| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006826404532732609, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.82640453273261e-05, | |
| "grad_norm": 1.1533392353157979e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.82640453273261e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 234.2617, | |
| "eval_samples_per_second": 26.33, | |
| "eval_steps_per_second": 13.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001365280906546522, | |
| "grad_norm": 1.1955745321756694e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020479213598197828, | |
| "grad_norm": 1.3316417607711628e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020479213598197828, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 235.5688, | |
| "eval_samples_per_second": 26.183, | |
| "eval_steps_per_second": 13.092, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002730561813093044, | |
| "grad_norm": 9.974223758035805e-06, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00034132022663663046, | |
| "grad_norm": 1.7771051716408692e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040958427196395656, | |
| "grad_norm": 1.1142774383188225e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00040958427196395656, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 227.6494, | |
| "eval_samples_per_second": 27.094, | |
| "eval_steps_per_second": 13.547, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00047784831729128267, | |
| "grad_norm": 1.0504824786039535e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005461123626186088, | |
| "grad_norm": 2.366983608226292e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006143764079459349, | |
| "grad_norm": 1.3963933270133566e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006143764079459349, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 233.8368, | |
| "eval_samples_per_second": 26.377, | |
| "eval_steps_per_second": 13.189, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006826404532732609, | |
| "grad_norm": 1.7626603948883712e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 254016700416.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |