| { | |
| "best_metric": 3.1137237548828125, | |
| "best_model_checkpoint": "runs/checkpoint-100", | |
| "epoch": 0.26455026455026454, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.13795485020402745, | |
| "eval_loss": 4.789039134979248, | |
| "eval_runtime": 37.8471, | |
| "eval_samples_per_second": 122.969, | |
| "eval_steps_per_second": 2.563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.9326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.13097405669206658, | |
| "eval_loss": 4.460000991821289, | |
| "eval_runtime": 37.702, | |
| "eval_samples_per_second": 123.442, | |
| "eval_steps_per_second": 2.573, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.017237469923391858, | |
| "eval_loss": 4.136398792266846, | |
| "eval_runtime": 37.8214, | |
| "eval_samples_per_second": 123.052, | |
| "eval_steps_per_second": 2.565, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 4.1299, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.001030985287561302, | |
| "eval_loss": 3.7156336307525635, | |
| "eval_runtime": 37.596, | |
| "eval_samples_per_second": 123.79, | |
| "eval_steps_per_second": 2.58, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.0002322747955471305, | |
| "eval_loss": 3.3965370655059814, | |
| "eval_runtime": 37.6834, | |
| "eval_samples_per_second": 123.503, | |
| "eval_steps_per_second": 2.574, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 3.4428, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.0001927115061956962, | |
| "eval_loss": 3.253018617630005, | |
| "eval_runtime": 37.7176, | |
| "eval_samples_per_second": 123.391, | |
| "eval_steps_per_second": 2.572, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 3.530917221687149e-05, | |
| "eval_loss": 3.1727356910705566, | |
| "eval_runtime": 37.8548, | |
| "eval_samples_per_second": 122.943, | |
| "eval_steps_per_second": 2.562, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 3.1873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 3.211858436594937e-05, | |
| "eval_loss": 3.131649971008301, | |
| "eval_runtime": 37.7677, | |
| "eval_samples_per_second": 123.227, | |
| "eval_steps_per_second": 2.568, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 2.4248467667008132e-05, | |
| "eval_loss": 3.116509437561035, | |
| "eval_runtime": 37.6259, | |
| "eval_samples_per_second": 123.691, | |
| "eval_steps_per_second": 2.578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0, | |
| "loss": 3.1176, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 2.2546820813182997e-05, | |
| "eval_loss": 3.1137237548828125, | |
| "eval_runtime": 37.9061, | |
| "eval_samples_per_second": 122.777, | |
| "eval_steps_per_second": 2.559, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "step": 100, | |
| "total_flos": 933745862246400.0, | |
| "train_loss": 3.762029037475586, | |
| "train_runtime": 467.4517, | |
| "train_samples_per_second": 10.268, | |
| "train_steps_per_second": 0.214 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 933745862246400.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |