Training in progress, step 72, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d39ba22a9179f47abd4d879e0b4c1c2e010cff882166ffa8ab63beed2ca9aa8b
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c64ba771557b848658cfe6bca58403819cd539c75e6699918369bc9ca6e006a
|
3 |
size 37430836
|
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:e9779a9e90815f9ae9fb64f6f9679ff811a7c3527e9bc2274689f47616e21268
|
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,
|
@@ -497,6 +497,20 @@
|
|
497 |
"learning_rate": 0.00014,
|
498 |
"loss": 1.2413,
|
499 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 1,
|
@@ -516,7 +530,7 @@
|
|
516 |
"attributes": {}
|
517 |
}
|
518 |
},
|
519 |
-
"total_flos": 8.
|
520 |
"train_batch_size": 4,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19753086419753085,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 72,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
497 |
"learning_rate": 0.00014,
|
498 |
"loss": 1.2413,
|
499 |
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.19478737997256515,
|
503 |
+
"grad_norm": 0.09149904549121857,
|
504 |
+
"learning_rate": 0.000142,
|
505 |
+
"loss": 1.2548,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.19753086419753085,
|
510 |
+
"grad_norm": 0.08837990462779999,
|
511 |
+
"learning_rate": 0.000144,
|
512 |
+
"loss": 1.3014,
|
513 |
+
"step": 72
|
514 |
}
|
515 |
],
|
516 |
"logging_steps": 1,
|
|
|
530 |
"attributes": {}
|
531 |
}
|
532 |
},
|
533 |
+
"total_flos": 8.906756480548454e+16,
|
534 |
"train_batch_size": 4,
|
535 |
"trial_name": null,
|
536 |
"trial_params": null
|