| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11695906432748537, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003898635477582846, | |
| "eval_loss": 1.299100399017334, | |
| "eval_runtime": 14.2397, | |
| "eval_samples_per_second": 7.584, | |
| "eval_steps_per_second": 3.792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 0.34185564517974854, | |
| "learning_rate": 6e-05, | |
| "loss": 1.226, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "eval_loss": 1.262163758277893, | |
| "eval_runtime": 14.4423, | |
| "eval_samples_per_second": 7.478, | |
| "eval_steps_per_second": 3.739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.40559282898902893, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2212, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.4018673598766327, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1511, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": 1.0319970846176147, | |
| "eval_runtime": 14.4874, | |
| "eval_samples_per_second": 7.455, | |
| "eval_steps_per_second": 3.727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.3412677049636841, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.0084, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 0.37400057911872864, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9351, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "eval_loss": 0.9427710771560669, | |
| "eval_runtime": 14.5232, | |
| "eval_samples_per_second": 7.436, | |
| "eval_steps_per_second": 3.718, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.37153348326683044, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.9626, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "eval_loss": 0.92406165599823, | |
| "eval_runtime": 14.5492, | |
| "eval_samples_per_second": 7.423, | |
| "eval_steps_per_second": 3.712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08187134502923976, | |
| "grad_norm": 0.3096253275871277, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9083, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.32009604573249817, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.9476, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "eval_loss": 0.9145325422286987, | |
| "eval_runtime": 14.5717, | |
| "eval_samples_per_second": 7.412, | |
| "eval_steps_per_second": 3.706, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.34855249524116516, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9452, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 0.3131394386291504, | |
| "learning_rate": 0.0, | |
| "loss": 0.869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "eval_loss": 0.9124156832695007, | |
| "eval_runtime": 28.0737, | |
| "eval_samples_per_second": 3.847, | |
| "eval_steps_per_second": 1.924, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9043369091072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |