Training in progress, step 2160, 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 sha256:46f89374a6a52e460712f1d29d33c735d8a061e966c75de1eb0b03621945cdf9
|
| 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:cad7b7fc98a272c138e91923980b5195bb0462825cfd82473a8fa870a708c812
|
| 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 sha256:2f559a301fc48e00d6a845196763254d622468cc0241a0bb4c049df86e5658c5
|
| 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": 16.
|
| 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,
|
|
@@ -3878,6 +3878,24 @@
|
|
| 3878 |
"mean_token_accuracy": 0.6600228071212768,
|
| 3879 |
"num_tokens": 7842178.0,
|
| 3880 |
"step": 2150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3881 |
}
|
| 3882 |
],
|
| 3883 |
"logging_steps": 5,
|
|
@@ -3897,7 +3915,7 @@
|
|
| 3897 |
"attributes": {}
|
| 3898 |
}
|
| 3899 |
},
|
| 3900 |
-
"total_flos": 3.
|
| 3901 |
"train_batch_size": 4,
|
| 3902 |
"trial_name": null,
|
| 3903 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3878 |
"mean_token_accuracy": 0.6600228071212768,
|
| 3879 |
"num_tokens": 7842178.0,
|
| 3880 |
"step": 2150
|
| 3881 |
+
},
|
| 3882 |
+
{
|
| 3883 |
+
"epoch": 16.576923076923077,
|
| 3884 |
+
"grad_norm": 0.0,
|
| 3885 |
+
"learning_rate": 3.923e-05,
|
| 3886 |
+
"loss": 1.7287,
|
| 3887 |
+
"mean_token_accuracy": 0.6550074636936187,
|
| 3888 |
+
"num_tokens": 7860260.0,
|
| 3889 |
+
"step": 2155
|
| 3890 |
+
},
|
| 3891 |
+
{
|
| 3892 |
+
"epoch": 16.615384615384617,
|
| 3893 |
+
"grad_norm": 0.0,
|
| 3894 |
+
"learning_rate": 3.9205e-05,
|
| 3895 |
+
"loss": 1.7764,
|
| 3896 |
+
"mean_token_accuracy": 0.6480809897184372,
|
| 3897 |
+
"num_tokens": 7877839.0,
|
| 3898 |
+
"step": 2160
|
| 3899 |
}
|
| 3900 |
],
|
| 3901 |
"logging_steps": 5,
|
|
|
|
| 3915 |
"attributes": {}
|
| 3916 |
}
|
| 3917 |
},
|
| 3918 |
+
"total_flos": 3.9904787858817024e+17,
|
| 3919 |
"train_batch_size": 4,
|
| 3920 |
"trial_name": null,
|
| 3921 |
"trial_params": null
|