{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.008454872120059184, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001690974424011837, "eval_loss": 4.695179462432861, "eval_runtime": 144.0478, "eval_samples_per_second": 17.286, "eval_steps_per_second": 8.643, "step": 1 }, { "epoch": 0.0008454872120059184, "grad_norm": 7.579517841339111, "learning_rate": 5e-05, "loss": 4.7342, "step": 5 }, { "epoch": 0.0016909744240118367, "grad_norm": 7.856087684631348, "learning_rate": 0.0001, "loss": 3.2303, "step": 10 }, { "epoch": 0.0016909744240118367, "eval_loss": 1.0427312850952148, "eval_runtime": 144.9035, "eval_samples_per_second": 17.184, "eval_steps_per_second": 8.592, "step": 10 }, { "epoch": 0.0025364616360177552, "grad_norm": 2.685682535171509, "learning_rate": 9.619397662556435e-05, "loss": 0.4402, "step": 15 }, { "epoch": 0.0033819488480236735, "grad_norm": 2.484118938446045, "learning_rate": 8.535533905932738e-05, "loss": 0.1726, "step": 20 }, { "epoch": 0.0033819488480236735, "eval_loss": 0.13887104392051697, "eval_runtime": 145.2477, "eval_samples_per_second": 17.143, "eval_steps_per_second": 8.572, "step": 20 }, { "epoch": 0.004227436060029592, "grad_norm": 1.2602101564407349, "learning_rate": 6.91341716182545e-05, "loss": 0.1889, "step": 25 }, { "epoch": 0.0050729232720355105, "grad_norm": 3.597075939178467, "learning_rate": 5e-05, "loss": 0.1737, "step": 30 }, { "epoch": 0.0050729232720355105, "eval_loss": 0.14064188301563263, "eval_runtime": 144.8704, "eval_samples_per_second": 17.188, "eval_steps_per_second": 8.594, "step": 30 }, { "epoch": 0.005918410484041429, "grad_norm": 0.8030089735984802, "learning_rate": 3.086582838174551e-05, "loss": 0.1342, "step": 35 }, { "epoch": 0.006763897696047347, "grad_norm": 1.667202115058899, "learning_rate": 1.4644660940672627e-05, "loss": 0.1783, "step": 40 }, { "epoch": 0.006763897696047347, "eval_loss": 0.1387166827917099, "eval_runtime": 145.4243, "eval_samples_per_second": 17.122, "eval_steps_per_second": 8.561, "step": 40 }, { "epoch": 0.007609384908053266, "grad_norm": 0.30066943168640137, "learning_rate": 3.8060233744356633e-06, "loss": 0.1361, "step": 45 }, { "epoch": 0.008454872120059184, "grad_norm": 2.7212069034576416, "learning_rate": 0.0, "loss": 0.1554, "step": 50 }, { "epoch": 0.008454872120059184, "eval_loss": 0.14785736799240112, "eval_runtime": 145.2718, "eval_samples_per_second": 17.14, "eval_steps_per_second": 8.57, "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": 8143665679564800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }