| { |
| "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 |
| } |
|
|
