Model save
Browse files- README.md +75 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: tinyllama_ft_full_5k_sample
|
| 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 |
+
# tinyllama_ft_full_5k_sample
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.8222
|
| 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: 0.0001
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 64
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.05
|
| 50 |
+
- num_epochs: 3
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 1.9059 | 0.256 | 20 | 1.8654 |
|
| 57 |
+
| 1.8532 | 0.512 | 40 | 1.8407 |
|
| 58 |
+
| 1.8333 | 0.768 | 60 | 1.8315 |
|
| 59 |
+
| 1.8178 | 1.0128 | 80 | 1.8279 |
|
| 60 |
+
| 1.8366 | 1.2688 | 100 | 1.8257 |
|
| 61 |
+
| 1.8249 | 1.5248 | 120 | 1.8241 |
|
| 62 |
+
| 1.7824 | 1.7808 | 140 | 1.8230 |
|
| 63 |
+
| 1.8051 | 2.0256 | 160 | 1.8222 |
|
| 64 |
+
| 1.7722 | 2.2816 | 180 | 1.8225 |
|
| 65 |
+
| 1.7967 | 2.5376 | 200 | 1.8223 |
|
| 66 |
+
| 1.7583 | 2.7936 | 220 | 1.8222 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.17.1
|
| 72 |
+
- Transformers 4.55.4
|
| 73 |
+
- Pytorch 2.8.0+cu126
|
| 74 |
+
- Datasets 4.0.0
|
| 75 |
+
- Tokenizers 0.21.4
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50503544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7bf0bd2de2d3ee8655906e9c50f29558d8eaad4149444f51093175a06cc2cea
|
| 3 |
size 50503544
|