Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: phi4-lora-xaji0y6d-1742330134
|
| 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 |
+
# phi4-lora-xaji0y6d-1742330134
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0010
|
| 20 |
+
- Perplexity: 2.7209
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-06
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 48 |
+
- num_epochs: 50
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------:|
|
| 55 |
+
| 5.6626 | 1.48 | 10 | 5.8212 | 337.3485 |
|
| 56 |
+
| 5.4363 | 2.96 | 20 | 5.4409 | 230.6381 |
|
| 57 |
+
| 5.2185 | 4.32 | 30 | 5.2027 | 181.7434 |
|
| 58 |
+
| 4.9729 | 5.8 | 40 | 4.9270 | 137.9507 |
|
| 59 |
+
| 4.68 | 7.16 | 50 | 4.6071 | 100.1871 |
|
| 60 |
+
| 4.3242 | 8.64 | 60 | 4.2787 | 72.1430 |
|
| 61 |
+
| 4.0147 | 10.0 | 70 | 3.9536 | 52.1171 |
|
| 62 |
+
| 3.7066 | 11.48 | 80 | 3.6597 | 38.8469 |
|
| 63 |
+
| 3.3654 | 12.96 | 90 | 3.3835 | 29.4712 |
|
| 64 |
+
| 3.1883 | 14.32 | 100 | 3.1183 | 22.6075 |
|
| 65 |
+
| 2.8444 | 15.8 | 110 | 2.8578 | 17.4224 |
|
| 66 |
+
| 2.6168 | 17.16 | 120 | 2.6088 | 13.5819 |
|
| 67 |
+
| 2.3689 | 18.64 | 130 | 2.3749 | 10.7493 |
|
| 68 |
+
| 2.1379 | 20.0 | 140 | 2.1532 | 8.6119 |
|
| 69 |
+
| 1.8909 | 21.48 | 150 | 1.9458 | 6.9986 |
|
| 70 |
+
| 1.7022 | 22.96 | 160 | 1.7602 | 5.8135 |
|
| 71 |
+
| 1.5127 | 24.32 | 170 | 1.6061 | 4.9831 |
|
| 72 |
+
| 1.3942 | 25.8 | 180 | 1.4847 | 4.4133 |
|
| 73 |
+
| 1.3053 | 27.16 | 190 | 1.3923 | 4.0240 |
|
| 74 |
+
| 1.2177 | 28.64 | 200 | 1.3193 | 3.7405 |
|
| 75 |
+
| 1.1161 | 30.0 | 210 | 1.2557 | 3.5101 |
|
| 76 |
+
| 1.1293 | 31.48 | 220 | 1.2023 | 3.3275 |
|
| 77 |
+
| 1.0622 | 32.96 | 230 | 1.1562 | 3.1778 |
|
| 78 |
+
| 1.015 | 34.32 | 240 | 1.1164 | 3.0536 |
|
| 79 |
+
| 0.9539 | 35.8 | 250 | 1.0830 | 2.9533 |
|
| 80 |
+
| 0.9387 | 37.16 | 260 | 1.0552 | 2.8725 |
|
| 81 |
+
| 0.8819 | 38.64 | 270 | 1.0340 | 2.8121 |
|
| 82 |
+
| 0.9162 | 40.0 | 280 | 1.0178 | 2.7670 |
|
| 83 |
+
| 0.8912 | 41.48 | 290 | 1.0074 | 2.7384 |
|
| 84 |
+
| 0.8641 | 42.96 | 300 | 1.0010 | 2.7209 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- PEFT 0.14.0
|
| 90 |
+
- Transformers 4.48.2
|
| 91 |
+
- Pytorch 2.1.0+cu118
|
| 92 |
+
- Datasets 3.4.1
|
| 93 |
+
- Tokenizers 0.21.1
|