| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002145539066690506, | |
| "eval_steps": 5, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.501633535425775e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 847.8984, | |
| "eval_samples_per_second": 7.639, | |
| "eval_steps_per_second": 3.82, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019504900606277329, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032508167677128876, | |
| "eval_loss": NaN, | |
| "eval_runtime": 847.0257, | |
| "eval_samples_per_second": 7.647, | |
| "eval_steps_per_second": 3.824, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00039009801212554657, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005851470181883198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010588235294117647, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006501633535425775, | |
| "eval_loss": NaN, | |
| "eval_runtime": 846.1381, | |
| "eval_samples_per_second": 7.655, | |
| "eval_steps_per_second": 3.828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007801960242510931, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009752450303138663, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009752450303138663, | |
| "eval_loss": NaN, | |
| "eval_runtime": 847.1704, | |
| "eval_samples_per_second": 7.645, | |
| "eval_steps_per_second": 3.823, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011702940363766397, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001300326707085155, | |
| "eval_loss": NaN, | |
| "eval_runtime": 845.487, | |
| "eval_samples_per_second": 7.661, | |
| "eval_steps_per_second": 3.831, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013653430424394129, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015603920485021863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016254083838564439, | |
| "eval_loss": NaN, | |
| "eval_runtime": 845.2981, | |
| "eval_samples_per_second": 7.662, | |
| "eval_steps_per_second": 3.832, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017554410545649595, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0019504900606277327, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019504900606277327, | |
| "eval_loss": NaN, | |
| "eval_runtime": 845.456, | |
| "eval_samples_per_second": 7.661, | |
| "eval_steps_per_second": 3.831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002145539066690506, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3834862821638144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |