diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..efddc446078b130c166da137097645ca4fac49b6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-174018/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-217522/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-87009/tokenizer.json filter=lfs diff=lfs merge=lfs -text +generated_predictions.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..177e278f632267bed84d50fe7e523270db240949 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +language: +- ja +- ko +base_model: facebook/mbart-large-50-many-to-many-mmt +tags: +- generated_from_trainer +metrics: +- bleu +model-index: +- name: jako_mbartLarge_100p_run1 + results: [] +--- + + + +# jako_mbartLarge_100p_run1 + +This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset. +It achieves the following results on the evaluation set: +- Loss: 0.6815 +- Bleu: 57.9768 +- Gen Len: 17.2796 + +## 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: 5e-05 +- train_batch_size: 2 +- eval_batch_size: 2 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 16 +- total_eval_batch_size: 8 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: linear +- lr_scheduler_warmup_steps: 500 +- num_epochs: 15 +- mixed_precision_training: Native AMP + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | +|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:| +| 0.7241 | 1.0 | 43504 | 0.7178 | 56.112 | 17.3165 | +| 0.5523 | 2.0 | 87009 | 0.6815 | 57.9768 | 17.2796 | +| 0.4356 | 3.0 | 130513 | 0.7014 | 58.5493 | 17.1569 | +| 0.3407 | 4.0 | 174018 | 0.7513 | 58.3826 | 17.1623 | +| 0.2605 | 5.0 | 217522 | 0.8122 | 58.7238 | 17.0888 | + + +### Framework versions + +- Transformers 4.35.2 +- Pytorch 2.1.1+cu121 +- Datasets 2.15.0 +- Tokenizers 0.15.0 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..81aa06e62953ea917a7f57997c2d9fecca108c36 --- /dev/null +++ b/all_results.json @@ -0,0 +1,22 @@ +{ + "epoch": 5.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7593.4193, + "eval_samples": 87008, + "eval_samples_per_second": 11.458, + "eval_steps_per_second": 1.432, + "predict_bleu": 58.0783, + "predict_gen_len": 17.2409, + "predict_loss": 0.6792132258415222, + "predict_runtime": 7605.1607, + "predict_samples": 87008, + "predict_samples_per_second": 11.441, + "predict_steps_per_second": 1.43, + "train_loss": 0.5236641572812728, + "train_runtime": 206817.4399, + "train_samples": 696070, + "train_samples_per_second": 50.484, + "train_steps_per_second": 3.155 +} \ No newline at end of file diff --git a/checkpoint-174018/config.json b/checkpoint-174018/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d123d026fa1d1679aeb1220d9ae316d7c13a0b --- /dev/null +++ b/checkpoint-174018/config.json @@ -0,0 +1,59 @@ +{ + "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt", + "_num_labels": 3, + "activation_dropout": 0.0, + "activation_function": "relu", + "add_bias_logits": false, + "add_final_layer_norm": true, + "architectures": [ + "MBartForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "classif_dropout": 0.0, + "classifier_dropout": 0.0, + "d_model": 1024, + "decoder_attention_heads": 16, + "decoder_ffn_dim": 4096, + "decoder_layerdrop": 0.0, + "decoder_layers": 12, + "decoder_start_token_id": 2, + "dropout": 0.1, + "early_stopping": true, + "encoder_attention_heads": 16, + "encoder_ffn_dim": 4096, + "encoder_layerdrop": 0.0, + "encoder_layers": 12, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "gradient_checkpointing": false, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "init_std": 0.02, + "is_encoder_decoder": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "max_length": 200, + "max_position_embeddings": 1024, + "model_type": "mbart", + "normalize_before": true, + "normalize_embedding": true, + "num_beams": 5, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "scale_embedding": true, + "static_position_embeddings": false, + "tokenizer_class": "MBart50Tokenizer", + "torch_dtype": "float32", + "transformers_version": "4.35.2", + "use_cache": true, + "vocab_size": 250054 +} diff --git a/checkpoint-174018/generation_config.json b/checkpoint-174018/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7e47c12e3900189593d4b56d0d776b58a7a55627 --- /dev/null +++ b/checkpoint-174018/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 0, + "decoder_start_token_id": 2, + "early_stopping": true, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "max_length": 200, + "num_beams": 5, + "pad_token_id": 1, + "transformers_version": "4.35.2" +} diff --git a/checkpoint-174018/model.safetensors b/checkpoint-174018/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d50e30291c013244532048d0ce0a94d15d4eaa6a --- /dev/null +++ b/checkpoint-174018/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0daaf266acfb58de0e85179a61d51aa567bce7c68bcdb934b0d3a498282e60 +size 2444578688 diff --git a/checkpoint-174018/optimizer.pt b/checkpoint-174018/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..32637f028efb630093c8eb97c4531d4d4f0270f4 --- /dev/null +++ b/checkpoint-174018/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd63b45e4e4b733a906c37454b12b8fb9b9a3244287d5a8e43a457c96501ccca +size 4887473903 diff --git a/checkpoint-174018/rng_state_0.pth b/checkpoint-174018/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..80d0dbd426b48d5467aebba9112748fe9befd4fc --- /dev/null +++ b/checkpoint-174018/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a78b891684fb7bc91fc7dbbbfd7f39ac988c343fef4b94e549d1492766531d3 +size 15024 diff --git a/checkpoint-174018/rng_state_1.pth b/checkpoint-174018/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..07998cc9b3c664090faa09057f3d9c8a45986337 --- /dev/null +++ b/checkpoint-174018/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c03af03e7d52ac4e1a2c50634f1e30eef025648cef26578eabf28b2761e79e +size 15024 diff --git a/checkpoint-174018/rng_state_2.pth b/checkpoint-174018/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..28dcc29d75627f6536d92a2db3102e46feb55c83 --- /dev/null +++ b/checkpoint-174018/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81197b1f61f83f0d3897cf98950a95171022cacd5c648bdc859f77040cb0a396 +size 15024 diff --git a/checkpoint-174018/rng_state_3.pth b/checkpoint-174018/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..5365667758b57bfd8938e31c320bf613af924449 --- /dev/null +++ b/checkpoint-174018/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a114c2303bea63782da5da0b278dd19c752ea443e98f041d04e7a01432897af +size 15024 diff --git a/checkpoint-174018/scheduler.pt b/checkpoint-174018/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..068a39a4384d1f2f7eda56e64b0690b1fb73c72a --- /dev/null +++ b/checkpoint-174018/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d08813b32a91856678827a4a2af2b3cb7ecd26ffd837c5ca98ef97f1c231a466 +size 1064 diff --git a/checkpoint-174018/sentencepiece.bpe.model b/checkpoint-174018/sentencepiece.bpe.model new file mode 100644 index 0000000000000000000000000000000000000000..7a3f40a75f870bc1f21700cd414dc2acc431583c --- /dev/null +++ b/checkpoint-174018/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/checkpoint-174018/special_tokens_map.json b/checkpoint-174018/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92619141640d5fcbb4429807de2248352b0dca79 --- /dev/null +++ b/checkpoint-174018/special_tokens_map.json @@ -0,0 +1,69 @@ +{ + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "cls_token": "", + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/checkpoint-174018/tokenizer.json b/checkpoint-174018/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86f15e5a3339d518716121ecef4c2a1dc9208b40 --- /dev/null +++ b/checkpoint-174018/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf1fb0f45fdd5ae9fc44fafee492652a423fc749833ef57c2fa801358549d92 +size 17110107 diff --git a/checkpoint-174018/tokenizer_config.json b/checkpoint-174018/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..70c0515a5815fcc727e11e053116348bfac12128 --- /dev/null +++ b/checkpoint-174018/tokenizer_config.json @@ -0,0 +1,528 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250001": { + "content": "ar_AR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250002": { + "content": "cs_CZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250003": { + "content": "de_DE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250004": { + "content": "en_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250005": { + "content": "es_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250006": { + "content": "et_EE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250007": { + "content": "fi_FI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250008": { + "content": "fr_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250009": { + "content": "gu_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250010": { + "content": "hi_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250011": { + "content": "it_IT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250012": { + "content": "ja_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250013": { + "content": "kk_KZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250014": { + "content": "ko_KR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250015": { + "content": "lt_LT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250016": { + "content": "lv_LV", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250017": { + "content": "my_MM", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250018": { + "content": "ne_NP", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250019": { + "content": "nl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250020": { + "content": "ro_RO", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250021": { + "content": "ru_RU", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250022": { + "content": "si_LK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250023": { + "content": "tr_TR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250024": { + "content": "vi_VN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250025": { + "content": "zh_CN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250026": { + "content": "af_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250027": { + "content": "az_AZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250028": { + "content": "bn_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250029": { + "content": "fa_IR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250030": { + "content": "he_IL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250031": { + "content": "hr_HR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250032": { + "content": "id_ID", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250033": { + "content": "ka_GE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250034": { + "content": "km_KH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250035": { + "content": "mk_MK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250036": { + "content": "ml_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250037": { + "content": "mn_MN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250038": { + "content": "mr_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250039": { + "content": "pl_PL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250040": { + "content": "ps_AF", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250041": { + "content": "pt_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250042": { + "content": "sv_SE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250043": { + "content": "sw_KE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250044": { + "content": "ta_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250045": { + "content": "te_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250046": { + "content": "th_TH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250047": { + "content": "tl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250048": { + "content": "uk_UA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250049": { + "content": "ur_PK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250050": { + "content": "xh_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250051": { + "content": "gl_ES", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250052": { + "content": "sl_SI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250053": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "clean_up_tokenization_spaces": true, + "cls_token": "", + "eos_token": "", + "language_codes": "ML50", + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "sp_model_kwargs": {}, + "src_lang": "ja_XX", + "tgt_lang": "ko_KR", + "tokenizer_class": "MBart50Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-174018/trainer_state.json b/checkpoint-174018/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..584cb54e97d3c123dabc66c27b462433c8ec7c57 --- /dev/null +++ b/checkpoint-174018/trainer_state.json @@ -0,0 +1,2147 @@ +{ + "best_metric": 0.6814723610877991, + "best_model_checkpoint": "./jako_mbartLarge_100p_run1/checkpoint-87009", + "epoch": 4.0, + "eval_steps": 500, + "global_step": 174018, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 4.97e-05, + "loss": 1.9891, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 4.996196669018189e-05, + "loss": 1.5354, + "step": 1000 + }, + { + "epoch": 0.03, + "learning_rate": 4.9923626660123305e-05, + "loss": 1.3833, + "step": 1500 + }, + { + "epoch": 0.05, + "learning_rate": 4.988528663006472e-05, + "loss": 1.2912, + "step": 2000 + }, + { + "epoch": 0.06, + "learning_rate": 4.984694660000614e-05, + "loss": 1.2355, + "step": 2500 + }, + { + "epoch": 0.07, + "learning_rate": 4.980860656994755e-05, + "loss": 1.1927, + "step": 3000 + }, + { + "epoch": 0.08, + "learning_rate": 4.977026653988897e-05, + "loss": 1.166, + "step": 3500 + }, + { + "epoch": 0.09, + "learning_rate": 4.9731926509830386e-05, + "loss": 1.1238, + "step": 4000 + }, + { + "epoch": 0.1, + "learning_rate": 4.9693586479771804e-05, + "loss": 1.0972, + "step": 4500 + }, + { + "epoch": 0.11, + "learning_rate": 4.9655246449713215e-05, + "loss": 1.0964, + "step": 5000 + }, + { + "epoch": 0.13, + "learning_rate": 4.961690641965463e-05, + "loss": 1.0611, + "step": 5500 + }, + { + "epoch": 0.14, + "learning_rate": 4.957871974971629e-05, + "loss": 1.0487, + "step": 6000 + }, + { + "epoch": 0.15, + "learning_rate": 4.9540379719657705e-05, + "loss": 1.0166, + "step": 6500 + }, + { + "epoch": 0.16, + "learning_rate": 4.9502039689599116e-05, + "loss": 1.0162, + "step": 7000 + }, + { + "epoch": 0.17, + "learning_rate": 4.946369965954053e-05, + "loss": 0.9952, + "step": 7500 + }, + { + "epoch": 0.18, + "learning_rate": 4.942535962948195e-05, + "loss": 0.9853, + "step": 8000 + }, + { + "epoch": 0.2, + "learning_rate": 4.9387096279483484e-05, + "loss": 0.9835, + "step": 8500 + }, + { + "epoch": 0.21, + "learning_rate": 4.9348832929485017e-05, + "loss": 0.9634, + "step": 9000 + }, + { + "epoch": 0.22, + "learning_rate": 4.9310492899426434e-05, + "loss": 0.9532, + "step": 9500 + }, + { + "epoch": 0.23, + "learning_rate": 4.927215286936785e-05, + "loss": 0.955, + "step": 10000 + }, + { + "epoch": 0.24, + "learning_rate": 4.923381283930927e-05, + "loss": 0.9392, + "step": 10500 + }, + { + "epoch": 0.25, + "learning_rate": 4.919547280925069e-05, + "loss": 0.9403, + "step": 11000 + }, + { + "epoch": 0.26, + "learning_rate": 4.91571327791921e-05, + "loss": 0.9177, + "step": 11500 + }, + { + "epoch": 0.28, + "learning_rate": 4.9118792749133516e-05, + "loss": 0.919, + "step": 12000 + }, + { + "epoch": 0.29, + "learning_rate": 4.908045271907493e-05, + "loss": 0.9036, + "step": 12500 + }, + { + "epoch": 0.3, + "learning_rate": 4.9042189369076466e-05, + "loss": 0.9019, + "step": 13000 + }, + { + "epoch": 0.31, + "learning_rate": 4.9003849339017884e-05, + "loss": 0.8969, + "step": 13500 + }, + { + "epoch": 0.32, + "learning_rate": 4.89655093089593e-05, + "loss": 0.891, + "step": 14000 + }, + { + "epoch": 0.33, + "learning_rate": 4.892716927890072e-05, + "loss": 0.8904, + "step": 14500 + }, + { + "epoch": 0.34, + "learning_rate": 4.888882924884213e-05, + "loss": 0.8833, + "step": 15000 + }, + { + "epoch": 0.36, + "learning_rate": 4.8850489218783554e-05, + "loss": 0.8668, + "step": 15500 + }, + { + "epoch": 0.37, + "learning_rate": 4.8812149188724965e-05, + "loss": 0.8692, + "step": 16000 + }, + { + "epoch": 0.38, + "learning_rate": 4.877380915866638e-05, + "loss": 0.8617, + "step": 16500 + }, + { + "epoch": 0.39, + "learning_rate": 4.8735469128607794e-05, + "loss": 0.866, + "step": 17000 + }, + { + "epoch": 0.4, + "learning_rate": 4.869720577860933e-05, + "loss": 0.8592, + "step": 17500 + }, + { + "epoch": 0.41, + "learning_rate": 4.8658865748550744e-05, + "loss": 0.8586, + "step": 18000 + }, + { + "epoch": 0.43, + "learning_rate": 4.862052571849217e-05, + "loss": 0.84, + "step": 18500 + }, + { + "epoch": 0.44, + "learning_rate": 4.8582262368493695e-05, + "loss": 0.84, + "step": 19000 + }, + { + "epoch": 0.45, + "learning_rate": 4.854392233843512e-05, + "loss": 0.8397, + "step": 19500 + }, + { + "epoch": 0.46, + "learning_rate": 4.850581234855688e-05, + "loss": 0.8338, + "step": 20000 + }, + { + "epoch": 0.47, + "learning_rate": 4.84674723184983e-05, + "loss": 0.838, + "step": 20500 + }, + { + "epoch": 0.48, + "learning_rate": 4.842913228843972e-05, + "loss": 0.8391, + "step": 21000 + }, + { + "epoch": 0.49, + "learning_rate": 4.8390792258381135e-05, + "loss": 0.8276, + "step": 21500 + }, + { + "epoch": 0.51, + "learning_rate": 4.8352452228322546e-05, + "loss": 0.8198, + "step": 22000 + }, + { + "epoch": 0.52, + "learning_rate": 4.8314112198263963e-05, + "loss": 0.8127, + "step": 22500 + }, + { + "epoch": 0.53, + "learning_rate": 4.827577216820538e-05, + "loss": 0.8184, + "step": 23000 + }, + { + "epoch": 0.54, + "learning_rate": 4.82374321381468e-05, + "loss": 0.817, + "step": 23500 + }, + { + "epoch": 0.55, + "learning_rate": 4.8199092108088216e-05, + "loss": 0.8196, + "step": 24000 + }, + { + "epoch": 0.56, + "learning_rate": 4.816075207802963e-05, + "loss": 0.8024, + "step": 24500 + }, + { + "epoch": 0.57, + "learning_rate": 4.812241204797105e-05, + "loss": 0.8133, + "step": 25000 + }, + { + "epoch": 0.59, + "learning_rate": 4.808407201791246e-05, + "loss": 0.8056, + "step": 25500 + }, + { + "epoch": 0.6, + "learning_rate": 4.804573198785388e-05, + "loss": 0.7972, + "step": 26000 + }, + { + "epoch": 0.61, + "learning_rate": 4.80073919577953e-05, + "loss": 0.8026, + "step": 26500 + }, + { + "epoch": 0.62, + "learning_rate": 4.7969051927736716e-05, + "loss": 0.7983, + "step": 27000 + }, + { + "epoch": 0.63, + "learning_rate": 4.793078857773824e-05, + "loss": 0.795, + "step": 27500 + }, + { + "epoch": 0.64, + "learning_rate": 4.7892448547679666e-05, + "loss": 0.803, + "step": 28000 + }, + { + "epoch": 0.66, + "learning_rate": 4.7854108517621084e-05, + "loss": 0.7911, + "step": 28500 + }, + { + "epoch": 0.67, + "learning_rate": 4.7815768487562494e-05, + "loss": 0.7757, + "step": 29000 + }, + { + "epoch": 0.68, + "learning_rate": 4.777742845750391e-05, + "loss": 0.777, + "step": 29500 + }, + { + "epoch": 0.69, + "learning_rate": 4.773908842744533e-05, + "loss": 0.7848, + "step": 30000 + }, + { + "epoch": 0.7, + "learning_rate": 4.770074839738675e-05, + "loss": 0.7834, + "step": 30500 + }, + { + "epoch": 0.71, + "learning_rate": 4.766240836732816e-05, + "loss": 0.7753, + "step": 31000 + }, + { + "epoch": 0.72, + "learning_rate": 4.7624068337269576e-05, + "loss": 0.7715, + "step": 31500 + }, + { + "epoch": 0.74, + "learning_rate": 4.7585728307211e-05, + "loss": 0.7714, + "step": 32000 + }, + { + "epoch": 0.75, + "learning_rate": 4.754738827715241e-05, + "loss": 0.7736, + "step": 32500 + }, + { + "epoch": 0.76, + "learning_rate": 4.750904824709383e-05, + "loss": 0.7767, + "step": 33000 + }, + { + "epoch": 0.77, + "learning_rate": 4.747070821703524e-05, + "loss": 0.7661, + "step": 33500 + }, + { + "epoch": 0.78, + "learning_rate": 4.7432368186976664e-05, + "loss": 0.7565, + "step": 34000 + }, + { + "epoch": 0.79, + "learning_rate": 4.739410483697819e-05, + "loss": 0.7515, + "step": 34500 + }, + { + "epoch": 0.8, + "learning_rate": 4.735584148697973e-05, + "loss": 0.7558, + "step": 35000 + }, + { + "epoch": 0.82, + "learning_rate": 4.731750145692114e-05, + "loss": 0.7642, + "step": 35500 + }, + { + "epoch": 0.83, + "learning_rate": 4.727916142686256e-05, + "loss": 0.7626, + "step": 36000 + }, + { + "epoch": 0.84, + "learning_rate": 4.7240821396803976e-05, + "loss": 0.7627, + "step": 36500 + }, + { + "epoch": 0.85, + "learning_rate": 4.7202481366745394e-05, + "loss": 0.7495, + "step": 37000 + }, + { + "epoch": 0.86, + "learning_rate": 4.716414133668681e-05, + "loss": 0.7582, + "step": 37500 + }, + { + "epoch": 0.87, + "learning_rate": 4.7125877986688344e-05, + "loss": 0.7481, + "step": 38000 + }, + { + "epoch": 0.88, + "learning_rate": 4.708753795662976e-05, + "loss": 0.7557, + "step": 38500 + }, + { + "epoch": 0.9, + "learning_rate": 4.704919792657117e-05, + "loss": 0.7384, + "step": 39000 + }, + { + "epoch": 0.91, + "learning_rate": 4.70108578965126e-05, + "loss": 0.742, + "step": 39500 + }, + { + "epoch": 0.92, + "learning_rate": 4.697251786645401e-05, + "loss": 0.7388, + "step": 40000 + }, + { + "epoch": 0.93, + "learning_rate": 4.6934177836395425e-05, + "loss": 0.7503, + "step": 40500 + }, + { + "epoch": 0.94, + "learning_rate": 4.689583780633684e-05, + "loss": 0.745, + "step": 41000 + }, + { + "epoch": 0.95, + "learning_rate": 4.685749777627826e-05, + "loss": 0.7228, + "step": 41500 + }, + { + "epoch": 0.97, + "learning_rate": 4.681915774621968e-05, + "loss": 0.7333, + "step": 42000 + }, + { + "epoch": 0.98, + "learning_rate": 4.678081771616109e-05, + "loss": 0.7371, + "step": 42500 + }, + { + "epoch": 0.99, + "learning_rate": 4.674247768610251e-05, + "loss": 0.733, + "step": 43000 + }, + { + "epoch": 1.0, + "learning_rate": 4.6704137656043925e-05, + "loss": 0.7241, + "step": 43500 + }, + { + "epoch": 1.0, + "eval_bleu": 56.112, + "eval_gen_len": 17.3165, + "eval_loss": 0.7177675366401672, + "eval_runtime": 7671.1849, + "eval_samples_per_second": 11.342, + "eval_steps_per_second": 1.418, + "step": 43504 + }, + { + "epoch": 1.01, + "learning_rate": 4.666587430604546e-05, + "loss": 0.7322, + "step": 44000 + }, + { + "epoch": 1.02, + "learning_rate": 4.6627534275986875e-05, + "loss": 0.7051, + "step": 44500 + }, + { + "epoch": 1.03, + "learning_rate": 4.658919424592829e-05, + "loss": 0.6935, + "step": 45000 + }, + { + "epoch": 1.05, + "learning_rate": 4.6550854215869704e-05, + "loss": 0.6831, + "step": 45500 + }, + { + "epoch": 1.06, + "learning_rate": 4.651259086587124e-05, + "loss": 0.6787, + "step": 46000 + }, + { + "epoch": 1.07, + "learning_rate": 4.6474327515872776e-05, + "loss": 0.6813, + "step": 46500 + }, + { + "epoch": 1.08, + "learning_rate": 4.6436140845934424e-05, + "loss": 0.6841, + "step": 47000 + }, + { + "epoch": 1.09, + "learning_rate": 4.639780081587584e-05, + "loss": 0.6697, + "step": 47500 + }, + { + "epoch": 1.1, + "learning_rate": 4.635946078581726e-05, + "loss": 0.6605, + "step": 48000 + }, + { + "epoch": 1.11, + "learning_rate": 4.632112075575868e-05, + "loss": 0.675, + "step": 48500 + }, + { + "epoch": 1.13, + "learning_rate": 4.6282780725700094e-05, + "loss": 0.6623, + "step": 49000 + }, + { + "epoch": 1.14, + "learning_rate": 4.6244440695641505e-05, + "loss": 0.6589, + "step": 49500 + }, + { + "epoch": 1.15, + "learning_rate": 4.620610066558292e-05, + "loss": 0.6476, + "step": 50000 + }, + { + "epoch": 1.16, + "learning_rate": 4.616776063552434e-05, + "loss": 0.6551, + "step": 50500 + }, + { + "epoch": 1.17, + "learning_rate": 4.612942060546576e-05, + "loss": 0.6502, + "step": 51000 + }, + { + "epoch": 1.18, + "learning_rate": 4.6091080575407176e-05, + "loss": 0.6478, + "step": 51500 + }, + { + "epoch": 1.2, + "learning_rate": 4.605274054534859e-05, + "loss": 0.6485, + "step": 52000 + }, + { + "epoch": 1.21, + "learning_rate": 4.6014400515290004e-05, + "loss": 0.6412, + "step": 52500 + }, + { + "epoch": 1.22, + "learning_rate": 4.597606048523142e-05, + "loss": 0.6376, + "step": 53000 + }, + { + "epoch": 1.23, + "learning_rate": 4.593772045517284e-05, + "loss": 0.6385, + "step": 53500 + }, + { + "epoch": 1.24, + "learning_rate": 4.589945710517437e-05, + "loss": 0.6366, + "step": 54000 + }, + { + "epoch": 1.25, + "learning_rate": 4.586111707511579e-05, + "loss": 0.6444, + "step": 54500 + }, + { + "epoch": 1.26, + "learning_rate": 4.582277704505721e-05, + "loss": 0.6311, + "step": 55000 + }, + { + "epoch": 1.28, + "learning_rate": 4.578451369505874e-05, + "loss": 0.6306, + "step": 55500 + }, + { + "epoch": 1.29, + "learning_rate": 4.574617366500016e-05, + "loss": 0.6199, + "step": 56000 + }, + { + "epoch": 1.3, + "learning_rate": 4.570783363494157e-05, + "loss": 0.6268, + "step": 56500 + }, + { + "epoch": 1.31, + "learning_rate": 4.566949360488299e-05, + "loss": 0.623, + "step": 57000 + }, + { + "epoch": 1.32, + "learning_rate": 4.5631153574824404e-05, + "loss": 0.6207, + "step": 57500 + }, + { + "epoch": 1.33, + "learning_rate": 4.559281354476582e-05, + "loss": 0.6204, + "step": 58000 + }, + { + "epoch": 1.34, + "learning_rate": 4.555447351470723e-05, + "loss": 0.6215, + "step": 58500 + }, + { + "epoch": 1.36, + "learning_rate": 4.551613348464866e-05, + "loss": 0.6114, + "step": 59000 + }, + { + "epoch": 1.37, + "learning_rate": 4.5477793454590075e-05, + "loss": 0.6134, + "step": 59500 + }, + { + "epoch": 1.38, + "learning_rate": 4.543953010459161e-05, + "loss": 0.6142, + "step": 60000 + }, + { + "epoch": 1.39, + "learning_rate": 4.5401190074533025e-05, + "loss": 0.6149, + "step": 60500 + }, + { + "epoch": 1.4, + "learning_rate": 4.5362850044474436e-05, + "loss": 0.6123, + "step": 61000 + }, + { + "epoch": 1.41, + "learning_rate": 4.5324510014415854e-05, + "loss": 0.6159, + "step": 61500 + }, + { + "epoch": 1.43, + "learning_rate": 4.5286246664417387e-05, + "loss": 0.6001, + "step": 62000 + }, + { + "epoch": 1.44, + "learning_rate": 4.5247906634358804e-05, + "loss": 0.6034, + "step": 62500 + }, + { + "epoch": 1.45, + "learning_rate": 4.520956660430022e-05, + "loss": 0.5999, + "step": 63000 + }, + { + "epoch": 1.46, + "learning_rate": 4.517122657424164e-05, + "loss": 0.6011, + "step": 63500 + }, + { + "epoch": 1.47, + "learning_rate": 4.513288654418305e-05, + "loss": 0.6051, + "step": 64000 + }, + { + "epoch": 1.48, + "learning_rate": 4.509454651412447e-05, + "loss": 0.6061, + "step": 64500 + }, + { + "epoch": 1.49, + "learning_rate": 4.5056206484065886e-05, + "loss": 0.598, + "step": 65000 + }, + { + "epoch": 1.51, + "learning_rate": 4.50178664540073e-05, + "loss": 0.5939, + "step": 65500 + }, + { + "epoch": 1.52, + "learning_rate": 4.497952642394872e-05, + "loss": 0.5905, + "step": 66000 + }, + { + "epoch": 1.53, + "learning_rate": 4.494118639389013e-05, + "loss": 0.5968, + "step": 66500 + }, + { + "epoch": 1.54, + "learning_rate": 4.490284636383155e-05, + "loss": 0.5943, + "step": 67000 + }, + { + "epoch": 1.55, + "learning_rate": 4.486450633377297e-05, + "loss": 0.6025, + "step": 67500 + }, + { + "epoch": 1.56, + "learning_rate": 4.4826166303714385e-05, + "loss": 0.5918, + "step": 68000 + }, + { + "epoch": 1.57, + "learning_rate": 4.47878262736558e-05, + "loss": 0.5983, + "step": 68500 + }, + { + "epoch": 1.59, + "learning_rate": 4.474948624359721e-05, + "loss": 0.5907, + "step": 69000 + }, + { + "epoch": 1.6, + "learning_rate": 4.471114621353864e-05, + "loss": 0.5852, + "step": 69500 + }, + { + "epoch": 1.61, + "learning_rate": 4.4672882863540164e-05, + "loss": 0.5886, + "step": 70000 + }, + { + "epoch": 1.62, + "learning_rate": 4.463454283348159e-05, + "loss": 0.5895, + "step": 70500 + }, + { + "epoch": 1.63, + "learning_rate": 4.4596202803423e-05, + "loss": 0.5887, + "step": 71000 + }, + { + "epoch": 1.64, + "learning_rate": 4.455786277336442e-05, + "loss": 0.5953, + "step": 71500 + }, + { + "epoch": 1.66, + "learning_rate": 4.451952274330583e-05, + "loss": 0.5888, + "step": 72000 + }, + { + "epoch": 1.67, + "learning_rate": 4.448118271324725e-05, + "loss": 0.571, + "step": 72500 + }, + { + "epoch": 1.68, + "learning_rate": 4.444291936324878e-05, + "loss": 0.576, + "step": 73000 + }, + { + "epoch": 1.69, + "learning_rate": 4.44045793331902e-05, + "loss": 0.5828, + "step": 73500 + }, + { + "epoch": 1.7, + "learning_rate": 4.436631598319173e-05, + "loss": 0.5875, + "step": 74000 + }, + { + "epoch": 1.71, + "learning_rate": 4.432797595313315e-05, + "loss": 0.5773, + "step": 74500 + }, + { + "epoch": 1.72, + "learning_rate": 4.428963592307457e-05, + "loss": 0.5741, + "step": 75000 + }, + { + "epoch": 1.74, + "learning_rate": 4.425129589301598e-05, + "loss": 0.5721, + "step": 75500 + }, + { + "epoch": 1.75, + "learning_rate": 4.42129558629574e-05, + "loss": 0.5797, + "step": 76000 + }, + { + "epoch": 1.76, + "learning_rate": 4.417461583289882e-05, + "loss": 0.5787, + "step": 76500 + }, + { + "epoch": 1.77, + "learning_rate": 4.4136275802840234e-05, + "loss": 0.5731, + "step": 77000 + }, + { + "epoch": 1.78, + "learning_rate": 4.409801245284177e-05, + "loss": 0.5642, + "step": 77500 + }, + { + "epoch": 1.79, + "learning_rate": 4.4059672422783185e-05, + "loss": 0.5653, + "step": 78000 + }, + { + "epoch": 1.8, + "learning_rate": 4.4021332392724596e-05, + "loss": 0.5663, + "step": 78500 + }, + { + "epoch": 1.82, + "learning_rate": 4.398299236266601e-05, + "loss": 0.5762, + "step": 79000 + }, + { + "epoch": 1.83, + "learning_rate": 4.394465233260743e-05, + "loss": 0.5742, + "step": 79500 + }, + { + "epoch": 1.84, + "learning_rate": 4.390631230254885e-05, + "loss": 0.5739, + "step": 80000 + }, + { + "epoch": 1.85, + "learning_rate": 4.3867972272490266e-05, + "loss": 0.5686, + "step": 80500 + }, + { + "epoch": 1.86, + "learning_rate": 4.382963224243168e-05, + "loss": 0.5757, + "step": 81000 + }, + { + "epoch": 1.87, + "learning_rate": 4.3791292212373095e-05, + "loss": 0.5654, + "step": 81500 + }, + { + "epoch": 1.88, + "learning_rate": 4.375295218231451e-05, + "loss": 0.5697, + "step": 82000 + }, + { + "epoch": 1.9, + "learning_rate": 4.371461215225593e-05, + "loss": 0.5582, + "step": 82500 + }, + { + "epoch": 1.91, + "learning_rate": 4.367627212219735e-05, + "loss": 0.5603, + "step": 83000 + }, + { + "epoch": 1.92, + "learning_rate": 4.363793209213876e-05, + "loss": 0.5564, + "step": 83500 + }, + { + "epoch": 1.93, + "learning_rate": 4.359959206208018e-05, + "loss": 0.5682, + "step": 84000 + }, + { + "epoch": 1.94, + "learning_rate": 4.356132871208171e-05, + "loss": 0.566, + "step": 84500 + }, + { + "epoch": 1.95, + "learning_rate": 4.3522988682023133e-05, + "loss": 0.5485, + "step": 85000 + }, + { + "epoch": 1.97, + "learning_rate": 4.3484648651964544e-05, + "loss": 0.5558, + "step": 85500 + }, + { + "epoch": 1.98, + "learning_rate": 4.344630862190596e-05, + "loss": 0.5592, + "step": 86000 + }, + { + "epoch": 1.99, + "learning_rate": 4.340796859184737e-05, + "loss": 0.5611, + "step": 86500 + }, + { + "epoch": 2.0, + "learning_rate": 4.337001196208938e-05, + "loss": 0.5523, + "step": 87000 + }, + { + "epoch": 2.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7592.1301, + "eval_samples_per_second": 11.46, + "eval_steps_per_second": 1.433, + "step": 87009 + }, + { + "epoch": 2.01, + "learning_rate": 4.33316719320308e-05, + "loss": 0.5617, + "step": 87500 + }, + { + "epoch": 2.02, + "learning_rate": 4.3293331901972215e-05, + "loss": 0.5392, + "step": 88000 + }, + { + "epoch": 2.03, + "learning_rate": 4.325499187191363e-05, + "loss": 0.5313, + "step": 88500 + }, + { + "epoch": 2.05, + "learning_rate": 4.321665184185504e-05, + "loss": 0.5247, + "step": 89000 + }, + { + "epoch": 2.06, + "learning_rate": 4.317831181179646e-05, + "loss": 0.5183, + "step": 89500 + }, + { + "epoch": 2.07, + "learning_rate": 4.313997178173788e-05, + "loss": 0.5266, + "step": 90000 + }, + { + "epoch": 2.08, + "learning_rate": 4.3101631751679296e-05, + "loss": 0.5256, + "step": 90500 + }, + { + "epoch": 2.09, + "learning_rate": 4.3063291721620714e-05, + "loss": 0.5148, + "step": 91000 + }, + { + "epoch": 2.1, + "learning_rate": 4.3024951691562125e-05, + "loss": 0.5097, + "step": 91500 + }, + { + "epoch": 2.11, + "learning_rate": 4.298661166150354e-05, + "loss": 0.5192, + "step": 92000 + }, + { + "epoch": 2.13, + "learning_rate": 4.294827163144496e-05, + "loss": 0.5125, + "step": 92500 + }, + { + "epoch": 2.14, + "learning_rate": 4.290993160138638e-05, + "loss": 0.5049, + "step": 93000 + }, + { + "epoch": 2.15, + "learning_rate": 4.2871591571327795e-05, + "loss": 0.4974, + "step": 93500 + }, + { + "epoch": 2.16, + "learning_rate": 4.2833251541269206e-05, + "loss": 0.5044, + "step": 94000 + }, + { + "epoch": 2.17, + "learning_rate": 4.279491151121063e-05, + "loss": 0.5026, + "step": 94500 + }, + { + "epoch": 2.18, + "learning_rate": 4.275657148115204e-05, + "loss": 0.5028, + "step": 95000 + }, + { + "epoch": 2.2, + "learning_rate": 4.271823145109346e-05, + "loss": 0.4992, + "step": 95500 + }, + { + "epoch": 2.21, + "learning_rate": 4.267989142103488e-05, + "loss": 0.5, + "step": 96000 + }, + { + "epoch": 2.22, + "learning_rate": 4.264162807103641e-05, + "loss": 0.4942, + "step": 96500 + }, + { + "epoch": 2.23, + "learning_rate": 4.260328804097782e-05, + "loss": 0.4942, + "step": 97000 + }, + { + "epoch": 2.24, + "learning_rate": 4.2564948010919245e-05, + "loss": 0.4952, + "step": 97500 + }, + { + "epoch": 2.25, + "learning_rate": 4.252660798086066e-05, + "loss": 0.4977, + "step": 98000 + }, + { + "epoch": 2.26, + "learning_rate": 4.2488344630862195e-05, + "loss": 0.4894, + "step": 98500 + }, + { + "epoch": 2.28, + "learning_rate": 4.245008128086372e-05, + "loss": 0.4887, + "step": 99000 + }, + { + "epoch": 2.29, + "learning_rate": 4.2411741250805146e-05, + "loss": 0.4813, + "step": 99500 + }, + { + "epoch": 2.3, + "learning_rate": 4.2373401220746563e-05, + "loss": 0.4851, + "step": 100000 + }, + { + "epoch": 2.31, + "learning_rate": 4.2335061190687974e-05, + "loss": 0.4865, + "step": 100500 + }, + { + "epoch": 2.32, + "learning_rate": 4.229672116062939e-05, + "loss": 0.4823, + "step": 101000 + }, + { + "epoch": 2.33, + "learning_rate": 4.225838113057081e-05, + "loss": 0.4806, + "step": 101500 + }, + { + "epoch": 2.34, + "learning_rate": 4.222011778057234e-05, + "loss": 0.4813, + "step": 102000 + }, + { + "epoch": 2.36, + "learning_rate": 4.218177775051376e-05, + "loss": 0.4734, + "step": 102500 + }, + { + "epoch": 2.37, + "learning_rate": 4.214343772045518e-05, + "loss": 0.479, + "step": 103000 + }, + { + "epoch": 2.38, + "learning_rate": 4.210509769039659e-05, + "loss": 0.4778, + "step": 103500 + }, + { + "epoch": 2.39, + "learning_rate": 4.2066757660338006e-05, + "loss": 0.4797, + "step": 104000 + }, + { + "epoch": 2.4, + "learning_rate": 4.2028417630279424e-05, + "loss": 0.474, + "step": 104500 + }, + { + "epoch": 2.41, + "learning_rate": 4.199007760022084e-05, + "loss": 0.4811, + "step": 105000 + }, + { + "epoch": 2.43, + "learning_rate": 4.1951814250222374e-05, + "loss": 0.464, + "step": 105500 + }, + { + "epoch": 2.44, + "learning_rate": 4.191347422016379e-05, + "loss": 0.4699, + "step": 106000 + }, + { + "epoch": 2.45, + "learning_rate": 4.187513419010521e-05, + "loss": 0.4655, + "step": 106500 + }, + { + "epoch": 2.46, + "learning_rate": 4.183679416004662e-05, + "loss": 0.4694, + "step": 107000 + }, + { + "epoch": 2.47, + "learning_rate": 4.179845412998804e-05, + "loss": 0.4698, + "step": 107500 + }, + { + "epoch": 2.48, + "learning_rate": 4.1760114099929456e-05, + "loss": 0.4714, + "step": 108000 + }, + { + "epoch": 2.49, + "learning_rate": 4.1721774069870873e-05, + "loss": 0.4627, + "step": 108500 + }, + { + "epoch": 2.51, + "learning_rate": 4.168343403981229e-05, + "loss": 0.4628, + "step": 109000 + }, + { + "epoch": 2.52, + "learning_rate": 4.16450940097537e-05, + "loss": 0.4565, + "step": 109500 + }, + { + "epoch": 2.53, + "learning_rate": 4.1606753979695126e-05, + "loss": 0.466, + "step": 110000 + }, + { + "epoch": 2.54, + "learning_rate": 4.156841394963654e-05, + "loss": 0.4635, + "step": 110500 + }, + { + "epoch": 2.55, + "learning_rate": 4.1530073919577955e-05, + "loss": 0.4694, + "step": 111000 + }, + { + "epoch": 2.56, + "learning_rate": 4.149181056957949e-05, + "loss": 0.4638, + "step": 111500 + }, + { + "epoch": 2.57, + "learning_rate": 4.1453470539520905e-05, + "loss": 0.4626, + "step": 112000 + }, + { + "epoch": 2.59, + "learning_rate": 4.1415130509462316e-05, + "loss": 0.4632, + "step": 112500 + }, + { + "epoch": 2.6, + "learning_rate": 4.137679047940374e-05, + "loss": 0.455, + "step": 113000 + }, + { + "epoch": 2.61, + "learning_rate": 4.133845044934516e-05, + "loss": 0.4553, + "step": 113500 + }, + { + "epoch": 2.62, + "learning_rate": 4.130018709934669e-05, + "loss": 0.4583, + "step": 114000 + }, + { + "epoch": 2.63, + "learning_rate": 4.126192374934822e-05, + "loss": 0.4596, + "step": 114500 + }, + { + "epoch": 2.64, + "learning_rate": 4.1223583719289635e-05, + "loss": 0.4634, + "step": 115000 + }, + { + "epoch": 2.65, + "learning_rate": 4.118524368923106e-05, + "loss": 0.4595, + "step": 115500 + }, + { + "epoch": 2.67, + "learning_rate": 4.1146980339232585e-05, + "loss": 0.4441, + "step": 116000 + }, + { + "epoch": 2.68, + "learning_rate": 4.110864030917401e-05, + "loss": 0.4517, + "step": 116500 + }, + { + "epoch": 2.69, + "learning_rate": 4.107030027911542e-05, + "loss": 0.4531, + "step": 117000 + }, + { + "epoch": 2.7, + "learning_rate": 4.103196024905684e-05, + "loss": 0.4556, + "step": 117500 + }, + { + "epoch": 2.71, + "learning_rate": 4.099362021899825e-05, + "loss": 0.4481, + "step": 118000 + }, + { + "epoch": 2.72, + "learning_rate": 4.095528018893967e-05, + "loss": 0.4483, + "step": 118500 + }, + { + "epoch": 2.74, + "learning_rate": 4.0916940158881084e-05, + "loss": 0.4457, + "step": 119000 + }, + { + "epoch": 2.75, + "learning_rate": 4.08786001288225e-05, + "loss": 0.452, + "step": 119500 + }, + { + "epoch": 2.76, + "learning_rate": 4.084026009876392e-05, + "loss": 0.4511, + "step": 120000 + }, + { + "epoch": 2.77, + "learning_rate": 4.080192006870534e-05, + "loss": 0.4466, + "step": 120500 + }, + { + "epoch": 2.78, + "learning_rate": 4.0763580038646755e-05, + "loss": 0.4368, + "step": 121000 + }, + { + "epoch": 2.79, + "learning_rate": 4.0725240008588166e-05, + "loss": 0.443, + "step": 121500 + }, + { + "epoch": 2.8, + "learning_rate": 4.0686976658589705e-05, + "loss": 0.441, + "step": 122000 + }, + { + "epoch": 2.82, + "learning_rate": 4.0648636628531116e-05, + "loss": 0.4503, + "step": 122500 + }, + { + "epoch": 2.83, + "learning_rate": 4.0610296598472534e-05, + "loss": 0.4487, + "step": 123000 + }, + { + "epoch": 2.84, + "learning_rate": 4.057195656841395e-05, + "loss": 0.4482, + "step": 123500 + }, + { + "epoch": 2.85, + "learning_rate": 4.053361653835537e-05, + "loss": 0.4449, + "step": 124000 + }, + { + "epoch": 2.86, + "learning_rate": 4.049527650829679e-05, + "loss": 0.4514, + "step": 124500 + }, + { + "epoch": 2.87, + "learning_rate": 4.04569364782382e-05, + "loss": 0.4407, + "step": 125000 + }, + { + "epoch": 2.88, + "learning_rate": 4.041867312823974e-05, + "loss": 0.443, + "step": 125500 + }, + { + "epoch": 2.9, + "learning_rate": 4.038033309818115e-05, + "loss": 0.434, + "step": 126000 + }, + { + "epoch": 2.91, + "learning_rate": 4.0341993068122566e-05, + "loss": 0.4384, + "step": 126500 + }, + { + "epoch": 2.92, + "learning_rate": 4.030365303806398e-05, + "loss": 0.4334, + "step": 127000 + }, + { + "epoch": 2.93, + "learning_rate": 4.0265389688065516e-05, + "loss": 0.4419, + "step": 127500 + }, + { + "epoch": 2.94, + "learning_rate": 4.0227049658006934e-05, + "loss": 0.4421, + "step": 128000 + }, + { + "epoch": 2.95, + "learning_rate": 4.018870962794835e-05, + "loss": 0.4244, + "step": 128500 + }, + { + "epoch": 2.97, + "learning_rate": 4.015036959788976e-05, + "loss": 0.4345, + "step": 129000 + }, + { + "epoch": 2.98, + "learning_rate": 4.01121062478913e-05, + "loss": 0.4374, + "step": 129500 + }, + { + "epoch": 2.99, + "learning_rate": 4.007376621783271e-05, + "loss": 0.4368, + "step": 130000 + }, + { + "epoch": 3.0, + "learning_rate": 4.003542618777413e-05, + "loss": 0.4356, + "step": 130500 + }, + { + "epoch": 3.0, + "eval_bleu": 58.5493, + "eval_gen_len": 17.1569, + "eval_loss": 0.7014300227165222, + "eval_runtime": 7450.9373, + "eval_samples_per_second": 11.677, + "eval_steps_per_second": 1.46, + "step": 130513 + }, + { + "epoch": 3.01, + "learning_rate": 3.9997086157715555e-05, + "loss": 0.4373, + "step": 131000 + }, + { + "epoch": 3.02, + "learning_rate": 3.9958746127656966e-05, + "loss": 0.42, + "step": 131500 + }, + { + "epoch": 3.03, + "learning_rate": 3.992040609759838e-05, + "loss": 0.4179, + "step": 132000 + }, + { + "epoch": 3.05, + "learning_rate": 3.9882066067539794e-05, + "loss": 0.406, + "step": 132500 + }, + { + "epoch": 3.06, + "learning_rate": 3.984372603748122e-05, + "loss": 0.4034, + "step": 133000 + }, + { + "epoch": 3.07, + "learning_rate": 3.980538600742263e-05, + "loss": 0.4103, + "step": 133500 + }, + { + "epoch": 3.08, + "learning_rate": 3.976704597736405e-05, + "loss": 0.4084, + "step": 134000 + }, + { + "epoch": 3.09, + "learning_rate": 3.9728705947305465e-05, + "loss": 0.4012, + "step": 134500 + }, + { + "epoch": 3.1, + "learning_rate": 3.969036591724688e-05, + "loss": 0.3966, + "step": 135000 + }, + { + "epoch": 3.11, + "learning_rate": 3.96520258871883e-05, + "loss": 0.4026, + "step": 135500 + }, + { + "epoch": 3.13, + "learning_rate": 3.961368585712971e-05, + "loss": 0.3983, + "step": 136000 + }, + { + "epoch": 3.14, + "learning_rate": 3.957542250713125e-05, + "loss": 0.3947, + "step": 136500 + }, + { + "epoch": 3.15, + "learning_rate": 3.953708247707266e-05, + "loss": 0.3894, + "step": 137000 + }, + { + "epoch": 3.16, + "learning_rate": 3.94988191270742e-05, + "loss": 0.3927, + "step": 137500 + }, + { + "epoch": 3.17, + "learning_rate": 3.946047909701561e-05, + "loss": 0.3919, + "step": 138000 + }, + { + "epoch": 3.18, + "learning_rate": 3.942213906695703e-05, + "loss": 0.3909, + "step": 138500 + }, + { + "epoch": 3.2, + "learning_rate": 3.938379903689845e-05, + "loss": 0.3914, + "step": 139000 + }, + { + "epoch": 3.21, + "learning_rate": 3.9345459006839865e-05, + "loss": 0.3876, + "step": 139500 + }, + { + "epoch": 3.22, + "learning_rate": 3.930727233690151e-05, + "loss": 0.3844, + "step": 140000 + }, + { + "epoch": 3.23, + "learning_rate": 3.926893230684293e-05, + "loss": 0.3871, + "step": 140500 + }, + { + "epoch": 3.24, + "learning_rate": 3.923059227678435e-05, + "loss": 0.3835, + "step": 141000 + }, + { + "epoch": 3.25, + "learning_rate": 3.9192252246725766e-05, + "loss": 0.3871, + "step": 141500 + }, + { + "epoch": 3.26, + "learning_rate": 3.915391221666718e-05, + "loss": 0.3803, + "step": 142000 + }, + { + "epoch": 3.28, + "learning_rate": 3.9115572186608594e-05, + "loss": 0.3776, + "step": 142500 + }, + { + "epoch": 3.29, + "learning_rate": 3.907723215655001e-05, + "loss": 0.3742, + "step": 143000 + }, + { + "epoch": 3.3, + "learning_rate": 3.903889212649143e-05, + "loss": 0.3778, + "step": 143500 + }, + { + "epoch": 3.31, + "learning_rate": 3.900055209643285e-05, + "loss": 0.3759, + "step": 144000 + }, + { + "epoch": 3.32, + "learning_rate": 3.896221206637426e-05, + "loss": 0.3756, + "step": 144500 + }, + { + "epoch": 3.33, + "learning_rate": 3.89239487163758e-05, + "loss": 0.3737, + "step": 145000 + }, + { + "epoch": 3.34, + "learning_rate": 3.888560868631721e-05, + "loss": 0.3749, + "step": 145500 + }, + { + "epoch": 3.36, + "learning_rate": 3.884734533631875e-05, + "loss": 0.3701, + "step": 146000 + }, + { + "epoch": 3.37, + "learning_rate": 3.880900530626016e-05, + "loss": 0.3736, + "step": 146500 + }, + { + "epoch": 3.38, + "learning_rate": 3.8770665276201576e-05, + "loss": 0.3706, + "step": 147000 + }, + { + "epoch": 3.39, + "learning_rate": 3.8732325246143e-05, + "loss": 0.3743, + "step": 147500 + }, + { + "epoch": 3.4, + "learning_rate": 3.869398521608441e-05, + "loss": 0.3665, + "step": 148000 + }, + { + "epoch": 3.41, + "learning_rate": 3.865564518602583e-05, + "loss": 0.3781, + "step": 148500 + }, + { + "epoch": 3.42, + "learning_rate": 3.861738183602736e-05, + "loss": 0.3591, + "step": 149000 + }, + { + "epoch": 3.44, + "learning_rate": 3.857904180596878e-05, + "loss": 0.365, + "step": 149500 + }, + { + "epoch": 3.45, + "learning_rate": 3.854070177591019e-05, + "loss": 0.3648, + "step": 150000 + }, + { + "epoch": 3.46, + "learning_rate": 3.8502361745851615e-05, + "loss": 0.3635, + "step": 150500 + }, + { + "epoch": 3.47, + "learning_rate": 3.8464021715793026e-05, + "loss": 0.3658, + "step": 151000 + }, + { + "epoch": 3.48, + "learning_rate": 3.8425681685734444e-05, + "loss": 0.3666, + "step": 151500 + }, + { + "epoch": 3.49, + "learning_rate": 3.838734165567586e-05, + "loss": 0.3579, + "step": 152000 + }, + { + "epoch": 3.51, + "learning_rate": 3.834900162561728e-05, + "loss": 0.3582, + "step": 152500 + }, + { + "epoch": 3.52, + "learning_rate": 3.8310661595558697e-05, + "loss": 0.3554, + "step": 153000 + }, + { + "epoch": 3.53, + "learning_rate": 3.8272474925620344e-05, + "loss": 0.3645, + "step": 153500 + }, + { + "epoch": 3.54, + "learning_rate": 3.823421157562188e-05, + "loss": 0.3605, + "step": 154000 + }, + { + "epoch": 3.55, + "learning_rate": 3.8195871545563295e-05, + "loss": 0.3657, + "step": 154500 + }, + { + "epoch": 3.56, + "learning_rate": 3.8157531515504706e-05, + "loss": 0.362, + "step": 155000 + }, + { + "epoch": 3.57, + "learning_rate": 3.811919148544612e-05, + "loss": 0.3585, + "step": 155500 + }, + { + "epoch": 3.59, + "learning_rate": 3.808085145538755e-05, + "loss": 0.3606, + "step": 156000 + }, + { + "epoch": 3.6, + "learning_rate": 3.8042664785449196e-05, + "loss": 0.3539, + "step": 156500 + }, + { + "epoch": 3.61, + "learning_rate": 3.8004324755390606e-05, + "loss": 0.3543, + "step": 157000 + }, + { + "epoch": 3.62, + "learning_rate": 3.7966061405392146e-05, + "loss": 0.3599, + "step": 157500 + }, + { + "epoch": 3.63, + "learning_rate": 3.792772137533356e-05, + "loss": 0.3613, + "step": 158000 + }, + { + "epoch": 3.64, + "learning_rate": 3.7889381345274975e-05, + "loss": 0.3616, + "step": 158500 + }, + { + "epoch": 3.65, + "learning_rate": 3.78510413152164e-05, + "loss": 0.357, + "step": 159000 + }, + { + "epoch": 3.67, + "learning_rate": 3.781270128515781e-05, + "loss": 0.3444, + "step": 159500 + }, + { + "epoch": 3.68, + "learning_rate": 3.777436125509923e-05, + "loss": 0.35, + "step": 160000 + }, + { + "epoch": 3.69, + "learning_rate": 3.773602122504064e-05, + "loss": 0.3515, + "step": 160500 + }, + { + "epoch": 3.7, + "learning_rate": 3.769768119498206e-05, + "loss": 0.3571, + "step": 161000 + }, + { + "epoch": 3.71, + "learning_rate": 3.7659341164923474e-05, + "loss": 0.3484, + "step": 161500 + }, + { + "epoch": 3.72, + "learning_rate": 3.762100113486489e-05, + "loss": 0.3467, + "step": 162000 + }, + { + "epoch": 3.74, + "learning_rate": 3.758266110480631e-05, + "loss": 0.3489, + "step": 162500 + }, + { + "epoch": 3.75, + "learning_rate": 3.754432107474773e-05, + "loss": 0.3505, + "step": 163000 + }, + { + "epoch": 3.76, + "learning_rate": 3.7505981044689144e-05, + "loss": 0.351, + "step": 163500 + }, + { + "epoch": 3.77, + "learning_rate": 3.7467641014630555e-05, + "loss": 0.3486, + "step": 164000 + }, + { + "epoch": 3.78, + "learning_rate": 3.7429377664632095e-05, + "loss": 0.3394, + "step": 164500 + }, + { + "epoch": 3.79, + "learning_rate": 3.7391037634573506e-05, + "loss": 0.3445, + "step": 165000 + }, + { + "epoch": 3.8, + "learning_rate": 3.735269760451492e-05, + "loss": 0.3417, + "step": 165500 + }, + { + "epoch": 3.82, + "learning_rate": 3.731435757445634e-05, + "loss": 0.3492, + "step": 166000 + }, + { + "epoch": 3.83, + "learning_rate": 3.727601754439776e-05, + "loss": 0.3519, + "step": 166500 + }, + { + "epoch": 3.84, + "learning_rate": 3.7237677514339176e-05, + "loss": 0.3484, + "step": 167000 + }, + { + "epoch": 3.85, + "learning_rate": 3.719933748428059e-05, + "loss": 0.3446, + "step": 167500 + }, + { + "epoch": 3.86, + "learning_rate": 3.7160997454222005e-05, + "loss": 0.3499, + "step": 168000 + }, + { + "epoch": 3.87, + "learning_rate": 3.712265742416342e-05, + "loss": 0.3465, + "step": 168500 + }, + { + "epoch": 3.88, + "learning_rate": 3.708431739410484e-05, + "loss": 0.3431, + "step": 169000 + }, + { + "epoch": 3.9, + "learning_rate": 3.704597736404625e-05, + "loss": 0.3379, + "step": 169500 + }, + { + "epoch": 3.91, + "learning_rate": 3.700771401404779e-05, + "loss": 0.3402, + "step": 170000 + }, + { + "epoch": 3.92, + "learning_rate": 3.69693739839892e-05, + "loss": 0.3379, + "step": 170500 + }, + { + "epoch": 3.93, + "learning_rate": 3.6931187314050856e-05, + "loss": 0.3468, + "step": 171000 + }, + { + "epoch": 3.94, + "learning_rate": 3.6892847283992274e-05, + "loss": 0.3433, + "step": 171500 + }, + { + "epoch": 3.95, + "learning_rate": 3.685450725393369e-05, + "loss": 0.3305, + "step": 172000 + }, + { + "epoch": 3.97, + "learning_rate": 3.68161672238751e-05, + "loss": 0.3373, + "step": 172500 + }, + { + "epoch": 3.98, + "learning_rate": 3.677782719381652e-05, + "loss": 0.3426, + "step": 173000 + }, + { + "epoch": 3.99, + "learning_rate": 3.673948716375794e-05, + "loss": 0.3387, + "step": 173500 + }, + { + "epoch": 4.0, + "learning_rate": 3.6701147133699355e-05, + "loss": 0.3407, + "step": 174000 + }, + { + "epoch": 4.0, + "eval_bleu": 58.3826, + "eval_gen_len": 17.1623, + "eval_loss": 0.7513108253479004, + "eval_runtime": 7458.9074, + "eval_samples_per_second": 11.665, + "eval_steps_per_second": 1.458, + "step": 174018 + } + ], + "logging_steps": 500, + "max_steps": 652560, + "num_train_epochs": 15, + "save_steps": 500, + "total_flos": 6.033913407575425e+18, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-174018/training_args.bin b/checkpoint-174018/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4d3d8487ffcaca78bad3b458878633a19376556 --- /dev/null +++ b/checkpoint-174018/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b731ecd386cb51a958b6c8f191496c616dc6e80b60cf4e62402772da333973 +size 4792 diff --git a/checkpoint-217522/config.json b/checkpoint-217522/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d123d026fa1d1679aeb1220d9ae316d7c13a0b --- /dev/null +++ b/checkpoint-217522/config.json @@ -0,0 +1,59 @@ +{ + "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt", + "_num_labels": 3, + "activation_dropout": 0.0, + "activation_function": "relu", + "add_bias_logits": false, + "add_final_layer_norm": true, + "architectures": [ + "MBartForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "classif_dropout": 0.0, + "classifier_dropout": 0.0, + "d_model": 1024, + "decoder_attention_heads": 16, + "decoder_ffn_dim": 4096, + "decoder_layerdrop": 0.0, + "decoder_layers": 12, + "decoder_start_token_id": 2, + "dropout": 0.1, + "early_stopping": true, + "encoder_attention_heads": 16, + "encoder_ffn_dim": 4096, + "encoder_layerdrop": 0.0, + "encoder_layers": 12, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "gradient_checkpointing": false, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "init_std": 0.02, + "is_encoder_decoder": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "max_length": 200, + "max_position_embeddings": 1024, + "model_type": "mbart", + "normalize_before": true, + "normalize_embedding": true, + "num_beams": 5, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "scale_embedding": true, + "static_position_embeddings": false, + "tokenizer_class": "MBart50Tokenizer", + "torch_dtype": "float32", + "transformers_version": "4.35.2", + "use_cache": true, + "vocab_size": 250054 +} diff --git a/checkpoint-217522/generation_config.json b/checkpoint-217522/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7e47c12e3900189593d4b56d0d776b58a7a55627 --- /dev/null +++ b/checkpoint-217522/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 0, + "decoder_start_token_id": 2, + "early_stopping": true, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "max_length": 200, + "num_beams": 5, + "pad_token_id": 1, + "transformers_version": "4.35.2" +} diff --git a/checkpoint-217522/model.safetensors b/checkpoint-217522/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab91140fca9e0d9d4f9ae32a8f0a4b3401215fc3 --- /dev/null +++ b/checkpoint-217522/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f483628a61a16b96d004b6c15d7a8f0196b924e9da08ab70634354fc3e31bbd +size 2444578688 diff --git a/checkpoint-217522/optimizer.pt b/checkpoint-217522/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5da1ca2ad4de7e25aee85491aa71c7d504496231 --- /dev/null +++ b/checkpoint-217522/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc05c66900a46905498e552a47d88fbf72f824f694a3ac142b78c47a632fc7e +size 4887473903 diff --git a/checkpoint-217522/rng_state_0.pth b/checkpoint-217522/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..726151d98b4c21c8b03a156f78a1e89faea05355 --- /dev/null +++ b/checkpoint-217522/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e20bd68a94dfb12a00842c4621b9aab9cb01297bcf5dfa75acaba869daa6ce4 +size 15024 diff --git a/checkpoint-217522/rng_state_1.pth b/checkpoint-217522/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..78d97cb516983afdcded9e856015f8e9d117e256 --- /dev/null +++ b/checkpoint-217522/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91e7f7025b35efbebc869df10cc4e03d5923936d61c9d83522f9ae760cd35ba +size 15024 diff --git a/checkpoint-217522/rng_state_2.pth b/checkpoint-217522/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..290854594d3af6e2817f78a1353e8164ef9df326 --- /dev/null +++ b/checkpoint-217522/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d42a837bd8226393744dd25070e85314f195de1485948f0b41179b2b638de1 +size 15024 diff --git a/checkpoint-217522/rng_state_3.pth b/checkpoint-217522/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ca44e11621d4fa998a263d4979eff59ec1a80ee --- /dev/null +++ b/checkpoint-217522/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5503ecc7d239f16aee50cab50682649946e62d726975c770d4a0259e0e5f99a7 +size 15024 diff --git a/checkpoint-217522/scheduler.pt b/checkpoint-217522/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cc0042230bedc058cf7bbf01341d4776a51a89d --- /dev/null +++ b/checkpoint-217522/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a003699053bdedc83a81d5fd5df4cbde1d80ee6dd5c97a23605d18cea26d06b9 +size 1064 diff --git a/checkpoint-217522/sentencepiece.bpe.model b/checkpoint-217522/sentencepiece.bpe.model new file mode 100644 index 0000000000000000000000000000000000000000..7a3f40a75f870bc1f21700cd414dc2acc431583c --- /dev/null +++ b/checkpoint-217522/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/checkpoint-217522/special_tokens_map.json b/checkpoint-217522/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92619141640d5fcbb4429807de2248352b0dca79 --- /dev/null +++ b/checkpoint-217522/special_tokens_map.json @@ -0,0 +1,69 @@ +{ + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "cls_token": "", + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/checkpoint-217522/tokenizer.json b/checkpoint-217522/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86f15e5a3339d518716121ecef4c2a1dc9208b40 --- /dev/null +++ b/checkpoint-217522/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf1fb0f45fdd5ae9fc44fafee492652a423fc749833ef57c2fa801358549d92 +size 17110107 diff --git a/checkpoint-217522/tokenizer_config.json b/checkpoint-217522/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..70c0515a5815fcc727e11e053116348bfac12128 --- /dev/null +++ b/checkpoint-217522/tokenizer_config.json @@ -0,0 +1,528 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250001": { + "content": "ar_AR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250002": { + "content": "cs_CZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250003": { + "content": "de_DE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250004": { + "content": "en_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250005": { + "content": "es_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250006": { + "content": "et_EE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250007": { + "content": "fi_FI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250008": { + "content": "fr_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250009": { + "content": "gu_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250010": { + "content": "hi_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250011": { + "content": "it_IT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250012": { + "content": "ja_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250013": { + "content": "kk_KZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250014": { + "content": "ko_KR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250015": { + "content": "lt_LT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250016": { + "content": "lv_LV", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250017": { + "content": "my_MM", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250018": { + "content": "ne_NP", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250019": { + "content": "nl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250020": { + "content": "ro_RO", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250021": { + "content": "ru_RU", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250022": { + "content": "si_LK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250023": { + "content": "tr_TR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250024": { + "content": "vi_VN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250025": { + "content": "zh_CN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250026": { + "content": "af_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250027": { + "content": "az_AZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250028": { + "content": "bn_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250029": { + "content": "fa_IR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250030": { + "content": "he_IL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250031": { + "content": "hr_HR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250032": { + "content": "id_ID", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250033": { + "content": "ka_GE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250034": { + "content": "km_KH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250035": { + "content": "mk_MK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250036": { + "content": "ml_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250037": { + "content": "mn_MN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250038": { + "content": "mr_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250039": { + "content": "pl_PL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250040": { + "content": "ps_AF", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250041": { + "content": "pt_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250042": { + "content": "sv_SE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250043": { + "content": "sw_KE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250044": { + "content": "ta_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250045": { + "content": "te_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250046": { + "content": "th_TH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250047": { + "content": "tl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250048": { + "content": "uk_UA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250049": { + "content": "ur_PK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250050": { + "content": "xh_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250051": { + "content": "gl_ES", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250052": { + "content": "sl_SI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250053": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "clean_up_tokenization_spaces": true, + "cls_token": "", + "eos_token": "", + "language_codes": "ML50", + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "sp_model_kwargs": {}, + "src_lang": "ja_XX", + "tgt_lang": "ko_KR", + "tokenizer_class": "MBart50Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-217522/trainer_state.json b/checkpoint-217522/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1543b705efa42961757340bb888f096ae942bd28 --- /dev/null +++ b/checkpoint-217522/trainer_state.json @@ -0,0 +1,2679 @@ +{ + "best_metric": 0.6814723610877991, + "best_model_checkpoint": "./jako_mbartLarge_100p_run1/checkpoint-87009", + "epoch": 4.999988506936064, + "eval_steps": 500, + "global_step": 217522, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 4.97e-05, + "loss": 1.9891, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 4.996196669018189e-05, + "loss": 1.5354, + "step": 1000 + }, + { + "epoch": 0.03, + "learning_rate": 4.9923626660123305e-05, + "loss": 1.3833, + "step": 1500 + }, + { + "epoch": 0.05, + "learning_rate": 4.988528663006472e-05, + "loss": 1.2912, + "step": 2000 + }, + { + "epoch": 0.06, + "learning_rate": 4.984694660000614e-05, + "loss": 1.2355, + "step": 2500 + }, + { + "epoch": 0.07, + "learning_rate": 4.980860656994755e-05, + "loss": 1.1927, + "step": 3000 + }, + { + "epoch": 0.08, + "learning_rate": 4.977026653988897e-05, + "loss": 1.166, + "step": 3500 + }, + { + "epoch": 0.09, + "learning_rate": 4.9731926509830386e-05, + "loss": 1.1238, + "step": 4000 + }, + { + "epoch": 0.1, + "learning_rate": 4.9693586479771804e-05, + "loss": 1.0972, + "step": 4500 + }, + { + "epoch": 0.11, + "learning_rate": 4.9655246449713215e-05, + "loss": 1.0964, + "step": 5000 + }, + { + "epoch": 0.13, + "learning_rate": 4.961690641965463e-05, + "loss": 1.0611, + "step": 5500 + }, + { + "epoch": 0.14, + "learning_rate": 4.957871974971629e-05, + "loss": 1.0487, + "step": 6000 + }, + { + "epoch": 0.15, + "learning_rate": 4.9540379719657705e-05, + "loss": 1.0166, + "step": 6500 + }, + { + "epoch": 0.16, + "learning_rate": 4.9502039689599116e-05, + "loss": 1.0162, + "step": 7000 + }, + { + "epoch": 0.17, + "learning_rate": 4.946369965954053e-05, + "loss": 0.9952, + "step": 7500 + }, + { + "epoch": 0.18, + "learning_rate": 4.942535962948195e-05, + "loss": 0.9853, + "step": 8000 + }, + { + "epoch": 0.2, + "learning_rate": 4.9387096279483484e-05, + "loss": 0.9835, + "step": 8500 + }, + { + "epoch": 0.21, + "learning_rate": 4.9348832929485017e-05, + "loss": 0.9634, + "step": 9000 + }, + { + "epoch": 0.22, + "learning_rate": 4.9310492899426434e-05, + "loss": 0.9532, + "step": 9500 + }, + { + "epoch": 0.23, + "learning_rate": 4.927215286936785e-05, + "loss": 0.955, + "step": 10000 + }, + { + "epoch": 0.24, + "learning_rate": 4.923381283930927e-05, + "loss": 0.9392, + "step": 10500 + }, + { + "epoch": 0.25, + "learning_rate": 4.919547280925069e-05, + "loss": 0.9403, + "step": 11000 + }, + { + "epoch": 0.26, + "learning_rate": 4.91571327791921e-05, + "loss": 0.9177, + "step": 11500 + }, + { + "epoch": 0.28, + "learning_rate": 4.9118792749133516e-05, + "loss": 0.919, + "step": 12000 + }, + { + "epoch": 0.29, + "learning_rate": 4.908045271907493e-05, + "loss": 0.9036, + "step": 12500 + }, + { + "epoch": 0.3, + "learning_rate": 4.9042189369076466e-05, + "loss": 0.9019, + "step": 13000 + }, + { + "epoch": 0.31, + "learning_rate": 4.9003849339017884e-05, + "loss": 0.8969, + "step": 13500 + }, + { + "epoch": 0.32, + "learning_rate": 4.89655093089593e-05, + "loss": 0.891, + "step": 14000 + }, + { + "epoch": 0.33, + "learning_rate": 4.892716927890072e-05, + "loss": 0.8904, + "step": 14500 + }, + { + "epoch": 0.34, + "learning_rate": 4.888882924884213e-05, + "loss": 0.8833, + "step": 15000 + }, + { + "epoch": 0.36, + "learning_rate": 4.8850489218783554e-05, + "loss": 0.8668, + "step": 15500 + }, + { + "epoch": 0.37, + "learning_rate": 4.8812149188724965e-05, + "loss": 0.8692, + "step": 16000 + }, + { + "epoch": 0.38, + "learning_rate": 4.877380915866638e-05, + "loss": 0.8617, + "step": 16500 + }, + { + "epoch": 0.39, + "learning_rate": 4.8735469128607794e-05, + "loss": 0.866, + "step": 17000 + }, + { + "epoch": 0.4, + "learning_rate": 4.869720577860933e-05, + "loss": 0.8592, + "step": 17500 + }, + { + "epoch": 0.41, + "learning_rate": 4.8658865748550744e-05, + "loss": 0.8586, + "step": 18000 + }, + { + "epoch": 0.43, + "learning_rate": 4.862052571849217e-05, + "loss": 0.84, + "step": 18500 + }, + { + "epoch": 0.44, + "learning_rate": 4.8582262368493695e-05, + "loss": 0.84, + "step": 19000 + }, + { + "epoch": 0.45, + "learning_rate": 4.854392233843512e-05, + "loss": 0.8397, + "step": 19500 + }, + { + "epoch": 0.46, + "learning_rate": 4.850581234855688e-05, + "loss": 0.8338, + "step": 20000 + }, + { + "epoch": 0.47, + "learning_rate": 4.84674723184983e-05, + "loss": 0.838, + "step": 20500 + }, + { + "epoch": 0.48, + "learning_rate": 4.842913228843972e-05, + "loss": 0.8391, + "step": 21000 + }, + { + "epoch": 0.49, + "learning_rate": 4.8390792258381135e-05, + "loss": 0.8276, + "step": 21500 + }, + { + "epoch": 0.51, + "learning_rate": 4.8352452228322546e-05, + "loss": 0.8198, + "step": 22000 + }, + { + "epoch": 0.52, + "learning_rate": 4.8314112198263963e-05, + "loss": 0.8127, + "step": 22500 + }, + { + "epoch": 0.53, + "learning_rate": 4.827577216820538e-05, + "loss": 0.8184, + "step": 23000 + }, + { + "epoch": 0.54, + "learning_rate": 4.82374321381468e-05, + "loss": 0.817, + "step": 23500 + }, + { + "epoch": 0.55, + "learning_rate": 4.8199092108088216e-05, + "loss": 0.8196, + "step": 24000 + }, + { + "epoch": 0.56, + "learning_rate": 4.816075207802963e-05, + "loss": 0.8024, + "step": 24500 + }, + { + "epoch": 0.57, + "learning_rate": 4.812241204797105e-05, + "loss": 0.8133, + "step": 25000 + }, + { + "epoch": 0.59, + "learning_rate": 4.808407201791246e-05, + "loss": 0.8056, + "step": 25500 + }, + { + "epoch": 0.6, + "learning_rate": 4.804573198785388e-05, + "loss": 0.7972, + "step": 26000 + }, + { + "epoch": 0.61, + "learning_rate": 4.80073919577953e-05, + "loss": 0.8026, + "step": 26500 + }, + { + "epoch": 0.62, + "learning_rate": 4.7969051927736716e-05, + "loss": 0.7983, + "step": 27000 + }, + { + "epoch": 0.63, + "learning_rate": 4.793078857773824e-05, + "loss": 0.795, + "step": 27500 + }, + { + "epoch": 0.64, + "learning_rate": 4.7892448547679666e-05, + "loss": 0.803, + "step": 28000 + }, + { + "epoch": 0.66, + "learning_rate": 4.7854108517621084e-05, + "loss": 0.7911, + "step": 28500 + }, + { + "epoch": 0.67, + "learning_rate": 4.7815768487562494e-05, + "loss": 0.7757, + "step": 29000 + }, + { + "epoch": 0.68, + "learning_rate": 4.777742845750391e-05, + "loss": 0.777, + "step": 29500 + }, + { + "epoch": 0.69, + "learning_rate": 4.773908842744533e-05, + "loss": 0.7848, + "step": 30000 + }, + { + "epoch": 0.7, + "learning_rate": 4.770074839738675e-05, + "loss": 0.7834, + "step": 30500 + }, + { + "epoch": 0.71, + "learning_rate": 4.766240836732816e-05, + "loss": 0.7753, + "step": 31000 + }, + { + "epoch": 0.72, + "learning_rate": 4.7624068337269576e-05, + "loss": 0.7715, + "step": 31500 + }, + { + "epoch": 0.74, + "learning_rate": 4.7585728307211e-05, + "loss": 0.7714, + "step": 32000 + }, + { + "epoch": 0.75, + "learning_rate": 4.754738827715241e-05, + "loss": 0.7736, + "step": 32500 + }, + { + "epoch": 0.76, + "learning_rate": 4.750904824709383e-05, + "loss": 0.7767, + "step": 33000 + }, + { + "epoch": 0.77, + "learning_rate": 4.747070821703524e-05, + "loss": 0.7661, + "step": 33500 + }, + { + "epoch": 0.78, + "learning_rate": 4.7432368186976664e-05, + "loss": 0.7565, + "step": 34000 + }, + { + "epoch": 0.79, + "learning_rate": 4.739410483697819e-05, + "loss": 0.7515, + "step": 34500 + }, + { + "epoch": 0.8, + "learning_rate": 4.735584148697973e-05, + "loss": 0.7558, + "step": 35000 + }, + { + "epoch": 0.82, + "learning_rate": 4.731750145692114e-05, + "loss": 0.7642, + "step": 35500 + }, + { + "epoch": 0.83, + "learning_rate": 4.727916142686256e-05, + "loss": 0.7626, + "step": 36000 + }, + { + "epoch": 0.84, + "learning_rate": 4.7240821396803976e-05, + "loss": 0.7627, + "step": 36500 + }, + { + "epoch": 0.85, + "learning_rate": 4.7202481366745394e-05, + "loss": 0.7495, + "step": 37000 + }, + { + "epoch": 0.86, + "learning_rate": 4.716414133668681e-05, + "loss": 0.7582, + "step": 37500 + }, + { + "epoch": 0.87, + "learning_rate": 4.7125877986688344e-05, + "loss": 0.7481, + "step": 38000 + }, + { + "epoch": 0.88, + "learning_rate": 4.708753795662976e-05, + "loss": 0.7557, + "step": 38500 + }, + { + "epoch": 0.9, + "learning_rate": 4.704919792657117e-05, + "loss": 0.7384, + "step": 39000 + }, + { + "epoch": 0.91, + "learning_rate": 4.70108578965126e-05, + "loss": 0.742, + "step": 39500 + }, + { + "epoch": 0.92, + "learning_rate": 4.697251786645401e-05, + "loss": 0.7388, + "step": 40000 + }, + { + "epoch": 0.93, + "learning_rate": 4.6934177836395425e-05, + "loss": 0.7503, + "step": 40500 + }, + { + "epoch": 0.94, + "learning_rate": 4.689583780633684e-05, + "loss": 0.745, + "step": 41000 + }, + { + "epoch": 0.95, + "learning_rate": 4.685749777627826e-05, + "loss": 0.7228, + "step": 41500 + }, + { + "epoch": 0.97, + "learning_rate": 4.681915774621968e-05, + "loss": 0.7333, + "step": 42000 + }, + { + "epoch": 0.98, + "learning_rate": 4.678081771616109e-05, + "loss": 0.7371, + "step": 42500 + }, + { + "epoch": 0.99, + "learning_rate": 4.674247768610251e-05, + "loss": 0.733, + "step": 43000 + }, + { + "epoch": 1.0, + "learning_rate": 4.6704137656043925e-05, + "loss": 0.7241, + "step": 43500 + }, + { + "epoch": 1.0, + "eval_bleu": 56.112, + "eval_gen_len": 17.3165, + "eval_loss": 0.7177675366401672, + "eval_runtime": 7671.1849, + "eval_samples_per_second": 11.342, + "eval_steps_per_second": 1.418, + "step": 43504 + }, + { + "epoch": 1.01, + "learning_rate": 4.666587430604546e-05, + "loss": 0.7322, + "step": 44000 + }, + { + "epoch": 1.02, + "learning_rate": 4.6627534275986875e-05, + "loss": 0.7051, + "step": 44500 + }, + { + "epoch": 1.03, + "learning_rate": 4.658919424592829e-05, + "loss": 0.6935, + "step": 45000 + }, + { + "epoch": 1.05, + "learning_rate": 4.6550854215869704e-05, + "loss": 0.6831, + "step": 45500 + }, + { + "epoch": 1.06, + "learning_rate": 4.651259086587124e-05, + "loss": 0.6787, + "step": 46000 + }, + { + "epoch": 1.07, + "learning_rate": 4.6474327515872776e-05, + "loss": 0.6813, + "step": 46500 + }, + { + "epoch": 1.08, + "learning_rate": 4.6436140845934424e-05, + "loss": 0.6841, + "step": 47000 + }, + { + "epoch": 1.09, + "learning_rate": 4.639780081587584e-05, + "loss": 0.6697, + "step": 47500 + }, + { + "epoch": 1.1, + "learning_rate": 4.635946078581726e-05, + "loss": 0.6605, + "step": 48000 + }, + { + "epoch": 1.11, + "learning_rate": 4.632112075575868e-05, + "loss": 0.675, + "step": 48500 + }, + { + "epoch": 1.13, + "learning_rate": 4.6282780725700094e-05, + "loss": 0.6623, + "step": 49000 + }, + { + "epoch": 1.14, + "learning_rate": 4.6244440695641505e-05, + "loss": 0.6589, + "step": 49500 + }, + { + "epoch": 1.15, + "learning_rate": 4.620610066558292e-05, + "loss": 0.6476, + "step": 50000 + }, + { + "epoch": 1.16, + "learning_rate": 4.616776063552434e-05, + "loss": 0.6551, + "step": 50500 + }, + { + "epoch": 1.17, + "learning_rate": 4.612942060546576e-05, + "loss": 0.6502, + "step": 51000 + }, + { + "epoch": 1.18, + "learning_rate": 4.6091080575407176e-05, + "loss": 0.6478, + "step": 51500 + }, + { + "epoch": 1.2, + "learning_rate": 4.605274054534859e-05, + "loss": 0.6485, + "step": 52000 + }, + { + "epoch": 1.21, + "learning_rate": 4.6014400515290004e-05, + "loss": 0.6412, + "step": 52500 + }, + { + "epoch": 1.22, + "learning_rate": 4.597606048523142e-05, + "loss": 0.6376, + "step": 53000 + }, + { + "epoch": 1.23, + "learning_rate": 4.593772045517284e-05, + "loss": 0.6385, + "step": 53500 + }, + { + "epoch": 1.24, + "learning_rate": 4.589945710517437e-05, + "loss": 0.6366, + "step": 54000 + }, + { + "epoch": 1.25, + "learning_rate": 4.586111707511579e-05, + "loss": 0.6444, + "step": 54500 + }, + { + "epoch": 1.26, + "learning_rate": 4.582277704505721e-05, + "loss": 0.6311, + "step": 55000 + }, + { + "epoch": 1.28, + "learning_rate": 4.578451369505874e-05, + "loss": 0.6306, + "step": 55500 + }, + { + "epoch": 1.29, + "learning_rate": 4.574617366500016e-05, + "loss": 0.6199, + "step": 56000 + }, + { + "epoch": 1.3, + "learning_rate": 4.570783363494157e-05, + "loss": 0.6268, + "step": 56500 + }, + { + "epoch": 1.31, + "learning_rate": 4.566949360488299e-05, + "loss": 0.623, + "step": 57000 + }, + { + "epoch": 1.32, + "learning_rate": 4.5631153574824404e-05, + "loss": 0.6207, + "step": 57500 + }, + { + "epoch": 1.33, + "learning_rate": 4.559281354476582e-05, + "loss": 0.6204, + "step": 58000 + }, + { + "epoch": 1.34, + "learning_rate": 4.555447351470723e-05, + "loss": 0.6215, + "step": 58500 + }, + { + "epoch": 1.36, + "learning_rate": 4.551613348464866e-05, + "loss": 0.6114, + "step": 59000 + }, + { + "epoch": 1.37, + "learning_rate": 4.5477793454590075e-05, + "loss": 0.6134, + "step": 59500 + }, + { + "epoch": 1.38, + "learning_rate": 4.543953010459161e-05, + "loss": 0.6142, + "step": 60000 + }, + { + "epoch": 1.39, + "learning_rate": 4.5401190074533025e-05, + "loss": 0.6149, + "step": 60500 + }, + { + "epoch": 1.4, + "learning_rate": 4.5362850044474436e-05, + "loss": 0.6123, + "step": 61000 + }, + { + "epoch": 1.41, + "learning_rate": 4.5324510014415854e-05, + "loss": 0.6159, + "step": 61500 + }, + { + "epoch": 1.43, + "learning_rate": 4.5286246664417387e-05, + "loss": 0.6001, + "step": 62000 + }, + { + "epoch": 1.44, + "learning_rate": 4.5247906634358804e-05, + "loss": 0.6034, + "step": 62500 + }, + { + "epoch": 1.45, + "learning_rate": 4.520956660430022e-05, + "loss": 0.5999, + "step": 63000 + }, + { + "epoch": 1.46, + "learning_rate": 4.517122657424164e-05, + "loss": 0.6011, + "step": 63500 + }, + { + "epoch": 1.47, + "learning_rate": 4.513288654418305e-05, + "loss": 0.6051, + "step": 64000 + }, + { + "epoch": 1.48, + "learning_rate": 4.509454651412447e-05, + "loss": 0.6061, + "step": 64500 + }, + { + "epoch": 1.49, + "learning_rate": 4.5056206484065886e-05, + "loss": 0.598, + "step": 65000 + }, + { + "epoch": 1.51, + "learning_rate": 4.50178664540073e-05, + "loss": 0.5939, + "step": 65500 + }, + { + "epoch": 1.52, + "learning_rate": 4.497952642394872e-05, + "loss": 0.5905, + "step": 66000 + }, + { + "epoch": 1.53, + "learning_rate": 4.494118639389013e-05, + "loss": 0.5968, + "step": 66500 + }, + { + "epoch": 1.54, + "learning_rate": 4.490284636383155e-05, + "loss": 0.5943, + "step": 67000 + }, + { + "epoch": 1.55, + "learning_rate": 4.486450633377297e-05, + "loss": 0.6025, + "step": 67500 + }, + { + "epoch": 1.56, + "learning_rate": 4.4826166303714385e-05, + "loss": 0.5918, + "step": 68000 + }, + { + "epoch": 1.57, + "learning_rate": 4.47878262736558e-05, + "loss": 0.5983, + "step": 68500 + }, + { + "epoch": 1.59, + "learning_rate": 4.474948624359721e-05, + "loss": 0.5907, + "step": 69000 + }, + { + "epoch": 1.6, + "learning_rate": 4.471114621353864e-05, + "loss": 0.5852, + "step": 69500 + }, + { + "epoch": 1.61, + "learning_rate": 4.4672882863540164e-05, + "loss": 0.5886, + "step": 70000 + }, + { + "epoch": 1.62, + "learning_rate": 4.463454283348159e-05, + "loss": 0.5895, + "step": 70500 + }, + { + "epoch": 1.63, + "learning_rate": 4.4596202803423e-05, + "loss": 0.5887, + "step": 71000 + }, + { + "epoch": 1.64, + "learning_rate": 4.455786277336442e-05, + "loss": 0.5953, + "step": 71500 + }, + { + "epoch": 1.66, + "learning_rate": 4.451952274330583e-05, + "loss": 0.5888, + "step": 72000 + }, + { + "epoch": 1.67, + "learning_rate": 4.448118271324725e-05, + "loss": 0.571, + "step": 72500 + }, + { + "epoch": 1.68, + "learning_rate": 4.444291936324878e-05, + "loss": 0.576, + "step": 73000 + }, + { + "epoch": 1.69, + "learning_rate": 4.44045793331902e-05, + "loss": 0.5828, + "step": 73500 + }, + { + "epoch": 1.7, + "learning_rate": 4.436631598319173e-05, + "loss": 0.5875, + "step": 74000 + }, + { + "epoch": 1.71, + "learning_rate": 4.432797595313315e-05, + "loss": 0.5773, + "step": 74500 + }, + { + "epoch": 1.72, + "learning_rate": 4.428963592307457e-05, + "loss": 0.5741, + "step": 75000 + }, + { + "epoch": 1.74, + "learning_rate": 4.425129589301598e-05, + "loss": 0.5721, + "step": 75500 + }, + { + "epoch": 1.75, + "learning_rate": 4.42129558629574e-05, + "loss": 0.5797, + "step": 76000 + }, + { + "epoch": 1.76, + "learning_rate": 4.417461583289882e-05, + "loss": 0.5787, + "step": 76500 + }, + { + "epoch": 1.77, + "learning_rate": 4.4136275802840234e-05, + "loss": 0.5731, + "step": 77000 + }, + { + "epoch": 1.78, + "learning_rate": 4.409801245284177e-05, + "loss": 0.5642, + "step": 77500 + }, + { + "epoch": 1.79, + "learning_rate": 4.4059672422783185e-05, + "loss": 0.5653, + "step": 78000 + }, + { + "epoch": 1.8, + "learning_rate": 4.4021332392724596e-05, + "loss": 0.5663, + "step": 78500 + }, + { + "epoch": 1.82, + "learning_rate": 4.398299236266601e-05, + "loss": 0.5762, + "step": 79000 + }, + { + "epoch": 1.83, + "learning_rate": 4.394465233260743e-05, + "loss": 0.5742, + "step": 79500 + }, + { + "epoch": 1.84, + "learning_rate": 4.390631230254885e-05, + "loss": 0.5739, + "step": 80000 + }, + { + "epoch": 1.85, + "learning_rate": 4.3867972272490266e-05, + "loss": 0.5686, + "step": 80500 + }, + { + "epoch": 1.86, + "learning_rate": 4.382963224243168e-05, + "loss": 0.5757, + "step": 81000 + }, + { + "epoch": 1.87, + "learning_rate": 4.3791292212373095e-05, + "loss": 0.5654, + "step": 81500 + }, + { + "epoch": 1.88, + "learning_rate": 4.375295218231451e-05, + "loss": 0.5697, + "step": 82000 + }, + { + "epoch": 1.9, + "learning_rate": 4.371461215225593e-05, + "loss": 0.5582, + "step": 82500 + }, + { + "epoch": 1.91, + "learning_rate": 4.367627212219735e-05, + "loss": 0.5603, + "step": 83000 + }, + { + "epoch": 1.92, + "learning_rate": 4.363793209213876e-05, + "loss": 0.5564, + "step": 83500 + }, + { + "epoch": 1.93, + "learning_rate": 4.359959206208018e-05, + "loss": 0.5682, + "step": 84000 + }, + { + "epoch": 1.94, + "learning_rate": 4.356132871208171e-05, + "loss": 0.566, + "step": 84500 + }, + { + "epoch": 1.95, + "learning_rate": 4.3522988682023133e-05, + "loss": 0.5485, + "step": 85000 + }, + { + "epoch": 1.97, + "learning_rate": 4.3484648651964544e-05, + "loss": 0.5558, + "step": 85500 + }, + { + "epoch": 1.98, + "learning_rate": 4.344630862190596e-05, + "loss": 0.5592, + "step": 86000 + }, + { + "epoch": 1.99, + "learning_rate": 4.340796859184737e-05, + "loss": 0.5611, + "step": 86500 + }, + { + "epoch": 2.0, + "learning_rate": 4.337001196208938e-05, + "loss": 0.5523, + "step": 87000 + }, + { + "epoch": 2.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7592.1301, + "eval_samples_per_second": 11.46, + "eval_steps_per_second": 1.433, + "step": 87009 + }, + { + "epoch": 2.01, + "learning_rate": 4.33316719320308e-05, + "loss": 0.5617, + "step": 87500 + }, + { + "epoch": 2.02, + "learning_rate": 4.3293331901972215e-05, + "loss": 0.5392, + "step": 88000 + }, + { + "epoch": 2.03, + "learning_rate": 4.325499187191363e-05, + "loss": 0.5313, + "step": 88500 + }, + { + "epoch": 2.05, + "learning_rate": 4.321665184185504e-05, + "loss": 0.5247, + "step": 89000 + }, + { + "epoch": 2.06, + "learning_rate": 4.317831181179646e-05, + "loss": 0.5183, + "step": 89500 + }, + { + "epoch": 2.07, + "learning_rate": 4.313997178173788e-05, + "loss": 0.5266, + "step": 90000 + }, + { + "epoch": 2.08, + "learning_rate": 4.3101631751679296e-05, + "loss": 0.5256, + "step": 90500 + }, + { + "epoch": 2.09, + "learning_rate": 4.3063291721620714e-05, + "loss": 0.5148, + "step": 91000 + }, + { + "epoch": 2.1, + "learning_rate": 4.3024951691562125e-05, + "loss": 0.5097, + "step": 91500 + }, + { + "epoch": 2.11, + "learning_rate": 4.298661166150354e-05, + "loss": 0.5192, + "step": 92000 + }, + { + "epoch": 2.13, + "learning_rate": 4.294827163144496e-05, + "loss": 0.5125, + "step": 92500 + }, + { + "epoch": 2.14, + "learning_rate": 4.290993160138638e-05, + "loss": 0.5049, + "step": 93000 + }, + { + "epoch": 2.15, + "learning_rate": 4.2871591571327795e-05, + "loss": 0.4974, + "step": 93500 + }, + { + "epoch": 2.16, + "learning_rate": 4.2833251541269206e-05, + "loss": 0.5044, + "step": 94000 + }, + { + "epoch": 2.17, + "learning_rate": 4.279491151121063e-05, + "loss": 0.5026, + "step": 94500 + }, + { + "epoch": 2.18, + "learning_rate": 4.275657148115204e-05, + "loss": 0.5028, + "step": 95000 + }, + { + "epoch": 2.2, + "learning_rate": 4.271823145109346e-05, + "loss": 0.4992, + "step": 95500 + }, + { + "epoch": 2.21, + "learning_rate": 4.267989142103488e-05, + "loss": 0.5, + "step": 96000 + }, + { + "epoch": 2.22, + "learning_rate": 4.264162807103641e-05, + "loss": 0.4942, + "step": 96500 + }, + { + "epoch": 2.23, + "learning_rate": 4.260328804097782e-05, + "loss": 0.4942, + "step": 97000 + }, + { + "epoch": 2.24, + "learning_rate": 4.2564948010919245e-05, + "loss": 0.4952, + "step": 97500 + }, + { + "epoch": 2.25, + "learning_rate": 4.252660798086066e-05, + "loss": 0.4977, + "step": 98000 + }, + { + "epoch": 2.26, + "learning_rate": 4.2488344630862195e-05, + "loss": 0.4894, + "step": 98500 + }, + { + "epoch": 2.28, + "learning_rate": 4.245008128086372e-05, + "loss": 0.4887, + "step": 99000 + }, + { + "epoch": 2.29, + "learning_rate": 4.2411741250805146e-05, + "loss": 0.4813, + "step": 99500 + }, + { + "epoch": 2.3, + "learning_rate": 4.2373401220746563e-05, + "loss": 0.4851, + "step": 100000 + }, + { + "epoch": 2.31, + "learning_rate": 4.2335061190687974e-05, + "loss": 0.4865, + "step": 100500 + }, + { + "epoch": 2.32, + "learning_rate": 4.229672116062939e-05, + "loss": 0.4823, + "step": 101000 + }, + { + "epoch": 2.33, + "learning_rate": 4.225838113057081e-05, + "loss": 0.4806, + "step": 101500 + }, + { + "epoch": 2.34, + "learning_rate": 4.222011778057234e-05, + "loss": 0.4813, + "step": 102000 + }, + { + "epoch": 2.36, + "learning_rate": 4.218177775051376e-05, + "loss": 0.4734, + "step": 102500 + }, + { + "epoch": 2.37, + "learning_rate": 4.214343772045518e-05, + "loss": 0.479, + "step": 103000 + }, + { + "epoch": 2.38, + "learning_rate": 4.210509769039659e-05, + "loss": 0.4778, + "step": 103500 + }, + { + "epoch": 2.39, + "learning_rate": 4.2066757660338006e-05, + "loss": 0.4797, + "step": 104000 + }, + { + "epoch": 2.4, + "learning_rate": 4.2028417630279424e-05, + "loss": 0.474, + "step": 104500 + }, + { + "epoch": 2.41, + "learning_rate": 4.199007760022084e-05, + "loss": 0.4811, + "step": 105000 + }, + { + "epoch": 2.43, + "learning_rate": 4.1951814250222374e-05, + "loss": 0.464, + "step": 105500 + }, + { + "epoch": 2.44, + "learning_rate": 4.191347422016379e-05, + "loss": 0.4699, + "step": 106000 + }, + { + "epoch": 2.45, + "learning_rate": 4.187513419010521e-05, + "loss": 0.4655, + "step": 106500 + }, + { + "epoch": 2.46, + "learning_rate": 4.183679416004662e-05, + "loss": 0.4694, + "step": 107000 + }, + { + "epoch": 2.47, + "learning_rate": 4.179845412998804e-05, + "loss": 0.4698, + "step": 107500 + }, + { + "epoch": 2.48, + "learning_rate": 4.1760114099929456e-05, + "loss": 0.4714, + "step": 108000 + }, + { + "epoch": 2.49, + "learning_rate": 4.1721774069870873e-05, + "loss": 0.4627, + "step": 108500 + }, + { + "epoch": 2.51, + "learning_rate": 4.168343403981229e-05, + "loss": 0.4628, + "step": 109000 + }, + { + "epoch": 2.52, + "learning_rate": 4.16450940097537e-05, + "loss": 0.4565, + "step": 109500 + }, + { + "epoch": 2.53, + "learning_rate": 4.1606753979695126e-05, + "loss": 0.466, + "step": 110000 + }, + { + "epoch": 2.54, + "learning_rate": 4.156841394963654e-05, + "loss": 0.4635, + "step": 110500 + }, + { + "epoch": 2.55, + "learning_rate": 4.1530073919577955e-05, + "loss": 0.4694, + "step": 111000 + }, + { + "epoch": 2.56, + "learning_rate": 4.149181056957949e-05, + "loss": 0.4638, + "step": 111500 + }, + { + "epoch": 2.57, + "learning_rate": 4.1453470539520905e-05, + "loss": 0.4626, + "step": 112000 + }, + { + "epoch": 2.59, + "learning_rate": 4.1415130509462316e-05, + "loss": 0.4632, + "step": 112500 + }, + { + "epoch": 2.6, + "learning_rate": 4.137679047940374e-05, + "loss": 0.455, + "step": 113000 + }, + { + "epoch": 2.61, + "learning_rate": 4.133845044934516e-05, + "loss": 0.4553, + "step": 113500 + }, + { + "epoch": 2.62, + "learning_rate": 4.130018709934669e-05, + "loss": 0.4583, + "step": 114000 + }, + { + "epoch": 2.63, + "learning_rate": 4.126192374934822e-05, + "loss": 0.4596, + "step": 114500 + }, + { + "epoch": 2.64, + "learning_rate": 4.1223583719289635e-05, + "loss": 0.4634, + "step": 115000 + }, + { + "epoch": 2.65, + "learning_rate": 4.118524368923106e-05, + "loss": 0.4595, + "step": 115500 + }, + { + "epoch": 2.67, + "learning_rate": 4.1146980339232585e-05, + "loss": 0.4441, + "step": 116000 + }, + { + "epoch": 2.68, + "learning_rate": 4.110864030917401e-05, + "loss": 0.4517, + "step": 116500 + }, + { + "epoch": 2.69, + "learning_rate": 4.107030027911542e-05, + "loss": 0.4531, + "step": 117000 + }, + { + "epoch": 2.7, + "learning_rate": 4.103196024905684e-05, + "loss": 0.4556, + "step": 117500 + }, + { + "epoch": 2.71, + "learning_rate": 4.099362021899825e-05, + "loss": 0.4481, + "step": 118000 + }, + { + "epoch": 2.72, + "learning_rate": 4.095528018893967e-05, + "loss": 0.4483, + "step": 118500 + }, + { + "epoch": 2.74, + "learning_rate": 4.0916940158881084e-05, + "loss": 0.4457, + "step": 119000 + }, + { + "epoch": 2.75, + "learning_rate": 4.08786001288225e-05, + "loss": 0.452, + "step": 119500 + }, + { + "epoch": 2.76, + "learning_rate": 4.084026009876392e-05, + "loss": 0.4511, + "step": 120000 + }, + { + "epoch": 2.77, + "learning_rate": 4.080192006870534e-05, + "loss": 0.4466, + "step": 120500 + }, + { + "epoch": 2.78, + "learning_rate": 4.0763580038646755e-05, + "loss": 0.4368, + "step": 121000 + }, + { + "epoch": 2.79, + "learning_rate": 4.0725240008588166e-05, + "loss": 0.443, + "step": 121500 + }, + { + "epoch": 2.8, + "learning_rate": 4.0686976658589705e-05, + "loss": 0.441, + "step": 122000 + }, + { + "epoch": 2.82, + "learning_rate": 4.0648636628531116e-05, + "loss": 0.4503, + "step": 122500 + }, + { + "epoch": 2.83, + "learning_rate": 4.0610296598472534e-05, + "loss": 0.4487, + "step": 123000 + }, + { + "epoch": 2.84, + "learning_rate": 4.057195656841395e-05, + "loss": 0.4482, + "step": 123500 + }, + { + "epoch": 2.85, + "learning_rate": 4.053361653835537e-05, + "loss": 0.4449, + "step": 124000 + }, + { + "epoch": 2.86, + "learning_rate": 4.049527650829679e-05, + "loss": 0.4514, + "step": 124500 + }, + { + "epoch": 2.87, + "learning_rate": 4.04569364782382e-05, + "loss": 0.4407, + "step": 125000 + }, + { + "epoch": 2.88, + "learning_rate": 4.041867312823974e-05, + "loss": 0.443, + "step": 125500 + }, + { + "epoch": 2.9, + "learning_rate": 4.038033309818115e-05, + "loss": 0.434, + "step": 126000 + }, + { + "epoch": 2.91, + "learning_rate": 4.0341993068122566e-05, + "loss": 0.4384, + "step": 126500 + }, + { + "epoch": 2.92, + "learning_rate": 4.030365303806398e-05, + "loss": 0.4334, + "step": 127000 + }, + { + "epoch": 2.93, + "learning_rate": 4.0265389688065516e-05, + "loss": 0.4419, + "step": 127500 + }, + { + "epoch": 2.94, + "learning_rate": 4.0227049658006934e-05, + "loss": 0.4421, + "step": 128000 + }, + { + "epoch": 2.95, + "learning_rate": 4.018870962794835e-05, + "loss": 0.4244, + "step": 128500 + }, + { + "epoch": 2.97, + "learning_rate": 4.015036959788976e-05, + "loss": 0.4345, + "step": 129000 + }, + { + "epoch": 2.98, + "learning_rate": 4.01121062478913e-05, + "loss": 0.4374, + "step": 129500 + }, + { + "epoch": 2.99, + "learning_rate": 4.007376621783271e-05, + "loss": 0.4368, + "step": 130000 + }, + { + "epoch": 3.0, + "learning_rate": 4.003542618777413e-05, + "loss": 0.4356, + "step": 130500 + }, + { + "epoch": 3.0, + "eval_bleu": 58.5493, + "eval_gen_len": 17.1569, + "eval_loss": 0.7014300227165222, + "eval_runtime": 7450.9373, + "eval_samples_per_second": 11.677, + "eval_steps_per_second": 1.46, + "step": 130513 + }, + { + "epoch": 3.01, + "learning_rate": 3.9997086157715555e-05, + "loss": 0.4373, + "step": 131000 + }, + { + "epoch": 3.02, + "learning_rate": 3.9958746127656966e-05, + "loss": 0.42, + "step": 131500 + }, + { + "epoch": 3.03, + "learning_rate": 3.992040609759838e-05, + "loss": 0.4179, + "step": 132000 + }, + { + "epoch": 3.05, + "learning_rate": 3.9882066067539794e-05, + "loss": 0.406, + "step": 132500 + }, + { + "epoch": 3.06, + "learning_rate": 3.984372603748122e-05, + "loss": 0.4034, + "step": 133000 + }, + { + "epoch": 3.07, + "learning_rate": 3.980538600742263e-05, + "loss": 0.4103, + "step": 133500 + }, + { + "epoch": 3.08, + "learning_rate": 3.976704597736405e-05, + "loss": 0.4084, + "step": 134000 + }, + { + "epoch": 3.09, + "learning_rate": 3.9728705947305465e-05, + "loss": 0.4012, + "step": 134500 + }, + { + "epoch": 3.1, + "learning_rate": 3.969036591724688e-05, + "loss": 0.3966, + "step": 135000 + }, + { + "epoch": 3.11, + "learning_rate": 3.96520258871883e-05, + "loss": 0.4026, + "step": 135500 + }, + { + "epoch": 3.13, + "learning_rate": 3.961368585712971e-05, + "loss": 0.3983, + "step": 136000 + }, + { + "epoch": 3.14, + "learning_rate": 3.957542250713125e-05, + "loss": 0.3947, + "step": 136500 + }, + { + "epoch": 3.15, + "learning_rate": 3.953708247707266e-05, + "loss": 0.3894, + "step": 137000 + }, + { + "epoch": 3.16, + "learning_rate": 3.94988191270742e-05, + "loss": 0.3927, + "step": 137500 + }, + { + "epoch": 3.17, + "learning_rate": 3.946047909701561e-05, + "loss": 0.3919, + "step": 138000 + }, + { + "epoch": 3.18, + "learning_rate": 3.942213906695703e-05, + "loss": 0.3909, + "step": 138500 + }, + { + "epoch": 3.2, + "learning_rate": 3.938379903689845e-05, + "loss": 0.3914, + "step": 139000 + }, + { + "epoch": 3.21, + "learning_rate": 3.9345459006839865e-05, + "loss": 0.3876, + "step": 139500 + }, + { + "epoch": 3.22, + "learning_rate": 3.930727233690151e-05, + "loss": 0.3844, + "step": 140000 + }, + { + "epoch": 3.23, + "learning_rate": 3.926893230684293e-05, + "loss": 0.3871, + "step": 140500 + }, + { + "epoch": 3.24, + "learning_rate": 3.923059227678435e-05, + "loss": 0.3835, + "step": 141000 + }, + { + "epoch": 3.25, + "learning_rate": 3.9192252246725766e-05, + "loss": 0.3871, + "step": 141500 + }, + { + "epoch": 3.26, + "learning_rate": 3.915391221666718e-05, + "loss": 0.3803, + "step": 142000 + }, + { + "epoch": 3.28, + "learning_rate": 3.9115572186608594e-05, + "loss": 0.3776, + "step": 142500 + }, + { + "epoch": 3.29, + "learning_rate": 3.907723215655001e-05, + "loss": 0.3742, + "step": 143000 + }, + { + "epoch": 3.3, + "learning_rate": 3.903889212649143e-05, + "loss": 0.3778, + "step": 143500 + }, + { + "epoch": 3.31, + "learning_rate": 3.900055209643285e-05, + "loss": 0.3759, + "step": 144000 + }, + { + "epoch": 3.32, + "learning_rate": 3.896221206637426e-05, + "loss": 0.3756, + "step": 144500 + }, + { + "epoch": 3.33, + "learning_rate": 3.89239487163758e-05, + "loss": 0.3737, + "step": 145000 + }, + { + "epoch": 3.34, + "learning_rate": 3.888560868631721e-05, + "loss": 0.3749, + "step": 145500 + }, + { + "epoch": 3.36, + "learning_rate": 3.884734533631875e-05, + "loss": 0.3701, + "step": 146000 + }, + { + "epoch": 3.37, + "learning_rate": 3.880900530626016e-05, + "loss": 0.3736, + "step": 146500 + }, + { + "epoch": 3.38, + "learning_rate": 3.8770665276201576e-05, + "loss": 0.3706, + "step": 147000 + }, + { + "epoch": 3.39, + "learning_rate": 3.8732325246143e-05, + "loss": 0.3743, + "step": 147500 + }, + { + "epoch": 3.4, + "learning_rate": 3.869398521608441e-05, + "loss": 0.3665, + "step": 148000 + }, + { + "epoch": 3.41, + "learning_rate": 3.865564518602583e-05, + "loss": 0.3781, + "step": 148500 + }, + { + "epoch": 3.42, + "learning_rate": 3.861738183602736e-05, + "loss": 0.3591, + "step": 149000 + }, + { + "epoch": 3.44, + "learning_rate": 3.857904180596878e-05, + "loss": 0.365, + "step": 149500 + }, + { + "epoch": 3.45, + "learning_rate": 3.854070177591019e-05, + "loss": 0.3648, + "step": 150000 + }, + { + "epoch": 3.46, + "learning_rate": 3.8502361745851615e-05, + "loss": 0.3635, + "step": 150500 + }, + { + "epoch": 3.47, + "learning_rate": 3.8464021715793026e-05, + "loss": 0.3658, + "step": 151000 + }, + { + "epoch": 3.48, + "learning_rate": 3.8425681685734444e-05, + "loss": 0.3666, + "step": 151500 + }, + { + "epoch": 3.49, + "learning_rate": 3.838734165567586e-05, + "loss": 0.3579, + "step": 152000 + }, + { + "epoch": 3.51, + "learning_rate": 3.834900162561728e-05, + "loss": 0.3582, + "step": 152500 + }, + { + "epoch": 3.52, + "learning_rate": 3.8310661595558697e-05, + "loss": 0.3554, + "step": 153000 + }, + { + "epoch": 3.53, + "learning_rate": 3.8272474925620344e-05, + "loss": 0.3645, + "step": 153500 + }, + { + "epoch": 3.54, + "learning_rate": 3.823421157562188e-05, + "loss": 0.3605, + "step": 154000 + }, + { + "epoch": 3.55, + "learning_rate": 3.8195871545563295e-05, + "loss": 0.3657, + "step": 154500 + }, + { + "epoch": 3.56, + "learning_rate": 3.8157531515504706e-05, + "loss": 0.362, + "step": 155000 + }, + { + "epoch": 3.57, + "learning_rate": 3.811919148544612e-05, + "loss": 0.3585, + "step": 155500 + }, + { + "epoch": 3.59, + "learning_rate": 3.808085145538755e-05, + "loss": 0.3606, + "step": 156000 + }, + { + "epoch": 3.6, + "learning_rate": 3.8042664785449196e-05, + "loss": 0.3539, + "step": 156500 + }, + { + "epoch": 3.61, + "learning_rate": 3.8004324755390606e-05, + "loss": 0.3543, + "step": 157000 + }, + { + "epoch": 3.62, + "learning_rate": 3.7966061405392146e-05, + "loss": 0.3599, + "step": 157500 + }, + { + "epoch": 3.63, + "learning_rate": 3.792772137533356e-05, + "loss": 0.3613, + "step": 158000 + }, + { + "epoch": 3.64, + "learning_rate": 3.7889381345274975e-05, + "loss": 0.3616, + "step": 158500 + }, + { + "epoch": 3.65, + "learning_rate": 3.78510413152164e-05, + "loss": 0.357, + "step": 159000 + }, + { + "epoch": 3.67, + "learning_rate": 3.781270128515781e-05, + "loss": 0.3444, + "step": 159500 + }, + { + "epoch": 3.68, + "learning_rate": 3.777436125509923e-05, + "loss": 0.35, + "step": 160000 + }, + { + "epoch": 3.69, + "learning_rate": 3.773602122504064e-05, + "loss": 0.3515, + "step": 160500 + }, + { + "epoch": 3.7, + "learning_rate": 3.769768119498206e-05, + "loss": 0.3571, + "step": 161000 + }, + { + "epoch": 3.71, + "learning_rate": 3.7659341164923474e-05, + "loss": 0.3484, + "step": 161500 + }, + { + "epoch": 3.72, + "learning_rate": 3.762100113486489e-05, + "loss": 0.3467, + "step": 162000 + }, + { + "epoch": 3.74, + "learning_rate": 3.758266110480631e-05, + "loss": 0.3489, + "step": 162500 + }, + { + "epoch": 3.75, + "learning_rate": 3.754432107474773e-05, + "loss": 0.3505, + "step": 163000 + }, + { + "epoch": 3.76, + "learning_rate": 3.7505981044689144e-05, + "loss": 0.351, + "step": 163500 + }, + { + "epoch": 3.77, + "learning_rate": 3.7467641014630555e-05, + "loss": 0.3486, + "step": 164000 + }, + { + "epoch": 3.78, + "learning_rate": 3.7429377664632095e-05, + "loss": 0.3394, + "step": 164500 + }, + { + "epoch": 3.79, + "learning_rate": 3.7391037634573506e-05, + "loss": 0.3445, + "step": 165000 + }, + { + "epoch": 3.8, + "learning_rate": 3.735269760451492e-05, + "loss": 0.3417, + "step": 165500 + }, + { + "epoch": 3.82, + "learning_rate": 3.731435757445634e-05, + "loss": 0.3492, + "step": 166000 + }, + { + "epoch": 3.83, + "learning_rate": 3.727601754439776e-05, + "loss": 0.3519, + "step": 166500 + }, + { + "epoch": 3.84, + "learning_rate": 3.7237677514339176e-05, + "loss": 0.3484, + "step": 167000 + }, + { + "epoch": 3.85, + "learning_rate": 3.719933748428059e-05, + "loss": 0.3446, + "step": 167500 + }, + { + "epoch": 3.86, + "learning_rate": 3.7160997454222005e-05, + "loss": 0.3499, + "step": 168000 + }, + { + "epoch": 3.87, + "learning_rate": 3.712265742416342e-05, + "loss": 0.3465, + "step": 168500 + }, + { + "epoch": 3.88, + "learning_rate": 3.708431739410484e-05, + "loss": 0.3431, + "step": 169000 + }, + { + "epoch": 3.9, + "learning_rate": 3.704597736404625e-05, + "loss": 0.3379, + "step": 169500 + }, + { + "epoch": 3.91, + "learning_rate": 3.700771401404779e-05, + "loss": 0.3402, + "step": 170000 + }, + { + "epoch": 3.92, + "learning_rate": 3.69693739839892e-05, + "loss": 0.3379, + "step": 170500 + }, + { + "epoch": 3.93, + "learning_rate": 3.6931187314050856e-05, + "loss": 0.3468, + "step": 171000 + }, + { + "epoch": 3.94, + "learning_rate": 3.6892847283992274e-05, + "loss": 0.3433, + "step": 171500 + }, + { + "epoch": 3.95, + "learning_rate": 3.685450725393369e-05, + "loss": 0.3305, + "step": 172000 + }, + { + "epoch": 3.97, + "learning_rate": 3.68161672238751e-05, + "loss": 0.3373, + "step": 172500 + }, + { + "epoch": 3.98, + "learning_rate": 3.677782719381652e-05, + "loss": 0.3426, + "step": 173000 + }, + { + "epoch": 3.99, + "learning_rate": 3.673948716375794e-05, + "loss": 0.3387, + "step": 173500 + }, + { + "epoch": 4.0, + "learning_rate": 3.6701147133699355e-05, + "loss": 0.3407, + "step": 174000 + }, + { + "epoch": 4.0, + "eval_bleu": 58.3826, + "eval_gen_len": 17.1623, + "eval_loss": 0.7513108253479004, + "eval_runtime": 7458.9074, + "eval_samples_per_second": 11.665, + "eval_steps_per_second": 1.458, + "step": 174018 + }, + { + "epoch": 4.01, + "learning_rate": 3.666280710364077e-05, + "loss": 0.3395, + "step": 174500 + }, + { + "epoch": 4.02, + "learning_rate": 3.6624467073582184e-05, + "loss": 0.3242, + "step": 175000 + }, + { + "epoch": 4.03, + "learning_rate": 3.658612704352361e-05, + "loss": 0.3246, + "step": 175500 + }, + { + "epoch": 4.05, + "learning_rate": 3.654778701346502e-05, + "loss": 0.3132, + "step": 176000 + }, + { + "epoch": 4.06, + "learning_rate": 3.6509446983406437e-05, + "loss": 0.3129, + "step": 176500 + }, + { + "epoch": 4.07, + "learning_rate": 3.6471106953347854e-05, + "loss": 0.3162, + "step": 177000 + }, + { + "epoch": 4.08, + "learning_rate": 3.643276692328927e-05, + "loss": 0.316, + "step": 177500 + }, + { + "epoch": 4.09, + "learning_rate": 3.639442689323069e-05, + "loss": 0.3088, + "step": 178000 + }, + { + "epoch": 4.1, + "learning_rate": 3.63560868631721e-05, + "loss": 0.3048, + "step": 178500 + }, + { + "epoch": 4.11, + "learning_rate": 3.631774683311352e-05, + "loss": 0.3126, + "step": 179000 + }, + { + "epoch": 4.13, + "learning_rate": 3.627948348311505e-05, + "loss": 0.3091, + "step": 179500 + }, + { + "epoch": 4.14, + "learning_rate": 3.624114345305647e-05, + "loss": 0.3046, + "step": 180000 + }, + { + "epoch": 4.15, + "learning_rate": 3.6202803422997886e-05, + "loss": 0.3008, + "step": 180500 + }, + { + "epoch": 4.16, + "learning_rate": 3.6164463392939304e-05, + "loss": 0.3037, + "step": 181000 + }, + { + "epoch": 4.17, + "learning_rate": 3.612612336288072e-05, + "loss": 0.3034, + "step": 181500 + }, + { + "epoch": 4.18, + "learning_rate": 3.608778333282213e-05, + "loss": 0.3025, + "step": 182000 + }, + { + "epoch": 4.19, + "learning_rate": 3.604944330276355e-05, + "loss": 0.3021, + "step": 182500 + }, + { + "epoch": 4.21, + "learning_rate": 3.601117995276508e-05, + "loss": 0.3015, + "step": 183000 + }, + { + "epoch": 4.22, + "learning_rate": 3.59728399227065e-05, + "loss": 0.2977, + "step": 183500 + }, + { + "epoch": 4.23, + "learning_rate": 3.593449989264792e-05, + "loss": 0.2999, + "step": 184000 + }, + { + "epoch": 4.24, + "learning_rate": 3.5896159862589336e-05, + "loss": 0.2953, + "step": 184500 + }, + { + "epoch": 4.25, + "learning_rate": 3.5857819832530747e-05, + "loss": 0.2992, + "step": 185000 + }, + { + "epoch": 4.26, + "learning_rate": 3.5819479802472164e-05, + "loss": 0.2927, + "step": 185500 + }, + { + "epoch": 4.28, + "learning_rate": 3.578113977241359e-05, + "loss": 0.2929, + "step": 186000 + }, + { + "epoch": 4.29, + "learning_rate": 3.5742799742355e-05, + "loss": 0.2919, + "step": 186500 + }, + { + "epoch": 4.3, + "learning_rate": 3.570445971229642e-05, + "loss": 0.2953, + "step": 187000 + }, + { + "epoch": 4.31, + "learning_rate": 3.566611968223783e-05, + "loss": 0.2962, + "step": 187500 + }, + { + "epoch": 4.32, + "learning_rate": 3.562777965217925e-05, + "loss": 0.2908, + "step": 188000 + }, + { + "epoch": 4.33, + "learning_rate": 3.558943962212066e-05, + "loss": 0.2918, + "step": 188500 + }, + { + "epoch": 4.34, + "learning_rate": 3.555109959206208e-05, + "loss": 0.2898, + "step": 189000 + }, + { + "epoch": 4.36, + "learning_rate": 3.5512836242063614e-05, + "loss": 0.2876, + "step": 189500 + }, + { + "epoch": 4.37, + "learning_rate": 3.547449621200503e-05, + "loss": 0.2893, + "step": 190000 + }, + { + "epoch": 4.38, + "learning_rate": 3.543615618194645e-05, + "loss": 0.2857, + "step": 190500 + }, + { + "epoch": 4.39, + "learning_rate": 3.539781615188787e-05, + "loss": 0.2898, + "step": 191000 + }, + { + "epoch": 4.4, + "learning_rate": 3.53595528018894e-05, + "loss": 0.2834, + "step": 191500 + }, + { + "epoch": 4.41, + "learning_rate": 3.532121277183082e-05, + "loss": 0.289, + "step": 192000 + }, + { + "epoch": 4.42, + "learning_rate": 3.528294942183235e-05, + "loss": 0.2804, + "step": 192500 + }, + { + "epoch": 4.44, + "learning_rate": 3.524460939177376e-05, + "loss": 0.2839, + "step": 193000 + }, + { + "epoch": 4.45, + "learning_rate": 3.5206269361715185e-05, + "loss": 0.2785, + "step": 193500 + }, + { + "epoch": 4.46, + "learning_rate": 3.5167929331656596e-05, + "loss": 0.2802, + "step": 194000 + }, + { + "epoch": 4.47, + "learning_rate": 3.5129589301598014e-05, + "loss": 0.286, + "step": 194500 + }, + { + "epoch": 4.48, + "learning_rate": 3.509124927153943e-05, + "loss": 0.2859, + "step": 195000 + }, + { + "epoch": 4.49, + "learning_rate": 3.5052985921540964e-05, + "loss": 0.2774, + "step": 195500 + }, + { + "epoch": 4.51, + "learning_rate": 3.501479925160261e-05, + "loss": 0.2788, + "step": 196000 + }, + { + "epoch": 4.52, + "learning_rate": 3.4976459221544036e-05, + "loss": 0.2754, + "step": 196500 + }, + { + "epoch": 4.53, + "learning_rate": 3.493811919148545e-05, + "loss": 0.282, + "step": 197000 + }, + { + "epoch": 4.54, + "learning_rate": 3.4899779161426865e-05, + "loss": 0.2809, + "step": 197500 + }, + { + "epoch": 4.55, + "learning_rate": 3.48615158114284e-05, + "loss": 0.2872, + "step": 198000 + }, + { + "epoch": 4.56, + "learning_rate": 3.4823175781369815e-05, + "loss": 0.2806, + "step": 198500 + }, + { + "epoch": 4.57, + "learning_rate": 3.4784835751311226e-05, + "loss": 0.2746, + "step": 199000 + }, + { + "epoch": 4.59, + "learning_rate": 3.474649572125265e-05, + "loss": 0.2793, + "step": 199500 + }, + { + "epoch": 4.6, + "learning_rate": 3.4708232371254177e-05, + "loss": 0.2781, + "step": 200000 + }, + { + "epoch": 4.61, + "learning_rate": 3.4669969021255716e-05, + "loss": 0.2773, + "step": 200500 + }, + { + "epoch": 4.62, + "learning_rate": 3.463162899119713e-05, + "loss": 0.2782, + "step": 201000 + }, + { + "epoch": 4.63, + "learning_rate": 3.4593288961138545e-05, + "loss": 0.2777, + "step": 201500 + }, + { + "epoch": 4.64, + "learning_rate": 3.455494893107996e-05, + "loss": 0.2792, + "step": 202000 + }, + { + "epoch": 4.65, + "learning_rate": 3.451660890102138e-05, + "loss": 0.276, + "step": 202500 + }, + { + "epoch": 4.67, + "learning_rate": 3.44782688709628e-05, + "loss": 0.2663, + "step": 203000 + }, + { + "epoch": 4.68, + "learning_rate": 3.4439928840904215e-05, + "loss": 0.2697, + "step": 203500 + }, + { + "epoch": 4.69, + "learning_rate": 3.440158881084563e-05, + "loss": 0.2733, + "step": 204000 + }, + { + "epoch": 4.7, + "learning_rate": 3.4363248780787044e-05, + "loss": 0.2759, + "step": 204500 + }, + { + "epoch": 4.71, + "learning_rate": 3.432490875072846e-05, + "loss": 0.271, + "step": 205000 + }, + { + "epoch": 4.72, + "learning_rate": 3.428656872066988e-05, + "loss": 0.2669, + "step": 205500 + }, + { + "epoch": 4.74, + "learning_rate": 3.42482286906113e-05, + "loss": 0.268, + "step": 206000 + }, + { + "epoch": 4.75, + "learning_rate": 3.4209888660552714e-05, + "loss": 0.27, + "step": 206500 + }, + { + "epoch": 4.76, + "learning_rate": 3.4171548630494125e-05, + "loss": 0.2719, + "step": 207000 + }, + { + "epoch": 4.77, + "learning_rate": 3.413320860043554e-05, + "loss": 0.2723, + "step": 207500 + }, + { + "epoch": 4.78, + "learning_rate": 3.409486857037696e-05, + "loss": 0.2612, + "step": 208000 + }, + { + "epoch": 4.79, + "learning_rate": 3.405652854031838e-05, + "loss": 0.2661, + "step": 208500 + }, + { + "epoch": 4.8, + "learning_rate": 3.4018188510259796e-05, + "loss": 0.2641, + "step": 209000 + }, + { + "epoch": 4.82, + "learning_rate": 3.397984848020121e-05, + "loss": 0.2685, + "step": 209500 + }, + { + "epoch": 4.83, + "learning_rate": 3.394150845014263e-05, + "loss": 0.2716, + "step": 210000 + }, + { + "epoch": 4.84, + "learning_rate": 3.390324510014416e-05, + "loss": 0.2693, + "step": 210500 + }, + { + "epoch": 4.85, + "learning_rate": 3.386490507008558e-05, + "loss": 0.2686, + "step": 211000 + }, + { + "epoch": 4.86, + "learning_rate": 3.382656504002699e-05, + "loss": 0.2743, + "step": 211500 + }, + { + "epoch": 4.87, + "learning_rate": 3.378822500996841e-05, + "loss": 0.2672, + "step": 212000 + }, + { + "epoch": 4.88, + "learning_rate": 3.374988497990982e-05, + "loss": 0.2656, + "step": 212500 + }, + { + "epoch": 4.9, + "learning_rate": 3.3711544949851245e-05, + "loss": 0.2578, + "step": 213000 + }, + { + "epoch": 4.91, + "learning_rate": 3.367320491979266e-05, + "loss": 0.263, + "step": 213500 + }, + { + "epoch": 4.92, + "learning_rate": 3.3634864889734074e-05, + "loss": 0.2642, + "step": 214000 + }, + { + "epoch": 4.93, + "learning_rate": 3.3596601539735613e-05, + "loss": 0.2681, + "step": 214500 + }, + { + "epoch": 4.94, + "learning_rate": 3.3558261509677024e-05, + "loss": 0.2632, + "step": 215000 + }, + { + "epoch": 4.95, + "learning_rate": 3.351992147961844e-05, + "loss": 0.2538, + "step": 215500 + }, + { + "epoch": 4.97, + "learning_rate": 3.348158144955986e-05, + "loss": 0.2608, + "step": 216000 + }, + { + "epoch": 4.98, + "learning_rate": 3.344324141950128e-05, + "loss": 0.2641, + "step": 216500 + }, + { + "epoch": 4.99, + "learning_rate": 3.340490138944269e-05, + "loss": 0.2592, + "step": 217000 + }, + { + "epoch": 5.0, + "learning_rate": 3.336663803944423e-05, + "loss": 0.2605, + "step": 217500 + }, + { + "epoch": 5.0, + "eval_bleu": 58.7238, + "eval_gen_len": 17.0888, + "eval_loss": 0.8122135400772095, + "eval_runtime": 7422.7798, + "eval_samples_per_second": 11.722, + "eval_steps_per_second": 1.465, + "step": 217522 + } + ], + "logging_steps": 500, + "max_steps": 652560, + "num_train_epochs": 15, + "save_steps": 500, + "total_flos": 7.542391759939043e+18, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-217522/training_args.bin b/checkpoint-217522/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4d3d8487ffcaca78bad3b458878633a19376556 --- /dev/null +++ b/checkpoint-217522/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b731ecd386cb51a958b6c8f191496c616dc6e80b60cf4e62402772da333973 +size 4792 diff --git a/checkpoint-87009/config.json b/checkpoint-87009/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d123d026fa1d1679aeb1220d9ae316d7c13a0b --- /dev/null +++ b/checkpoint-87009/config.json @@ -0,0 +1,59 @@ +{ + "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt", + "_num_labels": 3, + "activation_dropout": 0.0, + "activation_function": "relu", + "add_bias_logits": false, + "add_final_layer_norm": true, + "architectures": [ + "MBartForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "classif_dropout": 0.0, + "classifier_dropout": 0.0, + "d_model": 1024, + "decoder_attention_heads": 16, + "decoder_ffn_dim": 4096, + "decoder_layerdrop": 0.0, + "decoder_layers": 12, + "decoder_start_token_id": 2, + "dropout": 0.1, + "early_stopping": true, + "encoder_attention_heads": 16, + "encoder_ffn_dim": 4096, + "encoder_layerdrop": 0.0, + "encoder_layers": 12, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "gradient_checkpointing": false, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "init_std": 0.02, + "is_encoder_decoder": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "max_length": 200, + "max_position_embeddings": 1024, + "model_type": "mbart", + "normalize_before": true, + "normalize_embedding": true, + "num_beams": 5, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "scale_embedding": true, + "static_position_embeddings": false, + "tokenizer_class": "MBart50Tokenizer", + "torch_dtype": "float32", + "transformers_version": "4.35.2", + "use_cache": true, + "vocab_size": 250054 +} diff --git a/checkpoint-87009/generation_config.json b/checkpoint-87009/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7e47c12e3900189593d4b56d0d776b58a7a55627 --- /dev/null +++ b/checkpoint-87009/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 0, + "decoder_start_token_id": 2, + "early_stopping": true, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "max_length": 200, + "num_beams": 5, + "pad_token_id": 1, + "transformers_version": "4.35.2" +} diff --git a/checkpoint-87009/model.safetensors b/checkpoint-87009/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa743281f23a96ca2d66c81e92341c36254529df --- /dev/null +++ b/checkpoint-87009/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f359d7b7a214b7d33f8b720df9fb4977922176e4c5fa16d91238daeb1027a2 +size 2444578688 diff --git a/checkpoint-87009/optimizer.pt b/checkpoint-87009/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0997aa6ace575ec7f7aa91c8e0c1e981d1bd843 --- /dev/null +++ b/checkpoint-87009/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38d5139d9300234624ea3f83ee80526c18202627fda4bc5adc19dc63638eaa0 +size 4887473903 diff --git a/checkpoint-87009/rng_state_0.pth b/checkpoint-87009/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..2002fb26bfd83b2765c2aa8ef92c9234c45e842e --- /dev/null +++ b/checkpoint-87009/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46166c012e316e435016d0e3f3d98cb393b668a8468e9d0981d4420e442753f9 +size 15024 diff --git a/checkpoint-87009/rng_state_1.pth b/checkpoint-87009/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..67238d90a25b41cafcaef4a57d0d5a809a38d53d --- /dev/null +++ b/checkpoint-87009/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641db8587b2461e871f0234214d253811f15d12f7109d1fd4102ac1357a457f5 +size 15024 diff --git a/checkpoint-87009/rng_state_2.pth b/checkpoint-87009/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d83ecf5e451151645e1f55aebc00add3eb367a3 --- /dev/null +++ b/checkpoint-87009/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66811d476fe04b02198ecdb59590d27c31d02a1b034bf1f254d86ae3475bc7b4 +size 15024 diff --git a/checkpoint-87009/rng_state_3.pth b/checkpoint-87009/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f23650f4e8430c9ab4bd785ec89d3d7b30f7e6a --- /dev/null +++ b/checkpoint-87009/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62b319ce260583a0b18e19d711c49ef66d57af01315b2a4451ac0a4b4747245 +size 15024 diff --git a/checkpoint-87009/scheduler.pt b/checkpoint-87009/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b22793cc56bb8f77f03101c7c93006e7f57e876 --- /dev/null +++ b/checkpoint-87009/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555882394d7aacd99910ea6cc71bbe421925abef4fb1f1b252c9c17ae6ff5f5c +size 1064 diff --git a/checkpoint-87009/sentencepiece.bpe.model b/checkpoint-87009/sentencepiece.bpe.model new file mode 100644 index 0000000000000000000000000000000000000000..7a3f40a75f870bc1f21700cd414dc2acc431583c --- /dev/null +++ b/checkpoint-87009/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/checkpoint-87009/special_tokens_map.json b/checkpoint-87009/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92619141640d5fcbb4429807de2248352b0dca79 --- /dev/null +++ b/checkpoint-87009/special_tokens_map.json @@ -0,0 +1,69 @@ +{ + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "cls_token": "", + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/checkpoint-87009/tokenizer.json b/checkpoint-87009/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86f15e5a3339d518716121ecef4c2a1dc9208b40 --- /dev/null +++ b/checkpoint-87009/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf1fb0f45fdd5ae9fc44fafee492652a423fc749833ef57c2fa801358549d92 +size 17110107 diff --git a/checkpoint-87009/tokenizer_config.json b/checkpoint-87009/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..70c0515a5815fcc727e11e053116348bfac12128 --- /dev/null +++ b/checkpoint-87009/tokenizer_config.json @@ -0,0 +1,528 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250001": { + "content": "ar_AR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250002": { + "content": "cs_CZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250003": { + "content": "de_DE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250004": { + "content": "en_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250005": { + "content": "es_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250006": { + "content": "et_EE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250007": { + "content": "fi_FI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250008": { + "content": "fr_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250009": { + "content": "gu_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250010": { + "content": "hi_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250011": { + "content": "it_IT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250012": { + "content": "ja_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250013": { + "content": "kk_KZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250014": { + "content": "ko_KR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250015": { + "content": "lt_LT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250016": { + "content": "lv_LV", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250017": { + "content": "my_MM", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250018": { + "content": "ne_NP", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250019": { + "content": "nl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250020": { + "content": "ro_RO", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250021": { + "content": "ru_RU", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250022": { + "content": "si_LK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250023": { + "content": "tr_TR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250024": { + "content": "vi_VN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250025": { + "content": "zh_CN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250026": { + "content": "af_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250027": { + "content": "az_AZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250028": { + "content": "bn_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250029": { + "content": "fa_IR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250030": { + "content": "he_IL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250031": { + "content": "hr_HR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250032": { + "content": "id_ID", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250033": { + "content": "ka_GE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250034": { + "content": "km_KH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250035": { + "content": "mk_MK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250036": { + "content": "ml_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250037": { + "content": "mn_MN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250038": { + "content": "mr_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250039": { + "content": "pl_PL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250040": { + "content": "ps_AF", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250041": { + "content": "pt_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250042": { + "content": "sv_SE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250043": { + "content": "sw_KE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250044": { + "content": "ta_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250045": { + "content": "te_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250046": { + "content": "th_TH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250047": { + "content": "tl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250048": { + "content": "uk_UA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250049": { + "content": "ur_PK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250050": { + "content": "xh_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250051": { + "content": "gl_ES", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250052": { + "content": "sl_SI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250053": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "clean_up_tokenization_spaces": true, + "cls_token": "", + "eos_token": "", + "language_codes": "ML50", + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "sp_model_kwargs": {}, + "src_lang": "ja_XX", + "tgt_lang": "ko_KR", + "tokenizer_class": "MBart50Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-87009/trainer_state.json b/checkpoint-87009/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e595812d0111358e422179cedb5525b736309a81 --- /dev/null +++ b/checkpoint-87009/trainer_state.json @@ -0,0 +1,1083 @@ +{ + "best_metric": 0.6814723610877991, + "best_model_checkpoint": "./jako_mbartLarge_100p_run1/checkpoint-87009", + "epoch": 2.0, + "eval_steps": 500, + "global_step": 87009, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 4.97e-05, + "loss": 1.9891, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 4.996196669018189e-05, + "loss": 1.5354, + "step": 1000 + }, + { + "epoch": 0.03, + "learning_rate": 4.9923626660123305e-05, + "loss": 1.3833, + "step": 1500 + }, + { + "epoch": 0.05, + "learning_rate": 4.988528663006472e-05, + "loss": 1.2912, + "step": 2000 + }, + { + "epoch": 0.06, + "learning_rate": 4.984694660000614e-05, + "loss": 1.2355, + "step": 2500 + }, + { + "epoch": 0.07, + "learning_rate": 4.980860656994755e-05, + "loss": 1.1927, + "step": 3000 + }, + { + "epoch": 0.08, + "learning_rate": 4.977026653988897e-05, + "loss": 1.166, + "step": 3500 + }, + { + "epoch": 0.09, + "learning_rate": 4.9731926509830386e-05, + "loss": 1.1238, + "step": 4000 + }, + { + "epoch": 0.1, + "learning_rate": 4.9693586479771804e-05, + "loss": 1.0972, + "step": 4500 + }, + { + "epoch": 0.11, + "learning_rate": 4.9655246449713215e-05, + "loss": 1.0964, + "step": 5000 + }, + { + "epoch": 0.13, + "learning_rate": 4.961690641965463e-05, + "loss": 1.0611, + "step": 5500 + }, + { + "epoch": 0.14, + "learning_rate": 4.957871974971629e-05, + "loss": 1.0487, + "step": 6000 + }, + { + "epoch": 0.15, + "learning_rate": 4.9540379719657705e-05, + "loss": 1.0166, + "step": 6500 + }, + { + "epoch": 0.16, + "learning_rate": 4.9502039689599116e-05, + "loss": 1.0162, + "step": 7000 + }, + { + "epoch": 0.17, + "learning_rate": 4.946369965954053e-05, + "loss": 0.9952, + "step": 7500 + }, + { + "epoch": 0.18, + "learning_rate": 4.942535962948195e-05, + "loss": 0.9853, + "step": 8000 + }, + { + "epoch": 0.2, + "learning_rate": 4.9387096279483484e-05, + "loss": 0.9835, + "step": 8500 + }, + { + "epoch": 0.21, + "learning_rate": 4.9348832929485017e-05, + "loss": 0.9634, + "step": 9000 + }, + { + "epoch": 0.22, + "learning_rate": 4.9310492899426434e-05, + "loss": 0.9532, + "step": 9500 + }, + { + "epoch": 0.23, + "learning_rate": 4.927215286936785e-05, + "loss": 0.955, + "step": 10000 + }, + { + "epoch": 0.24, + "learning_rate": 4.923381283930927e-05, + "loss": 0.9392, + "step": 10500 + }, + { + "epoch": 0.25, + "learning_rate": 4.919547280925069e-05, + "loss": 0.9403, + "step": 11000 + }, + { + "epoch": 0.26, + "learning_rate": 4.91571327791921e-05, + "loss": 0.9177, + "step": 11500 + }, + { + "epoch": 0.28, + "learning_rate": 4.9118792749133516e-05, + "loss": 0.919, + "step": 12000 + }, + { + "epoch": 0.29, + "learning_rate": 4.908045271907493e-05, + "loss": 0.9036, + "step": 12500 + }, + { + "epoch": 0.3, + "learning_rate": 4.9042189369076466e-05, + "loss": 0.9019, + "step": 13000 + }, + { + "epoch": 0.31, + "learning_rate": 4.9003849339017884e-05, + "loss": 0.8969, + "step": 13500 + }, + { + "epoch": 0.32, + "learning_rate": 4.89655093089593e-05, + "loss": 0.891, + "step": 14000 + }, + { + "epoch": 0.33, + "learning_rate": 4.892716927890072e-05, + "loss": 0.8904, + "step": 14500 + }, + { + "epoch": 0.34, + "learning_rate": 4.888882924884213e-05, + "loss": 0.8833, + "step": 15000 + }, + { + "epoch": 0.36, + "learning_rate": 4.8850489218783554e-05, + "loss": 0.8668, + "step": 15500 + }, + { + "epoch": 0.37, + "learning_rate": 4.8812149188724965e-05, + "loss": 0.8692, + "step": 16000 + }, + { + "epoch": 0.38, + "learning_rate": 4.877380915866638e-05, + "loss": 0.8617, + "step": 16500 + }, + { + "epoch": 0.39, + "learning_rate": 4.8735469128607794e-05, + "loss": 0.866, + "step": 17000 + }, + { + "epoch": 0.4, + "learning_rate": 4.869720577860933e-05, + "loss": 0.8592, + "step": 17500 + }, + { + "epoch": 0.41, + "learning_rate": 4.8658865748550744e-05, + "loss": 0.8586, + "step": 18000 + }, + { + "epoch": 0.43, + "learning_rate": 4.862052571849217e-05, + "loss": 0.84, + "step": 18500 + }, + { + "epoch": 0.44, + "learning_rate": 4.8582262368493695e-05, + "loss": 0.84, + "step": 19000 + }, + { + "epoch": 0.45, + "learning_rate": 4.854392233843512e-05, + "loss": 0.8397, + "step": 19500 + }, + { + "epoch": 0.46, + "learning_rate": 4.850581234855688e-05, + "loss": 0.8338, + "step": 20000 + }, + { + "epoch": 0.47, + "learning_rate": 4.84674723184983e-05, + "loss": 0.838, + "step": 20500 + }, + { + "epoch": 0.48, + "learning_rate": 4.842913228843972e-05, + "loss": 0.8391, + "step": 21000 + }, + { + "epoch": 0.49, + "learning_rate": 4.8390792258381135e-05, + "loss": 0.8276, + "step": 21500 + }, + { + "epoch": 0.51, + "learning_rate": 4.8352452228322546e-05, + "loss": 0.8198, + "step": 22000 + }, + { + "epoch": 0.52, + "learning_rate": 4.8314112198263963e-05, + "loss": 0.8127, + "step": 22500 + }, + { + "epoch": 0.53, + "learning_rate": 4.827577216820538e-05, + "loss": 0.8184, + "step": 23000 + }, + { + "epoch": 0.54, + "learning_rate": 4.82374321381468e-05, + "loss": 0.817, + "step": 23500 + }, + { + "epoch": 0.55, + "learning_rate": 4.8199092108088216e-05, + "loss": 0.8196, + "step": 24000 + }, + { + "epoch": 0.56, + "learning_rate": 4.816075207802963e-05, + "loss": 0.8024, + "step": 24500 + }, + { + "epoch": 0.57, + "learning_rate": 4.812241204797105e-05, + "loss": 0.8133, + "step": 25000 + }, + { + "epoch": 0.59, + "learning_rate": 4.808407201791246e-05, + "loss": 0.8056, + "step": 25500 + }, + { + "epoch": 0.6, + "learning_rate": 4.804573198785388e-05, + "loss": 0.7972, + "step": 26000 + }, + { + "epoch": 0.61, + "learning_rate": 4.80073919577953e-05, + "loss": 0.8026, + "step": 26500 + }, + { + "epoch": 0.62, + "learning_rate": 4.7969051927736716e-05, + "loss": 0.7983, + "step": 27000 + }, + { + "epoch": 0.63, + "learning_rate": 4.793078857773824e-05, + "loss": 0.795, + "step": 27500 + }, + { + "epoch": 0.64, + "learning_rate": 4.7892448547679666e-05, + "loss": 0.803, + "step": 28000 + }, + { + "epoch": 0.66, + "learning_rate": 4.7854108517621084e-05, + "loss": 0.7911, + "step": 28500 + }, + { + "epoch": 0.67, + "learning_rate": 4.7815768487562494e-05, + "loss": 0.7757, + "step": 29000 + }, + { + "epoch": 0.68, + "learning_rate": 4.777742845750391e-05, + "loss": 0.777, + "step": 29500 + }, + { + "epoch": 0.69, + "learning_rate": 4.773908842744533e-05, + "loss": 0.7848, + "step": 30000 + }, + { + "epoch": 0.7, + "learning_rate": 4.770074839738675e-05, + "loss": 0.7834, + "step": 30500 + }, + { + "epoch": 0.71, + "learning_rate": 4.766240836732816e-05, + "loss": 0.7753, + "step": 31000 + }, + { + "epoch": 0.72, + "learning_rate": 4.7624068337269576e-05, + "loss": 0.7715, + "step": 31500 + }, + { + "epoch": 0.74, + "learning_rate": 4.7585728307211e-05, + "loss": 0.7714, + "step": 32000 + }, + { + "epoch": 0.75, + "learning_rate": 4.754738827715241e-05, + "loss": 0.7736, + "step": 32500 + }, + { + "epoch": 0.76, + "learning_rate": 4.750904824709383e-05, + "loss": 0.7767, + "step": 33000 + }, + { + "epoch": 0.77, + "learning_rate": 4.747070821703524e-05, + "loss": 0.7661, + "step": 33500 + }, + { + "epoch": 0.78, + "learning_rate": 4.7432368186976664e-05, + "loss": 0.7565, + "step": 34000 + }, + { + "epoch": 0.79, + "learning_rate": 4.739410483697819e-05, + "loss": 0.7515, + "step": 34500 + }, + { + "epoch": 0.8, + "learning_rate": 4.735584148697973e-05, + "loss": 0.7558, + "step": 35000 + }, + { + "epoch": 0.82, + "learning_rate": 4.731750145692114e-05, + "loss": 0.7642, + "step": 35500 + }, + { + "epoch": 0.83, + "learning_rate": 4.727916142686256e-05, + "loss": 0.7626, + "step": 36000 + }, + { + "epoch": 0.84, + "learning_rate": 4.7240821396803976e-05, + "loss": 0.7627, + "step": 36500 + }, + { + "epoch": 0.85, + "learning_rate": 4.7202481366745394e-05, + "loss": 0.7495, + "step": 37000 + }, + { + "epoch": 0.86, + "learning_rate": 4.716414133668681e-05, + "loss": 0.7582, + "step": 37500 + }, + { + "epoch": 0.87, + "learning_rate": 4.7125877986688344e-05, + "loss": 0.7481, + "step": 38000 + }, + { + "epoch": 0.88, + "learning_rate": 4.708753795662976e-05, + "loss": 0.7557, + "step": 38500 + }, + { + "epoch": 0.9, + "learning_rate": 4.704919792657117e-05, + "loss": 0.7384, + "step": 39000 + }, + { + "epoch": 0.91, + "learning_rate": 4.70108578965126e-05, + "loss": 0.742, + "step": 39500 + }, + { + "epoch": 0.92, + "learning_rate": 4.697251786645401e-05, + "loss": 0.7388, + "step": 40000 + }, + { + "epoch": 0.93, + "learning_rate": 4.6934177836395425e-05, + "loss": 0.7503, + "step": 40500 + }, + { + "epoch": 0.94, + "learning_rate": 4.689583780633684e-05, + "loss": 0.745, + "step": 41000 + }, + { + "epoch": 0.95, + "learning_rate": 4.685749777627826e-05, + "loss": 0.7228, + "step": 41500 + }, + { + "epoch": 0.97, + "learning_rate": 4.681915774621968e-05, + "loss": 0.7333, + "step": 42000 + }, + { + "epoch": 0.98, + "learning_rate": 4.678081771616109e-05, + "loss": 0.7371, + "step": 42500 + }, + { + "epoch": 0.99, + "learning_rate": 4.674247768610251e-05, + "loss": 0.733, + "step": 43000 + }, + { + "epoch": 1.0, + "learning_rate": 4.6704137656043925e-05, + "loss": 0.7241, + "step": 43500 + }, + { + "epoch": 1.0, + "eval_bleu": 56.112, + "eval_gen_len": 17.3165, + "eval_loss": 0.7177675366401672, + "eval_runtime": 7671.1849, + "eval_samples_per_second": 11.342, + "eval_steps_per_second": 1.418, + "step": 43504 + }, + { + "epoch": 1.01, + "learning_rate": 4.666587430604546e-05, + "loss": 0.7322, + "step": 44000 + }, + { + "epoch": 1.02, + "learning_rate": 4.6627534275986875e-05, + "loss": 0.7051, + "step": 44500 + }, + { + "epoch": 1.03, + "learning_rate": 4.658919424592829e-05, + "loss": 0.6935, + "step": 45000 + }, + { + "epoch": 1.05, + "learning_rate": 4.6550854215869704e-05, + "loss": 0.6831, + "step": 45500 + }, + { + "epoch": 1.06, + "learning_rate": 4.651259086587124e-05, + "loss": 0.6787, + "step": 46000 + }, + { + "epoch": 1.07, + "learning_rate": 4.6474327515872776e-05, + "loss": 0.6813, + "step": 46500 + }, + { + "epoch": 1.08, + "learning_rate": 4.6436140845934424e-05, + "loss": 0.6841, + "step": 47000 + }, + { + "epoch": 1.09, + "learning_rate": 4.639780081587584e-05, + "loss": 0.6697, + "step": 47500 + }, + { + "epoch": 1.1, + "learning_rate": 4.635946078581726e-05, + "loss": 0.6605, + "step": 48000 + }, + { + "epoch": 1.11, + "learning_rate": 4.632112075575868e-05, + "loss": 0.675, + "step": 48500 + }, + { + "epoch": 1.13, + "learning_rate": 4.6282780725700094e-05, + "loss": 0.6623, + "step": 49000 + }, + { + "epoch": 1.14, + "learning_rate": 4.6244440695641505e-05, + "loss": 0.6589, + "step": 49500 + }, + { + "epoch": 1.15, + "learning_rate": 4.620610066558292e-05, + "loss": 0.6476, + "step": 50000 + }, + { + "epoch": 1.16, + "learning_rate": 4.616776063552434e-05, + "loss": 0.6551, + "step": 50500 + }, + { + "epoch": 1.17, + "learning_rate": 4.612942060546576e-05, + "loss": 0.6502, + "step": 51000 + }, + { + "epoch": 1.18, + "learning_rate": 4.6091080575407176e-05, + "loss": 0.6478, + "step": 51500 + }, + { + "epoch": 1.2, + "learning_rate": 4.605274054534859e-05, + "loss": 0.6485, + "step": 52000 + }, + { + "epoch": 1.21, + "learning_rate": 4.6014400515290004e-05, + "loss": 0.6412, + "step": 52500 + }, + { + "epoch": 1.22, + "learning_rate": 4.597606048523142e-05, + "loss": 0.6376, + "step": 53000 + }, + { + "epoch": 1.23, + "learning_rate": 4.593772045517284e-05, + "loss": 0.6385, + "step": 53500 + }, + { + "epoch": 1.24, + "learning_rate": 4.589945710517437e-05, + "loss": 0.6366, + "step": 54000 + }, + { + "epoch": 1.25, + "learning_rate": 4.586111707511579e-05, + "loss": 0.6444, + "step": 54500 + }, + { + "epoch": 1.26, + "learning_rate": 4.582277704505721e-05, + "loss": 0.6311, + "step": 55000 + }, + { + "epoch": 1.28, + "learning_rate": 4.578451369505874e-05, + "loss": 0.6306, + "step": 55500 + }, + { + "epoch": 1.29, + "learning_rate": 4.574617366500016e-05, + "loss": 0.6199, + "step": 56000 + }, + { + "epoch": 1.3, + "learning_rate": 4.570783363494157e-05, + "loss": 0.6268, + "step": 56500 + }, + { + "epoch": 1.31, + "learning_rate": 4.566949360488299e-05, + "loss": 0.623, + "step": 57000 + }, + { + "epoch": 1.32, + "learning_rate": 4.5631153574824404e-05, + "loss": 0.6207, + "step": 57500 + }, + { + "epoch": 1.33, + "learning_rate": 4.559281354476582e-05, + "loss": 0.6204, + "step": 58000 + }, + { + "epoch": 1.34, + "learning_rate": 4.555447351470723e-05, + "loss": 0.6215, + "step": 58500 + }, + { + "epoch": 1.36, + "learning_rate": 4.551613348464866e-05, + "loss": 0.6114, + "step": 59000 + }, + { + "epoch": 1.37, + "learning_rate": 4.5477793454590075e-05, + "loss": 0.6134, + "step": 59500 + }, + { + "epoch": 1.38, + "learning_rate": 4.543953010459161e-05, + "loss": 0.6142, + "step": 60000 + }, + { + "epoch": 1.39, + "learning_rate": 4.5401190074533025e-05, + "loss": 0.6149, + "step": 60500 + }, + { + "epoch": 1.4, + "learning_rate": 4.5362850044474436e-05, + "loss": 0.6123, + "step": 61000 + }, + { + "epoch": 1.41, + "learning_rate": 4.5324510014415854e-05, + "loss": 0.6159, + "step": 61500 + }, + { + "epoch": 1.43, + "learning_rate": 4.5286246664417387e-05, + "loss": 0.6001, + "step": 62000 + }, + { + "epoch": 1.44, + "learning_rate": 4.5247906634358804e-05, + "loss": 0.6034, + "step": 62500 + }, + { + "epoch": 1.45, + "learning_rate": 4.520956660430022e-05, + "loss": 0.5999, + "step": 63000 + }, + { + "epoch": 1.46, + "learning_rate": 4.517122657424164e-05, + "loss": 0.6011, + "step": 63500 + }, + { + "epoch": 1.47, + "learning_rate": 4.513288654418305e-05, + "loss": 0.6051, + "step": 64000 + }, + { + "epoch": 1.48, + "learning_rate": 4.509454651412447e-05, + "loss": 0.6061, + "step": 64500 + }, + { + "epoch": 1.49, + "learning_rate": 4.5056206484065886e-05, + "loss": 0.598, + "step": 65000 + }, + { + "epoch": 1.51, + "learning_rate": 4.50178664540073e-05, + "loss": 0.5939, + "step": 65500 + }, + { + "epoch": 1.52, + "learning_rate": 4.497952642394872e-05, + "loss": 0.5905, + "step": 66000 + }, + { + "epoch": 1.53, + "learning_rate": 4.494118639389013e-05, + "loss": 0.5968, + "step": 66500 + }, + { + "epoch": 1.54, + "learning_rate": 4.490284636383155e-05, + "loss": 0.5943, + "step": 67000 + }, + { + "epoch": 1.55, + "learning_rate": 4.486450633377297e-05, + "loss": 0.6025, + "step": 67500 + }, + { + "epoch": 1.56, + "learning_rate": 4.4826166303714385e-05, + "loss": 0.5918, + "step": 68000 + }, + { + "epoch": 1.57, + "learning_rate": 4.47878262736558e-05, + "loss": 0.5983, + "step": 68500 + }, + { + "epoch": 1.59, + "learning_rate": 4.474948624359721e-05, + "loss": 0.5907, + "step": 69000 + }, + { + "epoch": 1.6, + "learning_rate": 4.471114621353864e-05, + "loss": 0.5852, + "step": 69500 + }, + { + "epoch": 1.61, + "learning_rate": 4.4672882863540164e-05, + "loss": 0.5886, + "step": 70000 + }, + { + "epoch": 1.62, + "learning_rate": 4.463454283348159e-05, + "loss": 0.5895, + "step": 70500 + }, + { + "epoch": 1.63, + "learning_rate": 4.4596202803423e-05, + "loss": 0.5887, + "step": 71000 + }, + { + "epoch": 1.64, + "learning_rate": 4.455786277336442e-05, + "loss": 0.5953, + "step": 71500 + }, + { + "epoch": 1.66, + "learning_rate": 4.451952274330583e-05, + "loss": 0.5888, + "step": 72000 + }, + { + "epoch": 1.67, + "learning_rate": 4.448118271324725e-05, + "loss": 0.571, + "step": 72500 + }, + { + "epoch": 1.68, + "learning_rate": 4.444291936324878e-05, + "loss": 0.576, + "step": 73000 + }, + { + "epoch": 1.69, + "learning_rate": 4.44045793331902e-05, + "loss": 0.5828, + "step": 73500 + }, + { + "epoch": 1.7, + "learning_rate": 4.436631598319173e-05, + "loss": 0.5875, + "step": 74000 + }, + { + "epoch": 1.71, + "learning_rate": 4.432797595313315e-05, + "loss": 0.5773, + "step": 74500 + }, + { + "epoch": 1.72, + "learning_rate": 4.428963592307457e-05, + "loss": 0.5741, + "step": 75000 + }, + { + "epoch": 1.74, + "learning_rate": 4.425129589301598e-05, + "loss": 0.5721, + "step": 75500 + }, + { + "epoch": 1.75, + "learning_rate": 4.42129558629574e-05, + "loss": 0.5797, + "step": 76000 + }, + { + "epoch": 1.76, + "learning_rate": 4.417461583289882e-05, + "loss": 0.5787, + "step": 76500 + }, + { + "epoch": 1.77, + "learning_rate": 4.4136275802840234e-05, + "loss": 0.5731, + "step": 77000 + }, + { + "epoch": 1.78, + "learning_rate": 4.409801245284177e-05, + "loss": 0.5642, + "step": 77500 + }, + { + "epoch": 1.79, + "learning_rate": 4.4059672422783185e-05, + "loss": 0.5653, + "step": 78000 + }, + { + "epoch": 1.8, + "learning_rate": 4.4021332392724596e-05, + "loss": 0.5663, + "step": 78500 + }, + { + "epoch": 1.82, + "learning_rate": 4.398299236266601e-05, + "loss": 0.5762, + "step": 79000 + }, + { + "epoch": 1.83, + "learning_rate": 4.394465233260743e-05, + "loss": 0.5742, + "step": 79500 + }, + { + "epoch": 1.84, + "learning_rate": 4.390631230254885e-05, + "loss": 0.5739, + "step": 80000 + }, + { + "epoch": 1.85, + "learning_rate": 4.3867972272490266e-05, + "loss": 0.5686, + "step": 80500 + }, + { + "epoch": 1.86, + "learning_rate": 4.382963224243168e-05, + "loss": 0.5757, + "step": 81000 + }, + { + "epoch": 1.87, + "learning_rate": 4.3791292212373095e-05, + "loss": 0.5654, + "step": 81500 + }, + { + "epoch": 1.88, + "learning_rate": 4.375295218231451e-05, + "loss": 0.5697, + "step": 82000 + }, + { + "epoch": 1.9, + "learning_rate": 4.371461215225593e-05, + "loss": 0.5582, + "step": 82500 + }, + { + "epoch": 1.91, + "learning_rate": 4.367627212219735e-05, + "loss": 0.5603, + "step": 83000 + }, + { + "epoch": 1.92, + "learning_rate": 4.363793209213876e-05, + "loss": 0.5564, + "step": 83500 + }, + { + "epoch": 1.93, + "learning_rate": 4.359959206208018e-05, + "loss": 0.5682, + "step": 84000 + }, + { + "epoch": 1.94, + "learning_rate": 4.356132871208171e-05, + "loss": 0.566, + "step": 84500 + }, + { + "epoch": 1.95, + "learning_rate": 4.3522988682023133e-05, + "loss": 0.5485, + "step": 85000 + }, + { + "epoch": 1.97, + "learning_rate": 4.3484648651964544e-05, + "loss": 0.5558, + "step": 85500 + }, + { + "epoch": 1.98, + "learning_rate": 4.344630862190596e-05, + "loss": 0.5592, + "step": 86000 + }, + { + "epoch": 1.99, + "learning_rate": 4.340796859184737e-05, + "loss": 0.5611, + "step": 86500 + }, + { + "epoch": 2.0, + "learning_rate": 4.337001196208938e-05, + "loss": 0.5523, + "step": 87000 + }, + { + "epoch": 2.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7592.1301, + "eval_samples_per_second": 11.46, + "eval_steps_per_second": 1.433, + "step": 87009 + } + ], + "logging_steps": 500, + "max_steps": 652560, + "num_train_epochs": 15, + "save_steps": 500, + "total_flos": 3.016956704056148e+18, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-87009/training_args.bin b/checkpoint-87009/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4d3d8487ffcaca78bad3b458878633a19376556 --- /dev/null +++ b/checkpoint-87009/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b731ecd386cb51a958b6c8f191496c616dc6e80b60cf4e62402772da333973 +size 4792 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d123d026fa1d1679aeb1220d9ae316d7c13a0b --- /dev/null +++ b/config.json @@ -0,0 +1,59 @@ +{ + "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt", + "_num_labels": 3, + "activation_dropout": 0.0, + "activation_function": "relu", + "add_bias_logits": false, + "add_final_layer_norm": true, + "architectures": [ + "MBartForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "classif_dropout": 0.0, + "classifier_dropout": 0.0, + "d_model": 1024, + "decoder_attention_heads": 16, + "decoder_ffn_dim": 4096, + "decoder_layerdrop": 0.0, + "decoder_layers": 12, + "decoder_start_token_id": 2, + "dropout": 0.1, + "early_stopping": true, + "encoder_attention_heads": 16, + "encoder_ffn_dim": 4096, + "encoder_layerdrop": 0.0, + "encoder_layers": 12, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "gradient_checkpointing": false, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "init_std": 0.02, + "is_encoder_decoder": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "max_length": 200, + "max_position_embeddings": 1024, + "model_type": "mbart", + "normalize_before": true, + "normalize_embedding": true, + "num_beams": 5, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "scale_embedding": true, + "static_position_embeddings": false, + "tokenizer_class": "MBart50Tokenizer", + "torch_dtype": "float32", + "transformers_version": "4.35.2", + "use_cache": true, + "vocab_size": 250054 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000000000000000000000000000000000000..6d2164996adb104f9ddb1415517550f00583a497 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,10 @@ +{ + "epoch": 5.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7593.4193, + "eval_samples": 87008, + "eval_samples_per_second": 11.458, + "eval_steps_per_second": 1.432 +} \ No newline at end of file diff --git a/generated_predictions.txt b/generated_predictions.txt new file mode 100644 index 0000000000000000000000000000000000000000..c20c4520620d092d4fbad4b90341a5ce39048468 --- /dev/null +++ b/generated_predictions.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431aa86a9803d5e843e3caf1cf78f07ea0952f409e0c85897d2c8b8ab08ae970 +size 11528951 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7e47c12e3900189593d4b56d0d776b58a7a55627 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 0, + "decoder_start_token_id": 2, + "early_stopping": true, + "eos_token_id": 2, + "forced_bos_token_id": 250014, + "forced_eos_token_id": 2, + "max_length": 200, + "num_beams": 5, + "pad_token_id": 1, + "transformers_version": "4.35.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa743281f23a96ca2d66c81e92341c36254529df --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f359d7b7a214b7d33f8b720df9fb4977922176e4c5fa16d91238daeb1027a2 +size 2444578688 diff --git a/predict_results.json b/predict_results.json new file mode 100644 index 0000000000000000000000000000000000000000..ddfff8c2f7d26ae1087a36598c85055d07118ff6 --- /dev/null +++ b/predict_results.json @@ -0,0 +1,9 @@ +{ + "predict_bleu": 58.0783, + "predict_gen_len": 17.2409, + "predict_loss": 0.6792132258415222, + "predict_runtime": 7605.1607, + "predict_samples": 87008, + "predict_samples_per_second": 11.441, + "predict_steps_per_second": 1.43 +} \ No newline at end of file diff --git a/sentencepiece.bpe.model b/sentencepiece.bpe.model new file mode 100644 index 0000000000000000000000000000000000000000..7a3f40a75f870bc1f21700cd414dc2acc431583c --- /dev/null +++ b/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92619141640d5fcbb4429807de2248352b0dca79 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,69 @@ +{ + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "cls_token": "", + "eos_token": "", + "mask_token": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86f15e5a3339d518716121ecef4c2a1dc9208b40 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf1fb0f45fdd5ae9fc44fafee492652a423fc749833ef57c2fa801358549d92 +size 17110107 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..70c0515a5815fcc727e11e053116348bfac12128 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,528 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250001": { + "content": "ar_AR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250002": { + "content": "cs_CZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250003": { + "content": "de_DE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250004": { + "content": "en_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250005": { + "content": "es_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250006": { + "content": "et_EE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250007": { + "content": "fi_FI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250008": { + "content": "fr_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250009": { + "content": "gu_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250010": { + "content": "hi_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250011": { + "content": "it_IT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250012": { + "content": "ja_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250013": { + "content": "kk_KZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250014": { + "content": "ko_KR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250015": { + "content": "lt_LT", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250016": { + "content": "lv_LV", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250017": { + "content": "my_MM", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250018": { + "content": "ne_NP", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250019": { + "content": "nl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250020": { + "content": "ro_RO", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250021": { + "content": "ru_RU", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250022": { + "content": "si_LK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250023": { + "content": "tr_TR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250024": { + "content": "vi_VN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250025": { + "content": "zh_CN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250026": { + "content": "af_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250027": { + "content": "az_AZ", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250028": { + "content": "bn_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250029": { + "content": "fa_IR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250030": { + "content": "he_IL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250031": { + "content": "hr_HR", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250032": { + "content": "id_ID", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250033": { + "content": "ka_GE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250034": { + "content": "km_KH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250035": { + "content": "mk_MK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250036": { + "content": "ml_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250037": { + "content": "mn_MN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250038": { + "content": "mr_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250039": { + "content": "pl_PL", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250040": { + "content": "ps_AF", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250041": { + "content": "pt_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250042": { + "content": "sv_SE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250043": { + "content": "sw_KE", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250044": { + "content": "ta_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250045": { + "content": "te_IN", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250046": { + "content": "th_TH", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250047": { + "content": "tl_XX", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250048": { + "content": "uk_UA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250049": { + "content": "ur_PK", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250050": { + "content": "xh_ZA", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250051": { + "content": "gl_ES", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250052": { + "content": "sl_SI", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250053": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "ar_AR", + "cs_CZ", + "de_DE", + "en_XX", + "es_XX", + "et_EE", + "fi_FI", + "fr_XX", + "gu_IN", + "hi_IN", + "it_IT", + "ja_XX", + "kk_KZ", + "ko_KR", + "lt_LT", + "lv_LV", + "my_MM", + "ne_NP", + "nl_XX", + "ro_RO", + "ru_RU", + "si_LK", + "tr_TR", + "vi_VN", + "zh_CN", + "af_ZA", + "az_AZ", + "bn_IN", + "fa_IR", + "he_IL", + "hr_HR", + "id_ID", + "ka_GE", + "km_KH", + "mk_MK", + "ml_IN", + "mn_MN", + "mr_IN", + "pl_PL", + "ps_AF", + "pt_XX", + "sv_SE", + "sw_KE", + "ta_IN", + "te_IN", + "th_TH", + "tl_XX", + "uk_UA", + "ur_PK", + "xh_ZA", + "gl_ES", + "sl_SI" + ], + "bos_token": "", + "clean_up_tokenization_spaces": true, + "cls_token": "", + "eos_token": "", + "language_codes": "ML50", + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sep_token": "", + "sp_model_kwargs": {}, + "src_lang": "ja_XX", + "tgt_lang": "ko_KR", + "tokenizer_class": "MBart50Tokenizer", + "unk_token": "" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..c495c8cd6b0ad2951f6bc09927dadc0b1e418cc0 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 5.0, + "train_loss": 0.5236641572812728, + "train_runtime": 206817.4399, + "train_samples": 696070, + "train_samples_per_second": 50.484, + "train_steps_per_second": 3.155 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..23ed50bc3df80562593648219c9e57b445af3a3c --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,2688 @@ +{ + "best_metric": 0.6814723610877991, + "best_model_checkpoint": "./jako_mbartLarge_100p_run1/checkpoint-87009", + "epoch": 4.999988506936064, + "eval_steps": 500, + "global_step": 217522, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 4.97e-05, + "loss": 1.9891, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 4.996196669018189e-05, + "loss": 1.5354, + "step": 1000 + }, + { + "epoch": 0.03, + "learning_rate": 4.9923626660123305e-05, + "loss": 1.3833, + "step": 1500 + }, + { + "epoch": 0.05, + "learning_rate": 4.988528663006472e-05, + "loss": 1.2912, + "step": 2000 + }, + { + "epoch": 0.06, + "learning_rate": 4.984694660000614e-05, + "loss": 1.2355, + "step": 2500 + }, + { + "epoch": 0.07, + "learning_rate": 4.980860656994755e-05, + "loss": 1.1927, + "step": 3000 + }, + { + "epoch": 0.08, + "learning_rate": 4.977026653988897e-05, + "loss": 1.166, + "step": 3500 + }, + { + "epoch": 0.09, + "learning_rate": 4.9731926509830386e-05, + "loss": 1.1238, + "step": 4000 + }, + { + "epoch": 0.1, + "learning_rate": 4.9693586479771804e-05, + "loss": 1.0972, + "step": 4500 + }, + { + "epoch": 0.11, + "learning_rate": 4.9655246449713215e-05, + "loss": 1.0964, + "step": 5000 + }, + { + "epoch": 0.13, + "learning_rate": 4.961690641965463e-05, + "loss": 1.0611, + "step": 5500 + }, + { + "epoch": 0.14, + "learning_rate": 4.957871974971629e-05, + "loss": 1.0487, + "step": 6000 + }, + { + "epoch": 0.15, + "learning_rate": 4.9540379719657705e-05, + "loss": 1.0166, + "step": 6500 + }, + { + "epoch": 0.16, + "learning_rate": 4.9502039689599116e-05, + "loss": 1.0162, + "step": 7000 + }, + { + "epoch": 0.17, + "learning_rate": 4.946369965954053e-05, + "loss": 0.9952, + "step": 7500 + }, + { + "epoch": 0.18, + "learning_rate": 4.942535962948195e-05, + "loss": 0.9853, + "step": 8000 + }, + { + "epoch": 0.2, + "learning_rate": 4.9387096279483484e-05, + "loss": 0.9835, + "step": 8500 + }, + { + "epoch": 0.21, + "learning_rate": 4.9348832929485017e-05, + "loss": 0.9634, + "step": 9000 + }, + { + "epoch": 0.22, + "learning_rate": 4.9310492899426434e-05, + "loss": 0.9532, + "step": 9500 + }, + { + "epoch": 0.23, + "learning_rate": 4.927215286936785e-05, + "loss": 0.955, + "step": 10000 + }, + { + "epoch": 0.24, + "learning_rate": 4.923381283930927e-05, + "loss": 0.9392, + "step": 10500 + }, + { + "epoch": 0.25, + "learning_rate": 4.919547280925069e-05, + "loss": 0.9403, + "step": 11000 + }, + { + "epoch": 0.26, + "learning_rate": 4.91571327791921e-05, + "loss": 0.9177, + "step": 11500 + }, + { + "epoch": 0.28, + "learning_rate": 4.9118792749133516e-05, + "loss": 0.919, + "step": 12000 + }, + { + "epoch": 0.29, + "learning_rate": 4.908045271907493e-05, + "loss": 0.9036, + "step": 12500 + }, + { + "epoch": 0.3, + "learning_rate": 4.9042189369076466e-05, + "loss": 0.9019, + "step": 13000 + }, + { + "epoch": 0.31, + "learning_rate": 4.9003849339017884e-05, + "loss": 0.8969, + "step": 13500 + }, + { + "epoch": 0.32, + "learning_rate": 4.89655093089593e-05, + "loss": 0.891, + "step": 14000 + }, + { + "epoch": 0.33, + "learning_rate": 4.892716927890072e-05, + "loss": 0.8904, + "step": 14500 + }, + { + "epoch": 0.34, + "learning_rate": 4.888882924884213e-05, + "loss": 0.8833, + "step": 15000 + }, + { + "epoch": 0.36, + "learning_rate": 4.8850489218783554e-05, + "loss": 0.8668, + "step": 15500 + }, + { + "epoch": 0.37, + "learning_rate": 4.8812149188724965e-05, + "loss": 0.8692, + "step": 16000 + }, + { + "epoch": 0.38, + "learning_rate": 4.877380915866638e-05, + "loss": 0.8617, + "step": 16500 + }, + { + "epoch": 0.39, + "learning_rate": 4.8735469128607794e-05, + "loss": 0.866, + "step": 17000 + }, + { + "epoch": 0.4, + "learning_rate": 4.869720577860933e-05, + "loss": 0.8592, + "step": 17500 + }, + { + "epoch": 0.41, + "learning_rate": 4.8658865748550744e-05, + "loss": 0.8586, + "step": 18000 + }, + { + "epoch": 0.43, + "learning_rate": 4.862052571849217e-05, + "loss": 0.84, + "step": 18500 + }, + { + "epoch": 0.44, + "learning_rate": 4.8582262368493695e-05, + "loss": 0.84, + "step": 19000 + }, + { + "epoch": 0.45, + "learning_rate": 4.854392233843512e-05, + "loss": 0.8397, + "step": 19500 + }, + { + "epoch": 0.46, + "learning_rate": 4.850581234855688e-05, + "loss": 0.8338, + "step": 20000 + }, + { + "epoch": 0.47, + "learning_rate": 4.84674723184983e-05, + "loss": 0.838, + "step": 20500 + }, + { + "epoch": 0.48, + "learning_rate": 4.842913228843972e-05, + "loss": 0.8391, + "step": 21000 + }, + { + "epoch": 0.49, + "learning_rate": 4.8390792258381135e-05, + "loss": 0.8276, + "step": 21500 + }, + { + "epoch": 0.51, + "learning_rate": 4.8352452228322546e-05, + "loss": 0.8198, + "step": 22000 + }, + { + "epoch": 0.52, + "learning_rate": 4.8314112198263963e-05, + "loss": 0.8127, + "step": 22500 + }, + { + "epoch": 0.53, + "learning_rate": 4.827577216820538e-05, + "loss": 0.8184, + "step": 23000 + }, + { + "epoch": 0.54, + "learning_rate": 4.82374321381468e-05, + "loss": 0.817, + "step": 23500 + }, + { + "epoch": 0.55, + "learning_rate": 4.8199092108088216e-05, + "loss": 0.8196, + "step": 24000 + }, + { + "epoch": 0.56, + "learning_rate": 4.816075207802963e-05, + "loss": 0.8024, + "step": 24500 + }, + { + "epoch": 0.57, + "learning_rate": 4.812241204797105e-05, + "loss": 0.8133, + "step": 25000 + }, + { + "epoch": 0.59, + "learning_rate": 4.808407201791246e-05, + "loss": 0.8056, + "step": 25500 + }, + { + "epoch": 0.6, + "learning_rate": 4.804573198785388e-05, + "loss": 0.7972, + "step": 26000 + }, + { + "epoch": 0.61, + "learning_rate": 4.80073919577953e-05, + "loss": 0.8026, + "step": 26500 + }, + { + "epoch": 0.62, + "learning_rate": 4.7969051927736716e-05, + "loss": 0.7983, + "step": 27000 + }, + { + "epoch": 0.63, + "learning_rate": 4.793078857773824e-05, + "loss": 0.795, + "step": 27500 + }, + { + "epoch": 0.64, + "learning_rate": 4.7892448547679666e-05, + "loss": 0.803, + "step": 28000 + }, + { + "epoch": 0.66, + "learning_rate": 4.7854108517621084e-05, + "loss": 0.7911, + "step": 28500 + }, + { + "epoch": 0.67, + "learning_rate": 4.7815768487562494e-05, + "loss": 0.7757, + "step": 29000 + }, + { + "epoch": 0.68, + "learning_rate": 4.777742845750391e-05, + "loss": 0.777, + "step": 29500 + }, + { + "epoch": 0.69, + "learning_rate": 4.773908842744533e-05, + "loss": 0.7848, + "step": 30000 + }, + { + "epoch": 0.7, + "learning_rate": 4.770074839738675e-05, + "loss": 0.7834, + "step": 30500 + }, + { + "epoch": 0.71, + "learning_rate": 4.766240836732816e-05, + "loss": 0.7753, + "step": 31000 + }, + { + "epoch": 0.72, + "learning_rate": 4.7624068337269576e-05, + "loss": 0.7715, + "step": 31500 + }, + { + "epoch": 0.74, + "learning_rate": 4.7585728307211e-05, + "loss": 0.7714, + "step": 32000 + }, + { + "epoch": 0.75, + "learning_rate": 4.754738827715241e-05, + "loss": 0.7736, + "step": 32500 + }, + { + "epoch": 0.76, + "learning_rate": 4.750904824709383e-05, + "loss": 0.7767, + "step": 33000 + }, + { + "epoch": 0.77, + "learning_rate": 4.747070821703524e-05, + "loss": 0.7661, + "step": 33500 + }, + { + "epoch": 0.78, + "learning_rate": 4.7432368186976664e-05, + "loss": 0.7565, + "step": 34000 + }, + { + "epoch": 0.79, + "learning_rate": 4.739410483697819e-05, + "loss": 0.7515, + "step": 34500 + }, + { + "epoch": 0.8, + "learning_rate": 4.735584148697973e-05, + "loss": 0.7558, + "step": 35000 + }, + { + "epoch": 0.82, + "learning_rate": 4.731750145692114e-05, + "loss": 0.7642, + "step": 35500 + }, + { + "epoch": 0.83, + "learning_rate": 4.727916142686256e-05, + "loss": 0.7626, + "step": 36000 + }, + { + "epoch": 0.84, + "learning_rate": 4.7240821396803976e-05, + "loss": 0.7627, + "step": 36500 + }, + { + "epoch": 0.85, + "learning_rate": 4.7202481366745394e-05, + "loss": 0.7495, + "step": 37000 + }, + { + "epoch": 0.86, + "learning_rate": 4.716414133668681e-05, + "loss": 0.7582, + "step": 37500 + }, + { + "epoch": 0.87, + "learning_rate": 4.7125877986688344e-05, + "loss": 0.7481, + "step": 38000 + }, + { + "epoch": 0.88, + "learning_rate": 4.708753795662976e-05, + "loss": 0.7557, + "step": 38500 + }, + { + "epoch": 0.9, + "learning_rate": 4.704919792657117e-05, + "loss": 0.7384, + "step": 39000 + }, + { + "epoch": 0.91, + "learning_rate": 4.70108578965126e-05, + "loss": 0.742, + "step": 39500 + }, + { + "epoch": 0.92, + "learning_rate": 4.697251786645401e-05, + "loss": 0.7388, + "step": 40000 + }, + { + "epoch": 0.93, + "learning_rate": 4.6934177836395425e-05, + "loss": 0.7503, + "step": 40500 + }, + { + "epoch": 0.94, + "learning_rate": 4.689583780633684e-05, + "loss": 0.745, + "step": 41000 + }, + { + "epoch": 0.95, + "learning_rate": 4.685749777627826e-05, + "loss": 0.7228, + "step": 41500 + }, + { + "epoch": 0.97, + "learning_rate": 4.681915774621968e-05, + "loss": 0.7333, + "step": 42000 + }, + { + "epoch": 0.98, + "learning_rate": 4.678081771616109e-05, + "loss": 0.7371, + "step": 42500 + }, + { + "epoch": 0.99, + "learning_rate": 4.674247768610251e-05, + "loss": 0.733, + "step": 43000 + }, + { + "epoch": 1.0, + "learning_rate": 4.6704137656043925e-05, + "loss": 0.7241, + "step": 43500 + }, + { + "epoch": 1.0, + "eval_bleu": 56.112, + "eval_gen_len": 17.3165, + "eval_loss": 0.7177675366401672, + "eval_runtime": 7671.1849, + "eval_samples_per_second": 11.342, + "eval_steps_per_second": 1.418, + "step": 43504 + }, + { + "epoch": 1.01, + "learning_rate": 4.666587430604546e-05, + "loss": 0.7322, + "step": 44000 + }, + { + "epoch": 1.02, + "learning_rate": 4.6627534275986875e-05, + "loss": 0.7051, + "step": 44500 + }, + { + "epoch": 1.03, + "learning_rate": 4.658919424592829e-05, + "loss": 0.6935, + "step": 45000 + }, + { + "epoch": 1.05, + "learning_rate": 4.6550854215869704e-05, + "loss": 0.6831, + "step": 45500 + }, + { + "epoch": 1.06, + "learning_rate": 4.651259086587124e-05, + "loss": 0.6787, + "step": 46000 + }, + { + "epoch": 1.07, + "learning_rate": 4.6474327515872776e-05, + "loss": 0.6813, + "step": 46500 + }, + { + "epoch": 1.08, + "learning_rate": 4.6436140845934424e-05, + "loss": 0.6841, + "step": 47000 + }, + { + "epoch": 1.09, + "learning_rate": 4.639780081587584e-05, + "loss": 0.6697, + "step": 47500 + }, + { + "epoch": 1.1, + "learning_rate": 4.635946078581726e-05, + "loss": 0.6605, + "step": 48000 + }, + { + "epoch": 1.11, + "learning_rate": 4.632112075575868e-05, + "loss": 0.675, + "step": 48500 + }, + { + "epoch": 1.13, + "learning_rate": 4.6282780725700094e-05, + "loss": 0.6623, + "step": 49000 + }, + { + "epoch": 1.14, + "learning_rate": 4.6244440695641505e-05, + "loss": 0.6589, + "step": 49500 + }, + { + "epoch": 1.15, + "learning_rate": 4.620610066558292e-05, + "loss": 0.6476, + "step": 50000 + }, + { + "epoch": 1.16, + "learning_rate": 4.616776063552434e-05, + "loss": 0.6551, + "step": 50500 + }, + { + "epoch": 1.17, + "learning_rate": 4.612942060546576e-05, + "loss": 0.6502, + "step": 51000 + }, + { + "epoch": 1.18, + "learning_rate": 4.6091080575407176e-05, + "loss": 0.6478, + "step": 51500 + }, + { + "epoch": 1.2, + "learning_rate": 4.605274054534859e-05, + "loss": 0.6485, + "step": 52000 + }, + { + "epoch": 1.21, + "learning_rate": 4.6014400515290004e-05, + "loss": 0.6412, + "step": 52500 + }, + { + "epoch": 1.22, + "learning_rate": 4.597606048523142e-05, + "loss": 0.6376, + "step": 53000 + }, + { + "epoch": 1.23, + "learning_rate": 4.593772045517284e-05, + "loss": 0.6385, + "step": 53500 + }, + { + "epoch": 1.24, + "learning_rate": 4.589945710517437e-05, + "loss": 0.6366, + "step": 54000 + }, + { + "epoch": 1.25, + "learning_rate": 4.586111707511579e-05, + "loss": 0.6444, + "step": 54500 + }, + { + "epoch": 1.26, + "learning_rate": 4.582277704505721e-05, + "loss": 0.6311, + "step": 55000 + }, + { + "epoch": 1.28, + "learning_rate": 4.578451369505874e-05, + "loss": 0.6306, + "step": 55500 + }, + { + "epoch": 1.29, + "learning_rate": 4.574617366500016e-05, + "loss": 0.6199, + "step": 56000 + }, + { + "epoch": 1.3, + "learning_rate": 4.570783363494157e-05, + "loss": 0.6268, + "step": 56500 + }, + { + "epoch": 1.31, + "learning_rate": 4.566949360488299e-05, + "loss": 0.623, + "step": 57000 + }, + { + "epoch": 1.32, + "learning_rate": 4.5631153574824404e-05, + "loss": 0.6207, + "step": 57500 + }, + { + "epoch": 1.33, + "learning_rate": 4.559281354476582e-05, + "loss": 0.6204, + "step": 58000 + }, + { + "epoch": 1.34, + "learning_rate": 4.555447351470723e-05, + "loss": 0.6215, + "step": 58500 + }, + { + "epoch": 1.36, + "learning_rate": 4.551613348464866e-05, + "loss": 0.6114, + "step": 59000 + }, + { + "epoch": 1.37, + "learning_rate": 4.5477793454590075e-05, + "loss": 0.6134, + "step": 59500 + }, + { + "epoch": 1.38, + "learning_rate": 4.543953010459161e-05, + "loss": 0.6142, + "step": 60000 + }, + { + "epoch": 1.39, + "learning_rate": 4.5401190074533025e-05, + "loss": 0.6149, + "step": 60500 + }, + { + "epoch": 1.4, + "learning_rate": 4.5362850044474436e-05, + "loss": 0.6123, + "step": 61000 + }, + { + "epoch": 1.41, + "learning_rate": 4.5324510014415854e-05, + "loss": 0.6159, + "step": 61500 + }, + { + "epoch": 1.43, + "learning_rate": 4.5286246664417387e-05, + "loss": 0.6001, + "step": 62000 + }, + { + "epoch": 1.44, + "learning_rate": 4.5247906634358804e-05, + "loss": 0.6034, + "step": 62500 + }, + { + "epoch": 1.45, + "learning_rate": 4.520956660430022e-05, + "loss": 0.5999, + "step": 63000 + }, + { + "epoch": 1.46, + "learning_rate": 4.517122657424164e-05, + "loss": 0.6011, + "step": 63500 + }, + { + "epoch": 1.47, + "learning_rate": 4.513288654418305e-05, + "loss": 0.6051, + "step": 64000 + }, + { + "epoch": 1.48, + "learning_rate": 4.509454651412447e-05, + "loss": 0.6061, + "step": 64500 + }, + { + "epoch": 1.49, + "learning_rate": 4.5056206484065886e-05, + "loss": 0.598, + "step": 65000 + }, + { + "epoch": 1.51, + "learning_rate": 4.50178664540073e-05, + "loss": 0.5939, + "step": 65500 + }, + { + "epoch": 1.52, + "learning_rate": 4.497952642394872e-05, + "loss": 0.5905, + "step": 66000 + }, + { + "epoch": 1.53, + "learning_rate": 4.494118639389013e-05, + "loss": 0.5968, + "step": 66500 + }, + { + "epoch": 1.54, + "learning_rate": 4.490284636383155e-05, + "loss": 0.5943, + "step": 67000 + }, + { + "epoch": 1.55, + "learning_rate": 4.486450633377297e-05, + "loss": 0.6025, + "step": 67500 + }, + { + "epoch": 1.56, + "learning_rate": 4.4826166303714385e-05, + "loss": 0.5918, + "step": 68000 + }, + { + "epoch": 1.57, + "learning_rate": 4.47878262736558e-05, + "loss": 0.5983, + "step": 68500 + }, + { + "epoch": 1.59, + "learning_rate": 4.474948624359721e-05, + "loss": 0.5907, + "step": 69000 + }, + { + "epoch": 1.6, + "learning_rate": 4.471114621353864e-05, + "loss": 0.5852, + "step": 69500 + }, + { + "epoch": 1.61, + "learning_rate": 4.4672882863540164e-05, + "loss": 0.5886, + "step": 70000 + }, + { + "epoch": 1.62, + "learning_rate": 4.463454283348159e-05, + "loss": 0.5895, + "step": 70500 + }, + { + "epoch": 1.63, + "learning_rate": 4.4596202803423e-05, + "loss": 0.5887, + "step": 71000 + }, + { + "epoch": 1.64, + "learning_rate": 4.455786277336442e-05, + "loss": 0.5953, + "step": 71500 + }, + { + "epoch": 1.66, + "learning_rate": 4.451952274330583e-05, + "loss": 0.5888, + "step": 72000 + }, + { + "epoch": 1.67, + "learning_rate": 4.448118271324725e-05, + "loss": 0.571, + "step": 72500 + }, + { + "epoch": 1.68, + "learning_rate": 4.444291936324878e-05, + "loss": 0.576, + "step": 73000 + }, + { + "epoch": 1.69, + "learning_rate": 4.44045793331902e-05, + "loss": 0.5828, + "step": 73500 + }, + { + "epoch": 1.7, + "learning_rate": 4.436631598319173e-05, + "loss": 0.5875, + "step": 74000 + }, + { + "epoch": 1.71, + "learning_rate": 4.432797595313315e-05, + "loss": 0.5773, + "step": 74500 + }, + { + "epoch": 1.72, + "learning_rate": 4.428963592307457e-05, + "loss": 0.5741, + "step": 75000 + }, + { + "epoch": 1.74, + "learning_rate": 4.425129589301598e-05, + "loss": 0.5721, + "step": 75500 + }, + { + "epoch": 1.75, + "learning_rate": 4.42129558629574e-05, + "loss": 0.5797, + "step": 76000 + }, + { + "epoch": 1.76, + "learning_rate": 4.417461583289882e-05, + "loss": 0.5787, + "step": 76500 + }, + { + "epoch": 1.77, + "learning_rate": 4.4136275802840234e-05, + "loss": 0.5731, + "step": 77000 + }, + { + "epoch": 1.78, + "learning_rate": 4.409801245284177e-05, + "loss": 0.5642, + "step": 77500 + }, + { + "epoch": 1.79, + "learning_rate": 4.4059672422783185e-05, + "loss": 0.5653, + "step": 78000 + }, + { + "epoch": 1.8, + "learning_rate": 4.4021332392724596e-05, + "loss": 0.5663, + "step": 78500 + }, + { + "epoch": 1.82, + "learning_rate": 4.398299236266601e-05, + "loss": 0.5762, + "step": 79000 + }, + { + "epoch": 1.83, + "learning_rate": 4.394465233260743e-05, + "loss": 0.5742, + "step": 79500 + }, + { + "epoch": 1.84, + "learning_rate": 4.390631230254885e-05, + "loss": 0.5739, + "step": 80000 + }, + { + "epoch": 1.85, + "learning_rate": 4.3867972272490266e-05, + "loss": 0.5686, + "step": 80500 + }, + { + "epoch": 1.86, + "learning_rate": 4.382963224243168e-05, + "loss": 0.5757, + "step": 81000 + }, + { + "epoch": 1.87, + "learning_rate": 4.3791292212373095e-05, + "loss": 0.5654, + "step": 81500 + }, + { + "epoch": 1.88, + "learning_rate": 4.375295218231451e-05, + "loss": 0.5697, + "step": 82000 + }, + { + "epoch": 1.9, + "learning_rate": 4.371461215225593e-05, + "loss": 0.5582, + "step": 82500 + }, + { + "epoch": 1.91, + "learning_rate": 4.367627212219735e-05, + "loss": 0.5603, + "step": 83000 + }, + { + "epoch": 1.92, + "learning_rate": 4.363793209213876e-05, + "loss": 0.5564, + "step": 83500 + }, + { + "epoch": 1.93, + "learning_rate": 4.359959206208018e-05, + "loss": 0.5682, + "step": 84000 + }, + { + "epoch": 1.94, + "learning_rate": 4.356132871208171e-05, + "loss": 0.566, + "step": 84500 + }, + { + "epoch": 1.95, + "learning_rate": 4.3522988682023133e-05, + "loss": 0.5485, + "step": 85000 + }, + { + "epoch": 1.97, + "learning_rate": 4.3484648651964544e-05, + "loss": 0.5558, + "step": 85500 + }, + { + "epoch": 1.98, + "learning_rate": 4.344630862190596e-05, + "loss": 0.5592, + "step": 86000 + }, + { + "epoch": 1.99, + "learning_rate": 4.340796859184737e-05, + "loss": 0.5611, + "step": 86500 + }, + { + "epoch": 2.0, + "learning_rate": 4.337001196208938e-05, + "loss": 0.5523, + "step": 87000 + }, + { + "epoch": 2.0, + "eval_bleu": 57.9768, + "eval_gen_len": 17.2796, + "eval_loss": 0.6814723610877991, + "eval_runtime": 7592.1301, + "eval_samples_per_second": 11.46, + "eval_steps_per_second": 1.433, + "step": 87009 + }, + { + "epoch": 2.01, + "learning_rate": 4.33316719320308e-05, + "loss": 0.5617, + "step": 87500 + }, + { + "epoch": 2.02, + "learning_rate": 4.3293331901972215e-05, + "loss": 0.5392, + "step": 88000 + }, + { + "epoch": 2.03, + "learning_rate": 4.325499187191363e-05, + "loss": 0.5313, + "step": 88500 + }, + { + "epoch": 2.05, + "learning_rate": 4.321665184185504e-05, + "loss": 0.5247, + "step": 89000 + }, + { + "epoch": 2.06, + "learning_rate": 4.317831181179646e-05, + "loss": 0.5183, + "step": 89500 + }, + { + "epoch": 2.07, + "learning_rate": 4.313997178173788e-05, + "loss": 0.5266, + "step": 90000 + }, + { + "epoch": 2.08, + "learning_rate": 4.3101631751679296e-05, + "loss": 0.5256, + "step": 90500 + }, + { + "epoch": 2.09, + "learning_rate": 4.3063291721620714e-05, + "loss": 0.5148, + "step": 91000 + }, + { + "epoch": 2.1, + "learning_rate": 4.3024951691562125e-05, + "loss": 0.5097, + "step": 91500 + }, + { + "epoch": 2.11, + "learning_rate": 4.298661166150354e-05, + "loss": 0.5192, + "step": 92000 + }, + { + "epoch": 2.13, + "learning_rate": 4.294827163144496e-05, + "loss": 0.5125, + "step": 92500 + }, + { + "epoch": 2.14, + "learning_rate": 4.290993160138638e-05, + "loss": 0.5049, + "step": 93000 + }, + { + "epoch": 2.15, + "learning_rate": 4.2871591571327795e-05, + "loss": 0.4974, + "step": 93500 + }, + { + "epoch": 2.16, + "learning_rate": 4.2833251541269206e-05, + "loss": 0.5044, + "step": 94000 + }, + { + "epoch": 2.17, + "learning_rate": 4.279491151121063e-05, + "loss": 0.5026, + "step": 94500 + }, + { + "epoch": 2.18, + "learning_rate": 4.275657148115204e-05, + "loss": 0.5028, + "step": 95000 + }, + { + "epoch": 2.2, + "learning_rate": 4.271823145109346e-05, + "loss": 0.4992, + "step": 95500 + }, + { + "epoch": 2.21, + "learning_rate": 4.267989142103488e-05, + "loss": 0.5, + "step": 96000 + }, + { + "epoch": 2.22, + "learning_rate": 4.264162807103641e-05, + "loss": 0.4942, + "step": 96500 + }, + { + "epoch": 2.23, + "learning_rate": 4.260328804097782e-05, + "loss": 0.4942, + "step": 97000 + }, + { + "epoch": 2.24, + "learning_rate": 4.2564948010919245e-05, + "loss": 0.4952, + "step": 97500 + }, + { + "epoch": 2.25, + "learning_rate": 4.252660798086066e-05, + "loss": 0.4977, + "step": 98000 + }, + { + "epoch": 2.26, + "learning_rate": 4.2488344630862195e-05, + "loss": 0.4894, + "step": 98500 + }, + { + "epoch": 2.28, + "learning_rate": 4.245008128086372e-05, + "loss": 0.4887, + "step": 99000 + }, + { + "epoch": 2.29, + "learning_rate": 4.2411741250805146e-05, + "loss": 0.4813, + "step": 99500 + }, + { + "epoch": 2.3, + "learning_rate": 4.2373401220746563e-05, + "loss": 0.4851, + "step": 100000 + }, + { + "epoch": 2.31, + "learning_rate": 4.2335061190687974e-05, + "loss": 0.4865, + "step": 100500 + }, + { + "epoch": 2.32, + "learning_rate": 4.229672116062939e-05, + "loss": 0.4823, + "step": 101000 + }, + { + "epoch": 2.33, + "learning_rate": 4.225838113057081e-05, + "loss": 0.4806, + "step": 101500 + }, + { + "epoch": 2.34, + "learning_rate": 4.222011778057234e-05, + "loss": 0.4813, + "step": 102000 + }, + { + "epoch": 2.36, + "learning_rate": 4.218177775051376e-05, + "loss": 0.4734, + "step": 102500 + }, + { + "epoch": 2.37, + "learning_rate": 4.214343772045518e-05, + "loss": 0.479, + "step": 103000 + }, + { + "epoch": 2.38, + "learning_rate": 4.210509769039659e-05, + "loss": 0.4778, + "step": 103500 + }, + { + "epoch": 2.39, + "learning_rate": 4.2066757660338006e-05, + "loss": 0.4797, + "step": 104000 + }, + { + "epoch": 2.4, + "learning_rate": 4.2028417630279424e-05, + "loss": 0.474, + "step": 104500 + }, + { + "epoch": 2.41, + "learning_rate": 4.199007760022084e-05, + "loss": 0.4811, + "step": 105000 + }, + { + "epoch": 2.43, + "learning_rate": 4.1951814250222374e-05, + "loss": 0.464, + "step": 105500 + }, + { + "epoch": 2.44, + "learning_rate": 4.191347422016379e-05, + "loss": 0.4699, + "step": 106000 + }, + { + "epoch": 2.45, + "learning_rate": 4.187513419010521e-05, + "loss": 0.4655, + "step": 106500 + }, + { + "epoch": 2.46, + "learning_rate": 4.183679416004662e-05, + "loss": 0.4694, + "step": 107000 + }, + { + "epoch": 2.47, + "learning_rate": 4.179845412998804e-05, + "loss": 0.4698, + "step": 107500 + }, + { + "epoch": 2.48, + "learning_rate": 4.1760114099929456e-05, + "loss": 0.4714, + "step": 108000 + }, + { + "epoch": 2.49, + "learning_rate": 4.1721774069870873e-05, + "loss": 0.4627, + "step": 108500 + }, + { + "epoch": 2.51, + "learning_rate": 4.168343403981229e-05, + "loss": 0.4628, + "step": 109000 + }, + { + "epoch": 2.52, + "learning_rate": 4.16450940097537e-05, + "loss": 0.4565, + "step": 109500 + }, + { + "epoch": 2.53, + "learning_rate": 4.1606753979695126e-05, + "loss": 0.466, + "step": 110000 + }, + { + "epoch": 2.54, + "learning_rate": 4.156841394963654e-05, + "loss": 0.4635, + "step": 110500 + }, + { + "epoch": 2.55, + "learning_rate": 4.1530073919577955e-05, + "loss": 0.4694, + "step": 111000 + }, + { + "epoch": 2.56, + "learning_rate": 4.149181056957949e-05, + "loss": 0.4638, + "step": 111500 + }, + { + "epoch": 2.57, + "learning_rate": 4.1453470539520905e-05, + "loss": 0.4626, + "step": 112000 + }, + { + "epoch": 2.59, + "learning_rate": 4.1415130509462316e-05, + "loss": 0.4632, + "step": 112500 + }, + { + "epoch": 2.6, + "learning_rate": 4.137679047940374e-05, + "loss": 0.455, + "step": 113000 + }, + { + "epoch": 2.61, + "learning_rate": 4.133845044934516e-05, + "loss": 0.4553, + "step": 113500 + }, + { + "epoch": 2.62, + "learning_rate": 4.130018709934669e-05, + "loss": 0.4583, + "step": 114000 + }, + { + "epoch": 2.63, + "learning_rate": 4.126192374934822e-05, + "loss": 0.4596, + "step": 114500 + }, + { + "epoch": 2.64, + "learning_rate": 4.1223583719289635e-05, + "loss": 0.4634, + "step": 115000 + }, + { + "epoch": 2.65, + "learning_rate": 4.118524368923106e-05, + "loss": 0.4595, + "step": 115500 + }, + { + "epoch": 2.67, + "learning_rate": 4.1146980339232585e-05, + "loss": 0.4441, + "step": 116000 + }, + { + "epoch": 2.68, + "learning_rate": 4.110864030917401e-05, + "loss": 0.4517, + "step": 116500 + }, + { + "epoch": 2.69, + "learning_rate": 4.107030027911542e-05, + "loss": 0.4531, + "step": 117000 + }, + { + "epoch": 2.7, + "learning_rate": 4.103196024905684e-05, + "loss": 0.4556, + "step": 117500 + }, + { + "epoch": 2.71, + "learning_rate": 4.099362021899825e-05, + "loss": 0.4481, + "step": 118000 + }, + { + "epoch": 2.72, + "learning_rate": 4.095528018893967e-05, + "loss": 0.4483, + "step": 118500 + }, + { + "epoch": 2.74, + "learning_rate": 4.0916940158881084e-05, + "loss": 0.4457, + "step": 119000 + }, + { + "epoch": 2.75, + "learning_rate": 4.08786001288225e-05, + "loss": 0.452, + "step": 119500 + }, + { + "epoch": 2.76, + "learning_rate": 4.084026009876392e-05, + "loss": 0.4511, + "step": 120000 + }, + { + "epoch": 2.77, + "learning_rate": 4.080192006870534e-05, + "loss": 0.4466, + "step": 120500 + }, + { + "epoch": 2.78, + "learning_rate": 4.0763580038646755e-05, + "loss": 0.4368, + "step": 121000 + }, + { + "epoch": 2.79, + "learning_rate": 4.0725240008588166e-05, + "loss": 0.443, + "step": 121500 + }, + { + "epoch": 2.8, + "learning_rate": 4.0686976658589705e-05, + "loss": 0.441, + "step": 122000 + }, + { + "epoch": 2.82, + "learning_rate": 4.0648636628531116e-05, + "loss": 0.4503, + "step": 122500 + }, + { + "epoch": 2.83, + "learning_rate": 4.0610296598472534e-05, + "loss": 0.4487, + "step": 123000 + }, + { + "epoch": 2.84, + "learning_rate": 4.057195656841395e-05, + "loss": 0.4482, + "step": 123500 + }, + { + "epoch": 2.85, + "learning_rate": 4.053361653835537e-05, + "loss": 0.4449, + "step": 124000 + }, + { + "epoch": 2.86, + "learning_rate": 4.049527650829679e-05, + "loss": 0.4514, + "step": 124500 + }, + { + "epoch": 2.87, + "learning_rate": 4.04569364782382e-05, + "loss": 0.4407, + "step": 125000 + }, + { + "epoch": 2.88, + "learning_rate": 4.041867312823974e-05, + "loss": 0.443, + "step": 125500 + }, + { + "epoch": 2.9, + "learning_rate": 4.038033309818115e-05, + "loss": 0.434, + "step": 126000 + }, + { + "epoch": 2.91, + "learning_rate": 4.0341993068122566e-05, + "loss": 0.4384, + "step": 126500 + }, + { + "epoch": 2.92, + "learning_rate": 4.030365303806398e-05, + "loss": 0.4334, + "step": 127000 + }, + { + "epoch": 2.93, + "learning_rate": 4.0265389688065516e-05, + "loss": 0.4419, + "step": 127500 + }, + { + "epoch": 2.94, + "learning_rate": 4.0227049658006934e-05, + "loss": 0.4421, + "step": 128000 + }, + { + "epoch": 2.95, + "learning_rate": 4.018870962794835e-05, + "loss": 0.4244, + "step": 128500 + }, + { + "epoch": 2.97, + "learning_rate": 4.015036959788976e-05, + "loss": 0.4345, + "step": 129000 + }, + { + "epoch": 2.98, + "learning_rate": 4.01121062478913e-05, + "loss": 0.4374, + "step": 129500 + }, + { + "epoch": 2.99, + "learning_rate": 4.007376621783271e-05, + "loss": 0.4368, + "step": 130000 + }, + { + "epoch": 3.0, + "learning_rate": 4.003542618777413e-05, + "loss": 0.4356, + "step": 130500 + }, + { + "epoch": 3.0, + "eval_bleu": 58.5493, + "eval_gen_len": 17.1569, + "eval_loss": 0.7014300227165222, + "eval_runtime": 7450.9373, + "eval_samples_per_second": 11.677, + "eval_steps_per_second": 1.46, + "step": 130513 + }, + { + "epoch": 3.01, + "learning_rate": 3.9997086157715555e-05, + "loss": 0.4373, + "step": 131000 + }, + { + "epoch": 3.02, + "learning_rate": 3.9958746127656966e-05, + "loss": 0.42, + "step": 131500 + }, + { + "epoch": 3.03, + "learning_rate": 3.992040609759838e-05, + "loss": 0.4179, + "step": 132000 + }, + { + "epoch": 3.05, + "learning_rate": 3.9882066067539794e-05, + "loss": 0.406, + "step": 132500 + }, + { + "epoch": 3.06, + "learning_rate": 3.984372603748122e-05, + "loss": 0.4034, + "step": 133000 + }, + { + "epoch": 3.07, + "learning_rate": 3.980538600742263e-05, + "loss": 0.4103, + "step": 133500 + }, + { + "epoch": 3.08, + "learning_rate": 3.976704597736405e-05, + "loss": 0.4084, + "step": 134000 + }, + { + "epoch": 3.09, + "learning_rate": 3.9728705947305465e-05, + "loss": 0.4012, + "step": 134500 + }, + { + "epoch": 3.1, + "learning_rate": 3.969036591724688e-05, + "loss": 0.3966, + "step": 135000 + }, + { + "epoch": 3.11, + "learning_rate": 3.96520258871883e-05, + "loss": 0.4026, + "step": 135500 + }, + { + "epoch": 3.13, + "learning_rate": 3.961368585712971e-05, + "loss": 0.3983, + "step": 136000 + }, + { + "epoch": 3.14, + "learning_rate": 3.957542250713125e-05, + "loss": 0.3947, + "step": 136500 + }, + { + "epoch": 3.15, + "learning_rate": 3.953708247707266e-05, + "loss": 0.3894, + "step": 137000 + }, + { + "epoch": 3.16, + "learning_rate": 3.94988191270742e-05, + "loss": 0.3927, + "step": 137500 + }, + { + "epoch": 3.17, + "learning_rate": 3.946047909701561e-05, + "loss": 0.3919, + "step": 138000 + }, + { + "epoch": 3.18, + "learning_rate": 3.942213906695703e-05, + "loss": 0.3909, + "step": 138500 + }, + { + "epoch": 3.2, + "learning_rate": 3.938379903689845e-05, + "loss": 0.3914, + "step": 139000 + }, + { + "epoch": 3.21, + "learning_rate": 3.9345459006839865e-05, + "loss": 0.3876, + "step": 139500 + }, + { + "epoch": 3.22, + "learning_rate": 3.930727233690151e-05, + "loss": 0.3844, + "step": 140000 + }, + { + "epoch": 3.23, + "learning_rate": 3.926893230684293e-05, + "loss": 0.3871, + "step": 140500 + }, + { + "epoch": 3.24, + "learning_rate": 3.923059227678435e-05, + "loss": 0.3835, + "step": 141000 + }, + { + "epoch": 3.25, + "learning_rate": 3.9192252246725766e-05, + "loss": 0.3871, + "step": 141500 + }, + { + "epoch": 3.26, + "learning_rate": 3.915391221666718e-05, + "loss": 0.3803, + "step": 142000 + }, + { + "epoch": 3.28, + "learning_rate": 3.9115572186608594e-05, + "loss": 0.3776, + "step": 142500 + }, + { + "epoch": 3.29, + "learning_rate": 3.907723215655001e-05, + "loss": 0.3742, + "step": 143000 + }, + { + "epoch": 3.3, + "learning_rate": 3.903889212649143e-05, + "loss": 0.3778, + "step": 143500 + }, + { + "epoch": 3.31, + "learning_rate": 3.900055209643285e-05, + "loss": 0.3759, + "step": 144000 + }, + { + "epoch": 3.32, + "learning_rate": 3.896221206637426e-05, + "loss": 0.3756, + "step": 144500 + }, + { + "epoch": 3.33, + "learning_rate": 3.89239487163758e-05, + "loss": 0.3737, + "step": 145000 + }, + { + "epoch": 3.34, + "learning_rate": 3.888560868631721e-05, + "loss": 0.3749, + "step": 145500 + }, + { + "epoch": 3.36, + "learning_rate": 3.884734533631875e-05, + "loss": 0.3701, + "step": 146000 + }, + { + "epoch": 3.37, + "learning_rate": 3.880900530626016e-05, + "loss": 0.3736, + "step": 146500 + }, + { + "epoch": 3.38, + "learning_rate": 3.8770665276201576e-05, + "loss": 0.3706, + "step": 147000 + }, + { + "epoch": 3.39, + "learning_rate": 3.8732325246143e-05, + "loss": 0.3743, + "step": 147500 + }, + { + "epoch": 3.4, + "learning_rate": 3.869398521608441e-05, + "loss": 0.3665, + "step": 148000 + }, + { + "epoch": 3.41, + "learning_rate": 3.865564518602583e-05, + "loss": 0.3781, + "step": 148500 + }, + { + "epoch": 3.42, + "learning_rate": 3.861738183602736e-05, + "loss": 0.3591, + "step": 149000 + }, + { + "epoch": 3.44, + "learning_rate": 3.857904180596878e-05, + "loss": 0.365, + "step": 149500 + }, + { + "epoch": 3.45, + "learning_rate": 3.854070177591019e-05, + "loss": 0.3648, + "step": 150000 + }, + { + "epoch": 3.46, + "learning_rate": 3.8502361745851615e-05, + "loss": 0.3635, + "step": 150500 + }, + { + "epoch": 3.47, + "learning_rate": 3.8464021715793026e-05, + "loss": 0.3658, + "step": 151000 + }, + { + "epoch": 3.48, + "learning_rate": 3.8425681685734444e-05, + "loss": 0.3666, + "step": 151500 + }, + { + "epoch": 3.49, + "learning_rate": 3.838734165567586e-05, + "loss": 0.3579, + "step": 152000 + }, + { + "epoch": 3.51, + "learning_rate": 3.834900162561728e-05, + "loss": 0.3582, + "step": 152500 + }, + { + "epoch": 3.52, + "learning_rate": 3.8310661595558697e-05, + "loss": 0.3554, + "step": 153000 + }, + { + "epoch": 3.53, + "learning_rate": 3.8272474925620344e-05, + "loss": 0.3645, + "step": 153500 + }, + { + "epoch": 3.54, + "learning_rate": 3.823421157562188e-05, + "loss": 0.3605, + "step": 154000 + }, + { + "epoch": 3.55, + "learning_rate": 3.8195871545563295e-05, + "loss": 0.3657, + "step": 154500 + }, + { + "epoch": 3.56, + "learning_rate": 3.8157531515504706e-05, + "loss": 0.362, + "step": 155000 + }, + { + "epoch": 3.57, + "learning_rate": 3.811919148544612e-05, + "loss": 0.3585, + "step": 155500 + }, + { + "epoch": 3.59, + "learning_rate": 3.808085145538755e-05, + "loss": 0.3606, + "step": 156000 + }, + { + "epoch": 3.6, + "learning_rate": 3.8042664785449196e-05, + "loss": 0.3539, + "step": 156500 + }, + { + "epoch": 3.61, + "learning_rate": 3.8004324755390606e-05, + "loss": 0.3543, + "step": 157000 + }, + { + "epoch": 3.62, + "learning_rate": 3.7966061405392146e-05, + "loss": 0.3599, + "step": 157500 + }, + { + "epoch": 3.63, + "learning_rate": 3.792772137533356e-05, + "loss": 0.3613, + "step": 158000 + }, + { + "epoch": 3.64, + "learning_rate": 3.7889381345274975e-05, + "loss": 0.3616, + "step": 158500 + }, + { + "epoch": 3.65, + "learning_rate": 3.78510413152164e-05, + "loss": 0.357, + "step": 159000 + }, + { + "epoch": 3.67, + "learning_rate": 3.781270128515781e-05, + "loss": 0.3444, + "step": 159500 + }, + { + "epoch": 3.68, + "learning_rate": 3.777436125509923e-05, + "loss": 0.35, + "step": 160000 + }, + { + "epoch": 3.69, + "learning_rate": 3.773602122504064e-05, + "loss": 0.3515, + "step": 160500 + }, + { + "epoch": 3.7, + "learning_rate": 3.769768119498206e-05, + "loss": 0.3571, + "step": 161000 + }, + { + "epoch": 3.71, + "learning_rate": 3.7659341164923474e-05, + "loss": 0.3484, + "step": 161500 + }, + { + "epoch": 3.72, + "learning_rate": 3.762100113486489e-05, + "loss": 0.3467, + "step": 162000 + }, + { + "epoch": 3.74, + "learning_rate": 3.758266110480631e-05, + "loss": 0.3489, + "step": 162500 + }, + { + "epoch": 3.75, + "learning_rate": 3.754432107474773e-05, + "loss": 0.3505, + "step": 163000 + }, + { + "epoch": 3.76, + "learning_rate": 3.7505981044689144e-05, + "loss": 0.351, + "step": 163500 + }, + { + "epoch": 3.77, + "learning_rate": 3.7467641014630555e-05, + "loss": 0.3486, + "step": 164000 + }, + { + "epoch": 3.78, + "learning_rate": 3.7429377664632095e-05, + "loss": 0.3394, + "step": 164500 + }, + { + "epoch": 3.79, + "learning_rate": 3.7391037634573506e-05, + "loss": 0.3445, + "step": 165000 + }, + { + "epoch": 3.8, + "learning_rate": 3.735269760451492e-05, + "loss": 0.3417, + "step": 165500 + }, + { + "epoch": 3.82, + "learning_rate": 3.731435757445634e-05, + "loss": 0.3492, + "step": 166000 + }, + { + "epoch": 3.83, + "learning_rate": 3.727601754439776e-05, + "loss": 0.3519, + "step": 166500 + }, + { + "epoch": 3.84, + "learning_rate": 3.7237677514339176e-05, + "loss": 0.3484, + "step": 167000 + }, + { + "epoch": 3.85, + "learning_rate": 3.719933748428059e-05, + "loss": 0.3446, + "step": 167500 + }, + { + "epoch": 3.86, + "learning_rate": 3.7160997454222005e-05, + "loss": 0.3499, + "step": 168000 + }, + { + "epoch": 3.87, + "learning_rate": 3.712265742416342e-05, + "loss": 0.3465, + "step": 168500 + }, + { + "epoch": 3.88, + "learning_rate": 3.708431739410484e-05, + "loss": 0.3431, + "step": 169000 + }, + { + "epoch": 3.9, + "learning_rate": 3.704597736404625e-05, + "loss": 0.3379, + "step": 169500 + }, + { + "epoch": 3.91, + "learning_rate": 3.700771401404779e-05, + "loss": 0.3402, + "step": 170000 + }, + { + "epoch": 3.92, + "learning_rate": 3.69693739839892e-05, + "loss": 0.3379, + "step": 170500 + }, + { + "epoch": 3.93, + "learning_rate": 3.6931187314050856e-05, + "loss": 0.3468, + "step": 171000 + }, + { + "epoch": 3.94, + "learning_rate": 3.6892847283992274e-05, + "loss": 0.3433, + "step": 171500 + }, + { + "epoch": 3.95, + "learning_rate": 3.685450725393369e-05, + "loss": 0.3305, + "step": 172000 + }, + { + "epoch": 3.97, + "learning_rate": 3.68161672238751e-05, + "loss": 0.3373, + "step": 172500 + }, + { + "epoch": 3.98, + "learning_rate": 3.677782719381652e-05, + "loss": 0.3426, + "step": 173000 + }, + { + "epoch": 3.99, + "learning_rate": 3.673948716375794e-05, + "loss": 0.3387, + "step": 173500 + }, + { + "epoch": 4.0, + "learning_rate": 3.6701147133699355e-05, + "loss": 0.3407, + "step": 174000 + }, + { + "epoch": 4.0, + "eval_bleu": 58.3826, + "eval_gen_len": 17.1623, + "eval_loss": 0.7513108253479004, + "eval_runtime": 7458.9074, + "eval_samples_per_second": 11.665, + "eval_steps_per_second": 1.458, + "step": 174018 + }, + { + "epoch": 4.01, + "learning_rate": 3.666280710364077e-05, + "loss": 0.3395, + "step": 174500 + }, + { + "epoch": 4.02, + "learning_rate": 3.6624467073582184e-05, + "loss": 0.3242, + "step": 175000 + }, + { + "epoch": 4.03, + "learning_rate": 3.658612704352361e-05, + "loss": 0.3246, + "step": 175500 + }, + { + "epoch": 4.05, + "learning_rate": 3.654778701346502e-05, + "loss": 0.3132, + "step": 176000 + }, + { + "epoch": 4.06, + "learning_rate": 3.6509446983406437e-05, + "loss": 0.3129, + "step": 176500 + }, + { + "epoch": 4.07, + "learning_rate": 3.6471106953347854e-05, + "loss": 0.3162, + "step": 177000 + }, + { + "epoch": 4.08, + "learning_rate": 3.643276692328927e-05, + "loss": 0.316, + "step": 177500 + }, + { + "epoch": 4.09, + "learning_rate": 3.639442689323069e-05, + "loss": 0.3088, + "step": 178000 + }, + { + "epoch": 4.1, + "learning_rate": 3.63560868631721e-05, + "loss": 0.3048, + "step": 178500 + }, + { + "epoch": 4.11, + "learning_rate": 3.631774683311352e-05, + "loss": 0.3126, + "step": 179000 + }, + { + "epoch": 4.13, + "learning_rate": 3.627948348311505e-05, + "loss": 0.3091, + "step": 179500 + }, + { + "epoch": 4.14, + "learning_rate": 3.624114345305647e-05, + "loss": 0.3046, + "step": 180000 + }, + { + "epoch": 4.15, + "learning_rate": 3.6202803422997886e-05, + "loss": 0.3008, + "step": 180500 + }, + { + "epoch": 4.16, + "learning_rate": 3.6164463392939304e-05, + "loss": 0.3037, + "step": 181000 + }, + { + "epoch": 4.17, + "learning_rate": 3.612612336288072e-05, + "loss": 0.3034, + "step": 181500 + }, + { + "epoch": 4.18, + "learning_rate": 3.608778333282213e-05, + "loss": 0.3025, + "step": 182000 + }, + { + "epoch": 4.19, + "learning_rate": 3.604944330276355e-05, + "loss": 0.3021, + "step": 182500 + }, + { + "epoch": 4.21, + "learning_rate": 3.601117995276508e-05, + "loss": 0.3015, + "step": 183000 + }, + { + "epoch": 4.22, + "learning_rate": 3.59728399227065e-05, + "loss": 0.2977, + "step": 183500 + }, + { + "epoch": 4.23, + "learning_rate": 3.593449989264792e-05, + "loss": 0.2999, + "step": 184000 + }, + { + "epoch": 4.24, + "learning_rate": 3.5896159862589336e-05, + "loss": 0.2953, + "step": 184500 + }, + { + "epoch": 4.25, + "learning_rate": 3.5857819832530747e-05, + "loss": 0.2992, + "step": 185000 + }, + { + "epoch": 4.26, + "learning_rate": 3.5819479802472164e-05, + "loss": 0.2927, + "step": 185500 + }, + { + "epoch": 4.28, + "learning_rate": 3.578113977241359e-05, + "loss": 0.2929, + "step": 186000 + }, + { + "epoch": 4.29, + "learning_rate": 3.5742799742355e-05, + "loss": 0.2919, + "step": 186500 + }, + { + "epoch": 4.3, + "learning_rate": 3.570445971229642e-05, + "loss": 0.2953, + "step": 187000 + }, + { + "epoch": 4.31, + "learning_rate": 3.566611968223783e-05, + "loss": 0.2962, + "step": 187500 + }, + { + "epoch": 4.32, + "learning_rate": 3.562777965217925e-05, + "loss": 0.2908, + "step": 188000 + }, + { + "epoch": 4.33, + "learning_rate": 3.558943962212066e-05, + "loss": 0.2918, + "step": 188500 + }, + { + "epoch": 4.34, + "learning_rate": 3.555109959206208e-05, + "loss": 0.2898, + "step": 189000 + }, + { + "epoch": 4.36, + "learning_rate": 3.5512836242063614e-05, + "loss": 0.2876, + "step": 189500 + }, + { + "epoch": 4.37, + "learning_rate": 3.547449621200503e-05, + "loss": 0.2893, + "step": 190000 + }, + { + "epoch": 4.38, + "learning_rate": 3.543615618194645e-05, + "loss": 0.2857, + "step": 190500 + }, + { + "epoch": 4.39, + "learning_rate": 3.539781615188787e-05, + "loss": 0.2898, + "step": 191000 + }, + { + "epoch": 4.4, + "learning_rate": 3.53595528018894e-05, + "loss": 0.2834, + "step": 191500 + }, + { + "epoch": 4.41, + "learning_rate": 3.532121277183082e-05, + "loss": 0.289, + "step": 192000 + }, + { + "epoch": 4.42, + "learning_rate": 3.528294942183235e-05, + "loss": 0.2804, + "step": 192500 + }, + { + "epoch": 4.44, + "learning_rate": 3.524460939177376e-05, + "loss": 0.2839, + "step": 193000 + }, + { + "epoch": 4.45, + "learning_rate": 3.5206269361715185e-05, + "loss": 0.2785, + "step": 193500 + }, + { + "epoch": 4.46, + "learning_rate": 3.5167929331656596e-05, + "loss": 0.2802, + "step": 194000 + }, + { + "epoch": 4.47, + "learning_rate": 3.5129589301598014e-05, + "loss": 0.286, + "step": 194500 + }, + { + "epoch": 4.48, + "learning_rate": 3.509124927153943e-05, + "loss": 0.2859, + "step": 195000 + }, + { + "epoch": 4.49, + "learning_rate": 3.5052985921540964e-05, + "loss": 0.2774, + "step": 195500 + }, + { + "epoch": 4.51, + "learning_rate": 3.501479925160261e-05, + "loss": 0.2788, + "step": 196000 + }, + { + "epoch": 4.52, + "learning_rate": 3.4976459221544036e-05, + "loss": 0.2754, + "step": 196500 + }, + { + "epoch": 4.53, + "learning_rate": 3.493811919148545e-05, + "loss": 0.282, + "step": 197000 + }, + { + "epoch": 4.54, + "learning_rate": 3.4899779161426865e-05, + "loss": 0.2809, + "step": 197500 + }, + { + "epoch": 4.55, + "learning_rate": 3.48615158114284e-05, + "loss": 0.2872, + "step": 198000 + }, + { + "epoch": 4.56, + "learning_rate": 3.4823175781369815e-05, + "loss": 0.2806, + "step": 198500 + }, + { + "epoch": 4.57, + "learning_rate": 3.4784835751311226e-05, + "loss": 0.2746, + "step": 199000 + }, + { + "epoch": 4.59, + "learning_rate": 3.474649572125265e-05, + "loss": 0.2793, + "step": 199500 + }, + { + "epoch": 4.6, + "learning_rate": 3.4708232371254177e-05, + "loss": 0.2781, + "step": 200000 + }, + { + "epoch": 4.61, + "learning_rate": 3.4669969021255716e-05, + "loss": 0.2773, + "step": 200500 + }, + { + "epoch": 4.62, + "learning_rate": 3.463162899119713e-05, + "loss": 0.2782, + "step": 201000 + }, + { + "epoch": 4.63, + "learning_rate": 3.4593288961138545e-05, + "loss": 0.2777, + "step": 201500 + }, + { + "epoch": 4.64, + "learning_rate": 3.455494893107996e-05, + "loss": 0.2792, + "step": 202000 + }, + { + "epoch": 4.65, + "learning_rate": 3.451660890102138e-05, + "loss": 0.276, + "step": 202500 + }, + { + "epoch": 4.67, + "learning_rate": 3.44782688709628e-05, + "loss": 0.2663, + "step": 203000 + }, + { + "epoch": 4.68, + "learning_rate": 3.4439928840904215e-05, + "loss": 0.2697, + "step": 203500 + }, + { + "epoch": 4.69, + "learning_rate": 3.440158881084563e-05, + "loss": 0.2733, + "step": 204000 + }, + { + "epoch": 4.7, + "learning_rate": 3.4363248780787044e-05, + "loss": 0.2759, + "step": 204500 + }, + { + "epoch": 4.71, + "learning_rate": 3.432490875072846e-05, + "loss": 0.271, + "step": 205000 + }, + { + "epoch": 4.72, + "learning_rate": 3.428656872066988e-05, + "loss": 0.2669, + "step": 205500 + }, + { + "epoch": 4.74, + "learning_rate": 3.42482286906113e-05, + "loss": 0.268, + "step": 206000 + }, + { + "epoch": 4.75, + "learning_rate": 3.4209888660552714e-05, + "loss": 0.27, + "step": 206500 + }, + { + "epoch": 4.76, + "learning_rate": 3.4171548630494125e-05, + "loss": 0.2719, + "step": 207000 + }, + { + "epoch": 4.77, + "learning_rate": 3.413320860043554e-05, + "loss": 0.2723, + "step": 207500 + }, + { + "epoch": 4.78, + "learning_rate": 3.409486857037696e-05, + "loss": 0.2612, + "step": 208000 + }, + { + "epoch": 4.79, + "learning_rate": 3.405652854031838e-05, + "loss": 0.2661, + "step": 208500 + }, + { + "epoch": 4.8, + "learning_rate": 3.4018188510259796e-05, + "loss": 0.2641, + "step": 209000 + }, + { + "epoch": 4.82, + "learning_rate": 3.397984848020121e-05, + "loss": 0.2685, + "step": 209500 + }, + { + "epoch": 4.83, + "learning_rate": 3.394150845014263e-05, + "loss": 0.2716, + "step": 210000 + }, + { + "epoch": 4.84, + "learning_rate": 3.390324510014416e-05, + "loss": 0.2693, + "step": 210500 + }, + { + "epoch": 4.85, + "learning_rate": 3.386490507008558e-05, + "loss": 0.2686, + "step": 211000 + }, + { + "epoch": 4.86, + "learning_rate": 3.382656504002699e-05, + "loss": 0.2743, + "step": 211500 + }, + { + "epoch": 4.87, + "learning_rate": 3.378822500996841e-05, + "loss": 0.2672, + "step": 212000 + }, + { + "epoch": 4.88, + "learning_rate": 3.374988497990982e-05, + "loss": 0.2656, + "step": 212500 + }, + { + "epoch": 4.9, + "learning_rate": 3.3711544949851245e-05, + "loss": 0.2578, + "step": 213000 + }, + { + "epoch": 4.91, + "learning_rate": 3.367320491979266e-05, + "loss": 0.263, + "step": 213500 + }, + { + "epoch": 4.92, + "learning_rate": 3.3634864889734074e-05, + "loss": 0.2642, + "step": 214000 + }, + { + "epoch": 4.93, + "learning_rate": 3.3596601539735613e-05, + "loss": 0.2681, + "step": 214500 + }, + { + "epoch": 4.94, + "learning_rate": 3.3558261509677024e-05, + "loss": 0.2632, + "step": 215000 + }, + { + "epoch": 4.95, + "learning_rate": 3.351992147961844e-05, + "loss": 0.2538, + "step": 215500 + }, + { + "epoch": 4.97, + "learning_rate": 3.348158144955986e-05, + "loss": 0.2608, + "step": 216000 + }, + { + "epoch": 4.98, + "learning_rate": 3.344324141950128e-05, + "loss": 0.2641, + "step": 216500 + }, + { + "epoch": 4.99, + "learning_rate": 3.340490138944269e-05, + "loss": 0.2592, + "step": 217000 + }, + { + "epoch": 5.0, + "learning_rate": 3.336663803944423e-05, + "loss": 0.2605, + "step": 217500 + }, + { + "epoch": 5.0, + "eval_bleu": 58.7238, + "eval_gen_len": 17.0888, + "eval_loss": 0.8122135400772095, + "eval_runtime": 7422.7798, + "eval_samples_per_second": 11.722, + "eval_steps_per_second": 1.465, + "step": 217522 + }, + { + "epoch": 5.0, + "step": 217522, + "total_flos": 7.542391759939043e+18, + "train_loss": 0.5236641572812728, + "train_runtime": 206817.4399, + "train_samples_per_second": 50.484, + "train_steps_per_second": 3.155 + } + ], + "logging_steps": 500, + "max_steps": 652560, + "num_train_epochs": 15, + "save_steps": 500, + "total_flos": 7.542391759939043e+18, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4d3d8487ffcaca78bad3b458878633a19376556 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b731ecd386cb51a958b6c8f191496c616dc6e80b60cf4e62402772da333973 +size 4792