Training in progress, step 4950, 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 sha256:5fdd5f2d6d21e05050a424b61745283c61b642499f9bbc900f324797dc00f137
|
| 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 sha256:6051d96da1ba95a470d2a29948a28776354320f590810b6868e94242daf02c3f
|
| 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 sha256:68d64796ac8b486794fc701de8295111c032abf776bb7a009dc4dd7509292d74
|
| 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": 38.
|
| 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,
|
|
@@ -8900,6 +8900,24 @@
|
|
| 8900 |
"mean_token_accuracy": 0.6506702989339829,
|
| 8901 |
"num_tokens": 18015990.0,
|
| 8902 |
"step": 4940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8903 |
}
|
| 8904 |
],
|
| 8905 |
"logging_steps": 5,
|
|
@@ -8919,7 +8937,7 @@
|
|
| 8919 |
"attributes": {}
|
| 8920 |
}
|
| 8921 |
},
|
| 8922 |
-
"total_flos": 9.
|
| 8923 |
"train_batch_size": 4,
|
| 8924 |
"trial_name": null,
|
| 8925 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8900 |
"mean_token_accuracy": 0.6506702989339829,
|
| 8901 |
"num_tokens": 18015990.0,
|
| 8902 |
"step": 4940
|
| 8903 |
+
},
|
| 8904 |
+
{
|
| 8905 |
+
"epoch": 38.03846153846154,
|
| 8906 |
+
"grad_norm": 0.0,
|
| 8907 |
+
"learning_rate": 2.5280000000000005e-05,
|
| 8908 |
+
"loss": 1.7561,
|
| 8909 |
+
"mean_token_accuracy": 0.6481132537126542,
|
| 8910 |
+
"num_tokens": 18034580.0,
|
| 8911 |
+
"step": 4945
|
| 8912 |
+
},
|
| 8913 |
+
{
|
| 8914 |
+
"epoch": 38.07692307692308,
|
| 8915 |
+
"grad_norm": 0.0,
|
| 8916 |
+
"learning_rate": 2.5255e-05,
|
| 8917 |
+
"loss": 1.7617,
|
| 8918 |
+
"mean_token_accuracy": 0.6524750530719757,
|
| 8919 |
+
"num_tokens": 18052519.0,
|
| 8920 |
+
"step": 4950
|
| 8921 |
}
|
| 8922 |
],
|
| 8923 |
"logging_steps": 5,
|
|
|
|
| 8937 |
"attributes": {}
|
| 8938 |
}
|
| 8939 |
},
|
| 8940 |
+
"total_flos": 9.148271686882099e+17,
|
| 8941 |
"train_batch_size": 4,
|
| 8942 |
"trial_name": null,
|
| 8943 |
"trial_params": null
|