| { | |
| "best_metric": 3.7421457767486572, | |
| "best_model_checkpoint": "en-to-lg/checkpoint-16", | |
| "epoch": 10.0, | |
| "eval_steps": 50, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.8596, | |
| "eval_gen_len": 20.4303, | |
| "eval_loss": 3.7421457767486572, | |
| "eval_runtime": 486.1664, | |
| "eval_samples_per_second": 25.006, | |
| "eval_steps_per_second": 0.782, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.855, | |
| "eval_gen_len": 20.5137, | |
| "eval_loss": 3.800355911254883, | |
| "eval_runtime": 489.6809, | |
| "eval_samples_per_second": 24.826, | |
| "eval_steps_per_second": 0.776, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.8413, | |
| "eval_gen_len": 20.4, | |
| "eval_loss": 3.806553602218628, | |
| "eval_runtime": 491.5388, | |
| "eval_samples_per_second": 24.733, | |
| "eval_steps_per_second": 0.773, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.8455, | |
| "eval_gen_len": 20.3859, | |
| "eval_loss": 3.864736557006836, | |
| "eval_runtime": 490.916, | |
| "eval_samples_per_second": 24.764, | |
| "eval_steps_per_second": 0.774, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.8527, | |
| "eval_gen_len": 20.3211, | |
| "eval_loss": 3.916616916656494, | |
| "eval_runtime": 490.8429, | |
| "eval_samples_per_second": 24.768, | |
| "eval_steps_per_second": 0.774, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.8539, | |
| "eval_gen_len": 20.3088, | |
| "eval_loss": 3.9686362743377686, | |
| "eval_runtime": 492.3847, | |
| "eval_samples_per_second": 24.69, | |
| "eval_steps_per_second": 0.772, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.8492, | |
| "eval_gen_len": 20.3507, | |
| "eval_loss": 3.9955193996429443, | |
| "eval_runtime": 494.2016, | |
| "eval_samples_per_second": 24.599, | |
| "eval_steps_per_second": 0.769, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.8387, | |
| "eval_gen_len": 20.3404, | |
| "eval_loss": 4.008735179901123, | |
| "eval_runtime": 491.9673, | |
| "eval_samples_per_second": 24.711, | |
| "eval_steps_per_second": 0.772, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.8345, | |
| "eval_gen_len": 20.3244, | |
| "eval_loss": 4.021594047546387, | |
| "eval_runtime": 491.5119, | |
| "eval_samples_per_second": 24.734, | |
| "eval_steps_per_second": 0.773, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.8431, | |
| "eval_gen_len": 20.3462, | |
| "eval_loss": 4.02959680557251, | |
| "eval_runtime": 491.997, | |
| "eval_samples_per_second": 24.71, | |
| "eval_steps_per_second": 0.772, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 53351789101056.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |