| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20408163265306123, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004081632653061225, | |
| "eval_loss": 7.391392230987549, | |
| "eval_runtime": 11.0051, | |
| "eval_samples_per_second": 9.45, | |
| "eval_steps_per_second": 4.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 11.124676704406738, | |
| "learning_rate": 5e-05, | |
| "loss": 7.4664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 20.21062660217285, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7943, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "eval_loss": 6.0373616218566895, | |
| "eval_runtime": 9.9482, | |
| "eval_samples_per_second": 10.454, | |
| "eval_steps_per_second": 5.227, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 12.157793998718262, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.3938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 30.501094818115234, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7522, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "eval_loss": 3.088772773742676, | |
| "eval_runtime": 9.1972, | |
| "eval_samples_per_second": 11.308, | |
| "eval_steps_per_second": 5.654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 14.440489768981934, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 7.746071815490723, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3264, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "eval_loss": 2.128019094467163, | |
| "eval_runtime": 9.9303, | |
| "eval_samples_per_second": 10.473, | |
| "eval_steps_per_second": 5.236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 13.87149429321289, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0025, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 9.869282722473145, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9886, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "eval_loss": 2.0035860538482666, | |
| "eval_runtime": 9.9467, | |
| "eval_samples_per_second": 10.456, | |
| "eval_steps_per_second": 5.228, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 23.738134384155273, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0754, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 9.707077980041504, | |
| "learning_rate": 0.0, | |
| "loss": 1.843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "eval_loss": 1.9997984170913696, | |
| "eval_runtime": 9.923, | |
| "eval_samples_per_second": 10.481, | |
| "eval_steps_per_second": 5.24, | |
| "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": 1285354690707456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |