| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012244648068406767, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.081549356135589e-05, | |
| "eval_loss": 2.077126979827881, | |
| "eval_runtime": 668.1977, | |
| "eval_samples_per_second": 15.439, | |
| "eval_steps_per_second": 7.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012244648068406768, | |
| "grad_norm": 4.9286346435546875, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9894, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024489296136813535, | |
| "grad_norm": 1.1367688179016113, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9179, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003265239484908471, | |
| "eval_loss": 1.7953277826309204, | |
| "eval_runtime": 667.8705, | |
| "eval_samples_per_second": 15.446, | |
| "eval_steps_per_second": 7.723, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000367339442052203, | |
| "grad_norm": 1.081079125404358, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7096, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004897859227362707, | |
| "grad_norm": 1.2086544036865234, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006122324034203384, | |
| "grad_norm": 1.120302438735962, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.7406, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006530478969816942, | |
| "eval_loss": 1.7136527299880981, | |
| "eval_runtime": 667.6475, | |
| "eval_samples_per_second": 15.451, | |
| "eval_steps_per_second": 7.726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000734678884104406, | |
| "grad_norm": 1.010192632675171, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008571253647884737, | |
| "grad_norm": 1.1784299612045288, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.7099, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009795718454725414, | |
| "grad_norm": 1.3243367671966553, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.6013, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009795718454725414, | |
| "eval_loss": 1.684644103050232, | |
| "eval_runtime": 667.3504, | |
| "eval_samples_per_second": 15.458, | |
| "eval_steps_per_second": 7.729, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001102018326156609, | |
| "grad_norm": 1.1877875328063965, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.6743, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0012244648068406767, | |
| "grad_norm": 1.2480648756027222, | |
| "learning_rate": 0.0, | |
| "loss": 1.6012, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 1.150341542313984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |