Training in progress, step 6800, 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:a58dc9a0e319fad057ffe57f3b5d60896aac26a7e587cadb82e349ec74254876
|
| 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:bf382e2fb53ee701394ff9c2c9ebf0ef6cb9874cb0f41119347510a7671c570a
|
| 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 sha256:74b4f7c6bc10c42e2932e732a9ec3676199959cf729028a70bc89ebd00f03759
|
| 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": 52.
|
| 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,
|
|
@@ -12230,6 +12230,24 @@
|
|
| 12230 |
"mean_token_accuracy": 0.6518424063920975,
|
| 12231 |
"num_tokens": 24763369.0,
|
| 12232 |
"step": 6790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12233 |
}
|
| 12234 |
],
|
| 12235 |
"logging_steps": 5,
|
|
@@ -12249,7 +12267,7 @@
|
|
| 12249 |
"attributes": {}
|
| 12250 |
}
|
| 12251 |
},
|
| 12252 |
-
"total_flos": 1.
|
| 12253 |
"train_batch_size": 4,
|
| 12254 |
"trial_name": null,
|
| 12255 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12230 |
"mean_token_accuracy": 0.6518424063920975,
|
| 12231 |
"num_tokens": 24763369.0,
|
| 12232 |
"step": 6790
|
| 12233 |
+
},
|
| 12234 |
+
{
|
| 12235 |
+
"epoch": 52.26923076923077,
|
| 12236 |
+
"grad_norm": 0.0,
|
| 12237 |
+
"learning_rate": 1.603e-05,
|
| 12238 |
+
"loss": 1.6843,
|
| 12239 |
+
"mean_token_accuracy": 0.662993323802948,
|
| 12240 |
+
"num_tokens": 24782101.0,
|
| 12241 |
+
"step": 6795
|
| 12242 |
+
},
|
| 12243 |
+
{
|
| 12244 |
+
"epoch": 52.30769230769231,
|
| 12245 |
+
"grad_norm": 0.0,
|
| 12246 |
+
"learning_rate": 1.6005e-05,
|
| 12247 |
+
"loss": 1.718,
|
| 12248 |
+
"mean_token_accuracy": 0.6558027982711792,
|
| 12249 |
+
"num_tokens": 24800571.0,
|
| 12250 |
+
"step": 6800
|
| 12251 |
}
|
| 12252 |
],
|
| 12253 |
"logging_steps": 5,
|
|
|
|
| 12267 |
"attributes": {}
|
| 12268 |
}
|
| 12269 |
},
|
| 12270 |
+
"total_flos": 1.25745144864768e+18,
|
| 12271 |
"train_batch_size": 4,
|
| 12272 |
"trial_name": null,
|
| 12273 |
"trial_params": null
|