Training in progress, step 1600, 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:d6e4bd22e52def8ccccc94ff33374f3ae64db15fa712a0c31f0d43fb6dd41fd6
|
| 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 sha256:8a8de6a8b89073e59e41319088fbc40a571892f6e75074b8862465427271f22f
|
| 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 sha256:838dc05cda52d38142a6c88abb10750a545d4764263ad715e238371581cb15c3
|
| 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 sha256:6748d25ec1195b5c83b89c95fc9d661ca2b782e196e028dfd40ee2527327415e
|
| 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,
|
|
@@ -202,13 +202,26 @@
|
|
| 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":
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
| 214 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.8453333333333335,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 202 |
"eval_samples_per_second": 1.779,
|
| 203 |
"eval_steps_per_second": 0.223,
|
| 204 |
"step": 1500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.85,
|
| 208 |
+
"learning_rate": 5.800922874093606e-06,
|
| 209 |
+
"loss": 0.5459,
|
| 210 |
+
"step": 1600
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.85,
|
| 214 |
+
"eval_runtime": 1404.9366,
|
| 215 |
+
"eval_samples_per_second": 1.779,
|
| 216 |
+
"eval_steps_per_second": 0.223,
|
| 217 |
+
"step": 1600
|
| 218 |
}
|
| 219 |
],
|
| 220 |
"logging_steps": 100,
|
| 221 |
"max_steps": 1686,
|
| 222 |
"num_train_epochs": 3,
|
| 223 |
"save_steps": 100,
|
| 224 |
+
"total_flos": 6.166502675841024e+17,
|
| 225 |
"trial_name": null,
|
| 226 |
"trial_params": null
|
| 227 |
}
|