| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00028088901372845055, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8088901372845056e-05, | |
| "grad_norm": 0.6148820519447327, | |
| "learning_rate": 2e-05, | |
| "loss": 44.4385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.8088901372845056e-05, | |
| "eval_loss": 11.11430549621582, | |
| "eval_runtime": 50.2653, | |
| "eval_samples_per_second": 298.218, | |
| "eval_steps_per_second": 149.109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.617780274569011e-05, | |
| "grad_norm": 0.6381494998931885, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.426670411853516e-05, | |
| "grad_norm": 0.6478617191314697, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5031, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.426670411853516e-05, | |
| "eval_loss": 11.11417293548584, | |
| "eval_runtime": 49.2863, | |
| "eval_samples_per_second": 304.141, | |
| "eval_steps_per_second": 152.071, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011235560549138022, | |
| "grad_norm": 0.7071318030357361, | |
| "learning_rate": 8e-05, | |
| "loss": 44.4346, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00014044450686422527, | |
| "grad_norm": 0.6881616711616516, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016853340823707032, | |
| "grad_norm": 0.747654378414154, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4517, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016853340823707032, | |
| "eval_loss": 11.112412452697754, | |
| "eval_runtime": 49.4184, | |
| "eval_samples_per_second": 303.328, | |
| "eval_steps_per_second": 151.664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019662230960991537, | |
| "grad_norm": 0.6621001362800598, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4646, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00022471121098276045, | |
| "grad_norm": 0.6574032306671143, | |
| "learning_rate": 0.00016, | |
| "loss": 44.4794, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00025280011235560547, | |
| "grad_norm": 0.6733637452125549, | |
| "learning_rate": 0.00018, | |
| "loss": 44.4163, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00025280011235560547, | |
| "eval_loss": 11.109125137329102, | |
| "eval_runtime": 49.2939, | |
| "eval_samples_per_second": 304.095, | |
| "eval_steps_per_second": 152.047, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00028088901372845055, | |
| "grad_norm": 0.6684051752090454, | |
| "learning_rate": 0.0002, | |
| "loss": 44.4089, | |
| "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": 163961634816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |