Training in progress, step 3900, 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 sha256:34ccd5de3dc33e2c7424dc7cf4b85a5a709fca9096fa4a9e57d5b285ff6b3114
|
| 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:fc942e4306700121c17e3615d588416b659b676b78b9a8f8eb5c18bf77158d0d
|
| 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:ddf16c50a5456b7ba636d92d279525e70ed7b592671b1bae1bbab7d4cde9be07
|
| 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:da2c93534b46f49cffb916f9acfdfa62706aa3d860ab98491bfe244dd7da6c9a
|
| 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": 7.
|
| 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,
|
|
@@ -329,6 +329,13 @@
|
|
| 329 |
"learning_rate": 7.466666666666667e-05,
|
| 330 |
"loss": 1.266,
|
| 331 |
"step": 3800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 332 |
}
|
| 333 |
],
|
| 334 |
"logging_steps": 100,
|
|
@@ -348,7 +355,7 @@
|
|
| 348 |
"attributes": {}
|
| 349 |
}
|
| 350 |
},
|
| 351 |
-
"total_flos":
|
| 352 |
"train_batch_size": 8,
|
| 353 |
"trial_name": null,
|
| 354 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.798781440399938,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 329 |
"learning_rate": 7.466666666666667e-05,
|
| 330 |
"loss": 1.266,
|
| 331 |
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.798781440399938,
|
| 335 |
+
"grad_norm": 0.17816804349422455,
|
| 336 |
+
"learning_rate": 7.4e-05,
|
| 337 |
+
"loss": 1.2611,
|
| 338 |
+
"step": 3900
|
| 339 |
}
|
| 340 |
],
|
| 341 |
"logging_steps": 100,
|
|
|
|
| 355 |
"attributes": {}
|
| 356 |
}
|
| 357 |
},
|
| 358 |
+
"total_flos": 6.086859778246574e+18,
|
| 359 |
"train_batch_size": 8,
|
| 360 |
"trial_name": null,
|
| 361 |
"trial_params": null
|