| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0054473648372599754, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005447364837259975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005447364837259975, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6273, | |
| "eval_samples_per_second": 25.239, | |
| "eval_steps_per_second": 12.636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001089472967451995, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016342094511779927, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016342094511779927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.0741, | |
| "eval_samples_per_second": 27.534, | |
| "eval_steps_per_second": 13.785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00217894593490399, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027236824186299877, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032684189023559854, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032684189023559854, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.1627, | |
| "eval_samples_per_second": 27.448, | |
| "eval_steps_per_second": 13.742, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0038131553860819827, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 5.6991, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00435789186980798, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004902628353533978, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004902628353533978, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.1429, | |
| "eval_samples_per_second": 27.467, | |
| "eval_steps_per_second": 13.751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0054473648372599754, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 2352558662221824.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |