Hugging Face's logo

MihaiIonascu
/
NL_to_IaC_T5

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
MihaiIonascu commited on
Commit
7e5dbfe
·
1 Parent(s): 178cbc1

Upload 12 files

Browse files
Files changed (11) hide show
  1. config.json +6 -6
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +2 -2
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +107 -0
  8. spiece.model +3 -0
  9. tokenizer_config.json +112 -0
  10. trainer_state.json +184 -0
  11. training_args.bin +3 -0
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
  "d_kv": 64,
8
- "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
- "num_decoder_layers": 6,
21
- "num_heads": 8,
22
- "num_layers": 6,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "t5-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,
 
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,
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e70577451da6c20a54e5cbf66667a2b24086c28ee9db014a5b2fe3588041e04
3
+ size 1783380741
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f201f2d0cd0a9d91888f688b57760f8817172765764bd266aec2e707188fa859
3
- size 242069785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6701af11dfa7cc642a5785064da7f9fbf4c8b1316b1de3fa888ac1e9036e0ae4
3
+ size 891702929
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0a9878fa6809c7ce5fcd4cc880f81223e67224a11f2e72869714ff4ce209c8
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16c184eeebd1760a8ebc14d442afc6552384a634bd57239ff27e187793d14ad
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256c01a3822eef6524d9c48aa8caf7f05eb1d6b7b3a7c5c2722fc87a968b2ae4
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 28.0,
5
+ "global_step": 14252,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.9801178781925346e-05,
13
+ "loss": 2.0175,
14
+ "step": 509
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 1.9601178781925344e-05,
19
+ "loss": 1.0916,
20
+ "step": 1018
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 1.9401571709233793e-05,
25
+ "loss": 0.9,
26
+ "step": 1527
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 1.920196463654224e-05,
31
+ "loss": 0.7942,
32
+ "step": 2036
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 1.900235756385069e-05,
37
+ "loss": 0.7212,
38
+ "step": 2545
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 1.8803536345776033e-05,
43
+ "loss": 0.6697,
44
+ "step": 3054
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 1.860432220039293e-05,
49
+ "loss": 0.6265,
50
+ "step": 3563
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 1.8407072691552063e-05,
55
+ "loss": 0.6136,
56
+ "step": 4072
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 1.8207465618860512e-05,
61
+ "loss": 0.8441,
62
+ "step": 4581
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 1.800943025540275e-05,
67
+ "loss": 1.0052,
68
+ "step": 5090
69
+ },
70
+ {
71
+ "epoch": 11.0,
72
+ "learning_rate": 1.7810216110019647e-05,
73
+ "loss": 0.9929,
74
+ "step": 5599
75
+ },
76
+ {
77
+ "epoch": 12.0,
78
+ "learning_rate": 1.7610609037328093e-05,
79
+ "loss": 0.983,
80
+ "step": 6108
81
+ },
82
+ {
83
+ "epoch": 13.0,
84
+ "learning_rate": 1.7412180746561888e-05,
85
+ "loss": 0.9804,
86
+ "step": 6617
87
+ },
88
+ {
89
+ "epoch": 14.0,
90
+ "learning_rate": 1.7213359528487232e-05,
91
+ "loss": 0.9818,
92
+ "step": 7126
93
+ },
94
+ {
95
+ "epoch": 15.0,
96
+ "learning_rate": 1.701375245579568e-05,
97
+ "loss": 0.9822,
98
+ "step": 7635
99
+ },
100
+ {
101
+ "epoch": 16.0,
102
+ "learning_rate": 1.6814931237721025e-05,
103
+ "loss": 0.9819,
104
+ "step": 8144
105
+ },
106
+ {
107
+ "epoch": 17.0,
108
+ "learning_rate": 1.6614931237721024e-05,
109
+ "loss": 0.9826,
110
+ "step": 8653
111
+ },
112
+ {
113
+ "epoch": 18.0,
114
+ "learning_rate": 1.6416895874263262e-05,
115
+ "loss": 0.9822,
116
+ "step": 9162
117
+ },
118
+ {
119
+ "epoch": 19.0,
120
+ "learning_rate": 1.6218074656188606e-05,
121
+ "loss": 0.9827,
122
+ "step": 9671
123
+ },
124
+ {
125
+ "epoch": 20.0,
126
+ "learning_rate": 1.6019646365422398e-05,
127
+ "loss": 0.9843,
128
+ "step": 10180
129
+ },
130
+ {
131
+ "epoch": 21.0,
132
+ "learning_rate": 1.5820039292730847e-05,
133
+ "loss": 0.9808,
134
+ "step": 10689
135
+ },
136
+ {
137
+ "epoch": 22.0,
138
+ "learning_rate": 1.5620432220039293e-05,
139
+ "loss": 0.9823,
140
+ "step": 11198
141
+ },
142
+ {
143
+ "epoch": 23.0,
144
+ "learning_rate": 1.5420825147347742e-05,
145
+ "loss": 0.9801,
146
+ "step": 11707
147
+ },
148
+ {
149
+ "epoch": 24.0,
150
+ "learning_rate": 1.5222396856581534e-05,
151
+ "loss": 0.9824,
152
+ "step": 12216
153
+ },
154
+ {
155
+ "epoch": 25.0,
156
+ "learning_rate": 1.5022789783889981e-05,
157
+ "loss": 0.9813,
158
+ "step": 12725
159
+ },
160
+ {
161
+ "epoch": 26.0,
162
+ "learning_rate": 1.4823968565815325e-05,
163
+ "loss": 0.9836,
164
+ "step": 13234
165
+ },
166
+ {
167
+ "epoch": 27.0,
168
+ "learning_rate": 1.4624361493123773e-05,
169
+ "loss": 0.9838,
170
+ "step": 13743
171
+ },
172
+ {
173
+ "epoch": 28.0,
174
+ "learning_rate": 1.4425933202357564e-05,
175
+ "loss": 0.9803,
176
+ "step": 14252
177
+ }
178
+ ],
179
+ "max_steps": 50900,
180
+ "num_train_epochs": 100,
181
+ "total_flos": 3675621063214080.0,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7c69e090b7d734cd3799901dff8241c01d2b59023b2b57ecd035e105b12ce0
3
+ size 3771