62 lines
2.2 KiB
Markdown
62 lines
2.2 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: other
|
||
|
|
base_model: Qwen/Qwen3-8B
|
||
|
|
tags:
|
||
|
|
- llama-factory
|
||
|
|
- full
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: nemosci-tasrep-a1mfc-dev1-maxeps__Qwen3-8B
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||
|
|
should probably proofread and complete it, then remove this comment. -->
|
||
|
|
|
||
|
|
# nemosci-tasrep-a1mfc-dev1-maxeps__Qwen3-8B
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--nemotron-terminal-scientific_computing/snapshots/610c7db0b8510b87e3c99b3bd49660bc56821866_thinking_preprocessed, the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--DCAgent--exp_tas_repetition_penalty_1.05_traces/snapshots/b4f5500e00651d5ffc7f8701f8a055d9b2b68a0a_thinking_preprocessed, the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--DCAgent--a1_multifile_composition/snapshots/a19e5e467f3e83605b4de72bb5b7923e5e55efa9_thinking_preprocessed, the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--DCAgent--exp_tas_max_episodes_512_traces/snapshots/236c1dc9aa6d24cf77ce281b5342d93bae685832_thinking_preprocessed and the /e/data1/datasets/playground/ot-baf/hf_hub/datasets--DCAgent--dev_set_part1_10k_glm_4.7_traces_jupiter/snapshots/f1871d1c1446b3b43cbfe2737d0df56cecf3f420_thinking_preprocessed datasets.
|
||
|
|
|
||
|
|
## Model description
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Intended uses & limitations
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Training and evaluation data
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Training procedure
|
||
|
|
|
||
|
|
### Training hyperparameters
|
||
|
|
|
||
|
|
The following hyperparameters were used during training:
|
||
|
|
- learning_rate: 4e-05
|
||
|
|
- train_batch_size: 1
|
||
|
|
- eval_batch_size: 8
|
||
|
|
- seed: 42
|
||
|
|
- distributed_type: multi-GPU
|
||
|
|
- num_devices: 32
|
||
|
|
- gradient_accumulation_steps: 3
|
||
|
|
- total_train_batch_size: 96
|
||
|
|
- total_eval_batch_size: 256
|
||
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||
|
|
- lr_scheduler_type: cosine
|
||
|
|
- lr_scheduler_warmup_ratio: 0.1
|
||
|
|
- num_epochs: 5.0
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.57.6
|
||
|
|
- Pytorch 2.9.1+cu130
|
||
|
|
- Datasets 4.7.0
|
||
|
|
- Tokenizers 0.22.2
|