| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14130434782608695, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036231884057971015, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0138, | |
| "eval_samples_per_second": 19.455, | |
| "eval_steps_per_second": 9.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018115942028985508, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.036231884057971016, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.036231884057971016, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0957, | |
| "eval_samples_per_second": 22.96, | |
| "eval_steps_per_second": 11.578, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05434782608695652, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07246376811594203, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07246376811594203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.1159, | |
| "eval_samples_per_second": 22.87, | |
| "eval_steps_per_second": 11.533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09057971014492754, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10869565217391304, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10869565217391304, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.1128, | |
| "eval_samples_per_second": 22.884, | |
| "eval_steps_per_second": 11.54, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12681159420289856, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 2270087809597440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |