Training in progress, step 7140, 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:d10086479153b6e37edd4ba383a4e0761b07f17d9306e7a3a671505739b3d299
|
| 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 sha256:7f4e7e802065f6a24abc971bf4e409216517e82accc7c4fe08aee877dbb33715
|
| 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 sha256:50c62b2cedb2d9cefb5011364719297143cba69d253ff510df916ae094bb77fa
|
| 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,
|
|
@@ -12842,6 +12842,24 @@
|
|
| 12842 |
"mean_token_accuracy": 0.6653303891420365,
|
| 12843 |
"num_tokens": 26003170.0,
|
| 12844 |
"step": 7130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12845 |
}
|
| 12846 |
],
|
| 12847 |
"logging_steps": 5,
|
|
@@ -12861,7 +12879,7 @@
|
|
| 12861 |
"attributes": {}
|
| 12862 |
}
|
| 12863 |
},
|
| 12864 |
-
"total_flos": 1.
|
| 12865 |
"train_batch_size": 4,
|
| 12866 |
"trial_name": null,
|
| 12867 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12842 |
"mean_token_accuracy": 0.6653303891420365,
|
| 12843 |
"num_tokens": 26003170.0,
|
| 12844 |
"step": 7130
|
| 12845 |
+
},
|
| 12846 |
+
{
|
| 12847 |
+
"epoch": 54.88461538461539,
|
| 12848 |
+
"grad_norm": 0.0,
|
| 12849 |
+
"learning_rate": 1.4330000000000002e-05,
|
| 12850 |
+
"loss": 1.7999,
|
| 12851 |
+
"mean_token_accuracy": 0.6397199392318725,
|
| 12852 |
+
"num_tokens": 26020817.0,
|
| 12853 |
+
"step": 7135
|
| 12854 |
+
},
|
| 12855 |
+
{
|
| 12856 |
+
"epoch": 54.92307692307692,
|
| 12857 |
+
"grad_norm": 0.0,
|
| 12858 |
+
"learning_rate": 1.4305000000000001e-05,
|
| 12859 |
+
"loss": 1.7184,
|
| 12860 |
+
"mean_token_accuracy": 0.6556466907262802,
|
| 12861 |
+
"num_tokens": 26039316.0,
|
| 12862 |
+
"step": 7140
|
| 12863 |
}
|
| 12864 |
],
|
| 12865 |
"logging_steps": 5,
|
|
|
|
| 12879 |
"attributes": {}
|
| 12880 |
}
|
| 12881 |
},
|
| 12882 |
+
"total_flos": 1.320345773823099e+18,
|
| 12883 |
"train_batch_size": 4,
|
| 12884 |
"trial_name": null,
|
| 12885 |
"trial_params": null
|