Training in progress, step 6600, 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:c5176fa69822f18a9b9fd3041e21b32966db7760dc53f4a2e5273e94ed632829
|
| 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 sha256:1c6521c058a5b3e0955914ba819f0070311c77466014078ef9e8cf11ecf44581
|
| 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:cfa22847f36e1965bdd6fcc670e181c19fac0019da9a8284f080f1ff38752144
|
| 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": 50.
|
| 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,
|
|
@@ -11870,6 +11870,24 @@
|
|
| 11870 |
"mean_token_accuracy": 0.6426284611225128,
|
| 11871 |
"num_tokens": 24034300.0,
|
| 11872 |
"step": 6590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11873 |
}
|
| 11874 |
],
|
| 11875 |
"logging_steps": 5,
|
|
@@ -11889,7 +11907,7 @@
|
|
| 11889 |
"attributes": {}
|
| 11890 |
}
|
| 11891 |
},
|
| 11892 |
-
"total_flos": 1.
|
| 11893 |
"train_batch_size": 4,
|
| 11894 |
"trial_name": null,
|
| 11895 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11870 |
"mean_token_accuracy": 0.6426284611225128,
|
| 11871 |
"num_tokens": 24034300.0,
|
| 11872 |
"step": 6590
|
| 11873 |
+
},
|
| 11874 |
+
{
|
| 11875 |
+
"epoch": 50.73076923076923,
|
| 11876 |
+
"grad_norm": 0.0,
|
| 11877 |
+
"learning_rate": 1.703e-05,
|
| 11878 |
+
"loss": 1.7132,
|
| 11879 |
+
"mean_token_accuracy": 0.6564747720956803,
|
| 11880 |
+
"num_tokens": 24052640.0,
|
| 11881 |
+
"step": 6595
|
| 11882 |
+
},
|
| 11883 |
+
{
|
| 11884 |
+
"epoch": 50.76923076923077,
|
| 11885 |
+
"grad_norm": 0.0,
|
| 11886 |
+
"learning_rate": 1.7005e-05,
|
| 11887 |
+
"loss": 1.7754,
|
| 11888 |
+
"mean_token_accuracy": 0.6513616561889648,
|
| 11889 |
+
"num_tokens": 24070441.0,
|
| 11890 |
+
"step": 6600
|
| 11891 |
}
|
| 11892 |
],
|
| 11893 |
"logging_steps": 5,
|
|
|
|
| 11907 |
"attributes": {}
|
| 11908 |
}
|
| 11909 |
},
|
| 11910 |
+
"total_flos": 1.2204120845293978e+18,
|
| 11911 |
"train_batch_size": 4,
|
| 11912 |
"trial_name": null,
|
| 11913 |
"trial_params": null
|