Training in progress, step 3500, 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 31466288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0445650b673f6acf4b81accd31266f2c4637fc19aa77cc6e396eaa4975a1eab
|
3 |
size 31466288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62950917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:286fd08dd930b8bfdfaa5d84780012e0686a79b98621af42af734f8c4f1c5e8d
|
3 |
size 62950917
|
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 sha256:330a75bddc9a21e822cfc3670609e9a673a0ce82e6de4caea030d25bd7d00980
|
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 sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
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,
|
@@ -469,13 +469,41 @@
|
|
469 |
"eval_samples_per_second": 11.289,
|
470 |
"eval_steps_per_second": 1.412,
|
471 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 100,
|
475 |
"max_steps": 4116,
|
476 |
"num_train_epochs": 3,
|
477 |
"save_steps": 100,
|
478 |
-
"total_flos":
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.221109390258789,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3500",
|
4 |
+
"epoch": 2.5500910746812386,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
469 |
"eval_samples_per_second": 11.289,
|
470 |
"eval_steps_per_second": 1.412,
|
471 |
"step": 3300
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.48,
|
475 |
+
"learning_rate": 0.0002,
|
476 |
+
"loss": 1.1648,
|
477 |
+
"step": 3400
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 2.48,
|
481 |
+
"eval_loss": 1.2390271425247192,
|
482 |
+
"eval_runtime": 555.5992,
|
483 |
+
"eval_samples_per_second": 11.292,
|
484 |
+
"eval_steps_per_second": 1.413,
|
485 |
+
"step": 3400
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.55,
|
489 |
+
"learning_rate": 0.0002,
|
490 |
+
"loss": 1.1497,
|
491 |
+
"step": 3500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.55,
|
495 |
+
"eval_loss": 1.221109390258789,
|
496 |
+
"eval_runtime": 555.5623,
|
497 |
+
"eval_samples_per_second": 11.293,
|
498 |
+
"eval_steps_per_second": 1.413,
|
499 |
+
"step": 3500
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 100,
|
503 |
"max_steps": 4116,
|
504 |
"num_train_epochs": 3,
|
505 |
"save_steps": 100,
|
506 |
+
"total_flos": 9.112777792001802e+17,
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|