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_offsetbias-8b_noise0.25_rmsd3
|
| 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/s04eoeqy)
|
| 19 |
+
# pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_offsetbias-8b_noise0.25_rmsd3
|
| 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: 0.7505
|
| 24 |
+
- Accuracy: 0.5293
|
| 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: 16
|
| 46 |
+
- seed: 3
|
| 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 | 0.8689 | 0.5066 |
|
| 59 |
+
| 0.8295 | 0.0648 | 100 | 0.8698 | 0.5166 |
|
| 60 |
+
| 0.8671 | 0.1296 | 200 | 0.8438 | 0.5069 |
|
| 61 |
+
| 0.8105 | 0.1944 | 300 | 0.8240 | 0.5208 |
|
| 62 |
+
| 0.886 | 0.2592 | 400 | 0.8095 | 0.5108 |
|
| 63 |
+
| 0.8053 | 0.3239 | 500 | 0.8076 | 0.5231 |
|
| 64 |
+
| 0.7888 | 0.3887 | 600 | 0.7906 | 0.5204 |
|
| 65 |
+
| 0.8221 | 0.4535 | 700 | 0.7882 | 0.5197 |
|
| 66 |
+
| 0.8142 | 0.5183 | 800 | 0.7900 | 0.5266 |
|
| 67 |
+
| 0.7933 | 0.5831 | 900 | 0.7874 | 0.5220 |
|
| 68 |
+
| 0.7587 | 0.6479 | 1000 | 0.7778 | 0.5216 |
|
| 69 |
+
| 0.7988 | 0.7127 | 1100 | 0.7777 | 0.5162 |
|
| 70 |
+
| 0.7923 | 0.7775 | 1200 | 0.7687 | 0.5193 |
|
| 71 |
+
| 0.7805 | 0.8422 | 1300 | 0.7661 | 0.5258 |
|
| 72 |
+
| 0.7813 | 0.9070 | 1400 | 0.7651 | 0.5135 |
|
| 73 |
+
| 0.7387 | 0.9718 | 1500 | 0.7662 | 0.5204 |
|
| 74 |
+
| 0.7574 | 1.0366 | 1600 | 0.7611 | 0.5289 |
|
| 75 |
+
| 0.7611 | 1.1014 | 1700 | 0.7639 | 0.5193 |
|
| 76 |
+
| 0.7342 | 1.1662 | 1800 | 0.7586 | 0.5239 |
|
| 77 |
+
| 0.7997 | 1.2310 | 1900 | 0.7551 | 0.5278 |
|
| 78 |
+
| 0.7758 | 1.2958 | 2000 | 0.7544 | 0.5235 |
|
| 79 |
+
| 0.8124 | 1.3605 | 2100 | 0.7537 | 0.5247 |
|
| 80 |
+
| 0.738 | 1.4253 | 2200 | 0.7567 | 0.5262 |
|
| 81 |
+
| 0.7772 | 1.4901 | 2300 | 0.7522 | 0.5270 |
|
| 82 |
+
| 0.7309 | 1.5549 | 2400 | 0.7511 | 0.5355 |
|
| 83 |
+
| 0.7993 | 1.6197 | 2500 | 0.7520 | 0.5262 |
|
| 84 |
+
| 0.7615 | 1.6845 | 2600 | 0.7523 | 0.5231 |
|
| 85 |
+
| 0.8552 | 1.7493 | 2700 | 0.7512 | 0.5262 |
|
| 86 |
+
| 0.8233 | 1.8141 | 2800 | 0.7492 | 0.5351 |
|
| 87 |
+
| 0.7167 | 1.8788 | 2900 | 0.7532 | 0.5243 |
|
| 88 |
+
| 0.7955 | 1.9436 | 3000 | 0.7518 | 0.5251 |
|
| 89 |
+
| 0.7253 | 2.0084 | 3100 | 0.7537 | 0.5228 |
|
| 90 |
+
| 0.7486 | 2.0732 | 3200 | 0.7571 | 0.5243 |
|
| 91 |
+
| 0.7257 | 2.1380 | 3300 | 0.7529 | 0.5297 |
|
| 92 |
+
| 0.7797 | 2.2028 | 3400 | 0.7502 | 0.5270 |
|
| 93 |
+
| 0.8078 | 2.2676 | 3500 | 0.7521 | 0.5243 |
|
| 94 |
+
| 0.7411 | 2.3324 | 3600 | 0.7544 | 0.5224 |
|
| 95 |
+
| 0.786 | 2.3971 | 3700 | 0.7479 | 0.5258 |
|
| 96 |
+
| 0.7742 | 2.4619 | 3800 | 0.7476 | 0.5243 |
|
| 97 |
+
| 0.7636 | 2.5267 | 3900 | 0.7493 | 0.5278 |
|
| 98 |
+
| 0.7319 | 2.5915 | 4000 | 0.7511 | 0.5305 |
|
| 99 |
+
| 0.7067 | 2.6563 | 4100 | 0.7526 | 0.5270 |
|
| 100 |
+
| 0.755 | 2.7211 | 4200 | 0.7490 | 0.5266 |
|
| 101 |
+
| 0.7467 | 2.7859 | 4300 | 0.7513 | 0.5316 |
|
| 102 |
+
| 0.7689 | 2.8507 | 4400 | 0.7498 | 0.5351 |
|
| 103 |
+
| 0.7495 | 2.9155 | 4500 | 0.7487 | 0.5208 |
|
| 104 |
+
| 0.7588 | 2.9802 | 4600 | 0.7484 | 0.5262 |
|
| 105 |
+
| 0.7426 | 3.0450 | 4700 | 0.7488 | 0.5228 |
|
| 106 |
+
| 0.7037 | 3.1098 | 4800 | 0.7484 | 0.5324 |
|
| 107 |
+
| 0.7679 | 3.1746 | 4900 | 0.7494 | 0.5301 |
|
| 108 |
+
| 0.7506 | 3.2394 | 5000 | 0.7513 | 0.5201 |
|
| 109 |
+
| 0.7599 | 3.3042 | 5100 | 0.7471 | 0.5274 |
|
| 110 |
+
| 0.761 | 3.3690 | 5200 | 0.7553 | 0.5251 |
|
| 111 |
+
| 0.7861 | 3.4338 | 5300 | 0.7454 | 0.5293 |
|
| 112 |
+
| 0.79 | 3.4985 | 5400 | 0.7502 | 0.5305 |
|
| 113 |
+
| 0.764 | 3.5633 | 5500 | 0.7480 | 0.5247 |
|
| 114 |
+
| 0.7753 | 3.6281 | 5600 | 0.7490 | 0.5386 |
|
| 115 |
+
| 0.7399 | 3.6929 | 5700 | 0.7488 | 0.5324 |
|
| 116 |
+
| 0.7504 | 3.7577 | 5800 | 0.7522 | 0.5301 |
|
| 117 |
+
| 0.7584 | 3.8225 | 5900 | 0.7480 | 0.5336 |
|
| 118 |
+
| 0.7508 | 3.8873 | 6000 | 0.7473 | 0.5324 |
|
| 119 |
+
| 0.7231 | 3.9521 | 6100 | 0.7538 | 0.5278 |
|
| 120 |
+
| 0.7644 | 4.0168 | 6200 | 0.7481 | 0.5316 |
|
| 121 |
+
| 0.7636 | 4.0816 | 6300 | 0.7482 | 0.5309 |
|
| 122 |
+
| 0.7639 | 4.1464 | 6400 | 0.7492 | 0.5251 |
|
| 123 |
+
| 0.7847 | 4.2112 | 6500 | 0.7529 | 0.5247 |
|
| 124 |
+
| 0.7384 | 4.2760 | 6600 | 0.7500 | 0.5247 |
|
| 125 |
+
| 0.7838 | 4.3408 | 6700 | 0.7466 | 0.5251 |
|
| 126 |
+
| 0.7448 | 4.4056 | 6800 | 0.7490 | 0.5266 |
|
| 127 |
+
| 0.7236 | 4.4704 | 6900 | 0.7520 | 0.5231 |
|
| 128 |
+
| 0.8039 | 4.5351 | 7000 | 0.7512 | 0.5278 |
|
| 129 |
+
| 0.7285 | 4.5999 | 7100 | 0.7509 | 0.5274 |
|
| 130 |
+
| 0.744 | 4.6647 | 7200 | 0.7508 | 0.5255 |
|
| 131 |
+
| 0.7712 | 4.7295 | 7300 | 0.7544 | 0.5220 |
|
| 132 |
+
| 0.7473 | 4.7943 | 7400 | 0.7508 | 0.5266 |
|
| 133 |
+
| 0.7904 | 4.8591 | 7500 | 0.7483 | 0.5312 |
|
| 134 |
+
| 0.776 | 4.9239 | 7600 | 0.7520 | 0.5212 |
|
| 135 |
+
| 0.7238 | 4.9887 | 7700 | 0.7504 | 0.5266 |
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
### Framework versions
|
| 139 |
+
|
| 140 |
+
- Transformers 4.42.4
|
| 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": "4.42.4",
|
| 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:d162b3384634f80725eccba8cb916265371a2f24c336627137e06e0d98c5d393
|
| 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 sha256:431642e38553e087c631cfed24ee634fe2057fbaaf2f082792723f3ffb439a2d
|
| 3 |
+
size 5304
|