| { | |
| "best_metric": 2.8250861167907715, | |
| "best_model_checkpoint": "en-to-lg-ufal-al/checkpoint-160", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "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": 12.3779, | |
| "eval_gen_len": 42.6083, | |
| "eval_loss": 2.9468307495117188, | |
| "eval_runtime": 1501.8811, | |
| "eval_samples_per_second": 10.334, | |
| "eval_steps_per_second": 0.323, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 12.5162, | |
| "eval_gen_len": 42.7061, | |
| "eval_loss": 2.9221065044403076, | |
| "eval_runtime": 1525.1235, | |
| "eval_samples_per_second": 10.176, | |
| "eval_steps_per_second": 0.318, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 12.6486, | |
| "eval_gen_len": 42.7809, | |
| "eval_loss": 2.8996763229370117, | |
| "eval_runtime": 1520.5333, | |
| "eval_samples_per_second": 10.207, | |
| "eval_steps_per_second": 0.319, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 1.846739411354065, | |
| "learning_rate": 1.3875e-05, | |
| "loss": 3.2685, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 12.7887, | |
| "eval_gen_len": 42.9278, | |
| "eval_loss": 2.8806185722351074, | |
| "eval_runtime": 1541.7574, | |
| "eval_samples_per_second": 10.066, | |
| "eval_steps_per_second": 0.315, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 12.8971, | |
| "eval_gen_len": 42.9779, | |
| "eval_loss": 2.863759994506836, | |
| "eval_runtime": 1538.3478, | |
| "eval_samples_per_second": 10.089, | |
| "eval_steps_per_second": 0.315, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 12.9175, | |
| "eval_gen_len": 42.9273, | |
| "eval_loss": 2.8501696586608887, | |
| "eval_runtime": 1540.1728, | |
| "eval_samples_per_second": 10.077, | |
| "eval_steps_per_second": 0.315, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 0.854383111000061, | |
| "learning_rate": 7.625e-06, | |
| "loss": 3.1513, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 12.9938, | |
| "eval_gen_len": 43.0523, | |
| "eval_loss": 2.839545249938965, | |
| "eval_runtime": 1546.6529, | |
| "eval_samples_per_second": 10.035, | |
| "eval_steps_per_second": 0.314, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 13.0635, | |
| "eval_gen_len": 43.0526, | |
| "eval_loss": 2.831665277481079, | |
| "eval_runtime": 1543.1426, | |
| "eval_samples_per_second": 10.057, | |
| "eval_steps_per_second": 0.314, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 13.1002, | |
| "eval_gen_len": 43.099, | |
| "eval_loss": 2.8269288539886475, | |
| "eval_runtime": 1549.5221, | |
| "eval_samples_per_second": 10.016, | |
| "eval_steps_per_second": 0.313, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 9.375, | |
| "grad_norm": 0.8836955428123474, | |
| "learning_rate": 1.3750000000000002e-06, | |
| "loss": 3.1409, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 13.0773, | |
| "eval_gen_len": 43.1512, | |
| "eval_loss": 2.8250861167907715, | |
| "eval_runtime": 1562.623, | |
| "eval_samples_per_second": 9.932, | |
| "eval_steps_per_second": 0.31, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 327971658792960.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |