Hugging Face's logo

sara-nabhani
/
google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64

Text2Text Generation
Transformers
PyTorch
t5
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
2
sara-nabhani commited on
Commit
8c55c1d
•
1 Parent(s): a8506d5

Model save

Browse files
Files changed (12) hide show
  1. last-checkpoint/generation_config.json → generation_config.json +0 -0
  2. last-checkpoint/config.json +0 -61
  3. last-checkpoint/optimizer.pt +0 -3
  4. last-checkpoint/pytorch_model.bin +0 -3
  5. last-checkpoint/rng_state.pth +0 -3
  6. last-checkpoint/scheduler.pt +0 -3
  7. last-checkpoint/special_tokens_map.json +0 -107
  8. last-checkpoint/tokenizer.json +0 -0
  9. last-checkpoint/tokenizer_config.json +0 -112
  10. last-checkpoint/trainer_state.json +0 -148
  11. last-checkpoint/training_args.bin +0 -3
  12. pytorch_model.bin +1 -1
last-checkpoint/generation_config.json → generation_config.json RENAMED
File without changes
last-checkpoint/config.json DELETED
@@ -1,61 +0,0 @@
1
- {
2
- "_name_or_path": "google/flan-t5-small",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "d_ff": 1024,
7
- "d_kv": 64,
8
- "d_model": 512,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "gelu_new",
11
- "dropout_rate": 0.1,
12
- "eos_token_id": 1,
13
- "feed_forward_proj": "gated-gelu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": true,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "n_positions": 512,
20
- "num_decoder_layers": 8,
21
- "num_heads": 6,
22
- "num_layers": 8,
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
- "tie_word_embeddings": false,
57
- "torch_dtype": "float32",
58
- "transformers_version": "4.27.4",
59
- "use_cache": true,
60
- "vocab_size": 32128
61
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc52c0fda0953e9c5a430c827e292d874b1f843ff7773931f9c93cc6008fe891
3
- size 1135685
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
3
- size 307910149
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8a619c5b75ad0de048a2974bf922da29a1e97a9cea67f262287c758eca45981
3
- size 14575
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f07e5c87a13181fdd91b70430838fde915aa2178a6a09686f68923b2683ae87
3
- size 627
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,107 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,112 +0,0 @@
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
- "sp_model_kwargs": {},
109
- "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
110
- "tokenizer_class": "T5Tokenizer",
111
- "unk_token": "<unk>"
112
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,148 +0,0 @@
1
- {
2
- "best_metric": 1.7871696949005127,
3
- "best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
4
- "epoch": 1.3979496738117427,
5
- "global_step": 12000,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.23,
12
- "learning_rate": 0.0004659832246039143,
13
- "loss": 1.4692,
14
- "step": 2000
15
- },
16
- {
17
- "epoch": 0.23,
18
- "eval_accuracy": 0.8211745580166633,
19
- "eval_bertscore_f1": 0.9286575323984018,
20
- "eval_bleu": 0.38561860316652036,
21
- "eval_f1": 0.8203013643438366,
22
- "eval_loss": 1.7871696949005127,
23
- "eval_rouge1": 0.5787165816995035,
24
- "eval_rouge2": 0.3685417962966523,
25
- "eval_rougeL": 0.5239321926914862,
26
- "eval_rougeLsum": 0.5257244126819034,
27
- "eval_runtime": 159.3394,
28
- "eval_samples_per_second": 61.768,
29
- "eval_steps_per_second": 0.966,
30
- "step": 2000
31
- },
32
- {
33
- "epoch": 0.47,
34
- "learning_rate": 0.0009319664492078286,
35
- "loss": 1.2505,
36
- "step": 4000
37
- },
38
- {
39
- "epoch": 0.47,
40
- "eval_accuracy": 0.8262548262548263,
41
- "eval_bertscore_f1": 0.9307863134553921,
42
- "eval_bleu": 0.39038732251575425,
43
- "eval_f1": 0.8263713441477889,
44
- "eval_loss": 1.8808104991912842,
45
- "eval_rouge1": 0.5869703246365517,
46
- "eval_rouge2": 0.3748641547543645,
47
- "eval_rougeL": 0.5321311878885444,
48
- "eval_rougeLsum": 0.5336937989329478,
49
- "eval_runtime": 142.2964,
50
- "eval_samples_per_second": 69.165,
51
- "eval_steps_per_second": 1.082,
52
- "step": 4000
53
- },
54
- {
55
- "epoch": 0.7,
56
- "learning_rate": 0.0009790552803256977,
57
- "loss": 1.2003,
58
- "step": 6000
59
- },
60
- {
61
- "epoch": 0.7,
62
- "eval_accuracy": 0.8474903474903475,
63
- "eval_bertscore_f1": 0.9325015046530636,
64
- "eval_bleu": 0.40037514315917067,
65
- "eval_f1": 0.8480955479827984,
66
- "eval_loss": 1.8476512432098389,
67
- "eval_rouge1": 0.5984358503927201,
68
- "eval_rouge2": 0.39129615048248045,
69
- "eval_rougeL": 0.5452371782543385,
70
- "eval_rougeLsum": 0.5468731108541084,
71
- "eval_runtime": 143.5626,
72
- "eval_samples_per_second": 68.555,
73
- "eval_steps_per_second": 1.073,
74
- "step": 6000
75
- },
76
- {
77
- "epoch": 0.93,
78
- "learning_rate": 0.0009545298474518076,
79
- "loss": 1.1624,
80
- "step": 8000
81
- },
82
- {
83
- "epoch": 0.93,
84
- "eval_accuracy": 0.8598862019914651,
85
- "eval_bertscore_f1": 0.9334783477709075,
86
- "eval_bleu": 0.4024137500087889,
87
- "eval_f1": 0.8587313635433268,
88
- "eval_loss": 1.8243632316589355,
89
- "eval_rouge1": 0.602912531326099,
90
- "eval_rouge2": 0.39282903833995186,
91
- "eval_rougeL": 0.5440694412996867,
92
- "eval_rougeLsum": 0.5457091432223387,
93
- "eval_runtime": 139.5669,
94
- "eval_samples_per_second": 70.518,
95
- "eval_steps_per_second": 1.103,
96
- "step": 8000
97
- },
98
- {
99
- "epoch": 1.16,
100
- "learning_rate": 0.0009300044145779173,
101
- "loss": 1.1155,
102
- "step": 10000
103
- },
104
- {
105
- "epoch": 1.16,
106
- "eval_accuracy": 0.8695387116439748,
107
- "eval_bertscore_f1": 0.9330506402710739,
108
- "eval_bleu": 0.4022160428281426,
109
- "eval_f1": 0.868816289704145,
110
- "eval_loss": 1.8499114513397217,
111
- "eval_rouge1": 0.6082846765097942,
112
- "eval_rouge2": 0.4018899263767985,
113
- "eval_rougeL": 0.5518885347721499,
114
- "eval_rougeLsum": 0.5540212762276107,
115
- "eval_runtime": 148.4149,
116
- "eval_samples_per_second": 66.314,
117
- "eval_steps_per_second": 1.038,
118
- "step": 10000
119
- },
120
- {
121
- "epoch": 1.4,
122
- "learning_rate": 0.0009054789817040271,
123
- "loss": 1.0913,
124
- "step": 12000
125
- },
126
- {
127
- "epoch": 1.4,
128
- "eval_accuracy": 0.8691322901849218,
129
- "eval_bertscore_f1": 0.9338201113503969,
130
- "eval_bleu": 0.4012059786299585,
131
- "eval_f1": 0.8686267742768865,
132
- "eval_loss": 1.870266079902649,
133
- "eval_rouge1": 0.6062872493545299,
134
- "eval_rouge2": 0.39947246134905595,
135
- "eval_rougeL": 0.5500107773403655,
136
- "eval_rougeLsum": 0.5520562338476832,
137
- "eval_runtime": 149.6673,
138
- "eval_samples_per_second": 65.759,
139
- "eval_steps_per_second": 1.029,
140
- "step": 12000
141
- }
142
- ],
143
- "max_steps": 85840,
144
- "num_train_epochs": 10,
145
- "total_flos": 1.6445151317200896e+16,
146
- "trial_name": null,
147
- "trial_params": null
148
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f646a3faadd89d6e0ebf583dc895130b809f60717a6dce58266a8b7d13e80755
3
- size 4027
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5488e44d05732c8456886c008afe4f848e12be9687ec9ebef630cd4c8f668149
3
  size 307910149