| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028037383177570093, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 3.153057813644409, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "eval_loss": 3.5910470485687256, | |
| "eval_runtime": 4.8275, | |
| "eval_samples_per_second": 9.322, | |
| "eval_steps_per_second": 4.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 3.5898184776306152, | |
| "learning_rate": 4e-05, | |
| "loss": 3.6859, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 3.4159717559814453, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6541, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "eval_loss": 3.5559732913970947, | |
| "eval_runtime": 3.2553, | |
| "eval_samples_per_second": 13.823, | |
| "eval_steps_per_second": 7.065, | |
| "step": 3 | |
| } | |
| ], | |
| "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": 554869576433664.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |