Training in progress, step 64, 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:b16d6eb07033b72a3b2968dc0dc635125ffab4a31846978220b6caf42e45fad7
|
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 sha256:4e1a5df9978303ccfad162c5fd2bedf1e222d91ffaa01e9f8d185b50633a3219
|
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 sha256:14bf2f4838ff5eca2b84152c5f01ed2f55b189468509c0c79a96ec148e07b9cb
|
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,
|
@@ -434,6 +434,27 @@
|
|
434 |
"learning_rate": 0.000122,
|
435 |
"loss": 1.4028,
|
436 |
"step": 61
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
437 |
}
|
438 |
],
|
439 |
"logging_steps": 1,
|
@@ -453,7 +474,7 @@
|
|
453 |
"attributes": {}
|
454 |
}
|
455 |
},
|
456 |
-
"total_flos": 7.
|
457 |
"train_batch_size": 4,
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1755829903978052,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 64,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
434 |
"learning_rate": 0.000122,
|
435 |
"loss": 1.4028,
|
436 |
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.1700960219478738,
|
440 |
+
"grad_norm": 0.16491512954235077,
|
441 |
+
"learning_rate": 0.000124,
|
442 |
+
"loss": 1.3366,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1728395061728395,
|
447 |
+
"grad_norm": 0.1202845573425293,
|
448 |
+
"learning_rate": 0.000126,
|
449 |
+
"loss": 1.3201,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.1755829903978052,
|
454 |
+
"grad_norm": 0.10146432369947433,
|
455 |
+
"learning_rate": 0.00012800000000000002,
|
456 |
+
"loss": 1.3083,
|
457 |
+
"step": 64
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 1,
|
|
|
474 |
"attributes": {}
|
475 |
}
|
476 |
},
|
477 |
+
"total_flos": 7.909975005462528e+16,
|
478 |
"train_batch_size": 4,
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|