| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007108457287057277, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.108457287057277e-05, | |
| "grad_norm": 1.3611820936203003, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.108457287057277e-05, | |
| "eval_loss": 1.4612771272659302, | |
| "eval_runtime": 327.8483, | |
| "eval_samples_per_second": 18.069, | |
| "eval_steps_per_second": 9.035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014216914574114554, | |
| "grad_norm": 1.971325397491455, | |
| "learning_rate": 4e-05, | |
| "loss": 5.9595, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021325371861171828, | |
| "grad_norm": 2.276702642440796, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2857, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021325371861171828, | |
| "eval_loss": 1.4580942392349243, | |
| "eval_runtime": 326.2984, | |
| "eval_samples_per_second": 18.155, | |
| "eval_steps_per_second": 9.078, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002843382914822911, | |
| "grad_norm": 1.9200899600982666, | |
| "learning_rate": 8e-05, | |
| "loss": 5.8643, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00035542286435286385, | |
| "grad_norm": 1.8585262298583984, | |
| "learning_rate": 0.0001, | |
| "loss": 6.2348, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042650743722343656, | |
| "grad_norm": 2.8255438804626465, | |
| "learning_rate": 0.00012, | |
| "loss": 6.2096, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00042650743722343656, | |
| "eval_loss": 1.4093888998031616, | |
| "eval_runtime": 327.6889, | |
| "eval_samples_per_second": 18.078, | |
| "eval_steps_per_second": 9.039, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004975920100940093, | |
| "grad_norm": 1.7055060863494873, | |
| "learning_rate": 0.00014, | |
| "loss": 5.3916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005686765829645822, | |
| "grad_norm": 2.4237794876098633, | |
| "learning_rate": 0.00016, | |
| "loss": 5.8644, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006397611558351549, | |
| "grad_norm": 2.705052137374878, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0628, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006397611558351549, | |
| "eval_loss": 1.2537384033203125, | |
| "eval_runtime": 327.2385, | |
| "eval_samples_per_second": 18.103, | |
| "eval_steps_per_second": 9.052, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007108457287057277, | |
| "grad_norm": 3.4350829124450684, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2079, | |
| "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": 3166204172697600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |