| { | |
| "best_metric": 0.9343328475952148, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05884083553986467, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011768167107972932, | |
| "eval_loss": 1.4336028099060059, | |
| "eval_runtime": 63.7044, | |
| "eval_samples_per_second": 22.479, | |
| "eval_steps_per_second": 5.62, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011768167107972934, | |
| "grad_norm": 1.2304390668869019, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023536334215945868, | |
| "grad_norm": 0.6472563743591309, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 6.0483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "grad_norm": 0.7562745213508606, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 3.9027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047072668431891736, | |
| "grad_norm": 0.8033158779144287, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 1.8585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "grad_norm": 1.7948169708251953, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 1.7989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "eval_loss": 0.9343328475952148, | |
| "eval_runtime": 64.9646, | |
| "eval_samples_per_second": 22.043, | |
| "eval_steps_per_second": 5.511, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 3.361817002770432e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |