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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2170ae8d08ba85a70900bc8d34e067926432cd8c6ae9a7a628dbcaafba7b35e
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c011e239765023dd2a6794a56eba6e53de6ace5c477d02cbf603c6151929685
|
3 |
size 341314196
|
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 sha256:7f6e23a05cbfc0213723b7cf803a83a3bebb0eaebe9bfe5d290a6e2c7a19e84d
|
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:b0edab479cf5df2fd0e0eb08833b9040a0342b7b3b1ce5f746c88e4c78156c68
|
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": 2.
|
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": 9.958,
|
433 |
"eval_steps_per_second": 1.285,
|
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": 3.
|
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": 2.7272727272727275,
|
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": 9.958,
|
433 |
"eval_steps_per_second": 1.285,
|
434 |
"step": 143
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.618181818181818,
|
438 |
+
"grad_norm": 0.3637115955352783,
|
439 |
+
"learning_rate": 4.52511911603265e-07,
|
440 |
+
"loss": 0.036,
|
441 |
+
"step": 144
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.672727272727273,
|
445 |
+
"grad_norm": 0.41367557644844055,
|
446 |
+
"learning_rate": 1.132562476771959e-07,
|
447 |
+
"loss": 0.0382,
|
448 |
+
"step": 147
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 2.7272727272727275,
|
452 |
+
"grad_norm": 0.5478535294532776,
|
453 |
+
"learning_rate": 0.0,
|
454 |
+
"loss": 0.0333,
|
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": 3.389441447244595e+17,
|
476 |
"train_batch_size": 8,
|
477 |
"trial_name": null,
|
478 |
"trial_params": null
|