| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.986666666666667, | |
| "eval_steps": 500, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 9.412764922702348, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.5102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 6.313179166401434, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.1989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 5.655906942216565, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.7143, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 7.038149436459667, | |
| "learning_rate": 9.990263847374976e-05, | |
| "loss": 0.9001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 13.082350769847622, | |
| "learning_rate": 9.930902394260747e-05, | |
| "loss": 0.9829, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 5.046437234782843, | |
| "learning_rate": 9.818229479678158e-05, | |
| "loss": 0.9798, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 5.146826578374137, | |
| "learning_rate": 9.653463289927411e-05, | |
| "loss": 1.0628, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 4.011140449496279, | |
| "learning_rate": 9.438385228425938e-05, | |
| "loss": 1.0443, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 10.96171152773486, | |
| "learning_rate": 9.175320655700406e-05, | |
| "loss": 1.0457, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 4.961498008924087, | |
| "learning_rate": 8.86711374827494e-05, | |
| "loss": 1.0249, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 4.6475501141852265, | |
| "learning_rate": 8.517096748273951e-05, | |
| "loss": 1.0873, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 4.428876971621146, | |
| "learning_rate": 8.129053936203687e-05, | |
| "loss": 0.7218, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 5.801138115283359, | |
| "learning_rate": 7.707180716428237e-05, | |
| "loss": 0.6494, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 4.0351599378267595, | |
| "learning_rate": 7.256038257695687e-05, | |
| "loss": 0.6379, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 4.0864268190783894, | |
| "learning_rate": 6.780504179127734e-05, | |
| "loss": 0.6164, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 4.708947394754259, | |
| "learning_rate": 6.28571981484123e-05, | |
| "loss": 0.597, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 4.279448887973702, | |
| "learning_rate": 5.7770346273610254e-05, | |
| "loss": 0.5859, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.92470191003172, | |
| "learning_rate": 5.2599483708099016e-05, | |
| "loss": 0.5793, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 3.4738210484808136, | |
| "learning_rate": 4.740051629190099e-05, | |
| "loss": 0.5843, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 3.8095727115118607, | |
| "learning_rate": 4.2229653726389765e-05, | |
| "loss": 0.4927, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 39.411006077166576, | |
| "learning_rate": 3.714280185158771e-05, | |
| "loss": 0.5614, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 3.0318398508133986, | |
| "learning_rate": 3.219495820872265e-05, | |
| "loss": 0.6168, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 2.323712025359315, | |
| "learning_rate": 2.7439617423043145e-05, | |
| "loss": 0.4263, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 2.2885384111375395, | |
| "learning_rate": 2.2928192835717644e-05, | |
| "loss": 0.2691, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.914625424128763, | |
| "learning_rate": 1.8709460637963123e-05, | |
| "loss": 0.2317, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 1.7713461830093022, | |
| "learning_rate": 1.4829032517260489e-05, | |
| "loss": 0.2562, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.437839693921665, | |
| "learning_rate": 1.132886251725061e-05, | |
| "loss": 0.2132, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 1.8118456334838464, | |
| "learning_rate": 8.246793442995954e-06, | |
| "loss": 0.2589, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 2.5235712198342437, | |
| "learning_rate": 5.616147715740611e-06, | |
| "loss": 0.2305, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.6667275190466975, | |
| "learning_rate": 3.465367100725908e-06, | |
| "loss": 0.2083, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 2.5602982214331, | |
| "learning_rate": 1.8177052032184283e-06, | |
| "loss": 0.212, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 2.356039432068881, | |
| "learning_rate": 6.909760573925561e-07, | |
| "loss": 0.2055, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 1.9207416625625227, | |
| "learning_rate": 9.73615262502503e-08, | |
| "loss": 0.1871, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "step": 336, | |
| "total_flos": 1204578902016.0, | |
| "train_loss": 0.5951760939898945, | |
| "train_runtime": 1003.6822, | |
| "train_samples_per_second": 2.69, | |
| "train_steps_per_second": 0.335 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1204578902016.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |