Training in progress, step 6050, 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 sha256:27082180d454d4fd6918917d0dd28a6f0ada852e0593945fd48d1408500a1fa9
|
| 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 sha256:8822252da316a51773da56b957d753de189a37e84d20becc2715d5388b5d75fe
|
| 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 sha256:080621d4c2c423ff1c4a0139d9fff0c0625a178a878aa619000239bd6ddfb7c1
|
| 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": 46.
|
| 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,
|
|
@@ -10880,6 +10880,24 @@
|
|
| 10880 |
"mean_token_accuracy": 0.65768404006958,
|
| 10881 |
"num_tokens": 22028277.0,
|
| 10882 |
"step": 6040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10883 |
}
|
| 10884 |
],
|
| 10885 |
"logging_steps": 5,
|
|
@@ -10899,7 +10917,7 @@
|
|
| 10899 |
"attributes": {}
|
| 10900 |
}
|
| 10901 |
},
|
| 10902 |
-
"total_flos": 1.
|
| 10903 |
"train_batch_size": 4,
|
| 10904 |
"trial_name": null,
|
| 10905 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10880 |
"mean_token_accuracy": 0.65768404006958,
|
| 10881 |
"num_tokens": 22028277.0,
|
| 10882 |
"step": 6040
|
| 10883 |
+
},
|
| 10884 |
+
{
|
| 10885 |
+
"epoch": 46.5,
|
| 10886 |
+
"grad_norm": 0.0,
|
| 10887 |
+
"learning_rate": 1.978e-05,
|
| 10888 |
+
"loss": 1.7751,
|
| 10889 |
+
"mean_token_accuracy": 0.6457584232091904,
|
| 10890 |
+
"num_tokens": 22046348.0,
|
| 10891 |
+
"step": 6045
|
| 10892 |
+
},
|
| 10893 |
+
{
|
| 10894 |
+
"epoch": 46.53846153846154,
|
| 10895 |
+
"grad_norm": 0.0,
|
| 10896 |
+
"learning_rate": 1.9755e-05,
|
| 10897 |
+
"loss": 1.8084,
|
| 10898 |
+
"mean_token_accuracy": 0.6365677118301392,
|
| 10899 |
+
"num_tokens": 22064065.0,
|
| 10900 |
+
"step": 6050
|
| 10901 |
}
|
| 10902 |
],
|
| 10903 |
"logging_steps": 5,
|
|
|
|
| 10917 |
"attributes": {}
|
| 10918 |
}
|
| 10919 |
},
|
| 10920 |
+
"total_flos": 1.1181794319772877e+18,
|
| 10921 |
"train_batch_size": 4,
|
| 10922 |
"trial_name": null,
|
| 10923 |
"trial_params": null
|