| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001485729567504123, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4857295675041229e-05, | |
| "grad_norm": 10.441267013549805, | |
| "learning_rate": 2e-05, | |
| "loss": 9.6058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.4857295675041229e-05, | |
| "eval_loss": 2.7660813331604004, | |
| "eval_runtime": 1149.3891, | |
| "eval_samples_per_second": 24.657, | |
| "eval_steps_per_second": 12.328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.9714591350082458e-05, | |
| "grad_norm": 10.460489273071289, | |
| "learning_rate": 4e-05, | |
| "loss": 10.7889, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.4571887025123685e-05, | |
| "grad_norm": 9.41769790649414, | |
| "learning_rate": 6e-05, | |
| "loss": 10.1904, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.4571887025123685e-05, | |
| "eval_loss": 2.736844539642334, | |
| "eval_runtime": 1154.5829, | |
| "eval_samples_per_second": 24.546, | |
| "eval_steps_per_second": 12.273, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.9429182700164916e-05, | |
| "grad_norm": 9.358512878417969, | |
| "learning_rate": 8e-05, | |
| "loss": 10.6507, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.428647837520615e-05, | |
| "grad_norm": 10.204730987548828, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2412, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.914377405024737e-05, | |
| "grad_norm": 10.428735733032227, | |
| "learning_rate": 0.00012, | |
| "loss": 9.6887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.914377405024737e-05, | |
| "eval_loss": 2.4252917766571045, | |
| "eval_runtime": 1153.3493, | |
| "eval_samples_per_second": 24.572, | |
| "eval_steps_per_second": 12.286, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010400106972528861, | |
| "grad_norm": 8.287118911743164, | |
| "learning_rate": 0.00014, | |
| "loss": 9.837, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00011885836540032983, | |
| "grad_norm": 7.838613986968994, | |
| "learning_rate": 0.00016, | |
| "loss": 8.7304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00013371566107537106, | |
| "grad_norm": 6.961249828338623, | |
| "learning_rate": 0.00018, | |
| "loss": 7.8282, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00013371566107537106, | |
| "eval_loss": 2.0542776584625244, | |
| "eval_runtime": 1151.0236, | |
| "eval_samples_per_second": 24.622, | |
| "eval_steps_per_second": 12.311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001485729567504123, | |
| "grad_norm": 6.564357280731201, | |
| "learning_rate": 0.0002, | |
| "loss": 7.6557, | |
| "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": 1873043106299904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |