Upload with huggingface_hub

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "outputs",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],

eval_results.txt

@@ -0,0 +1 @@
+eval_loss = 5.7833870226686654

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": false, "adafactor_scale_parameter": false, "adafactor_warmup_init": false, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 0.001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "google/mt5-small", "model_type": "mt5", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 2, "optimizer": "Adafactor", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 2, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": -1, "scheduler": "constant_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": "MT5 English-Chinese Translation", "warmup_ratio": 0.06, "warmup_steps": 6939, "weight_decay": 0.0, "model_class": "T5Model", "dataset_class": null, "do_sample": false, "early_stopping": true, "evaluate_generated_text": false, "length_penalty": 2.0, "max_length": 20, "max_steps": -1, "num_beams": 2, "num_return_sequences": 1, "preprocess_inputs": false, "repetition_penalty": 1.0, "special_tokens_list": [], "top_k": null, "top_p": null, "use_multiprocessed_decoding": true}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a80071cd1fb6ab0c52c97c2b761bd1689bbc9e22af5c408afc169a445a6cdf
+size 2879813

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0264ac2a77fa710325879d7a4ffe352fb63c26fe5a8c45f8aa46fa9485a095
-size 1200769797
+oid sha256:17a7fb074f51603a32d196e9708df76b25f688e7eb4c08f5f71a1c4766b9b54e
+size 1200772485

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f1b5b9eb89faf5cd268037a9b88c66a4fa7c448a23d5e5a3bb208000aae76c
+size 627

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f988b5a899b6e56692a5d3af8719468f662277065159d936b93ff8845fdac3
+size 3195