Training in progress, step 8150, 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:de43f440f74aee26a87c96ae11724919b2937d65b4d71875f24bb5055274ed94
|
| 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 sha256:54e4cc0bd90d8382477cba925e9ba93d39c4af54b212aafea9c81b2ecdcedcef
|
| 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 sha256:61462b73964a29580f2456bfee9a254c5ad98c8268241d058729b65e76cfa72f
|
| 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": 62.
|
| 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,
|
|
@@ -14660,6 +14660,24 @@
|
|
| 14660 |
"mean_token_accuracy": 0.6421294629573822,
|
| 14661 |
"num_tokens": 29686310.0,
|
| 14662 |
"step": 8140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14663 |
}
|
| 14664 |
],
|
| 14665 |
"logging_steps": 5,
|
|
@@ -14679,7 +14697,7 @@
|
|
| 14679 |
"attributes": {}
|
| 14680 |
}
|
| 14681 |
},
|
| 14682 |
-
"total_flos": 1.
|
| 14683 |
"train_batch_size": 4,
|
| 14684 |
"trial_name": null,
|
| 14685 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14660 |
"mean_token_accuracy": 0.6421294629573822,
|
| 14661 |
"num_tokens": 29686310.0,
|
| 14662 |
"step": 8140
|
| 14663 |
+
},
|
| 14664 |
+
{
|
| 14665 |
+
"epoch": 62.65384615384615,
|
| 14666 |
+
"grad_norm": 0.0,
|
| 14667 |
+
"learning_rate": 9.28e-06,
|
| 14668 |
+
"loss": 1.6784,
|
| 14669 |
+
"mean_token_accuracy": 0.6623817592859268,
|
| 14670 |
+
"num_tokens": 29705325.0,
|
| 14671 |
+
"step": 8145
|
| 14672 |
+
},
|
| 14673 |
+
{
|
| 14674 |
+
"epoch": 62.69230769230769,
|
| 14675 |
+
"grad_norm": 0.0,
|
| 14676 |
+
"learning_rate": 9.255e-06,
|
| 14677 |
+
"loss": 1.6656,
|
| 14678 |
+
"mean_token_accuracy": 0.6657170474529266,
|
| 14679 |
+
"num_tokens": 29724477.0,
|
| 14680 |
+
"step": 8150
|
| 14681 |
}
|
| 14682 |
],
|
| 14683 |
"logging_steps": 5,
|
|
|
|
| 14697 |
"attributes": {}
|
| 14698 |
}
|
| 14699 |
},
|
| 14700 |
+
"total_flos": 1.5070951369064448e+18,
|
| 14701 |
"train_batch_size": 4,
|
| 14702 |
"trial_name": null,
|
| 14703 |
"trial_params": null
|