Femboyuwu2000
commited on
Commit
•
64dfaa7
1
Parent(s):
a8d3c55
Training in progress, step 80, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47f45bb6b4f07f7d432390b14be121ef3fde57d9170f5a9f4b4c37cff8852554
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d8969f31b5a0f091cc220fc791b3de73ca8cb027c812d52dcbb2597614b59c
|
3 |
size 2423738
|
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:ef17d5f9b420f5d86fa9fe589f3c843a6c4095df024510341423c1a1b417d1a8
|
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:b1b46a53d749681ad7163f82e3c76fde0da752adc35db447dc604f9a8c960ad4
|
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":
|
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,
|
@@ -28,6 +28,13 @@
|
|
28 |
"learning_rate": 1e-05,
|
29 |
"loss": 3.5828,
|
30 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 20,
|
@@ -35,7 +42,7 @@
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 1,
|
37 |
"save_steps": 20,
|
38 |
-
"total_flos":
|
39 |
"train_batch_size": 1,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.226020094479855e-05,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 80,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
28 |
"learning_rate": 1e-05,
|
29 |
"loss": 3.5828,
|
30 |
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0,
|
34 |
+
"grad_norm": 2.782036542892456,
|
35 |
+
"learning_rate": 1.3166666666666665e-05,
|
36 |
+
"loss": 3.5865,
|
37 |
+
"step": 80
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 20,
|
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 1,
|
44 |
"save_steps": 20,
|
45 |
+
"total_flos": 457519177248768.0,
|
46 |
"train_batch_size": 1,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|