| { | |
| "best_metric": 1.675691843032837, | |
| "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-1250", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 1875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.3769932985305786, | |
| "learning_rate": 8.771929824561403e-05, | |
| "loss": 2.0308, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.740922212600708, | |
| "eval_runtime": 4.9828, | |
| "eval_samples_per_second": 20.069, | |
| "eval_steps_per_second": 5.017, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.283903956413269, | |
| "learning_rate": 9.986202859963424e-05, | |
| "loss": 1.7637, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7477470636367798, | |
| "eval_runtime": 4.9882, | |
| "eval_samples_per_second": 20.047, | |
| "eval_steps_per_second": 5.012, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.5214710235595703, | |
| "learning_rate": 9.935570765205927e-05, | |
| "loss": 1.7386, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.69858980178833, | |
| "eval_runtime": 4.988, | |
| "eval_samples_per_second": 20.048, | |
| "eval_steps_per_second": 5.012, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.9870548248291016, | |
| "learning_rate": 9.848115669304158e-05, | |
| "loss": 1.7239, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.7267831563949585, | |
| "eval_runtime": 4.9814, | |
| "eval_samples_per_second": 20.075, | |
| "eval_steps_per_second": 5.019, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.197464108467102, | |
| "learning_rate": 9.724490051829306e-05, | |
| "loss": 1.7004, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.7107303142547607, | |
| "eval_runtime": 4.9953, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 5.005, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.062972903251648, | |
| "learning_rate": 9.565616251143094e-05, | |
| "loss": 1.7174, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.7235748767852783, | |
| "eval_runtime": 4.9773, | |
| "eval_samples_per_second": 20.091, | |
| "eval_steps_per_second": 5.023, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.8863743543624878, | |
| "learning_rate": 9.372679583072762e-05, | |
| "loss": 1.7156, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.705377459526062, | |
| "eval_runtime": 4.9832, | |
| "eval_samples_per_second": 20.067, | |
| "eval_steps_per_second": 5.017, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.1850109100341797, | |
| "learning_rate": 9.147119497580047e-05, | |
| "loss": 1.7013, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.7099401950836182, | |
| "eval_runtime": 4.9875, | |
| "eval_samples_per_second": 20.05, | |
| "eval_steps_per_second": 5.013, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.9806734323501587, | |
| "learning_rate": 8.890618839401924e-05, | |
| "loss": 1.6887, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.6758233308792114, | |
| "eval_runtime": 4.9812, | |
| "eval_samples_per_second": 20.075, | |
| "eval_steps_per_second": 5.019, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.8731200695037842, | |
| "learning_rate": 8.605091292786664e-05, | |
| "loss": 1.6963, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.6987907886505127, | |
| "eval_runtime": 4.9844, | |
| "eval_samples_per_second": 20.063, | |
| "eval_steps_per_second": 5.016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.2332689762115479, | |
| "learning_rate": 8.292667103996738e-05, | |
| "loss": 1.7313, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.7032952308654785, | |
| "eval_runtime": 4.9781, | |
| "eval_samples_per_second": 20.088, | |
| "eval_steps_per_second": 5.022, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.2375348806381226, | |
| "learning_rate": 7.955677188099235e-05, | |
| "loss": 1.6986, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.6838198900222778, | |
| "eval_runtime": 4.9789, | |
| "eval_samples_per_second": 20.085, | |
| "eval_steps_per_second": 5.021, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 1.6269843578338623, | |
| "learning_rate": 7.59663573861888e-05, | |
| "loss": 1.6478, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.717869520187378, | |
| "eval_runtime": 4.9837, | |
| "eval_samples_per_second": 20.065, | |
| "eval_steps_per_second": 5.016, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.6488033533096313, | |
| "learning_rate": 7.218221469798465e-05, | |
| "loss": 1.6154, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.671476125717163, | |
| "eval_runtime": 5.0061, | |
| "eval_samples_per_second": 19.976, | |
| "eval_steps_per_second": 4.994, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.118487596511841, | |
| "learning_rate": 6.823257631413276e-05, | |
| "loss": 1.5951, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.6910121440887451, | |
| "eval_runtime": 4.9788, | |
| "eval_samples_per_second": 20.085, | |
| "eval_steps_per_second": 5.021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.9570444822311401, | |
| "learning_rate": 6.414690945243768e-05, | |
| "loss": 1.6109, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.7327255010604858, | |
| "eval_runtime": 4.9795, | |
| "eval_samples_per_second": 20.082, | |
| "eval_steps_per_second": 5.021, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 1.9022583961486816, | |
| "learning_rate": 5.9955696203559285e-05, | |
| "loss": 1.615, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "eval_loss": 1.7244207859039307, | |
| "eval_runtime": 4.9869, | |
| "eval_samples_per_second": 20.052, | |
| "eval_steps_per_second": 5.013, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.445749044418335, | |
| "learning_rate": 5.5690206112115884e-05, | |
| "loss": 1.6122, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.689263939857483, | |
| "eval_runtime": 4.9757, | |
| "eval_samples_per_second": 20.098, | |
| "eval_steps_per_second": 5.024, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.5496785640716553, | |
| "learning_rate": 5.1382262882799395e-05, | |
| "loss": 1.6248, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.6721502542495728, | |
| "eval_runtime": 4.9817, | |
| "eval_samples_per_second": 20.073, | |
| "eval_steps_per_second": 5.018, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.7256929874420166, | |
| "learning_rate": 4.706400695204749e-05, | |
| "loss": 1.5938, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.698430061340332, | |
| "eval_runtime": 4.9786, | |
| "eval_samples_per_second": 20.086, | |
| "eval_steps_per_second": 5.021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 2.525702714920044, | |
| "learning_rate": 4.276765569666291e-05, | |
| "loss": 1.616, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "eval_loss": 1.6906436681747437, | |
| "eval_runtime": 4.9808, | |
| "eval_samples_per_second": 20.077, | |
| "eval_steps_per_second": 5.019, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 2.1740636825561523, | |
| "learning_rate": 3.8525263068401055e-05, | |
| "loss": 1.5903, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.6799463033676147, | |
| "eval_runtime": 4.9781, | |
| "eval_samples_per_second": 20.088, | |
| "eval_steps_per_second": 5.022, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 2.1382858753204346, | |
| "learning_rate": 3.436848044782893e-05, | |
| "loss": 1.583, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "eval_loss": 1.6741628646850586, | |
| "eval_runtime": 4.9792, | |
| "eval_samples_per_second": 20.084, | |
| "eval_steps_per_second": 5.021, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.8631138801574707, | |
| "learning_rate": 3.032832050166239e-05, | |
| "loss": 1.5876, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.6653131246566772, | |
| "eval_runtime": 4.9832, | |
| "eval_samples_per_second": 20.067, | |
| "eval_steps_per_second": 5.017, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.0618934631347656, | |
| "learning_rate": 2.6434925805380144e-05, | |
| "loss": 1.5982, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.675691843032837, | |
| "eval_runtime": 4.9832, | |
| "eval_samples_per_second": 20.067, | |
| "eval_steps_per_second": 5.017, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 2.440321207046509, | |
| "learning_rate": 2.2717343957360653e-05, | |
| "loss": 1.4717, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 1.7430232763290405, | |
| "eval_runtime": 4.9759, | |
| "eval_samples_per_second": 20.097, | |
| "eval_steps_per_second": 5.024, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 3.0594778060913086, | |
| "learning_rate": 1.9203310862356577e-05, | |
| "loss": 1.4536, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.765580177307129, | |
| "eval_runtime": 4.9891, | |
| "eval_samples_per_second": 20.044, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 3.2999825477600098, | |
| "learning_rate": 1.5919043801171672e-05, | |
| "loss": 1.4503, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 1.7877963781356812, | |
| "eval_runtime": 4.98, | |
| "eval_samples_per_second": 20.08, | |
| "eval_steps_per_second": 5.02, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 4.290762901306152, | |
| "learning_rate": 1.288904583039358e-05, | |
| "loss": 1.4655, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.7701205015182495, | |
| "eval_runtime": 4.986, | |
| "eval_samples_per_second": 20.056, | |
| "eval_steps_per_second": 5.014, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 3.0238780975341797, | |
| "learning_rate": 1.013592297150449e-05, | |
| "loss": 1.4481, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.7533233165740967, | |
| "eval_runtime": 4.9911, | |
| "eval_samples_per_second": 20.036, | |
| "eval_steps_per_second": 5.009, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 3.3997039794921875, | |
| "learning_rate": 7.680215553274045e-06, | |
| "loss": 1.4335, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 1.7479755878448486, | |
| "eval_runtime": 4.9816, | |
| "eval_samples_per_second": 20.074, | |
| "eval_steps_per_second": 5.018, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 4.031099319458008, | |
| "learning_rate": 5.5402449657446956e-06, | |
| "loss": 1.4505, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.7693780660629272, | |
| "eval_runtime": 4.9807, | |
| "eval_samples_per_second": 20.078, | |
| "eval_steps_per_second": 5.019, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 4.104003429412842, | |
| "learning_rate": 3.731976969137929e-06, | |
| "loss": 1.4537, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 1.7657314538955688, | |
| "eval_runtime": 4.9778, | |
| "eval_samples_per_second": 20.089, | |
| "eval_steps_per_second": 5.022, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 2.632106304168701, | |
| "learning_rate": 2.268902577497639e-06, | |
| "loss": 1.4496, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "eval_loss": 1.7661254405975342, | |
| "eval_runtime": 4.9885, | |
| "eval_samples_per_second": 20.046, | |
| "eval_steps_per_second": 5.012, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 2.8151047229766846, | |
| "learning_rate": 1.1619374057669662e-06, | |
| "loss": 1.4586, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.7688201665878296, | |
| "eval_runtime": 4.9887, | |
| "eval_samples_per_second": 20.045, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 3.2328884601593018, | |
| "learning_rate": 4.1934023124329257e-07, | |
| "loss": 1.4583, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.7641412019729614, | |
| "eval_runtime": 4.9803, | |
| "eval_samples_per_second": 20.079, | |
| "eval_steps_per_second": 5.02, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 4.39493465423584, | |
| "learning_rate": 4.665137700333166e-08, | |
| "loss": 1.4495, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 1.765012502670288, | |
| "eval_runtime": 4.9788, | |
| "eval_samples_per_second": 20.085, | |
| "eval_steps_per_second": 5.021, | |
| "step": 1850 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.819416637396746e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |