Training in progress, step 1500, 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 40036040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a4bd7fdf55e3dc14dafac5eabc602bfc786e56aa4588445dd73a3c49c98c20
|
| 3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21689885
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c9569bbcdf9e0b5a99be0c2331750fb49a9d46fed026786844af69d1d5cfeac
|
| 3 |
size 21689885
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:404c13d5ef3472b7c26b5b3f9921f88125c5dd4465020c92fe2a47af60e3d654
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acf7052250ac2211212dabe0d11e5984c5369b6649520f06a30b0a27af27acba
|
| 3 |
size 627
|
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": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -189,13 +189,26 @@
|
|
| 189 |
"eval_samples_per_second": 1.781,
|
| 190 |
"eval_steps_per_second": 0.223,
|
| 191 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
}
|
| 193 |
],
|
| 194 |
"logging_steps": 100,
|
| 195 |
"max_steps": 1686,
|
| 196 |
"num_train_epochs": 3,
|
| 197 |
"save_steps": 100,
|
| 198 |
-
"total_flos": 5.
|
| 199 |
"trial_name": null,
|
| 200 |
"trial_params": null
|
| 201 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.6675555555555555,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 189 |
"eval_samples_per_second": 1.781,
|
| 190 |
"eval_steps_per_second": 0.223,
|
| 191 |
"step": 1400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.67,
|
| 195 |
+
"learning_rate": 1.2392880685563612e-05,
|
| 196 |
+
"loss": 0.5481,
|
| 197 |
+
"step": 1500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.67,
|
| 201 |
+
"eval_runtime": 1405.6755,
|
| 202 |
+
"eval_samples_per_second": 1.779,
|
| 203 |
+
"eval_steps_per_second": 0.223,
|
| 204 |
+
"step": 1500
|
| 205 |
}
|
| 206 |
],
|
| 207 |
"logging_steps": 100,
|
| 208 |
"max_steps": 1686,
|
| 209 |
"num_train_epochs": 3,
|
| 210 |
"save_steps": 100,
|
| 211 |
+
"total_flos": 5.751249970397184e+17,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
| 214 |
}
|