Training in progress, step 130, 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 864368280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af0e4da7a4daf38aa41d02324e0fb0781d71211d85d53148acfde21b9d1ce324
|
3 |
size 864368280
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 439588164
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b222345931cd8549effd6393be9a1c7633d43d03cfc00e47815dadc800787da3
|
3 |
size 439588164
|
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 sha256:41726cfc9334bd6dd72627baf76be711287f22c8cd8167539158c5a9ec825da3
|
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:aec3ffa606cc7b66d7e0ba20c7c1c47643e7f38d54a597b271e1c47d5abb9ef2
|
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": 2.
|
5 |
"eval_steps": 11,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -383,6 +383,27 @@
|
|
383 |
"eval_samples_per_second": 7.957,
|
384 |
"eval_steps_per_second": 1.09,
|
385 |
"step": 121
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
386 |
}
|
387 |
],
|
388 |
"logging_steps": 3,
|
@@ -397,12 +418,12 @@
|
|
397 |
"should_evaluate": false,
|
398 |
"should_log": false,
|
399 |
"should_save": true,
|
400 |
-
"should_training_stop":
|
401 |
},
|
402 |
"attributes": {}
|
403 |
}
|
404 |
},
|
405 |
-
"total_flos": 2.
|
406 |
"train_batch_size": 8,
|
407 |
"trial_name": null,
|
408 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9885057471264367,
|
5 |
"eval_steps": 11,
|
6 |
+
"global_step": 130,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
383 |
"eval_samples_per_second": 7.957,
|
384 |
"eval_steps_per_second": 1.09,
|
385 |
"step": 121
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 2.8275862068965516,
|
389 |
+
"grad_norm": 1.9297926425933838,
|
390 |
+
"learning_rate": 8.372546218022747e-07,
|
391 |
+
"loss": 0.7666,
|
392 |
+
"step": 123
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.896551724137931,
|
396 |
+
"grad_norm": 1.666353702545166,
|
397 |
+
"learning_rate": 2.7390523158633554e-07,
|
398 |
+
"loss": 0.6233,
|
399 |
+
"step": 126
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 2.9655172413793105,
|
403 |
+
"grad_norm": 1.1451926231384277,
|
404 |
+
"learning_rate": 1.7133751222137007e-08,
|
405 |
+
"loss": 0.5853,
|
406 |
+
"step": 129
|
407 |
}
|
408 |
],
|
409 |
"logging_steps": 3,
|
|
|
418 |
"should_evaluate": false,
|
419 |
"should_log": false,
|
420 |
"should_save": true,
|
421 |
+
"should_training_stop": true
|
422 |
},
|
423 |
"attributes": {}
|
424 |
}
|
425 |
},
|
426 |
+
"total_flos": 2.176515519409029e+17,
|
427 |
"train_batch_size": 8,
|
428 |
"trial_name": null,
|
429 |
"trial_params": null
|