Hugging Face's logo

shnl
/
mrc-vinewsqa-vit5

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
shnl commited on
Commit
106f522
•
1 Parent(s): 31c50d5

'mrc'

Browse files
Files changed (12) hide show
  1. config.json +31 -0
  2. generation_config.json +7 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +103 -0
  8. spiece.model +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +108 -0
  11. trainer_state.json +142 -0
  12. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "VietAI/vit5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.27.4",
29
+ "use_cache": true,
30
+ "vocab_size": 36096
31
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.4"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e9a683761a7380b1d8c6eb28733c7bdf95f974c52b6f25304901e6717795aa
3
+ size 1807760133
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3832d34be82ae15b502b8591231dec8d6137a6258340c2bddd7ff2c15b082511
3
+ size 903892625
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c174d064882da5f739b2ec1c8998a52258446ef27283c1f479423b9532a195
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42c0952ace25abadb455bf95b3218b668bd82c8fedc128349576e02e6265a6a
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
100
+ "eos_token": "</s>",
101
+ "pad_token": "<pad>",
102
+ "unk_token": "<unk>"
103
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
3
+ size 820370
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
100
+ "eos_token": "</s>",
101
+ "extra_ids": 96,
102
+ "model_max_length": 1000000000000000019884624838656,
103
+ "pad_token": "<pad>",
104
+ "sp_model_kwargs": {},
105
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--VietAI--vit5-base/snapshots/2209a38d735ede63e88f5aa52bcdc11a05a37b85/special_tokens_map.json",
106
+ "tokenizer_class": "T5Tokenizer",
107
+ "unk_token": "<unk>"
108
+ }
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.109542245502164,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.73,
12
+ "eval_loss": 0.04153425619006157,
13
+ "eval_runtime": 134.1421,
14
+ "eval_samples_per_second": 18.615,
15
+ "eval_steps_per_second": 1.17,
16
+ "step": 200
17
+ },
18
+ {
19
+ "epoch": 1.46,
20
+ "eval_loss": 0.03776169568300247,
21
+ "eval_runtime": 133.8056,
22
+ "eval_samples_per_second": 18.661,
23
+ "eval_steps_per_second": 1.173,
24
+ "step": 400
25
+ },
26
+ {
27
+ "epoch": 1.82,
28
+ "learning_rate": 8.60545524394929e-05,
29
+ "loss": 1.1974,
30
+ "step": 500
31
+ },
32
+ {
33
+ "epoch": 2.19,
34
+ "eval_loss": 0.038170840591192245,
35
+ "eval_runtime": 133.7976,
36
+ "eval_samples_per_second": 18.663,
37
+ "eval_steps_per_second": 1.173,
38
+ "step": 600
39
+ },
40
+ {
41
+ "epoch": 2.92,
42
+ "eval_loss": 0.03970686346292496,
43
+ "eval_runtime": 133.7983,
44
+ "eval_samples_per_second": 18.662,
45
+ "eval_steps_per_second": 1.173,
46
+ "step": 800
47
+ },
48
+ {
49
+ "epoch": 3.64,
50
+ "learning_rate": 6.684594698424894e-05,
51
+ "loss": 0.0176,
52
+ "step": 1000
53
+ },
54
+ {
55
+ "epoch": 3.64,
56
+ "eval_loss": 0.040207117795944214,
57
+ "eval_runtime": 133.8022,
58
+ "eval_samples_per_second": 18.662,
59
+ "eval_steps_per_second": 1.173,
60
+ "step": 1000
61
+ },
62
+ {
63
+ "epoch": 4.37,
64
+ "eval_loss": 0.04497513547539711,
65
+ "eval_runtime": 133.8142,
66
+ "eval_samples_per_second": 18.66,
67
+ "eval_steps_per_second": 1.173,
68
+ "step": 1200
69
+ },
70
+ {
71
+ "epoch": 5.1,
72
+ "eval_loss": 0.04816456884145737,
73
+ "eval_runtime": 133.7956,
74
+ "eval_samples_per_second": 18.663,
75
+ "eval_steps_per_second": 1.173,
76
+ "step": 1400
77
+ },
78
+ {
79
+ "epoch": 5.47,
80
+ "learning_rate": 4.7637341529005e-05,
81
+ "loss": 0.0096,
82
+ "step": 1500
83
+ },
84
+ {
85
+ "epoch": 5.83,
86
+ "eval_loss": 0.04493580386042595,
87
+ "eval_runtime": 133.8039,
88
+ "eval_samples_per_second": 18.662,
89
+ "eval_steps_per_second": 1.173,
90
+ "step": 1600
91
+ },
92
+ {
93
+ "epoch": 6.56,
94
+ "eval_loss": 0.04887638986110687,
95
+ "eval_runtime": 133.8071,
96
+ "eval_samples_per_second": 18.661,
97
+ "eval_steps_per_second": 1.173,
98
+ "step": 1800
99
+ },
100
+ {
101
+ "epoch": 7.29,
102
+ "learning_rate": 2.8428736073761048e-05,
103
+ "loss": 0.0049,
104
+ "step": 2000
105
+ },
106
+ {
107
+ "epoch": 7.29,
108
+ "eval_loss": 0.05439848080277443,
109
+ "eval_runtime": 133.7974,
110
+ "eval_samples_per_second": 18.663,
111
+ "eval_steps_per_second": 1.173,
112
+ "step": 2000
113
+ },
114
+ {
115
+ "epoch": 8.02,
116
+ "eval_loss": 0.055828921496868134,
117
+ "eval_runtime": 133.8004,
118
+ "eval_samples_per_second": 18.662,
119
+ "eval_steps_per_second": 1.173,
120
+ "step": 2200
121
+ },
122
+ {
123
+ "epoch": 8.75,
124
+ "eval_loss": 0.056505098938941956,
125
+ "eval_runtime": 133.7919,
126
+ "eval_samples_per_second": 18.663,
127
+ "eval_steps_per_second": 1.173,
128
+ "step": 2400
129
+ },
130
+ {
131
+ "epoch": 9.11,
132
+ "learning_rate": 9.220130618517096e-06,
133
+ "loss": 0.0028,
134
+ "step": 2500
135
+ }
136
+ ],
137
+ "max_steps": 2740,
138
+ "num_train_epochs": 10,
139
+ "total_flos": 1.9485556373716992e+17,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9292c2674d48e0e43abf4a97eefacf86ab6021379cbec37dc831b99b1954a6f1
3
+ size 3643