| { | |
| "best_metric": 1.0691055059432983, | |
| "best_model_checkpoint": "./outputs/checkpoint-2200", | |
| "epoch": 2.9333333333333336, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2967, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.1817998886108398, | |
| "eval_runtime": 187.6804, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.289, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0115, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.1461560726165771, | |
| "eval_runtime": 186.2762, | |
| "eval_samples_per_second": 10.361, | |
| "eval_steps_per_second": 1.299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9918, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1315025091171265, | |
| "eval_runtime": 186.4761, | |
| "eval_samples_per_second": 10.35, | |
| "eval_steps_per_second": 1.298, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1221688985824585, | |
| "eval_runtime": 186.7425, | |
| "eval_samples_per_second": 10.335, | |
| "eval_steps_per_second": 1.296, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9657, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1161261796951294, | |
| "eval_runtime": 186.7488, | |
| "eval_samples_per_second": 10.335, | |
| "eval_steps_per_second": 1.296, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9675, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.111202597618103, | |
| "eval_runtime": 186.3885, | |
| "eval_samples_per_second": 10.355, | |
| "eval_steps_per_second": 1.298, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9638, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1068408489227295, | |
| "eval_runtime": 186.3328, | |
| "eval_samples_per_second": 10.358, | |
| "eval_steps_per_second": 1.299, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9531, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.102936029434204, | |
| "eval_runtime": 186.6863, | |
| "eval_samples_per_second": 10.338, | |
| "eval_steps_per_second": 1.296, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9517, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.0996404886245728, | |
| "eval_runtime": 186.5382, | |
| "eval_samples_per_second": 10.346, | |
| "eval_steps_per_second": 1.297, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9489, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.098088026046753, | |
| "eval_runtime": 186.2211, | |
| "eval_samples_per_second": 10.364, | |
| "eval_steps_per_second": 1.3, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9445, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.0934962034225464, | |
| "eval_runtime": 186.2589, | |
| "eval_samples_per_second": 10.362, | |
| "eval_steps_per_second": 1.299, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9363, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.0906414985656738, | |
| "eval_runtime": 186.6323, | |
| "eval_samples_per_second": 10.341, | |
| "eval_steps_per_second": 1.297, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9411, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.0867207050323486, | |
| "eval_runtime": 186.79, | |
| "eval_samples_per_second": 10.332, | |
| "eval_steps_per_second": 1.296, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9422, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.0864734649658203, | |
| "eval_runtime": 186.4609, | |
| "eval_samples_per_second": 10.351, | |
| "eval_steps_per_second": 1.298, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9357, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0845235586166382, | |
| "eval_runtime": 186.2213, | |
| "eval_samples_per_second": 10.364, | |
| "eval_steps_per_second": 1.3, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9329, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.0820677280426025, | |
| "eval_runtime": 187.4263, | |
| "eval_samples_per_second": 10.297, | |
| "eval_steps_per_second": 1.291, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9306, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.0760257244110107, | |
| "eval_runtime": 186.9978, | |
| "eval_samples_per_second": 10.321, | |
| "eval_steps_per_second": 1.294, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9245, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.077230453491211, | |
| "eval_runtime": 187.3361, | |
| "eval_samples_per_second": 10.302, | |
| "eval_steps_per_second": 1.292, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9215, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.0725194215774536, | |
| "eval_runtime": 186.9082, | |
| "eval_samples_per_second": 10.326, | |
| "eval_steps_per_second": 1.295, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9309, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.0725408792495728, | |
| "eval_runtime": 186.323, | |
| "eval_samples_per_second": 10.358, | |
| "eval_steps_per_second": 1.299, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9263, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.0695561170578003, | |
| "eval_runtime": 186.9997, | |
| "eval_samples_per_second": 10.321, | |
| "eval_steps_per_second": 1.294, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9178, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.0691055059432983, | |
| "eval_runtime": 187.389, | |
| "eval_samples_per_second": 10.299, | |
| "eval_steps_per_second": 1.291, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 3.110307163440169e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |