| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0045731084888326326, | |
| "eval_steps": 14, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "eval_loss": 2.5971131324768066, | |
| "eval_runtime": 98.8794, | |
| "eval_samples_per_second": 26.072, | |
| "eval_steps_per_second": 13.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016332530317259401, | |
| "grad_norm": 2.0664286613464355, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 9.928, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022865542444163163, | |
| "eval_loss": 2.4638168811798096, | |
| "eval_runtime": 98.8933, | |
| "eval_samples_per_second": 26.068, | |
| "eval_steps_per_second": 13.034, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0032665060634518802, | |
| "grad_norm": 3.385493278503418, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 9.6198, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0045731084888326326, | |
| "eval_loss": 2.3797528743743896, | |
| "eval_runtime": 98.9153, | |
| "eval_samples_per_second": 26.063, | |
| "eval_steps_per_second": 13.031, | |
| "step": 28 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 55, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5049122650324992.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |