Training in progress, step 37, 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 41599888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d6a63435b55eae4a969345c6d4ed4ddb834c23aaa554c2a01e11f0789906f3f
|
| 3 |
size 41599888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21516104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe97ff2fde5d85ef8eebc2c88ec7463d912c31a8d6167b3aa37f8523ebf1bb72
|
| 3 |
size 21516104
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e085bd535a6c4ffa6d9fc6ccee38616bc6817ec88e00cc6da1cb6b640987319e
|
| 3 |
size 14244
|
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:f2685023609357b3c71d494f9f2b08d0b04f89f15281eccb4d799be8cf74d722
|
| 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": 0.
|
| 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,
|
|
@@ -259,6 +259,13 @@
|
|
| 259 |
"learning_rate": 3.846153846153847e-06,
|
| 260 |
"loss": 0.0116,
|
| 261 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 262 |
}
|
| 263 |
],
|
| 264 |
"logging_steps": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9315499606608969,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 37,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 259 |
"learning_rate": 3.846153846153847e-06,
|
| 260 |
"loss": 0.0116,
|
| 261 |
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9315499606608969,
|
| 265 |
+
"grad_norm": 0.945986270904541,
|
| 266 |
+
"learning_rate": 2.564102564102564e-06,
|
| 267 |
+
"loss": 0.016,
|
| 268 |
+
"step": 37
|
| 269 |
}
|
| 270 |
],
|
| 271 |
"logging_steps": 1,
|