| { | |
| "best_metric": 0.4819493889808655, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 0.023954725568675204, | |
| "eval_steps": 50, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.984908522891735e-05, | |
| "eval_loss": 2.0086100101470947, | |
| "eval_runtime": 702.0595, | |
| "eval_samples_per_second": 15.023, | |
| "eval_steps_per_second": 7.512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003193963409156694, | |
| "grad_norm": 60.47791290283203, | |
| "learning_rate": 5e-05, | |
| "loss": 8.1173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003992454261445867, | |
| "eval_loss": 0.7402405142784119, | |
| "eval_runtime": 703.0805, | |
| "eval_samples_per_second": 15.001, | |
| "eval_steps_per_second": 7.501, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006387926818313388, | |
| "grad_norm": 37.602317810058594, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2458, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007984908522891734, | |
| "eval_loss": 0.645350456237793, | |
| "eval_runtime": 703.8766, | |
| "eval_samples_per_second": 14.984, | |
| "eval_steps_per_second": 7.493, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.009581890227470082, | |
| "grad_norm": 35.46270751953125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.8448, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.011977362784337602, | |
| "eval_loss": 0.6013292670249939, | |
| "eval_runtime": 703.7908, | |
| "eval_samples_per_second": 14.986, | |
| "eval_steps_per_second": 7.494, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012775853636626776, | |
| "grad_norm": 19.138328552246094, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.5843, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.015969817045783468, | |
| "grad_norm": 44.18806838989258, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.4517, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.015969817045783468, | |
| "eval_loss": 0.5775735974311829, | |
| "eval_runtime": 704.1932, | |
| "eval_samples_per_second": 14.977, | |
| "eval_steps_per_second": 7.489, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.019163780454940164, | |
| "grad_norm": 28.21241569519043, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1189, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.019962271307229336, | |
| "eval_loss": 0.520143449306488, | |
| "eval_runtime": 704.7521, | |
| "eval_samples_per_second": 14.966, | |
| "eval_steps_per_second": 7.483, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.022357743864096856, | |
| "grad_norm": 24.794347763061523, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9716, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.023954725568675204, | |
| "eval_loss": 0.4819493889808655, | |
| "eval_runtime": 704.0197, | |
| "eval_samples_per_second": 14.981, | |
| "eval_steps_per_second": 7.491, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0613210338453094e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |