Training in progress, step 9720, 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:e0cb1750a851a40c8eb56756582181ef03bf0e1d5c7baf242deb5cd894302a5f
|
| 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 sha256:0b017d34b012386414e61fdcf2814d100f439f6665446d38943352646bd222e3
|
| 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 sha256:2ed0d8bbe61156318d9068db8a8d7ea8739a79a02dedad8bbcd99b5fe23acc8a
|
| 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": 74.
|
| 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,
|
|
@@ -17486,6 +17486,24 @@
|
|
| 17486 |
"mean_token_accuracy": 0.6562795639038086,
|
| 17487 |
"num_tokens": 35411155.0,
|
| 17488 |
"step": 9710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17489 |
}
|
| 17490 |
],
|
| 17491 |
"logging_steps": 5,
|
|
@@ -17505,7 +17523,7 @@
|
|
| 17505 |
"attributes": {}
|
| 17506 |
}
|
| 17507 |
},
|
| 17508 |
-
"total_flos": 1.
|
| 17509 |
"train_batch_size": 4,
|
| 17510 |
"trial_name": null,
|
| 17511 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17486 |
"mean_token_accuracy": 0.6562795639038086,
|
| 17487 |
"num_tokens": 35411155.0,
|
| 17488 |
"step": 9710
|
| 17489 |
+
},
|
| 17490 |
+
{
|
| 17491 |
+
"epoch": 74.73076923076923,
|
| 17492 |
+
"grad_norm": 0.0,
|
| 17493 |
+
"learning_rate": 1.43e-06,
|
| 17494 |
+
"loss": 1.7366,
|
| 17495 |
+
"mean_token_accuracy": 0.6549755454063415,
|
| 17496 |
+
"num_tokens": 35429377.0,
|
| 17497 |
+
"step": 9715
|
| 17498 |
+
},
|
| 17499 |
+
{
|
| 17500 |
+
"epoch": 74.76923076923077,
|
| 17501 |
+
"grad_norm": 0.0,
|
| 17502 |
+
"learning_rate": 1.405e-06,
|
| 17503 |
+
"loss": 1.6836,
|
| 17504 |
+
"mean_token_accuracy": 0.658492824435234,
|
| 17505 |
+
"num_tokens": 35448518.0,
|
| 17506 |
+
"step": 9720
|
| 17507 |
}
|
| 17508 |
],
|
| 17509 |
"logging_steps": 5,
|
|
|
|
| 17523 |
"attributes": {}
|
| 17524 |
}
|
| 17525 |
},
|
| 17526 |
+
"total_flos": 1.797720675484631e+18,
|
| 17527 |
"train_batch_size": 4,
|
| 17528 |
"trial_name": null,
|
| 17529 |
"trial_params": null
|