Training in progress, step 3800, 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 sha256:8ec54b6e9d44618beffafa5adcc40298ea28f5ef450b82f3dbd128df69ab1b2a
|
| 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 sha256:584dbf40bc297b011acea4b27ed6014fdcc9750305e06ac50c287c9353c477a2
|
| 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:bb84dcaa20075334c3b0550e0d57d1eca98be0a9f0b21e49e9cede1104b462c1
|
| 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": 29.
|
| 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,
|
|
@@ -6830,6 +6830,24 @@
|
|
| 6830 |
"mean_token_accuracy": 0.6564319849014282,
|
| 6831 |
"num_tokens": 13822922.0,
|
| 6832 |
"step": 3790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6833 |
}
|
| 6834 |
],
|
| 6835 |
"logging_steps": 5,
|
|
@@ -6849,7 +6867,7 @@
|
|
| 6849 |
"attributes": {}
|
| 6850 |
}
|
| 6851 |
},
|
| 6852 |
-
"total_flos": 7.
|
| 6853 |
"train_batch_size": 4,
|
| 6854 |
"trial_name": null,
|
| 6855 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6830 |
"mean_token_accuracy": 0.6564319849014282,
|
| 6831 |
"num_tokens": 13822922.0,
|
| 6832 |
"step": 3790
|
| 6833 |
+
},
|
| 6834 |
+
{
|
| 6835 |
+
"epoch": 29.192307692307693,
|
| 6836 |
+
"grad_norm": 0.0,
|
| 6837 |
+
"learning_rate": 3.1030000000000006e-05,
|
| 6838 |
+
"loss": 1.7008,
|
| 6839 |
+
"mean_token_accuracy": 0.6606447160243988,
|
| 6840 |
+
"num_tokens": 13840985.0,
|
| 6841 |
+
"step": 3795
|
| 6842 |
+
},
|
| 6843 |
+
{
|
| 6844 |
+
"epoch": 29.23076923076923,
|
| 6845 |
+
"grad_norm": 0.0,
|
| 6846 |
+
"learning_rate": 3.1005e-05,
|
| 6847 |
+
"loss": 1.7041,
|
| 6848 |
+
"mean_token_accuracy": 0.6543154448270798,
|
| 6849 |
+
"num_tokens": 13859478.0,
|
| 6850 |
+
"step": 3800
|
| 6851 |
}
|
| 6852 |
],
|
| 6853 |
"logging_steps": 5,
|
|
|
|
| 6867 |
"attributes": {}
|
| 6868 |
}
|
| 6869 |
},
|
| 6870 |
+
"total_flos": 7.023611411841024e+17,
|
| 6871 |
"train_batch_size": 4,
|
| 6872 |
"trial_name": null,
|
| 6873 |
"trial_params": null
|