| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03894839337877313, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012982797792924375, | |
| "eval_loss": NaN, | |
| "eval_runtime": 107.629, | |
| "eval_samples_per_second": 13.565, | |
| "eval_steps_per_second": 4.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038948393378773127, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007789678675754625, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0103862382343395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 107.3842, | |
| "eval_samples_per_second": 13.596, | |
| "eval_steps_per_second": 4.535, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011684518013631937, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01557935735150925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019474196689386564, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020772476468679, | |
| "eval_loss": NaN, | |
| "eval_runtime": 107.3747, | |
| "eval_samples_per_second": 13.597, | |
| "eval_steps_per_second": 4.536, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023369036027263874, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027263875365141188, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0311587147030185, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0311587147030185, | |
| "eval_loss": NaN, | |
| "eval_runtime": 107.3537, | |
| "eval_samples_per_second": 13.6, | |
| "eval_steps_per_second": 4.536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.035053554040895815, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03894839337877313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.746129551917056e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |