Training in progress, step 74, 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 60010048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a9059adf79ca428d9d0d795989ab3ec468669cce56f2e5462ac02ce2a3bb99c
|
3 |
size 60010048
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30427860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1559361ac2d776ad1b592483aa89fc3782eb6e4b7542b8999e665696bae0d7
|
3 |
size 30427860
|
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 sha256:46a86174539a86c9c10ef9b72608d49039cdad58e77dd25141a021b27f07e927
|
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,
|
@@ -504,6 +504,27 @@
|
|
504 |
"learning_rate": 0.000142,
|
505 |
"loss": 1.2399,
|
506 |
"step": 71
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
507 |
}
|
508 |
],
|
509 |
"logging_steps": 1,
|
@@ -523,7 +544,7 @@
|
|
523 |
"attributes": {}
|
524 |
}
|
525 |
},
|
526 |
-
"total_flos":
|
527 |
"train_batch_size": 4,
|
528 |
"trial_name": null,
|
529 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2030178326474623,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 74,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
504 |
"learning_rate": 0.000142,
|
505 |
"loss": 1.2399,
|
506 |
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.19753086419753085,
|
510 |
+
"grad_norm": 0.11786019057035446,
|
511 |
+
"learning_rate": 0.000144,
|
512 |
+
"loss": 1.2704,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.20027434842249658,
|
517 |
+
"grad_norm": 0.11220725625753403,
|
518 |
+
"learning_rate": 0.000146,
|
519 |
+
"loss": 1.2782,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.2030178326474623,
|
524 |
+
"grad_norm": 0.10791537165641785,
|
525 |
+
"learning_rate": 0.000148,
|
526 |
+
"loss": 1.304,
|
527 |
+
"step": 74
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 1,
|
|
|
544 |
"attributes": {}
|
545 |
}
|
546 |
},
|
547 |
+
"total_flos": 9.011919058054349e+16,
|
548 |
"train_batch_size": 4,
|
549 |
"trial_name": null,
|
550 |
"trial_params": null
|