| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009751293265269306, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9502586530538612e-05, | |
| "eval_loss": 3.3730149269104004, | |
| "eval_runtime": 1353.409, | |
| "eval_samples_per_second": 15.952, | |
| "eval_steps_per_second": 7.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.751293265269307e-05, | |
| "grad_norm": 22.736345291137695, | |
| "learning_rate": 5e-05, | |
| "loss": 14.6789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019502586530538614, | |
| "grad_norm": 28.169536590576172, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019502586530538614, | |
| "eval_loss": 2.65612530708313, | |
| "eval_runtime": 1359.0253, | |
| "eval_samples_per_second": 15.886, | |
| "eval_steps_per_second": 7.943, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002925387979580792, | |
| "grad_norm": 18.491188049316406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.0615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003900517306107723, | |
| "grad_norm": 20.197280883789062, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.5525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003900517306107723, | |
| "eval_loss": 2.060377597808838, | |
| "eval_runtime": 1351.5612, | |
| "eval_samples_per_second": 15.974, | |
| "eval_steps_per_second": 7.987, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004875646632634653, | |
| "grad_norm": 21.58411979675293, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.0305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005850775959161584, | |
| "grad_norm": 22.63473892211914, | |
| "learning_rate": 5e-05, | |
| "loss": 7.9584, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005850775959161584, | |
| "eval_loss": 1.8975735902786255, | |
| "eval_runtime": 1354.7033, | |
| "eval_samples_per_second": 15.937, | |
| "eval_steps_per_second": 7.969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006825905285688514, | |
| "grad_norm": 19.12643814086914, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.1474, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007801034612215446, | |
| "grad_norm": 21.884143829345703, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.7595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007801034612215446, | |
| "eval_loss": 1.8448659181594849, | |
| "eval_runtime": 1361.7391, | |
| "eval_samples_per_second": 15.855, | |
| "eval_steps_per_second": 7.927, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008776163938742376, | |
| "grad_norm": 20.621267318725586, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.2005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0009751293265269306, | |
| "grad_norm": 20.958507537841797, | |
| "learning_rate": 0.0, | |
| "loss": 7.2268, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0009751293265269306, | |
| "eval_loss": 1.8370400667190552, | |
| "eval_runtime": 1357.8052, | |
| "eval_samples_per_second": 15.901, | |
| "eval_steps_per_second": 7.95, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |