staturecrane commited on
Commit
c76ffb5
1 Parent(s): f6db1d2

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -12,9 +12,9 @@ probably proofread and complete it, then remove this comment. -->
12
 
13
  # staturecrane/news_kg_model
14
 
15
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 4.2731
18
  - Epoch: 0
19
 
20
  ## Model description
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Epoch |
43
  |:----------:|:-----:|
44
- | 4.2731 | 0 |
45
 
46
 
47
  ### Framework versions
 
12
 
13
  # staturecrane/news_kg_model
14
 
15
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 3.0111
18
  - Epoch: 0
19
 
20
  ## Model description
 
41
 
42
  | Train Loss | Epoch |
43
  |:----------:|:-----:|
44
+ | 3.0111 | 0 |
45
 
46
 
47
  ### Framework versions
config.json CHANGED
@@ -1,59 +1,45 @@
1
  {
2
- "_name_or_path": "t5-small",
 
 
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
- "d_kv": 64,
8
- "d_model": 512,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "relu",
11
- "dropout_rate": 0.1,
12
- "eos_token_id": 1,
13
- "feed_forward_proj": "relu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": false,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "n_positions": 512,
20
- "num_decoder_layers": 6,
21
- "num_heads": 8,
22
- "num_layers": 6,
23
- "output_past": true,
24
- "pad_token_id": 0,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
 
 
 
 
 
 
 
27
  "task_specific_params": {
28
- "summarization": {
29
- "early_stopping": true,
30
- "length_penalty": 2.0,
31
- "max_length": 200,
32
- "min_length": 30,
33
- "no_repeat_ngram_size": 3,
34
- "num_beams": 4,
35
- "prefix": "summarize: "
36
- },
37
- "translation_en_to_de": {
38
- "early_stopping": true,
39
- "max_length": 300,
40
- "num_beams": 4,
41
- "prefix": "translate English to German: "
42
- },
43
- "translation_en_to_fr": {
44
- "early_stopping": true,
45
- "max_length": 300,
46
- "num_beams": 4,
47
- "prefix": "translate English to French: "
48
- },
49
- "translation_en_to_ro": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to Romanian: "
54
  }
55
  },
56
  "transformers_version": "4.27.4",
57
  "use_cache": true,
58
- "vocab_size": 32128
59
  }
 
1
  {
2
+ "_name_or_path": "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
  "transformers_version": "4.27.4",
43
  "use_cache": true,
44
+ "vocab_size": 50257
45
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
  "transformers_version": "4.27.4"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
 
5
  "transformers_version": "4.27.4"
6
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,107 +1,6 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
107
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:809368e838878a325b4c39982f3c3dc94c6ab5776e02e024a44a8b8ea01cc189
3
- size 373902664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466389859c65b171a10544ba76fd001a161de4b72d0e5e238e4bdc281b74ef39
3
+ size 327745472
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,111 +1,9 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
- "eos_token": "</s>",
105
- "extra_ids": 100,
106
- "model_max_length": 512,
107
- "pad_token": "<pad>",
108
  "special_tokens_map_file": null,
109
- "tokenizer_class": "T5Tokenizer",
110
- "unk_token": "<unk>"
111
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "special_tokens_map_file": null,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff