Training in progress, step 9310, 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 sha256:1e6e31aef638ba3813d5a527616603cac85472ce3bfb4a2ff052ce416b9e6f70
|
| 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 sha256:56356d25971e632c13557761540847286407f55bf1ce1a5236d9887501efb02e
|
| 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 sha256:28c1cf4e9d85f48f16a26904c4b8a6d9016c1366e95be6c16e96125480d6ac08
|
| 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": 71.
|
| 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,
|
|
@@ -16748,6 +16748,24 @@
|
|
| 16748 |
"mean_token_accuracy": 0.647359648346901,
|
| 16749 |
"num_tokens": 33918686.0,
|
| 16750 |
"step": 9300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16751 |
}
|
| 16752 |
],
|
| 16753 |
"logging_steps": 5,
|
|
@@ -16767,7 +16785,7 @@
|
|
| 16767 |
"attributes": {}
|
| 16768 |
}
|
| 16769 |
},
|
| 16770 |
-
"total_flos": 1.
|
| 16771 |
"train_batch_size": 4,
|
| 16772 |
"trial_name": null,
|
| 16773 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16748 |
"mean_token_accuracy": 0.647359648346901,
|
| 16749 |
"num_tokens": 33918686.0,
|
| 16750 |
"step": 9300
|
| 16751 |
+
},
|
| 16752 |
+
{
|
| 16753 |
+
"epoch": 71.57692307692308,
|
| 16754 |
+
"grad_norm": 0.0,
|
| 16755 |
+
"learning_rate": 3.4799999999999997e-06,
|
| 16756 |
+
"loss": 1.6996,
|
| 16757 |
+
"mean_token_accuracy": 0.6571532785892487,
|
| 16758 |
+
"num_tokens": 33937081.0,
|
| 16759 |
+
"step": 9305
|
| 16760 |
+
},
|
| 16761 |
+
{
|
| 16762 |
+
"epoch": 71.61538461538461,
|
| 16763 |
+
"grad_norm": 0.0,
|
| 16764 |
+
"learning_rate": 3.455e-06,
|
| 16765 |
+
"loss": 1.7333,
|
| 16766 |
+
"mean_token_accuracy": 0.6503713637590408,
|
| 16767 |
+
"num_tokens": 33954828.0,
|
| 16768 |
+
"step": 9310
|
| 16769 |
}
|
| 16770 |
],
|
| 16771 |
"logging_steps": 5,
|
|
|
|
| 16785 |
"attributes": {}
|
| 16786 |
}
|
| 16787 |
},
|
| 16788 |
+
"total_flos": 1.7218383749259264e+18,
|
| 16789 |
"train_batch_size": 4,
|
| 16790 |
"trial_name": null,
|
| 16791 |
"trial_params": null
|