| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014724829744156083, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029449659488312165, | |
| "grad_norm": 3.5325353145599365, | |
| "learning_rate": 1e-05, | |
| "loss": 4.1784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029449659488312165, | |
| "eval_loss": 4.3567214012146, | |
| "eval_runtime": 302.8557, | |
| "eval_samples_per_second": 18.884, | |
| "eval_steps_per_second": 9.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005889931897662433, | |
| "grad_norm": 3.7289960384368896, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4864, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005889931897662433, | |
| "eval_loss": 4.337247371673584, | |
| "eval_runtime": 79.5092, | |
| "eval_samples_per_second": 71.929, | |
| "eval_steps_per_second": 35.971, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000883489784649365, | |
| "grad_norm": 3.515183448791504, | |
| "learning_rate": 3e-05, | |
| "loss": 4.4776, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011779863795324866, | |
| "grad_norm": 3.0221738815307617, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9299, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011779863795324866, | |
| "eval_loss": 4.234365940093994, | |
| "eval_runtime": 81.9856, | |
| "eval_samples_per_second": 69.756, | |
| "eval_steps_per_second": 34.884, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014724829744156083, | |
| "grad_norm": 3.6643760204315186, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2711, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1000194661416960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |