Training in progress, step 9470, 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:b71677580cf57a8e104453aa0165b9011f4e29e3074d0d7146aedbf6faf9063c
|
| 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 sha256:34147036eaba29e025e77366e36948841382acfc5233bc991fd313af3b8bfdd2
|
| 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 sha256:546b476b6075269bacf9ba7f6848f8075caf8021a1cd9021e7ace9397257275c
|
| 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": 72.
|
| 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,
|
|
@@ -17036,6 +17036,24 @@
|
|
| 17036 |
"mean_token_accuracy": 0.6520882248878479,
|
| 17037 |
"num_tokens": 34498104.0,
|
| 17038 |
"step": 9460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17039 |
}
|
| 17040 |
],
|
| 17041 |
"logging_steps": 5,
|
|
@@ -17055,7 +17073,7 @@
|
|
| 17055 |
"attributes": {}
|
| 17056 |
}
|
| 17057 |
},
|
| 17058 |
-
"total_flos": 1.
|
| 17059 |
"train_batch_size": 4,
|
| 17060 |
"trial_name": null,
|
| 17061 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17036 |
"mean_token_accuracy": 0.6520882248878479,
|
| 17037 |
"num_tokens": 34498104.0,
|
| 17038 |
"step": 9460
|
| 17039 |
+
},
|
| 17040 |
+
{
|
| 17041 |
+
"epoch": 72.8076923076923,
|
| 17042 |
+
"grad_norm": 0.0,
|
| 17043 |
+
"learning_rate": 2.68e-06,
|
| 17044 |
+
"loss": 1.7094,
|
| 17045 |
+
"mean_token_accuracy": 0.6541548132896423,
|
| 17046 |
+
"num_tokens": 34516905.0,
|
| 17047 |
+
"step": 9465
|
| 17048 |
+
},
|
| 17049 |
+
{
|
| 17050 |
+
"epoch": 72.84615384615384,
|
| 17051 |
+
"grad_norm": 0.0,
|
| 17052 |
+
"learning_rate": 2.655e-06,
|
| 17053 |
+
"loss": 1.6942,
|
| 17054 |
+
"mean_token_accuracy": 0.6577578127384186,
|
| 17055 |
+
"num_tokens": 34535704.0,
|
| 17056 |
+
"step": 9470
|
| 17057 |
}
|
| 17058 |
],
|
| 17059 |
"logging_steps": 5,
|
|
|
|
| 17073 |
"attributes": {}
|
| 17074 |
}
|
| 17075 |
},
|
| 17076 |
+
"total_flos": 1.7512693599146803e+18,
|
| 17077 |
"train_batch_size": 4,
|
| 17078 |
"trial_name": null,
|
| 17079 |
"trial_params": null
|