Training in progress, step 7560, 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:eb55891e55119908b8391ca744ab868e7556c1b674dc450eeea761ac51edb2d2
|
| 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:c147004e2b9878cda7ba9623f1b8c27dc440b84ffb5b1f8205c003a65204c4f6
|
| 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:d5dff20bad6597c4573ece1b3428b58555cd97d2f154992a73d551c8956f2154
|
| 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": 58.
|
| 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,
|
|
@@ -13598,6 +13598,24 @@
|
|
| 13598 |
"mean_token_accuracy": 0.6379787772893906,
|
| 13599 |
"num_tokens": 27534566.0,
|
| 13600 |
"step": 7550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13601 |
}
|
| 13602 |
],
|
| 13603 |
"logging_steps": 5,
|
|
@@ -13617,7 +13635,7 @@
|
|
| 13617 |
"attributes": {}
|
| 13618 |
}
|
| 13619 |
},
|
| 13620 |
-
"total_flos": 1.
|
| 13621 |
"train_batch_size": 4,
|
| 13622 |
"trial_name": null,
|
| 13623 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13598 |
"mean_token_accuracy": 0.6379787772893906,
|
| 13599 |
"num_tokens": 27534566.0,
|
| 13600 |
"step": 7550
|
| 13601 |
+
},
|
| 13602 |
+
{
|
| 13603 |
+
"epoch": 58.11538461538461,
|
| 13604 |
+
"grad_norm": 0.0,
|
| 13605 |
+
"learning_rate": 1.2230000000000001e-05,
|
| 13606 |
+
"loss": 1.7963,
|
| 13607 |
+
"mean_token_accuracy": 0.6373230516910553,
|
| 13608 |
+
"num_tokens": 27552046.0,
|
| 13609 |
+
"step": 7555
|
| 13610 |
+
},
|
| 13611 |
+
{
|
| 13612 |
+
"epoch": 58.15384615384615,
|
| 13613 |
+
"grad_norm": 0.0,
|
| 13614 |
+
"learning_rate": 1.2205000000000001e-05,
|
| 13615 |
+
"loss": 1.7564,
|
| 13616 |
+
"mean_token_accuracy": 0.6494860410690307,
|
| 13617 |
+
"num_tokens": 27569697.0,
|
| 13618 |
+
"step": 7560
|
| 13619 |
}
|
| 13620 |
],
|
| 13621 |
"logging_steps": 5,
|
|
|
|
| 13635 |
"attributes": {}
|
| 13636 |
}
|
| 13637 |
},
|
| 13638 |
+
"total_flos": 1.397695193693061e+18,
|
| 13639 |
"train_batch_size": 4,
|
| 13640 |
"trial_name": null,
|
| 13641 |
"trial_params": null
|