| { |
| "best_metric": 1.623923897743225, |
| "best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-140", |
| "epoch": 10.0, |
| "eval_steps": 5, |
| "global_step": 140, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.642857142857143e-05, |
| "loss": 2.2959, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_loss": 2.26009202003479, |
| "eval_runtime": 2.5228, |
| "eval_samples_per_second": 2.378, |
| "eval_steps_per_second": 0.396, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 9.285714285714286e-05, |
| "loss": 2.2056, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.71, |
| "eval_loss": 2.15522837638855, |
| "eval_runtime": 2.5338, |
| "eval_samples_per_second": 2.368, |
| "eval_steps_per_second": 0.395, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 8.92857142857143e-05, |
| "loss": 2.097, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.07, |
| "eval_loss": 2.0667991638183594, |
| "eval_runtime": 2.5411, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.394, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 8.571428571428571e-05, |
| "loss": 2.0293, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.43, |
| "eval_loss": 2.0328972339630127, |
| "eval_runtime": 2.5419, |
| "eval_samples_per_second": 2.36, |
| "eval_steps_per_second": 0.393, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 8.214285714285714e-05, |
| "loss": 2.0228, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.79, |
| "eval_loss": 1.998112678527832, |
| "eval_runtime": 2.5416, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.393, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 7.857142857142858e-05, |
| "loss": 1.9493, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.14, |
| "eval_loss": 1.968154788017273, |
| "eval_runtime": 2.5414, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.393, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 1.9252, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_loss": 1.937127947807312, |
| "eval_runtime": 2.5401, |
| "eval_samples_per_second": 2.362, |
| "eval_steps_per_second": 0.394, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 7.142857142857143e-05, |
| "loss": 1.8848, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.86, |
| "eval_loss": 1.9035807847976685, |
| "eval_runtime": 2.5391, |
| "eval_samples_per_second": 2.363, |
| "eval_steps_per_second": 0.394, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 6.785714285714286e-05, |
| "loss": 1.8708, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.21, |
| "eval_loss": 1.8712326288223267, |
| "eval_runtime": 2.5413, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.394, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 6.428571428571429e-05, |
| "loss": 1.795, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.57, |
| "eval_loss": 1.8411849737167358, |
| "eval_runtime": 2.5425, |
| "eval_samples_per_second": 2.36, |
| "eval_steps_per_second": 0.393, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 6.0714285714285715e-05, |
| "loss": 1.7851, |
| "step": 55 |
| }, |
| { |
| "epoch": 3.93, |
| "eval_loss": 1.8131023645401, |
| "eval_runtime": 2.5418, |
| "eval_samples_per_second": 2.36, |
| "eval_steps_per_second": 0.393, |
| "step": 55 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 5.714285714285714e-05, |
| "loss": 1.737, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.29, |
| "eval_loss": 1.7883529663085938, |
| "eval_runtime": 2.541, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.394, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 5.3571428571428575e-05, |
| "loss": 1.7509, |
| "step": 65 |
| }, |
| { |
| "epoch": 4.64, |
| "eval_loss": 1.7668665647506714, |
| "eval_runtime": 2.5422, |
| "eval_samples_per_second": 2.36, |
| "eval_steps_per_second": 0.393, |
| "step": 65 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 5e-05, |
| "loss": 1.7, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.7516651153564453, |
| "eval_runtime": 2.5412, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.394, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.36, |
| "learning_rate": 4.642857142857143e-05, |
| "loss": 1.6734, |
| "step": 75 |
| }, |
| { |
| "epoch": 5.36, |
| "eval_loss": 1.7334843873977661, |
| "eval_runtime": 2.5431, |
| "eval_samples_per_second": 2.359, |
| "eval_steps_per_second": 0.393, |
| "step": 75 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.6719, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.71, |
| "eval_loss": 1.7061794996261597, |
| "eval_runtime": 2.5412, |
| "eval_samples_per_second": 2.361, |
| "eval_steps_per_second": 0.394, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.07, |
| "learning_rate": 3.928571428571429e-05, |
| "loss": 1.5932, |
| "step": 85 |
| }, |
| { |
| "epoch": 6.07, |
| "eval_loss": 1.6727076768875122, |
| "eval_runtime": 2.5367, |
| "eval_samples_per_second": 2.365, |
| "eval_steps_per_second": 0.394, |
| "step": 85 |
| }, |
| { |
| "epoch": 6.43, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 1.5866, |
| "step": 90 |
| }, |
| { |
| "epoch": 6.43, |
| "eval_loss": 1.66474187374115, |
| "eval_runtime": 2.5383, |
| "eval_samples_per_second": 2.364, |
| "eval_steps_per_second": 0.394, |
| "step": 90 |
| }, |
| { |
| "epoch": 6.79, |
| "learning_rate": 3.2142857142857144e-05, |
| "loss": 1.577, |
| "step": 95 |
| }, |
| { |
| "epoch": 6.79, |
| "eval_loss": 1.6590815782546997, |
| "eval_runtime": 2.5384, |
| "eval_samples_per_second": 2.364, |
| "eval_steps_per_second": 0.394, |
| "step": 95 |
| }, |
| { |
| "epoch": 7.14, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 1.5532, |
| "step": 100 |
| }, |
| { |
| "epoch": 7.14, |
| "eval_loss": 1.6509045362472534, |
| "eval_runtime": 2.5429, |
| "eval_samples_per_second": 2.359, |
| "eval_steps_per_second": 0.393, |
| "step": 100 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 2.5e-05, |
| "loss": 1.5099, |
| "step": 105 |
| }, |
| { |
| "epoch": 7.5, |
| "eval_loss": 1.6463295221328735, |
| "eval_runtime": 2.5379, |
| "eval_samples_per_second": 2.364, |
| "eval_steps_per_second": 0.394, |
| "step": 105 |
| }, |
| { |
| "epoch": 7.86, |
| "learning_rate": 2.1428571428571428e-05, |
| "loss": 1.5717, |
| "step": 110 |
| }, |
| { |
| "epoch": 7.86, |
| "eval_loss": 1.6409095525741577, |
| "eval_runtime": 2.5359, |
| "eval_samples_per_second": 2.366, |
| "eval_steps_per_second": 0.394, |
| "step": 110 |
| }, |
| { |
| "epoch": 8.21, |
| "learning_rate": 1.785714285714286e-05, |
| "loss": 1.5354, |
| "step": 115 |
| }, |
| { |
| "epoch": 8.21, |
| "eval_loss": 1.6344412565231323, |
| "eval_runtime": 2.5372, |
| "eval_samples_per_second": 2.365, |
| "eval_steps_per_second": 0.394, |
| "step": 115 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 1.5127, |
| "step": 120 |
| }, |
| { |
| "epoch": 8.57, |
| "eval_loss": 1.6305923461914062, |
| "eval_runtime": 2.537, |
| "eval_samples_per_second": 2.365, |
| "eval_steps_per_second": 0.394, |
| "step": 120 |
| }, |
| { |
| "epoch": 8.93, |
| "learning_rate": 1.0714285714285714e-05, |
| "loss": 1.5234, |
| "step": 125 |
| }, |
| { |
| "epoch": 8.93, |
| "eval_loss": 1.6271618604660034, |
| "eval_runtime": 2.5403, |
| "eval_samples_per_second": 2.362, |
| "eval_steps_per_second": 0.394, |
| "step": 125 |
| }, |
| { |
| "epoch": 9.29, |
| "learning_rate": 7.142857142857143e-06, |
| "loss": 1.4811, |
| "step": 130 |
| }, |
| { |
| "epoch": 9.29, |
| "eval_loss": 1.6272777318954468, |
| "eval_runtime": 2.5362, |
| "eval_samples_per_second": 2.366, |
| "eval_steps_per_second": 0.394, |
| "step": 130 |
| }, |
| { |
| "epoch": 9.64, |
| "learning_rate": 3.5714285714285714e-06, |
| "loss": 1.5167, |
| "step": 135 |
| }, |
| { |
| "epoch": 9.64, |
| "eval_loss": 1.625247597694397, |
| "eval_runtime": 2.5383, |
| "eval_samples_per_second": 2.364, |
| "eval_steps_per_second": 0.394, |
| "step": 135 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0, |
| "loss": 1.4972, |
| "step": 140 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.623923897743225, |
| "eval_runtime": 2.536, |
| "eval_samples_per_second": 2.366, |
| "eval_steps_per_second": 0.394, |
| "step": 140 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 140, |
| "num_train_epochs": 10, |
| "save_steps": 10, |
| "total_flos": 4.54958436581376e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
