Training in progress, step 6550, 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:c0f49d6e177b990bfe946d022fdcf7c5cd16a212a48dfcf78ee33167eb381f13
|
| 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 sha256:2ad77c7acffca1cae06584ffdccff52db4437df766e1187903971dba6215d94a
|
| 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 sha256:372b0466770f123fe16dddcd5fc8666cb8a00242f2a186d44a4123ad876591f8
|
| 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": 50.
|
| 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,
|
|
@@ -11780,6 +11780,24 @@
|
|
| 11780 |
"mean_token_accuracy": 0.6457631707191467,
|
| 11781 |
"num_tokens": 23851205.0,
|
| 11782 |
"step": 6540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11783 |
}
|
| 11784 |
],
|
| 11785 |
"logging_steps": 5,
|
|
@@ -11799,7 +11817,7 @@
|
|
| 11799 |
"attributes": {}
|
| 11800 |
}
|
| 11801 |
},
|
| 11802 |
-
"total_flos": 1.
|
| 11803 |
"train_batch_size": 4,
|
| 11804 |
"trial_name": null,
|
| 11805 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11780 |
"mean_token_accuracy": 0.6457631707191467,
|
| 11781 |
"num_tokens": 23851205.0,
|
| 11782 |
"step": 6540
|
| 11783 |
+
},
|
| 11784 |
+
{
|
| 11785 |
+
"epoch": 50.34615384615385,
|
| 11786 |
+
"grad_norm": 0.0,
|
| 11787 |
+
"learning_rate": 1.728e-05,
|
| 11788 |
+
"loss": 1.7517,
|
| 11789 |
+
"mean_token_accuracy": 0.6463135719299317,
|
| 11790 |
+
"num_tokens": 23869701.0,
|
| 11791 |
+
"step": 6545
|
| 11792 |
+
},
|
| 11793 |
+
{
|
| 11794 |
+
"epoch": 50.38461538461539,
|
| 11795 |
+
"grad_norm": 0.0,
|
| 11796 |
+
"learning_rate": 1.7255000000000003e-05,
|
| 11797 |
+
"loss": 1.7099,
|
| 11798 |
+
"mean_token_accuracy": 0.6558305144309997,
|
| 11799 |
+
"num_tokens": 23887966.0,
|
| 11800 |
+
"step": 6550
|
| 11801 |
}
|
| 11802 |
],
|
| 11803 |
"logging_steps": 5,
|
|
|
|
| 11817 |
"attributes": {}
|
| 11818 |
}
|
| 11819 |
},
|
| 11820 |
+
"total_flos": 1.2111142952838758e+18,
|
| 11821 |
"train_batch_size": 4,
|
| 11822 |
"trial_name": null,
|
| 11823 |
"trial_params": null
|