| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2, | |
| "eval_steps": 25, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 228.72581481933594, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 249.7137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6.804035186767578, | |
| "eval_runtime": 4.0265, | |
| "eval_samples_per_second": 12.418, | |
| "eval_steps_per_second": 3.229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 274.20172119140625, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 218.5379, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 334.215087890625, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 152.1201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 298.2025146484375, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 75.3702, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 146.9689483642578, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 39.0576, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 56.45572280883789, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 26.6338, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 40.98987579345703, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 24.2585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 43.17973327636719, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 23.1042, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 29.856830596923828, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 22.0812, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 18.565689086914062, | |
| "learning_rate": 1e-05, | |
| "loss": 22.2119, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0518209551663104e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |