| { | |
| "best_metric": 11.742330551147461, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.11661807580174927, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011661807580174927, | |
| "eval_loss": 11.762678146362305, | |
| "eval_runtime": 1.6672, | |
| "eval_samples_per_second": 216.536, | |
| "eval_steps_per_second": 54.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011661807580174927, | |
| "grad_norm": 0.1031990498304367, | |
| "learning_rate": 4.0600000000000004e-05, | |
| "loss": 11.7629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023323615160349854, | |
| "grad_norm": 0.12429989129304886, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 11.7609, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03498542274052478, | |
| "grad_norm": 0.188057541847229, | |
| "learning_rate": 0.00012179999999999999, | |
| "loss": 11.7631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04664723032069971, | |
| "grad_norm": 0.19203342497348785, | |
| "learning_rate": 0.00016240000000000002, | |
| "loss": 11.7586, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 0.3170674443244934, | |
| "learning_rate": 0.000203, | |
| "loss": 11.7389, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "eval_loss": 11.746705055236816, | |
| "eval_runtime": 1.6333, | |
| "eval_samples_per_second": 221.02, | |
| "eval_steps_per_second": 55.714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06997084548104957, | |
| "grad_norm": 0.2140980362892151, | |
| "learning_rate": 0.00020275275110137215, | |
| "loss": 11.7573, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.1588020920753479, | |
| "learning_rate": 0.00020201220897726938, | |
| "loss": 11.7488, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09329446064139942, | |
| "grad_norm": 0.20971915125846863, | |
| "learning_rate": 0.00020078198147448128, | |
| "loss": 11.7447, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10495626822157435, | |
| "grad_norm": 0.19178971648216248, | |
| "learning_rate": 0.00019906806213773937, | |
| "loss": 11.7421, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "grad_norm": 0.22939780354499817, | |
| "learning_rate": 0.0001968788010097697, | |
| "loss": 11.7342, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "eval_loss": 11.742330551147461, | |
| "eval_runtime": 1.6574, | |
| "eval_samples_per_second": 217.817, | |
| "eval_steps_per_second": 54.907, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "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": 5179323187200.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |