allstax commited on
Commit
299c19b
1 Parent(s): 7025848

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "patrickvonplaten/longformer2roberta-cnn_dailymail-fp16",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 514,
49
+ "min_length": 0,
50
+ "model_type": "roberta",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": false,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "type_vocab_size": 1,
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "use_cache": true,
85
+ "vocab_size": 50265
86
+ },
87
+ "decoder_start_token_id": 0,
88
+ "encoder": {
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_mode": "longformer",
93
+ "attention_probs_dropout_prob": 0.1,
94
+ "attention_window": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512
107
+ ],
108
+ "bad_words_ids": null,
109
+ "begin_suppress_tokens": null,
110
+ "bos_token_id": 0,
111
+ "chunk_size_feed_forward": 0,
112
+ "cross_attention_hidden_size": null,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_sample": false,
116
+ "early_stopping": false,
117
+ "encoder_no_repeat_ngram_size": 0,
118
+ "eos_token_id": 2,
119
+ "exponential_decay_length_penalty": null,
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "gradient_checkpointing": false,
124
+ "hidden_act": "gelu",
125
+ "hidden_dropout_prob": 0.1,
126
+ "hidden_size": 768,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "ignore_attention_mask": false,
132
+ "initializer_range": 0.02,
133
+ "intermediate_size": 3072,
134
+ "is_decoder": false,
135
+ "is_encoder_decoder": false,
136
+ "label2id": {
137
+ "LABEL_0": 0,
138
+ "LABEL_1": 1
139
+ },
140
+ "layer_norm_eps": 1e-05,
141
+ "length_penalty": 1.0,
142
+ "max_length": 20,
143
+ "max_position_embeddings": 4098,
144
+ "min_length": 0,
145
+ "model_type": "longformer",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_attention_heads": 12,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_hidden_layers": 12,
151
+ "num_return_sequences": 1,
152
+ "onnx_export": false,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_scores": false,
156
+ "pad_token_id": 1,
157
+ "prefix": null,
158
+ "problem_type": null,
159
+ "pruned_heads": {},
160
+ "remove_invalid_values": false,
161
+ "repetition_penalty": 1.0,
162
+ "return_dict": false,
163
+ "return_dict_in_generate": false,
164
+ "sep_token_id": 2,
165
+ "suppress_tokens": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": true,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "type_vocab_size": 1,
177
+ "typical_p": 1.0,
178
+ "use_bfloat16": false,
179
+ "use_cache": true,
180
+ "vocab_size": 50265
181
+ },
182
+ "eos_token_id": 2,
183
+ "is_encoder_decoder": true,
184
+ "max_length": 142,
185
+ "min_length": 56,
186
+ "model_type": "encoder-decoder",
187
+ "no_repeat_ngram_size": 3,
188
+ "pad_token_id": 2,
189
+ "torch_dtype": "float32",
190
+ "transformers_version": "4.38.2"
191
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "max_length": 142,
6
+ "min_length": 56,
7
+ "no_repeat_ngram_size": 3,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.38.2"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb05608c8b8005f5087594c3a6f2330253362cb72fea03fb9cb16b9b1e09194
3
+ size 1206970564
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2ebb1591ef1a20f8897488d28efa828009af1874a9a5e57860496060677d58
3
+ size 2239409895
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e3eef43f957931c5614324f467dce8c5ea37af114c6a63121c406d42ad70a8
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea6e784ffec92ecfd0b1ceeed21fd8c7222a59e62100bb23df569ad3c19077d
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "unk_token": "<unk>",
56
+ "use_fast": true
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 397,
6
+ "global_step": 2384,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.17,
13
+ "eval_gen_len": 81.6102,
14
+ "eval_loss": 1.3396695852279663,
15
+ "eval_rouge1": 52.6908,
16
+ "eval_rouge2": 34.3367,
17
+ "eval_rougeL": 43.9351,
18
+ "eval_rougeLsum": 44.0153,
19
+ "eval_runtime": 41.4692,
20
+ "eval_samples_per_second": 1.423,
21
+ "eval_steps_per_second": 0.723,
22
+ "step": 397
23
+ },
24
+ {
25
+ "epoch": 0.21,
26
+ "grad_norm": 6.220447063446045,
27
+ "learning_rate": 1.895763422818792e-05,
28
+ "loss": 0.719,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.33,
33
+ "eval_gen_len": 84.2203,
34
+ "eval_loss": 1.363059639930725,
35
+ "eval_rouge1": 54.543,
36
+ "eval_rouge2": 36.4199,
37
+ "eval_rougeL": 45.8273,
38
+ "eval_rougeLsum": 45.7925,
39
+ "eval_runtime": 42.2281,
40
+ "eval_samples_per_second": 1.397,
41
+ "eval_steps_per_second": 0.71,
42
+ "step": 794
43
+ },
44
+ {
45
+ "epoch": 0.42,
46
+ "grad_norm": 8.490495681762695,
47
+ "learning_rate": 1.7908976510067115e-05,
48
+ "loss": 0.7459,
49
+ "step": 1000
50
+ },
51
+ {
52
+ "epoch": 0.5,
53
+ "eval_gen_len": 85.2373,
54
+ "eval_loss": 1.3582559823989868,
55
+ "eval_rouge1": 53.2262,
56
+ "eval_rouge2": 34.8889,
57
+ "eval_rougeL": 44.1043,
58
+ "eval_rougeLsum": 44.0998,
59
+ "eval_runtime": 42.6328,
60
+ "eval_samples_per_second": 1.384,
61
+ "eval_steps_per_second": 0.704,
62
+ "step": 1191
63
+ },
64
+ {
65
+ "epoch": 0.63,
66
+ "grad_norm": 6.794929027557373,
67
+ "learning_rate": 1.686031879194631e-05,
68
+ "loss": 0.7154,
69
+ "step": 1500
70
+ },
71
+ {
72
+ "epoch": 0.67,
73
+ "eval_gen_len": 83.7797,
74
+ "eval_loss": 1.3886514902114868,
75
+ "eval_rouge1": 54.9928,
76
+ "eval_rouge2": 37.1125,
77
+ "eval_rougeL": 46.4105,
78
+ "eval_rougeLsum": 46.4044,
79
+ "eval_runtime": 42.3464,
80
+ "eval_samples_per_second": 1.393,
81
+ "eval_steps_per_second": 0.708,
82
+ "step": 1588
83
+ },
84
+ {
85
+ "epoch": 0.83,
86
+ "eval_gen_len": 85.8814,
87
+ "eval_loss": 1.3405011892318726,
88
+ "eval_rouge1": 52.5543,
89
+ "eval_rouge2": 33.702,
90
+ "eval_rougeL": 42.9428,
91
+ "eval_rougeLsum": 43.0015,
92
+ "eval_runtime": 43.1199,
93
+ "eval_samples_per_second": 1.368,
94
+ "eval_steps_per_second": 0.696,
95
+ "step": 1985
96
+ },
97
+ {
98
+ "epoch": 0.84,
99
+ "grad_norm": 8.691970825195312,
100
+ "learning_rate": 1.5811661073825504e-05,
101
+ "loss": 0.7507,
102
+ "step": 2000
103
+ },
104
+ {
105
+ "epoch": 1.0,
106
+ "eval_gen_len": 81.7797,
107
+ "eval_loss": 1.3399206399917603,
108
+ "eval_rouge1": 52.4327,
109
+ "eval_rouge2": 34.1158,
110
+ "eval_rougeL": 43.2742,
111
+ "eval_rougeLsum": 43.1693,
112
+ "eval_runtime": 41.935,
113
+ "eval_samples_per_second": 1.407,
114
+ "eval_steps_per_second": 0.715,
115
+ "step": 2382
116
+ }
117
+ ],
118
+ "logging_steps": 500,
119
+ "max_steps": 9536,
120
+ "num_input_tokens_seen": 0,
121
+ "num_train_epochs": 4,
122
+ "save_steps": 1192,
123
+ "total_flos": 5.17811143698432e+16,
124
+ "train_batch_size": 2,
125
+ "trial_name": null,
126
+ "trial_params": null
127
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4e5ae08c2abdcb5ffb7b68b3ee7ae6c985193d6b10476bae766aeb2165fe26
3
+ size 4984
vocab.json ADDED
The diff for this file is too large to render. See raw diff