Wangzaistone123
commited on
Commit
•
67056fe
1
Parent(s):
f84ed2a
LoRA files
Browse files- README.md +8 -8
- adapter_model.bin +3 -0
- finetuning_args.json +16 -0
- rng_state.pth +3 -0
- trainer_state.json +67 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.4.0
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17465154ebf39490592fab680f319d692b019002de17d58460f1f1745722266b
|
3 |
+
size 209770637
|
finetuning_args.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dpo_beta": 0.1,
|
3 |
+
"finetuning_type": "lora",
|
4 |
+
"lora_alpha": 32.0,
|
5 |
+
"lora_dropout": 0.1,
|
6 |
+
"lora_rank": 64,
|
7 |
+
"lora_target": [
|
8 |
+
"q_proj",
|
9 |
+
"v_proj"
|
10 |
+
],
|
11 |
+
"name_module_trainable": "mlp",
|
12 |
+
"num_hidden_layers": 32,
|
13 |
+
"num_layer_trainable": 3,
|
14 |
+
"ppo_score_norm": false,
|
15 |
+
"resume_lora_training": true
|
16 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:295fd0124fd4af5b98b14acffeb4407253dd0e74441344e646e94f1841b842a2
|
3 |
+
size 14575
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.3911537128998726,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.92,
|
13 |
+
"learning_rate": 0.0001934857749846208,
|
14 |
+
"loss": 0.1563,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.85,
|
19 |
+
"learning_rate": 0.00017479180248950295,
|
20 |
+
"loss": 0.0667,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 2.77,
|
25 |
+
"learning_rate": 0.00014635361737993667,
|
26 |
+
"loss": 0.0389,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.7,
|
31 |
+
"learning_rate": 0.00011187627439257638,
|
32 |
+
"loss": 0.0217,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 4.62,
|
37 |
+
"learning_rate": 7.58516369304635e-05,
|
38 |
+
"loss": 0.012,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 5.54,
|
43 |
+
"learning_rate": 4.2973156884111344e-05,
|
44 |
+
"loss": 0.0058,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 6.47,
|
49 |
+
"learning_rate": 1.752439059723171e-05,
|
50 |
+
"loss": 0.0025,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 7.39,
|
55 |
+
"learning_rate": 2.8209178689553083e-06,
|
56 |
+
"loss": 0.0014,
|
57 |
+
"step": 4000
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 500,
|
61 |
+
"max_steps": 4328,
|
62 |
+
"num_train_epochs": 8,
|
63 |
+
"save_steps": 2000,
|
64 |
+
"total_flos": 3.256255138554317e+18,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26ab201b1691dcc90c25344dfa536d42c15fbb4ac7ce976f99dfd505fa7fb1bc
|
3 |
+
size 3496
|