Training in progress, step 4840, 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 sha256:1a6d99943c9b0c1733aea57bcbfc5c940622bc9b5e532486d990545e3319b320
|
| 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 sha256:53a6f0107666bdf4ab71bc389f00d24fe017f2847f27a615d3fd251d05bd3310
|
| 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 sha256:5913575cf9d59969169fe494f0421956dc39a1c0781185c20e63bec63fb1403a
|
| 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": 37.
|
| 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,
|
|
@@ -8702,6 +8702,24 @@
|
|
| 8702 |
"mean_token_accuracy": 0.6589970797300339,
|
| 8703 |
"num_tokens": 17616052.0,
|
| 8704 |
"step": 4830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8705 |
}
|
| 8706 |
],
|
| 8707 |
"logging_steps": 5,
|
|
@@ -8721,7 +8739,7 @@
|
|
| 8721 |
"attributes": {}
|
| 8722 |
}
|
| 8723 |
},
|
| 8724 |
-
"total_flos": 8.
|
| 8725 |
"train_batch_size": 4,
|
| 8726 |
"trial_name": null,
|
| 8727 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8702 |
"mean_token_accuracy": 0.6589970797300339,
|
| 8703 |
"num_tokens": 17616052.0,
|
| 8704 |
"step": 4830
|
| 8705 |
+
},
|
| 8706 |
+
{
|
| 8707 |
+
"epoch": 37.19230769230769,
|
| 8708 |
+
"grad_norm": 0.0,
|
| 8709 |
+
"learning_rate": 2.583e-05,
|
| 8710 |
+
"loss": 1.7732,
|
| 8711 |
+
"mean_token_accuracy": 0.6425283402204514,
|
| 8712 |
+
"num_tokens": 17633798.0,
|
| 8713 |
+
"step": 4835
|
| 8714 |
+
},
|
| 8715 |
+
{
|
| 8716 |
+
"epoch": 37.23076923076923,
|
| 8717 |
+
"grad_norm": 0.0,
|
| 8718 |
+
"learning_rate": 2.5805e-05,
|
| 8719 |
+
"loss": 1.7705,
|
| 8720 |
+
"mean_token_accuracy": 0.6458623111248016,
|
| 8721 |
+
"num_tokens": 17651657.0,
|
| 8722 |
+
"step": 4840
|
| 8723 |
}
|
| 8724 |
],
|
| 8725 |
"logging_steps": 5,
|
|
|
|
| 8739 |
"attributes": {}
|
| 8740 |
}
|
| 8741 |
},
|
| 8742 |
+
"total_flos": 8.945118532642406e+17,
|
| 8743 |
"train_batch_size": 4,
|
| 8744 |
"trial_name": null,
|
| 8745 |
"trial_params": null
|