Model save
Browse files- README.md +87 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/phi-2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: phi2-mentalchat16k
|
| 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 |
+
# phi2-mentalchat16k
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7296
|
| 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: 0.0002
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
+
- num_epochs: 4
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.8915 | 0.1496 | 100 | 0.8518 |
|
| 55 |
+
| 0.8464 | 0.2992 | 200 | 0.8102 |
|
| 56 |
+
| 0.7874 | 0.4488 | 300 | 0.7927 |
|
| 57 |
+
| 0.7999 | 0.5984 | 400 | 0.7814 |
|
| 58 |
+
| 0.7901 | 0.7479 | 500 | 0.7731 |
|
| 59 |
+
| 0.7801 | 0.8975 | 600 | 0.7647 |
|
| 60 |
+
| 0.7585 | 1.0471 | 700 | 0.7639 |
|
| 61 |
+
| 0.7592 | 1.1967 | 800 | 0.7576 |
|
| 62 |
+
| 0.7431 | 1.3463 | 900 | 0.7542 |
|
| 63 |
+
| 0.7555 | 1.4959 | 1000 | 0.7501 |
|
| 64 |
+
| 0.7354 | 1.6455 | 1100 | 0.7456 |
|
| 65 |
+
| 0.7281 | 1.7951 | 1200 | 0.7422 |
|
| 66 |
+
| 0.7312 | 1.9447 | 1300 | 0.7395 |
|
| 67 |
+
| 0.6984 | 2.0942 | 1400 | 0.7389 |
|
| 68 |
+
| 0.7037 | 2.2438 | 1500 | 0.7382 |
|
| 69 |
+
| 0.6913 | 2.3934 | 1600 | 0.7357 |
|
| 70 |
+
| 0.7229 | 2.5430 | 1700 | 0.7341 |
|
| 71 |
+
| 0.7095 | 2.6926 | 1800 | 0.7326 |
|
| 72 |
+
| 0.6994 | 2.8422 | 1900 | 0.7319 |
|
| 73 |
+
| 0.6995 | 2.9918 | 2000 | 0.7298 |
|
| 74 |
+
| 0.6887 | 3.1414 | 2100 | 0.7314 |
|
| 75 |
+
| 0.6712 | 3.2909 | 2200 | 0.7308 |
|
| 76 |
+
| 0.6867 | 3.4405 | 2300 | 0.7300 |
|
| 77 |
+
| 0.6817 | 3.5901 | 2400 | 0.7299 |
|
| 78 |
+
| 0.681 | 3.7397 | 2500 | 0.7296 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- PEFT 0.13.2
|
| 84 |
+
- Transformers 4.46.3
|
| 85 |
+
- Pytorch 2.4.1+cu118
|
| 86 |
+
- Datasets 3.1.0
|
| 87 |
+
- Tokenizers 0.20.3
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41977360
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d80833c27cee255799a3bfbda672d7114700cf2a4ca494036a68c03d65f71a
|
| 3 |
size 41977360
|