Training in progress, step 1800, 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:b23bbf8e2596c69ade90bdc024987f09023799ee0a67f340bd5762b13fb39b2b
|
| 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 sha256:9b5275c4032b1e3f929b02daec7945e8c0af2d4f48ab0c6ad547f385702bcb0e
|
| 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 sha256:59038f6fd31a878a0088aa82a3fa047e39cd383b08a1e2f45a6b7fe38fcc6c68
|
| 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 sha256:3fbcd595bd682a5655776734b02f2217b8256b553a1f0e90feb357642ed64497
|
| 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,
|
|
@@ -150,6 +150,13 @@
|
|
| 150 |
"learning_rate": 8.866666666666668e-05,
|
| 151 |
"loss": 1.3045,
|
| 152 |
"step": 1700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
}
|
| 154 |
],
|
| 155 |
"logging_steps": 100,
|
|
@@ -169,7 +176,7 @@
|
|
| 169 |
"attributes": {}
|
| 170 |
}
|
| 171 |
},
|
| 172 |
-
"total_flos": 2.
|
| 173 |
"train_batch_size": 8,
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.5994375878768943,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 150 |
"learning_rate": 8.866666666666668e-05,
|
| 151 |
"loss": 1.3045,
|
| 152 |
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.5994375878768943,
|
| 156 |
+
"grad_norm": 0.1482376754283905,
|
| 157 |
+
"learning_rate": 8.800000000000001e-05,
|
| 158 |
+
"loss": 1.2961,
|
| 159 |
+
"step": 1800
|
| 160 |
}
|
| 161 |
],
|
| 162 |
"logging_steps": 100,
|
|
|
|
| 176 |
"attributes": {}
|
| 177 |
}
|
| 178 |
},
|
| 179 |
+
"total_flos": 2.8093220107761746e+18,
|
| 180 |
"train_batch_size": 8,
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|