| { | |
| "best_metric": 1.234089970588684, | |
| "best_model_checkpoint": "./outputs/checkpoint-2200", | |
| "epoch": 2.9333333333333336, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "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": 1.4897, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3608959913253784, | |
| "eval_runtime": 129.2301, | |
| "eval_samples_per_second": 14.935, | |
| "eval_steps_per_second": 1.873, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1623, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.3195548057556152, | |
| "eval_runtime": 128.3462, | |
| "eval_samples_per_second": 15.037, | |
| "eval_steps_per_second": 1.886, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1372, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.3046056032180786, | |
| "eval_runtime": 127.9116, | |
| "eval_samples_per_second": 15.089, | |
| "eval_steps_per_second": 1.892, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1256, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2946586608886719, | |
| "eval_runtime": 128.2992, | |
| "eval_samples_per_second": 15.043, | |
| "eval_steps_per_second": 1.886, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1119, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.2872602939605713, | |
| "eval_runtime": 128.1326, | |
| "eval_samples_per_second": 15.063, | |
| "eval_steps_per_second": 1.889, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1139, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2798593044281006, | |
| "eval_runtime": 127.1516, | |
| "eval_samples_per_second": 15.179, | |
| "eval_steps_per_second": 1.903, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1079, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.2776304483413696, | |
| "eval_runtime": 127.0627, | |
| "eval_samples_per_second": 15.189, | |
| "eval_steps_per_second": 1.905, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0976, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2741276025772095, | |
| "eval_runtime": 127.4814, | |
| "eval_samples_per_second": 15.139, | |
| "eval_steps_per_second": 1.898, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0956, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2668750286102295, | |
| "eval_runtime": 127.4471, | |
| "eval_samples_per_second": 15.144, | |
| "eval_steps_per_second": 1.899, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0927, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.2661573886871338, | |
| "eval_runtime": 127.7348, | |
| "eval_samples_per_second": 15.109, | |
| "eval_steps_per_second": 1.895, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0881, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.260953664779663, | |
| "eval_runtime": 127.6819, | |
| "eval_samples_per_second": 15.116, | |
| "eval_steps_per_second": 1.895, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0776, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2578165531158447, | |
| "eval_runtime": 128.6774, | |
| "eval_samples_per_second": 14.999, | |
| "eval_steps_per_second": 1.881, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0839, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.2555885314941406, | |
| "eval_runtime": 127.1086, | |
| "eval_samples_per_second": 15.184, | |
| "eval_steps_per_second": 1.904, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0843, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.2506641149520874, | |
| "eval_runtime": 130.0402, | |
| "eval_samples_per_second": 14.842, | |
| "eval_steps_per_second": 1.861, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0785, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2521893978118896, | |
| "eval_runtime": 127.1994, | |
| "eval_samples_per_second": 15.173, | |
| "eval_steps_per_second": 1.903, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0763, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.247235655784607, | |
| "eval_runtime": 127.1673, | |
| "eval_samples_per_second": 15.177, | |
| "eval_steps_per_second": 1.903, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0725, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.2424886226654053, | |
| "eval_runtime": 127.0277, | |
| "eval_samples_per_second": 15.194, | |
| "eval_steps_per_second": 1.905, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0668, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.2424781322479248, | |
| "eval_runtime": 127.5992, | |
| "eval_samples_per_second": 15.125, | |
| "eval_steps_per_second": 1.897, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0603, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.2405894994735718, | |
| "eval_runtime": 127.1826, | |
| "eval_samples_per_second": 15.175, | |
| "eval_steps_per_second": 1.903, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0716, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.23755943775177, | |
| "eval_runtime": 126.9688, | |
| "eval_samples_per_second": 15.201, | |
| "eval_steps_per_second": 1.906, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0647, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.2376608848571777, | |
| "eval_runtime": 127.1015, | |
| "eval_samples_per_second": 15.185, | |
| "eval_steps_per_second": 1.904, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0595, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.234089970588684, | |
| "eval_runtime": 126.9486, | |
| "eval_samples_per_second": 15.203, | |
| "eval_steps_per_second": 1.906, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 7.800080571706982e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |