Training in progress, step 9830, 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:aefe2b45d031a5d4e5dcbf3cdaad0644aa9e53d6ad4cd193f60e75b95a288004
|
| 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 sha256:947ba22482f94b95d6f1447f0652a064adc8f020db2ac62e7395d0b9e1cbcbda
|
| 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:adec07227d7ba5680587967ee4f0d7098eef3788ca01b6957fb6773f23de5be0
|
| 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": 75.
|
| 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,
|
|
@@ -17684,6 +17684,24 @@
|
|
| 17684 |
"mean_token_accuracy": 0.6560279041528702,
|
| 17685 |
"num_tokens": 35814453.0,
|
| 17686 |
"step": 9820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17687 |
}
|
| 17688 |
],
|
| 17689 |
"logging_steps": 5,
|
|
@@ -17703,7 +17721,7 @@
|
|
| 17703 |
"attributes": {}
|
| 17704 |
}
|
| 17705 |
},
|
| 17706 |
-
"total_flos": 1.
|
| 17707 |
"train_batch_size": 4,
|
| 17708 |
"trial_name": null,
|
| 17709 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17684 |
"mean_token_accuracy": 0.6560279041528702,
|
| 17685 |
"num_tokens": 35814453.0,
|
| 17686 |
"step": 9820
|
| 17687 |
+
},
|
| 17688 |
+
{
|
| 17689 |
+
"epoch": 75.57692307692308,
|
| 17690 |
+
"grad_norm": 0.0,
|
| 17691 |
+
"learning_rate": 8.8e-07,
|
| 17692 |
+
"loss": 1.717,
|
| 17693 |
+
"mean_token_accuracy": 0.6553375959396363,
|
| 17694 |
+
"num_tokens": 35833053.0,
|
| 17695 |
+
"step": 9825
|
| 17696 |
+
},
|
| 17697 |
+
{
|
| 17698 |
+
"epoch": 75.61538461538461,
|
| 17699 |
+
"grad_norm": 0.0,
|
| 17700 |
+
"learning_rate": 8.550000000000001e-07,
|
| 17701 |
+
"loss": 1.7881,
|
| 17702 |
+
"mean_token_accuracy": 0.6422079712152481,
|
| 17703 |
+
"num_tokens": 35850712.0,
|
| 17704 |
+
"step": 9830
|
| 17705 |
}
|
| 17706 |
],
|
| 17707 |
"logging_steps": 5,
|
|
|
|
| 17721 |
"attributes": {}
|
| 17722 |
}
|
| 17723 |
},
|
| 17724 |
+
"total_flos": 1.8180486932402995e+18,
|
| 17725 |
"train_batch_size": 4,
|
| 17726 |
"trial_name": null,
|
| 17727 |
"trial_params": null
|