thesergiu commited on
Commit
b283602
1 Parent(s): 8813de2

End of training

Browse files
Files changed (5) hide show
  1. README.md +50 -0
  2. config.json +185 -0
  3. generation_config.json +14 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mrm8488/roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: roberta2roberta_daily_cnn_finetuned
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
+ # roberta2roberta_daily_cnn_finetuned
15
+
16
+ This model is a fine-tuned version of [mrm8488/roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization](https://huggingface.co/mrm8488/roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 16
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 1
42
+ - num_epochs: 3.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.37.2
48
+ - Pytorch 1.13.0+cu116
49
+ - Datasets 2.16.1
50
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mrm8488/roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "nyu-mll/roberta-med-small-1M-1",
8
+ "_num_labels": 2,
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "RobertaForMaskedLM"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "gradient_checkpointing": false,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 512,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 2048,
40
+ "is_decoder": true,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 514,
50
+ "min_length": 0,
51
+ "model_type": "roberta",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 8,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 6,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_past": true,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "position_embedding_type": "absolute",
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "type_vocab_size": 1,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 50265
88
+ },
89
+ "decoder_start_token_id": 0,
90
+ "early_stopping": true,
91
+ "encoder": {
92
+ "_name_or_path": "nyu-mll/roberta-med-small-1M-1",
93
+ "_num_labels": 2,
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "RobertaForMaskedLM"
97
+ ],
98
+ "attention_probs_dropout_prob": 0.1,
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": 0,
102
+ "chunk_size_feed_forward": 0,
103
+ "classifier_dropout": null,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": 2,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "gradient_checkpointing": false,
116
+ "hidden_act": "gelu",
117
+ "hidden_dropout_prob": 0.1,
118
+ "hidden_size": 512,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 2048,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "max_position_embeddings": 514,
135
+ "min_length": 0,
136
+ "model_type": "roberta",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 8,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_hidden_layers": 6,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_past": true,
146
+ "output_scores": false,
147
+ "pad_token_id": 1,
148
+ "position_embedding_type": "absolute",
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "type_vocab_size": 1,
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false,
171
+ "use_cache": true,
172
+ "vocab_size": 50265
173
+ },
174
+ "eos_token_id": 2,
175
+ "is_encoder_decoder": true,
176
+ "length_penalty": 2.0,
177
+ "max_length": 142,
178
+ "min_length": 56,
179
+ "model_type": "encoder-decoder",
180
+ "no_repeat_ngram_size": 3,
181
+ "num_beams": 4,
182
+ "torch_dtype": "float32",
183
+ "transformers_version": "4.37.2",
184
+ "vocab_size": 50265
185
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "length_penalty": 2.0,
8
+ "max_length": 142,
9
+ "min_length": 56,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 4,
12
+ "pad_token_id": 1,
13
+ "transformers_version": "4.37.2"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd194b8e49ed0a3b4e1683c0857268a76b2390336f1dc55e296bc2ee131e534d
3
+ size 386897396
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae96da333a89e40d65c835001ca2cd0816746b5c575109d76908722c28136b57
3
+ size 4411