| { | |
| "best_metric": 2.11523699760437, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.0023091577347162623, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.697192449054207e-05, | |
| "eval_loss": 3.152271032333374, | |
| "eval_runtime": 145.4284, | |
| "eval_samples_per_second": 37.62, | |
| "eval_steps_per_second": 18.813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023091577347162623, | |
| "grad_norm": 4.9489617347717285, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9612, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003848596224527104, | |
| "eval_loss": 2.7971303462982178, | |
| "eval_runtime": 144.5756, | |
| "eval_samples_per_second": 37.842, | |
| "eval_steps_per_second": 18.924, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00046183154694325247, | |
| "grad_norm": 5.416839599609375, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 3.1989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006927473204148787, | |
| "grad_norm": 6.466828346252441, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.5814, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007697192449054208, | |
| "eval_loss": 2.392669200897217, | |
| "eval_runtime": 146.5681, | |
| "eval_samples_per_second": 37.327, | |
| "eval_steps_per_second": 18.667, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009236630938865049, | |
| "grad_norm": 6.966540336608887, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.3569, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011545788673581311, | |
| "grad_norm": 5.7430901527404785, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.4699, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011545788673581311, | |
| "eval_loss": 2.2286555767059326, | |
| "eval_runtime": 144.9312, | |
| "eval_samples_per_second": 37.749, | |
| "eval_steps_per_second": 18.878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013854946408297574, | |
| "grad_norm": 5.223223686218262, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.9696, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015394384898108416, | |
| "eval_loss": 2.1526098251342773, | |
| "eval_runtime": 145.259, | |
| "eval_samples_per_second": 37.664, | |
| "eval_steps_per_second": 18.835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016164104143013835, | |
| "grad_norm": 5.161473751068115, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 2.1286, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018473261877730099, | |
| "grad_norm": 4.5876030921936035, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 2.2251, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019242981122635518, | |
| "eval_loss": 2.120673656463623, | |
| "eval_runtime": 148.0665, | |
| "eval_samples_per_second": 36.95, | |
| "eval_steps_per_second": 18.478, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002078241961244636, | |
| "grad_norm": 3.2490625381469727, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 2.0832, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0023091577347162623, | |
| "grad_norm": 5.288578510284424, | |
| "learning_rate": 0.0, | |
| "loss": 1.8478, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023091577347162623, | |
| "eval_loss": 2.11523699760437, | |
| "eval_runtime": 145.3354, | |
| "eval_samples_per_second": 37.644, | |
| "eval_steps_per_second": 18.825, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 540715725619200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |