ramdhanfirdaus
commited on
Commit
•
02210c0
1
Parent(s):
ff443e5
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 75507072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9558ffacb1406cf319cb4564cd910ab2eb5c43f2c3fdad67a59a22f993d61909
|
3 |
size 75507072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151034501
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deadd118a49b60af187a6021b932f75dab37d56200bfa634238d4e39da3da637
|
3 |
size 151034501
|
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 sha256:84bb513a36255f7d8ac49c282923197f8cd306767f0110ec7b93a182523a1deb
|
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": 15.024,
|
386 |
"eval_steps_per_second": 1.88,
|
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":
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1963659524917603,
|
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": 15.024,
|
386 |
"eval_steps_per_second": 1.88,
|
387 |
"step": 2700
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.04,
|
391 |
+
"learning_rate": 0.0002,
|
392 |
+
"loss": 1.1787,
|
393 |
+
"step": 2800
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 2.04,
|
397 |
+
"eval_loss": 1.1963659524917603,
|
398 |
+
"eval_runtime": 417.7494,
|
399 |
+
"eval_samples_per_second": 15.019,
|
400 |
+
"eval_steps_per_second": 1.879,
|
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": 9.077493057814364e+17,
|
409 |
"trial_name": null,
|
410 |
"trial_params": null
|
411 |
}
|