Training in progress, step 490, 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:f23259158c53e420286fd28ff250b475ee12f7e00a3272a984943a4180b79ec2
|
| 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:bacbf1704544de8ed170e1936dad02fbd07c582f844a2887ff373d2a34f27fb4
|
| 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 sha256:038a919295ff9786354e4cab7220a5a44ff7b4a02192d4ab66cdb2b401b5c5e8
|
| 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": 3.
|
| 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,
|
|
@@ -872,6 +872,24 @@
|
|
| 872 |
"mean_token_accuracy": 0.6383150666952133,
|
| 873 |
"num_tokens": 1752374.0,
|
| 874 |
"step": 480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 875 |
}
|
| 876 |
],
|
| 877 |
"logging_steps": 5,
|
|
@@ -891,7 +909,7 @@
|
|
| 891 |
"attributes": {}
|
| 892 |
}
|
| 893 |
},
|
| 894 |
-
"total_flos":
|
| 895 |
"train_batch_size": 4,
|
| 896 |
"trial_name": null,
|
| 897 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 872 |
"mean_token_accuracy": 0.6383150666952133,
|
| 873 |
"num_tokens": 1752374.0,
|
| 874 |
"step": 480
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.730769230769231,
|
| 878 |
+
"grad_norm": 0.0,
|
| 879 |
+
"learning_rate": 4.758e-05,
|
| 880 |
+
"loss": 1.7517,
|
| 881 |
+
"mean_token_accuracy": 0.6486301571130753,
|
| 882 |
+
"num_tokens": 1770507.0,
|
| 883 |
+
"step": 485
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 3.769230769230769,
|
| 887 |
+
"grad_norm": 0.0,
|
| 888 |
+
"learning_rate": 4.7555e-05,
|
| 889 |
+
"loss": 1.786,
|
| 890 |
+
"mean_token_accuracy": 0.6404696077108383,
|
| 891 |
+
"num_tokens": 1788454.0,
|
| 892 |
+
"step": 490
|
| 893 |
}
|
| 894 |
],
|
| 895 |
"logging_steps": 5,
|
|
|
|
| 909 |
"attributes": {}
|
| 910 |
}
|
| 911 |
},
|
| 912 |
+
"total_flos": 9.063558248988672e+16,
|
| 913 |
"train_batch_size": 4,
|
| 914 |
"trial_name": null,
|
| 915 |
"trial_params": null
|