| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003463755348224675, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.621542633957431e-05, | |
| "eval_loss": 3.1601955890655518, | |
| "eval_runtime": 13080.0915, | |
| "eval_samples_per_second": 2.677, | |
| "eval_steps_per_second": 1.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028864627901872294, | |
| "grad_norm": 88.87578582763672, | |
| "learning_rate": 3e-05, | |
| "loss": 100.51, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005772925580374459, | |
| "grad_norm": 85.21216583251953, | |
| "learning_rate": 6e-05, | |
| "loss": 96.5347, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008659388370561688, | |
| "grad_norm": 77.13072967529297, | |
| "learning_rate": 9e-05, | |
| "loss": 80.7471, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008659388370561688, | |
| "eval_loss": 2.1278481483459473, | |
| "eval_runtime": 13090.1143, | |
| "eval_samples_per_second": 2.675, | |
| "eval_steps_per_second": 1.337, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011545851160748917, | |
| "grad_norm": 68.87947845458984, | |
| "learning_rate": 0.00012, | |
| "loss": 64.7623, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014432313950936146, | |
| "grad_norm": 43.136959075927734, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.3736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0017318776741123375, | |
| "grad_norm": 41.73539352416992, | |
| "learning_rate": 0.00018, | |
| "loss": 31.1364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017318776741123375, | |
| "eval_loss": 0.844988226890564, | |
| "eval_runtime": 13063.393, | |
| "eval_samples_per_second": 2.68, | |
| "eval_steps_per_second": 1.34, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020205239531310604, | |
| "grad_norm": 37.0665397644043, | |
| "learning_rate": 0.0001999229036240723, | |
| "loss": 25.9659, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0023091702321497835, | |
| "grad_norm": 32.10556411743164, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 19.8184, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002597816511168506, | |
| "grad_norm": 39.13405990600586, | |
| "learning_rate": 0.00019624552364536473, | |
| "loss": 15.5343, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002597816511168506, | |
| "eval_loss": 0.4686388671398163, | |
| "eval_runtime": 11313.8601, | |
| "eval_samples_per_second": 3.094, | |
| "eval_steps_per_second": 1.547, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0028864627901872292, | |
| "grad_norm": 29.395793914794922, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 14.8443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003175109069205952, | |
| "grad_norm": 27.154170989990234, | |
| "learning_rate": 0.00018724960070727972, | |
| "loss": 13.3753, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003463755348224675, | |
| "grad_norm": 23.787752151489258, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.3941, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003463755348224675, | |
| "eval_loss": 0.3380902111530304, | |
| "eval_runtime": 10045.2845, | |
| "eval_samples_per_second": 3.485, | |
| "eval_steps_per_second": 1.743, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8932962735580774e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |