| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.4650615155696869, | |
| "learning_rate": 0.0001942857142857143, | |
| "loss": 1.6005, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.35644277930259705, | |
| "learning_rate": 0.00018285714285714286, | |
| "loss": 1.2866, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.3376062512397766, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 1.2692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.29242751002311707, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.26348423957824707, | |
| "learning_rate": 0.00014857142857142857, | |
| "loss": 1.2455, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.25888073444366455, | |
| "learning_rate": 0.00013714285714285716, | |
| "loss": 1.2225, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.2843521237373352, | |
| "learning_rate": 0.00012571428571428572, | |
| "loss": 1.1816, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.27835819125175476, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 1.1955, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.26826807856559753, | |
| "learning_rate": 0.00010285714285714286, | |
| "loss": 1.2116, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.2616140842437744, | |
| "learning_rate": 9.142857142857143e-05, | |
| "loss": 1.2011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.26591983437538147, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1728, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.26238107681274414, | |
| "learning_rate": 6.857142857142858e-05, | |
| "loss": 1.1702, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.3198803961277008, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.1627, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.26853621006011963, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 1.2259, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.2809404730796814, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 1.1997, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3085035979747772, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 1.1556, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.2664521038532257, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 1.22, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.331316202878952, | |
| "learning_rate": 0.0, | |
| "loss": 1.1834, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.7831377329691034e+17, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |