| { | |
| "best_metric": 1.9817668199539185, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.042811273635390654, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014270424545130217, | |
| "eval_loss": 2.0832407474517822, | |
| "eval_runtime": 136.0325, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 1.088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004281127363539065, | |
| "grad_norm": 0.6863715648651123, | |
| "learning_rate": 0.00012, | |
| "loss": 8.1141, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007135212272565109, | |
| "eval_loss": 2.0657401084899902, | |
| "eval_runtime": 138.1923, | |
| "eval_samples_per_second": 4.269, | |
| "eval_steps_per_second": 1.071, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00856225472707813, | |
| "grad_norm": 0.7139294743537903, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 7.9067, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012843382090617196, | |
| "grad_norm": 0.9212773442268372, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.0932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014270424545130217, | |
| "eval_loss": 2.019080400466919, | |
| "eval_runtime": 138.1329, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 1.071, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01712450945415626, | |
| "grad_norm": 0.788345217704773, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 8.3807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021405636817695327, | |
| "grad_norm": 0.5324597954750061, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.1896, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021405636817695327, | |
| "eval_loss": 1.9932217597961426, | |
| "eval_runtime": 138.9247, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 1.065, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025686764181234393, | |
| "grad_norm": 0.4385243058204651, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 8.184, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028540849090260435, | |
| "eval_loss": 1.9875426292419434, | |
| "eval_runtime": 139.0154, | |
| "eval_samples_per_second": 4.244, | |
| "eval_steps_per_second": 1.065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029967891544773455, | |
| "grad_norm": 0.47669491171836853, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 8.3955, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03424901890831252, | |
| "grad_norm": 0.5693178176879883, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 8.3168, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03567606136282554, | |
| "eval_loss": 1.9830142259597778, | |
| "eval_runtime": 138.1006, | |
| "eval_samples_per_second": 4.272, | |
| "eval_steps_per_second": 1.072, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.038530146271851584, | |
| "grad_norm": 0.5196043252944946, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 8.2678, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.042811273635390654, | |
| "grad_norm": 0.6024002432823181, | |
| "learning_rate": 0.0, | |
| "loss": 7.9644, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042811273635390654, | |
| "eval_loss": 1.9817668199539185, | |
| "eval_runtime": 138.1174, | |
| "eval_samples_per_second": 4.272, | |
| "eval_steps_per_second": 1.072, | |
| "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": 3.5450456956207104e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |