Training in progress, step 480, 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 sha256:2360c7198f3535a48324990e83ea20b4a29432cf6d8eeb4d140dca734a0ab985
|
| 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 sha256:244f2ee6a9727723b7d20388b6c0bfdd588474bf1474187c0765d65d74c41305
|
| 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:e82e8ed0b96a64885ac5b0a7f6c12d3967556ff19832c22d5fbf4c75ea14bc67
|
| 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": 3.
|
| 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,
|
|
@@ -854,6 +854,24 @@
|
|
| 854 |
"mean_token_accuracy": 0.6671018153429031,
|
| 855 |
"num_tokens": 1717113.0,
|
| 856 |
"step": 470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 857 |
}
|
| 858 |
],
|
| 859 |
"logging_steps": 5,
|
|
@@ -873,7 +891,7 @@
|
|
| 873 |
"attributes": {}
|
| 874 |
}
|
| 875 |
},
|
| 876 |
-
"total_flos": 8.
|
| 877 |
"train_batch_size": 4,
|
| 878 |
"trial_name": null,
|
| 879 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 854 |
"mean_token_accuracy": 0.6671018153429031,
|
| 855 |
"num_tokens": 1717113.0,
|
| 856 |
"step": 470
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.6538461538461537,
|
| 860 |
+
"grad_norm": 0.0,
|
| 861 |
+
"learning_rate": 4.763e-05,
|
| 862 |
+
"loss": 1.7797,
|
| 863 |
+
"mean_token_accuracy": 0.6456864833831787,
|
| 864 |
+
"num_tokens": 1735083.0,
|
| 865 |
+
"step": 475
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 3.6923076923076925,
|
| 869 |
+
"grad_norm": 0.0,
|
| 870 |
+
"learning_rate": 4.7605e-05,
|
| 871 |
+
"loss": 1.83,
|
| 872 |
+
"mean_token_accuracy": 0.6383150666952133,
|
| 873 |
+
"num_tokens": 1752374.0,
|
| 874 |
+
"step": 480
|
| 875 |
}
|
| 876 |
],
|
| 877 |
"logging_steps": 5,
|
|
|
|
| 891 |
"attributes": {}
|
| 892 |
}
|
| 893 |
},
|
| 894 |
+
"total_flos": 8.87900924731392e+16,
|
| 895 |
"train_batch_size": 4,
|
| 896 |
"trial_name": null,
|
| 897 |
"trial_params": null
|