jvalline commited on
Commit
23d68df
·
verified ·
1 Parent(s): 9d8cf90

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. README.md +12 -70
  2. config.json +6 -6
  3. model.safetensors +2 -2
  4. special_tokens_map.json +3 -21
  5. tokenizer.json +1 -6
  6. training_args.bin +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: t5-small
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # randomization_model
18
 
19
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.2271
22
  - Bleu: 0.0001
23
  - Accuracy: 0.0
24
- - Gen Len: 18.997
25
 
26
  ## Model description
27
 
@@ -41,83 +41,25 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
- - train_batch_size: 10
45
- - eval_batch_size: 10
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 3
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Accuracy | Gen Len |
55
- |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:-------:|
56
- | 6.7713 | 0.05 | 50 | 4.1342 | 0.0 | 0.0 | 19.0 |
57
- | 4.0962 | 0.1 | 100 | 3.6084 | 0.0 | 0.0 | 19.0 |
58
- | 3.7511 | 0.15 | 150 | 3.3793 | 0.0 | 0.0 | 18.99 |
59
- | 3.6618 | 0.2 | 200 | 3.2099 | 0.0 | 0.0 | 18.9845 |
60
- | 3.5055 | 0.25 | 250 | 3.0655 | 0.0 | 0.0 | 18.9845 |
61
- | 3.4285 | 0.3 | 300 | 2.9465 | 0.0 | 0.0 | 18.986 |
62
- | 3.323 | 0.35 | 350 | 2.8558 | 0.0 | 0.0 | 18.982 |
63
- | 3.257 | 0.4 | 400 | 2.7828 | 0.0 | 0.0 | 18.9845 |
64
- | 3.2148 | 0.45 | 450 | 2.7311 | 0.0 | 0.0 | 18.9915 |
65
- | 3.1964 | 0.5 | 500 | 2.6861 | 0.0 | 0.0 | 18.9905 |
66
- | 3.108 | 0.55 | 550 | 2.6446 | 0.0 | 0.0 | 18.9905 |
67
- | 3.0801 | 0.6 | 600 | 2.6087 | 0.0 | 0.0 | 18.9925 |
68
- | 3.0439 | 0.65 | 650 | 2.5770 | 0.0 | 0.0 | 18.9915 |
69
- | 3.0683 | 0.7 | 700 | 2.5504 | 0.0 | 0.0 | 18.9955 |
70
- | 3.0283 | 0.75 | 750 | 2.5223 | 0.0 | 0.0 | 18.9955 |
71
- | 3.0292 | 0.8 | 800 | 2.5003 | 0.0 | 0.0 | 18.9935 |
72
- | 2.9533 | 0.85 | 850 | 2.4797 | 0.0 | 0.0 | 18.9965 |
73
- | 3.006 | 0.9 | 900 | 2.4627 | 0.0 | 0.0 | 19.0 |
74
- | 2.9028 | 0.95 | 950 | 2.4463 | 0.0 | 0.0 | 18.997 |
75
- | 2.9219 | 1.0 | 1000 | 2.4287 | 0.0 | 0.0 | 18.996 |
76
- | 2.8995 | 1.05 | 1050 | 2.4120 | 0.0 | 0.0 | 18.9995 |
77
- | 2.8857 | 1.1 | 1100 | 2.3988 | 0.0 | 0.0 | 19.0 |
78
- | 2.8971 | 1.15 | 1150 | 2.3861 | 0.0 | 0.0 | 18.998 |
79
- | 2.8882 | 1.2 | 1200 | 2.3747 | 0.0 | 0.0 | 18.998 |
80
- | 2.8425 | 1.25 | 1250 | 2.3632 | 0.0 | 0.0 | 18.998 |
81
- | 2.865 | 1.3 | 1300 | 2.3544 | 0.0 | 0.0 | 18.998 |
82
- | 2.8245 | 1.35 | 1350 | 2.3440 | 0.0 | 0.0 | 18.998 |
83
- | 2.8208 | 1.4 | 1400 | 2.3373 | 0.0 | 0.0 | 18.998 |
84
- | 2.8397 | 1.45 | 1450 | 2.3286 | 0.0 | 0.0 | 18.998 |
85
- | 2.8103 | 1.5 | 1500 | 2.3203 | 0.0 | 0.0 | 18.998 |
86
- | 2.82 | 1.55 | 1550 | 2.3133 | 0.0 | 0.0 | 18.9995 |
87
- | 2.7653 | 1.6 | 1600 | 2.3058 | 0.0 | 0.0 | 18.998 |
88
- | 2.7945 | 1.65 | 1650 | 2.2998 | 0.0 | 0.0 | 18.998 |
89
- | 2.7758 | 1.7 | 1700 | 2.2940 | 0.0001 | 0.0 | 18.998 |
90
- | 2.8035 | 1.75 | 1750 | 2.2886 | 0.0001 | 0.0 | 18.998 |
91
- | 2.8045 | 1.8 | 1800 | 2.2827 | 0.0001 | 0.0 | 18.998 |
92
- | 2.7667 | 1.85 | 1850 | 2.2777 | 0.0001 | 0.0 | 18.9965 |
93
- | 2.7792 | 1.9 | 1900 | 2.2730 | 0.0001 | 0.0 | 18.9965 |
94
- | 2.7337 | 1.95 | 1950 | 2.2683 | 0.0001 | 0.0 | 18.9965 |
95
- | 2.7634 | 2.0 | 2000 | 2.2647 | 0.0001 | 0.0 | 18.9965 |
96
- | 2.7357 | 2.05 | 2050 | 2.2607 | 0.0001 | 0.0 | 18.998 |
97
- | 2.7261 | 2.1 | 2100 | 2.2569 | 0.0001 | 0.0 | 18.998 |
98
- | 2.7827 | 2.15 | 2150 | 2.2539 | 0.0001 | 0.0 | 18.998 |
99
- | 2.7363 | 2.2 | 2200 | 2.2509 | 0.0001 | 0.0 | 18.998 |
100
- | 2.7647 | 2.25 | 2250 | 2.2480 | 0.0001 | 0.0 | 18.998 |
101
- | 2.737 | 2.3 | 2300 | 2.2449 | 0.0001 | 0.0 | 18.998 |
102
- | 2.72 | 2.35 | 2350 | 2.2422 | 0.0001 | 0.0 | 18.998 |
103
- | 2.7312 | 2.4 | 2400 | 2.2403 | 0.0001 | 0.0 | 18.998 |
104
- | 2.7345 | 2.45 | 2450 | 2.2382 | 0.0001 | 0.0 | 18.998 |
105
- | 2.6951 | 2.5 | 2500 | 2.2363 | 0.0001 | 0.0 | 18.998 |
106
- | 2.7591 | 2.55 | 2550 | 2.2349 | 0.0001 | 0.0 | 18.998 |
107
- | 2.7018 | 2.6 | 2600 | 2.2333 | 0.0001 | 0.0 | 18.998 |
108
- | 2.6993 | 2.65 | 2650 | 2.2321 | 0.0001 | 0.0 | 18.998 |
109
- | 2.7006 | 2.7 | 2700 | 2.2309 | 0.0001 | 0.0 | 18.998 |
110
- | 2.6694 | 2.75 | 2750 | 2.2296 | 0.0001 | 0.0 | 18.998 |
111
- | 2.7018 | 2.8 | 2800 | 2.2287 | 0.0001 | 0.0 | 18.998 |
112
- | 2.7285 | 2.85 | 2850 | 2.2281 | 0.0001 | 0.0 | 18.998 |
113
- | 2.6873 | 2.9 | 2900 | 2.2276 | 0.0001 | 0.0 | 18.997 |
114
- | 2.7121 | 2.95 | 2950 | 2.2273 | 0.0001 | 0.0 | 18.997 |
115
- | 2.7176 | 3.0 | 3000 | 2.2271 | 0.0001 | 0.0 | 18.997 |
116
 
117
 
118
  ### Framework versions
119
 
120
  - Transformers 4.37.1
121
- - Pytorch 2.1.0+cu121
122
  - Datasets 2.16.1
123
  - Tokenizers 0.15.1
 
1
  ---
2
  license: apache-2.0
3
+ base_model: t5-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
16
 
17
  # randomization_model
18
 
19
+ This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1397
22
  - Bleu: 0.0001
23
  - Accuracy: 0.0
24
+ - Gen Len: 18.9987
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 2
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Accuracy | Gen Len |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|:-------:|
56
+ | 0.2127 | 1.0 | 6250 | 0.1517 | 0.0001 | 0.0 | 18.9987 |
57
+ | 0.1844 | 2.0 | 12500 | 0.1397 | 0.0001 | 0.0 | 18.9987 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 4.37.1
63
+ - Pytorch 2.3.0.dev20240122+cu121
64
  - Datasets 2.16.1
65
  - Tokenizers 0.15.1
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
  "d_kv": 64,
9
- "d_model": 512,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 6,
22
- "num_heads": 8,
23
- "num_layers": 6,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
  "d_kv": 64,
9
+ "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
 
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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9de13f573190168dd8af8e2178fa752d35f9e9f73a2b2c2587ee0f4cafd9002
3
- size 242041896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60d986a1f82f878dd2be5f422d6e3156ed191fbc6a9ccf3309626fc1639e961
3
+ size 891644712
special_tokens_map.json CHANGED
@@ -101,25 +101,7 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": {
105
- "content": "</s>",
106
- "lstrip": false,
107
- "normalized": false,
108
- "rstrip": false,
109
- "single_word": false
110
- },
111
- "pad_token": {
112
- "content": "<pad>",
113
- "lstrip": false,
114
- "normalized": false,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "unk_token": {
119
- "content": "<unk>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false
124
- }
125
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e51819030c3ee068bcccae76b550e921a016437505c7fae8065b0ca02f9bedea
3
- size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d6b5ce9f23e446f662744be068c8fe580a40206247ec914bcd6fc838d79796
3
+ size 4920