Training in progress, step 7700, 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 sha256:3ae0a105868eb9923c591be8f20e21690801458937a6643f3e1e44eb5eb394e5
|
| 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 sha256:3cb6b247f1a6eb598e852f4afc209609d20fd99d5f2b4d420e94ed7a08b682ef
|
| 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 sha256:9a83b452803484bae0ada71d25451f1e2ce815743bb37256c1e7e8d5dc548cc4
|
| 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": 59.
|
| 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,
|
|
@@ -13850,6 +13850,24 @@
|
|
| 13850 |
"mean_token_accuracy": 0.6441430777311326,
|
| 13851 |
"num_tokens": 28044444.0,
|
| 13852 |
"step": 7690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13853 |
}
|
| 13854 |
],
|
| 13855 |
"logging_steps": 5,
|
|
@@ -13869,7 +13887,7 @@
|
|
| 13869 |
"attributes": {}
|
| 13870 |
}
|
| 13871 |
},
|
| 13872 |
-
"total_flos": 1.
|
| 13873 |
"train_batch_size": 4,
|
| 13874 |
"trial_name": null,
|
| 13875 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13850 |
"mean_token_accuracy": 0.6441430777311326,
|
| 13851 |
"num_tokens": 28044444.0,
|
| 13852 |
"step": 7690
|
| 13853 |
+
},
|
| 13854 |
+
{
|
| 13855 |
+
"epoch": 59.19230769230769,
|
| 13856 |
+
"grad_norm": 0.0,
|
| 13857 |
+
"learning_rate": 1.153e-05,
|
| 13858 |
+
"loss": 1.8019,
|
| 13859 |
+
"mean_token_accuracy": 0.637511157989502,
|
| 13860 |
+
"num_tokens": 28062363.0,
|
| 13861 |
+
"step": 7695
|
| 13862 |
+
},
|
| 13863 |
+
{
|
| 13864 |
+
"epoch": 59.23076923076923,
|
| 13865 |
+
"grad_norm": 0.0,
|
| 13866 |
+
"learning_rate": 1.1505e-05,
|
| 13867 |
+
"loss": 1.6635,
|
| 13868 |
+
"mean_token_accuracy": 0.665479126572609,
|
| 13869 |
+
"num_tokens": 28081357.0,
|
| 13870 |
+
"step": 7700
|
| 13871 |
}
|
| 13872 |
],
|
| 13873 |
"logging_steps": 5,
|
|
|
|
| 13887 |
"attributes": {}
|
| 13888 |
}
|
| 13889 |
},
|
| 13890 |
+
"total_flos": 1.423785147886633e+18,
|
| 13891 |
"train_batch_size": 4,
|
| 13892 |
"trial_name": null,
|
| 13893 |
"trial_params": null
|