| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 50, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5.2354709418837674e-05, | |
| "loss": 1.6331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.959919839679359e-05, | |
| "loss": 0.8124, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 2.1140503883361816, | |
| "eval_runtime": 11.8386, | |
| "eval_samples_per_second": 0.76, | |
| "eval_steps_per_second": 0.169, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.68436873747495e-05, | |
| "loss": 0.766, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.408817635270541e-05, | |
| "loss": 0.562, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.9290642738342285, | |
| "eval_runtime": 11.9715, | |
| "eval_samples_per_second": 0.752, | |
| "eval_steps_per_second": 0.167, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.133266533066132e-05, | |
| "loss": 0.3301, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8577154308617235e-05, | |
| "loss": 0.3811, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.065908908843994, | |
| "eval_runtime": 11.9277, | |
| "eval_samples_per_second": 0.755, | |
| "eval_steps_per_second": 0.168, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.582164328657315e-05, | |
| "loss": 0.3086, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.306613226452906e-05, | |
| "loss": 0.2969, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 2.2028963565826416, | |
| "eval_runtime": 11.9591, | |
| "eval_samples_per_second": 0.753, | |
| "eval_steps_per_second": 0.167, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.0310621242484972e-05, | |
| "loss": 0.2236, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.755511022044088e-05, | |
| "loss": 0.2148, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 2.3397459983825684, | |
| "eval_runtime": 11.8913, | |
| "eval_samples_per_second": 0.757, | |
| "eval_steps_per_second": 0.168, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 2.4799599198396796e-05, | |
| "loss": 0.1813, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.2044088176352705e-05, | |
| "loss": 0.2172, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.2869534492492676, | |
| "eval_runtime": 11.8718, | |
| "eval_samples_per_second": 0.758, | |
| "eval_steps_per_second": 0.168, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.9288577154308618e-05, | |
| "loss": 0.1436, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.653306613226453e-05, | |
| "loss": 0.1659, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 2.3965632915496826, | |
| "eval_runtime": 11.9151, | |
| "eval_samples_per_second": 0.755, | |
| "eval_steps_per_second": 0.168, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.377755511022044e-05, | |
| "loss": 0.1664, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 1.1022044088176353e-05, | |
| "loss": 0.1165, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_loss": 2.4968247413635254, | |
| "eval_runtime": 11.858, | |
| "eval_samples_per_second": 0.759, | |
| "eval_steps_per_second": 0.169, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 8.266533066132265e-06, | |
| "loss": 0.1572, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 5.511022044088176e-06, | |
| "loss": 0.1174, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.4439687728881836, | |
| "eval_runtime": 11.9003, | |
| "eval_samples_per_second": 0.756, | |
| "eval_steps_per_second": 0.168, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 50, | |
| "total_flos": 1.104886503936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |