Commit
•
702ad5a
1
Parent(s):
9b1f717
End of training
Browse files- README.md +96 -0
- config.json +41 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wiki_qa
|
8 |
+
model-index:
|
9 |
+
- name: output
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# output
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wiki_qa dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8781
|
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-05
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 0.9106 | 0.08 | 200 | 0.7699 |
|
52 |
+
| 0.9505 | 0.16 | 400 | 0.6965 |
|
53 |
+
| 0.8446 | 0.24 | 600 | 0.7000 |
|
54 |
+
| 0.8765 | 0.31 | 800 | 0.6573 |
|
55 |
+
| 0.7792 | 0.39 | 1000 | 0.7359 |
|
56 |
+
| 0.9293 | 0.47 | 1200 | 0.6926 |
|
57 |
+
| 0.9715 | 0.55 | 1400 | 0.7032 |
|
58 |
+
| 0.8898 | 0.63 | 1600 | 0.7208 |
|
59 |
+
| 1.0288 | 0.71 | 1800 | 0.6954 |
|
60 |
+
| 0.7782 | 0.79 | 2000 | 0.6629 |
|
61 |
+
| 0.9419 | 0.86 | 2200 | 0.7061 |
|
62 |
+
| 0.7138 | 0.94 | 2400 | 0.7086 |
|
63 |
+
| 0.9334 | 1.02 | 2600 | 0.6752 |
|
64 |
+
| 0.9274 | 1.1 | 2800 | 0.7142 |
|
65 |
+
| 0.7217 | 1.18 | 3000 | 0.7227 |
|
66 |
+
| 0.74 | 1.26 | 3200 | 0.6896 |
|
67 |
+
| 0.9408 | 1.34 | 3400 | 0.7039 |
|
68 |
+
| 0.8503 | 1.41 | 3600 | 0.7456 |
|
69 |
+
| 0.8816 | 1.49 | 3800 | 0.7226 |
|
70 |
+
| 0.7751 | 1.57 | 4000 | 0.7182 |
|
71 |
+
| 0.8669 | 1.65 | 4200 | 0.6904 |
|
72 |
+
| 1.059 | 1.73 | 4400 | 0.7131 |
|
73 |
+
| 0.8442 | 1.81 | 4600 | 0.7063 |
|
74 |
+
| 0.9162 | 1.89 | 4800 | 0.7128 |
|
75 |
+
| 0.9022 | 1.96 | 5000 | 0.7249 |
|
76 |
+
| 0.9427 | 2.04 | 5200 | 0.7333 |
|
77 |
+
| 0.9122 | 2.12 | 5400 | 0.6852 |
|
78 |
+
| 0.8159 | 2.2 | 5600 | 0.6950 |
|
79 |
+
| 0.9489 | 2.28 | 5800 | 0.7137 |
|
80 |
+
| 0.9976 | 2.36 | 6000 | 0.7101 |
|
81 |
+
| 0.9305 | 2.44 | 6200 | 0.7059 |
|
82 |
+
| 0.6405 | 2.51 | 6400 | 0.7167 |
|
83 |
+
| 0.9515 | 2.59 | 6600 | 0.6875 |
|
84 |
+
| 0.7186 | 2.67 | 6800 | 0.7057 |
|
85 |
+
| 0.9221 | 2.75 | 7000 | 0.6805 |
|
86 |
+
| 0.9118 | 2.83 | 7200 | 0.7011 |
|
87 |
+
| 0.9784 | 2.91 | 7400 | 0.6936 |
|
88 |
+
| 0.7532 | 2.99 | 7600 | 0.7046 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.33.0
|
94 |
+
- Pytorch 2.0.0
|
95 |
+
- Datasets 2.1.0
|
96 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"pad_token_id": 50256,
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"summary_activation": null,
|
27 |
+
"summary_first_dropout": 0.1,
|
28 |
+
"summary_proj_to_labels": true,
|
29 |
+
"summary_type": "cls_index",
|
30 |
+
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.33.0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:556f3cab88bcd39443c90b0b8739bd4ad73a5b4a383033b67955bcdbd94f915c
|
3 |
+
size 497813601
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a270fa050aa90a6630310474e7a40ed15c0833e249a0b3676a74c014f5fef34f
|
3 |
+
size 4027
|