| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 100, |
| "global_step": 169, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.029585798816568046, |
| "grad_norm": 0.07426696918416174, |
| "learning_rate": 5.882352941176471e-06, |
| "loss": 0.7515, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05917159763313609, |
| "grad_norm": 0.08040276233943516, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 0.755, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08875739644970414, |
| "grad_norm": 0.09568613129719651, |
| "learning_rate": 1.7647058823529414e-05, |
| "loss": 0.7553, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.11834319526627218, |
| "grad_norm": 0.11073070319325445, |
| "learning_rate": 1.9980782984658682e-05, |
| "loss": 0.7481, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.14792899408284024, |
| "grad_norm": 0.1085253681695973, |
| "learning_rate": 1.9863613034027224e-05, |
| "loss": 0.742, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17751479289940827, |
| "grad_norm": 0.10317427695342557, |
| "learning_rate": 1.9641197940012136e-05, |
| "loss": 0.7317, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.20710059171597633, |
| "grad_norm": 0.1095919075191608, |
| "learning_rate": 1.9315910880512792e-05, |
| "loss": 0.7394, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23668639053254437, |
| "grad_norm": 0.10584984713775991, |
| "learning_rate": 1.8891222681391853e-05, |
| "loss": 0.7445, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.26627218934911245, |
| "grad_norm": 0.1052036771871902, |
| "learning_rate": 1.8371664782625287e-05, |
| "loss": 0.7382, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2958579881656805, |
| "grad_norm": 0.10185995684228026, |
| "learning_rate": 1.7762780887657576e-05, |
| "loss": 0.7327, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3254437869822485, |
| "grad_norm": 0.11605723315982408, |
| "learning_rate": 1.7071067811865477e-05, |
| "loss": 0.7265, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.35502958579881655, |
| "grad_norm": 0.09496481679546319, |
| "learning_rate": 1.6303906161279554e-05, |
| "loss": 0.7404, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 0.09399123086469602, |
| "learning_rate": 1.5469481581224274e-05, |
| "loss": 0.7183, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.41420118343195267, |
| "grad_norm": 0.09454325149914487, |
| "learning_rate": 1.4576697415156818e-05, |
| "loss": 0.7239, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.4437869822485207, |
| "grad_norm": 0.09665316804682329, |
| "learning_rate": 1.3635079705638298e-05, |
| "loss": 0.7374, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.47337278106508873, |
| "grad_norm": 0.0931576465014015, |
| "learning_rate": 1.2654675551080724e-05, |
| "loss": 0.7206, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5029585798816568, |
| "grad_norm": 0.09445002041196521, |
| "learning_rate": 1.164594590280734e-05, |
| "loss": 0.727, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5325443786982249, |
| "grad_norm": 0.08585910164532164, |
| "learning_rate": 1.0619653946285948e-05, |
| "loss": 0.7287, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5621301775147929, |
| "grad_norm": 0.0926566404725236, |
| "learning_rate": 9.586750257511868e-06, |
| "loss": 0.7378, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.591715976331361, |
| "grad_norm": 0.08672021822123627, |
| "learning_rate": 8.558255959926533e-06, |
| "loss": 0.7164, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.591715976331361, |
| "eval_loss": 0.7641129493713379, |
| "eval_runtime": 1.9602, |
| "eval_samples_per_second": 65.298, |
| "eval_steps_per_second": 2.041, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.621301775147929, |
| "grad_norm": 0.08622854416758327, |
| "learning_rate": 7.545145128592009e-06, |
| "loss": 0.7216, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.650887573964497, |
| "grad_norm": 0.08204894186576381, |
| "learning_rate": 6.558227696373617e-06, |
| "loss": 0.7346, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6804733727810651, |
| "grad_norm": 0.08097299352958673, |
| "learning_rate": 5.608034111526298e-06, |
| "loss": 0.73, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.7100591715976331, |
| "grad_norm": 0.07682552342075682, |
| "learning_rate": 4.704702977392914e-06, |
| "loss": 0.7212, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7396449704142012, |
| "grad_norm": 0.08086018117086849, |
| "learning_rate": 3.857872873103322e-06, |
| "loss": 0.7248, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.07606171025014277, |
| "learning_rate": 3.0765795095517026e-06, |
| "loss": 0.728, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7988165680473372, |
| "grad_norm": 0.08257799296717885, |
| "learning_rate": 2.369159318001937e-06, |
| "loss": 0.7323, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.8284023668639053, |
| "grad_norm": 0.07889584661038457, |
| "learning_rate": 1.743160500034443e-06, |
| "loss": 0.7251, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8579881656804734, |
| "grad_norm": 0.08171166394737774, |
| "learning_rate": 1.2052624879351105e-06, |
| "loss": 0.7324, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8875739644970414, |
| "grad_norm": 0.07432343760979292, |
| "learning_rate": 7.612046748871327e-07, |
| "loss": 0.743, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.9171597633136095, |
| "grad_norm": 0.07790477411393834, |
| "learning_rate": 4.1572517541747294e-07, |
| "loss": 0.7386, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.9467455621301775, |
| "grad_norm": 0.07339780497225679, |
| "learning_rate": 1.7251026952640583e-07, |
| "loss": 0.7383, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9763313609467456, |
| "grad_norm": 0.07176968893681754, |
| "learning_rate": 3.4155069933301535e-08, |
| "loss": 0.7225, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 169, |
| "total_flos": 76916824473600.0, |
| "train_loss": 0.7337305870281874, |
| "train_runtime": 1235.0855, |
| "train_samples_per_second": 17.497, |
| "train_steps_per_second": 0.137 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 169, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 76916824473600.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
