wen1126 commited on
Commit
2e69dba
1 Parent(s): a090632

End of training

Browse files
README.md CHANGED
@@ -1,8 +1,9 @@
1
  ---
2
- license: apache-2.0
3
- base_model: distilroberta-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: github_cybersecurity_READMEs
8
  results: []
@@ -13,9 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # github_cybersecurity_READMEs
15
 
16
- This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.9244
 
19
 
20
  ## Model description
21
 
@@ -44,11 +46,11 @@ The following hyperparameters were used during training:
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 125 | 2.0094 |
50
- | No log | 2.0 | 250 | 1.9825 |
51
- | No log | 3.0 | 375 | 1.9307 |
52
 
53
 
54
  ### Framework versions
 
1
  ---
2
+ base_model: geralt/MechDistilGPT2
 
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
  model-index:
8
  - name: github_cybersecurity_READMEs
9
  results: []
 
14
 
15
  # github_cybersecurity_READMEs
16
 
17
+ This model is a fine-tuned version of [geralt/MechDistilGPT2](https://huggingface.co/geralt/MechDistilGPT2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 9.7201
20
+ - Accuracy: 0.0193
21
 
22
  ## Model description
23
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 13 | 10.5158 | 0.0045 |
52
+ | No log | 2.0 | 26 | 9.9496 | 0.0123 |
53
+ | No log | 3.0 | 39 | 9.7201 | 0.0193 |
54
 
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,27 +1,47 @@
1
  {
2
- "_name_or_path": "distilroberta-base",
 
 
3
  "architectures": [
4
- "RobertaForMaskedLM"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "roberta",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 6,
20
- "pad_token_id": 1,
21
- "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.40.0.dev0",
24
- "type_vocab_size": 1,
25
  "use_cache": true,
26
- "vocab_size": 50265
27
  }
 
1
  {
2
+ "_name_or_path": "geralt/MechDistilGPT2",
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
+ "gradient_checkpointing": false,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
  "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 6,
27
+ "n_positions": 1024,
28
+ "reorder_and_upcast_attn": false,
29
+ "resid_pdrop": 0.1,
30
+ "scale_attn_by_inverse_layer_idx": false,
31
+ "scale_attn_weights": true,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "task_specific_params": {
38
+ "text-generation": {
39
+ "do_sample": true,
40
+ "max_length": 50
41
+ }
42
+ },
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.40.0.dev0",
 
45
  "use_cache": true,
46
+ "vocab_size": 50257
47
  }
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": "4.40.0.dev0"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e80beda022203385774264b57bab5b093c0c448aefd59e04ad123828e5e944b
3
- size 328693404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c70592eb397d53edc37e1022ce1d35d5f45ae527a9927b54c8da13099f8ea2
3
+ size 327657928
runs/Apr16_17-53-09_wen/events.out.tfevents.1713261192.wen.553.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40885470503a666524e8d524399aadd248082277efa7f75520789a1535c6b83
3
+ size 6419
runs/Apr16_17-53-09_wen/events.out.tfevents.1713269383.wen.553.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca32c73b9fd24e6d815ab66f63d0fc40ad112823d0fea89fae1ff496fd2c706
3
+ size 11451
runs/Apr16_20-37-25_wen/events.out.tfevents.1713271061.wen.553.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745be82cb5055bdc6f44c02367f830a0da6d1c8ce4952fd2ca40d35f97e99bde
3
+ size 7053
runs/Apr16_20-47-54_wen/events.out.tfevents.1713271689.wen.553.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed05e3d88fca7ae222d103357399039510b493e6cc8680a82695f96c35bc3909
3
+ size 6419
runs/Apr16_20-47-54_wen/events.out.tfevents.1713272059.wen.553.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16291ed11cc3a8e88f186619e7eab2c0597cb6c3befb37a49a02240b9a841d2
3
+ size 405
runs/Apr16_20-57-59_wen/events.out.tfevents.1713272282.wen.553.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a84a0eaa13e74de243787d9685b9fd4b66db29d144ff7e2a2262c0d99b876b
3
+ size 6422
runs/Apr16_20-57-59_wen/events.out.tfevents.1713273203.wen.553.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eac4e04088ca063275e28f2b6031b3c3345348dfc5518144cbb7caa67b15ac9
3
+ size 405
runs/Apr16_21-41-40_wen/events.out.tfevents.1713274908.wen.553.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffec03283f7a3b86457aabc2026d00e2db91c04b76470652668f0e2a148f43d4
3
+ size 6419
runs/Apr16_21-41-40_wen/events.out.tfevents.1713275076.wen.553.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7826b467d4733e7d83bab1a3dfc1140b36549538bf4ec0b5d047324749b05edd
3
+ size 405
runs/Apr17_14-33-26_wen/events.out.tfevents.1713335607.wen.565.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89fbb3b0739b02ccbeaf9f3718527a1259b965a4a78c8af9e8248717f09faf0a
3
+ size 6419
runs/Apr17_14-33-26_wen/events.out.tfevents.1713335793.wen.565.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011cd6cffa6e64864a49280d12e90fe3c6b00eb2db674dc9dfe1f7bbd00676c6
3
+ size 405
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55e3f2e4c72d52143e55d22b9f765cfcfd8f22102a7fd5ae9b252d33dc44e0c2
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1063b382d4da87445d1e8e4eeafbda112b39aa8e56f2c0dee6afc5c3f5258605
3
  size 4984