{ "best_metric": null, "best_model_checkpoint": null, "epoch": 61.53846153846154, "eval_steps": 500, "global_step": 4000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.5384615384615383, "grad_norm": 28.85655403137207, "learning_rate": 9.9812e-06, "loss": 1.0794, "step": 100 }, { "epoch": 3.076923076923077, "grad_norm": 40.480037689208984, "learning_rate": 9.961400000000001e-06, "loss": 1.1026, "step": 200 }, { "epoch": 4.615384615384615, "grad_norm": 22.348379135131836, "learning_rate": 9.941600000000002e-06, "loss": 1.1211, "step": 300 }, { "epoch": 6.153846153846154, "grad_norm": 49.462806701660156, "learning_rate": 9.921600000000002e-06, "loss": 1.1217, "step": 400 }, { "epoch": 7.6923076923076925, "grad_norm": 37.26523208618164, "learning_rate": 9.901600000000002e-06, "loss": 1.0993, "step": 500 }, { "epoch": 9.23076923076923, "grad_norm": 265.8311767578125, "learning_rate": 9.8816e-06, "loss": 1.1576, "step": 600 }, { "epoch": 10.76923076923077, "grad_norm": 48.439048767089844, "learning_rate": 9.8616e-06, "loss": 1.1029, "step": 700 }, { "epoch": 12.307692307692308, "grad_norm": 200.80213928222656, "learning_rate": 9.8416e-06, "loss": 1.1375, "step": 800 }, { "epoch": 13.846153846153847, "grad_norm": 54.096126556396484, "learning_rate": 9.821600000000001e-06, "loss": 1.1134, "step": 900 }, { "epoch": 15.384615384615385, "grad_norm": 72.55537414550781, "learning_rate": 9.801600000000001e-06, "loss": 1.1364, "step": 1000 }, { "epoch": 16.923076923076923, "grad_norm": 45.86960983276367, "learning_rate": 9.781600000000001e-06, "loss": 1.1259, "step": 1100 }, { "epoch": 18.46153846153846, "grad_norm": 44.21461868286133, "learning_rate": 9.761600000000002e-06, "loss": 1.1144, "step": 1200 }, { "epoch": 20.0, "grad_norm": 49.014503479003906, "learning_rate": 9.741600000000002e-06, "loss": 1.1151, "step": 1300 }, { "epoch": 21.53846153846154, "grad_norm": 62.7434196472168, "learning_rate": 9.7216e-06, "loss": 1.1129, "step": 1400 }, { "epoch": 23.076923076923077, "grad_norm": 48.607032775878906, "learning_rate": 9.7016e-06, "loss": 1.1189, "step": 1500 }, { "epoch": 24.615384615384617, "grad_norm": 43.288368225097656, "learning_rate": 9.6816e-06, "loss": 1.102, "step": 1600 }, { "epoch": 26.153846153846153, "grad_norm": 33.83266067504883, "learning_rate": 9.6616e-06, "loss": 1.1091, "step": 1700 }, { "epoch": 27.692307692307693, "grad_norm": 54.347755432128906, "learning_rate": 9.641600000000001e-06, "loss": 1.1478, "step": 1800 }, { "epoch": 29.23076923076923, "grad_norm": 68.06307220458984, "learning_rate": 9.621600000000001e-06, "loss": 1.1384, "step": 1900 }, { "epoch": 30.76923076923077, "grad_norm": 24.473976135253906, "learning_rate": 9.601600000000001e-06, "loss": 1.1218, "step": 2000 }, { "epoch": 32.30769230769231, "grad_norm": 33.08134460449219, "learning_rate": 9.5818e-06, "loss": 1.0807, "step": 2100 }, { "epoch": 33.84615384615385, "grad_norm": 32.798397064208984, "learning_rate": 9.5618e-06, "loss": 1.1548, "step": 2200 }, { "epoch": 35.38461538461539, "grad_norm": 49.251651763916016, "learning_rate": 9.5418e-06, "loss": 1.1056, "step": 2300 }, { "epoch": 36.92307692307692, "grad_norm": 47.84526062011719, "learning_rate": 9.521800000000001e-06, "loss": 1.169, "step": 2400 }, { "epoch": 38.46153846153846, "grad_norm": 66.61646270751953, "learning_rate": 9.501800000000001e-06, "loss": 1.1505, "step": 2500 }, { "epoch": 40.0, "grad_norm": 84.58892059326172, "learning_rate": 9.481800000000001e-06, "loss": 1.1117, "step": 2600 }, { "epoch": 41.53846153846154, "grad_norm": 86.26738739013672, "learning_rate": 9.461800000000001e-06, "loss": 1.0914, "step": 2700 }, { "epoch": 43.07692307692308, "grad_norm": 106.57470703125, "learning_rate": 9.441800000000002e-06, "loss": 1.1232, "step": 2800 }, { "epoch": 44.61538461538461, "grad_norm": 133.2903289794922, "learning_rate": 9.4218e-06, "loss": 1.1544, "step": 2900 }, { "epoch": 46.15384615384615, "grad_norm": 75.39508819580078, "learning_rate": 9.4018e-06, "loss": 1.1699, "step": 3000 }, { "epoch": 47.69230769230769, "grad_norm": 45.91976547241211, "learning_rate": 9.3818e-06, "loss": 1.1652, "step": 3100 }, { "epoch": 49.23076923076923, "grad_norm": 37.38508605957031, "learning_rate": 9.3618e-06, "loss": 1.1386, "step": 3200 }, { "epoch": 50.76923076923077, "grad_norm": 106.42298126220703, "learning_rate": 9.341800000000001e-06, "loss": 1.0903, "step": 3300 }, { "epoch": 52.30769230769231, "grad_norm": 59.256103515625, "learning_rate": 9.321800000000001e-06, "loss": 1.1266, "step": 3400 }, { "epoch": 53.84615384615385, "grad_norm": 61.493003845214844, "learning_rate": 9.301800000000001e-06, "loss": 1.1047, "step": 3500 }, { "epoch": 55.38461538461539, "grad_norm": 149.27308654785156, "learning_rate": 9.281800000000001e-06, "loss": 1.1132, "step": 3600 }, { "epoch": 56.92307692307692, "grad_norm": 81.58853912353516, "learning_rate": 9.2618e-06, "loss": 1.083, "step": 3700 }, { "epoch": 58.46153846153846, "grad_norm": 39.950843811035156, "learning_rate": 9.2418e-06, "loss": 1.09, "step": 3800 }, { "epoch": 60.0, "grad_norm": 66.99285888671875, "learning_rate": 9.2218e-06, "loss": 1.1161, "step": 3900 }, { "epoch": 61.53846153846154, "grad_norm": 28.769887924194336, "learning_rate": 9.2018e-06, "loss": 1.1061, "step": 4000 } ], "logging_steps": 100, "max_steps": 50000, "num_input_tokens_seen": 0, "num_train_epochs": 770, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.528972664832e+19, "train_batch_size": 8, "trial_name": null, "trial_params": null }