Training in progress, step 2710, 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 sha256:9678bd9ed69c01f228af6b217eff54290d970f210cba6c7117d3aaebdbbb4776
|
| 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 sha256:6ba4cdfe4eed59e17ed828f6e02afcb8cc079419a2d0f7d34b81577969021163
|
| 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 sha256:145770609d2dec5c4d0f2de537493c200de50c90f8b7cb78e4bf15cd9c2829db
|
| 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": 20.
|
| 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,
|
|
@@ -4868,6 +4868,24 @@
|
|
| 4868 |
"mean_token_accuracy": 0.6773371279239655,
|
| 4869 |
"num_tokens": 9845929.0,
|
| 4870 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4871 |
}
|
| 4872 |
],
|
| 4873 |
"logging_steps": 5,
|
|
@@ -4887,7 +4905,7 @@
|
|
| 4887 |
"attributes": {}
|
| 4888 |
}
|
| 4889 |
},
|
| 4890 |
-
"total_flos":
|
| 4891 |
"train_batch_size": 4,
|
| 4892 |
"trial_name": null,
|
| 4893 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4868 |
"mean_token_accuracy": 0.6773371279239655,
|
| 4869 |
"num_tokens": 9845929.0,
|
| 4870 |
"step": 2700
|
| 4871 |
+
},
|
| 4872 |
+
{
|
| 4873 |
+
"epoch": 20.807692307692307,
|
| 4874 |
+
"grad_norm": 0.0,
|
| 4875 |
+
"learning_rate": 3.648e-05,
|
| 4876 |
+
"loss": 1.7548,
|
| 4877 |
+
"mean_token_accuracy": 0.6442576110363006,
|
| 4878 |
+
"num_tokens": 9864387.0,
|
| 4879 |
+
"step": 2705
|
| 4880 |
+
},
|
| 4881 |
+
{
|
| 4882 |
+
"epoch": 20.846153846153847,
|
| 4883 |
+
"grad_norm": 0.0,
|
| 4884 |
+
"learning_rate": 3.6455e-05,
|
| 4885 |
+
"loss": 1.7623,
|
| 4886 |
+
"mean_token_accuracy": 0.6505689769983292,
|
| 4887 |
+
"num_tokens": 9881953.0,
|
| 4888 |
+
"step": 2710
|
| 4889 |
}
|
| 4890 |
],
|
| 4891 |
"logging_steps": 5,
|
|
|
|
| 4905 |
"attributes": {}
|
| 4906 |
}
|
| 4907 |
},
|
| 4908 |
+
"total_flos": 5.007306789568512e+17,
|
| 4909 |
"train_batch_size": 4,
|
| 4910 |
"trial_name": null,
|
| 4911 |
"trial_params": null
|