Training in progress, step 11900, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efb77d7d570661585169f276ba2af872b16bd30ad343d8c208da992d9da8e7cf
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:924b725b7e1204f28edf1e0a514696b0cc3b3379036637fcb7f015379c0fb456
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5ea6feef52f164377ed93bed2dbd484bac24983bc81e5264cf26241ecf793dd
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ded0ce8c2d8686604f40889683ca39879633e7c6e7afea5372290e03f7c87cea
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 23.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1017,6 +1017,13 @@
|
|
| 1017 |
"learning_rate": 2.1333333333333335e-05,
|
| 1018 |
"loss": 1.224,
|
| 1019 |
"step": 11800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1020 |
}
|
| 1021 |
],
|
| 1022 |
"logging_steps": 100,
|
|
@@ -1036,7 +1043,7 @@
|
|
| 1036 |
"attributes": {}
|
| 1037 |
}
|
| 1038 |
},
|
| 1039 |
-
"total_flos": 1.
|
| 1040 |
"train_batch_size": 8,
|
| 1041 |
"trial_name": null,
|
| 1042 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.796281830963913,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1017 |
"learning_rate": 2.1333333333333335e-05,
|
| 1018 |
"loss": 1.224,
|
| 1019 |
"step": 11800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 23.796281830963913,
|
| 1023 |
+
"grad_norm": 0.244966521859169,
|
| 1024 |
+
"learning_rate": 2.0666666666666666e-05,
|
| 1025 |
+
"loss": 1.2247,
|
| 1026 |
+
"step": 11900
|
| 1027 |
}
|
| 1028 |
],
|
| 1029 |
"logging_steps": 100,
|
|
|
|
| 1043 |
"attributes": {}
|
| 1044 |
}
|
| 1045 |
},
|
| 1046 |
+
"total_flos": 1.8572710963375505e+19,
|
| 1047 |
"train_batch_size": 8,
|
| 1048 |
"trial_name": null,
|
| 1049 |
"trial_params": null
|