| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003918793882327328, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00043542154248081425, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043542154248081425, | |
| "eval_loss": NaN, | |
| "eval_runtime": 825.2293, | |
| "eval_samples_per_second": 4.687, | |
| "eval_steps_per_second": 2.344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008708430849616285, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013062646274424427, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013062646274424427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 776.8851, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 2.489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001741686169923257, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021771077124040712, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026125292548848855, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0026125292548848855, | |
| "eval_loss": NaN, | |
| "eval_runtime": 777.5883, | |
| "eval_samples_per_second": 4.974, | |
| "eval_steps_per_second": 2.487, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0030479507973656997, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003483372339846514, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003918793882327328, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003918793882327328, | |
| "eval_loss": NaN, | |
| "eval_runtime": 777.5033, | |
| "eval_samples_per_second": 4.975, | |
| "eval_steps_per_second": 2.487, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.704945439349146e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |