| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020107784973506633, | |
| "eval_steps": 500, | |
| "global_step": 111, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.2849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.3474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.3589, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019954719225730847, | |
| "loss": 1.3078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019679487013963564, | |
| "loss": 1.2688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019161084574320696, | |
| "loss": 1.3346, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018412535328311814, | |
| "loss": 1.2897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001745264449675755, | |
| "loss": 1.2717, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016305526670845226, | |
| "loss": 1.2734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013568862215918717, | |
| "loss": 1.2708, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00012048066680651908, | |
| "loss": 1.2435, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00010475819158237425, | |
| "loss": 1.2824, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.891618000989891e-05, | |
| "loss": 1.2778, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.335261863099651e-05, | |
| "loss": 1.2511, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.845849869981137e-05, | |
| "loss": 1.2728, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.4607993613388976e-05, | |
| "loss": 1.2866, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.21490588442868e-05, | |
| "loss": 1.2377, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.139469052572127e-05, | |
| "loss": 1.2673, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.2615062293021507e-05, | |
| "loss": 1.2778, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.2666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.8071302737293295e-06, | |
| "loss": 1.2382, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5.0345761681491746e-08, | |
| "loss": 1.2627, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.2271578311920166, | |
| "eval_runtime": 1802.5494, | |
| "eval_samples_per_second": 16.27, | |
| "eval_steps_per_second": 1.356, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "step": 111, | |
| "total_flos": 79541494087680.0, | |
| "train_loss": 1.2791897563246992, | |
| "train_runtime": 2444.0756, | |
| "train_samples_per_second": 2.168, | |
| "train_steps_per_second": 0.045 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 111, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 79541494087680.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |