| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.974958263772955, | |
| "eval_steps": 10, | |
| "global_step": 745, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3217, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.4901315789473684, | |
| "eval_loss": 0.7262606620788574, | |
| "eval_runtime": 25.3718, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.995, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3e-05, | |
| "loss": 0.56, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.5526315789473685, | |
| "eval_loss": 0.6898001432418823, | |
| "eval_runtime": 25.3761, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5281, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5888157894736842, | |
| "eval_loss": 0.6465093493461609, | |
| "eval_runtime": 25.3947, | |
| "eval_samples_per_second": 11.971, | |
| "eval_steps_per_second": 2.993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3e-05, | |
| "loss": 0.994, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.5986842105263158, | |
| "eval_loss": 0.7351367473602295, | |
| "eval_runtime": 25.4621, | |
| "eval_samples_per_second": 11.939, | |
| "eval_steps_per_second": 2.985, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.6118421052631579, | |
| "eval_loss": 0.6004362106323242, | |
| "eval_runtime": 25.4138, | |
| "eval_samples_per_second": 11.962, | |
| "eval_steps_per_second": 2.991, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4732, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.6348684210526315, | |
| "eval_loss": 0.5782976746559143, | |
| "eval_runtime": 25.369, | |
| "eval_samples_per_second": 11.983, | |
| "eval_steps_per_second": 2.996, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4466, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.6414473684210527, | |
| "eval_loss": 0.5713546872138977, | |
| "eval_runtime": 25.3858, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8737, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.618421052631579, | |
| "eval_loss": 0.567269504070282, | |
| "eval_runtime": 25.3639, | |
| "eval_samples_per_second": 11.986, | |
| "eval_steps_per_second": 2.996, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4471, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.6282894736842105, | |
| "eval_loss": 0.5630530118942261, | |
| "eval_runtime": 25.3754, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.46, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.6348684210526315, | |
| "eval_loss": 0.5503756999969482, | |
| "eval_runtime": 25.3686, | |
| "eval_samples_per_second": 11.983, | |
| "eval_steps_per_second": 2.996, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3294, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.625, | |
| "eval_loss": 0.6009898781776428, | |
| "eval_runtime": 25.3647, | |
| "eval_samples_per_second": 11.985, | |
| "eval_steps_per_second": 2.996, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6526, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.6282894736842105, | |
| "eval_loss": 0.5730816721916199, | |
| "eval_runtime": 25.3832, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 2.994, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3712, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.6447368421052632, | |
| "eval_loss": 0.5378755331039429, | |
| "eval_runtime": 25.3825, | |
| "eval_samples_per_second": 11.977, | |
| "eval_steps_per_second": 2.994, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3341, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.6282894736842105, | |
| "eval_loss": 0.5408769249916077, | |
| "eval_runtime": 25.3787, | |
| "eval_samples_per_second": 11.979, | |
| "eval_steps_per_second": 2.995, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.552, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6381578947368421, | |
| "eval_loss": 0.5310616493225098, | |
| "eval_runtime": 25.4512, | |
| "eval_samples_per_second": 11.944, | |
| "eval_steps_per_second": 2.986, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4681, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.6414473684210527, | |
| "eval_loss": 0.5371212959289551, | |
| "eval_runtime": 25.3633, | |
| "eval_samples_per_second": 11.986, | |
| "eval_steps_per_second": 2.996, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3119, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.6282894736842105, | |
| "eval_loss": 0.6171860694885254, | |
| "eval_runtime": 25.3622, | |
| "eval_samples_per_second": 11.986, | |
| "eval_steps_per_second": 2.997, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3082, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.5360857844352722, | |
| "eval_runtime": 25.3868, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5217, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.625, | |
| "eval_loss": 0.5467653870582581, | |
| "eval_runtime": 25.3846, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 2.994, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3888, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_accuracy": 0.631578947368421, | |
| "eval_loss": 0.5891463756561279, | |
| "eval_runtime": 25.374, | |
| "eval_samples_per_second": 11.981, | |
| "eval_steps_per_second": 2.995, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2841, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.6282894736842105, | |
| "eval_loss": 0.5428625345230103, | |
| "eval_runtime": 25.3734, | |
| "eval_samples_per_second": 11.981, | |
| "eval_steps_per_second": 2.995, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2728, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_accuracy": 0.6381578947368421, | |
| "eval_loss": 0.5246651768684387, | |
| "eval_runtime": 25.3858, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5563, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.5003584027290344, | |
| "eval_runtime": 25.3763, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2862, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 0.4741169810295105, | |
| "eval_runtime": 25.3852, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2289, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.5441343188285828, | |
| "eval_runtime": 25.3897, | |
| "eval_samples_per_second": 11.973, | |
| "eval_steps_per_second": 2.993, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2481, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.5170696377754211, | |
| "eval_runtime": 25.3747, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3e-05, | |
| "loss": 0.329, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 0.5371391177177429, | |
| "eval_runtime": 25.3708, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.996, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1741, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6677631578947368, | |
| "eval_loss": 0.5411613583564758, | |
| "eval_runtime": 25.3792, | |
| "eval_samples_per_second": 11.978, | |
| "eval_steps_per_second": 2.995, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2888, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.6710526315789473, | |
| "eval_loss": 0.5130823850631714, | |
| "eval_runtime": 25.3665, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 2.996, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4157, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6447368421052632, | |
| "eval_loss": 0.45547178387641907, | |
| "eval_runtime": 25.356, | |
| "eval_samples_per_second": 11.989, | |
| "eval_steps_per_second": 2.997, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1982, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.6611842105263158, | |
| "eval_loss": 0.5670450329780579, | |
| "eval_runtime": 25.3778, | |
| "eval_samples_per_second": 11.979, | |
| "eval_steps_per_second": 2.995, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3e-05, | |
| "loss": 0.106, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.6677631578947368, | |
| "eval_loss": 0.7942893505096436, | |
| "eval_runtime": 25.3984, | |
| "eval_samples_per_second": 11.969, | |
| "eval_steps_per_second": 2.992, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1718, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.6644736842105263, | |
| "eval_loss": 0.7496399879455566, | |
| "eval_runtime": 25.3753, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3e-05, | |
| "loss": 0.214, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.6842105263157895, | |
| "eval_loss": 0.626396656036377, | |
| "eval_runtime": 25.3727, | |
| "eval_samples_per_second": 11.981, | |
| "eval_steps_per_second": 2.995, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1571, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_accuracy": 0.631578947368421, | |
| "eval_loss": 0.6138848066329956, | |
| "eval_runtime": 25.3708, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.996, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1432, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.6842105263157895, | |
| "eval_loss": 0.6198970675468445, | |
| "eval_runtime": 25.3819, | |
| "eval_samples_per_second": 11.977, | |
| "eval_steps_per_second": 2.994, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1038, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_accuracy": 0.6973684210526315, | |
| "eval_loss": 0.636822521686554, | |
| "eval_runtime": 25.4286, | |
| "eval_samples_per_second": 11.955, | |
| "eval_steps_per_second": 2.989, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1728, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_accuracy": 0.6677631578947368, | |
| "eval_loss": 0.7889474630355835, | |
| "eval_runtime": 25.3888, | |
| "eval_samples_per_second": 11.974, | |
| "eval_steps_per_second": 2.993, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.14, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 0.795179545879364, | |
| "eval_runtime": 25.3862, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1522, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_accuracy": 0.6578947368421053, | |
| "eval_loss": 0.7745038866996765, | |
| "eval_runtime": 25.3703, | |
| "eval_samples_per_second": 11.983, | |
| "eval_steps_per_second": 2.996, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1345, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.7230806946754456, | |
| "eval_runtime": 25.3678, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 2.996, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1587, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_accuracy": 0.6480263157894737, | |
| "eval_loss": 0.7153956890106201, | |
| "eval_runtime": 25.3506, | |
| "eval_samples_per_second": 11.992, | |
| "eval_steps_per_second": 2.998, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1391, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.6923157572746277, | |
| "eval_runtime": 25.3652, | |
| "eval_samples_per_second": 11.985, | |
| "eval_steps_per_second": 2.996, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3e-05, | |
| "loss": 0.129, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.6710526315789473, | |
| "eval_loss": 0.6483842730522156, | |
| "eval_runtime": 25.3639, | |
| "eval_samples_per_second": 11.986, | |
| "eval_steps_per_second": 2.996, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2092, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.6743421052631579, | |
| "eval_loss": 0.5821840167045593, | |
| "eval_runtime": 25.3814, | |
| "eval_samples_per_second": 11.977, | |
| "eval_steps_per_second": 2.994, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3e-05, | |
| "loss": 0.015, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.6578947368421053, | |
| "eval_loss": 1.1217145919799805, | |
| "eval_runtime": 25.3698, | |
| "eval_samples_per_second": 11.983, | |
| "eval_steps_per_second": 2.996, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 3e-05, | |
| "loss": 0.051, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_accuracy": 0.6480263157894737, | |
| "eval_loss": 1.5789867639541626, | |
| "eval_runtime": 25.3704, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.996, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0999, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_accuracy": 0.6677631578947368, | |
| "eval_loss": 1.5168237686157227, | |
| "eval_runtime": 25.3794, | |
| "eval_samples_per_second": 11.978, | |
| "eval_steps_per_second": 2.995, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1776, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_accuracy": 0.6875, | |
| "eval_loss": 1.2342281341552734, | |
| "eval_runtime": 25.3944, | |
| "eval_samples_per_second": 11.971, | |
| "eval_steps_per_second": 2.993, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0612, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "eval_accuracy": 0.6973684210526315, | |
| "eval_loss": 1.0370548963546753, | |
| "eval_runtime": 25.385, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 2.994, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0858, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_accuracy": 0.6776315789473685, | |
| "eval_loss": 1.0277096033096313, | |
| "eval_runtime": 25.386, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0316, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_accuracy": 0.680921052631579, | |
| "eval_loss": 1.0386649370193481, | |
| "eval_runtime": 25.3706, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.996, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1899, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_accuracy": 0.6907894736842105, | |
| "eval_loss": 0.8184946775436401, | |
| "eval_runtime": 25.3771, | |
| "eval_samples_per_second": 11.979, | |
| "eval_steps_per_second": 2.995, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1517, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_accuracy": 0.6842105263157895, | |
| "eval_loss": 0.7053664922714233, | |
| "eval_runtime": 25.3758, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0324, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_accuracy": 0.6842105263157895, | |
| "eval_loss": 0.8504552245140076, | |
| "eval_runtime": 25.3714, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.995, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0646, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.6611842105263158, | |
| "eval_loss": 1.0056827068328857, | |
| "eval_runtime": 25.3614, | |
| "eval_samples_per_second": 11.987, | |
| "eval_steps_per_second": 2.997, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1038, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_accuracy": 0.6644736842105263, | |
| "eval_loss": 1.0026819705963135, | |
| "eval_runtime": 25.376, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0844, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.9926165342330933, | |
| "eval_runtime": 25.3651, | |
| "eval_samples_per_second": 11.985, | |
| "eval_steps_per_second": 2.996, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0986, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.6578947368421053, | |
| "eval_loss": 0.9245979189872742, | |
| "eval_runtime": 25.3574, | |
| "eval_samples_per_second": 11.989, | |
| "eval_steps_per_second": 2.997, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0627, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 0.8538947105407715, | |
| "eval_runtime": 25.3724, | |
| "eval_samples_per_second": 11.982, | |
| "eval_steps_per_second": 2.995, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0513, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_accuracy": 0.6513157894736842, | |
| "eval_loss": 0.924721896648407, | |
| "eval_runtime": 25.4077, | |
| "eval_samples_per_second": 11.965, | |
| "eval_steps_per_second": 2.991, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0484, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 1.112806797027588, | |
| "eval_runtime": 25.3865, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0244, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_accuracy": 0.6480263157894737, | |
| "eval_loss": 1.2701855897903442, | |
| "eval_runtime": 25.3744, | |
| "eval_samples_per_second": 11.981, | |
| "eval_steps_per_second": 2.995, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0672, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_accuracy": 0.6414473684210527, | |
| "eval_loss": 1.716863751411438, | |
| "eval_runtime": 25.3891, | |
| "eval_samples_per_second": 11.974, | |
| "eval_steps_per_second": 2.993, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0824, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "eval_accuracy": 0.6414473684210527, | |
| "eval_loss": 1.662705659866333, | |
| "eval_runtime": 25.3803, | |
| "eval_samples_per_second": 11.978, | |
| "eval_steps_per_second": 2.994, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0068, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_accuracy": 0.6348684210526315, | |
| "eval_loss": 1.342494010925293, | |
| "eval_runtime": 25.376, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.044, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.6611842105263158, | |
| "eval_loss": 1.2208458185195923, | |
| "eval_runtime": 25.3753, | |
| "eval_samples_per_second": 11.98, | |
| "eval_steps_per_second": 2.995, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0378, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_accuracy": 0.6447368421052632, | |
| "eval_loss": 1.289115309715271, | |
| "eval_runtime": 25.3905, | |
| "eval_samples_per_second": 11.973, | |
| "eval_steps_per_second": 2.993, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0411, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_accuracy": 0.6611842105263158, | |
| "eval_loss": 1.3528344631195068, | |
| "eval_runtime": 25.3678, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 2.996, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0215, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_accuracy": 0.6677631578947368, | |
| "eval_loss": 1.2606314420700073, | |
| "eval_runtime": 25.3852, | |
| "eval_samples_per_second": 11.975, | |
| "eval_steps_per_second": 2.994, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0438, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_accuracy": 0.6546052631578947, | |
| "eval_loss": 1.2514981031417847, | |
| "eval_runtime": 25.3679, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 2.996, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0936, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_accuracy": 0.6644736842105263, | |
| "eval_loss": 1.0857858657836914, | |
| "eval_runtime": 25.3812, | |
| "eval_samples_per_second": 11.977, | |
| "eval_steps_per_second": 2.994, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0305, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_accuracy": 0.6578947368421053, | |
| "eval_loss": 0.9838737845420837, | |
| "eval_runtime": 25.3673, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 2.996, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0282, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_accuracy": 0.680921052631579, | |
| "eval_loss": 1.0233386754989624, | |
| "eval_runtime": 25.3685, | |
| "eval_samples_per_second": 11.983, | |
| "eval_steps_per_second": 2.996, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "step": 745, | |
| "total_flos": 2.959225892752589e+17, | |
| "train_loss": 0.25739487704614666, | |
| "train_runtime": 4901.8806, | |
| "train_samples_per_second": 2.444, | |
| "train_steps_per_second": 0.152 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 745, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 150, | |
| "total_flos": 2.959225892752589e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |