| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04666083406240887, | |
| "eval_steps": 5, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011665208515602217, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.2342, | |
| "eval_samples_per_second": 29.507, | |
| "eval_steps_per_second": 14.795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003499562554680665, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0058326042578011085, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8776, | |
| "eval_samples_per_second": 30.393, | |
| "eval_steps_per_second": 15.239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00699912510936133, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010498687664041995, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011665208515602217, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9065, | |
| "eval_samples_per_second": 30.32, | |
| "eval_steps_per_second": 15.202, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01399825021872266, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017497812773403325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017497812773403325, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9494, | |
| "eval_samples_per_second": 30.211, | |
| "eval_steps_per_second": 15.147, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02099737532808399, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023330417031204434, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8738, | |
| "eval_samples_per_second": 30.403, | |
| "eval_steps_per_second": 15.244, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024496937882764653, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014067366430758004, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02799650043744532, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029163021289005542, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8783, | |
| "eval_samples_per_second": 30.391, | |
| "eval_steps_per_second": 15.238, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.920883091822408e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03499562554680665, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03499562554680665, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8857, | |
| "eval_samples_per_second": 30.373, | |
| "eval_steps_per_second": 15.228, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03849518810148731, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260567e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.040828229804607756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8779, | |
| "eval_samples_per_second": 30.392, | |
| "eval_steps_per_second": 15.238, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04199475065616798, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.045494313210848646, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.478104631726711e-07, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04666083406240887, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.8817, | |
| "eval_samples_per_second": 30.383, | |
| "eval_steps_per_second": 15.234, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3202353117265920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |