| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.412280701754386, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.973626373626374e-05, | |
| "loss": 1.622, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.24010217113665389, | |
| "eval_loss": 1.6581733226776123, | |
| "eval_runtime": 381.1384, | |
| "eval_samples_per_second": 4.109, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.9406593406593407e-05, | |
| "loss": 1.3721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.2835249042145594, | |
| "eval_loss": 1.9170576333999634, | |
| "eval_runtime": 378.5115, | |
| "eval_samples_per_second": 4.137, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.907692307692308e-05, | |
| "loss": 1.1269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.36845466155810985, | |
| "eval_loss": 1.7032861709594727, | |
| "eval_runtime": 385.3173, | |
| "eval_samples_per_second": 4.064, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8747252747252748e-05, | |
| "loss": 0.9152, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.388250319284802, | |
| "eval_loss": 1.7423878908157349, | |
| "eval_runtime": 388.0594, | |
| "eval_samples_per_second": 4.035, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.8417582417582416e-05, | |
| "loss": 0.732, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.4616858237547893, | |
| "eval_loss": 1.5253428220748901, | |
| "eval_runtime": 386.9842, | |
| "eval_samples_per_second": 4.047, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.8087912087912088e-05, | |
| "loss": 0.684, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.4367816091954023, | |
| "eval_loss": 1.6441736221313477, | |
| "eval_runtime": 388.1257, | |
| "eval_samples_per_second": 4.035, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.775824175824176e-05, | |
| "loss": 0.5538, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.5108556832694764, | |
| "eval_loss": 1.450364351272583, | |
| "eval_runtime": 389.4611, | |
| "eval_samples_per_second": 4.021, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.7428571428571428e-05, | |
| "loss": 0.5425, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.49936143039591313, | |
| "eval_loss": 1.4108269214630127, | |
| "eval_runtime": 389.7612, | |
| "eval_samples_per_second": 4.018, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.70989010989011e-05, | |
| "loss": 0.514, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5057471264367817, | |
| "eval_loss": 1.4206087589263916, | |
| "eval_runtime": 396.4756, | |
| "eval_samples_per_second": 3.95, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.6769230769230772e-05, | |
| "loss": 0.3068, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.5159642401021711, | |
| "eval_loss": 1.6294729709625244, | |
| "eval_runtime": 394.6782, | |
| "eval_samples_per_second": 3.968, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.643956043956044e-05, | |
| "loss": 0.2865, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.5076628352490421, | |
| "eval_loss": 1.733625888824463, | |
| "eval_runtime": 393.6145, | |
| "eval_samples_per_second": 3.979, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.6109890109890112e-05, | |
| "loss": 0.301, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_accuracy": 0.6277139208173691, | |
| "eval_loss": 1.2089332342147827, | |
| "eval_runtime": 389.8374, | |
| "eval_samples_per_second": 4.017, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.578021978021978e-05, | |
| "loss": 0.2517, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.5983397190293742, | |
| "eval_loss": 1.3427765369415283, | |
| "eval_runtime": 388.9975, | |
| "eval_samples_per_second": 4.026, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.545054945054945e-05, | |
| "loss": 0.2819, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.5600255427841635, | |
| "eval_loss": 1.5083413124084473, | |
| "eval_runtime": 390.3746, | |
| "eval_samples_per_second": 4.012, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.512087912087912e-05, | |
| "loss": 0.2706, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_accuracy": 0.6047254150702427, | |
| "eval_loss": 1.5413047075271606, | |
| "eval_runtime": 389.1952, | |
| "eval_samples_per_second": 4.024, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.479120879120879e-05, | |
| "loss": 0.1991, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.598978288633461, | |
| "eval_loss": 1.5572402477264404, | |
| "eval_runtime": 389.1243, | |
| "eval_samples_per_second": 4.024, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.446153846153846e-05, | |
| "loss": 0.2726, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.6021711366538953, | |
| "eval_loss": 1.4013671875, | |
| "eval_runtime": 392.7301, | |
| "eval_samples_per_second": 3.987, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.4131868131868133e-05, | |
| "loss": 0.2015, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.5676883780332056, | |
| "eval_loss": 2.248255729675293, | |
| "eval_runtime": 389.7999, | |
| "eval_samples_per_second": 4.017, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.38021978021978e-05, | |
| "loss": 0.173, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_accuracy": 0.644316730523627, | |
| "eval_loss": 1.5393086671829224, | |
| "eval_runtime": 390.3149, | |
| "eval_samples_per_second": 4.012, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.3472527472527474e-05, | |
| "loss": 0.1177, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.6028097062579821, | |
| "eval_loss": 1.9018601179122925, | |
| "eval_runtime": 390.5708, | |
| "eval_samples_per_second": 4.01, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.3142857142857145e-05, | |
| "loss": 0.0907, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_accuracy": 0.6194125159642401, | |
| "eval_loss": 1.8655920028686523, | |
| "eval_runtime": 392.1244, | |
| "eval_samples_per_second": 3.994, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.2813186813186814e-05, | |
| "loss": 0.1878, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.6296296296296297, | |
| "eval_loss": 1.998379111289978, | |
| "eval_runtime": 390.0846, | |
| "eval_samples_per_second": 4.015, | |
| "step": 2200 | |
| } | |
| ], | |
| "max_steps": 9120, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.137068831744e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |