Training in progress, step 7120, 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 sha256:88ad9c8cc704160ff1b9660c98f2859149c7c25a72324119be1909ce628911e8
|
| 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:be8eed765bf896a12564b90d79e8a81c709da1763131b8c401f4f864ee0c0ddc
|
| 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 sha256:63b5d9018ae2fbbc1ca3cf63df429d2212b867f6cffdf1bfbf11e9f6ebc2f580
|
| 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": 54.
|
| 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,
|
|
@@ -12806,6 +12806,24 @@
|
|
| 12806 |
"mean_token_accuracy": 0.6525210946798324,
|
| 12807 |
"num_tokens": 25931516.0,
|
| 12808 |
"step": 7110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12809 |
}
|
| 12810 |
],
|
| 12811 |
"logging_steps": 5,
|
|
@@ -12825,7 +12843,7 @@
|
|
| 12825 |
"attributes": {}
|
| 12826 |
}
|
| 12827 |
},
|
| 12828 |
-
"total_flos": 1.
|
| 12829 |
"train_batch_size": 4,
|
| 12830 |
"trial_name": null,
|
| 12831 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12806 |
"mean_token_accuracy": 0.6525210946798324,
|
| 12807 |
"num_tokens": 25931516.0,
|
| 12808 |
"step": 7110
|
| 12809 |
+
},
|
| 12810 |
+
{
|
| 12811 |
+
"epoch": 54.73076923076923,
|
| 12812 |
+
"grad_norm": 0.0,
|
| 12813 |
+
"learning_rate": 1.4430000000000002e-05,
|
| 12814 |
+
"loss": 1.7648,
|
| 12815 |
+
"mean_token_accuracy": 0.6474990725517273,
|
| 12816 |
+
"num_tokens": 25949015.0,
|
| 12817 |
+
"step": 7115
|
| 12818 |
+
},
|
| 12819 |
+
{
|
| 12820 |
+
"epoch": 54.76923076923077,
|
| 12821 |
+
"grad_norm": 0.0,
|
| 12822 |
+
"learning_rate": 1.4405000000000002e-05,
|
| 12823 |
+
"loss": 1.7407,
|
| 12824 |
+
"mean_token_accuracy": 0.6535341709852218,
|
| 12825 |
+
"num_tokens": 25967346.0,
|
| 12826 |
+
"step": 7120
|
| 12827 |
}
|
| 12828 |
],
|
| 12829 |
"logging_steps": 5,
|
|
|
|
| 12843 |
"attributes": {}
|
| 12844 |
}
|
| 12845 |
},
|
| 12846 |
+
"total_flos": 1.3166835328150733e+18,
|
| 12847 |
"train_batch_size": 4,
|
| 12848 |
"trial_name": null,
|
| 12849 |
"trial_params": null
|