
| 12669 |
"trial_params": null
|