| { | |
| "best_metric": 0.899671052631579, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-pos-ud-Coptic-Scriptorium/checkpoint-7500", | |
| "epoch": 256.4102564102564, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.92e-05, | |
| "loss": 1.66, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 7.946845637583894e-05, | |
| "loss": 0.6182, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 7.893154362416109e-05, | |
| "loss": 0.382, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 7.839463087248322e-05, | |
| "loss": 0.2534, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 7.785771812080537e-05, | |
| "loss": 0.1725, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "eval_accuracy": 0.8799342105263158, | |
| "eval_loss": 0.4891912639141083, | |
| "eval_runtime": 1.5366, | |
| "eval_samples_per_second": 247.947, | |
| "eval_steps_per_second": 31.237, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.732080536912752e-05, | |
| "loss": 0.1148, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 7.678389261744967e-05, | |
| "loss": 0.0807, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 7.624697986577182e-05, | |
| "loss": 0.0562, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 7.571006711409396e-05, | |
| "loss": 0.0443, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 7.517315436241611e-05, | |
| "loss": 0.0372, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "eval_accuracy": 0.8819444444444444, | |
| "eval_loss": 0.6423949599266052, | |
| "eval_runtime": 1.5561, | |
| "eval_samples_per_second": 244.836, | |
| "eval_steps_per_second": 30.845, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 7.463624161073826e-05, | |
| "loss": 0.0289, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 7.409932885906041e-05, | |
| "loss": 0.0236, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 7.356241610738256e-05, | |
| "loss": 0.0185, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 7.30255033557047e-05, | |
| "loss": 0.016, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 7.248859060402685e-05, | |
| "loss": 0.0161, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "eval_accuracy": 0.8866959064327485, | |
| "eval_loss": 0.7260786890983582, | |
| "eval_runtime": 1.5383, | |
| "eval_samples_per_second": 247.68, | |
| "eval_steps_per_second": 31.204, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 41.03, | |
| "learning_rate": 7.1951677852349e-05, | |
| "loss": 0.0142, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 43.59, | |
| "learning_rate": 7.141476510067115e-05, | |
| "loss": 0.0116, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 7.08778523489933e-05, | |
| "loss": 0.0117, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 7.034093959731545e-05, | |
| "loss": 0.0109, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 6.98040268456376e-05, | |
| "loss": 0.0096, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "eval_accuracy": 0.8880665204678363, | |
| "eval_loss": 0.8069060444831848, | |
| "eval_runtime": 1.5297, | |
| "eval_samples_per_second": 249.069, | |
| "eval_steps_per_second": 31.379, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.926711409395974e-05, | |
| "loss": 0.0086, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 56.41, | |
| "learning_rate": 6.873020134228189e-05, | |
| "loss": 0.0079, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "learning_rate": 6.819328859060404e-05, | |
| "loss": 0.0069, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 6.765637583892619e-05, | |
| "loss": 0.0063, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 6.711946308724834e-05, | |
| "loss": 0.0075, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "eval_accuracy": 0.8915387426900585, | |
| "eval_loss": 0.828658401966095, | |
| "eval_runtime": 1.5268, | |
| "eval_samples_per_second": 249.541, | |
| "eval_steps_per_second": 31.438, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 6.658255033557048e-05, | |
| "loss": 0.0069, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 6.604563758389262e-05, | |
| "loss": 0.0071, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 71.79, | |
| "learning_rate": 6.550872483221477e-05, | |
| "loss": 0.0071, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 74.36, | |
| "learning_rate": 6.497181208053692e-05, | |
| "loss": 0.006, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "learning_rate": 6.443489932885906e-05, | |
| "loss": 0.0058, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "eval_accuracy": 0.8901681286549707, | |
| "eval_loss": 0.8421908020973206, | |
| "eval_runtime": 1.5301, | |
| "eval_samples_per_second": 249.0, | |
| "eval_steps_per_second": 31.37, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 79.49, | |
| "learning_rate": 6.389798657718121e-05, | |
| "loss": 0.0064, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 82.05, | |
| "learning_rate": 6.336107382550336e-05, | |
| "loss": 0.0058, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 84.62, | |
| "learning_rate": 6.282416107382551e-05, | |
| "loss": 0.0061, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 87.18, | |
| "learning_rate": 6.228724832214766e-05, | |
| "loss": 0.0062, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 89.74, | |
| "learning_rate": 6.17503355704698e-05, | |
| "loss": 0.0052, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 89.74, | |
| "eval_accuracy": 0.8907163742690059, | |
| "eval_loss": 0.8915664553642273, | |
| "eval_runtime": 1.5301, | |
| "eval_samples_per_second": 248.996, | |
| "eval_steps_per_second": 31.37, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 92.31, | |
| "learning_rate": 6.121342281879195e-05, | |
| "loss": 0.004, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 94.87, | |
| "learning_rate": 6.06765100671141e-05, | |
| "loss": 0.0055, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 97.44, | |
| "learning_rate": 6.013959731543624e-05, | |
| "loss": 0.0043, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 5.960268456375839e-05, | |
| "loss": 0.004, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 102.56, | |
| "learning_rate": 5.906577181208054e-05, | |
| "loss": 0.0036, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 102.56, | |
| "eval_accuracy": 0.8918128654970761, | |
| "eval_loss": 0.8925005793571472, | |
| "eval_runtime": 1.5336, | |
| "eval_samples_per_second": 248.438, | |
| "eval_steps_per_second": 31.299, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 105.13, | |
| "learning_rate": 5.852885906040269e-05, | |
| "loss": 0.0044, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 107.69, | |
| "learning_rate": 5.7991946308724836e-05, | |
| "loss": 0.003, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 110.26, | |
| "learning_rate": 5.7455033557046984e-05, | |
| "loss": 0.0038, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 112.82, | |
| "learning_rate": 5.691812080536913e-05, | |
| "loss": 0.0034, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 115.38, | |
| "learning_rate": 5.638120805369128e-05, | |
| "loss": 0.0034, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 115.38, | |
| "eval_accuracy": 0.8918128654970761, | |
| "eval_loss": 0.9117233753204346, | |
| "eval_runtime": 1.5348, | |
| "eval_samples_per_second": 248.239, | |
| "eval_steps_per_second": 31.274, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 117.95, | |
| "learning_rate": 5.584429530201343e-05, | |
| "loss": 0.0039, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 120.51, | |
| "learning_rate": 5.530738255033558e-05, | |
| "loss": 0.0037, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 123.08, | |
| "learning_rate": 5.4770469798657725e-05, | |
| "loss": 0.0031, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 125.64, | |
| "learning_rate": 5.4233557046979874e-05, | |
| "loss": 0.0038, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 128.21, | |
| "learning_rate": 5.3696644295302015e-05, | |
| "loss": 0.004, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 128.21, | |
| "eval_accuracy": 0.8946454678362573, | |
| "eval_loss": 0.8941249847412109, | |
| "eval_runtime": 1.5416, | |
| "eval_samples_per_second": 247.142, | |
| "eval_steps_per_second": 31.136, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 130.77, | |
| "learning_rate": 5.315973154362416e-05, | |
| "loss": 0.0025, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 133.33, | |
| "learning_rate": 5.262281879194631e-05, | |
| "loss": 0.0025, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 135.9, | |
| "learning_rate": 5.208590604026846e-05, | |
| "loss": 0.0035, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 138.46, | |
| "learning_rate": 5.154899328859061e-05, | |
| "loss": 0.0028, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 141.03, | |
| "learning_rate": 5.1012080536912756e-05, | |
| "loss": 0.0033, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 141.03, | |
| "eval_accuracy": 0.8901681286549707, | |
| "eval_loss": 0.9474687576293945, | |
| "eval_runtime": 1.5483, | |
| "eval_samples_per_second": 246.083, | |
| "eval_steps_per_second": 31.003, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 143.59, | |
| "learning_rate": 5.0475167785234905e-05, | |
| "loss": 0.0026, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 146.15, | |
| "learning_rate": 4.993825503355705e-05, | |
| "loss": 0.0021, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 148.72, | |
| "learning_rate": 4.94013422818792e-05, | |
| "loss": 0.0025, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 151.28, | |
| "learning_rate": 4.886442953020135e-05, | |
| "loss": 0.002, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 153.85, | |
| "learning_rate": 4.83275167785235e-05, | |
| "loss": 0.0028, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 153.85, | |
| "eval_accuracy": 0.8967470760233918, | |
| "eval_loss": 0.9054576754570007, | |
| "eval_runtime": 1.5492, | |
| "eval_samples_per_second": 245.926, | |
| "eval_steps_per_second": 30.983, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 156.41, | |
| "learning_rate": 4.779060402684564e-05, | |
| "loss": 0.0026, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 158.97, | |
| "learning_rate": 4.725369127516779e-05, | |
| "loss": 0.0022, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 161.54, | |
| "learning_rate": 4.6716778523489936e-05, | |
| "loss": 0.0026, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 164.1, | |
| "learning_rate": 4.6179865771812084e-05, | |
| "loss": 0.0025, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "learning_rate": 4.564295302013423e-05, | |
| "loss": 0.0014, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "eval_accuracy": 0.8951937134502924, | |
| "eval_loss": 0.9585675597190857, | |
| "eval_runtime": 1.544, | |
| "eval_samples_per_second": 246.764, | |
| "eval_steps_per_second": 31.088, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 169.23, | |
| "learning_rate": 4.510604026845638e-05, | |
| "loss": 0.0027, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 171.79, | |
| "learning_rate": 4.456912751677853e-05, | |
| "loss": 0.0016, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 174.36, | |
| "learning_rate": 4.403221476510068e-05, | |
| "loss": 0.0024, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 176.92, | |
| "learning_rate": 4.3495302013422825e-05, | |
| "loss": 0.0017, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 179.49, | |
| "learning_rate": 4.295838926174497e-05, | |
| "loss": 0.0018, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 179.49, | |
| "eval_accuracy": 0.89546783625731, | |
| "eval_loss": 0.9691464900970459, | |
| "eval_runtime": 1.518, | |
| "eval_samples_per_second": 250.996, | |
| "eval_steps_per_second": 31.622, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 182.05, | |
| "learning_rate": 4.242147651006712e-05, | |
| "loss": 0.0023, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 184.62, | |
| "learning_rate": 4.188456375838927e-05, | |
| "loss": 0.0027, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 187.18, | |
| "learning_rate": 4.134765100671141e-05, | |
| "loss": 0.0021, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 189.74, | |
| "learning_rate": 4.081073825503356e-05, | |
| "loss": 0.002, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 192.31, | |
| "learning_rate": 4.027382550335571e-05, | |
| "loss": 0.0017, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 192.31, | |
| "eval_accuracy": 0.899671052631579, | |
| "eval_loss": 0.92512446641922, | |
| "eval_runtime": 1.5211, | |
| "eval_samples_per_second": 250.471, | |
| "eval_steps_per_second": 31.555, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 194.87, | |
| "learning_rate": 3.9736912751677856e-05, | |
| "loss": 0.0017, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 197.44, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.0019, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 3.866308724832215e-05, | |
| "loss": 0.0022, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 202.56, | |
| "learning_rate": 3.81261744966443e-05, | |
| "loss": 0.0012, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 205.13, | |
| "learning_rate": 3.758926174496645e-05, | |
| "loss": 0.0016, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 205.13, | |
| "eval_accuracy": 0.8972953216374269, | |
| "eval_loss": 0.9501896500587463, | |
| "eval_runtime": 1.5504, | |
| "eval_samples_per_second": 245.737, | |
| "eval_steps_per_second": 30.959, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 207.69, | |
| "learning_rate": 3.705234899328859e-05, | |
| "loss": 0.0013, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 210.26, | |
| "learning_rate": 3.651543624161074e-05, | |
| "loss": 0.0011, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 212.82, | |
| "learning_rate": 3.597852348993289e-05, | |
| "loss": 0.0015, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 215.38, | |
| "learning_rate": 3.5441610738255035e-05, | |
| "loss": 0.0009, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 217.95, | |
| "learning_rate": 3.490469798657718e-05, | |
| "loss": 0.0015, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 217.95, | |
| "eval_accuracy": 0.8966557017543859, | |
| "eval_loss": 0.9619430303573608, | |
| "eval_runtime": 1.5407, | |
| "eval_samples_per_second": 247.295, | |
| "eval_steps_per_second": 31.155, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 220.51, | |
| "learning_rate": 3.436778523489933e-05, | |
| "loss": 0.0011, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 223.08, | |
| "learning_rate": 3.383087248322148e-05, | |
| "loss": 0.002, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 225.64, | |
| "learning_rate": 3.329395973154363e-05, | |
| "loss": 0.0012, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 228.21, | |
| "learning_rate": 3.2757046979865776e-05, | |
| "loss": 0.0011, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 230.77, | |
| "learning_rate": 3.2220134228187925e-05, | |
| "loss": 0.001, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 230.77, | |
| "eval_accuracy": 0.899671052631579, | |
| "eval_loss": 0.9450499415397644, | |
| "eval_runtime": 1.5395, | |
| "eval_samples_per_second": 247.489, | |
| "eval_steps_per_second": 31.18, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 233.33, | |
| "learning_rate": 3.168322147651007e-05, | |
| "loss": 0.0009, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 235.9, | |
| "learning_rate": 3.114630872483222e-05, | |
| "loss": 0.0009, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 238.46, | |
| "learning_rate": 3.060939597315436e-05, | |
| "loss": 0.0011, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 241.03, | |
| "learning_rate": 3.007248322147651e-05, | |
| "loss": 0.0006, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 243.59, | |
| "learning_rate": 2.953557046979866e-05, | |
| "loss": 0.0011, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 243.59, | |
| "eval_accuracy": 0.8972953216374269, | |
| "eval_loss": 0.9794738292694092, | |
| "eval_runtime": 1.5217, | |
| "eval_samples_per_second": 250.373, | |
| "eval_steps_per_second": 31.543, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 246.15, | |
| "learning_rate": 2.8998657718120807e-05, | |
| "loss": 0.0009, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 248.72, | |
| "learning_rate": 2.8461744966442955e-05, | |
| "loss": 0.0009, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 251.28, | |
| "learning_rate": 2.79248322147651e-05, | |
| "loss": 0.0008, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 253.85, | |
| "learning_rate": 2.738791946308725e-05, | |
| "loss": 0.0004, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 256.41, | |
| "learning_rate": 2.6851006711409397e-05, | |
| "loss": 0.0011, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 256.41, | |
| "eval_accuracy": 0.8970211988304093, | |
| "eval_loss": 1.0004897117614746, | |
| "eval_runtime": 1.5228, | |
| "eval_samples_per_second": 250.203, | |
| "eval_steps_per_second": 31.522, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 256.41, | |
| "step": 10000, | |
| "total_flos": 5.166941021601792e+16, | |
| "train_loss": 0.03826559160500765, | |
| "train_runtime": 1428.3699, | |
| "train_samples_per_second": 336.047, | |
| "train_steps_per_second": 10.501 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 385, | |
| "total_flos": 5.166941021601792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |