gradientlab/__init__.py,sha256=6u9ZL0mrE3MHju-ugEFLbC-G3qObDeZP8uu1tvKRrYA,57
gradientlab/data_utils/experiment_path.py,sha256=gyXD2wHjV8d-Iq-fE01HHUB5DnjqRs2rSOgsr0a9tew,158
gradientlab/data_utils/torch_datasets/tokenized_text_ds.py,sha256=WebA6bb8YzmQ-Cz4CP-WZXesrYPydH3quTSNIbq-zeM,332
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/RESULTS.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/__main__.py,sha256=z_-Svktby8wUK-aFZ-SDx1pj4jXIto645uU9pwL1epI,1353
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/eval.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/exp_config.py,sha256=mIeapBa9e9_BFW_07UfgJ5MBrGOQvMIEjGcADkBdC0c,822
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/attention.py,sha256=3Ux46aoL3QKVFdC_VldfcuUPgBlmmuKp4VcsibBrfcg,5882
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/factory.py,sha256=LcJf71J1jhrAWs6HoJc3vojXKYT5ex5q7o4wmfKreLA,1239
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/model.py,sha256=34LdOgvheHnEo2ZqXFVplExyX_xn_zDHb80jco718lQ,6189
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/model_cfg.py,sha256=57fj00Y_AI8OxX-obOIq-kK-8eHvjWitmvKE99868OQ,1694
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/positional_encoding.py,sha256=Ql1eIE0Akrhxqv2Pk7tRrA_3kjwBXl1l9aQGsCWjeGI,745
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/modeling/transformer.py,sha256=2qTjUvA-7YTZX72PGYpKZQ0h9TUZCXBDobVum3SFIRg,3050
gradientlab/experiments/exp20251016_0_lm_20m_polyrelu_lm_vanilla_fineweb_ita/trainer.py,sha256=UpQCMdYkohKUU5agM_EKNqFuLd8H4w5qj9KQ241RHbQ,7158
gradientlab/logging_utils/log_model_params.py,sha256=tmNT2sQ9Oofd9Wrrj6l7mp9TjmaR8u21_9InTYrNZ7k,2746
gradientlab/neuralblocks/activations/polynorm.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/neuralblocks/activations/swiglu.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/neuralblocks/attention/causal_mask.py,sha256=uymJvMA5Ga5vijWUklbpEues3tq2BDAYKheJjRqiRxo,1624
gradientlab/neuralblocks/ffn/polynorm.py,sha256=r_A4Zz2UF0ZDt6lzXyknDV4Wa4RlNHHAkjk2fp7xdSs,1224
gradientlab/neuralblocks/ffn/swiglu.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/neuralblocks/model_types.py,sha256=U02Fi8UoLdzhgahpllfBaQ2rs0R9i8s0jfjkfIcgNYY,327
gradientlab/neuralblocks/norm_layers/rmsnorm.py,sha256=3hj40Kawds6W7OxMF2AOXaCIIpnA7GtGSN8uXybDq7M,560
gradientlab/neuralblocks/optim/adamw_params.py,sha256=nVdQ4Y8cxVcYizz4u9vOc25wxt4HPWpEIdgh84a1jKo,1703
gradientlab/neuralblocks/schedulers/cosine_with_warmup.py,sha256=SNNEBZCks7VA9_qcHYCXBeo6hxmELL-3lRWllQPfAtY,752
gradientlab/neuralblocks/transformer/block.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/neuralblocks/transformer/model.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab/tokenizers/byte_tokenizer.py,sha256=Aa5uNDlO6I8K8rhRS_OjT3nIFycKPUCrfimsaGWXE78,625
gradientlab/tokenizers/qwen_tokenizer.py,sha256=IO2TDmW-HC7hDAgn0YWdswPHHE32aLxoj76ZlvYjDSc,164
gradientlab/training_utils/hf_save.py,sha256=1wCb3QJEUJGgZOFgR79mMrNJB1shQx4RS5CQoVwTm9M,956
gradientlab/training_utils/schedulers/cosine.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
gradientlab-0.1.1.dist-info/WHEEL,sha256=M6du7VZflc4UPsGphmOXHANdgk8zessdJG0DBUuoA-U,78
gradientlab-0.1.1.dist-info/METADATA,sha256=SB-mf27t9tc1hZDkrDKMReTw3uwwOEZYrXzFokL7gTE,2714
gradientlab-0.1.1.dist-info/RECORD,,
