thymiantheherb
commited on
Commit
•
44fcc4b
1
Parent(s):
216e91b
End of training
Browse files- README.md +81 -59
- config.json +46 -46
- generation_config.json +6 -6
- model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,59 +1,81 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: distilbert/distilgpt2
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
|
7 |
-
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
-
|
38 |
-
-
|
39 |
-
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
-
|
59 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert/distilgpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- eli5_category
|
8 |
+
metrics:
|
9 |
+
- bleu
|
10 |
+
model-index:
|
11 |
+
- name: distilgpt2-finetuned
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Causal Language Modeling
|
15 |
+
type: text-generation
|
16 |
+
dataset:
|
17 |
+
name: eli5_category
|
18 |
+
type: eli5_category
|
19 |
+
config: default
|
20 |
+
split: None
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Bleu
|
24 |
+
type: bleu
|
25 |
+
value: 0.010587533155110318
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# distilgpt2-finetuned
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 3.7703
|
36 |
+
- Bleu: 0.0106
|
37 |
+
- Bertscore Precision: 0.1609
|
38 |
+
- Bertscore Recall: 0.1758
|
39 |
+
- Bertscore F1: 0.1677
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 2e-05
|
59 |
+
- train_batch_size: 8
|
60 |
+
- eval_batch_size: 8
|
61 |
+
- seed: 42
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- num_epochs: 3.0
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------------------:|:----------------:|:------------:|
|
71 |
+
| 3.8816 | 1.0 | 4000 | 3.7775 | 0.0107 | 0.1607 | 0.1756 | 0.1675 |
|
72 |
+
| 3.7273 | 2.0 | 8000 | 3.7660 | 0.0107 | 0.1608 | 0.1757 | 0.1676 |
|
73 |
+
| 3.6125 | 3.0 | 12000 | 3.7703 | 0.0106 | 0.1609 | 0.1758 | 0.1677 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.40.2
|
79 |
+
- Pytorch 2.3.0+cu121
|
80 |
+
- Datasets 2.19.1
|
81 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,46 +1,46 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert/distilgpt2",
|
3 |
-
"_num_labels": 1,
|
4 |
-
"activation_function": "gelu_new",
|
5 |
-
"architectures": [
|
6 |
-
"GPT2LMHeadModel"
|
7 |
-
],
|
8 |
-
"attn_pdrop": 0.1,
|
9 |
-
"bos_token_id": 50256,
|
10 |
-
"embd_pdrop": 0.1,
|
11 |
-
"eos_token_id": 50256,
|
12 |
-
"id2label": {
|
13 |
-
"0": "LABEL_0"
|
14 |
-
},
|
15 |
-
"initializer_range": 0.02,
|
16 |
-
"label2id": {
|
17 |
-
"LABEL_0": 0
|
18 |
-
},
|
19 |
-
"layer_norm_epsilon": 1e-05,
|
20 |
-
"model_type": "gpt2",
|
21 |
-
"n_ctx": 1024,
|
22 |
-
"n_embd": 768,
|
23 |
-
"n_head": 12,
|
24 |
-
"n_inner": null,
|
25 |
-
"n_layer": 6,
|
26 |
-
"n_positions": 1024,
|
27 |
-
"reorder_and_upcast_attn": false,
|
28 |
-
"resid_pdrop": 0.1,
|
29 |
-
"scale_attn_by_inverse_layer_idx": false,
|
30 |
-
"scale_attn_weights": true,
|
31 |
-
"summary_activation": null,
|
32 |
-
"summary_first_dropout": 0.1,
|
33 |
-
"summary_proj_to_labels": true,
|
34 |
-
"summary_type": "cls_index",
|
35 |
-
"summary_use_proj": true,
|
36 |
-
"task_specific_params": {
|
37 |
-
"text-generation": {
|
38 |
-
"do_sample": true,
|
39 |
-
"max_length": 50
|
40 |
-
}
|
41 |
-
},
|
42 |
-
"torch_dtype": "float32",
|
43 |
-
"transformers_version": "4.
|
44 |
-
"use_cache": true,
|
45 |
-
"vocab_size": 50257
|
46 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.40.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 50256,
|
4 |
-
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.
|
6 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.40.2"
|
6 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327657928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41d6a81d2957121e25266b5deefdd4d465e947761e64aec5d04f68c22f7a9651
|
3 |
size 327657928
|
training_args.bin
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:cc320c476cfad9c910c6c99a784234e4e5e9b59b1cd6298c0267335ab023f2d3
|
3 |
+
size 5048
|