| { | |
| "best_metric": 1.2378512620925903, | |
| "best_model_checkpoint": "./outputs/checkpoint-2000", | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 100, | |
| "global_step": 2000, | |
| "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": 1.4919, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.361365795135498, | |
| "eval_runtime": 127.054, | |
| "eval_samples_per_second": 15.19, | |
| "eval_steps_per_second": 1.905, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1628, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.319554328918457, | |
| "eval_runtime": 126.2625, | |
| "eval_samples_per_second": 15.286, | |
| "eval_steps_per_second": 1.917, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1376, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.3056749105453491, | |
| "eval_runtime": 126.1549, | |
| "eval_samples_per_second": 15.299, | |
| "eval_steps_per_second": 1.918, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1257, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2944581508636475, | |
| "eval_runtime": 126.2031, | |
| "eval_samples_per_second": 15.293, | |
| "eval_steps_per_second": 1.918, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1123, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.2884504795074463, | |
| "eval_runtime": 126.384, | |
| "eval_samples_per_second": 15.271, | |
| "eval_steps_per_second": 1.915, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1146, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2814782857894897, | |
| "eval_runtime": 126.0146, | |
| "eval_samples_per_second": 15.316, | |
| "eval_steps_per_second": 1.92, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1083, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.2781809568405151, | |
| "eval_runtime": 126.2703, | |
| "eval_samples_per_second": 15.285, | |
| "eval_steps_per_second": 1.917, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0979, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2742822170257568, | |
| "eval_runtime": 126.1208, | |
| "eval_samples_per_second": 15.303, | |
| "eval_steps_per_second": 1.919, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0957, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2677264213562012, | |
| "eval_runtime": 126.1088, | |
| "eval_samples_per_second": 15.304, | |
| "eval_steps_per_second": 1.919, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.093, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.2662891149520874, | |
| "eval_runtime": 126.1871, | |
| "eval_samples_per_second": 15.295, | |
| "eval_steps_per_second": 1.918, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0885, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.2611089944839478, | |
| "eval_runtime": 126.2589, | |
| "eval_samples_per_second": 15.286, | |
| "eval_steps_per_second": 1.917, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0774, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2578654289245605, | |
| "eval_runtime": 126.1209, | |
| "eval_samples_per_second": 15.303, | |
| "eval_steps_per_second": 1.919, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0839, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.2557995319366455, | |
| "eval_runtime": 126.5159, | |
| "eval_samples_per_second": 15.255, | |
| "eval_steps_per_second": 1.913, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0845, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.250588297843933, | |
| "eval_runtime": 125.971, | |
| "eval_samples_per_second": 15.321, | |
| "eval_steps_per_second": 1.921, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0783, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2534571886062622, | |
| "eval_runtime": 126.2955, | |
| "eval_samples_per_second": 15.282, | |
| "eval_steps_per_second": 1.916, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0763, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.2468171119689941, | |
| "eval_runtime": 126.0777, | |
| "eval_samples_per_second": 15.308, | |
| "eval_steps_per_second": 1.919, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0727, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.2436426877975464, | |
| "eval_runtime": 126.3899, | |
| "eval_samples_per_second": 15.27, | |
| "eval_steps_per_second": 1.915, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0668, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.2427366971969604, | |
| "eval_runtime": 126.2299, | |
| "eval_samples_per_second": 15.29, | |
| "eval_steps_per_second": 1.917, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0604, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.2404277324676514, | |
| "eval_runtime": 126.4354, | |
| "eval_samples_per_second": 15.265, | |
| "eval_steps_per_second": 1.914, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0717, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.2378512620925903, | |
| "eval_runtime": 126.3766, | |
| "eval_samples_per_second": 15.272, | |
| "eval_steps_per_second": 1.915, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 7.090695034659226e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |