| { | |
| "best_metric": 0.9765165448188782, | |
| "best_model_checkpoint": "./outputs/checkpoint-1700", | |
| "epoch": 2.2666666666666666, | |
| "eval_steps": 100, | |
| "global_step": 1700, | |
| "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": 1.0608, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.0753934383392334, | |
| "eval_runtime": 354.351, | |
| "eval_samples_per_second": 5.447, | |
| "eval_steps_per_second": 0.683, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9182, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.05315363407135, | |
| "eval_runtime": 352.7918, | |
| "eval_samples_per_second": 5.471, | |
| "eval_steps_per_second": 0.686, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9037, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.0414820909500122, | |
| "eval_runtime": 353.1451, | |
| "eval_samples_per_second": 5.465, | |
| "eval_steps_per_second": 0.685, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8943, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.0332194566726685, | |
| "eval_runtime": 353.4062, | |
| "eval_samples_per_second": 5.461, | |
| "eval_steps_per_second": 0.685, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8814, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.0276169776916504, | |
| "eval_runtime": 353.0472, | |
| "eval_samples_per_second": 5.467, | |
| "eval_steps_per_second": 0.685, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8819, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.0176780223846436, | |
| "eval_runtime": 352.9946, | |
| "eval_samples_per_second": 5.468, | |
| "eval_steps_per_second": 0.686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8786, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.0153926610946655, | |
| "eval_runtime": 353.3606, | |
| "eval_samples_per_second": 5.462, | |
| "eval_steps_per_second": 0.685, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8684, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.0099254846572876, | |
| "eval_runtime": 353.3411, | |
| "eval_samples_per_second": 5.462, | |
| "eval_steps_per_second": 0.685, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8637, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.007003903388977, | |
| "eval_runtime": 353.8068, | |
| "eval_samples_per_second": 5.455, | |
| "eval_steps_per_second": 0.684, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.0005298852920532, | |
| "eval_runtime": 353.5757, | |
| "eval_samples_per_second": 5.459, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8587, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.9988044500350952, | |
| "eval_runtime": 354.8862, | |
| "eval_samples_per_second": 5.438, | |
| "eval_steps_per_second": 0.682, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8584, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.994540810585022, | |
| "eval_runtime": 353.5912, | |
| "eval_samples_per_second": 5.458, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8524, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.9898069500923157, | |
| "eval_runtime": 353.7953, | |
| "eval_samples_per_second": 5.455, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8463, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.9868175387382507, | |
| "eval_runtime": 362.9203, | |
| "eval_samples_per_second": 5.318, | |
| "eval_steps_per_second": 0.667, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8474, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9852352142333984, | |
| "eval_runtime": 354.2588, | |
| "eval_samples_per_second": 5.448, | |
| "eval_steps_per_second": 0.683, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8381, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.9809827208518982, | |
| "eval_runtime": 353.3062, | |
| "eval_samples_per_second": 5.463, | |
| "eval_steps_per_second": 0.685, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8416, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.9765165448188782, | |
| "eval_runtime": 353.8102, | |
| "eval_samples_per_second": 5.455, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 4.807017024378716e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |