| { | |
| "best_metric": 1.1136090755462646, | |
| "best_model_checkpoint": "./outputs/checkpoint-1400", | |
| "epoch": 1.8666666666666667, | |
| "eval_steps": 100, | |
| "global_step": 1400, | |
| "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": 1.1585, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.2455021142959595, | |
| "eval_runtime": 180.387, | |
| "eval_samples_per_second": 10.699, | |
| "eval_steps_per_second": 1.342, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0213, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.2179733514785767, | |
| "eval_runtime": 177.6597, | |
| "eval_samples_per_second": 10.863, | |
| "eval_steps_per_second": 1.362, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0046, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.202022671699524, | |
| "eval_runtime": 178.5482, | |
| "eval_samples_per_second": 10.809, | |
| "eval_steps_per_second": 1.355, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9918, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1907917261123657, | |
| "eval_runtime": 177.5912, | |
| "eval_samples_per_second": 10.868, | |
| "eval_steps_per_second": 1.363, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9766, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.177116870880127, | |
| "eval_runtime": 177.7523, | |
| "eval_samples_per_second": 10.858, | |
| "eval_steps_per_second": 1.361, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9721, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1658653020858765, | |
| "eval_runtime": 177.5002, | |
| "eval_samples_per_second": 10.873, | |
| "eval_steps_per_second": 1.363, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9654, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1600923538208008, | |
| "eval_runtime": 177.776, | |
| "eval_samples_per_second": 10.856, | |
| "eval_steps_per_second": 1.361, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9506, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.1476994752883911, | |
| "eval_runtime": 181.2478, | |
| "eval_samples_per_second": 10.648, | |
| "eval_steps_per_second": 1.335, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9393, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.1420533657073975, | |
| "eval_runtime": 179.6022, | |
| "eval_samples_per_second": 10.746, | |
| "eval_steps_per_second": 1.347, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9312, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.1350293159484863, | |
| "eval_runtime": 178.8474, | |
| "eval_samples_per_second": 10.791, | |
| "eval_steps_per_second": 1.353, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9391, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.1300640106201172, | |
| "eval_runtime": 177.6952, | |
| "eval_samples_per_second": 10.861, | |
| "eval_steps_per_second": 1.362, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9278, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.1249330043792725, | |
| "eval_runtime": 177.6317, | |
| "eval_samples_per_second": 10.865, | |
| "eval_steps_per_second": 1.362, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9172, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.116977572441101, | |
| "eval_runtime": 177.8374, | |
| "eval_samples_per_second": 10.853, | |
| "eval_steps_per_second": 1.361, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9175, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.1136090755462646, | |
| "eval_runtime": 177.225, | |
| "eval_samples_per_second": 10.89, | |
| "eval_steps_per_second": 1.365, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.0464609713209344e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |