| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009727626459143969, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.72762645914397e-05, | |
| "grad_norm": 11.805068969726562, | |
| "learning_rate": 2e-05, | |
| "loss": 25.9028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.72762645914397e-05, | |
| "eval_loss": 6.9870405197143555, | |
| "eval_runtime": 419.1622, | |
| "eval_samples_per_second": 10.328, | |
| "eval_steps_per_second": 5.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001945525291828794, | |
| "grad_norm": 25.130884170532227, | |
| "learning_rate": 4e-05, | |
| "loss": 30.0975, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00029182879377431906, | |
| "grad_norm": 11.360361099243164, | |
| "learning_rate": 6e-05, | |
| "loss": 27.8426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029182879377431906, | |
| "eval_loss": 6.985621929168701, | |
| "eval_runtime": 427.0575, | |
| "eval_samples_per_second": 10.137, | |
| "eval_steps_per_second": 5.07, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003891050583657588, | |
| "grad_norm": 13.882640838623047, | |
| "learning_rate": 8e-05, | |
| "loss": 29.1269, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00048638132295719845, | |
| "grad_norm": 41.90673065185547, | |
| "learning_rate": 0.0001, | |
| "loss": 32.9532, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005836575875486381, | |
| "grad_norm": 25.500226974487305, | |
| "learning_rate": 0.00012, | |
| "loss": 28.3286, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005836575875486381, | |
| "eval_loss": 6.694687843322754, | |
| "eval_runtime": 432.8707, | |
| "eval_samples_per_second": 10.001, | |
| "eval_steps_per_second": 5.001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006809338521400778, | |
| "grad_norm": 29.363405227661133, | |
| "learning_rate": 0.00014, | |
| "loss": 24.3552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007782101167315176, | |
| "grad_norm": 35.309017181396484, | |
| "learning_rate": 0.00016, | |
| "loss": 25.8133, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008754863813229572, | |
| "grad_norm": 55.91795349121094, | |
| "learning_rate": 0.00018, | |
| "loss": 26.7211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008754863813229572, | |
| "eval_loss": 6.142773628234863, | |
| "eval_runtime": 432.8243, | |
| "eval_samples_per_second": 10.002, | |
| "eval_steps_per_second": 5.002, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009727626459143969, | |
| "grad_norm": 55.8961181640625, | |
| "learning_rate": 0.0002, | |
| "loss": 23.6468, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628749242040320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |