Training in progress, step 7480, 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:f2fbdc825790534c5ec4d41f6ad2d90771f26edfdb946f98a9c6fb8c74627556
|
| 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 sha256:530f544c3b4fc1e8424eeea6e94cbe3322a06166cfe00f0c5ec97e2beef9bf5b
|
| 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 sha256:9e6f085ee5f5b1792161a07a29028d8b4eda9d38e95b2879552c16e6d4a5e0aa
|
| 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": 57.
|
| 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,
|
|
@@ -13454,6 +13454,24 @@
|
|
| 13454 |
"mean_token_accuracy": 0.6468398660421372,
|
| 13455 |
"num_tokens": 27243113.0,
|
| 13456 |
"step": 7470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13457 |
}
|
| 13458 |
],
|
| 13459 |
"logging_steps": 5,
|
|
@@ -13473,7 +13491,7 @@
|
|
| 13473 |
"attributes": {}
|
| 13474 |
}
|
| 13475 |
},
|
| 13476 |
-
"total_flos": 1.
|
| 13477 |
"train_batch_size": 4,
|
| 13478 |
"trial_name": null,
|
| 13479 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13454 |
"mean_token_accuracy": 0.6468398660421372,
|
| 13455 |
"num_tokens": 27243113.0,
|
| 13456 |
"step": 7470
|
| 13457 |
+
},
|
| 13458 |
+
{
|
| 13459 |
+
"epoch": 57.5,
|
| 13460 |
+
"grad_norm": 0.0,
|
| 13461 |
+
"learning_rate": 1.263e-05,
|
| 13462 |
+
"loss": 1.7591,
|
| 13463 |
+
"mean_token_accuracy": 0.6493138283491134,
|
| 13464 |
+
"num_tokens": 27261095.0,
|
| 13465 |
+
"step": 7475
|
| 13466 |
+
},
|
| 13467 |
+
{
|
| 13468 |
+
"epoch": 57.53846153846154,
|
| 13469 |
+
"grad_norm": 0.0,
|
| 13470 |
+
"learning_rate": 1.2605e-05,
|
| 13471 |
+
"loss": 1.7276,
|
| 13472 |
+
"mean_token_accuracy": 0.6510590463876724,
|
| 13473 |
+
"num_tokens": 27279536.0,
|
| 13474 |
+
"step": 7480
|
| 13475 |
}
|
| 13476 |
],
|
| 13477 |
"logging_steps": 5,
|
|
|
|
| 13491 |
"attributes": {}
|
| 13492 |
}
|
| 13493 |
},
|
| 13494 |
+
"total_flos": 1.3831203795222528e+18,
|
| 13495 |
"train_batch_size": 4,
|
| 13496 |
"trial_name": null,
|
| 13497 |
"trial_params": null
|