| { | |
| "best_metric": 6.333486080169678, | |
| "best_model_checkpoint": "./output/checkpoint-150", | |
| "epoch": 0.9036144578313253, | |
| "eval_steps": 150, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.060240963855421686, | |
| "grad_norm": 52.598548889160156, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.4587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12048192771084337, | |
| "grad_norm": 1.3145289421081543, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1245, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 47.875640869140625, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.0925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 25.39703369140625, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1134, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30120481927710846, | |
| "grad_norm": 22.82965660095215, | |
| "learning_rate": 6.25e-05, | |
| "loss": 0.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 0.446526437997818, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.5273, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42168674698795183, | |
| "grad_norm": 50.92262649536133, | |
| "learning_rate": 8.75e-05, | |
| "loss": 0.2283, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 65.35910034179688, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3627, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 8.19798755645752, | |
| "learning_rate": 0.00011250000000000001, | |
| "loss": 0.2596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 141.95716857910156, | |
| "learning_rate": 0.000125, | |
| "loss": 0.6644, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6626506024096386, | |
| "grad_norm": 736.8707885742188, | |
| "learning_rate": 0.00012499871543489787, | |
| "loss": 0.9693, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 249.3212432861328, | |
| "learning_rate": 0.00012499486179239495, | |
| "loss": 1.4457, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7831325301204819, | |
| "grad_norm": 30.746965408325195, | |
| "learning_rate": 0.00012498843923089938, | |
| "loss": 1.4675, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8433734939759037, | |
| "grad_norm": 41.87055587768555, | |
| "learning_rate": 0.0001249794480144175, | |
| "loss": 3.2459, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 64.25176239013672, | |
| "learning_rate": 0.000124967888512543, | |
| "loss": 5.6311, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "eval_loss": 6.333486080169678, | |
| "eval_runtime": 3.9268, | |
| "eval_samples_per_second": 9.422, | |
| "eval_steps_per_second": 9.422, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 31, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 481056683261952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |