Training in progress, step 2525, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:378c742a2ed47583532794cae1fd2de4a6760ea2e1b8121476178b01d980da3e
|
| 3 |
size 108113968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57081771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a898a183983728143a712f6bc3eb4cff78c82a63ea213dd37b8d81025cbe4b5c
|
| 3 |
size 57081771
|
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 sha256:9e3a9e09f9c50cf219bb4c5d3609a4ab4f8f9e31801cf50cb4cced79e186978e
|
| 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": 0.
|
| 6 |
"eval_steps": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1008,6 +1008,16 @@
|
|
| 1008 |
"mean_token_accuracy": 0.9397714591026306,
|
| 1009 |
"num_tokens": 82619.0,
|
| 1010 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 25,
|
|
@@ -1027,7 +1037,7 @@
|
|
| 1027 |
"attributes": {}
|
| 1028 |
}
|
| 1029 |
},
|
| 1030 |
-
"total_flos": 2.
|
| 1031 |
"train_batch_size": 4,
|
| 1032 |
"trial_name": null,
|
| 1033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7651515151515151,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 2525,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1008 |
"mean_token_accuracy": 0.9397714591026306,
|
| 1009 |
"num_tokens": 82619.0,
|
| 1010 |
"step": 2500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 0.1771928510069847,
|
| 1014 |
+
"epoch": 0.7651515151515151,
|
| 1015 |
+
"grad_norm": 0.2506214380264282,
|
| 1016 |
+
"learning_rate": 0.0002,
|
| 1017 |
+
"loss": 0.17615240097045898,
|
| 1018 |
+
"mean_token_accuracy": 0.9421089863777161,
|
| 1019 |
+
"num_tokens": 123713.0,
|
| 1020 |
+
"step": 2525
|
| 1021 |
}
|
| 1022 |
],
|
| 1023 |
"logging_steps": 25,
|
|
|
|
| 1037 |
"attributes": {}
|
| 1038 |
}
|
| 1039 |
},
|
| 1040 |
+
"total_flos": 2.4410656586072064e+17,
|
| 1041 |
"train_batch_size": 4,
|
| 1042 |
"trial_name": null,
|
| 1043 |
"trial_params": null
|