Model save
Browse files
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 [](https://huggingface.co/) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -33,87 +33,105 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate: 0.
|
| 37 |
- train_batch_size: 32
|
| 38 |
- eval_batch_size: 32
|
| 39 |
-
- seed:
|
| 40 |
- gradient_accumulation_steps: 2
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
-
- lr_scheduler_type:
|
| 44 |
-
- lr_scheduler_warmup_steps:
|
| 45 |
- num_epochs: 1
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
|
|
| 54 |
-
| 0.
|
| 55 |
-
|
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
|
| 119 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1981
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0001
|
| 37 |
- train_batch_size: 32
|
| 38 |
- eval_batch_size: 32
|
| 39 |
+
- seed: 43
|
| 40 |
- gradient_accumulation_steps: 2
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: constant_with_warmup
|
| 44 |
+
- lr_scheduler_warmup_steps: 500
|
| 45 |
- num_epochs: 1
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 51 |
+
| 0.6455 | 0.0119 | 1000 | 0.2053 |
|
| 52 |
+
| 0.6832 | 0.0238 | 2000 | 0.2058 |
|
| 53 |
+
| 0.6383 | 0.0357 | 3000 | 0.2058 |
|
| 54 |
+
| 0.6507 | 0.0476 | 4000 | 0.2069 |
|
| 55 |
+
| 0.6877 | 0.0596 | 5000 | 0.2060 |
|
| 56 |
+
| 0.6479 | 0.0715 | 6000 | 0.2054 |
|
| 57 |
+
| 0.7227 | 0.0834 | 7000 | 0.2056 |
|
| 58 |
+
| 0.7055 | 0.0953 | 8000 | 0.2057 |
|
| 59 |
+
| 0.6465 | 0.1072 | 9000 | 0.2052 |
|
| 60 |
+
| 0.7416 | 0.1191 | 10000 | 0.2046 |
|
| 61 |
+
| 0.7090 | 0.1310 | 11000 | 0.2048 |
|
| 62 |
+
| 0.6912 | 0.1429 | 12000 | 0.2060 |
|
| 63 |
+
| 0.5886 | 0.1549 | 13000 | 0.2056 |
|
| 64 |
+
| 0.7237 | 0.1668 | 14000 | 0.2045 |
|
| 65 |
+
| 0.6725 | 0.1787 | 15000 | 0.2046 |
|
| 66 |
+
| 0.6518 | 0.1906 | 16000 | 0.2038 |
|
| 67 |
+
| 0.6546 | 0.2025 | 17000 | 0.2042 |
|
| 68 |
+
| 0.6793 | 0.2144 | 18000 | 0.2032 |
|
| 69 |
+
| 0.6697 | 0.2263 | 19000 | 0.2035 |
|
| 70 |
+
| 0.7108 | 0.2382 | 20000 | 0.2042 |
|
| 71 |
+
| 0.7447 | 0.2502 | 21000 | 0.2038 |
|
| 72 |
+
| 0.6575 | 0.2621 | 22000 | 0.2039 |
|
| 73 |
+
| 0.7154 | 0.2740 | 23000 | 0.2034 |
|
| 74 |
+
| 0.6833 | 0.2859 | 24000 | 0.2024 |
|
| 75 |
+
| 0.6613 | 0.2978 | 25000 | 0.2028 |
|
| 76 |
+
| 0.6906 | 0.3097 | 26000 | 0.2025 |
|
| 77 |
+
| 0.6843 | 0.3216 | 27000 | 0.2027 |
|
| 78 |
+
| 0.6966 | 0.3335 | 28000 | 0.2023 |
|
| 79 |
+
| 0.6801 | 0.3454 | 29000 | 0.2027 |
|
| 80 |
+
| 0.7171 | 0.3574 | 30000 | 0.2027 |
|
| 81 |
+
| 0.7029 | 0.3693 | 31000 | 0.2017 |
|
| 82 |
+
| 0.6876 | 0.3812 | 32000 | 0.2019 |
|
| 83 |
+
| 0.6646 | 0.3931 | 33000 | 0.2022 |
|
| 84 |
+
| 0.6834 | 0.4050 | 34000 | 0.2022 |
|
| 85 |
+
| 0.6868 | 0.4169 | 35000 | 0.2014 |
|
| 86 |
+
| 0.6831 | 0.4288 | 36000 | 0.2019 |
|
| 87 |
+
| 0.6309 | 0.4407 | 37000 | 0.2009 |
|
| 88 |
+
| 0.6603 | 0.4527 | 38000 | 0.2007 |
|
| 89 |
+
| 0.6818 | 0.4646 | 39000 | 0.2006 |
|
| 90 |
+
| 0.6539 | 0.4765 | 40000 | 0.2001 |
|
| 91 |
+
| 0.6999 | 0.4884 | 41000 | 0.2001 |
|
| 92 |
+
| 0.6870 | 0.5003 | 42000 | 0.1997 |
|
| 93 |
+
| 0.5977 | 0.5122 | 43000 | 0.2000 |
|
| 94 |
+
| 0.6747 | 0.5241 | 44000 | 0.2002 |
|
| 95 |
+
| 0.6695 | 0.5360 | 45000 | 0.2005 |
|
| 96 |
+
| 0.6763 | 0.5479 | 46000 | 0.1992 |
|
| 97 |
+
| 0.6656 | 0.5599 | 47000 | 0.2006 |
|
| 98 |
+
| 0.6674 | 0.5718 | 48000 | 0.2000 |
|
| 99 |
+
| 0.7177 | 0.5837 | 49000 | 0.1995 |
|
| 100 |
+
| 0.6904 | 0.5956 | 50000 | 0.1999 |
|
| 101 |
+
| 0.6421 | 0.6075 | 51000 | 0.2003 |
|
| 102 |
+
| 0.6555 | 0.6194 | 52000 | 0.2004 |
|
| 103 |
+
| 0.7010 | 0.6313 | 53000 | 0.2003 |
|
| 104 |
+
| 0.6520 | 0.6432 | 54000 | 0.1993 |
|
| 105 |
+
| 0.6284 | 0.6552 | 55000 | 0.1999 |
|
| 106 |
+
| 0.6770 | 0.6671 | 56000 | 0.1994 |
|
| 107 |
+
| 0.7453 | 0.6790 | 57000 | 0.1993 |
|
| 108 |
+
| 0.6441 | 0.6909 | 58000 | 0.1978 |
|
| 109 |
+
| 0.6670 | 0.7028 | 59000 | 0.1980 |
|
| 110 |
+
| 0.6380 | 0.7147 | 60000 | 0.1979 |
|
| 111 |
+
| 0.7013 | 0.7266 | 61000 | 0.1984 |
|
| 112 |
+
| 0.6442 | 0.7385 | 62000 | 0.1988 |
|
| 113 |
+
| 0.6750 | 0.7505 | 63000 | 0.1981 |
|
| 114 |
+
| 0.6776 | 0.7624 | 64000 | 0.1985 |
|
| 115 |
+
| 0.6316 | 0.7743 | 65000 | 0.1992 |
|
| 116 |
+
| 0.6929 | 0.7862 | 66000 | 0.1988 |
|
| 117 |
+
| 0.6887 | 0.7981 | 67000 | 0.1982 |
|
| 118 |
+
| 0.6502 | 0.8100 | 68000 | 0.1975 |
|
| 119 |
+
| 0.7152 | 0.8219 | 69000 | 0.1983 |
|
| 120 |
+
| 0.6906 | 0.8338 | 70000 | 0.1985 |
|
| 121 |
+
| 0.6128 | 0.8457 | 71000 | 0.1978 |
|
| 122 |
+
| 0.5966 | 0.8577 | 72000 | 0.1973 |
|
| 123 |
+
| 0.6726 | 0.8696 | 73000 | 0.1983 |
|
| 124 |
+
| 0.6668 | 0.8815 | 74000 | 0.1984 |
|
| 125 |
+
| 0.6337 | 0.8934 | 75000 | 0.1982 |
|
| 126 |
+
| 0.6272 | 0.9053 | 76000 | 0.1973 |
|
| 127 |
+
| 0.7112 | 0.9172 | 77000 | 0.1978 |
|
| 128 |
+
| 0.5871 | 0.9291 | 78000 | 0.1989 |
|
| 129 |
+
| 0.6428 | 0.9410 | 79000 | 0.1972 |
|
| 130 |
+
| 0.6740 | 0.9530 | 80000 | 0.1966 |
|
| 131 |
+
| 0.6933 | 0.9649 | 81000 | 0.1976 |
|
| 132 |
+
| 0.6668 | 0.9768 | 82000 | 0.1975 |
|
| 133 |
+
| 0.5919 | 0.9887 | 83000 | 0.1977 |
|
| 134 |
+
| 0.7215 | 1.0 | 83950 | 0.1981 |
|
| 135 |
|
| 136 |
|
| 137 |
### Framework versions
|