| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004232974447649747, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.465948895299493e-06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2194.5797, | |
| "eval_samples_per_second": 22.663, | |
| "eval_steps_per_second": 11.332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.2329744476497466e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.465948895299493e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.465948895299493e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2195.5669, | |
| "eval_samples_per_second": 22.652, | |
| "eval_steps_per_second": 11.326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001269892334294924, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00016931897790598986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00016931897790598986, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2275.7667, | |
| "eval_samples_per_second": 21.854, | |
| "eval_steps_per_second": 10.927, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00021164872238248734, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0002539784668589848, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0002539784668589848, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2263.4199, | |
| "eval_samples_per_second": 21.973, | |
| "eval_steps_per_second": 10.987, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00029630821133548227, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0003386379558119797, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0003386379558119797, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2246.8873, | |
| "eval_samples_per_second": 22.135, | |
| "eval_steps_per_second": 11.068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00038096770028847723, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0004232974447649747, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0004232974447649747, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2255.6239, | |
| "eval_samples_per_second": 22.049, | |
| "eval_steps_per_second": 11.025, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1734995683049472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |