Training in progress, step 6510, 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 sha256:454079b015e5bada8f80acee64b196c967f328a7f6131511b400088241651cf9
|
| 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:e87d754822df356f56a816cc67a64cacbbc88b5be3d5a35fb374c4046c72aec8
|
| 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 sha256:61619f5621dd6f937ad554eb055359f0818c086505392082195f8786ab5058b9
|
| 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": 50.
|
| 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,
|
|
@@ -11708,6 +11708,24 @@
|
|
| 11708 |
"mean_token_accuracy": 0.6494122266769409,
|
| 11709 |
"num_tokens": 23705250.0,
|
| 11710 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11711 |
}
|
| 11712 |
],
|
| 11713 |
"logging_steps": 5,
|
|
@@ -11727,7 +11745,7 @@
|
|
| 11727 |
"attributes": {}
|
| 11728 |
}
|
| 11729 |
},
|
| 11730 |
-
"total_flos": 1.
|
| 11731 |
"train_batch_size": 4,
|
| 11732 |
"trial_name": null,
|
| 11733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11708 |
"mean_token_accuracy": 0.6494122266769409,
|
| 11709 |
"num_tokens": 23705250.0,
|
| 11710 |
"step": 6500
|
| 11711 |
+
},
|
| 11712 |
+
{
|
| 11713 |
+
"epoch": 50.03846153846154,
|
| 11714 |
+
"grad_norm": 0.0,
|
| 11715 |
+
"learning_rate": 1.7480000000000002e-05,
|
| 11716 |
+
"loss": 1.7627,
|
| 11717 |
+
"mean_token_accuracy": 0.6493338525295258,
|
| 11718 |
+
"num_tokens": 23722587.0,
|
| 11719 |
+
"step": 6505
|
| 11720 |
+
},
|
| 11721 |
+
{
|
| 11722 |
+
"epoch": 50.07692307692308,
|
| 11723 |
+
"grad_norm": 0.0,
|
| 11724 |
+
"learning_rate": 1.7455e-05,
|
| 11725 |
+
"loss": 1.7611,
|
| 11726 |
+
"mean_token_accuracy": 0.6497463405132293,
|
| 11727 |
+
"num_tokens": 23740287.0,
|
| 11728 |
+
"step": 6510
|
| 11729 |
}
|
| 11730 |
],
|
| 11731 |
"logging_steps": 5,
|
|
|
|
| 11745 |
"attributes": {}
|
| 11746 |
}
|
| 11747 |
},
|
| 11748 |
+
"total_flos": 1.2035402124499354e+18,
|
| 11749 |
"train_batch_size": 4,
|
| 11750 |
"trial_name": null,
|
| 11751 |
"trial_params": null
|