Hugging Face's logo

cattana
/
flan-t5-large-qasem-joint-tokenized

Text2Text Generation
Transformers
PyTorch
t5
Inference Endpoints
text-generation-inference
Model card Files Community
cattana commited on
Commit
de04c68
•
1 Parent(s): a917ea1

init

Browse files
Files changed (11) hide show
  1. added_tokens.json +3 -0
  2. all_results.json +8 -0
  3. config.json +32 -0
  4. generation_config.json +6 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +107 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +112 -0
  9. train_results.json +8 -0
  10. trainer_state.json +205 -0
  11. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "`": 32100
3
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.18819899583558072,
4
+ "train_runtime": 25349.1542,
5
+ "train_samples": 102614,
6
+ "train_samples_per_second": 4.048,
7
+ "train_steps_per_second": 0.253
8
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-large",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
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": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.27.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32128
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.27.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4b6e084739bd81152b16c8439dc87f25f52b204b7a684c865aaa5a67c25321
3
+ size 3132793669
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ "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-large/snapshots/314bc112b191ec17b625ba81438dc73d6c23659d/special_tokens_map.json",
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.18819899583558072,
4
+ "train_runtime": 25349.1542,
5
+ "train_samples": 102614,
6
+ "train_samples_per_second": 4.048,
7
+ "train_steps_per_second": 0.253
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9999220394480393,
5
+ "global_step": 6413,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 4.610166848588804e-05,
13
+ "loss": 1.501,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "eval_gen_len": 38.430038252466275,
19
+ "eval_loss": 0.11725818365812302,
20
+ "eval_runtime": 1525.1588,
21
+ "eval_samples_per_second": 3.257,
22
+ "eval_steps_per_second": 0.407,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "learning_rate": 4.220333697177608e-05,
28
+ "loss": 0.0972,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.16,
33
+ "eval_gen_len": 38.57358566539158,
34
+ "eval_loss": 0.10414853692054749,
35
+ "eval_runtime": 1374.4335,
36
+ "eval_samples_per_second": 3.614,
37
+ "eval_steps_per_second": 0.452,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.23,
42
+ "learning_rate": 3.830500545766412e-05,
43
+ "loss": 0.0871,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 0.23,
48
+ "eval_gen_len": 41.80269780551641,
49
+ "eval_loss": 0.09756787866353989,
50
+ "eval_runtime": 1416.1217,
51
+ "eval_samples_per_second": 3.507,
52
+ "eval_steps_per_second": 0.439,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 0.31,
57
+ "learning_rate": 3.440667394355216e-05,
58
+ "loss": 0.0821,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 0.31,
63
+ "eval_gen_len": 38.83108516206966,
64
+ "eval_loss": 0.09272466599941254,
65
+ "eval_runtime": 1386.2597,
66
+ "eval_samples_per_second": 3.583,
67
+ "eval_steps_per_second": 0.448,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.39,
72
+ "learning_rate": 3.05083424294402e-05,
73
+ "loss": 0.0796,
74
+ "step": 2500
75
+ },
76
+ {
77
+ "epoch": 0.39,
78
+ "eval_gen_len": 42.82927320314073,
79
+ "eval_loss": 0.09029995650053024,
80
+ "eval_runtime": 1431.1493,
81
+ "eval_samples_per_second": 3.471,
82
+ "eval_steps_per_second": 0.434,
83
+ "step": 2500
84
+ },
85
+ {
86
+ "epoch": 0.47,
87
+ "learning_rate": 2.6610010915328243e-05,
88
+ "loss": 0.0766,
89
+ "step": 3000
90
+ },
91
+ {
92
+ "epoch": 0.47,
93
+ "eval_gen_len": 41.111938796053956,
94
+ "eval_loss": 0.08799975365400314,
95
+ "eval_runtime": 1401.8123,
96
+ "eval_samples_per_second": 3.543,
97
+ "eval_steps_per_second": 0.443,
98
+ "step": 3000
99
+ },
100
+ {
101
+ "epoch": 0.55,
102
+ "learning_rate": 2.271167940121628e-05,
103
+ "loss": 0.0741,
104
+ "step": 3500
105
+ },
106
+ {
107
+ "epoch": 0.55,
108
+ "eval_gen_len": 40.73605798268573,
109
+ "eval_loss": 0.08718982338905334,
110
+ "eval_runtime": 1373.6325,
111
+ "eval_samples_per_second": 3.616,
112
+ "eval_steps_per_second": 0.452,
113
+ "step": 3500
114
+ },
115
+ {
116
+ "epoch": 0.62,
117
+ "learning_rate": 1.881334788710432e-05,
118
+ "loss": 0.0729,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 0.62,
123
+ "eval_gen_len": 39.60056372055567,
124
+ "eval_loss": 0.08510363847017288,
125
+ "eval_runtime": 1369.314,
126
+ "eval_samples_per_second": 3.627,
127
+ "eval_steps_per_second": 0.454,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 0.7,
132
+ "learning_rate": 1.491501637299236e-05,
133
+ "loss": 0.0723,
134
+ "step": 4500
135
+ },
136
+ {
137
+ "epoch": 0.7,
138
+ "eval_gen_len": 40.53654117173344,
139
+ "eval_loss": 0.08480597287416458,
140
+ "eval_runtime": 1394.4001,
141
+ "eval_samples_per_second": 3.562,
142
+ "eval_steps_per_second": 0.445,
143
+ "step": 4500
144
+ },
145
+ {
146
+ "epoch": 0.78,
147
+ "learning_rate": 1.1016684858880399e-05,
148
+ "loss": 0.0729,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 0.78,
153
+ "eval_gen_len": 41.251258304811756,
154
+ "eval_loss": 0.08257019519805908,
155
+ "eval_runtime": 1406.7799,
156
+ "eval_samples_per_second": 3.531,
157
+ "eval_steps_per_second": 0.441,
158
+ "step": 5000
159
+ },
160
+ {
161
+ "epoch": 0.86,
162
+ "learning_rate": 7.11835334476844e-06,
163
+ "loss": 0.071,
164
+ "step": 5500
165
+ },
166
+ {
167
+ "epoch": 0.86,
168
+ "eval_gen_len": 41.85141936782766,
169
+ "eval_loss": 0.08206828683614731,
170
+ "eval_runtime": 1411.1175,
171
+ "eval_samples_per_second": 3.52,
172
+ "eval_steps_per_second": 0.44,
173
+ "step": 5500
174
+ },
175
+ {
176
+ "epoch": 0.94,
177
+ "learning_rate": 3.220021830656479e-06,
178
+ "loss": 0.0699,
179
+ "step": 6000
180
+ },
181
+ {
182
+ "epoch": 0.94,
183
+ "eval_gen_len": 41.36098248439702,
184
+ "eval_loss": 0.08196299523115158,
185
+ "eval_runtime": 1408.2137,
186
+ "eval_samples_per_second": 3.527,
187
+ "eval_steps_per_second": 0.441,
188
+ "step": 6000
189
+ },
190
+ {
191
+ "epoch": 1.0,
192
+ "step": 6413,
193
+ "total_flos": 1.2273483536252928e+17,
194
+ "train_loss": 0.18819899583558072,
195
+ "train_runtime": 25349.1542,
196
+ "train_samples_per_second": 4.048,
197
+ "train_steps_per_second": 0.253
198
+ }
199
+ ],
200
+ "max_steps": 6413,
201
+ "num_train_epochs": 1,
202
+ "total_flos": 1.2273483536252928e+17,
203
+ "trial_name": null,
204
+ "trial_params": null
205
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a38624933b054791a7accedebed4dc471fd43ae61a85250b313a1f92cd1217a
3
+ size 3771