| { | |
| "best_metric": 0.8112931251525879, | |
| "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-110", | |
| "epoch": 0.17500683620453925, | |
| "eval_steps": 10, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010937927262783703, | |
| "grad_norm": 1.4765043258666992, | |
| "learning_rate": 0.00029999015487222375, | |
| "loss": 1.0078, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010937927262783703, | |
| "eval_loss": 0.9145990014076233, | |
| "eval_runtime": 2007.1957, | |
| "eval_samples_per_second": 23.476, | |
| "eval_steps_per_second": 0.734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021875854525567406, | |
| "grad_norm": 0.5130007266998291, | |
| "learning_rate": 0.00029996062078124905, | |
| "loss": 0.5077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021875854525567406, | |
| "eval_loss": 0.836322009563446, | |
| "eval_runtime": 2008.0976, | |
| "eval_samples_per_second": 23.465, | |
| "eval_steps_per_second": 0.734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "grad_norm": 0.6383033394813538, | |
| "learning_rate": 0.0002999114016039678, | |
| "loss": 0.4613, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "eval_loss": 0.8337860703468323, | |
| "eval_runtime": 2007.8768, | |
| "eval_samples_per_second": 23.468, | |
| "eval_steps_per_second": 0.734, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04375170905113481, | |
| "grad_norm": 0.4186599552631378, | |
| "learning_rate": 0.00029984250380130117, | |
| "loss": 0.4794, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04375170905113481, | |
| "eval_loss": 0.8337470889091492, | |
| "eval_runtime": 2006.2999, | |
| "eval_samples_per_second": 23.486, | |
| "eval_steps_per_second": 0.734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05468963631391851, | |
| "grad_norm": 0.39893779158592224, | |
| "learning_rate": 0.0002997539364173515, | |
| "loss": 0.4624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05468963631391851, | |
| "eval_loss": 0.8181310892105103, | |
| "eval_runtime": 2006.8912, | |
| "eval_samples_per_second": 23.479, | |
| "eval_steps_per_second": 0.734, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "grad_norm": 0.3842828571796417, | |
| "learning_rate": 0.00029964571107821494, | |
| "loss": 0.4366, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "eval_loss": 0.8186683058738708, | |
| "eval_runtime": 2007.9415, | |
| "eval_samples_per_second": 23.467, | |
| "eval_steps_per_second": 0.734, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07656549083948591, | |
| "grad_norm": 0.36217156052589417, | |
| "learning_rate": 0.00029951784199045534, | |
| "loss": 0.4323, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07656549083948591, | |
| "eval_loss": 0.8172433972358704, | |
| "eval_runtime": 2006.1302, | |
| "eval_samples_per_second": 23.488, | |
| "eval_steps_per_second": 0.734, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "grad_norm": 0.3985615074634552, | |
| "learning_rate": 0.0002993703459392396, | |
| "loss": 0.433, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "eval_loss": 0.8255128860473633, | |
| "eval_runtime": 2007.4062, | |
| "eval_samples_per_second": 23.473, | |
| "eval_steps_per_second": 0.734, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09844134536505332, | |
| "grad_norm": 0.38471728563308716, | |
| "learning_rate": 0.00029920324228613376, | |
| "loss": 0.4401, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09844134536505332, | |
| "eval_loss": 0.8299794793128967, | |
| "eval_runtime": 2006.2366, | |
| "eval_samples_per_second": 23.487, | |
| "eval_steps_per_second": 0.734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10937927262783702, | |
| "grad_norm": 0.4009046256542206, | |
| "learning_rate": 0.0002990165529665622, | |
| "loss": 0.4019, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10937927262783702, | |
| "eval_loss": 0.8478946089744568, | |
| "eval_runtime": 2006.4757, | |
| "eval_samples_per_second": 23.484, | |
| "eval_steps_per_second": 0.734, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12031719989062073, | |
| "grad_norm": 0.3922439515590668, | |
| "learning_rate": 0.0002988103024869277, | |
| "loss": 0.4112, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12031719989062073, | |
| "eval_loss": 0.8112931251525879, | |
| "eval_runtime": 2005.6033, | |
| "eval_samples_per_second": 23.494, | |
| "eval_steps_per_second": 0.734, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "grad_norm": 0.37745875120162964, | |
| "learning_rate": 0.00029858451792139453, | |
| "loss": 0.4009, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "eval_loss": 0.845430314540863, | |
| "eval_runtime": 2006.7483, | |
| "eval_samples_per_second": 23.481, | |
| "eval_steps_per_second": 0.734, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14219305441618812, | |
| "grad_norm": 0.3471999764442444, | |
| "learning_rate": 0.0002983392289083346, | |
| "loss": 0.4023, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14219305441618812, | |
| "eval_loss": 0.8435468077659607, | |
| "eval_runtime": 2005.5353, | |
| "eval_samples_per_second": 23.495, | |
| "eval_steps_per_second": 0.734, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15313098167897182, | |
| "grad_norm": 0.32064810395240784, | |
| "learning_rate": 0.0002980744676464371, | |
| "loss": 0.3924, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15313098167897182, | |
| "eval_loss": 0.8307648301124573, | |
| "eval_runtime": 2005.4412, | |
| "eval_samples_per_second": 23.496, | |
| "eval_steps_per_second": 0.735, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16406890894175555, | |
| "grad_norm": 0.31663310527801514, | |
| "learning_rate": 0.0002977902688904813, | |
| "loss": 0.4079, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16406890894175555, | |
| "eval_loss": 0.8372470140457153, | |
| "eval_runtime": 2005.2559, | |
| "eval_samples_per_second": 23.498, | |
| "eval_steps_per_second": 0.735, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "grad_norm": 0.351032018661499, | |
| "learning_rate": 0.00029748666994677467, | |
| "loss": 0.3898, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "eval_loss": 0.8541739583015442, | |
| "eval_runtime": 2005.8203, | |
| "eval_samples_per_second": 23.492, | |
| "eval_steps_per_second": 0.734, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "step": 160, | |
| "total_flos": 2.8452078024759706e+17, | |
| "train_loss": 0.4666908696293831, | |
| "train_runtime": 39003.3227, | |
| "train_samples_per_second": 18.002, | |
| "train_steps_per_second": 0.07 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2742, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8452078024759706e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |