61 lines
3.0 KiB
Markdown
61 lines
3.0 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: other
|
||
|
|
base_model: Qwen/Qwen3-8B
|
||
|
|
tags:
|
||
|
|
- llama-factory
|
||
|
|
- full
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: 100k_epochs3__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. -->
|
||
|
|
|
||
|
|
# 100k_epochs3__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/hf_hub/datasets--DCAgent--swesmith-sandboxes-with_tests-gpt-5-mini-passed_glm_4.7_traces/snapshots/b9b0e0d113e9c37dd035f03644315478acc04487_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-uns-r2egym-16_8x_glm_4.7_traces_jupiter_cleaned/snapshots/f33c2e87626104d2406a7182a6a713bf0b337bdb_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-syh-r2egym-askllm-hardened_glm_4.7_traces_jupiter/snapshots/625842bb217a7168a4b563bc70dc391100b5f483_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-syh-r2egym-askllm-constrained_glm_4.7_traces_jupiter/snapshots/c6f0acf401312da7f0acba098ddc5bfc2d3abcb8_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_tas_optimal_combined_traces/snapshots/ebbeebd254227e227eae6f6f3f25dd76407c5d1c_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_tas_repetition_penalty_1.05_traces/snapshots/b4f5500e00651d5ffc7f8701f8a055d9b2b68a0a_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_tas_max_episodes_512_traces/snapshots/236c1dc9aa6d24cf77ce281b5342d93bae685832_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_tas_timeout_multiplier_8.0_traces/snapshots/cb412ce40164f838f33e77b98af549d815413346_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--glm46-Toolscale-tasks-traces/snapshots/a8a1e7cf8edaa7730bc8ef37d9907888946e830b_thinking_preprocessed and the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--Kimi-K2T-swesmith-32ep-131k/snapshots/7e98e8f444f5bfe78b0e0a94fab0ec28d0487b6e_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: 128
|
||
|
|
- total_train_batch_size: 128
|
||
|
|
- total_eval_batch_size: 1024
|
||
|
|
- 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: 3.0
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.57.6
|
||
|
|
- Pytorch 2.9.1+cu130
|
||
|
|
- Datasets 4.7.0
|
||
|
|
- Tokenizers 0.22.2
|