Training in progress, step 150, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc36f6104be0405cf13ed25029f548088dfc35d08f30f7ecd71800bd0a56c01
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:092f9dc86ddb18f5caa9a036819884f48e68d0eb13ab2f776dee52302c1260ce
|
3 |
size 85723284
|
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:befdb7486277db7ff22af44d01ba80f12f8d774bd0eba53133d2835310ece080
|
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:d1320cc0c91c904e1b37627facbc7bdd09ad072c5e9a4fe376e5569a5cdf3a73
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -432,6 +432,27 @@
|
|
432 |
"eval_samples_per_second": 6.618,
|
433 |
"eval_steps_per_second": 0.831,
|
434 |
"step": 143
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
435 |
}
|
436 |
],
|
437 |
"logging_steps": 3,
|
@@ -446,12 +467,12 @@
|
|
446 |
"should_evaluate": false,
|
447 |
"should_log": false,
|
448 |
"should_save": true,
|
449 |
-
"should_training_stop":
|
450 |
},
|
451 |
"attributes": {}
|
452 |
}
|
453 |
},
|
454 |
-
"total_flos": 4.
|
455 |
"train_batch_size": 8,
|
456 |
"trial_name": null,
|
457 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.16953941791466515,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
432 |
"eval_samples_per_second": 6.618,
|
433 |
"eval_steps_per_second": 0.831,
|
434 |
"step": 143
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.16275784119807854,
|
438 |
+
"grad_norm": 0.9032691717147827,
|
439 |
+
"learning_rate": 2.262559558016325e-07,
|
440 |
+
"loss": 0.4993,
|
441 |
+
"step": 144
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.16614862955637186,
|
445 |
+
"grad_norm": 1.033461332321167,
|
446 |
+
"learning_rate": 5.662812383859795e-08,
|
447 |
+
"loss": 0.4605,
|
448 |
+
"step": 147
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.16953941791466515,
|
452 |
+
"grad_norm": 0.9426572322845459,
|
453 |
+
"learning_rate": 0.0,
|
454 |
+
"loss": 0.4887,
|
455 |
+
"step": 150
|
456 |
}
|
457 |
],
|
458 |
"logging_steps": 3,
|
|
|
467 |
"should_evaluate": false,
|
468 |
"should_log": false,
|
469 |
"should_save": true,
|
470 |
+
"should_training_stop": true
|
471 |
},
|
472 |
"attributes": {}
|
473 |
}
|
474 |
},
|
475 |
+
"total_flos": 4.218781823926272e+17,
|
476 |
"train_batch_size": 8,
|
477 |
"trial_name": null,
|
478 |
"trial_params": null
|