| { | |
| "best_metric": 1.1784791946411133, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "epoch": 2.8, | |
| "eval_steps": 100, | |
| "global_step": 2100, | |
| "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": 1.2694, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3544635772705078, | |
| "eval_runtime": 457.1536, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.529, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.105, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.319144368171692, | |
| "eval_runtime": 457.9804, | |
| "eval_samples_per_second": 4.214, | |
| "eval_steps_per_second": 0.528, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0849, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.299824833869934, | |
| "eval_runtime": 460.2328, | |
| "eval_samples_per_second": 4.194, | |
| "eval_steps_per_second": 0.526, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0697, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2875007390975952, | |
| "eval_runtime": 456.2021, | |
| "eval_samples_per_second": 4.231, | |
| "eval_steps_per_second": 0.53, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0562, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.2735565900802612, | |
| "eval_runtime": 461.3936, | |
| "eval_samples_per_second": 4.183, | |
| "eval_steps_per_second": 0.524, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0508, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2612242698669434, | |
| "eval_runtime": 456.1293, | |
| "eval_samples_per_second": 4.231, | |
| "eval_steps_per_second": 0.531, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0415, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.2570828199386597, | |
| "eval_runtime": 457.3356, | |
| "eval_samples_per_second": 4.22, | |
| "eval_steps_per_second": 0.529, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0297, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2444695234298706, | |
| "eval_runtime": 456.605, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.53, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0188, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.237799882888794, | |
| "eval_runtime": 457.5939, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.529, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0072, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.231415033340454, | |
| "eval_runtime": 457.4529, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.015, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.2254621982574463, | |
| "eval_runtime": 456.3078, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0025, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2201733589172363, | |
| "eval_runtime": 456.928, | |
| "eval_samples_per_second": 4.224, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9925, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.2122855186462402, | |
| "eval_runtime": 457.7214, | |
| "eval_samples_per_second": 4.217, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.993, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.207801342010498, | |
| "eval_runtime": 457.1756, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9807, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2016816139221191, | |
| "eval_runtime": 457.4366, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.529, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9755, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.2005386352539062, | |
| "eval_runtime": 458.0891, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.528, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9716, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.1973503828048706, | |
| "eval_runtime": 455.3031, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.532, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9706, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.1895887851715088, | |
| "eval_runtime": 458.1796, | |
| "eval_samples_per_second": 4.212, | |
| "eval_steps_per_second": 0.528, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9625, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.1847771406173706, | |
| "eval_runtime": 456.5256, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.53, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9561, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.1837488412857056, | |
| "eval_runtime": 455.884, | |
| "eval_samples_per_second": 4.234, | |
| "eval_steps_per_second": 0.531, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.966, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.1784791946411133, | |
| "eval_runtime": 455.9297, | |
| "eval_samples_per_second": 4.233, | |
| "eval_steps_per_second": 0.531, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 6.987573836110234e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |