Training in progress, step 5390, 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 sha256:59317a150ec1188b9a7295faea92acc5c4643309ede074f86a7d83e2b8d63a19
|
| 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 sha256:08593eb380a891749b62ec8b5dcbb7d50f48453e70dc1afbcd87c88425aa2074
|
| 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 sha256:1e6cce707cff2346a49374bb79e8ab61fefcd53a6ef1c537cad2254447888afe
|
| 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": 41.
|
| 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,
|
|
@@ -9692,6 +9692,24 @@
|
|
| 9692 |
"mean_token_accuracy": 0.6403976768255234,
|
| 9693 |
"num_tokens": 19620846.0,
|
| 9694 |
"step": 5380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9695 |
}
|
| 9696 |
],
|
| 9697 |
"logging_steps": 5,
|
|
@@ -9711,7 +9729,7 @@
|
|
| 9711 |
"attributes": {}
|
| 9712 |
}
|
| 9713 |
},
|
| 9714 |
-
"total_flos": 9.
|
| 9715 |
"train_batch_size": 4,
|
| 9716 |
"trial_name": null,
|
| 9717 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9692 |
"mean_token_accuracy": 0.6403976768255234,
|
| 9693 |
"num_tokens": 19620846.0,
|
| 9694 |
"step": 5380
|
| 9695 |
+
},
|
| 9696 |
+
{
|
| 9697 |
+
"epoch": 41.42307692307692,
|
| 9698 |
+
"grad_norm": 0.0,
|
| 9699 |
+
"learning_rate": 2.3080000000000003e-05,
|
| 9700 |
+
"loss": 1.7217,
|
| 9701 |
+
"mean_token_accuracy": 0.6528929799795151,
|
| 9702 |
+
"num_tokens": 19639574.0,
|
| 9703 |
+
"step": 5385
|
| 9704 |
+
},
|
| 9705 |
+
{
|
| 9706 |
+
"epoch": 41.46153846153846,
|
| 9707 |
+
"grad_norm": 0.0,
|
| 9708 |
+
"learning_rate": 2.3055000000000002e-05,
|
| 9709 |
+
"loss": 1.8022,
|
| 9710 |
+
"mean_token_accuracy": 0.641742405295372,
|
| 9711 |
+
"num_tokens": 19657464.0,
|
| 9712 |
+
"step": 5390
|
| 9713 |
}
|
| 9714 |
],
|
| 9715 |
"logging_steps": 5,
|
|
|
|
| 9729 |
"attributes": {}
|
| 9730 |
}
|
| 9731 |
},
|
| 9732 |
+
"total_flos": 9.960358744866816e+17,
|
| 9733 |
"train_batch_size": 4,
|
| 9734 |
"trial_name": null,
|
| 9735 |
"trial_params": null
|