Training in progress, step 4300, 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:d2862e68df902827f17da6db0a9b1267dc98451f05a961c20b9b4e5a48adb580
|
| 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 sha256:21e015b2524a5c63ea259c90eb41ec4d7fd16846e56c686f15cb86bc8147d2fa
|
| 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 sha256:11f17657fe9a933b8533a97a1c74264514f5b7e31fd2ab5f3f46a5033a2cfbbd
|
| 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": 33.
|
| 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,
|
|
@@ -7730,6 +7730,24 @@
|
|
| 7730 |
"mean_token_accuracy": 0.6526326090097427,
|
| 7731 |
"num_tokens": 15645465.0,
|
| 7732 |
"step": 4290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7733 |
}
|
| 7734 |
],
|
| 7735 |
"logging_steps": 5,
|
|
@@ -7749,7 +7767,7 @@
|
|
| 7749 |
"attributes": {}
|
| 7750 |
}
|
| 7751 |
},
|
| 7752 |
-
"total_flos": 7.
|
| 7753 |
"train_batch_size": 4,
|
| 7754 |
"trial_name": null,
|
| 7755 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7730 |
"mean_token_accuracy": 0.6526326090097427,
|
| 7731 |
"num_tokens": 15645465.0,
|
| 7732 |
"step": 4290
|
| 7733 |
+
},
|
| 7734 |
+
{
|
| 7735 |
+
"epoch": 33.03846153846154,
|
| 7736 |
+
"grad_norm": 0.0,
|
| 7737 |
+
"learning_rate": 2.853e-05,
|
| 7738 |
+
"loss": 1.7299,
|
| 7739 |
+
"mean_token_accuracy": 0.6534471154212952,
|
| 7740 |
+
"num_tokens": 15663771.0,
|
| 7741 |
+
"step": 4295
|
| 7742 |
+
},
|
| 7743 |
+
{
|
| 7744 |
+
"epoch": 33.07692307692308,
|
| 7745 |
+
"grad_norm": 0.0,
|
| 7746 |
+
"learning_rate": 2.8505000000000002e-05,
|
| 7747 |
+
"loss": 1.7432,
|
| 7748 |
+
"mean_token_accuracy": 0.6503149479627609,
|
| 7749 |
+
"num_tokens": 15682167.0,
|
| 7750 |
+
"step": 4300
|
| 7751 |
}
|
| 7752 |
],
|
| 7753 |
"logging_steps": 5,
|
|
|
|
| 7767 |
"attributes": {}
|
| 7768 |
}
|
| 7769 |
},
|
| 7770 |
+
"total_flos": 7.94736625558487e+17,
|
| 7771 |
"train_batch_size": 4,
|
| 7772 |
"trial_name": null,
|
| 7773 |
"trial_params": null
|