End of training
Browse files- README.md +143 -0
- config.json +37 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +214 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- reward-trainer
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_pythia-6.9b_noise0.2_rmsd2
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rylan/switching-rms-rm/runs/y6at0px5)
|
| 19 |
+
# pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_pythia-6.9b_noise0.2_rmsd2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0](https://huggingface.co/RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.7555
|
| 24 |
+
- Accuracy: 0.5675
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 1e-05
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 2
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.025
|
| 52 |
+
- num_epochs: 5
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 58 |
+
| No log | 0 | 0 | 0.9081 | 0.5067 |
|
| 59 |
+
| 0.91 | 0.0648 | 100 | 0.9088 | 0.4963 |
|
| 60 |
+
| 0.819 | 0.1295 | 200 | 0.8684 | 0.5098 |
|
| 61 |
+
| 0.83 | 0.1943 | 300 | 0.8459 | 0.5198 |
|
| 62 |
+
| 0.7615 | 0.2591 | 400 | 0.8256 | 0.5317 |
|
| 63 |
+
| 0.8714 | 0.3238 | 500 | 0.8182 | 0.5286 |
|
| 64 |
+
| 0.8431 | 0.3886 | 600 | 0.7987 | 0.5413 |
|
| 65 |
+
| 0.7517 | 0.4534 | 700 | 0.7950 | 0.5306 |
|
| 66 |
+
| 0.7986 | 0.5181 | 800 | 0.7914 | 0.5386 |
|
| 67 |
+
| 0.804 | 0.5829 | 900 | 0.7822 | 0.5406 |
|
| 68 |
+
| 0.7574 | 0.6477 | 1000 | 0.7845 | 0.5483 |
|
| 69 |
+
| 0.7994 | 0.7124 | 1100 | 0.7835 | 0.5456 |
|
| 70 |
+
| 0.787 | 0.7772 | 1200 | 0.7773 | 0.5475 |
|
| 71 |
+
| 0.781 | 0.8420 | 1300 | 0.7771 | 0.5544 |
|
| 72 |
+
| 0.8476 | 0.9067 | 1400 | 0.7700 | 0.5648 |
|
| 73 |
+
| 0.7512 | 0.9715 | 1500 | 0.7666 | 0.5636 |
|
| 74 |
+
| 0.7769 | 1.0363 | 1600 | 0.7682 | 0.5602 |
|
| 75 |
+
| 0.7542 | 1.1010 | 1700 | 0.7639 | 0.5617 |
|
| 76 |
+
| 0.7483 | 1.1658 | 1800 | 0.7639 | 0.5606 |
|
| 77 |
+
| 0.7264 | 1.2306 | 1900 | 0.7618 | 0.5690 |
|
| 78 |
+
| 0.7151 | 1.2953 | 2000 | 0.7612 | 0.5709 |
|
| 79 |
+
| 0.7464 | 1.3601 | 2100 | 0.7624 | 0.5606 |
|
| 80 |
+
| 0.7304 | 1.4249 | 2200 | 0.7578 | 0.5671 |
|
| 81 |
+
| 0.7727 | 1.4896 | 2300 | 0.7585 | 0.5571 |
|
| 82 |
+
| 0.7169 | 1.5544 | 2400 | 0.7564 | 0.5659 |
|
| 83 |
+
| 0.7038 | 1.6192 | 2500 | 0.7575 | 0.5648 |
|
| 84 |
+
| 0.7283 | 1.6839 | 2600 | 0.7599 | 0.5663 |
|
| 85 |
+
| 0.7861 | 1.7487 | 2700 | 0.7544 | 0.5740 |
|
| 86 |
+
| 0.7279 | 1.8135 | 2800 | 0.7573 | 0.5625 |
|
| 87 |
+
| 0.7814 | 1.8782 | 2900 | 0.7588 | 0.5590 |
|
| 88 |
+
| 0.7361 | 1.9430 | 3000 | 0.7535 | 0.5705 |
|
| 89 |
+
| 0.7679 | 2.0078 | 3100 | 0.7540 | 0.5667 |
|
| 90 |
+
| 0.7625 | 2.0725 | 3200 | 0.7530 | 0.5705 |
|
| 91 |
+
| 0.7783 | 2.1373 | 3300 | 0.7549 | 0.5582 |
|
| 92 |
+
| 0.7589 | 2.2021 | 3400 | 0.7579 | 0.5652 |
|
| 93 |
+
| 0.7891 | 2.2668 | 3500 | 0.7563 | 0.5671 |
|
| 94 |
+
| 0.7092 | 2.3316 | 3600 | 0.7535 | 0.5625 |
|
| 95 |
+
| 0.7253 | 2.3964 | 3700 | 0.7518 | 0.5671 |
|
| 96 |
+
| 0.7155 | 2.4611 | 3800 | 0.7534 | 0.5755 |
|
| 97 |
+
| 0.802 | 2.5259 | 3900 | 0.7562 | 0.5690 |
|
| 98 |
+
| 0.7109 | 2.5907 | 4000 | 0.7529 | 0.5679 |
|
| 99 |
+
| 0.714 | 2.6554 | 4100 | 0.7548 | 0.5667 |
|
| 100 |
+
| 0.7307 | 2.7202 | 4200 | 0.7532 | 0.5590 |
|
| 101 |
+
| 0.7531 | 2.7850 | 4300 | 0.7544 | 0.5648 |
|
| 102 |
+
| 0.7225 | 2.8497 | 4400 | 0.7558 | 0.5652 |
|
| 103 |
+
| 0.7156 | 2.9145 | 4500 | 0.7524 | 0.5736 |
|
| 104 |
+
| 0.7635 | 2.9793 | 4600 | 0.7555 | 0.5652 |
|
| 105 |
+
| 0.6646 | 3.0440 | 4700 | 0.7517 | 0.5732 |
|
| 106 |
+
| 0.7721 | 3.1088 | 4800 | 0.7563 | 0.5621 |
|
| 107 |
+
| 0.7731 | 3.1736 | 4900 | 0.7570 | 0.5648 |
|
| 108 |
+
| 0.6982 | 3.2383 | 5000 | 0.7552 | 0.5725 |
|
| 109 |
+
| 0.7271 | 3.3031 | 5100 | 0.7591 | 0.5625 |
|
| 110 |
+
| 0.7447 | 3.3679 | 5200 | 0.7589 | 0.5656 |
|
| 111 |
+
| 0.7745 | 3.4326 | 5300 | 0.7544 | 0.5702 |
|
| 112 |
+
| 0.745 | 3.4974 | 5400 | 0.7567 | 0.5667 |
|
| 113 |
+
| 0.7375 | 3.5622 | 5500 | 0.7544 | 0.5675 |
|
| 114 |
+
| 0.7916 | 3.6269 | 5600 | 0.7565 | 0.5648 |
|
| 115 |
+
| 0.71 | 3.6917 | 5700 | 0.7574 | 0.5702 |
|
| 116 |
+
| 0.7964 | 3.7565 | 5800 | 0.7540 | 0.5705 |
|
| 117 |
+
| 0.7266 | 3.8212 | 5900 | 0.7550 | 0.5659 |
|
| 118 |
+
| 0.7312 | 3.8860 | 6000 | 0.7518 | 0.5717 |
|
| 119 |
+
| 0.7473 | 3.9508 | 6100 | 0.7561 | 0.5648 |
|
| 120 |
+
| 0.7065 | 4.0155 | 6200 | 0.7580 | 0.5586 |
|
| 121 |
+
| 0.7449 | 4.0803 | 6300 | 0.7532 | 0.5663 |
|
| 122 |
+
| 0.8008 | 4.1451 | 6400 | 0.7540 | 0.5729 |
|
| 123 |
+
| 0.8077 | 4.2098 | 6500 | 0.7580 | 0.5567 |
|
| 124 |
+
| 0.7311 | 4.2746 | 6600 | 0.7575 | 0.5682 |
|
| 125 |
+
| 0.7022 | 4.3394 | 6700 | 0.7540 | 0.5640 |
|
| 126 |
+
| 0.7783 | 4.4041 | 6800 | 0.7547 | 0.5629 |
|
| 127 |
+
| 0.7552 | 4.4689 | 6900 | 0.7557 | 0.5606 |
|
| 128 |
+
| 0.7291 | 4.5337 | 7000 | 0.7509 | 0.5725 |
|
| 129 |
+
| 0.7502 | 4.5984 | 7100 | 0.7544 | 0.5748 |
|
| 130 |
+
| 0.775 | 4.6632 | 7200 | 0.7543 | 0.5644 |
|
| 131 |
+
| 0.753 | 4.7280 | 7300 | 0.7528 | 0.5675 |
|
| 132 |
+
| 0.7585 | 4.7927 | 7400 | 0.7554 | 0.5698 |
|
| 133 |
+
| 0.718 | 4.8575 | 7500 | 0.7557 | 0.5679 |
|
| 134 |
+
| 0.7368 | 4.9223 | 7600 | 0.7527 | 0.5705 |
|
| 135 |
+
| 0.7514 | 4.9870 | 7700 | 0.7548 | 0.5690 |
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
### Framework versions
|
| 139 |
+
|
| 140 |
+
- Transformers 4.43.2
|
| 141 |
+
- Pytorch 2.3.0+cu121
|
| 142 |
+
- Datasets 2.20.0
|
| 143 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 512,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 2048,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 2048,
|
| 24 |
+
"model_type": "gpt_neox",
|
| 25 |
+
"num_attention_heads": 8,
|
| 26 |
+
"num_hidden_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rotary_emb_base": 10000,
|
| 30 |
+
"rotary_pct": 0.25,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.43.2",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"use_parallel_residual": true,
|
| 36 |
+
"vocab_size": 50304
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c967f9e81f1fbd55e5c6742d8fb808f85857f85faaf7694df7979fcce82ded4
|
| 3 |
+
size 89351576
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"clean_up_tokenization_spaces": true,
|
| 209 |
+
"eos_token": "<|endoftext|>",
|
| 210 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 211 |
+
"pad_token": "<|endoftext|>",
|
| 212 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 213 |
+
"unk_token": "<|endoftext|>"
|
| 214 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d739b1f17ba7709d5f4f33b40542c07d96b008457ff48ce609c58e9b7e0d4330
|
| 3 |
+
size 5368
|