DuongTrongChi
commited on
Commit
•
4b06ea1
1
Parent(s):
c4880e9
Training in progress, step 57, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f82a8f9b0add76d31ea6ae4cb5db11e7ebe4f9b3dfd72c23ab9716529079cc7c
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675156
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cb79e240b6e00c990502fc6e3fd7587e23f92da510346a60334db2be12add81
|
3 |
size 50675156
|
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 sha256:880edddbe46127edc7ba6dd26bd5a9a8099912d97f367e9ef6f4ce4f3857b7b3
|
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,
|
@@ -385,6 +385,27 @@
|
|
385 |
"learning_rate": 0.00010800000000000001,
|
386 |
"loss": 1.2237,
|
387 |
"step": 54
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 1,
|
@@ -404,7 +425,7 @@
|
|
404 |
"attributes": {}
|
405 |
}
|
406 |
},
|
407 |
-
"total_flos": 1.
|
408 |
"train_batch_size": 16,
|
409 |
"trial_name": null,
|
410 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.15637860082304528,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 57,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
385 |
"learning_rate": 0.00010800000000000001,
|
386 |
"loss": 1.2237,
|
387 |
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.15089163237311384,
|
391 |
+
"grad_norm": 0.167573019862175,
|
392 |
+
"learning_rate": 0.00011000000000000002,
|
393 |
+
"loss": 1.268,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.15363511659807957,
|
398 |
+
"grad_norm": 0.16625213623046875,
|
399 |
+
"learning_rate": 0.00011200000000000001,
|
400 |
+
"loss": 1.23,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.15637860082304528,
|
405 |
+
"grad_norm": 0.17408426105976105,
|
406 |
+
"learning_rate": 0.00011399999999999999,
|
407 |
+
"loss": 1.2036,
|
408 |
+
"step": 57
|
409 |
}
|
410 |
],
|
411 |
"logging_steps": 1,
|
|
|
425 |
"attributes": {}
|
426 |
}
|
427 |
},
|
428 |
+
"total_flos": 1.6292298586005504e+17,
|
429 |
"train_batch_size": 16,
|
430 |
"trial_name": null,
|
431 |
"trial_params": null
|