Hugging Face's logo

edumunozsala
/
bertin2bertin_news_highlights

Text2Text Generation
Transformers
PyTorch
Safetensors
encoder-decoder
Inference Endpoints
Model card Files Community
1
edumunozsala commited on
Commit
24ddaab
•
1 Parent(s): a5f7e6d

Training in progress, epoch 1

Browse files
Files changed (22) hide show
  1. .gitignore +1 -0
  2. config.json +175 -0
  3. last-checkpoint/config.json +175 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scaler.pt +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/special_tokens_map.json +1 -0
  11. last-checkpoint/tokenizer.json +0 -0
  12. last-checkpoint/tokenizer_config.json +1 -0
  13. last-checkpoint/trainer_state.json +81 -0
  14. last-checkpoint/training_args.bin +3 -0
  15. last-checkpoint/vocab.json +0 -0
  16. merges.txt +0 -0
  17. pytorch_model.bin +3 -0
  18. special_tokens_map.json +1 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +1 -0
  21. training_args.bin +3 -0
  22. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "RobertaForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 514,
46
+ "min_length": 0,
47
+ "model_type": "roberta",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.12.3",
77
+ "type_vocab_size": 1,
78
+ "use_bfloat16": false,
79
+ "use_cache": true,
80
+ "vocab_size": 50265
81
+ },
82
+ "decoder_start_token_id": 0,
83
+ "early_stopping": true,
84
+ "encoder": {
85
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
86
+ "add_cross_attention": false,
87
+ "architectures": [
88
+ "RobertaForMaskedLM"
89
+ ],
90
+ "attention_probs_dropout_prob": 0.1,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": 0,
93
+ "chunk_size_feed_forward": 0,
94
+ "classifier_dropout": null,
95
+ "cross_attention_hidden_size": null,
96
+ "decoder_start_token_id": null,
97
+ "diversity_penalty": 0.0,
98
+ "do_sample": false,
99
+ "early_stopping": false,
100
+ "encoder_no_repeat_ngram_size": 0,
101
+ "eos_token_id": 2,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "gradient_checkpointing": false,
106
+ "hidden_act": "gelu",
107
+ "hidden_dropout_prob": 0.1,
108
+ "hidden_size": 768,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "is_decoder": false,
116
+ "is_encoder_decoder": false,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "layer_norm_eps": 1e-05,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "max_position_embeddings": 514,
125
+ "min_length": 0,
126
+ "model_type": "roberta",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 12,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 12,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": 1,
137
+ "position_embedding_type": "absolute",
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.12.3",
156
+ "type_vocab_size": 1,
157
+ "use_bfloat16": false,
158
+ "use_cache": true,
159
+ "vocab_size": 50265
160
+ },
161
+ "eos_token_id": 2,
162
+ "is_encoder_decoder": true,
163
+ "length_penalty": 2.0,
164
+ "max_length": 16,
165
+ "min_length": 4,
166
+ "model_type": "encoder-decoder",
167
+ "no_repeat_ngram_size": 1,
168
+ "num_beams": 4,
169
+ "pad_token_id": 1,
170
+ "repetition_penalty": 2.0,
171
+ "tie_encoder_decoder": true,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": null,
174
+ "vocab_size": 50265
175
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "RobertaForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 514,
46
+ "min_length": 0,
47
+ "model_type": "roberta",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.12.3",
77
+ "type_vocab_size": 1,
78
+ "use_bfloat16": false,
79
+ "use_cache": true,
80
+ "vocab_size": 50265
81
+ },
82
+ "decoder_start_token_id": 0,
83
+ "early_stopping": true,
84
+ "encoder": {
85
+ "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
86
+ "add_cross_attention": false,
87
+ "architectures": [
88
+ "RobertaForMaskedLM"
89
+ ],
90
+ "attention_probs_dropout_prob": 0.1,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": 0,
93
+ "chunk_size_feed_forward": 0,
94
+ "classifier_dropout": null,
95
+ "cross_attention_hidden_size": null,
96
+ "decoder_start_token_id": null,
97
+ "diversity_penalty": 0.0,
98
+ "do_sample": false,
99
+ "early_stopping": false,
100
+ "encoder_no_repeat_ngram_size": 0,
101
+ "eos_token_id": 2,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "gradient_checkpointing": false,
106
+ "hidden_act": "gelu",
107
+ "hidden_dropout_prob": 0.1,
108
+ "hidden_size": 768,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "is_decoder": false,
116
+ "is_encoder_decoder": false,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "layer_norm_eps": 1e-05,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "max_position_embeddings": 514,
125
+ "min_length": 0,
126
+ "model_type": "roberta",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 12,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 12,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": 1,
137
+ "position_embedding_type": "absolute",
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.12.3",
156
+ "type_vocab_size": 1,
157
+ "use_bfloat16": false,
158
+ "use_cache": true,
159
+ "vocab_size": 50265
160
+ },
161
+ "eos_token_id": 2,
162
+ "is_encoder_decoder": true,
163
+ "length_penalty": 2.0,
164
+ "max_length": 16,
165
+ "min_length": 4,
166
+ "model_type": "encoder-decoder",
167
+ "no_repeat_ngram_size": 1,
168
+ "num_beams": 4,
169
+ "pad_token_id": 1,
170
+ "repetition_penalty": 2.0,
171
+ "tie_encoder_decoder": true,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": null,
174
+ "vocab_size": 50265
175
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a83631a6eaa5b644deaa6a74a747be618c044273259915edd1192749a27d61
3
+ size 1224701433
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d379000491104e12d8f8f5c0c1846cb78fd70566cee9ae37abc8c17c1e8b7c
3
+ size 614807605
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff810b09080fb0cb75ce66b92963bff3282ee58b84499e6e35f8db39805af09e
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f695270a3a57ed6287a329cf2221f3dee69b2e52349672fb4e441788696ce16
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a93e9dcf19073791e7fbe2b56d05d5698693fc00638ccb46493089a7f97298
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-roberta-base-spanish", "tokenizer_class": "RobertaTokenizer"}
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0001521383092040196,
3
+ "best_model_checkpoint": "/opt/ml/model/checkpoint-4627",
4
+ "epoch": 1.0,
5
+ "global_step": 4627,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 2.976e-05,
13
+ "loss": 3.0635,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.22,
18
+ "learning_rate": 2.9674896220231594e-05,
19
+ "loss": 0.1023,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.32,
24
+ "learning_rate": 2.9347170635787637e-05,
25
+ "loss": 0.0253,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.43,
30
+ "learning_rate": 2.9019445051343676e-05,
31
+ "loss": 0.012,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.54,
36
+ "learning_rate": 2.8691719466899716e-05,
37
+ "loss": 0.007,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.65,
42
+ "learning_rate": 2.8363993882455756e-05,
43
+ "loss": 0.0049,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.76,
48
+ "learning_rate": 2.80362682980118e-05,
49
+ "loss": 0.0042,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.86,
54
+ "learning_rate": 2.770854271356784e-05,
55
+ "loss": 0.0034,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.97,
60
+ "learning_rate": 2.738081712912388e-05,
61
+ "loss": 0.0027,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.0,
66
+ "eval_loss": 0.0001521383092040196,
67
+ "eval_rouge2_fmeasure": 0.0001,
68
+ "eval_rouge2_precision": 0.0001,
69
+ "eval_rouge2_recall": 0.0002,
70
+ "eval_runtime": 1140.1653,
71
+ "eval_samples_per_second": 5.646,
72
+ "eval_steps_per_second": 0.706,
73
+ "step": 4627
74
+ }
75
+ ],
76
+ "max_steps": 46270,
77
+ "num_train_epochs": 10,
78
+ "total_flos": 1.46662238093616e+16,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f49d9f13eb265fbabb362db55f0940178eabce78a3c984abeafa7497b5d3cc
3
+ size 3119
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d379000491104e12d8f8f5c0c1846cb78fd70566cee9ae37abc8c17c1e8b7c
3
+ size 614807605
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-roberta-base-spanish", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f49d9f13eb265fbabb362db55f0940178eabce78a3c984abeafa7497b5d3cc
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff