Hugging Face's logo

aruca
/
pegasus_x-meeting-summarizer-gpt3.5

Text2Text Generation
Transformers
TensorBoard
Safetensors
pegasus_x
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
aruca commited on
Commit
219cd0a
•
1 Parent(s): d56ac9f

End of training

Browse files
Files changed (6) hide show
  1. README.md +58 -58
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Mar07_11-28-21_dd6894533b8d/events.out.tfevents.1709810901.dd6894533b8d.494.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.6064
18
 
19
  ## Model description
20
 
@@ -47,67 +47,67 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3.7528 | 0.05 | 10 | 2.5788 |
51
- | 2.7466 | 0.11 | 20 | 2.2694 |
52
- | 2.4032 | 0.16 | 30 | 2.1298 |
53
- | 2.3188 | 0.21 | 40 | 2.0389 |
54
- | 2.1827 | 0.27 | 50 | 1.9788 |
55
- | 2.1284 | 0.32 | 60 | 1.9291 |
56
- | 2.1275 | 0.37 | 70 | 1.9024 |
57
- | 2.0536 | 0.43 | 80 | 1.8587 |
58
- | 1.9901 | 0.48 | 90 | 1.8407 |
59
- | 1.9769 | 0.53 | 100 | 1.8211 |
60
- | 1.9643 | 0.59 | 110 | 1.8048 |
61
- | 1.8846 | 0.64 | 120 | 1.7921 |
62
- | 1.9294 | 0.69 | 130 | 1.7837 |
63
- | 1.903 | 0.75 | 140 | 1.7664 |
64
- | 1.9329 | 0.8 | 150 | 1.7606 |
65
- | 1.865 | 0.85 | 160 | 1.7493 |
66
- | 1.8414 | 0.91 | 170 | 1.7404 |
67
- | 1.8793 | 0.96 | 180 | 1.7310 |
68
- | 1.8519 | 1.01 | 190 | 1.7165 |
69
- | 1.7918 | 1.07 | 200 | 1.7132 |
70
- | 1.7815 | 1.12 | 210 | 1.7087 |
71
- | 1.7503 | 1.17 | 220 | 1.7019 |
72
- | 1.7545 | 1.23 | 230 | 1.6937 |
73
- | 1.7088 | 1.28 | 240 | 1.6905 |
74
- | 1.7231 | 1.33 | 250 | 1.6862 |
75
- | 1.7584 | 1.39 | 260 | 1.6807 |
76
- | 1.7537 | 1.44 | 270 | 1.6762 |
77
- | 1.7867 | 1.49 | 280 | 1.6685 |
78
- | 1.7666 | 1.55 | 290 | 1.6642 |
79
- | 1.7076 | 1.6 | 300 | 1.6580 |
80
- | 1.6894 | 1.65 | 310 | 1.6596 |
81
- | 1.7207 | 1.71 | 320 | 1.6535 |
82
- | 1.6743 | 1.76 | 330 | 1.6565 |
83
- | 1.7197 | 1.81 | 340 | 1.6491 |
84
- | 1.7027 | 1.87 | 350 | 1.6438 |
85
- | 1.7161 | 1.92 | 360 | 1.6388 |
86
- | 1.7256 | 1.97 | 370 | 1.6368 |
87
- | 1.6623 | 2.03 | 380 | 1.6370 |
88
- | 1.6041 | 2.08 | 390 | 1.6402 |
89
- | 1.6308 | 2.13 | 400 | 1.6289 |
90
- | 1.6384 | 2.19 | 410 | 1.6333 |
91
- | 1.6223 | 2.24 | 420 | 1.6291 |
92
- | 1.6163 | 2.29 | 430 | 1.6212 |
93
- | 1.6232 | 2.35 | 440 | 1.6267 |
94
- | 1.6081 | 2.4 | 450 | 1.6302 |
95
- | 1.619 | 2.45 | 460 | 1.6196 |
96
- | 1.5802 | 2.51 | 470 | 1.6215 |
97
- | 1.6313 | 2.56 | 480 | 1.6216 |
98
- | 1.5968 | 2.61 | 490 | 1.6153 |
99
- | 1.589 | 2.67 | 500 | 1.6137 |
100
- | 1.6087 | 2.72 | 510 | 1.6129 |
101
- | 1.5614 | 2.77 | 520 | 1.6085 |
102
- | 1.6109 | 2.83 | 530 | 1.6067 |
103
- | 1.596 | 2.88 | 540 | 1.6097 |
104
- | 1.6343 | 2.93 | 550 | 1.5979 |
105
- | 1.5774 | 2.99 | 560 | 1.6064 |
106
 
107
 
108
  ### Framework versions
109
 
110
- - Transformers 4.38.1
111
  - Pytorch 2.1.0+cu121
112
  - Datasets 2.18.0
113
  - Tokenizers 0.15.2
 
14
 
15
  This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.3143
18
 
19
  ## Model description
20
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 3.5583 | 0.05 | 10 | 2.3912 |
51
+ | 2.5255 | 0.11 | 20 | 2.0221 |
52
+ | 2.1546 | 0.16 | 30 | 1.8584 |
53
+ | 2.0147 | 0.21 | 40 | 1.7538 |
54
+ | 1.9291 | 0.27 | 50 | 1.6817 |
55
+ | 1.8566 | 0.32 | 60 | 1.6424 |
56
+ | 1.8325 | 0.37 | 70 | 1.6027 |
57
+ | 1.7709 | 0.43 | 80 | 1.5801 |
58
+ | 1.7153 | 0.48 | 90 | 1.5569 |
59
+ | 1.6983 | 0.53 | 100 | 1.5337 |
60
+ | 1.6936 | 0.59 | 110 | 1.5292 |
61
+ | 1.6254 | 0.64 | 120 | 1.5039 |
62
+ | 1.629 | 0.69 | 130 | 1.4861 |
63
+ | 1.6537 | 0.75 | 140 | 1.4684 |
64
+ | 1.6449 | 0.8 | 150 | 1.4621 |
65
+ | 1.5916 | 0.85 | 160 | 1.4497 |
66
+ | 1.5764 | 0.91 | 170 | 1.4385 |
67
+ | 1.5899 | 0.96 | 180 | 1.4406 |
68
+ | 1.5556 | 1.01 | 190 | 1.4307 |
69
+ | 1.4869 | 1.07 | 200 | 1.4263 |
70
+ | 1.482 | 1.12 | 210 | 1.4156 |
71
+ | 1.486 | 1.17 | 220 | 1.4109 |
72
+ | 1.4407 | 1.23 | 230 | 1.4092 |
73
+ | 1.4183 | 1.28 | 240 | 1.4010 |
74
+ | 1.4226 | 1.33 | 250 | 1.3988 |
75
+ | 1.4611 | 1.39 | 260 | 1.3917 |
76
+ | 1.4823 | 1.44 | 270 | 1.3881 |
77
+ | 1.4877 | 1.49 | 280 | 1.3800 |
78
+ | 1.464 | 1.55 | 290 | 1.3799 |
79
+ | 1.4327 | 1.6 | 300 | 1.3712 |
80
+ | 1.4189 | 1.65 | 310 | 1.3725 |
81
+ | 1.495 | 1.71 | 320 | 1.3649 |
82
+ | 1.387 | 1.76 | 330 | 1.3640 |
83
+ | 1.4308 | 1.81 | 340 | 1.3595 |
84
+ | 1.4045 | 1.87 | 350 | 1.3547 |
85
+ | 1.4227 | 1.92 | 360 | 1.3549 |
86
+ | 1.444 | 1.97 | 370 | 1.3487 |
87
+ | 1.3747 | 2.03 | 380 | 1.3467 |
88
+ | 1.3504 | 2.08 | 390 | 1.3530 |
89
+ | 1.3493 | 2.13 | 400 | 1.3438 |
90
+ | 1.3099 | 2.19 | 410 | 1.3494 |
91
+ | 1.3484 | 2.24 | 420 | 1.3374 |
92
+ | 1.3541 | 2.29 | 430 | 1.3343 |
93
+ | 1.3044 | 2.35 | 440 | 1.3383 |
94
+ | 1.3457 | 2.4 | 450 | 1.3373 |
95
+ | 1.3017 | 2.45 | 460 | 1.3291 |
96
+ | 1.2956 | 2.51 | 470 | 1.3289 |
97
+ | 1.322 | 2.56 | 480 | 1.3300 |
98
+ | 1.3219 | 2.61 | 490 | 1.3211 |
99
+ | 1.3026 | 2.67 | 500 | 1.3254 |
100
+ | 1.3183 | 2.72 | 510 | 1.3191 |
101
+ | 1.2709 | 2.77 | 520 | 1.3160 |
102
+ | 1.303 | 2.83 | 530 | 1.3141 |
103
+ | 1.2857 | 2.88 | 540 | 1.3189 |
104
+ | 1.3126 | 2.93 | 550 | 1.3082 |
105
+ | 1.3053 | 2.99 | 560 | 1.3143 |
106
 
107
 
108
  ### Framework versions
109
 
110
+ - Transformers 4.38.2
111
  - Pytorch 2.1.0+cu121
112
  - Datasets 2.18.0
113
  - Tokenizers 0.15.2
config.json CHANGED
@@ -54,7 +54,7 @@
54
  "stagger_local_blocks": true,
55
  "static_position_embeddings": true,
56
  "torch_dtype": "float32",
57
- "transformers_version": "4.38.1",
58
  "use_cache": true,
59
  "vocab_size": 96103
60
  }
 
54
  "stagger_local_blocks": true,
55
  "static_position_embeddings": true,
56
  "torch_dtype": "float32",
57
+ "transformers_version": "4.38.2",
58
  "use_cache": true,
59
  "vocab_size": 96103
60
  }
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  "max_length": 16384,
9
  "num_beams": 8,
10
  "pad_token_id": 0,
11
- "transformers_version": "4.38.1"
12
  }
 
8
  "max_length": 16384,
9
  "num_beams": 8,
10
  "pad_token_id": 0,
11
+ "transformers_version": "4.38.2"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee8580e5261e11ba2ac78ee1ab3f7e36ad743dc3dec0745845561f8b084e832d
3
  size 1089213696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9bbd4e5a909d19cacab038929226c859d711967f94fe63fbe231de11da5cdc
3
  size 1089213696
runs/Mar07_11-28-21_dd6894533b8d/events.out.tfevents.1709810901.dd6894533b8d.494.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8d07cb4fbbc965d712ced8238f22381762010326337465120e85bc94ae1063
3
+ size 32721
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:109373ae87a3ec4d7ef93a8aa3affc231a05d6f6c24be8d853b0d0807d4075fb
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a047579681a9084ff70c1e98fdf6a82fdad158447da9676ce53258c1da2488
3
  size 4920