| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6000.0, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 200.0, | |
| "eval_loss": 4.5546875, | |
| "eval_runtime": 0.0952, | |
| "eval_samples_per_second": 63.02, | |
| "eval_steps_per_second": 10.503, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "eval_loss": 5.13671875, | |
| "eval_runtime": 0.0952, | |
| "eval_samples_per_second": 62.996, | |
| "eval_steps_per_second": 10.499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3672, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 600.0, | |
| "eval_loss": 5.375, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.813, | |
| "eval_steps_per_second": 10.469, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 800.0, | |
| "eval_loss": 5.5390625, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.807, | |
| "eval_steps_per_second": 10.468, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0064, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1000.0, | |
| "eval_loss": 5.6484375, | |
| "eval_runtime": 0.0939, | |
| "eval_samples_per_second": 63.886, | |
| "eval_steps_per_second": 10.648, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1200.0, | |
| "eval_loss": 5.76171875, | |
| "eval_runtime": 0.0951, | |
| "eval_samples_per_second": 63.073, | |
| "eval_steps_per_second": 10.512, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1400.0, | |
| "eval_loss": 5.83203125, | |
| "eval_runtime": 0.0957, | |
| "eval_samples_per_second": 62.694, | |
| "eval_steps_per_second": 10.449, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0032, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1600.0, | |
| "eval_loss": 5.93359375, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.898, | |
| "eval_steps_per_second": 10.483, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1800.0, | |
| "eval_loss": 5.953125, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.854, | |
| "eval_steps_per_second": 10.476, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0024, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2000.0, | |
| "eval_loss": 6.03515625, | |
| "eval_runtime": 0.0935, | |
| "eval_samples_per_second": 64.153, | |
| "eval_steps_per_second": 10.692, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2200.0, | |
| "eval_loss": 6.1015625, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.861, | |
| "eval_steps_per_second": 10.477, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2400.0, | |
| "eval_loss": 6.15625, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.877, | |
| "eval_steps_per_second": 10.479, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0018, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2600.0, | |
| "eval_loss": 6.26171875, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.805, | |
| "eval_steps_per_second": 10.468, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2800.0, | |
| "eval_loss": 6.25390625, | |
| "eval_runtime": 0.0952, | |
| "eval_samples_per_second": 63.053, | |
| "eval_steps_per_second": 10.509, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0014, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "eval_loss": 6.32421875, | |
| "eval_runtime": 0.0938, | |
| "eval_samples_per_second": 63.961, | |
| "eval_steps_per_second": 10.66, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3200.0, | |
| "eval_loss": 6.28125, | |
| "eval_runtime": 0.0934, | |
| "eval_samples_per_second": 64.273, | |
| "eval_steps_per_second": 10.712, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3400.0, | |
| "eval_loss": 6.34765625, | |
| "eval_runtime": 0.0935, | |
| "eval_samples_per_second": 64.183, | |
| "eval_steps_per_second": 10.697, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0014, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3600.0, | |
| "eval_loss": 6.36328125, | |
| "eval_runtime": 0.0935, | |
| "eval_samples_per_second": 64.157, | |
| "eval_steps_per_second": 10.693, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3800.0, | |
| "eval_loss": 6.5078125, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.909, | |
| "eval_steps_per_second": 10.485, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 4000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0009, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4000.0, | |
| "eval_loss": 6.5546875, | |
| "eval_runtime": 0.0937, | |
| "eval_samples_per_second": 64.049, | |
| "eval_steps_per_second": 10.675, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4200.0, | |
| "eval_loss": 6.46484375, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.864, | |
| "eval_steps_per_second": 10.477, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 4400.0, | |
| "eval_loss": 6.59765625, | |
| "eval_runtime": 0.0937, | |
| "eval_samples_per_second": 64.005, | |
| "eval_steps_per_second": 10.667, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 4500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0008, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4600.0, | |
| "eval_loss": 6.640625, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.799, | |
| "eval_steps_per_second": 10.467, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 4800.0, | |
| "eval_loss": 6.625, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.869, | |
| "eval_steps_per_second": 10.478, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 5000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0005, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5000.0, | |
| "eval_loss": 6.66796875, | |
| "eval_runtime": 0.0937, | |
| "eval_samples_per_second": 64.004, | |
| "eval_steps_per_second": 10.667, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5200.0, | |
| "eval_loss": 6.671875, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.801, | |
| "eval_steps_per_second": 10.467, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 5400.0, | |
| "eval_loss": 6.78125, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 62.857, | |
| "eval_steps_per_second": 10.476, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 5500.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0005, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 5600.0, | |
| "eval_loss": 6.83984375, | |
| "eval_runtime": 0.0958, | |
| "eval_samples_per_second": 62.636, | |
| "eval_steps_per_second": 10.439, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 5800.0, | |
| "eval_loss": 6.64453125, | |
| "eval_runtime": 0.0954, | |
| "eval_samples_per_second": 62.879, | |
| "eval_steps_per_second": 10.48, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 6000.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0007, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6000.0, | |
| "eval_loss": 6.7578125, | |
| "eval_runtime": 0.0935, | |
| "eval_samples_per_second": 64.204, | |
| "eval_steps_per_second": 10.701, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6000.0, | |
| "step": 6000, | |
| "total_flos": 5.016807094930637e+16, | |
| "train_loss": 0.032272634650270145, | |
| "train_runtime": 8757.5386, | |
| "train_samples_per_second": 10.962, | |
| "train_steps_per_second": 0.685 | |
| } | |
| ], | |
| "max_steps": 6000, | |
| "num_train_epochs": 6000, | |
| "total_flos": 5.016807094930637e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |