Model save
Browse files- README.md +84 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mifeng09/my_final_llama_model_v2_add_wiki_fix_resume
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:mifeng09/my_final_llama_model_v2_add_wiki_fix_resume
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama_lora_20k_alpaca_begining
|
| 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 |
+
# llama_lora_20k_alpaca_begining
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mifeng09/my_final_llama_model_v2_add_wiki_fix_resume](https://huggingface.co/mifeng09/my_final_llama_model_v2_add_wiki_fix_resume) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 3.7591
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- lr_scheduler_warmup_steps: 101
|
| 50 |
+
- num_epochs: 3
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 4.2374 | 0.1484 | 50 | 4.0144 |
|
| 57 |
+
| 4.3818 | 0.2967 | 100 | 3.9270 |
|
| 58 |
+
| 3.944 | 0.4451 | 150 | 3.8766 |
|
| 59 |
+
| 3.3377 | 0.5935 | 200 | 3.8441 |
|
| 60 |
+
| 3.3489 | 0.7418 | 250 | 3.8238 |
|
| 61 |
+
| 3.5876 | 0.8902 | 300 | 3.8094 |
|
| 62 |
+
| 3.7506 | 1.0386 | 350 | 3.7967 |
|
| 63 |
+
| 3.9164 | 1.1869 | 400 | 3.7891 |
|
| 64 |
+
| 4.4806 | 1.3353 | 450 | 3.7829 |
|
| 65 |
+
| 4.078 | 1.4837 | 500 | 3.7769 |
|
| 66 |
+
| 3.8764 | 1.6320 | 550 | 3.7716 |
|
| 67 |
+
| 3.7083 | 1.7804 | 600 | 3.7681 |
|
| 68 |
+
| 3.5106 | 1.9288 | 650 | 3.7660 |
|
| 69 |
+
| 3.8436 | 2.0772 | 700 | 3.7631 |
|
| 70 |
+
| 3.8274 | 2.2255 | 750 | 3.7621 |
|
| 71 |
+
| 4.0989 | 2.3739 | 800 | 3.7603 |
|
| 72 |
+
| 3.7672 | 2.5223 | 850 | 3.7594 |
|
| 73 |
+
| 3.7825 | 2.6706 | 900 | 3.7592 |
|
| 74 |
+
| 3.8184 | 2.8190 | 950 | 3.7591 |
|
| 75 |
+
| 4.0853 | 2.9674 | 1000 | 3.7591 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- PEFT 0.18.0
|
| 81 |
+
- Transformers 4.57.3
|
| 82 |
+
- Pytorch 2.9.0+cpu
|
| 83 |
+
- Datasets 4.0.0
|
| 84 |
+
- 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 1321024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1660eed46ba6f0d3fa1ec0731090d018b236a179f4718f8ff7102f222b325f96
|
| 3 |
size 1321024
|