Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 7 |
+
model-index:
|
| 8 |
+
- name: phi-3-4k-instruct-domain-sft-1
|
| 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 |
+
# phi-3-4k-instruct-domain-sft-1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.9328
|
| 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: 2e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 128
|
| 43 |
+
- total_train_batch_size: 512
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 2
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.8958 | 0.1445 | 10 | 1.0716 |
|
| 54 |
+
| 1.7839 | 0.2890 | 20 | 1.0458 |
|
| 55 |
+
| 1.7146 | 0.4335 | 30 | 1.0222 |
|
| 56 |
+
| 1.6457 | 0.5780 | 40 | 1.0029 |
|
| 57 |
+
| 1.591 | 0.7225 | 50 | 0.9872 |
|
| 58 |
+
| 1.552 | 0.8670 | 60 | 0.9740 |
|
| 59 |
+
| 1.5115 | 1.0115 | 70 | 0.9631 |
|
| 60 |
+
| 1.4681 | 1.1560 | 80 | 0.9541 |
|
| 61 |
+
| 1.4469 | 1.3005 | 90 | 0.9468 |
|
| 62 |
+
| 1.419 | 1.4450 | 100 | 0.9412 |
|
| 63 |
+
| 1.4033 | 1.5895 | 110 | 0.9371 |
|
| 64 |
+
| 1.3928 | 1.7340 | 120 | 0.9343 |
|
| 65 |
+
| 1.3887 | 1.8785 | 130 | 0.9328 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- PEFT 0.10.0
|
| 71 |
+
- Transformers 4.40.1
|
| 72 |
+
- Pytorch 2.2.2+cu121
|
| 73 |
+
- Datasets 2.19.0
|
| 74 |
+
- 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 431920400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba5cb04f89ec98f61ef11399dba33cbce3cb93a004d1b7cdf6d5909d0f4ad9e7
|
| 3 |
size 431920400
|
runs/Apr26_21-40-36_gpuhpc06/events.out.tfevents.1714135239.gpuhpc06
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0cbe0fb50889b9c1b61025c7d34ca78e10d9875c98994f89bd4976bb2fb92f7
|
| 3 |
+
size 12002
|