Training in progress, step 5810, 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:d86d87180c19c3aa0024862becb6d7d7fdf88d3797a27e0fbed97a529b2263a9
|
| 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:dbf680bf6a7fbf6f222aa8f47aca523018bb90913efdf6f577464cf4f24ad8ca
|
| 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:a40d87c82ed636ede04d48098b5d66e144262c3ba7923adf74033573dc6bcfe8
|
| 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,
|
|
@@ -10448,6 +10448,24 @@
|
|
| 10448 |
"mean_token_accuracy": 0.6554509729146958,
|
| 10449 |
"num_tokens": 21152459.0,
|
| 10450 |
"step": 5800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10451 |
}
|
| 10452 |
],
|
| 10453 |
"logging_steps": 5,
|
|
@@ -10467,7 +10485,7 @@
|
|
| 10467 |
"attributes": {}
|
| 10468 |
}
|
| 10469 |
},
|
| 10470 |
-
"total_flos": 1.
|
| 10471 |
"train_batch_size": 4,
|
| 10472 |
"trial_name": null,
|
| 10473 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10448 |
"mean_token_accuracy": 0.6554509729146958,
|
| 10449 |
"num_tokens": 21152459.0,
|
| 10450 |
"step": 5800
|
| 10451 |
+
},
|
| 10452 |
+
{
|
| 10453 |
+
"epoch": 44.65384615384615,
|
| 10454 |
+
"grad_norm": 0.0,
|
| 10455 |
+
"learning_rate": 2.098e-05,
|
| 10456 |
+
"loss": 1.6493,
|
| 10457 |
+
"mean_token_accuracy": 0.6667488932609558,
|
| 10458 |
+
"num_tokens": 21171676.0,
|
| 10459 |
+
"step": 5805
|
| 10460 |
+
},
|
| 10461 |
+
{
|
| 10462 |
+
"epoch": 44.69230769230769,
|
| 10463 |
+
"grad_norm": 0.0,
|
| 10464 |
+
"learning_rate": 2.0955e-05,
|
| 10465 |
+
"loss": 1.8191,
|
| 10466 |
+
"mean_token_accuracy": 0.6378259479999542,
|
| 10467 |
+
"num_tokens": 21188876.0,
|
| 10468 |
+
"step": 5810
|
| 10469 |
}
|
| 10470 |
],
|
| 10471 |
"logging_steps": 5,
|
|
|
|
| 10485 |
"attributes": {}
|
| 10486 |
}
|
| 10487 |
},
|
| 10488 |
+
"total_flos": 1.0737190481220403e+18,
|
| 10489 |
"train_batch_size": 4,
|
| 10490 |
"trial_name": null,
|
| 10491 |
"trial_params": null
|