Training in progress, step 8810, 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 sha256:653059c0ad36daae63ed432b5b1c1cbd636c7ca9f89f5e7f80c85830c2529583
|
| 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 sha256:4310fa45d37d9781a7089cc8c81d0202c1d70e8c28ff5898fb91f8fbb57271d5
|
| 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 sha256:136ff850f86535df33f45739a381c7dfae1717e10c8cef26cb26741a7827d8b6
|
| 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": 67.
|
| 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,
|
|
@@ -15848,6 +15848,24 @@
|
|
| 15848 |
"mean_token_accuracy": 0.6513085424900055,
|
| 15849 |
"num_tokens": 32092096.0,
|
| 15850 |
"step": 8800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15851 |
}
|
| 15852 |
],
|
| 15853 |
"logging_steps": 5,
|
|
@@ -15867,7 +15885,7 @@
|
|
| 15867 |
"attributes": {}
|
| 15868 |
}
|
| 15869 |
},
|
| 15870 |
-
"total_flos": 1.
|
| 15871 |
"train_batch_size": 4,
|
| 15872 |
"trial_name": null,
|
| 15873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15848 |
"mean_token_accuracy": 0.6513085424900055,
|
| 15849 |
"num_tokens": 32092096.0,
|
| 15850 |
"step": 8800
|
| 15851 |
+
},
|
| 15852 |
+
{
|
| 15853 |
+
"epoch": 67.73076923076923,
|
| 15854 |
+
"grad_norm": 0.0,
|
| 15855 |
+
"learning_rate": 5.98e-06,
|
| 15856 |
+
"loss": 1.6929,
|
| 15857 |
+
"mean_token_accuracy": 0.6587874621152878,
|
| 15858 |
+
"num_tokens": 32110873.0,
|
| 15859 |
+
"step": 8805
|
| 15860 |
+
},
|
| 15861 |
+
{
|
| 15862 |
+
"epoch": 67.76923076923077,
|
| 15863 |
+
"grad_norm": 0.0,
|
| 15864 |
+
"learning_rate": 5.955000000000001e-06,
|
| 15865 |
+
"loss": 1.6503,
|
| 15866 |
+
"mean_token_accuracy": 0.6717524290084839,
|
| 15867 |
+
"num_tokens": 32129582.0,
|
| 15868 |
+
"step": 8810
|
| 15869 |
}
|
| 15870 |
],
|
| 15871 |
"logging_steps": 5,
|
|
|
|
| 15885 |
"attributes": {}
|
| 15886 |
}
|
| 15887 |
},
|
| 15888 |
+
"total_flos": 1.6291510483083264e+18,
|
| 15889 |
"train_batch_size": 4,
|
| 15890 |
"trial_name": null,
|
| 15891 |
"trial_params": null
|