Training in progress, step 6570, 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 sha256:6fde86fb7324deb7cb6d5ca1e5a2e68a9d6ce01a34c329936c055039b63ef75b
|
| 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 sha256:86605a31a4fb688318bbb023bfe64eb89917ec88ff1169da20e06fab302d5439
|
| 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:dbaf8e29b73d31eb48e00a215ee08cb9bba350e8fd8060dcf6f11a30ca8f610d
|
| 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,
|
|
@@ -11816,6 +11816,24 @@
|
|
| 11816 |
"mean_token_accuracy": 0.6480530560016632,
|
| 11817 |
"num_tokens": 23925538.0,
|
| 11818 |
"step": 6560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11819 |
}
|
| 11820 |
],
|
| 11821 |
"logging_steps": 5,
|
|
@@ -11835,7 +11853,7 @@
|
|
| 11835 |
"attributes": {}
|
| 11836 |
}
|
| 11837 |
},
|
| 11838 |
-
"total_flos": 1.
|
| 11839 |
"train_batch_size": 4,
|
| 11840 |
"trial_name": null,
|
| 11841 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11816 |
"mean_token_accuracy": 0.6480530560016632,
|
| 11817 |
"num_tokens": 23925538.0,
|
| 11818 |
"step": 6560
|
| 11819 |
+
},
|
| 11820 |
+
{
|
| 11821 |
+
"epoch": 50.5,
|
| 11822 |
+
"grad_norm": 0.0,
|
| 11823 |
+
"learning_rate": 1.718e-05,
|
| 11824 |
+
"loss": 1.7476,
|
| 11825 |
+
"mean_token_accuracy": 0.6457035690546036,
|
| 11826 |
+
"num_tokens": 23943937.0,
|
| 11827 |
+
"step": 6565
|
| 11828 |
+
},
|
| 11829 |
+
{
|
| 11830 |
+
"epoch": 50.53846153846154,
|
| 11831 |
+
"grad_norm": 0.0,
|
| 11832 |
+
"learning_rate": 1.7155e-05,
|
| 11833 |
+
"loss": 1.829,
|
| 11834 |
+
"mean_token_accuracy": 0.6348341315984726,
|
| 11835 |
+
"num_tokens": 23961264.0,
|
| 11836 |
+
"step": 6570
|
| 11837 |
}
|
| 11838 |
],
|
| 11839 |
"logging_steps": 5,
|
|
|
|
| 11853 |
"attributes": {}
|
| 11854 |
}
|
| 11855 |
},
|
| 11856 |
+
"total_flos": 1.214810673808343e+18,
|
| 11857 |
"train_batch_size": 4,
|
| 11858 |
"trial_name": null,
|
| 11859 |
"trial_params": null
|