Hugging Face's logo

mika5883
/
MT5_large_A_art

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
mika5883 commited on
Commit
400b001
·
verified ·
1 Parent(s): c8a3784

mt5_A_v1

Browse files
Files changed (5) hide show
  1. README.md +93 -0
  2. generation_config.json +8 -0
  3. model.safetensors +1 -1
  4. runs/Apr20_14-00-16_g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585/events.out.tfevents.1745157618.g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585.26688.0 +2 -2
  5. runs/Apr20_14-00-16_g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585/events.out.tfevents.1745171965.g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585.26688.1 +3 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: ai-forever/sage-mt5-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: MT5_large_A_art
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
+ # MT5_large_A_art
16
+
17
+ This model is a fine-tuned version of [ai-forever/sage-mt5-large](https://huggingface.co/ai-forever/sage-mt5-large) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2006
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: 3.83229e-05
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 64
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 3300
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.9979 | 0.0303 | 100 | 0.2649 |
54
+ | 0.5176 | 0.0606 | 200 | 0.2170 |
55
+ | 0.3916 | 0.0909 | 300 | 0.1973 |
56
+ | 0.3356 | 0.1212 | 400 | 0.1928 |
57
+ | 0.2993 | 0.1515 | 500 | 0.1937 |
58
+ | 0.2783 | 0.1818 | 600 | 0.1919 |
59
+ | 0.268 | 0.2121 | 700 | 0.1907 |
60
+ | 0.2697 | 0.2424 | 800 | 0.1914 |
61
+ | 0.2491 | 0.2726 | 900 | 0.1901 |
62
+ | 0.2488 | 0.3029 | 1000 | 0.1888 |
63
+ | 0.238 | 0.3332 | 1100 | 0.1861 |
64
+ | 0.2414 | 0.3635 | 1200 | 0.1872 |
65
+ | 0.2378 | 0.3938 | 1300 | 0.1857 |
66
+ | 0.2286 | 0.4241 | 1400 | 0.1842 |
67
+ | 0.2201 | 0.4544 | 1500 | 0.1849 |
68
+ | 0.2217 | 0.4847 | 1600 | 0.1845 |
69
+ | 0.2195 | 0.5150 | 1700 | 0.1835 |
70
+ | 0.2137 | 0.5453 | 1800 | 0.1818 |
71
+ | 0.2147 | 0.5756 | 1900 | 0.1822 |
72
+ | 0.2246 | 0.6059 | 2000 | 0.1806 |
73
+ | 0.2151 | 0.6362 | 2100 | 0.1806 |
74
+ | 0.2179 | 0.6665 | 2200 | 0.1805 |
75
+ | 0.2219 | 0.6968 | 2300 | 0.1806 |
76
+ | 0.2126 | 0.7271 | 2400 | 0.1808 |
77
+ | 0.2149 | 0.7573 | 2500 | 0.1802 |
78
+ | 0.2137 | 0.7876 | 2600 | 0.1806 |
79
+ | 0.2146 | 0.8179 | 2700 | 0.1803 |
80
+ | 0.2078 | 0.8482 | 2800 | 0.1803 |
81
+ | 0.2084 | 0.8785 | 2900 | 0.1805 |
82
+ | 0.2153 | 0.9088 | 3000 | 0.1801 |
83
+ | 0.2134 | 0.9391 | 3100 | 0.1799 |
84
+ | 0.2169 | 0.9694 | 3200 | 0.1799 |
85
+ | 0.2181 | 0.9997 | 3300 | 0.1799 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.48.1
91
+ - Pytorch 2.5.1+cu124
92
+ - Datasets 3.0.1
93
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "max_length": 256,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.48.1"
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6faefeb67578541f8bbe8e8d4a89a19bf207b03b306ae2ad7fa65a6d09b3a3c6
3
  size 4918393736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ffa54762df49affe05a53b6ef5b5a47012f38a361c828f3147b3ac4e25b7e71
3
  size 4918393736
runs/Apr20_14-00-16_g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585/events.out.tfevents.1745157618.g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585.26688.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5f6709340d82b51bee3a52b3ec99e537b8ab129a36780ae1c25c6fbf6ae0468
3
- size 17488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e762b5ab0c70d506026074b2eb30b863cb46ccb0f9ffec53ef33c3d95df716
3
+ size 21698
runs/Apr20_14-00-16_g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585/events.out.tfevents.1745171965.g21-b5c2fce8-3b68-327d-ad5b-a53ce6085585.26688.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340af32027090a61731473e1d1ec16525f9a8b82fc17dc240f3dd198306a4d0d
3
+ size 359