Training in progress, step 4360, 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 sha256:94a49a6cbe0d813fbb742001d5b1328cefc9e91ccffd039eddb0077c110fb315
|
| 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 sha256:35d801fd836b9bc6bf7d1830f4d61b263e5ae480dc668379edb822cc39004cdd
|
| 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 sha256:6fad4433921c74f1b9ca43a4250f6b09925450193fb5c5724ae276b37ca8013b
|
| 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": 33.
|
| 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,
|
|
@@ -7838,6 +7838,24 @@
|
|
| 7838 |
"mean_token_accuracy": 0.667979073524475,
|
| 7839 |
"num_tokens": 15867134.0,
|
| 7840 |
"step": 4350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7841 |
}
|
| 7842 |
],
|
| 7843 |
"logging_steps": 5,
|
|
@@ -7857,7 +7875,7 @@
|
|
| 7857 |
"attributes": {}
|
| 7858 |
}
|
| 7859 |
},
|
| 7860 |
-
"total_flos": 8.
|
| 7861 |
"train_batch_size": 4,
|
| 7862 |
"trial_name": null,
|
| 7863 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7838 |
"mean_token_accuracy": 0.667979073524475,
|
| 7839 |
"num_tokens": 15867134.0,
|
| 7840 |
"step": 4350
|
| 7841 |
+
},
|
| 7842 |
+
{
|
| 7843 |
+
"epoch": 33.5,
|
| 7844 |
+
"grad_norm": 0.0,
|
| 7845 |
+
"learning_rate": 2.8230000000000002e-05,
|
| 7846 |
+
"loss": 1.7647,
|
| 7847 |
+
"mean_token_accuracy": 0.6481159001588821,
|
| 7848 |
+
"num_tokens": 15885242.0,
|
| 7849 |
+
"step": 4355
|
| 7850 |
+
},
|
| 7851 |
+
{
|
| 7852 |
+
"epoch": 33.53846153846154,
|
| 7853 |
+
"grad_norm": 0.0,
|
| 7854 |
+
"learning_rate": 2.8205000000000005e-05,
|
| 7855 |
+
"loss": 1.8012,
|
| 7856 |
+
"mean_token_accuracy": 0.6423881828784943,
|
| 7857 |
+
"num_tokens": 15902772.0,
|
| 7858 |
+
"step": 4360
|
| 7859 |
}
|
| 7860 |
],
|
| 7861 |
"logging_steps": 5,
|
|
|
|
| 7875 |
"attributes": {}
|
| 7876 |
}
|
| 7877 |
},
|
| 7878 |
+
"total_flos": 8.059507203199795e+17,
|
| 7879 |
"train_batch_size": 4,
|
| 7880 |
"trial_name": null,
|
| 7881 |
"trial_params": null
|