Model save
Browse files- README.md +79 -0
- generation_config.json +8 -0
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2-xl
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: lmind_hotpot_train1000_eval500_v1_recite_qa_gpt2-xl
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# lmind_hotpot_train1000_eval500_v1_recite_qa_gpt2-xl
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4181
|
| 21 |
+
- Accuracy: 0.7496
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 3e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: constant
|
| 46 |
+
- num_epochs: 20.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 1.9823 | 1.0 | 248 | 1.6149 | 0.6398 |
|
| 53 |
+
| 1.3868 | 2.0 | 496 | 1.1929 | 0.6700 |
|
| 54 |
+
| 0.9102 | 3.0 | 744 | 0.8513 | 0.6992 |
|
| 55 |
+
| 0.5869 | 4.0 | 992 | 0.6181 | 0.7218 |
|
| 56 |
+
| 0.364 | 5.0 | 1240 | 0.4963 | 0.7352 |
|
| 57 |
+
| 0.2706 | 6.0 | 1488 | 0.4413 | 0.7420 |
|
| 58 |
+
| 0.1906 | 7.0 | 1736 | 0.4085 | 0.7458 |
|
| 59 |
+
| 0.1474 | 8.0 | 1984 | 0.4010 | 0.7477 |
|
| 60 |
+
| 0.1264 | 9.0 | 2232 | 0.3979 | 0.7484 |
|
| 61 |
+
| 0.1091 | 10.0 | 2480 | 0.4060 | 0.7487 |
|
| 62 |
+
| 0.1072 | 11.0 | 2728 | 0.4050 | 0.7490 |
|
| 63 |
+
| 0.0969 | 12.0 | 2976 | 0.4081 | 0.7492 |
|
| 64 |
+
| 0.0935 | 13.0 | 3224 | 0.4145 | 0.7495 |
|
| 65 |
+
| 0.0932 | 14.0 | 3472 | 0.4078 | 0.7494 |
|
| 66 |
+
| 0.0929 | 15.0 | 3720 | 0.4140 | 0.7494 |
|
| 67 |
+
| 0.0951 | 16.0 | 3968 | 0.4145 | 0.7495 |
|
| 68 |
+
| 0.0926 | 17.0 | 4216 | 0.4134 | 0.7495 |
|
| 69 |
+
| 0.0946 | 18.0 | 4464 | 0.4257 | 0.7493 |
|
| 70 |
+
| 0.0897 | 19.0 | 4712 | 0.4164 | 0.7496 |
|
| 71 |
+
| 0.092 | 20.0 | 4960 | 0.4181 | 0.7496 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.34.0
|
| 77 |
+
- Pytorch 2.1.0+cu121
|
| 78 |
+
- Datasets 2.14.5
|
| 79 |
+
- Tokenizers 0.14.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 50256,
|
| 6 |
+
"max_length": 50,
|
| 7 |
+
"transformers_version": "4.34.0"
|
| 8 |
+
}
|