Training in progress, step 173, 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 1001465824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eae2757e83b9aeaeed247f86747314384a73a443319ad6b3434d372d0306e0a9
|
3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 509176980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:046a0cf1b275f01298af197a0ea8c1b133b20f129c8cc0fba9d6d416f23eec48
|
3 |
size 509176980
|
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:ed7ef44e0be5ae6f671b8552794c084c69f5daa1ee2258881e51a57db189afdc
|
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 sha256:13cea8c13b7ff143621afe3809a9208b72f31395569d02b28f3b5848f77c0a7e
|
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":
|
5 |
"eval_steps": 15,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -488,6 +488,20 @@
|
|
488 |
"eval_samples_per_second": 2.232,
|
489 |
"eval_steps_per_second": 0.299,
|
490 |
"step": 165
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
491 |
}
|
492 |
],
|
493 |
"logging_steps": 3,
|
@@ -502,12 +516,12 @@
|
|
502 |
"should_evaluate": false,
|
503 |
"should_log": false,
|
504 |
"should_save": true,
|
505 |
-
"should_training_stop":
|
506 |
},
|
507 |
"attributes": {}
|
508 |
}
|
509 |
},
|
510 |
-
"total_flos": 8.
|
511 |
"train_batch_size": 8,
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0086580086580086,
|
5 |
"eval_steps": 15,
|
6 |
+
"global_step": 173,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
488 |
"eval_samples_per_second": 2.232,
|
489 |
"eval_steps_per_second": 0.299,
|
490 |
"step": 165
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 2.9177489177489178,
|
494 |
+
"grad_norm": 1.2679266929626465,
|
495 |
+
"learning_rate": 2.319895532739369e-07,
|
496 |
+
"loss": 1.6958,
|
497 |
+
"step": 168
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.9696969696969697,
|
501 |
+
"grad_norm": 1.2044878005981445,
|
502 |
+
"learning_rate": 3.7142468185014104e-08,
|
503 |
+
"loss": 1.697,
|
504 |
+
"step": 171
|
505 |
}
|
506 |
],
|
507 |
"logging_steps": 3,
|
|
|
516 |
"should_evaluate": false,
|
517 |
"should_log": false,
|
518 |
"should_save": true,
|
519 |
+
"should_training_stop": true
|
520 |
},
|
521 |
"attributes": {}
|
522 |
}
|
523 |
},
|
524 |
+
"total_flos": 8.887307373379584e+17,
|
525 |
"train_batch_size": 8,
|
526 |
"trial_name": null,
|
527 |
"trial_params": null
|