Translation
English
Japanese
Eval Results
quickmt-ja-en / eole-model /config.json
radinplaid's picture
Upload folder using huggingface_hub
4f9134c verified
{
"src_vocab": "ja.eole.vocab",
"save_data": "data",
"valid_metrics": [
"BLEU"
],
"tensorboard_log_dir": "tensorboard",
"report_every": 100,
"vocab_size_multiple": 8,
"seed": 1234,
"transforms": [
"sentencepiece",
"filtertoolong"
],
"overwrite": true,
"src_vocab_size": 32000,
"tgt_vocab": "en.eole.vocab",
"share_vocab": false,
"tensorboard": true,
"n_sample": 0,
"tgt_vocab_size": 32000,
"tensorboard_log_dir_dated": "tensorboard/Dec-24_20-29-50",
"training": {
"batch_type": "tokens",
"param_init_method": "xavier_uniform",
"batch_size_multiple": 8,
"learning_rate": 3.0,
"attention_dropout": [
0.1
],
"accum_steps": [
0
],
"batch_size": 15000,
"model_path": "quickmt-ja-en-eole-model",
"keep_checkpoint": 4,
"adam_beta2": 0.998,
"gpu_ranks": [
0
],
"average_decay": 0.0001,
"warmup_steps": 5000,
"valid_steps": 5000,
"dropout": [
0.1
],
"dropout_steps": [
0
],
"prefetch_factor": 64,
"max_grad_norm": 0.0,
"world_size": 1,
"compute_dtype": "torch.float16",
"train_steps": 200000,
"accum_count": [
8
],
"num_workers": 0,
"normalization": "tokens",
"decay_method": "noam",
"optim": "adamw",
"valid_batch_size": 2048,
"bucket_size": 256000,
"label_smoothing": 0.1,
"save_checkpoint_steps": 5000
},
"model": {
"layer_norm": "standard",
"hidden_size": 768,
"add_estimator": false,
"mlp_activation_fn": "gelu",
"share_embeddings": false,
"heads": 16,
"transformer_ff": 4096,
"add_qkvbias": false,
"share_decoder_embeddings": false,
"position_encoding_type": "SinusoidalInterleaved",
"add_ffnbias": true,
"architecture": "transformer",
"encoder": {
"src_word_vec_size": 768,
"n_positions": null,
"layer_norm": "standard",
"encoder_type": "transformer",
"hidden_size": 768,
"mlp_activation_fn": "gelu",
"heads": 16,
"transformer_ff": 4096,
"position_encoding_type": "SinusoidalInterleaved",
"add_ffnbias": true,
"add_qkvbias": false,
"layers": 12
},
"embeddings": {
"word_vec_size": 768,
"src_word_vec_size": 768,
"tgt_word_vec_size": 768,
"position_encoding_type": "SinusoidalInterleaved"
},
"decoder": {
"n_positions": null,
"layer_norm": "standard",
"hidden_size": 768,
"mlp_activation_fn": "gelu",
"tgt_word_vec_size": 768,
"layers": 2,
"heads": 16,
"transformer_ff": 4096,
"position_encoding_type": "SinusoidalInterleaved",
"add_ffnbias": true,
"add_qkvbias": false,
"decoder_type": "transformer"
}
},
"transforms_configs": {
"sentencepiece": {
"tgt_subword_model": "${MODEL_PATH}/en.spm.model",
"src_subword_model": "${MODEL_PATH}/ja.spm.model"
},
"filtertoolong": {
"tgt_seq_length": 256,
"src_seq_length": 256
}
},
"data": {
"corpus_1": {
"path_tgt": "hf://quickmt/quickmt-train.ja-en/en",
"path_align": null,
"path_src": "hf://quickmt/quickmt-train.ja-en/ja",
"transforms": [
"sentencepiece",
"filtertoolong"
],
"weight": 2,
"path_sco": "hf://quickmt/quickmt-train.ja-en/sco"
},
"corpus_2": {
"path_tgt": "hf://quickmt/newscrawl2024-en-backtranslated-ja/en",
"path_align": null,
"path_src": "hf://quickmt/newscrawl2024-en-backtranslated-ja/ja",
"transforms": [
"sentencepiece",
"filtertoolong"
],
"weight": 1,
"path_sco": "hf://quickmt/newscrawl2024-en-backtranslated-ja/sco"
},
"corpus_3": {
"path_tgt": "hf://quickmt/madlad400-en-backtranslated-ja/en",
"path_align": null,
"path_src": "hf://quickmt/madlad400-en-backtranslated-ja/ja",
"transforms": [
"sentencepiece",
"filtertoolong"
],
"weight": 2,
"path_sco": "hf://quickmt/madlad400-en-backtranslated-ja/sco"
},
"valid": {
"path_align": null,
"path_src": "valid.ja",
"transforms": [
"sentencepiece",
"filtertoolong"
],
"path_tgt": "valid.en"
}
}
}