Hugging Face's logo

CrisisNarratives
/
adapter-8classes-single_label

Text2Text Generation
Transformers
PyTorch
English
t5
text-generation-inference
Inference Endpoints
Model card Files Community
Faeze commited on
Commit
5f2f386
•
1 Parent(s): 916f296

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. all_results.json +34 -0
  2. config.json +139 -0
  3. eval_instances_normalized_attn_scores.pt +3 -0
  4. eval_results.json +12 -0
  5. performance_results.json +4 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +1 -0
  8. spiece.model +3 -0
  9. test_instances_normalized_attn_scores.pt +3 -0
  10. test_results.json +12 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +1 -0
  13. train_results.json +14 -0
  14. trainer_state.json +0 -0
  15. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 200.0,
3
+ "eval_accuracy": 77.03703703703704,
4
+ "eval_average_metrics": 77.53590008051296,
5
+ "eval_classification_report": "{\"acceptance\": {\"precision\": 1.0, \"recall\": 0.8888888888888888, \"f1-score\": 0.9411764705882353, \"support\": 9.0}, \"apology\": {\"precision\": 1.0, \"recall\": 0.5, \"f1-score\": 0.6666666666666666, \"support\": 2.0}, \"appreciation\": {\"precision\": 0.7692307692307693, \"recall\": 0.9090909090909091, \"f1-score\": 0.8333333333333333, \"support\": 11.0}, \"challenge\": {\"precision\": 0.7105263157894737, \"recall\": 0.75, \"f1-score\": 0.7297297297297298, \"support\": 36.0}, \"informing statement\": {\"precision\": 0.7941176470588235, \"recall\": 0.6923076923076923, \"f1-score\": 0.7397260273972601, \"support\": 39.0}, \"question\": {\"precision\": 0.7777777777777778, \"recall\": 0.7777777777777778, \"f1-score\": 0.7777777777777778, \"support\": 9.0}, \"rejection\": {\"precision\": 1.0, \"recall\": 0.8461538461538461, \"f1-score\": 0.9166666666666666, \"support\": 13.0}, \"request\": {\"precision\": 0.6190476190476191, \"recall\": 0.8125, \"f1-score\": 0.7027027027027026, \"support\": 16.0}, \"accuracy\": 0.7703703703703704, \"macro avg\": {\"precision\": 0.833837516113058, \"recall\": 0.7720898892773893, \"f1-score\": 0.7884724218577965, \"support\": 135.0}, \"weighted avg\": {\"precision\": 0.784561747926041, \"recall\": 0.7703703703703704, \"f1-score\": 0.7722228406219811, \"support\": 135.0}}",
6
+ "eval_f1_macro": 78.84724218577965,
7
+ "eval_f1_micro": 77.03703703703704,
8
+ "eval_f1_weighted": 77.22228406219811,
9
+ "eval_loss": 1.0223504304885864,
10
+ "eval_runtime": 1.7125,
11
+ "eval_samples_per_second": 78.832,
12
+ "init_mem_cpu_alloc_delta": -543014912,
13
+ "init_mem_cpu_peaked_delta": 543023104,
14
+ "init_mem_gpu_alloc_delta": 891528192,
15
+ "init_mem_gpu_peaked_delta": 0,
16
+ "peak_memory": 5.305544921875,
17
+ "test_accuracy": 77.03703703703704,
18
+ "test_average_metrics": 77.53590008051296,
19
+ "test_classification_report": "{\"acceptance\": {\"precision\": 1.0, \"recall\": 0.8888888888888888, \"f1-score\": 0.9411764705882353, \"support\": 9.0}, \"apology\": {\"precision\": 1.0, \"recall\": 0.5, \"f1-score\": 0.6666666666666666, \"support\": 2.0}, \"appreciation\": {\"precision\": 0.7692307692307693, \"recall\": 0.9090909090909091, \"f1-score\": 0.8333333333333333, \"support\": 11.0}, \"challenge\": {\"precision\": 0.7105263157894737, \"recall\": 0.75, \"f1-score\": 0.7297297297297298, \"support\": 36.0}, \"informing statement\": {\"precision\": 0.7941176470588235, \"recall\": 0.6923076923076923, \"f1-score\": 0.7397260273972601, \"support\": 39.0}, \"question\": {\"precision\": 0.7777777777777778, \"recall\": 0.7777777777777778, \"f1-score\": 0.7777777777777778, \"support\": 9.0}, \"rejection\": {\"precision\": 1.0, \"recall\": 0.8461538461538461, \"f1-score\": 0.9166666666666666, \"support\": 13.0}, \"request\": {\"precision\": 0.6190476190476191, \"recall\": 0.8125, \"f1-score\": 0.7027027027027026, \"support\": 16.0}, \"accuracy\": 0.7703703703703704, \"macro avg\": {\"precision\": 0.833837516113058, \"recall\": 0.7720898892773893, \"f1-score\": 0.7884724218577965, \"support\": 135.0}, \"weighted avg\": {\"precision\": 0.784561747926041, \"recall\": 0.7703703703703704, \"f1-score\": 0.7722228406219811, \"support\": 135.0}}",
20
+ "test_f1_macro": 78.84724218577965,
21
+ "test_f1_micro": 77.03703703703704,
22
+ "test_f1_weighted": 77.22228406219811,
23
+ "test_loss": 1.0223504304885864,
24
+ "test_runtime": 1.6896,
25
+ "test_samples_per_second": 79.902,
26
+ "total_time in minutes ": 37.44455833333333,
27
+ "train_mem_cpu_alloc_delta": 1023647744,
28
+ "train_mem_cpu_peaked_delta": 32768,
29
+ "train_mem_gpu_alloc_delta": 40251392,
30
+ "train_mem_gpu_peaked_delta": 4624237568,
31
+ "train_runtime": 2245.6861,
32
+ "train_samples": 541,
33
+ "train_samples_per_second": 1.514
34
+ }
config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "attn_method": "linear",
7
+ "attn_prefix_tuning": false,
8
+ "class_weights": [
9
+ 0.43349358974358976,
10
+ 0.4663793103448276,
11
+ 1.0734126984126984,
12
+ 1.3004807692307692,
13
+ 1.4701086956521738,
14
+ 1.8277027027027026,
15
+ 1.9321428571428572,
16
+ 9.660714285714286
17
+ ],
18
+ "d_ff": 3072,
19
+ "d_kv": 64,
20
+ "d_model": 768,
21
+ "decoder_start_token_id": 0,
22
+ "dropout_rate": 0.1,
23
+ "eos_token_id": 1,
24
+ "feed_forward_proj": "relu",
25
+ "fix_attention": false,
26
+ "gradient_checkpointing": false,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1",
30
+ "2": "LABEL_2",
31
+ "3": "LABEL_3",
32
+ "4": "LABEL_4",
33
+ "5": "LABEL_5",
34
+ "6": "LABEL_6",
35
+ "7": "LABEL_7"
36
+ },
37
+ "ignore_target": false,
38
+ "init_prefix_method": "random",
39
+ "initializer_factor": 1.0,
40
+ "is_contrastive": false,
41
+ "is_encoder_decoder": true,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1,
45
+ "LABEL_2": 2,
46
+ "LABEL_3": 3,
47
+ "LABEL_4": 4,
48
+ "LABEL_5": 5,
49
+ "LABEL_6": 6,
50
+ "LABEL_7": 7
51
+ },
52
+ "label_based": false,
53
+ "label_token_ids": [
54
+ [
55
+ 16,
56
+ 10454,
57
+ 2493,
58
+ 1
59
+ ],
60
+ [
61
+ 1921,
62
+ 1
63
+ ],
64
+ [
65
+ 1690,
66
+ 1
67
+ ],
68
+ [
69
+ 21530,
70
+ 1
71
+ ],
72
+ [
73
+ 11746,
74
+ 1
75
+ ],
76
+ [
77
+ 11122,
78
+ 1
79
+ ],
80
+ [
81
+ 822,
82
+ 1
83
+ ],
84
+ [
85
+ 30430,
86
+ 1
87
+ ]
88
+ ],
89
+ "layer_norm_epsilon": 1e-06,
90
+ "learned_temperature": false,
91
+ "max_length": 4,
92
+ "model_type": "t5",
93
+ "n_positions": 512,
94
+ "normalize_prefixes": false,
95
+ "num_decoder_layers": 12,
96
+ "num_heads": 12,
97
+ "num_layers": 12,
98
+ "num_target": 1,
99
+ "output_past": true,
100
+ "pad_token_id": 0,
101
+ "prefix_num": 1,
102
+ "prefix_tuning": false,
103
+ "relative_attention_num_buckets": 32,
104
+ "shared_attn": false,
105
+ "task_specific_params": {
106
+ "summarization": {
107
+ "early_stopping": true,
108
+ "length_penalty": 2.0,
109
+ "max_length": 200,
110
+ "min_length": 30,
111
+ "no_repeat_ngram_size": 3,
112
+ "num_beams": 4,
113
+ "prefix": "summarize: "
114
+ },
115
+ "translation_en_to_de": {
116
+ "early_stopping": true,
117
+ "max_length": 300,
118
+ "num_beams": 4,
119
+ "prefix": "translate English to German: "
120
+ },
121
+ "translation_en_to_fr": {
122
+ "early_stopping": true,
123
+ "max_length": 300,
124
+ "num_beams": 4,
125
+ "prefix": "translate English to French: "
126
+ },
127
+ "translation_en_to_ro": {
128
+ "early_stopping": true,
129
+ "max_length": 300,
130
+ "num_beams": 4,
131
+ "prefix": "translate English to Romanian: "
132
+ }
133
+ },
134
+ "temperature": 2000,
135
+ "train_task_adapters": true,
136
+ "transformers_version": "4.6.0",
137
+ "use_cache": true,
138
+ "vocab_size": 32100
139
+ }
eval_instances_normalized_attn_scores.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50764592c09d3053c8ca12d3bd7108d14b2d3b3e93191cb4e40cfdac94418f81
3
+ size 1048
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 200.0,
3
+ "eval_accuracy": 77.03703703703704,
4
+ "eval_average_metrics": 77.53590008051296,
5
+ "eval_classification_report": "{\"acceptance\": {\"precision\": 1.0, \"recall\": 0.8888888888888888, \"f1-score\": 0.9411764705882353, \"support\": 9.0}, \"apology\": {\"precision\": 1.0, \"recall\": 0.5, \"f1-score\": 0.6666666666666666, \"support\": 2.0}, \"appreciation\": {\"precision\": 0.7692307692307693, \"recall\": 0.9090909090909091, \"f1-score\": 0.8333333333333333, \"support\": 11.0}, \"challenge\": {\"precision\": 0.7105263157894737, \"recall\": 0.75, \"f1-score\": 0.7297297297297298, \"support\": 36.0}, \"informing statement\": {\"precision\": 0.7941176470588235, \"recall\": 0.6923076923076923, \"f1-score\": 0.7397260273972601, \"support\": 39.0}, \"question\": {\"precision\": 0.7777777777777778, \"recall\": 0.7777777777777778, \"f1-score\": 0.7777777777777778, \"support\": 9.0}, \"rejection\": {\"precision\": 1.0, \"recall\": 0.8461538461538461, \"f1-score\": 0.9166666666666666, \"support\": 13.0}, \"request\": {\"precision\": 0.6190476190476191, \"recall\": 0.8125, \"f1-score\": 0.7027027027027026, \"support\": 16.0}, \"accuracy\": 0.7703703703703704, \"macro avg\": {\"precision\": 0.833837516113058, \"recall\": 0.7720898892773893, \"f1-score\": 0.7884724218577965, \"support\": 135.0}, \"weighted avg\": {\"precision\": 0.784561747926041, \"recall\": 0.7703703703703704, \"f1-score\": 0.7722228406219811, \"support\": 135.0}}",
6
+ "eval_f1_macro": 78.84724218577965,
7
+ "eval_f1_micro": 77.03703703703704,
8
+ "eval_f1_weighted": 77.22228406219811,
9
+ "eval_loss": 1.0223504304885864,
10
+ "eval_runtime": 1.7125,
11
+ "eval_samples_per_second": 78.832
12
+ }
performance_results.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "peak_memory": 5.305544921875,
3
+ "total_time in minutes ": 37.44455833333333
4
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc1901707a11e71612f4b0ba1d930600c37d021d547e04aef44ae04e83df670
3
+ size 898972302
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
test_instances_normalized_attn_scores.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf18366eb389698056f39a6158bd36abae1b39c77767057ccaca0a3c413cd26
3
+ size 1048
test_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 200.0,
3
+ "test_accuracy": 77.03703703703704,
4
+ "test_average_metrics": 77.53590008051296,
5
+ "test_classification_report": "{\"acceptance\": {\"precision\": 1.0, \"recall\": 0.8888888888888888, \"f1-score\": 0.9411764705882353, \"support\": 9.0}, \"apology\": {\"precision\": 1.0, \"recall\": 0.5, \"f1-score\": 0.6666666666666666, \"support\": 2.0}, \"appreciation\": {\"precision\": 0.7692307692307693, \"recall\": 0.9090909090909091, \"f1-score\": 0.8333333333333333, \"support\": 11.0}, \"challenge\": {\"precision\": 0.7105263157894737, \"recall\": 0.75, \"f1-score\": 0.7297297297297298, \"support\": 36.0}, \"informing statement\": {\"precision\": 0.7941176470588235, \"recall\": 0.6923076923076923, \"f1-score\": 0.7397260273972601, \"support\": 39.0}, \"question\": {\"precision\": 0.7777777777777778, \"recall\": 0.7777777777777778, \"f1-score\": 0.7777777777777778, \"support\": 9.0}, \"rejection\": {\"precision\": 1.0, \"recall\": 0.8461538461538461, \"f1-score\": 0.9166666666666666, \"support\": 13.0}, \"request\": {\"precision\": 0.6190476190476191, \"recall\": 0.8125, \"f1-score\": 0.7027027027027026, \"support\": 16.0}, \"accuracy\": 0.7703703703703704, \"macro avg\": {\"precision\": 0.833837516113058, \"recall\": 0.7720898892773893, \"f1-score\": 0.7884724218577965, \"support\": 135.0}, \"weighted avg\": {\"precision\": 0.784561747926041, \"recall\": 0.7703703703703704, \"f1-score\": 0.7722228406219811, \"support\": 135.0}}",
6
+ "test_f1_macro": 78.84724218577965,
7
+ "test_f1_micro": 77.03703703703704,
8
+ "test_f1_weighted": 77.22228406219811,
9
+ "test_loss": 1.0223504304885864,
10
+ "test_runtime": 1.6896,
11
+ "test_samples_per_second": 79.902
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 200.0,
3
+ "init_mem_cpu_alloc_delta": -543014912,
4
+ "init_mem_cpu_peaked_delta": 543023104,
5
+ "init_mem_gpu_alloc_delta": 891528192,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1023647744,
8
+ "train_mem_cpu_peaked_delta": 32768,
9
+ "train_mem_gpu_alloc_delta": 40251392,
10
+ "train_mem_gpu_peaked_delta": 4624237568,
11
+ "train_runtime": 2245.6861,
12
+ "train_samples": 541,
13
+ "train_samples_per_second": 1.514
14
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb1bc0a068808062e1b03d269a6f6bd850ff54067fc524902f8e3bdf1f70443
3
+ size 3384