Training in progress, step 440, 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:b033a26d385e0142a21876a136c8db89bd78f425d9aa5ea19f7f6d21c34a1fb6
|
| 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 sha256:40516e8e7b9f7d48e12a11b71524372e98a0bf10293b6cf59245a0bb8d2dda51
|
| 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:f0966ebae8a3e88fa5fc14d96cb35b335ba37dab1bb82fc8d01515a60396bfec
|
| 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": 3.
|
| 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,
|
|
@@ -782,6 +782,24 @@
|
|
| 782 |
"mean_token_accuracy": 0.6622169464826584,
|
| 783 |
"num_tokens": 1568042.0,
|
| 784 |
"step": 430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 785 |
}
|
| 786 |
],
|
| 787 |
"logging_steps": 5,
|
|
@@ -801,7 +819,7 @@
|
|
| 801 |
"attributes": {}
|
| 802 |
}
|
| 803 |
},
|
| 804 |
-
"total_flos":
|
| 805 |
"train_batch_size": 4,
|
| 806 |
"trial_name": null,
|
| 807 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.3846153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 782 |
"mean_token_accuracy": 0.6622169464826584,
|
| 783 |
"num_tokens": 1568042.0,
|
| 784 |
"step": 430
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.3461538461538463,
|
| 788 |
+
"grad_norm": 0.0,
|
| 789 |
+
"learning_rate": 4.783e-05,
|
| 790 |
+
"loss": 1.6894,
|
| 791 |
+
"mean_token_accuracy": 0.6561817824840546,
|
| 792 |
+
"num_tokens": 1586468.0,
|
| 793 |
+
"step": 435
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.3846153846153846,
|
| 797 |
+
"grad_norm": 0.0,
|
| 798 |
+
"learning_rate": 4.7805e-05,
|
| 799 |
+
"loss": 1.6675,
|
| 800 |
+
"mean_token_accuracy": 0.6636441439390183,
|
| 801 |
+
"num_tokens": 1605918.0,
|
| 802 |
+
"step": 440
|
| 803 |
}
|
| 804 |
],
|
| 805 |
"logging_steps": 5,
|
|
|
|
| 819 |
"attributes": {}
|
| 820 |
}
|
| 821 |
},
|
| 822 |
+
"total_flos": 8.133969859411968e+16,
|
| 823 |
"train_batch_size": 4,
|
| 824 |
"trial_name": null,
|
| 825 |
"trial_params": null
|