Hugging Face's logo

Shakhovak
/
flan-t5-base-absa-joint

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Shakhovak commited on
Commit
7bfaff4
•
1 Parent(s): bfadae1

End of training

Browse files
Files changed (4) hide show
  1. README.md +9 -22
  2. model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1955
19
 
20
  ## Model description
21
 
@@ -41,36 +41,23 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_ratio: 0.1
44
- - num_epochs: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3.0955 | 0.26 | 100 | 0.6148 |
51
- | 0.6658 | 0.52 | 200 | 0.3579 |
52
- | 0.4605 | 0.79 | 300 | 0.2902 |
53
- | 0.4011 | 1.05 | 400 | 0.2537 |
54
- | 0.3489 | 1.31 | 500 | 0.2344 |
55
- | 0.3543 | 1.57 | 600 | 0.2339 |
56
- | 0.3223 | 1.84 | 700 | 0.2214 |
57
- | 0.2887 | 2.1 | 800 | 0.2132 |
58
- | 0.2823 | 2.36 | 900 | 0.2036 |
59
- | 0.2691 | 2.62 | 1000 | 0.2044 |
60
- | 0.2615 | 2.89 | 1100 | 0.1978 |
61
- | 0.2429 | 3.15 | 1200 | 0.1966 |
62
- | 0.2253 | 3.41 | 1300 | 0.1975 |
63
- | 0.2274 | 3.67 | 1400 | 0.1916 |
64
- | 0.2354 | 3.94 | 1500 | 0.1925 |
65
- | 0.2025 | 4.2 | 1600 | 0.1956 |
66
- | 0.1988 | 4.46 | 1700 | 0.1956 |
67
- | 0.2216 | 4.72 | 1800 | 0.1962 |
68
- | 0.2082 | 4.99 | 1900 | 0.1955 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.38.2
74
- - Pytorch 2.0.1+cu118
75
  - Datasets 2.18.0
76
  - Tokenizers 0.15.2
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2208
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_ratio: 0.1
44
+ - num_epochs: 3
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 1.6993 | 0.45 | 200 | 0.3259 |
51
+ | 0.4165 | 0.9 | 400 | 0.2624 |
52
+ | 0.3401 | 1.35 | 600 | 0.2353 |
53
+ | 0.2937 | 1.8 | 800 | 0.2160 |
54
+ | 0.2655 | 2.25 | 1000 | 0.2244 |
55
+ | 0.2427 | 2.7 | 1200 | 0.2208 |
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
59
 
60
  - Transformers 4.38.2
61
+ - Pytorch 2.2.1+cu121
62
  - Datasets 2.18.0
63
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:123e5660ee007ebf3b7f40c4cde40d578ae4d370ed8b523f312419163fac4923
3
  size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b019a40f9f32687fd74cba0bf640d3da7fad44cd4750ed03c2389a69a3501c60
3
  size 990345064
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 88,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 88
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 89,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 89
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae06d4a295447b79162c0e09b99d069c6c7691c73ba2f1c07b2843d84064acd0
3
- size 4667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0367e46bf3e8bea1456b28a3f9b13dcbf6d25654b455fd12a1d630b7db7d5438
3
+ size 5112