End of training
Browse files- README.md +58 -0
- tokenizer.json +0 -0
- tokenizer_config.json +38 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Sebestianmek/Seb-AI-S1-Mini-350M
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Seb-AI-S1-Mini-Instruct
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# Seb-AI-S1-Mini-Instruct
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [Sebestianmek/Seb-AI-S1-Mini-350M](https://huggingface.co/Sebestianmek/Seb-AI-S1-Mini-350M) on the None dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.00015
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 32
|
| 41 |
+
- total_train_batch_size: 128
|
| 42 |
+
- optimizer: Use OptimizerNames.ADAFACTOR and the args are:
|
| 43 |
+
No additional optimizer arguments
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 40
|
| 46 |
+
- training_steps: 600
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- Transformers 5.20.2
|
| 56 |
+
- Pytorch 2.11.0+cu130
|
| 57 |
+
- Datasets 4.8.5
|
| 58 |
+
- Tokenizers 0.23.3
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|endoftext|>",
|
| 10 |
+
"<|im_start|>",
|
| 11 |
+
"<|im_end|>",
|
| 12 |
+
"<repo_name>",
|
| 13 |
+
"<reponame>",
|
| 14 |
+
"<file_sep>",
|
| 15 |
+
"<filename>",
|
| 16 |
+
"<gh_stars>",
|
| 17 |
+
"<issue_start>",
|
| 18 |
+
"<issue_comment>",
|
| 19 |
+
"<issue_closed>",
|
| 20 |
+
"<jupyter_start>",
|
| 21 |
+
"<jupyter_text>",
|
| 22 |
+
"<jupyter_code>",
|
| 23 |
+
"<jupyter_output>",
|
| 24 |
+
"<jupyter_script>",
|
| 25 |
+
"<empty_output>"
|
| 26 |
+
],
|
| 27 |
+
"is_local": false,
|
| 28 |
+
"local_files_only": false,
|
| 29 |
+
"max_length": 512,
|
| 30 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 31 |
+
"pad_token": "<|endoftext|>",
|
| 32 |
+
"stride": 0,
|
| 33 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 34 |
+
"truncation_side": "right",
|
| 35 |
+
"truncation_strategy": "longest_first",
|
| 36 |
+
"unk_token": "<|endoftext|>",
|
| 37 |
+
"vocab_size": 49152
|
| 38 |
+
}
|