| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029331964508322946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "grad_norm": 1.0992687940597534, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "eval_loss": 1.8006389141082764, | |
| "eval_runtime": 35.4617, | |
| "eval_samples_per_second": 40.494, | |
| "eval_steps_per_second": 20.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005866392901664589, | |
| "grad_norm": 1.3805053234100342, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8222, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "grad_norm": 0.8901240229606628, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6299, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "eval_loss": 1.7950878143310547, | |
| "eval_runtime": 34.5132, | |
| "eval_samples_per_second": 41.607, | |
| "eval_steps_per_second": 20.804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011732785803329178, | |
| "grad_norm": 1.3633474111557007, | |
| "learning_rate": 8e-05, | |
| "loss": 1.99, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014665982254161473, | |
| "grad_norm": 0.9711157083511353, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "grad_norm": 0.7914196848869324, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9315, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "eval_loss": 1.746018886566162, | |
| "eval_runtime": 34.5455, | |
| "eval_samples_per_second": 41.568, | |
| "eval_steps_per_second": 20.784, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002053237515582606, | |
| "grad_norm": 0.6777245998382568, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7689, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023465571606658357, | |
| "grad_norm": 1.1216522455215454, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7802, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "grad_norm": 1.011056661605835, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "eval_loss": 1.6742736101150513, | |
| "eval_runtime": 34.5986, | |
| "eval_samples_per_second": 41.505, | |
| "eval_steps_per_second": 20.752, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029331964508322946, | |
| "grad_norm": 0.6331936717033386, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6393, | |
| "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": 76723802603520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |