| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 0.09189555048942566, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.4532, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 0.2126905471086502, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.4489, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.291930615901947, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3832, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 0.387766569852829, | |
| "learning_rate": 1.9929278846732883e-05, | |
| "loss": 2.3484, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 0.44600173830986023, | |
| "learning_rate": 1.9718115683235418e-05, | |
| "loss": 2.2994, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 0.5669222474098206, | |
| "learning_rate": 1.936949724999762e-05, | |
| "loss": 2.2533, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.5654759407043457, | |
| "learning_rate": 1.8888354486549238e-05, | |
| "loss": 2.2411, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 0.598199188709259, | |
| "learning_rate": 1.8281492787113707e-05, | |
| "loss": 2.2293, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.7203428745269775, | |
| "learning_rate": 1.7557495743542586e-05, | |
| "loss": 2.2373, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 0.6085770130157471, | |
| "learning_rate": 1.6726603737012527e-05, | |
| "loss": 2.1998, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3741496598639456, | |
| "grad_norm": 0.6738985180854797, | |
| "learning_rate": 1.5800569095711983e-05, | |
| "loss": 2.1795, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.8266023993492126, | |
| "learning_rate": 1.479248986720057e-05, | |
| "loss": 2.1566, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4421768707482993, | |
| "grad_norm": 0.7727716565132141, | |
| "learning_rate": 1.3716624556603275e-05, | |
| "loss": 2.1502, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.7054930329322815, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 2.1539, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 0.9656850099563599, | |
| "learning_rate": 1.1423148382732854e-05, | |
| "loss": 2.1572, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 0.8141266107559204, | |
| "learning_rate": 1.0237976975461074e-05, | |
| "loss": 2.1334, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5782312925170068, | |
| "grad_norm": 0.9043893218040466, | |
| "learning_rate": 9.049439566958176e-06, | |
| "loss": 2.1557, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.720611035823822, | |
| "learning_rate": 7.874347104470234e-06, | |
| "loss": 2.1538, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6462585034013606, | |
| "grad_norm": 0.7873674631118774, | |
| "learning_rate": 6.729320366825785e-06, | |
| "loss": 2.1355, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 0.7871781587600708, | |
| "learning_rate": 5.630554876306407e-06, | |
| "loss": 2.1427, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.9765840768814087, | |
| "learning_rate": 4.593591825444028e-06, | |
| "loss": 2.1339, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7482993197278912, | |
| "grad_norm": 0.7794718742370605, | |
| "learning_rate": 3.633098258809119e-06, | |
| "loss": 2.1044, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.782312925170068, | |
| "grad_norm": 0.8481063842773438, | |
| "learning_rate": 2.7626596189492983e-06, | |
| "loss": 2.135, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.8674197196960449, | |
| "learning_rate": 1.994587590756397e-06, | |
| "loss": 2.0957, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.8503401360544217, | |
| "grad_norm": 0.7360070943832397, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 2.1157, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8843537414965986, | |
| "grad_norm": 0.8483572602272034, | |
| "learning_rate": 8.073969641833446e-07, | |
| "loss": 2.1549, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 0.8476448059082031, | |
| "learning_rate": 4.0507026385502747e-07, | |
| "loss": 2.1144, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.8742887377738953, | |
| "learning_rate": 1.3845646281813508e-07, | |
| "loss": 2.1354, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.9863945578231292, | |
| "grad_norm": 0.8896283507347107, | |
| "learning_rate": 1.1326608169920373e-08, | |
| "loss": 2.1175, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2940, | |
| "total_flos": 5.34201935659008e+16, | |
| "train_loss": 2.1967257285604673, | |
| "train_runtime": 922.9625, | |
| "train_samples_per_second": 6.37, | |
| "train_steps_per_second": 3.185 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2940, | |
| "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": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.34201935659008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |