Training in progress, step 2610, 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 sha256:1a52424699eaafc1821e4a9813e3cd59645697ffa84a59db4f6ccf5472c2dcee
|
| 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 sha256:08228b1027e182d5243cd088cfabdf579ece7d43f31d9085286ae7a6a2241daf
|
| 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 sha256:3fa8b95544bc64a609e1274cf7a3c44611efcc390e415ff17b1e5432fba6a951
|
| 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": 20.
|
| 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,
|
|
@@ -4688,6 +4688,24 @@
|
|
| 4688 |
"mean_token_accuracy": 0.6534196078777313,
|
| 4689 |
"num_tokens": 9482100.0,
|
| 4690 |
"step": 2600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4691 |
}
|
| 4692 |
],
|
| 4693 |
"logging_steps": 5,
|
|
@@ -4707,7 +4725,7 @@
|
|
| 4707 |
"attributes": {}
|
| 4708 |
}
|
| 4709 |
},
|
| 4710 |
-
"total_flos": 4.
|
| 4711 |
"train_batch_size": 4,
|
| 4712 |
"trial_name": null,
|
| 4713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4688 |
"mean_token_accuracy": 0.6534196078777313,
|
| 4689 |
"num_tokens": 9482100.0,
|
| 4690 |
"step": 2600
|
| 4691 |
+
},
|
| 4692 |
+
{
|
| 4693 |
+
"epoch": 20.03846153846154,
|
| 4694 |
+
"grad_norm": 0.0,
|
| 4695 |
+
"learning_rate": 3.698e-05,
|
| 4696 |
+
"loss": 1.7222,
|
| 4697 |
+
"mean_token_accuracy": 0.6527847439050675,
|
| 4698 |
+
"num_tokens": 9500755.0,
|
| 4699 |
+
"step": 2605
|
| 4700 |
+
},
|
| 4701 |
+
{
|
| 4702 |
+
"epoch": 20.076923076923077,
|
| 4703 |
+
"grad_norm": 0.0,
|
| 4704 |
+
"learning_rate": 3.6955e-05,
|
| 4705 |
+
"loss": 1.8368,
|
| 4706 |
+
"mean_token_accuracy": 0.6314696133136749,
|
| 4707 |
+
"num_tokens": 9518008.0,
|
| 4708 |
+
"step": 2610
|
| 4709 |
}
|
| 4710 |
],
|
| 4711 |
"logging_steps": 5,
|
|
|
|
| 4725 |
"attributes": {}
|
| 4726 |
}
|
| 4727 |
},
|
| 4728 |
+
"total_flos": 4.8241217007599616e+17,
|
| 4729 |
"train_batch_size": 4,
|
| 4730 |
"trial_name": null,
|
| 4731 |
"trial_params": null
|