| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014534179545564654, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.689453030376436e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1116.6045, | |
| "eval_samples_per_second": 3.892, | |
| "eval_steps_per_second": 1.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029068359091129306, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00048447265151882175, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1117.3431, | |
| "eval_samples_per_second": 3.89, | |
| "eval_steps_per_second": 1.945, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005813671818225861, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008720507727338791, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009689453030376435, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1117.1294, | |
| "eval_samples_per_second": 3.89, | |
| "eval_steps_per_second": 1.945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011627343636451723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014534179545564654, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014534179545564654, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1116.3214, | |
| "eval_samples_per_second": 3.893, | |
| "eval_steps_per_second": 1.947, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.94858446749696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |