Training in progress, step 2500, 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 sha256:8b8b0a90bdc170007cf3a2fb2f05797b7444d957ffacb0716eb2e43708fd473b
|
| 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 sha256:20aaa1aebce0ab429885f4a9a76c0bea8cc04e396a07ab74b60e850c06e7a34d
|
| 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 sha256:1c9d0789a3647e7759096b4e0b0888e39c1c65428cf396f31ebd671fca523a74
|
| 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,
|
|
@@ -998,6 +998,16 @@
|
|
| 998 |
"mean_token_accuracy": 0.9395198082923889,
|
| 999 |
"num_tokens": 41461.0,
|
| 1000 |
"step": 2475
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1001 |
}
|
| 1002 |
],
|
| 1003 |
"logging_steps": 25,
|
|
@@ -1017,7 +1027,7 @@
|
|
| 1017 |
"attributes": {}
|
| 1018 |
}
|
| 1019 |
},
|
| 1020 |
-
"total_flos": 2.
|
| 1021 |
"train_batch_size": 4,
|
| 1022 |
"trial_name": null,
|
| 1023 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7575757575757576,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 998 |
"mean_token_accuracy": 0.9395198082923889,
|
| 999 |
"num_tokens": 41461.0,
|
| 1000 |
"step": 2475
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 0.18014651894569397,
|
| 1004 |
+
"epoch": 0.7575757575757576,
|
| 1005 |
+
"grad_norm": 0.22747038304805756,
|
| 1006 |
+
"learning_rate": 0.0002,
|
| 1007 |
+
"loss": 0.18118663787841796,
|
| 1008 |
+
"mean_token_accuracy": 0.9397714591026306,
|
| 1009 |
+
"num_tokens": 82619.0,
|
| 1010 |
+
"step": 2500
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 25,
|
|
|
|
| 1027 |
"attributes": {}
|
| 1028 |
}
|
| 1029 |
},
|
| 1030 |
+
"total_flos": 2.41677766460842e+17,
|
| 1031 |
"train_batch_size": 4,
|
| 1032 |
"trial_name": null,
|
| 1033 |
"trial_params": null
|