| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5182724252491694, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013289036544850499, | |
| "eval_loss": 2.4356181621551514, | |
| "eval_runtime": 0.9253, | |
| "eval_samples_per_second": 34.582, | |
| "eval_steps_per_second": 17.291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 4.659164905548096, | |
| "learning_rate": 0.0002, | |
| "loss": 1.911, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17275747508305647, | |
| "eval_loss": 1.3857810497283936, | |
| "eval_runtime": 0.9252, | |
| "eval_samples_per_second": 34.587, | |
| "eval_steps_per_second": 17.294, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 2.4893510341644287, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.3128, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34551495016611294, | |
| "eval_loss": 1.2328505516052246, | |
| "eval_runtime": 0.9268, | |
| "eval_samples_per_second": 34.526, | |
| "eval_steps_per_second": 17.263, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 1.948126196861267, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5182724252491694, | |
| "eval_loss": 1.2024189233779907, | |
| "eval_runtime": 0.9576, | |
| "eval_samples_per_second": 33.419, | |
| "eval_steps_per_second": 16.709, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1950379589763072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |