Training in progress, step 1700, 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:b4973abdd818146c3a2f1ada2a7886d1b1e38c72a2078bc1da83b7ee8606bbc4
|
| 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:b81433cff1ecbae99f74f29d57892b0c42c62fcf6ae9b78b342e57beed669689
|
| 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:aca9e2cf3ff489a53b928d688a0191cffffea384a01e22238c9f5aacd067ea0c
|
| 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:f35bee751eb77ffff19864476726347b03225210d4b4cc7b5f9374386dfc4e74
|
| 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": 3.
|
| 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,
|
|
@@ -143,6 +143,13 @@
|
|
| 143 |
"learning_rate": 8.933333333333334e-05,
|
| 144 |
"loss": 1.3093,
|
| 145 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
}
|
| 147 |
],
|
| 148 |
"logging_steps": 100,
|
|
@@ -162,7 +169,7 @@
|
|
| 162 |
"attributes": {}
|
| 163 |
}
|
| 164 |
},
|
| 165 |
-
"total_flos": 2.
|
| 166 |
"train_batch_size": 8,
|
| 167 |
"trial_name": null,
|
| 168 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.3994688329948444,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 143 |
"learning_rate": 8.933333333333334e-05,
|
| 144 |
"loss": 1.3093,
|
| 145 |
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.3994688329948444,
|
| 149 |
+
"grad_norm": 0.13981318473815918,
|
| 150 |
+
"learning_rate": 8.866666666666668e-05,
|
| 151 |
+
"loss": 1.3045,
|
| 152 |
+
"step": 1700
|
| 153 |
}
|
| 154 |
],
|
| 155 |
"logging_steps": 100,
|
|
|
|
| 169 |
"attributes": {}
|
| 170 |
}
|
| 171 |
},
|
| 172 |
+
"total_flos": 2.653247039588008e+18,
|
| 173 |
"train_batch_size": 8,
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|