Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- ko
+- en
+base_model: ./reduced_model
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: tst-translation-output
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# tst-translation-output
+
+This model is a fine-tuned version of [./reduced_model](https://huggingface.co/./reduced_model) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7663
+- Bleu: 19.3382
+- Gen Len: 17.8929
+
+## 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: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 2.6161        | 11.09 | 2000 | 3.1762          | 13.5109 | 19.1966 |
+| 2.6161        | 13.86 | 2500 | 3.0375          | 16.2868 | 18.7985 |
+| 1.4467        | 16.62 | 3000 | 3.1328          | 17.6991 | 18.1949 |
+| 1.4467        | 19.39 | 3500 | 3.2690          | 17.9052 | 18.3117 |
+| 0.6809        | 22.15 | 4000 | 3.3850          | 18.4075 | 18.2149 |
+| 0.6809        | 24.91 | 4500 | 3.4465          | 19.0339 | 18.009  |
+| 0.3422        | 27.68 | 5000 | 3.5680          | 18.7281 | 17.5902 |
+| 0.3422        | 30.44 | 5500 | 3.6350          | 19.1534 | 18.2177 |
+| 0.1941        | 33.2  | 6000 | 3.7153          | 19.2575 | 17.8784 |
+| 0.1941        | 35.97 | 6500 | 3.7382          | 19.2475 | 17.9831 |
+| 0.1271        | 38.73 | 7000 | 3.7573          | 19.3045 | 17.9889 |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 39.83,
+    "eval_bleu": 19.3382,
+    "eval_gen_len": 17.8929,
+    "eval_loss": 3.7662878036499023,
+    "eval_runtime": 242.4649,
+    "eval_samples": 2894,
+    "eval_samples_per_second": 11.936,
+    "eval_steps_per_second": 1.493,
+    "predict_bleu": 27.4786,
+    "predict_gen_len": 18.3914,
+    "predict_loss": 3.0754947662353516,
+    "predict_runtime": 250.3792,
+    "predict_samples": 2895,
+    "predict_samples_per_second": 11.562,
+    "predict_steps_per_second": 1.446,
+    "train_loss": 0.5723760350545247,
+    "train_runtime": 23953.291,
+    "train_samples": 23160,
+    "train_samples_per_second": 38.675,
+    "train_steps_per_second": 0.301
+}

checkpoint-7000/config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "./reduced_model",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "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": 250004,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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": 1024,
+  "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,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 250027
+}

checkpoint-7000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 250004,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 1024,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.1"
+}

checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7b12f224fccf075eddd36af2f68f94cfd170eb68ff3f155606c6e7f2dc381f
+size 4887259502

checkpoint-7000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1cb08d3a258969abcc45a8a2ba94eba91eb84f667a3e573461da49bb8d0f48
+size 2444583325

checkpoint-7000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd69a76d5722493474b57a0fcdd821ad2ba74581ec9cdb56f3c68161c1a194e5
+size 17655

checkpoint-7000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374bc3352dde9998d5c6c01595b5ab6498e57429c3470ab01b66a755961028d3
+size 17655

checkpoint-7000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b0d6d8826ef37ff748881940d730f411b3264d6f957469c5dcb85db1b2bd0d
+size 17655

checkpoint-7000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5627e7e3b36a7c5cdb68605fbe6ef70f2f75894af07efbc44b376fb89eb31cd9
+size 17655

checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c379d5e956ea2710523259c187b33fcf2c78ef55823f6c3ad6668cacb6aa4e0c
+size 627

checkpoint-7000/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

checkpoint-7000/special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "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"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-7000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c645d47f1b17b579114ff283e7a1023a596dbd37a6c8b189c3c9870afdbb00c0
+size 17103594

checkpoint-7000/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBartTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-7000/trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 38.72884283246977,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.53,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 8.0967,
+      "step": 1000
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 3.619444444444445e-05,
+      "loss": 2.6161,
+      "step": 2000
+    },
+    {
+      "epoch": 11.09,
+      "eval_bleu": 13.5109,
+      "eval_gen_len": 19.1966,
+      "eval_loss": 3.176215171813965,
+      "eval_runtime": 298.8186,
+      "eval_samples_per_second": 9.685,
+      "eval_steps_per_second": 1.211,
+      "step": 2000
+    },
+    {
+      "epoch": 13.86,
+      "eval_bleu": 16.2868,
+      "eval_gen_len": 18.7985,
+      "eval_loss": 3.037487268447876,
+      "eval_runtime": 263.6174,
+      "eval_samples_per_second": 10.978,
+      "eval_steps_per_second": 1.373,
+      "step": 2500
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 2.9270833333333338e-05,
+      "loss": 1.4467,
+      "step": 3000
+    },
+    {
+      "epoch": 16.62,
+      "eval_bleu": 17.6991,
+      "eval_gen_len": 18.1949,
+      "eval_loss": 3.132826328277588,
+      "eval_runtime": 253.8432,
+      "eval_samples_per_second": 11.401,
+      "eval_steps_per_second": 1.426,
+      "step": 3000
+    },
+    {
+      "epoch": 19.39,
+      "eval_bleu": 17.9052,
+      "eval_gen_len": 18.3117,
+      "eval_loss": 3.2690258026123047,
+      "eval_runtime": 250.4816,
+      "eval_samples_per_second": 11.554,
+      "eval_steps_per_second": 1.445,
+      "step": 3500
+    },
+    {
+      "epoch": 22.15,
+      "learning_rate": 2.232638888888889e-05,
+      "loss": 0.6809,
+      "step": 4000
+    },
+    {
+      "epoch": 22.15,
+      "eval_bleu": 18.4075,
+      "eval_gen_len": 18.2149,
+      "eval_loss": 3.3850443363189697,
+      "eval_runtime": 248.7531,
+      "eval_samples_per_second": 11.634,
+      "eval_steps_per_second": 1.455,
+      "step": 4000
+    },
+    {
+      "epoch": 24.91,
+      "eval_bleu": 19.0339,
+      "eval_gen_len": 18.009,
+      "eval_loss": 3.446467876434326,
+      "eval_runtime": 246.4301,
+      "eval_samples_per_second": 11.744,
+      "eval_steps_per_second": 1.469,
+      "step": 4500
+    },
+    {
+      "epoch": 27.68,
+      "learning_rate": 1.5381944444444445e-05,
+      "loss": 0.3422,
+      "step": 5000
+    },
+    {
+      "epoch": 27.68,
+      "eval_bleu": 18.7281,
+      "eval_gen_len": 17.5902,
+      "eval_loss": 3.5680091381073,
+      "eval_runtime": 242.436,
+      "eval_samples_per_second": 11.937,
+      "eval_steps_per_second": 1.493,
+      "step": 5000
+    },
+    {
+      "epoch": 30.44,
+      "eval_bleu": 19.1534,
+      "eval_gen_len": 18.2177,
+      "eval_loss": 3.634960651397705,
+      "eval_runtime": 247.9202,
+      "eval_samples_per_second": 11.673,
+      "eval_steps_per_second": 1.46,
+      "step": 5500
+    },
+    {
+      "epoch": 33.2,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.1941,
+      "step": 6000
+    },
+    {
+      "epoch": 33.2,
+      "eval_bleu": 19.2575,
+      "eval_gen_len": 17.8784,
+      "eval_loss": 3.7152717113494873,
+      "eval_runtime": 241.6987,
+      "eval_samples_per_second": 11.974,
+      "eval_steps_per_second": 1.498,
+      "step": 6000
+    },
+    {
+      "epoch": 35.97,
+      "eval_bleu": 19.2475,
+      "eval_gen_len": 17.9831,
+      "eval_loss": 3.738178253173828,
+      "eval_runtime": 245.2172,
+      "eval_samples_per_second": 11.802,
+      "eval_steps_per_second": 1.476,
+      "step": 6500
+    },
+    {
+      "epoch": 38.73,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1271,
+      "step": 7000
+    },
+    {
+      "epoch": 38.73,
+      "eval_bleu": 19.3045,
+      "eval_gen_len": 17.9889,
+      "eval_loss": 3.757262706756592,
+      "eval_runtime": 245.3062,
+      "eval_samples_per_second": 11.798,
+      "eval_steps_per_second": 1.476,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 7200,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 1.941748272070656e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8cd9179b4ffcf2f9bbae7daf2139334286c941918b41091b10dbba57133407
+size 4219

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "./reduced_model",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "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": 250004,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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": 1024,
+  "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,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 250027
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 39.83,
+    "eval_bleu": 19.3382,
+    "eval_gen_len": 17.8929,
+    "eval_loss": 3.7662878036499023,
+    "eval_runtime": 242.4649,
+    "eval_samples": 2894,
+    "eval_samples_per_second": 11.936,
+    "eval_steps_per_second": 1.493
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 250004,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 1024,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.1"
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 27.4786,
+    "predict_gen_len": 18.3914,
+    "predict_loss": 3.0754947662353516,
+    "predict_runtime": 250.3792,
+    "predict_samples": 2895,
+    "predict_samples_per_second": 11.562,
+    "predict_steps_per_second": 1.446
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad538795d1f4dc04183c7059cddda9939185d06f284173aa715ccf58a040d74
+size 2444583325

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "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"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c645d47f1b17b579114ff283e7a1023a596dbd37a6c8b189c3c9870afdbb00c0
+size 17103594

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBartTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.83,
+    "train_loss": 0.5723760350545247,
+    "train_runtime": 23953.291,
+    "train_samples": 23160,
+    "train_samples_per_second": 38.675,
+    "train_steps_per_second": 0.301
+}

trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 39.83419689119171,
+  "eval_steps": 500,
+  "global_step": 7200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.53,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 8.0967,
+      "step": 1000
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 3.619444444444445e-05,
+      "loss": 2.6161,
+      "step": 2000
+    },
+    {
+      "epoch": 11.09,
+      "eval_bleu": 13.5109,
+      "eval_gen_len": 19.1966,
+      "eval_loss": 3.176215171813965,
+      "eval_runtime": 298.8186,
+      "eval_samples_per_second": 9.685,
+      "eval_steps_per_second": 1.211,
+      "step": 2000
+    },
+    {
+      "epoch": 13.86,
+      "eval_bleu": 16.2868,
+      "eval_gen_len": 18.7985,
+      "eval_loss": 3.037487268447876,
+      "eval_runtime": 263.6174,
+      "eval_samples_per_second": 10.978,
+      "eval_steps_per_second": 1.373,
+      "step": 2500
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 2.9270833333333338e-05,
+      "loss": 1.4467,
+      "step": 3000
+    },
+    {
+      "epoch": 16.62,
+      "eval_bleu": 17.6991,
+      "eval_gen_len": 18.1949,
+      "eval_loss": 3.132826328277588,
+      "eval_runtime": 253.8432,
+      "eval_samples_per_second": 11.401,
+      "eval_steps_per_second": 1.426,
+      "step": 3000
+    },
+    {
+      "epoch": 19.39,
+      "eval_bleu": 17.9052,
+      "eval_gen_len": 18.3117,
+      "eval_loss": 3.2690258026123047,
+      "eval_runtime": 250.4816,
+      "eval_samples_per_second": 11.554,
+      "eval_steps_per_second": 1.445,
+      "step": 3500
+    },
+    {
+      "epoch": 22.15,
+      "learning_rate": 2.232638888888889e-05,
+      "loss": 0.6809,
+      "step": 4000
+    },
+    {
+      "epoch": 22.15,
+      "eval_bleu": 18.4075,
+      "eval_gen_len": 18.2149,
+      "eval_loss": 3.3850443363189697,
+      "eval_runtime": 248.7531,
+      "eval_samples_per_second": 11.634,
+      "eval_steps_per_second": 1.455,
+      "step": 4000
+    },
+    {
+      "epoch": 24.91,
+      "eval_bleu": 19.0339,
+      "eval_gen_len": 18.009,
+      "eval_loss": 3.446467876434326,
+      "eval_runtime": 246.4301,
+      "eval_samples_per_second": 11.744,
+      "eval_steps_per_second": 1.469,
+      "step": 4500
+    },
+    {
+      "epoch": 27.68,
+      "learning_rate": 1.5381944444444445e-05,
+      "loss": 0.3422,
+      "step": 5000
+    },
+    {
+      "epoch": 27.68,
+      "eval_bleu": 18.7281,
+      "eval_gen_len": 17.5902,
+      "eval_loss": 3.5680091381073,
+      "eval_runtime": 242.436,
+      "eval_samples_per_second": 11.937,
+      "eval_steps_per_second": 1.493,
+      "step": 5000
+    },
+    {
+      "epoch": 30.44,
+      "eval_bleu": 19.1534,
+      "eval_gen_len": 18.2177,
+      "eval_loss": 3.634960651397705,
+      "eval_runtime": 247.9202,
+      "eval_samples_per_second": 11.673,
+      "eval_steps_per_second": 1.46,
+      "step": 5500
+    },
+    {
+      "epoch": 33.2,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.1941,
+      "step": 6000
+    },
+    {
+      "epoch": 33.2,
+      "eval_bleu": 19.2575,
+      "eval_gen_len": 17.8784,
+      "eval_loss": 3.7152717113494873,
+      "eval_runtime": 241.6987,
+      "eval_samples_per_second": 11.974,
+      "eval_steps_per_second": 1.498,
+      "step": 6000
+    },
+    {
+      "epoch": 35.97,
+      "eval_bleu": 19.2475,
+      "eval_gen_len": 17.9831,
+      "eval_loss": 3.738178253173828,
+      "eval_runtime": 245.2172,
+      "eval_samples_per_second": 11.802,
+      "eval_steps_per_second": 1.476,
+      "step": 6500
+    },
+    {
+      "epoch": 38.73,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1271,
+      "step": 7000
+    },
+    {
+      "epoch": 38.73,
+      "eval_bleu": 19.3045,
+      "eval_gen_len": 17.9889,
+      "eval_loss": 3.757262706756592,
+      "eval_runtime": 245.3062,
+      "eval_samples_per_second": 11.798,
+      "eval_steps_per_second": 1.476,
+      "step": 7000
+    },
+    {
+      "epoch": 39.83,
+      "step": 7200,
+      "total_flos": 1.9972267941298176e+18,
+      "train_loss": 0.5723760350545247,
+      "train_runtime": 23953.291,
+      "train_samples_per_second": 38.675,
+      "train_steps_per_second": 0.301
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 7200,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 1.9972267941298176e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8cd9179b4ffcf2f9bbae7daf2139334286c941918b41091b10dbba57133407
+size 4219