| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00039878370968545937, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.9878370968545935e-05, | |
| "grad_norm": 25.301746368408203, | |
| "learning_rate": 2e-05, | |
| "loss": 14.3378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.9878370968545935e-05, | |
| "eval_loss": 13.684350967407227, | |
| "eval_runtime": 444.4276, | |
| "eval_samples_per_second": 23.759, | |
| "eval_steps_per_second": 11.88, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.975674193709187e-05, | |
| "grad_norm": 40.36569595336914, | |
| "learning_rate": 4e-05, | |
| "loss": 12.4279, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001196351129056378, | |
| "grad_norm": 27.88860321044922, | |
| "learning_rate": 6e-05, | |
| "loss": 12.8658, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001196351129056378, | |
| "eval_loss": 13.17912483215332, | |
| "eval_runtime": 442.4539, | |
| "eval_samples_per_second": 23.865, | |
| "eval_steps_per_second": 11.933, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015951348387418374, | |
| "grad_norm": 31.7746524810791, | |
| "learning_rate": 8e-05, | |
| "loss": 13.8295, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019939185484272969, | |
| "grad_norm": 33.25734329223633, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6314, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002392702258112756, | |
| "grad_norm": 33.9842414855957, | |
| "learning_rate": 0.00012, | |
| "loss": 7.9178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002392702258112756, | |
| "eval_loss": 6.492359161376953, | |
| "eval_runtime": 442.525, | |
| "eval_samples_per_second": 23.861, | |
| "eval_steps_per_second": 11.932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027914859677982153, | |
| "grad_norm": 28.602575302124023, | |
| "learning_rate": 0.00014, | |
| "loss": 9.9776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003190269677483675, | |
| "grad_norm": 13.103843688964844, | |
| "learning_rate": 0.00016, | |
| "loss": 2.213, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003589053387169134, | |
| "grad_norm": 16.657100677490234, | |
| "learning_rate": 0.00018, | |
| "loss": 4.471, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003589053387169134, | |
| "eval_loss": 3.651150941848755, | |
| "eval_runtime": 442.6764, | |
| "eval_samples_per_second": 23.853, | |
| "eval_steps_per_second": 11.927, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00039878370968545937, | |
| "grad_norm": 24.20899200439453, | |
| "learning_rate": 0.0002, | |
| "loss": 7.3309, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2820585478422528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |