| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008466002649858829, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.693200529971766e-05, | |
| "eval_loss": 6.939432144165039, | |
| "eval_runtime": 384.3868, | |
| "eval_samples_per_second": 64.695, | |
| "eval_steps_per_second": 32.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.46600264985883e-05, | |
| "grad_norm": 0.2929963171482086, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9387, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001693200529971766, | |
| "grad_norm": 0.27149704098701477, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001693200529971766, | |
| "eval_loss": 6.936197280883789, | |
| "eval_runtime": 402.4358, | |
| "eval_samples_per_second": 61.794, | |
| "eval_steps_per_second": 30.897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002539800794957649, | |
| "grad_norm": 0.28503113985061646, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003386401059943532, | |
| "grad_norm": 0.24860993027687073, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9316, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003386401059943532, | |
| "eval_loss": 6.928938388824463, | |
| "eval_runtime": 310.0666, | |
| "eval_samples_per_second": 80.202, | |
| "eval_steps_per_second": 40.101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00042330013249294147, | |
| "grad_norm": 0.2915782928466797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005079601589915298, | |
| "grad_norm": 0.29080092906951904, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9242, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005079601589915298, | |
| "eval_loss": 6.923147201538086, | |
| "eval_runtime": 292.5271, | |
| "eval_samples_per_second": 85.011, | |
| "eval_steps_per_second": 42.505, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000592620185490118, | |
| "grad_norm": 0.29354530572891235, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9219, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0006772802119887064, | |
| "grad_norm": 0.2872024476528168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.9202, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006772802119887064, | |
| "eval_loss": 6.920102119445801, | |
| "eval_runtime": 332.362, | |
| "eval_samples_per_second": 74.822, | |
| "eval_steps_per_second": 37.411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007619402384872946, | |
| "grad_norm": 0.2954590618610382, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9203, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0008466002649858829, | |
| "grad_norm": 0.3101924657821655, | |
| "learning_rate": 0.0, | |
| "loss": 6.9172, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008466002649858829, | |
| "eval_loss": 6.919541835784912, | |
| "eval_runtime": 339.0118, | |
| "eval_samples_per_second": 73.354, | |
| "eval_steps_per_second": 36.677, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 86350639104.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |