| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17173278378842521, | |
| "eval_steps": 50, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.3773773773773775e-05, | |
| "loss": 0.9928, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 0.8941472172737122, | |
| "eval_runtime": 5245.4303, | |
| "eval_samples_per_second": 0.987, | |
| "eval_steps_per_second": 0.123, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.877, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.8646272420883179, | |
| "eval_runtime": 5219.884, | |
| "eval_samples_per_second": 0.992, | |
| "eval_steps_per_second": 0.124, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.1271271271271275e-05, | |
| "loss": 0.8642, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.8599761128425598, | |
| "eval_runtime": 5214.4761, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.0020020020020023e-05, | |
| "loss": 0.8576, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.8569617867469788, | |
| "eval_runtime": 5214.0664, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.8768768768768768e-05, | |
| "loss": 0.8349, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.8535052537918091, | |
| "eval_runtime": 5222.9322, | |
| "eval_samples_per_second": 0.991, | |
| "eval_steps_per_second": 0.124, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.7517517517517516e-05, | |
| "loss": 0.85, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.8515381813049316, | |
| "eval_runtime": 5214.0267, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.6266266266266268e-05, | |
| "loss": 0.8548, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.8497709035873413, | |
| "eval_runtime": 5213.6211, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 0.8366, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.8475283980369568, | |
| "eval_runtime": 5213.1999, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3763763763763765e-05, | |
| "loss": 0.8408, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.8464268445968628, | |
| "eval_runtime": 5213.2855, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.2512512512512515e-05, | |
| "loss": 0.8645, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.8458148241043091, | |
| "eval_runtime": 5213.7104, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.1261261261261261e-05, | |
| "loss": 0.8507, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.8435949087142944, | |
| "eval_runtime": 5210.7804, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.0010010010010011e-05, | |
| "loss": 0.8592, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.8434337973594666, | |
| "eval_runtime": 5210.4901, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.758758758758758e-06, | |
| "loss": 0.8326, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.8415650129318237, | |
| "eval_runtime": 5212.5986, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.507507507507508e-06, | |
| "loss": 0.8272, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.8408710360527039, | |
| "eval_runtime": 5217.8607, | |
| "eval_samples_per_second": 0.992, | |
| "eval_steps_per_second": 0.124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.256256256256257e-06, | |
| "loss": 0.82, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.8401119709014893, | |
| "eval_runtime": 5220.4921, | |
| "eval_samples_per_second": 0.991, | |
| "eval_steps_per_second": 0.124, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.005005005005006e-06, | |
| "loss": 0.826, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.8393945097923279, | |
| "eval_runtime": 5287.3794, | |
| "eval_samples_per_second": 0.979, | |
| "eval_steps_per_second": 0.122, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.753753753753754e-06, | |
| "loss": 0.8468, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.8389515280723572, | |
| "eval_runtime": 5212.07, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.502502502502503e-06, | |
| "loss": 0.8438, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.8384743928909302, | |
| "eval_runtime": 5211.9686, | |
| "eval_samples_per_second": 0.993, | |
| "eval_steps_per_second": 0.124, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.2512512512512514e-06, | |
| "loss": 0.8384, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.838046669960022, | |
| "eval_runtime": 5209.2343, | |
| "eval_samples_per_second": 0.994, | |
| "eval_steps_per_second": 0.124, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0, | |
| "loss": 0.8527, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.8379368782043457, | |
| "eval_runtime": 5209.3452, | |
| "eval_samples_per_second": 0.994, | |
| "eval_steps_per_second": 0.124, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 1.76841553870848e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |