Model save
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
9 |
+
model-index:
|
10 |
+
- name: llama3-L1-SFT-L2-KTO
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# llama3-L1-SFT-L2-KTO
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2122
|
22 |
+
- Rewards/chosen: 0.3257
|
23 |
+
- Rewards/rejected: -9.5548
|
24 |
+
- Rewards/accuracies: 1.0
|
25 |
+
- Rewards/margins: 9.8805
|
26 |
+
- Logps/rejected: -1018.5145
|
27 |
+
- Logps/chosen: -12.0858
|
28 |
+
- Logits/rejected: 1.0988
|
29 |
+
- Logits/chosen: 0.1932
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 5e-06
|
49 |
+
- train_batch_size: 1
|
50 |
+
- eval_batch_size: 1
|
51 |
+
- seed: 42
|
52 |
+
- distributed_type: multi-GPU
|
53 |
+
- num_devices: 2
|
54 |
+
- gradient_accumulation_steps: 4
|
55 |
+
- total_train_batch_size: 8
|
56 |
+
- total_eval_batch_size: 2
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: cosine
|
59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
60 |
+
- num_epochs: 1
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
65 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
66 |
+
| 0.2129 | 0.4994 | 1000 | 0.2124 | 0.3252 | -9.3514 | 1.0 | 9.6766 | -998.1762 | -12.1315 | 1.1081 | 0.2036 |
|
67 |
+
| 0.2118 | 0.9989 | 2000 | 0.2122 | 0.3257 | -9.5548 | 1.0 | 9.8805 | -1018.5145 | -12.0858 | 1.0988 | 0.1932 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.7.1
|
73 |
+
- Transformers 4.40.2
|
74 |
+
- Pytorch 2.1.2+cu121
|
75 |
+
- Datasets 2.18.0
|
76 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83946192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:693e404e5e556ffdce4b15da9650499a4f7123effd01b314aea14132dd988de0
|
3 |
size 83946192
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9998751404669747,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.2449444185841929,
|
5 |
+
"train_runtime": 3711.3289,
|
6 |
+
"train_samples": 16017,
|
7 |
+
"train_samples_per_second": 4.316,
|
8 |
+
"train_steps_per_second": 0.539
|
9 |
+
}
|
runs/May10_01-58-41_612e66badb5c/events.out.tfevents.1715306418.612e66badb5c.51730.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d579ea50305ebfbc8440f7cffd4e7461c8b54845e2803543ef0e26867c5d2e
|
3 |
+
size 144885
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9998751404669747,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.2449444185841929,
|
5 |
+
"train_runtime": 3711.3289,
|
6 |
+
"train_samples": 16017,
|
7 |
+
"train_samples_per_second": 4.316,
|
8 |
+
"train_steps_per_second": 0.539
|
9 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|