Model save
Browse files- README.md +83 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.1
|
| 4 |
+
base_model: meta-llama/Llama-3.1-70B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:meta-llama/Llama-3.1-70B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: llama71b-mentalchat16k
|
| 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 |
+
# llama71b-mentalchat16k
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.7052
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 8e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 50 |
+
- num_epochs: 3
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.8207 | 0.1496 | 100 | 0.7920 |
|
| 58 |
+
| 0.7716 | 0.2992 | 200 | 0.7492 |
|
| 59 |
+
| 0.7208 | 0.4488 | 300 | 0.7363 |
|
| 60 |
+
| 0.7237 | 0.5985 | 400 | 0.7187 |
|
| 61 |
+
| 0.7156 | 0.7481 | 500 | 0.7088 |
|
| 62 |
+
| 0.7024 | 0.8977 | 600 | 0.6963 |
|
| 63 |
+
| 0.6125 | 1.0464 | 700 | 0.7004 |
|
| 64 |
+
| 0.5753 | 1.1960 | 800 | 0.6942 |
|
| 65 |
+
| 0.5497 | 1.3456 | 900 | 0.6878 |
|
| 66 |
+
| 0.5589 | 1.4952 | 1000 | 0.6804 |
|
| 67 |
+
| 0.5453 | 1.6448 | 1100 | 0.6761 |
|
| 68 |
+
| 0.5316 | 1.7945 | 1200 | 0.6693 |
|
| 69 |
+
| 0.5422 | 1.9441 | 1300 | 0.6634 |
|
| 70 |
+
| 0.349 | 2.0928 | 1400 | 0.7011 |
|
| 71 |
+
| 0.3481 | 2.2424 | 1500 | 0.7033 |
|
| 72 |
+
| 0.337 | 2.3920 | 1600 | 0.7048 |
|
| 73 |
+
| 0.3505 | 2.5416 | 1700 | 0.7049 |
|
| 74 |
+
| 0.3424 | 2.6912 | 1800 | 0.7052 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- PEFT 0.18.0
|
| 80 |
+
- Transformers 4.57.1
|
| 81 |
+
- Pytorch 2.5.1+cu124
|
| 82 |
+
- Datasets 4.4.1
|
| 83 |
+
- Tokenizers 0.22.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3313653480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:659856363f61a8ae2956f101950358abb38162de26afe46ed58aac8340aad3d1
|
| 3 |
size 3313653480
|