Training in progress, step 8830, 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:db1a2b3852a9bfdef9b27238ce2c19b9cf5ddf3390b7b578e0f88b7770c30d90
|
| 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:b30d10d3611c71ef1d90b8daad50fc930c4f0d8f98a90f1dd03671c521d123d6
|
| 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 sha256:4f3afe2c7c66cd6a0e2c1dc2903ad6552944f1d763d56c78307c194ce6d91e33
|
| 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": 67.
|
| 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,
|
|
@@ -15884,6 +15884,24 @@
|
|
| 15884 |
"mean_token_accuracy": 0.642418372631073,
|
| 15885 |
"num_tokens": 32165982.0,
|
| 15886 |
"step": 8820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15887 |
}
|
| 15888 |
],
|
| 15889 |
"logging_steps": 5,
|
|
@@ -15903,7 +15921,7 @@
|
|
| 15903 |
"attributes": {}
|
| 15904 |
}
|
| 15905 |
},
|
| 15906 |
-
"total_flos": 1.
|
| 15907 |
"train_batch_size": 4,
|
| 15908 |
"trial_name": null,
|
| 15909 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15884 |
"mean_token_accuracy": 0.642418372631073,
|
| 15885 |
"num_tokens": 32165982.0,
|
| 15886 |
"step": 8820
|
| 15887 |
+
},
|
| 15888 |
+
{
|
| 15889 |
+
"epoch": 67.88461538461539,
|
| 15890 |
+
"grad_norm": 0.0,
|
| 15891 |
+
"learning_rate": 5.8800000000000005e-06,
|
| 15892 |
+
"loss": 1.6831,
|
| 15893 |
+
"mean_token_accuracy": 0.6590377599000931,
|
| 15894 |
+
"num_tokens": 32185226.0,
|
| 15895 |
+
"step": 8825
|
| 15896 |
+
},
|
| 15897 |
+
{
|
| 15898 |
+
"epoch": 67.92307692307692,
|
| 15899 |
+
"grad_norm": 0.0,
|
| 15900 |
+
"learning_rate": 5.855e-06,
|
| 15901 |
+
"loss": 1.8126,
|
| 15902 |
+
"mean_token_accuracy": 0.6364179074764251,
|
| 15903 |
+
"num_tokens": 32202532.0,
|
| 15904 |
+
"step": 8830
|
| 15905 |
}
|
| 15906 |
],
|
| 15907 |
"logging_steps": 5,
|
|
|
|
| 15921 |
"attributes": {}
|
| 15922 |
}
|
| 15923 |
},
|
| 15924 |
+
"total_flos": 1.632809319837696e+18,
|
| 15925 |
"train_batch_size": 4,
|
| 15926 |
"trial_name": null,
|
| 15927 |
"trial_params": null
|