| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004764173415912339, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004764173415912339, | |
| "grad_norm": 1.7114481925964355, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004764173415912339, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.2525, | |
| "eval_samples_per_second": 29.221, | |
| "eval_steps_per_second": 14.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009528346831824678, | |
| "grad_norm": 1.6032798290252686, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5293, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014292520247737017, | |
| "grad_norm": 1.4384857416152954, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0505, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014292520247737017, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.3188, | |
| "eval_samples_per_second": 30.151, | |
| "eval_steps_per_second": 15.076, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019056693663649356, | |
| "grad_norm": 1.4929753541946411, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4071, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023820867079561697, | |
| "grad_norm": 1.3990875482559204, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028585040495474035, | |
| "grad_norm": 1.4919512271881104, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7419, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028585040495474035, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.4292, | |
| "eval_samples_per_second": 30.038, | |
| "eval_steps_per_second": 15.019, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033349213911386373, | |
| "grad_norm": 1.566218614578247, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5994, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003811338732729871, | |
| "grad_norm": 1.520134687423706, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5051, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004287756074321105, | |
| "grad_norm": 2.302412509918213, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5605, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004287756074321105, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.1846, | |
| "eval_samples_per_second": 31.365, | |
| "eval_steps_per_second": 15.682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004764173415912339, | |
| "grad_norm": 1.2178163528442383, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2253, | |
| "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": 1849596460400640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |