Training in progress, step 5790, 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:b602de067b3eeb5d36f756ea61848f9b4a77f5d98297e380ec20edd2379a34a0
|
| 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 sha256:95a5141fdaf5b6933d0cde6674113069c1b398a8eb0376ea22ce2e4d7e05b817
|
| 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 sha256:3ac7f651dffdd41ccae653490b0928e0d257b108bc194507bebbbe2779470e92
|
| 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": 44.
|
| 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,
|
|
@@ -10412,6 +10412,24 @@
|
|
| 10412 |
"mean_token_accuracy": 0.655006617307663,
|
| 10413 |
"num_tokens": 21078736.0,
|
| 10414 |
"step": 5780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10415 |
}
|
| 10416 |
],
|
| 10417 |
"logging_steps": 5,
|
|
@@ -10431,7 +10449,7 @@
|
|
| 10431 |
"attributes": {}
|
| 10432 |
}
|
| 10433 |
},
|
| 10434 |
-
"total_flos": 1.
|
| 10435 |
"train_batch_size": 4,
|
| 10436 |
"trial_name": null,
|
| 10437 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10412 |
"mean_token_accuracy": 0.655006617307663,
|
| 10413 |
"num_tokens": 21078736.0,
|
| 10414 |
"step": 5780
|
| 10415 |
+
},
|
| 10416 |
+
{
|
| 10417 |
+
"epoch": 44.5,
|
| 10418 |
+
"grad_norm": 0.0,
|
| 10419 |
+
"learning_rate": 2.1079999999999998e-05,
|
| 10420 |
+
"loss": 1.7458,
|
| 10421 |
+
"mean_token_accuracy": 0.648220095038414,
|
| 10422 |
+
"num_tokens": 21097223.0,
|
| 10423 |
+
"step": 5785
|
| 10424 |
+
},
|
| 10425 |
+
{
|
| 10426 |
+
"epoch": 44.53846153846154,
|
| 10427 |
+
"grad_norm": 0.0,
|
| 10428 |
+
"learning_rate": 2.1055e-05,
|
| 10429 |
+
"loss": 1.6928,
|
| 10430 |
+
"mean_token_accuracy": 0.6601225137710571,
|
| 10431 |
+
"num_tokens": 21116083.0,
|
| 10432 |
+
"step": 5790
|
| 10433 |
}
|
| 10434 |
],
|
| 10435 |
"logging_steps": 5,
|
|
|
|
| 10449 |
"attributes": {}
|
| 10450 |
}
|
| 10451 |
},
|
| 10452 |
+
"total_flos": 1.0700399765245133e+18,
|
| 10453 |
"train_batch_size": 4,
|
| 10454 |
"trial_name": null,
|
| 10455 |
"trial_params": null
|