Model save
Browse files- README.md +74 -12
- adapter_model.safetensors +1 -1
README.md
CHANGED
@@ -1,23 +1,85 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- en
|
4 |
license: apache-2.0
|
|
|
5 |
tags:
|
6 |
-
- text-generation-inference
|
7 |
-
- transformers
|
8 |
-
- unsloth
|
9 |
-
- llama
|
10 |
- trl
|
11 |
- orpo
|
|
|
|
|
12 |
base_model: cognitivecomputations/dolphin-2.9.1-yi-1.5-9b
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
-
- **Developed by:** baconnier
|
18 |
-
- **License:** apache-2.0
|
19 |
-
- **Finetuned from model :** cognitivecomputations/dolphin-2.9.1-yi-1.5-9b
|
20 |
|
21 |
-
|
22 |
|
23 |
-
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- orpo
|
7 |
+
- unsloth
|
8 |
+
- generated_from_trainer
|
9 |
base_model: cognitivecomputations/dolphin-2.9.1-yi-1.5-9b
|
10 |
+
model-index:
|
11 |
+
- name: Gaston_dolphin-2.9.1-yi-1.5-9b
|
12 |
+
results: []
|
13 |
---
|
14 |
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bacoco/Gaston_dolphin-2.9.1-yi-1.5-9b/runs/4d2n86g4)
|
19 |
+
# Gaston_dolphin-2.9.1-yi-1.5-9b
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.9.1-yi-1.5-9b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-yi-1.5-9b) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4290
|
24 |
+
- Rewards/chosen: -0.0153
|
25 |
+
- Rewards/rejected: -0.2895
|
26 |
+
- Rewards/accuracies: 0.9985
|
27 |
+
- Rewards/margins: 0.2742
|
28 |
+
- Logps/rejected: -2.8952
|
29 |
+
- Logps/chosen: -0.1528
|
30 |
+
- Logits/rejected: -0.1534
|
31 |
+
- Logits/chosen: 0.0002
|
32 |
+
- Nll Loss: 0.4278
|
33 |
+
- Log Odds Ratio: -0.0124
|
34 |
+
- Log Odds Chosen: 4.8981
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 8e-06
|
54 |
+
- train_batch_size: 4
|
55 |
+
- eval_batch_size: 4
|
56 |
+
- seed: 42
|
57 |
+
- gradient_accumulation_steps: 4
|
58 |
+
- total_train_batch_size: 16
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: cosine
|
61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 1
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|
67 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
|
68 |
+
| 0.5193 | 0.1005 | 103 | 0.5159 | -0.0187 | -0.0825 | 0.9971 | 0.0638 | -0.8248 | -0.1866 | 0.1547 | 0.1467 | 0.5004 | -0.1555 | 2.0327 |
|
69 |
+
| 0.4988 | 0.2009 | 206 | 0.4724 | -0.0170 | -0.1413 | 0.9985 | 0.1243 | -1.4130 | -0.1703 | 0.0154 | -0.0134 | 0.4661 | -0.0627 | 3.0432 |
|
70 |
+
| 0.4375 | 0.3014 | 309 | 0.4577 | -0.0162 | -0.1628 | 0.9985 | 0.1466 | -1.6283 | -0.1622 | 0.1372 | 0.1328 | 0.4530 | -0.0467 | 3.3955 |
|
71 |
+
| 0.4738 | 0.4019 | 412 | 0.4463 | -0.0160 | -0.2198 | 0.9985 | 0.2038 | -2.1980 | -0.1596 | -0.0220 | 0.0649 | 0.4438 | -0.0250 | 4.0928 |
|
72 |
+
| 0.4893 | 0.5023 | 515 | 0.4406 | -0.0159 | -0.2499 | 0.9985 | 0.2341 | -2.4993 | -0.1585 | -0.0720 | 0.0474 | 0.4388 | -0.0185 | 4.4389 |
|
73 |
+
| 0.4565 | 0.6028 | 618 | 0.4357 | -0.0157 | -0.3289 | 0.9985 | 0.3133 | -3.2895 | -0.1566 | -0.1392 | 0.0470 | 0.4347 | -0.0093 | 5.2916 |
|
74 |
+
| 0.4069 | 0.7032 | 721 | 0.4324 | -0.0154 | -0.3096 | 0.9985 | 0.2942 | -3.0962 | -0.1544 | -0.1833 | -0.0044 | 0.4313 | -0.0107 | 5.1028 |
|
75 |
+
| 0.4297 | 0.8037 | 824 | 0.4299 | -0.0153 | -0.2854 | 0.9985 | 0.2701 | -2.8536 | -0.1528 | -0.1911 | -0.0397 | 0.4286 | -0.0129 | 4.8536 |
|
76 |
+
| 0.4437 | 0.9042 | 927 | 0.4290 | -0.0153 | -0.2895 | 0.9985 | 0.2742 | -2.8952 | -0.1528 | -0.1534 | 0.0002 | 0.4278 | -0.0124 | 4.8981 |
|
77 |
|
|
|
|
|
|
|
78 |
|
79 |
+
### Framework versions
|
80 |
|
81 |
+
- PEFT 0.11.1
|
82 |
+
- Transformers 4.41.0
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- 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 1742825432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ff27532d459f0a271bb5a4545ff31ef929f7a94f7cc0e460ed6daebeec7752
|
3 |
size 1742825432
|