| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016842105263157894, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 2.831493377685547, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 4.256342887878418, | |
| "eval_runtime": 15.5577, | |
| "eval_samples_per_second": 16.069, | |
| "eval_steps_per_second": 8.035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 1.51045823097229, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1888, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 1.9805704355239868, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "eval_loss": 4.245272636413574, | |
| "eval_runtime": 12.2844, | |
| "eval_samples_per_second": 20.351, | |
| "eval_steps_per_second": 10.176, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736842105263158, | |
| "grad_norm": 1.6960570812225342, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 2.2655293941497803, | |
| "learning_rate": 0.0001, | |
| "loss": 3.85, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 2.5489346981048584, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "eval_loss": 4.007666110992432, | |
| "eval_runtime": 12.3015, | |
| "eval_samples_per_second": 20.323, | |
| "eval_steps_per_second": 10.161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011789473684210527, | |
| "grad_norm": 2.641709804534912, | |
| "learning_rate": 0.00014, | |
| "loss": 3.7767, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "grad_norm": 2.998255729675293, | |
| "learning_rate": 0.00016, | |
| "loss": 3.6866, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 2.785567283630371, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9816, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "eval_loss": 2.961019992828369, | |
| "eval_runtime": 12.2983, | |
| "eval_samples_per_second": 20.328, | |
| "eval_steps_per_second": 10.164, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 2.879101276397705, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3847, | |
| "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": 3166205430988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |