ramdhanfirdaus
commited on
Commit
•
62f266a
1
Parent(s):
7b4c572
Training in progress, step 2800, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e24e09d9874cfe63e946a3885f4501b58eea3039e8d489d62c7a9c02175a6b0
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38e4a629669fe4871341593d23ba93a00020483850008a05512c6a86a10d25ad
|
3 |
size 100693001
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9d6bd701fca6e19968b0e9d9d7fe0c31a82f71b8340d6006477f972d51d1483
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -385,13 +385,27 @@
|
|
385 |
"eval_samples_per_second": 43.585,
|
386 |
"eval_steps_per_second": 5.453,
|
387 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 100,
|
391 |
"max_steps": 4116,
|
392 |
"num_train_epochs": 3,
|
393 |
"save_steps": 100,
|
394 |
-
"total_flos": 1.
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3606998920440674,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2800",
|
4 |
+
"epoch": 2.040072859744991,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
385 |
"eval_samples_per_second": 43.585,
|
386 |
"eval_steps_per_second": 5.453,
|
387 |
"step": 2700
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.04,
|
391 |
+
"learning_rate": 0.0002,
|
392 |
+
"loss": 1.3402,
|
393 |
+
"step": 2800
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 2.04,
|
397 |
+
"eval_loss": 1.3606998920440674,
|
398 |
+
"eval_runtime": 144.0067,
|
399 |
+
"eval_samples_per_second": 43.567,
|
400 |
+
"eval_steps_per_second": 5.451,
|
401 |
+
"step": 2800
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 100,
|
405 |
"max_steps": 4116,
|
406 |
"num_train_epochs": 3,
|
407 |
"save_steps": 100,
|
408 |
+
"total_flos": 1.6689897048172954e+17,
|
409 |
"trial_name": null,
|
410 |
"trial_params": null
|
411 |
}
|