Commit
•
59d3e97
1
Parent(s):
5a19bd9
Model save
Browse files- README.md +81 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- llama-factory
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Llama2_AAID_new_mixed_train_final
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# Llama2_AAID_new_mixed_train_final
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5159
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0003
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 256
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 3.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 52 |
+
| 1.2211 | 0.0109 | 10 | 0.5508 |
|
| 53 |
+
| 0.446 | 0.0219 | 20 | 0.5180 |
|
| 54 |
+
| 0.3889 | 0.0328 | 30 | 0.5139 |
|
| 55 |
+
| 0.3757 | 0.0438 | 40 | 0.5758 |
|
| 56 |
+
| 0.3551 | 0.0547 | 50 | 0.5461 |
|
| 57 |
+
| 0.3351 | 0.0656 | 60 | 0.5407 |
|
| 58 |
+
| 0.3269 | 0.0766 | 70 | 0.5335 |
|
| 59 |
+
| 0.3231 | 0.0875 | 80 | 0.5121 |
|
| 60 |
+
| 0.3324 | 0.0984 | 90 | 0.5196 |
|
| 61 |
+
| 0.3039 | 0.1094 | 100 | 0.5252 |
|
| 62 |
+
| 0.3083 | 0.1203 | 110 | 0.5070 |
|
| 63 |
+
| 0.3034 | 0.1313 | 120 | 0.5375 |
|
| 64 |
+
| 0.3061 | 0.1422 | 130 | 0.5346 |
|
| 65 |
+
| 0.3021 | 0.1531 | 140 | 0.5112 |
|
| 66 |
+
| 0.3067 | 0.1641 | 150 | 0.5191 |
|
| 67 |
+
| 0.2958 | 0.1750 | 160 | 0.5278 |
|
| 68 |
+
| 0.3002 | 0.1859 | 170 | 0.5170 |
|
| 69 |
+
| 0.2896 | 0.1969 | 180 | 0.5086 |
|
| 70 |
+
| 0.2989 | 0.2078 | 190 | 0.5300 |
|
| 71 |
+
| 0.3012 | 0.2188 | 200 | 0.5137 |
|
| 72 |
+
| 0.2802 | 0.2297 | 210 | 0.5159 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- PEFT 0.11.1
|
| 78 |
+
- Transformers 4.41.1
|
| 79 |
+
- Pytorch 2.3.0+cu121
|
| 80 |
+
- Datasets 2.19.1
|
| 81 |
+
- 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 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a14e9a463325a9547a31eb29849b5e80920306038c758b842427ae0d54e53281
|
| 3 |
size 80013120
|