Training in progress, step 1580, 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:e23d6bb3eb885562b677627ec587d8c7ca29c7a21c38ea9a18c66119393925fb
|
| 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 sha256:1342856acd84c4a4fc26f3e11fbe777fd62b80ab9778e1365445d07409472ce8
|
| 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:e4dff3a9fde5c8b8dd4d390d6774d463e20798cd629ee9283cd26ab66167310a
|
| 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": 12.
|
| 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,
|
|
@@ -2834,6 +2834,24 @@
|
|
| 2834 |
"mean_token_accuracy": 0.6480188548564911,
|
| 2835 |
"num_tokens": 5724377.0,
|
| 2836 |
"step": 1570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2837 |
}
|
| 2838 |
],
|
| 2839 |
"logging_steps": 5,
|
|
@@ -2853,7 +2871,7 @@
|
|
| 2853 |
"attributes": {}
|
| 2854 |
}
|
| 2855 |
},
|
| 2856 |
-
"total_flos": 2.
|
| 2857 |
"train_batch_size": 4,
|
| 2858 |
"trial_name": null,
|
| 2859 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2834 |
"mean_token_accuracy": 0.6480188548564911,
|
| 2835 |
"num_tokens": 5724377.0,
|
| 2836 |
"step": 1570
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 12.115384615384615,
|
| 2840 |
+
"grad_norm": 0.0,
|
| 2841 |
+
"learning_rate": 4.2130000000000005e-05,
|
| 2842 |
+
"loss": 1.7288,
|
| 2843 |
+
"mean_token_accuracy": 0.653497377038002,
|
| 2844 |
+
"num_tokens": 5742391.0,
|
| 2845 |
+
"step": 1575
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 12.153846153846153,
|
| 2849 |
+
"grad_norm": 0.0,
|
| 2850 |
+
"learning_rate": 4.2105e-05,
|
| 2851 |
+
"loss": 1.8046,
|
| 2852 |
+
"mean_token_accuracy": 0.6407176822423934,
|
| 2853 |
+
"num_tokens": 5759857.0,
|
| 2854 |
+
"step": 1580
|
| 2855 |
}
|
| 2856 |
],
|
| 2857 |
"logging_steps": 5,
|
|
|
|
| 2871 |
"attributes": {}
|
| 2872 |
}
|
| 2873 |
},
|
| 2874 |
+
"total_flos": 2.916987268276224e+17,
|
| 2875 |
"train_batch_size": 4,
|
| 2876 |
"trial_name": null,
|
| 2877 |
"trial_params": null
|