End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: phi3.5-mini-adapter_v2
|
| 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 |
+
# phi3.5-mini-adapter_v2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1344
|
| 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: 1e-05
|
| 39 |
+
- train_batch_size: 24
|
| 40 |
+
- eval_batch_size: 24
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 48
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 47 |
+
- num_epochs: 50
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 17.6422 | 0.4545 | 10 | 17.2166 |
|
| 54 |
+
| 13.0308 | 0.9091 | 20 | 12.5267 |
|
| 55 |
+
| 8.4662 | 1.3636 | 30 | 7.9483 |
|
| 56 |
+
| 2.4521 | 1.8182 | 40 | 1.3982 |
|
| 57 |
+
| 0.3917 | 2.2727 | 50 | 0.3427 |
|
| 58 |
+
| 0.3042 | 2.7273 | 60 | 0.3092 |
|
| 59 |
+
| 0.2051 | 3.1818 | 70 | 0.2451 |
|
| 60 |
+
| 0.2043 | 3.6364 | 80 | 0.2022 |
|
| 61 |
+
| 0.1599 | 4.0909 | 90 | 0.1907 |
|
| 62 |
+
| 0.1658 | 4.5455 | 100 | 0.1727 |
|
| 63 |
+
| 0.1527 | 5.0 | 110 | 0.1595 |
|
| 64 |
+
| 0.1281 | 5.4545 | 120 | 0.1501 |
|
| 65 |
+
| 0.1079 | 5.9091 | 130 | 0.1435 |
|
| 66 |
+
| 0.0896 | 6.3636 | 140 | 0.1369 |
|
| 67 |
+
| 0.097 | 6.8182 | 150 | 0.1340 |
|
| 68 |
+
| 0.0841 | 7.2727 | 160 | 0.1449 |
|
| 69 |
+
| 0.0771 | 7.7273 | 170 | 0.1344 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.11.1
|
| 75 |
+
- Transformers 4.43.1
|
| 76 |
+
- Pytorch 2.4.0+cu121
|
| 77 |
+
- Datasets 2.19.1
|
| 78 |
+
- 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 1610648152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf6e78eaccbff325e8e4df91a41977e7fc8dda124dbce87d907dce648a84dc6
|
| 3 |
size 1610648152
|
runs/Aug22_19-04-22_B650E/events.out.tfevents.1724367868.B650E.2966.0
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 sha256:68310794cdeb5e09449e70b4dabe5591812cc77a5990b161d9372f0d456e2b49
|
| 3 |
+
size 48668
|