| { | |
| "best_metric": 0.5146914124488831, | |
| "best_model_checkpoint": "saves/Llama2-7B/lora/train_1/checkpoint-200", | |
| "epoch": 0.4375170905113481, | |
| "eval_steps": 40, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04375170905113481, | |
| "grad_norm": 0.3878575265407562, | |
| "learning_rate": 0.00014457831325301204, | |
| "loss": 1.5222, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04375170905113481, | |
| "eval_loss": 0.5363553762435913, | |
| "eval_runtime": 236.0458, | |
| "eval_samples_per_second": 19.962, | |
| "eval_steps_per_second": 0.627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "grad_norm": 0.41417649388313293, | |
| "learning_rate": 0.0002891566265060241, | |
| "loss": 0.3981, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "eval_loss": 0.554685652256012, | |
| "eval_runtime": 236.0602, | |
| "eval_samples_per_second": 19.961, | |
| "eval_steps_per_second": 0.627, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "grad_norm": 0.3590388894081116, | |
| "learning_rate": 0.00029985669589905196, | |
| "loss": 0.3297, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "eval_loss": 0.5275963544845581, | |
| "eval_runtime": 236.3869, | |
| "eval_samples_per_second": 19.933, | |
| "eval_steps_per_second": 0.626, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "grad_norm": 0.21372735500335693, | |
| "learning_rate": 0.0002993796936474492, | |
| "loss": 0.3131, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "eval_loss": 0.5312083959579468, | |
| "eval_runtime": 236.0472, | |
| "eval_samples_per_second": 19.962, | |
| "eval_steps_per_second": 0.627, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "grad_norm": 0.18935319781303406, | |
| "learning_rate": 0.00029856911617379416, | |
| "loss": 0.3049, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "eval_loss": 0.5146914124488831, | |
| "eval_runtime": 236.117, | |
| "eval_samples_per_second": 19.956, | |
| "eval_steps_per_second": 0.627, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "grad_norm": 0.18968264758586884, | |
| "learning_rate": 0.00029742677355383513, | |
| "loss": 0.2906, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "eval_loss": 0.5208326578140259, | |
| "eval_runtime": 236.1292, | |
| "eval_samples_per_second": 19.955, | |
| "eval_steps_per_second": 0.627, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "grad_norm": 0.19735340774059296, | |
| "learning_rate": 0.0002959552167179149, | |
| "loss": 0.2862, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "eval_loss": 0.5312994122505188, | |
| "eval_runtime": 236.1867, | |
| "eval_samples_per_second": 19.95, | |
| "eval_steps_per_second": 0.627, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "grad_norm": 0.19487717747688293, | |
| "learning_rate": 0.00029415773175456614, | |
| "loss": 0.2799, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "eval_loss": 0.5453993082046509, | |
| "eval_runtime": 236.1259, | |
| "eval_samples_per_second": 19.955, | |
| "eval_steps_per_second": 0.627, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3937653814602133, | |
| "grad_norm": 0.22721989452838898, | |
| "learning_rate": 0.0002920383325724476, | |
| "loss": 0.2748, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3937653814602133, | |
| "eval_loss": 0.5482673645019531, | |
| "eval_runtime": 236.0858, | |
| "eval_samples_per_second": 19.959, | |
| "eval_steps_per_second": 0.627, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "grad_norm": 0.22632545232772827, | |
| "learning_rate": 0.0002896017519370078, | |
| "loss": 0.2613, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "eval_loss": 0.5433260202407837, | |
| "eval_runtime": 236.1474, | |
| "eval_samples_per_second": 19.954, | |
| "eval_steps_per_second": 0.627, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "step": 400, | |
| "total_flos": 7.549890655703532e+17, | |
| "train_loss": 0.42607839822769167, | |
| "train_runtime": 21547.2809, | |
| "train_samples_per_second": 32.585, | |
| "train_steps_per_second": 0.127 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 2742, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 40, | |
| "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": 7.549890655703532e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |