Training in progress, step 1300, 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 sha256:87d5249d20554fe354743154b54f927db5b78df91daf1cc35c2a79e0e2163c8e
|
| 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:f981fe47449bc5d2fad9a41e39e69ecbbf3cf7f6b3c3fa5edd3e08822f8f2397
|
| 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:ed5a8a436709ced1493a3f831d259343bd3c0183bb82ea6d0dca2bdb52be88b7
|
| 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 sha256:2f5ecbfe60b45227d9cf3903e66c2e3072c6f275fcc43ed807b20ab44b920fa9
|
| 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": 2.
|
| 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,
|
|
@@ -107,6 +107,13 @@
|
|
| 107 |
"learning_rate": 9.200000000000001e-05,
|
| 108 |
"loss": 1.3134,
|
| 109 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
}
|
| 111 |
],
|
| 112 |
"logging_steps": 100,
|
|
@@ -126,7 +133,7 @@
|
|
| 126 |
"attributes": {}
|
| 127 |
}
|
| 128 |
},
|
| 129 |
-
"total_flos":
|
| 130 |
"train_batch_size": 8,
|
| 131 |
"trial_name": null,
|
| 132 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.5995938134666456,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 107 |
"learning_rate": 9.200000000000001e-05,
|
| 108 |
"loss": 1.3134,
|
| 109 |
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.5995938134666456,
|
| 113 |
+
"grad_norm": 0.12833993136882782,
|
| 114 |
+
"learning_rate": 9.133333333333334e-05,
|
| 115 |
+
"loss": 1.3161,
|
| 116 |
+
"step": 1300
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"logging_steps": 100,
|
|
|
|
| 133 |
"attributes": {}
|
| 134 |
}
|
| 135 |
},
|
| 136 |
+
"total_flos": 2.0289563117056164e+18,
|
| 137 |
"train_batch_size": 8,
|
| 138 |
"trial_name": null,
|
| 139 |
"trial_params": null
|