End of training
Browse files
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: EleutherAI/gpt-neo-125m
|
3 |
+
library_name: peft
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: gpt-neoMedChatbot
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# gpt-neoMedChatbot
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.4059
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant
|
46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
47 |
+
- num_epochs: 3
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 3.1874 | 0.0709 | 100 | 3.0118 |
|
54 |
+
| 2.8756 | 0.1417 | 200 | 2.8228 |
|
55 |
+
| 2.7134 | 0.2126 | 300 | 2.7358 |
|
56 |
+
| 2.6948 | 0.2835 | 400 | 2.6833 |
|
57 |
+
| 2.6386 | 0.3544 | 500 | 2.6441 |
|
58 |
+
| 2.6525 | 0.4252 | 600 | 2.6150 |
|
59 |
+
| 2.6242 | 0.4961 | 700 | 2.5856 |
|
60 |
+
| 2.6444 | 0.5670 | 800 | 2.5701 |
|
61 |
+
| 2.6007 | 0.6378 | 900 | 2.5540 |
|
62 |
+
| 2.462 | 0.7087 | 1000 | 2.5418 |
|
63 |
+
| 2.5641 | 0.7796 | 1100 | 2.5315 |
|
64 |
+
| 2.4672 | 0.8505 | 1200 | 2.5238 |
|
65 |
+
| 2.5017 | 0.9213 | 1300 | 2.5146 |
|
66 |
+
| 2.6389 | 0.9922 | 1400 | 2.5083 |
|
67 |
+
| 2.4869 | 1.0631 | 1500 | 2.5021 |
|
68 |
+
| 2.5302 | 1.1339 | 1600 | 2.4942 |
|
69 |
+
| 2.497 | 1.2048 | 1700 | 2.4886 |
|
70 |
+
| 2.4965 | 1.2757 | 1800 | 2.4846 |
|
71 |
+
| 2.5535 | 1.3466 | 1900 | 2.4783 |
|
72 |
+
| 2.5747 | 1.4174 | 2000 | 2.4732 |
|
73 |
+
| 2.4534 | 1.4883 | 2100 | 2.4679 |
|
74 |
+
| 2.4909 | 1.5592 | 2200 | 2.4657 |
|
75 |
+
| 2.5192 | 1.6300 | 2300 | 2.4617 |
|
76 |
+
| 2.4271 | 1.7009 | 2400 | 2.4573 |
|
77 |
+
| 2.4855 | 1.7718 | 2500 | 2.4542 |
|
78 |
+
| 2.4599 | 1.8427 | 2600 | 2.4530 |
|
79 |
+
| 2.4482 | 1.9135 | 2700 | 2.4444 |
|
80 |
+
| 2.493 | 1.9844 | 2800 | 2.4446 |
|
81 |
+
| 2.3527 | 2.0553 | 2900 | 2.4414 |
|
82 |
+
| 2.5243 | 2.1262 | 3000 | 2.4376 |
|
83 |
+
| 2.4644 | 2.1970 | 3100 | 2.4330 |
|
84 |
+
| 2.386 | 2.2679 | 3200 | 2.4308 |
|
85 |
+
| 2.3762 | 2.3388 | 3300 | 2.4281 |
|
86 |
+
| 2.3827 | 2.4096 | 3400 | 2.4245 |
|
87 |
+
| 2.3487 | 2.4805 | 3500 | 2.4221 |
|
88 |
+
| 2.4737 | 2.5514 | 3600 | 2.4192 |
|
89 |
+
| 2.4907 | 2.6223 | 3700 | 2.4171 |
|
90 |
+
| 2.3967 | 2.6931 | 3800 | 2.4159 |
|
91 |
+
| 2.4772 | 2.7640 | 3900 | 2.4146 |
|
92 |
+
| 2.4114 | 2.8349 | 4000 | 2.4106 |
|
93 |
+
| 2.4017 | 2.9057 | 4100 | 2.4065 |
|
94 |
+
| 2.3477 | 2.9766 | 4200 | 2.4059 |
|
95 |
+
|
96 |
+
|
97 |
+
### Framework versions
|
98 |
+
|
99 |
+
- PEFT 0.12.0
|
100 |
+
- Transformers 4.42.4
|
101 |
+
- Pytorch 2.3.1+cu121
|
102 |
+
- Datasets 2.21.0
|
103 |
+
- Tokenizers 0.19.1
|