| { | |
| "best_metric": 2.3775434494018555, | |
| "best_model_checkpoint": "./outputs/checkpoint-900", | |
| "epoch": 0.6557377049180327, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7201, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.618009567260742, | |
| "eval_runtime": 1145.9752, | |
| "eval_samples_per_second": 5.475, | |
| "eval_steps_per_second": 0.685, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5807, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.5655324459075928, | |
| "eval_runtime": 1107.0292, | |
| "eval_samples_per_second": 5.667, | |
| "eval_steps_per_second": 0.709, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5387, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.530600070953369, | |
| "eval_runtime": 1174.5089, | |
| "eval_samples_per_second": 5.342, | |
| "eval_steps_per_second": 0.668, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.496591806411743, | |
| "eval_runtime": 1111.3152, | |
| "eval_samples_per_second": 5.646, | |
| "eval_steps_per_second": 0.706, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4699, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.470156192779541, | |
| "eval_runtime": 1148.7316, | |
| "eval_samples_per_second": 5.462, | |
| "eval_steps_per_second": 0.683, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4445, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.4447057247161865, | |
| "eval_runtime": 1011.8783, | |
| "eval_samples_per_second": 6.2, | |
| "eval_steps_per_second": 0.776, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4269, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.4192888736724854, | |
| "eval_runtime": 1320.0264, | |
| "eval_samples_per_second": 4.753, | |
| "eval_steps_per_second": 0.595, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4054, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.3991127014160156, | |
| "eval_runtime": 1042.8122, | |
| "eval_samples_per_second": 6.016, | |
| "eval_steps_per_second": 0.753, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3697, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.3775434494018555, | |
| "eval_runtime": 1384.392, | |
| "eval_samples_per_second": 4.532, | |
| "eval_steps_per_second": 0.567, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.64265735974912e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |