Training in progress, step 51, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed74a0d8491165d996e8776ba32beca7052097a87db4e3a98575bea310c1246b
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31b5af10838dcc096aff3ddaf830a7fa7c00f6926f26c5df1e99acf055396a6e
|
3 |
size 37430836
|
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 sha256:67bf645d6a0b7e40216f236f0f0240fabb9fff82a39bdd98a967655e8e8d3112
|
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,
|
@@ -357,6 +357,13 @@
|
|
357 |
"learning_rate": 0.0001,
|
358 |
"loss": 1.4201,
|
359 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 1,
|
@@ -376,7 +383,7 @@
|
|
376 |
"attributes": {}
|
377 |
}
|
378 |
},
|
379 |
-
"total_flos": 6.
|
380 |
"train_batch_size": 4,
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.13991769547325103,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 51,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
357 |
"learning_rate": 0.0001,
|
358 |
"loss": 1.4201,
|
359 |
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.13991769547325103,
|
363 |
+
"grad_norm": 0.11906778067350388,
|
364 |
+
"learning_rate": 0.00010200000000000001,
|
365 |
+
"loss": 1.3745,
|
366 |
+
"step": 51
|
367 |
}
|
368 |
],
|
369 |
"logging_steps": 1,
|
|
|
383 |
"attributes": {}
|
384 |
}
|
385 |
},
|
386 |
+
"total_flos": 6.302807675675443e+16,
|
387 |
"train_batch_size": 4,
|
388 |
"trial_name": null,
|
389 |
"trial_params": null
|