Training in progress, step 1900, 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 sha256:24064aa8683230a7b3a039fd81e1b05e0ff78db2e5bf584fe89728e9df23ffe5
|
| 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 sha256:9e7683c83debe0cae274d7783463a965c02eab380f24d7b8882509a86c4f8309
|
| 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 sha256:9386b4e0c43c2c20517e468db5aea4f7e38dafdd46988a182c3761eebc734402
|
| 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:b1880aef90fa44f8fcb9d240241d2b9fce349526552d8adb6f96784c29ef5265
|
| 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,
|
|
@@ -157,6 +157,13 @@
|
|
| 157 |
"learning_rate": 8.800000000000001e-05,
|
| 158 |
"loss": 1.2961,
|
| 159 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
}
|
| 161 |
],
|
| 162 |
"logging_steps": 100,
|
|
@@ -176,7 +183,7 @@
|
|
| 176 |
"attributes": {}
|
| 177 |
}
|
| 178 |
},
|
| 179 |
-
"total_flos": 2.
|
| 180 |
"train_batch_size": 8,
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.799406342758944,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 157 |
"learning_rate": 8.800000000000001e-05,
|
| 158 |
"loss": 1.2961,
|
| 159 |
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.799406342758944,
|
| 163 |
+
"grad_norm": 0.13838326930999756,
|
| 164 |
+
"learning_rate": 8.733333333333333e-05,
|
| 165 |
+
"loss": 1.2946,
|
| 166 |
+
"step": 1900
|
| 167 |
}
|
| 168 |
],
|
| 169 |
"logging_steps": 100,
|
|
|
|
| 183 |
"attributes": {}
|
| 184 |
}
|
| 185 |
},
|
| 186 |
+
"total_flos": 2.965396981964341e+18,
|
| 187 |
"train_batch_size": 8,
|
| 188 |
"trial_name": null,
|
| 189 |
"trial_params": null
|