Hugging Face's logo

devagonal
/
flan-t5-base-squad-qag

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
devagonal commited on
Commit
1afdd86
·
verified ·
1 Parent(s): 38b3ab3

End of training

Browse files
Files changed (5) hide show
  1. README.md +159 -0
  2. config.json +62 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/flan-t5-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: flan-t5-base-squad-qag
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # flan-t5-base-squad-qag
16
+
17
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 15.5366
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 100
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-------:|:----:|:---------------:|
52
+ | 46.6459 | 0.5714 | 1 | 43.1485 |
53
+ | 65.3532 | 1.5714 | 2 | 41.6135 |
54
+ | 62.735 | 2.5714 | 3 | 40.4950 |
55
+ | 61.766 | 3.5714 | 4 | 39.5923 |
56
+ | 57.7849 | 4.5714 | 5 | 38.7835 |
57
+ | 55.8212 | 5.5714 | 6 | 38.0234 |
58
+ | 55.277 | 6.5714 | 7 | 37.3084 |
59
+ | 53.3929 | 7.5714 | 8 | 36.6244 |
60
+ | 53.3042 | 8.5714 | 9 | 35.9682 |
61
+ | 51.6622 | 9.5714 | 10 | 35.3432 |
62
+ | 50.679 | 10.5714 | 11 | 34.7521 |
63
+ | 49.5895 | 11.5714 | 12 | 34.1904 |
64
+ | 48.219 | 12.5714 | 13 | 33.6558 |
65
+ | 47.7489 | 13.5714 | 14 | 33.1496 |
66
+ | 46.8016 | 14.5714 | 15 | 32.6729 |
67
+ | 45.2487 | 15.5714 | 16 | 32.2232 |
68
+ | 45.3148 | 16.5714 | 17 | 31.7991 |
69
+ | 44.3454 | 17.5714 | 18 | 31.3964 |
70
+ | 43.6766 | 18.5714 | 19 | 31.0145 |
71
+ | 42.8757 | 19.5714 | 20 | 30.6499 |
72
+ | 42.9431 | 20.5714 | 21 | 30.2991 |
73
+ | 41.7531 | 21.5714 | 22 | 29.9607 |
74
+ | 41.2977 | 22.5714 | 23 | 29.6343 |
75
+ | 40.7757 | 23.5714 | 24 | 29.3154 |
76
+ | 40.0453 | 24.5714 | 25 | 29.0031 |
77
+ | 39.602 | 25.5714 | 26 | 28.6966 |
78
+ | 39.7306 | 26.5714 | 27 | 28.3944 |
79
+ | 38.703 | 27.5714 | 28 | 28.0947 |
80
+ | 38.7594 | 28.5714 | 29 | 27.7978 |
81
+ | 38.3422 | 29.5714 | 30 | 27.5051 |
82
+ | 38.1699 | 30.5714 | 31 | 27.2152 |
83
+ | 37.9031 | 31.5714 | 32 | 26.9286 |
84
+ | 36.9734 | 32.5714 | 33 | 26.6434 |
85
+ | 37.0667 | 33.5714 | 34 | 26.3599 |
86
+ | 36.466 | 34.5714 | 35 | 26.0803 |
87
+ | 35.9406 | 35.5714 | 36 | 25.8051 |
88
+ | 35.6333 | 36.5714 | 37 | 25.5321 |
89
+ | 35.3167 | 37.5714 | 38 | 25.2619 |
90
+ | 35.3965 | 38.5714 | 39 | 24.9950 |
91
+ | 34.5731 | 39.5714 | 40 | 24.7318 |
92
+ | 34.2446 | 40.5714 | 41 | 24.4734 |
93
+ | 34.2668 | 41.5714 | 42 | 24.2188 |
94
+ | 33.6151 | 42.5714 | 43 | 23.9683 |
95
+ | 33.5523 | 43.5714 | 44 | 23.7208 |
96
+ | 33.0644 | 44.5714 | 45 | 23.4754 |
97
+ | 32.7476 | 45.5714 | 46 | 23.2334 |
98
+ | 32.9809 | 46.5714 | 47 | 22.9938 |
99
+ | 32.0039 | 47.5714 | 48 | 22.7560 |
100
+ | 32.0855 | 48.5714 | 49 | 22.5215 |
101
+ | 31.6121 | 49.5714 | 50 | 22.2902 |
102
+ | 31.5072 | 50.5714 | 51 | 22.0626 |
103
+ | 31.0177 | 51.5714 | 52 | 21.8383 |
104
+ | 30.7915 | 52.5714 | 53 | 21.6181 |
105
+ | 30.6385 | 53.5714 | 54 | 21.4022 |
106
+ | 30.0557 | 54.5714 | 55 | 21.1892 |
107
+ | 30.2011 | 55.5714 | 56 | 20.9796 |
108
+ | 29.8038 | 56.5714 | 57 | 20.7722 |
109
+ | 29.5406 | 57.5714 | 58 | 20.5675 |
110
+ | 29.2149 | 58.5714 | 59 | 20.3655 |
111
+ | 29.2198 | 59.5714 | 60 | 20.1660 |
112
+ | 28.8561 | 60.5714 | 61 | 19.9673 |
113
+ | 28.6416 | 61.5714 | 62 | 19.7716 |
114
+ | 28.8112 | 62.5714 | 63 | 19.5786 |
115
+ | 28.2165 | 63.5714 | 64 | 19.3885 |
116
+ | 27.8991 | 64.5714 | 65 | 19.2027 |
117
+ | 27.5846 | 65.5714 | 66 | 19.0196 |
118
+ | 27.2384 | 66.5714 | 67 | 18.8399 |
119
+ | 27.0191 | 67.5714 | 68 | 18.6630 |
120
+ | 27.1786 | 68.5714 | 69 | 18.4899 |
121
+ | 26.8166 | 69.5714 | 70 | 18.3193 |
122
+ | 26.5479 | 70.5714 | 71 | 18.1547 |
123
+ | 26.083 | 71.5714 | 72 | 17.9942 |
124
+ | 26.2608 | 72.5714 | 73 | 17.8381 |
125
+ | 26.4425 | 73.5714 | 74 | 17.6867 |
126
+ | 25.715 | 74.5714 | 75 | 17.5401 |
127
+ | 25.3579 | 75.5714 | 76 | 17.3974 |
128
+ | 25.4759 | 76.5714 | 77 | 17.2583 |
129
+ | 25.494 | 77.5714 | 78 | 17.1240 |
130
+ | 25.2856 | 78.5714 | 79 | 16.9947 |
131
+ | 24.9815 | 79.5714 | 80 | 16.8690 |
132
+ | 25.0225 | 80.5714 | 81 | 16.7476 |
133
+ | 24.868 | 81.5714 | 82 | 16.6309 |
134
+ | 24.7249 | 82.5714 | 83 | 16.5196 |
135
+ | 24.446 | 83.5714 | 84 | 16.4145 |
136
+ | 24.7399 | 84.5714 | 85 | 16.3154 |
137
+ | 24.1898 | 85.5714 | 86 | 16.2216 |
138
+ | 24.451 | 86.5714 | 87 | 16.1322 |
139
+ | 24.1094 | 87.5714 | 88 | 16.0485 |
140
+ | 23.9994 | 88.5714 | 89 | 15.9708 |
141
+ | 23.7422 | 89.5714 | 90 | 15.8995 |
142
+ | 23.967 | 90.5714 | 91 | 15.8342 |
143
+ | 23.7289 | 91.5714 | 92 | 15.7749 |
144
+ | 23.5241 | 92.5714 | 93 | 15.7217 |
145
+ | 23.5077 | 93.5714 | 94 | 15.6754 |
146
+ | 23.7215 | 94.5714 | 95 | 15.6356 |
147
+ | 23.5504 | 95.5714 | 96 | 15.6024 |
148
+ | 23.4054 | 96.5714 | 97 | 15.5761 |
149
+ | 23.4654 | 97.5714 | 98 | 15.5563 |
150
+ | 23.3449 | 98.5714 | 99 | 15.5431 |
151
+ | 23.5244 | 99.5714 | 100 | 15.5366 |
152
+
153
+
154
+ ### Framework versions
155
+
156
+ - Transformers 4.48.3
157
+ - Pytorch 2.5.1+cu124
158
+ - Datasets 3.3.0
159
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.48.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
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": "4.48.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658fe126de3aff1db7948e1191610f24e9e043bd78e658041ffd0444f5117bac
3
+ size 990345064
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b48a7b05b84c5aaea40f37f4b8716d1ec376635b9b47010b9e5e30e46035b19
3
+ size 5368