Training in progress, step 7060, 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 sha256:88066a048311790b81041c7e75cf3de318c50669524b439702a0b9df0ed80fa0
|
| 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 sha256:1e98f4b9ce5c8c695ba8d56842e11f5cbfe6b97db61dfad666348185c2c22496
|
| 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:cebf2871fe184222e4d655a684bd9bed4955f3ba3d5957a85e773340ff2acd36
|
| 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": 54.
|
| 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,
|
|
@@ -12698,6 +12698,24 @@
|
|
| 12698 |
"mean_token_accuracy": 0.6480139315128326,
|
| 12699 |
"num_tokens": 25712064.0,
|
| 12700 |
"step": 7050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12701 |
}
|
| 12702 |
],
|
| 12703 |
"logging_steps": 5,
|
|
@@ -12717,7 +12735,7 @@
|
|
| 12717 |
"attributes": {}
|
| 12718 |
}
|
| 12719 |
},
|
| 12720 |
-
"total_flos": 1.
|
| 12721 |
"train_batch_size": 4,
|
| 12722 |
"trial_name": null,
|
| 12723 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12698 |
"mean_token_accuracy": 0.6480139315128326,
|
| 12699 |
"num_tokens": 25712064.0,
|
| 12700 |
"step": 7050
|
| 12701 |
+
},
|
| 12702 |
+
{
|
| 12703 |
+
"epoch": 54.26923076923077,
|
| 12704 |
+
"grad_norm": 0.0,
|
| 12705 |
+
"learning_rate": 1.473e-05,
|
| 12706 |
+
"loss": 1.701,
|
| 12707 |
+
"mean_token_accuracy": 0.6573342353105545,
|
| 12708 |
+
"num_tokens": 25731391.0,
|
| 12709 |
+
"step": 7055
|
| 12710 |
+
},
|
| 12711 |
+
{
|
| 12712 |
+
"epoch": 54.30769230769231,
|
| 12713 |
+
"grad_norm": 0.0,
|
| 12714 |
+
"learning_rate": 1.4704999999999999e-05,
|
| 12715 |
+
"loss": 1.7046,
|
| 12716 |
+
"mean_token_accuracy": 0.6552079916000366,
|
| 12717 |
+
"num_tokens": 25750436.0,
|
| 12718 |
+
"step": 7060
|
| 12719 |
}
|
| 12720 |
],
|
| 12721 |
"logging_steps": 5,
|
|
|
|
| 12735 |
"attributes": {}
|
| 12736 |
}
|
| 12737 |
},
|
| 12738 |
+
"total_flos": 1.3056361561571328e+18,
|
| 12739 |
"train_batch_size": 4,
|
| 12740 |
"trial_name": null,
|
| 12741 |
"trial_params": null
|