Training in progress, step 5270, 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:f6131fa8cc9e9c3816fc779289a0280a389b7405d8edd8f277573b808023a20e
|
| 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 sha256:3353e3949c13410cb9f29f9b71f5ba6aab142a67a6d6d502b1fc7b3e23aeac0b
|
| 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 sha256:85cafd581c1712c38dff2436a4735d8397844bca3f595165b2dedec659b45132
|
| 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": 40.
|
| 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,
|
|
@@ -9476,6 +9476,24 @@
|
|
| 9476 |
"mean_token_accuracy": 0.6500023663043976,
|
| 9477 |
"num_tokens": 19179916.0,
|
| 9478 |
"step": 5260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9479 |
}
|
| 9480 |
],
|
| 9481 |
"logging_steps": 5,
|
|
@@ -9495,7 +9513,7 @@
|
|
| 9495 |
"attributes": {}
|
| 9496 |
}
|
| 9497 |
},
|
| 9498 |
-
"total_flos": 9.
|
| 9499 |
"train_batch_size": 4,
|
| 9500 |
"trial_name": null,
|
| 9501 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9476 |
"mean_token_accuracy": 0.6500023663043976,
|
| 9477 |
"num_tokens": 19179916.0,
|
| 9478 |
"step": 5260
|
| 9479 |
+
},
|
| 9480 |
+
{
|
| 9481 |
+
"epoch": 40.5,
|
| 9482 |
+
"grad_norm": 0.0,
|
| 9483 |
+
"learning_rate": 2.3680000000000004e-05,
|
| 9484 |
+
"loss": 1.7584,
|
| 9485 |
+
"mean_token_accuracy": 0.6516165018081665,
|
| 9486 |
+
"num_tokens": 19197579.0,
|
| 9487 |
+
"step": 5265
|
| 9488 |
+
},
|
| 9489 |
+
{
|
| 9490 |
+
"epoch": 40.53846153846154,
|
| 9491 |
+
"grad_norm": 0.0,
|
| 9492 |
+
"learning_rate": 2.3655000000000003e-05,
|
| 9493 |
+
"loss": 1.6656,
|
| 9494 |
+
"mean_token_accuracy": 0.6603842228651047,
|
| 9495 |
+
"num_tokens": 19217073.0,
|
| 9496 |
+
"step": 5270
|
| 9497 |
}
|
| 9498 |
],
|
| 9499 |
"logging_steps": 5,
|
|
|
|
| 9513 |
"attributes": {}
|
| 9514 |
}
|
| 9515 |
},
|
| 9516 |
+
"total_flos": 9.737645587601818e+17,
|
| 9517 |
"train_batch_size": 4,
|
| 9518 |
"trial_name": null,
|
| 9519 |
"trial_params": null
|