Training in progress, step 9390, 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 sha256:7144b204094534a18addf7c926790d372bdc4ea91563fe027453adbff0d902a5
|
| 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:f0e69fda5b8330e719defcb4af88a82944ce357fed21485762068b2d83b592be
|
| 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 sha256:36b8535764430422dfbf4f5216f209546ad4008fd8216e12a33aee4a5405ca4a
|
| 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": 72.
|
| 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,
|
|
@@ -16892,6 +16892,24 @@
|
|
| 16892 |
"mean_token_accuracy": 0.6562888383865356,
|
| 16893 |
"num_tokens": 34209348.0,
|
| 16894 |
"step": 9380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16895 |
}
|
| 16896 |
],
|
| 16897 |
"logging_steps": 5,
|
|
@@ -16911,7 +16929,7 @@
|
|
| 16911 |
"attributes": {}
|
| 16912 |
}
|
| 16913 |
},
|
| 16914 |
-
"total_flos": 1.
|
| 16915 |
"train_batch_size": 4,
|
| 16916 |
"trial_name": null,
|
| 16917 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16892 |
"mean_token_accuracy": 0.6562888383865356,
|
| 16893 |
"num_tokens": 34209348.0,
|
| 16894 |
"step": 9380
|
| 16895 |
+
},
|
| 16896 |
+
{
|
| 16897 |
+
"epoch": 72.1923076923077,
|
| 16898 |
+
"grad_norm": 0.0,
|
| 16899 |
+
"learning_rate": 3.08e-06,
|
| 16900 |
+
"loss": 1.6941,
|
| 16901 |
+
"mean_token_accuracy": 0.6613337188959122,
|
| 16902 |
+
"num_tokens": 34227848.0,
|
| 16903 |
+
"step": 9385
|
| 16904 |
+
},
|
| 16905 |
+
{
|
| 16906 |
+
"epoch": 72.23076923076923,
|
| 16907 |
+
"grad_norm": 0.0,
|
| 16908 |
+
"learning_rate": 3.0550000000000004e-06,
|
| 16909 |
+
"loss": 1.6769,
|
| 16910 |
+
"mean_token_accuracy": 0.6630650132894516,
|
| 16911 |
+
"num_tokens": 34246818.0,
|
| 16912 |
+
"step": 9390
|
| 16913 |
}
|
| 16914 |
],
|
| 16915 |
"logging_steps": 5,
|
|
|
|
| 16929 |
"attributes": {}
|
| 16930 |
}
|
| 16931 |
},
|
| 16932 |
+
"total_flos": 1.7366321455393997e+18,
|
| 16933 |
"train_batch_size": 4,
|
| 16934 |
"trial_name": null,
|
| 16935 |
"trial_params": null
|