samhitmantrala
commited on
Commit
•
0631ff5
1
Parent(s):
e2c9b20
End of training
Browse files- README.md +106 -0
- config.json +46 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Mar30_07-50-36_3318b9903d1b/events.out.tfevents.1711785037.3318b9903d1b.864.0 +3 -0
- runs/Mar30_07-51-05_3318b9903d1b/events.out.tfevents.1711785066.3318b9903d1b.864.1 +3 -0
- runs/Mar30_07-51-05_3318b9903d1b/events.out.tfevents.1711785228.3318b9903d1b.864.2 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert/distilgpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: asas
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# asas
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.9407
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 32
|
39 |
+
- eval_batch_size: 32
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 50
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 1 | 3.6268 |
|
50 |
+
| No log | 2.0 | 2 | 3.5162 |
|
51 |
+
| No log | 3.0 | 3 | 3.4110 |
|
52 |
+
| No log | 4.0 | 4 | 3.3132 |
|
53 |
+
| No log | 5.0 | 5 | 3.2226 |
|
54 |
+
| No log | 6.0 | 6 | 3.1384 |
|
55 |
+
| No log | 7.0 | 7 | 3.0606 |
|
56 |
+
| No log | 8.0 | 8 | 2.9873 |
|
57 |
+
| No log | 9.0 | 9 | 2.9196 |
|
58 |
+
| No log | 10.0 | 10 | 2.8566 |
|
59 |
+
| No log | 11.0 | 11 | 2.7985 |
|
60 |
+
| No log | 12.0 | 12 | 2.7445 |
|
61 |
+
| No log | 13.0 | 13 | 2.6941 |
|
62 |
+
| No log | 14.0 | 14 | 2.6469 |
|
63 |
+
| No log | 15.0 | 15 | 2.6030 |
|
64 |
+
| No log | 16.0 | 16 | 2.5614 |
|
65 |
+
| No log | 17.0 | 17 | 2.5217 |
|
66 |
+
| No log | 18.0 | 18 | 2.4843 |
|
67 |
+
| No log | 19.0 | 19 | 2.4492 |
|
68 |
+
| No log | 20.0 | 20 | 2.4161 |
|
69 |
+
| No log | 21.0 | 21 | 2.3847 |
|
70 |
+
| No log | 22.0 | 22 | 2.3547 |
|
71 |
+
| No log | 23.0 | 23 | 2.3258 |
|
72 |
+
| No log | 24.0 | 24 | 2.2982 |
|
73 |
+
| No log | 25.0 | 25 | 2.2719 |
|
74 |
+
| No log | 26.0 | 26 | 2.2469 |
|
75 |
+
| No log | 27.0 | 27 | 2.2232 |
|
76 |
+
| No log | 28.0 | 28 | 2.2009 |
|
77 |
+
| No log | 29.0 | 29 | 2.1795 |
|
78 |
+
| No log | 30.0 | 30 | 2.1590 |
|
79 |
+
| No log | 31.0 | 31 | 2.1393 |
|
80 |
+
| No log | 32.0 | 32 | 2.1209 |
|
81 |
+
| No log | 33.0 | 33 | 2.1035 |
|
82 |
+
| No log | 34.0 | 34 | 2.0871 |
|
83 |
+
| No log | 35.0 | 35 | 2.0715 |
|
84 |
+
| No log | 36.0 | 36 | 2.0564 |
|
85 |
+
| No log | 37.0 | 37 | 2.0424 |
|
86 |
+
| No log | 38.0 | 38 | 2.0289 |
|
87 |
+
| No log | 39.0 | 39 | 2.0161 |
|
88 |
+
| No log | 40.0 | 40 | 2.0037 |
|
89 |
+
| No log | 41.0 | 41 | 1.9929 |
|
90 |
+
| No log | 42.0 | 42 | 1.9830 |
|
91 |
+
| No log | 43.0 | 43 | 1.9741 |
|
92 |
+
| No log | 44.0 | 44 | 1.9660 |
|
93 |
+
| No log | 45.0 | 45 | 1.9589 |
|
94 |
+
| No log | 46.0 | 46 | 1.9529 |
|
95 |
+
| No log | 47.0 | 47 | 1.9480 |
|
96 |
+
| No log | 48.0 | 48 | 1.9443 |
|
97 |
+
| No log | 49.0 | 49 | 1.9420 |
|
98 |
+
| No log | 50.0 | 50 | 1.9407 |
|
99 |
+
|
100 |
+
|
101 |
+
### Framework versions
|
102 |
+
|
103 |
+
- Transformers 4.38.2
|
104 |
+
- Pytorch 2.2.1+cu121
|
105 |
+
- Datasets 2.18.0
|
106 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +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": "4.38.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bbd9da6a18d639005396eb97dc5195341a135b9a3e30f656803144549f73299
|
3 |
+
size 327657928
|
runs/Mar30_07-50-36_3318b9903d1b/events.out.tfevents.1711785037.3318b9903d1b.864.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b0ce50fe261d7f0360316b45d9bd212b795fbbd0b778b9ccfd93ddf51c5b819
|
3 |
+
size 6207
|
runs/Mar30_07-51-05_3318b9903d1b/events.out.tfevents.1711785066.3318b9903d1b.864.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c03493b620b2526a26c3ce0d04b46d8ae0d3597f7f77c8fbf9c8f1941391335
|
3 |
+
size 18525
|
runs/Mar30_07-51-05_3318b9903d1b/events.out.tfevents.1711785228.3318b9903d1b.864.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:276349eec1b92ed3689db2d31b5d0cd51e37b67e8048da9f1868089429a049d4
|
3 |
+
size 354
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55240b477f61962813ad7a35b1a64ce04bc6c7551eea00757881e223b82dd4cf
|
3 |
+
size 4856
|