Hugging Face's logo

rbelanec
/
train_openbookqa_1754652174

PEFT
Safetensors
llama-factory
prefix-tuning
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
5abbb1a
路
verified 路
1 Parent(s): d0d14e8

Model save

Browse files
Files changed (2) hide show
  1. README.md +81 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: train_openbookqa_1754652174
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # train_openbookqa_1754652174
17
+
18
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7000
21
+ - Num Input Tokens Seen: 4204168
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 123
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 10.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------------:|
53
+ | 4.7201 | 0.5 | 558 | 4.3558 | 210048 |
54
+ | 0.8136 | 1.0 | 1116 | 0.8080 | 420520 |
55
+ | 0.7929 | 1.5 | 1674 | 0.7312 | 630888 |
56
+ | 0.7296 | 2.0 | 2232 | 0.7163 | 841024 |
57
+ | 0.8036 | 2.5 | 2790 | 0.7250 | 1051168 |
58
+ | 0.7289 | 3.0 | 3348 | 0.7142 | 1261304 |
59
+ | 0.698 | 3.5 | 3906 | 0.7066 | 1472152 |
60
+ | 0.7177 | 4.0 | 4464 | 0.7047 | 1682016 |
61
+ | 0.6778 | 4.5 | 5022 | 0.7019 | 1892160 |
62
+ | 0.7394 | 5.0 | 5580 | 0.7092 | 2102920 |
63
+ | 0.6996 | 5.5 | 6138 | 0.7000 | 2311976 |
64
+ | 0.7012 | 6.0 | 6696 | 0.7014 | 2523672 |
65
+ | 0.6863 | 6.5 | 7254 | 0.7022 | 2732440 |
66
+ | 0.6765 | 7.0 | 7812 | 0.7004 | 2943688 |
67
+ | 0.7108 | 7.5 | 8370 | 0.7001 | 3153640 |
68
+ | 0.7097 | 8.0 | 8928 | 0.6994 | 3363864 |
69
+ | 0.6701 | 8.5 | 9486 | 0.6988 | 3574616 |
70
+ | 0.7297 | 9.0 | 10044 | 0.6996 | 3783840 |
71
+ | 0.6966 | 9.5 | 10602 | 0.6985 | 3994976 |
72
+ | 0.6937 | 10.0 | 11160 | 0.7000 | 4204168 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.15.2
78
+ - Transformers 4.51.3
79
+ - Pytorch 2.8.0+cu128
80
+ - Datasets 3.6.0
81
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce3655411ee81a40e7df752832814985f270e924e048e3009795c04c299b0786
3
  size 26214528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9faf648f287fd3245987ad7efcefc975e9885bb6658433ddf8ff836e5bf00c83
3
  size 26214528