| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14316392269148176, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007158196134574087, | |
| "eval_loss": 0.7471321821212769, | |
| "eval_runtime": 35.0025, | |
| "eval_samples_per_second": 16.827, | |
| "eval_steps_per_second": 8.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0071581961345740875, | |
| "grad_norm": 0.3041437268257141, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014316392269148175, | |
| "grad_norm": 0.21548660099506378, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4944, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021474588403722263, | |
| "grad_norm": 0.302517831325531, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5196, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02863278453829635, | |
| "grad_norm": 0.2508035898208618, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4403, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03579098067287044, | |
| "grad_norm": 0.20165234804153442, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4687, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03579098067287044, | |
| "eval_loss": 0.4433478116989136, | |
| "eval_runtime": 33.6585, | |
| "eval_samples_per_second": 17.499, | |
| "eval_steps_per_second": 8.765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04294917680744453, | |
| "grad_norm": 0.19860732555389404, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4482, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05010737294201861, | |
| "grad_norm": 0.2684027850627899, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4554, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0572655690765927, | |
| "grad_norm": 0.2177385836839676, | |
| "learning_rate": 0.0002, | |
| "loss": 0.432, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06442376521116679, | |
| "grad_norm": 0.2141849547624588, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4056, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07158196134574088, | |
| "grad_norm": 0.22702062129974365, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4283, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07158196134574088, | |
| "eval_loss": 0.4245603382587433, | |
| "eval_runtime": 33.7143, | |
| "eval_samples_per_second": 17.47, | |
| "eval_steps_per_second": 8.75, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07874015748031496, | |
| "grad_norm": 0.23127739131450653, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4524, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08589835361488905, | |
| "grad_norm": 0.231285959482193, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4068, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09305654974946313, | |
| "grad_norm": 0.22599922120571136, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4394, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.10021474588403723, | |
| "grad_norm": 0.22092868387699127, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4272, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1073729420186113, | |
| "grad_norm": 0.2594935894012451, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4254, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1073729420186113, | |
| "eval_loss": 0.4146997332572937, | |
| "eval_runtime": 33.7342, | |
| "eval_samples_per_second": 17.46, | |
| "eval_steps_per_second": 8.745, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1145311381531854, | |
| "grad_norm": 0.25014057755470276, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4102, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12168933428775948, | |
| "grad_norm": 0.24548886716365814, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4263, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12884753042233357, | |
| "grad_norm": 0.237931028008461, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4323, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13600572655690765, | |
| "grad_norm": 0.21747586131095886, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4161, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.14316392269148176, | |
| "grad_norm": 0.24018722772598267, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3944, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14316392269148176, | |
| "eval_loss": 0.40698060393333435, | |
| "eval_runtime": 33.7394, | |
| "eval_samples_per_second": 17.457, | |
| "eval_steps_per_second": 8.743, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.5912916934656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |