End of training
Browse files- README.md +102 -7
- adapter_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [Aharneish/gpt2-spiritual](https://huggingface.co/Aharneish/gpt2-spiritual) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
- eval_runtime: 2.5023
|
20 |
-
- eval_samples_per_second: 335.285
|
21 |
-
- eval_steps_per_second: 10.79
|
22 |
-
- epoch: 72.03
|
23 |
-
- step: 17000
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,7 +34,7 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate:
|
43 |
- train_batch_size: 32
|
44 |
- eval_batch_size: 32
|
45 |
- seed: 42
|
@@ -47,6 +42,106 @@ The following hyperparameters were used during training:
|
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 200
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
### Framework versions
|
51 |
|
52 |
- Transformers 4.34.0
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [Aharneish/gpt2-spiritual](https://huggingface.co/Aharneish/gpt2-spiritual) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6818
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-05
|
38 |
- train_batch_size: 32
|
39 |
- eval_batch_size: 32
|
40 |
- seed: 42
|
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 200
|
44 |
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
49 |
+
| 2.489 | 2.12 | 500 | 1.9065 |
|
50 |
+
| 2.2722 | 4.24 | 1000 | 1.6764 |
|
51 |
+
| 2.1401 | 6.36 | 1500 | 1.5225 |
|
52 |
+
| 2.0433 | 8.47 | 2000 | 1.3953 |
|
53 |
+
| 1.9827 | 10.59 | 2500 | 1.3053 |
|
54 |
+
| 1.9249 | 12.71 | 3000 | 1.2289 |
|
55 |
+
| 1.8814 | 14.83 | 3500 | 1.1599 |
|
56 |
+
| 1.8562 | 16.95 | 4000 | 1.1164 |
|
57 |
+
| 1.8285 | 19.07 | 4500 | 1.0753 |
|
58 |
+
| 1.8037 | 21.19 | 5000 | 1.0442 |
|
59 |
+
| 1.7835 | 23.31 | 5500 | 1.0104 |
|
60 |
+
| 1.7675 | 25.42 | 6000 | 0.9916 |
|
61 |
+
| 1.7554 | 27.54 | 6500 | 0.9726 |
|
62 |
+
| 1.7389 | 29.66 | 7000 | 0.9672 |
|
63 |
+
| 1.7284 | 31.78 | 7500 | 0.9443 |
|
64 |
+
| 1.7196 | 33.9 | 8000 | 0.9335 |
|
65 |
+
| 1.7104 | 36.02 | 8500 | 0.9153 |
|
66 |
+
| 1.7013 | 38.14 | 9000 | 0.9058 |
|
67 |
+
| 1.6862 | 40.25 | 9500 | 0.8875 |
|
68 |
+
| 1.6828 | 42.37 | 10000 | 0.8942 |
|
69 |
+
| 1.6779 | 44.49 | 10500 | 0.8804 |
|
70 |
+
| 1.67 | 46.61 | 11000 | 0.8699 |
|
71 |
+
| 1.6648 | 48.73 | 11500 | 0.8617 |
|
72 |
+
| 1.6576 | 50.85 | 12000 | 0.8481 |
|
73 |
+
| 1.6506 | 52.97 | 12500 | 0.8562 |
|
74 |
+
| 1.647 | 55.08 | 13000 | 0.8444 |
|
75 |
+
| 1.6382 | 57.2 | 13500 | 0.8349 |
|
76 |
+
| 1.6401 | 59.32 | 14000 | 0.8380 |
|
77 |
+
| 1.6304 | 61.44 | 14500 | 0.8254 |
|
78 |
+
| 1.6283 | 63.56 | 15000 | 0.8234 |
|
79 |
+
| 1.6159 | 65.68 | 15500 | 0.8119 |
|
80 |
+
| 1.622 | 67.8 | 16000 | 0.8119 |
|
81 |
+
| 1.6146 | 69.92 | 16500 | 0.8091 |
|
82 |
+
| 1.6101 | 72.03 | 17000 | 0.8034 |
|
83 |
+
| 1.6049 | 74.15 | 17500 | 0.7934 |
|
84 |
+
| 1.5976 | 76.27 | 18000 | 0.7905 |
|
85 |
+
| 1.5949 | 78.39 | 18500 | 0.7883 |
|
86 |
+
| 1.5907 | 80.51 | 19000 | 0.7874 |
|
87 |
+
| 1.5952 | 82.63 | 19500 | 0.7869 |
|
88 |
+
| 1.5843 | 84.75 | 20000 | 0.7811 |
|
89 |
+
| 1.5857 | 86.86 | 20500 | 0.7793 |
|
90 |
+
| 1.5813 | 88.98 | 21000 | 0.7725 |
|
91 |
+
| 1.5753 | 91.1 | 21500 | 0.7727 |
|
92 |
+
| 1.5725 | 93.22 | 22000 | 0.7663 |
|
93 |
+
| 1.5687 | 95.34 | 22500 | 0.7643 |
|
94 |
+
| 1.5696 | 97.46 | 23000 | 0.7667 |
|
95 |
+
| 1.5605 | 99.58 | 23500 | 0.7615 |
|
96 |
+
| 1.5681 | 101.69 | 24000 | 0.7581 |
|
97 |
+
| 1.5587 | 103.81 | 24500 | 0.7563 |
|
98 |
+
| 1.5573 | 105.93 | 25000 | 0.7559 |
|
99 |
+
| 1.5532 | 108.05 | 25500 | 0.7482 |
|
100 |
+
| 1.5488 | 110.17 | 26000 | 0.7496 |
|
101 |
+
| 1.5468 | 112.29 | 26500 | 0.7440 |
|
102 |
+
| 1.5496 | 114.41 | 27000 | 0.7427 |
|
103 |
+
| 1.5471 | 116.53 | 27500 | 0.7449 |
|
104 |
+
| 1.5367 | 118.64 | 28000 | 0.7405 |
|
105 |
+
| 1.5375 | 120.76 | 28500 | 0.7368 |
|
106 |
+
| 1.5362 | 122.88 | 29000 | 0.7302 |
|
107 |
+
| 1.5347 | 125.0 | 29500 | 0.7294 |
|
108 |
+
| 1.5309 | 127.12 | 30000 | 0.7306 |
|
109 |
+
| 1.5267 | 129.24 | 30500 | 0.7240 |
|
110 |
+
| 1.5289 | 131.36 | 31000 | 0.7288 |
|
111 |
+
| 1.523 | 133.47 | 31500 | 0.7268 |
|
112 |
+
| 1.5197 | 135.59 | 32000 | 0.7200 |
|
113 |
+
| 1.5184 | 137.71 | 32500 | 0.7192 |
|
114 |
+
| 1.5188 | 139.83 | 33000 | 0.7140 |
|
115 |
+
| 1.5161 | 141.95 | 33500 | 0.7182 |
|
116 |
+
| 1.5156 | 144.07 | 34000 | 0.7136 |
|
117 |
+
| 1.5066 | 146.19 | 34500 | 0.7079 |
|
118 |
+
| 1.5063 | 148.31 | 35000 | 0.7099 |
|
119 |
+
| 1.5103 | 150.42 | 35500 | 0.7099 |
|
120 |
+
| 1.5046 | 152.54 | 36000 | 0.7059 |
|
121 |
+
| 1.503 | 154.66 | 36500 | 0.7057 |
|
122 |
+
| 1.5005 | 156.78 | 37000 | 0.7026 |
|
123 |
+
| 1.4998 | 158.9 | 37500 | 0.7014 |
|
124 |
+
| 1.4989 | 161.02 | 38000 | 0.6996 |
|
125 |
+
| 1.4931 | 163.14 | 38500 | 0.6997 |
|
126 |
+
| 1.4915 | 165.25 | 39000 | 0.6957 |
|
127 |
+
| 1.489 | 167.37 | 39500 | 0.6974 |
|
128 |
+
| 1.4906 | 169.49 | 40000 | 0.6969 |
|
129 |
+
| 1.4859 | 171.61 | 40500 | 0.6956 |
|
130 |
+
| 1.4881 | 173.73 | 41000 | 0.6921 |
|
131 |
+
| 1.4836 | 175.85 | 41500 | 0.6928 |
|
132 |
+
| 1.4818 | 177.97 | 42000 | 0.6901 |
|
133 |
+
| 1.482 | 180.08 | 42500 | 0.6912 |
|
134 |
+
| 1.4778 | 182.2 | 43000 | 0.6885 |
|
135 |
+
| 1.4763 | 184.32 | 43500 | 0.6885 |
|
136 |
+
| 1.4807 | 186.44 | 44000 | 0.6848 |
|
137 |
+
| 1.474 | 188.56 | 44500 | 0.6833 |
|
138 |
+
| 1.4712 | 190.68 | 45000 | 0.6829 |
|
139 |
+
| 1.4715 | 192.8 | 45500 | 0.6826 |
|
140 |
+
| 1.4682 | 194.92 | 46000 | 0.6831 |
|
141 |
+
| 1.4706 | 197.03 | 46500 | 0.6819 |
|
142 |
+
| 1.4674 | 199.15 | 47000 | 0.6818 |
|
143 |
+
|
144 |
+
|
145 |
### Framework versions
|
146 |
|
147 |
- Transformers 4.34.0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2367673
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:329f8fbc351b7cf1dd372933782553d8b549854ddc056efc7be162a751095d65
|
3 |
size 2367673
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7efa6633cea00b3209c57d35e256132e3e9991c7c8131237da4650c16a0ef14e
|
3 |
size 4091
|