| { | |
| "best_metric": 2.3947181701660156, | |
| "best_model_checkpoint": "../checkpoints/FinalTrains_Runde2_720samples\\checkpoint-2300", | |
| "epoch": 27.07017543859649, | |
| "eval_steps": 50, | |
| "global_step": 2301, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5847953216374269, | |
| "grad_norm": 2511.836181640625, | |
| "learning_rate": 1.6399999999999998e-06, | |
| "loss": 11.5208, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5847953216374269, | |
| "eval_loss": 7.463321208953857, | |
| "eval_runtime": 48.9349, | |
| "eval_samples_per_second": 2.943, | |
| "eval_steps_per_second": 2.943, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1695906432748537, | |
| "grad_norm": 582.1835327148438, | |
| "learning_rate": 1.9672e-06, | |
| "loss": 5.9458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1695906432748537, | |
| "eval_loss": 4.85849142074585, | |
| "eval_runtime": 51.5611, | |
| "eval_samples_per_second": 2.793, | |
| "eval_steps_per_second": 2.793, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "grad_norm": 429.77252197265625, | |
| "learning_rate": 1.9272e-06, | |
| "loss": 4.5189, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "eval_loss": 4.148195743560791, | |
| "eval_runtime": 53.3669, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 2.698, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.3391812865497075, | |
| "grad_norm": 246.91941833496094, | |
| "learning_rate": 1.8872e-06, | |
| "loss": 3.9677, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.3391812865497075, | |
| "eval_loss": 3.7681965827941895, | |
| "eval_runtime": 48.4728, | |
| "eval_samples_per_second": 2.971, | |
| "eval_steps_per_second": 2.971, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.9239766081871346, | |
| "grad_norm": 326.88507080078125, | |
| "learning_rate": 1.8471999999999999e-06, | |
| "loss": 3.6828, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.9239766081871346, | |
| "eval_loss": 3.4826574325561523, | |
| "eval_runtime": 47.8574, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "grad_norm": 216.14739990234375, | |
| "learning_rate": 1.8071999999999998e-06, | |
| "loss": 3.3901, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "eval_loss": 3.304009437561035, | |
| "eval_runtime": 48.0808, | |
| "eval_samples_per_second": 2.995, | |
| "eval_steps_per_second": 2.995, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.093567251461988, | |
| "grad_norm": 159.58961486816406, | |
| "learning_rate": 1.7672e-06, | |
| "loss": 3.2532, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.093567251461988, | |
| "eval_loss": 3.1738274097442627, | |
| "eval_runtime": 47.8126, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 3.012, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.678362573099415, | |
| "grad_norm": 161.6717071533203, | |
| "learning_rate": 1.7272e-06, | |
| "loss": 3.1071, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.678362573099415, | |
| "eval_loss": 3.0628068447113037, | |
| "eval_runtime": 48.0252, | |
| "eval_samples_per_second": 2.998, | |
| "eval_steps_per_second": 2.998, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "grad_norm": 146.9420166015625, | |
| "learning_rate": 1.6872e-06, | |
| "loss": 2.9944, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "eval_loss": 2.990321159362793, | |
| "eval_runtime": 47.8573, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.847953216374269, | |
| "grad_norm": 233.46127319335938, | |
| "learning_rate": 1.6471999999999999e-06, | |
| "loss": 2.898, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.847953216374269, | |
| "eval_loss": 2.9129867553710938, | |
| "eval_runtime": 47.7606, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.432748538011696, | |
| "grad_norm": 217.460205078125, | |
| "learning_rate": 1.6071999999999998e-06, | |
| "loss": 2.8098, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.432748538011696, | |
| "eval_loss": 2.862227439880371, | |
| "eval_runtime": 47.7417, | |
| "eval_samples_per_second": 3.016, | |
| "eval_steps_per_second": 3.016, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.017543859649122, | |
| "grad_norm": 171.82847595214844, | |
| "learning_rate": 1.5671999999999998e-06, | |
| "loss": 2.7165, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.017543859649122, | |
| "eval_loss": 2.827782392501831, | |
| "eval_runtime": 47.7602, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.60233918128655, | |
| "grad_norm": 255.87489318847656, | |
| "learning_rate": 1.5271999999999998e-06, | |
| "loss": 2.6446, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.60233918128655, | |
| "eval_loss": 2.7759788036346436, | |
| "eval_runtime": 47.7257, | |
| "eval_samples_per_second": 3.017, | |
| "eval_steps_per_second": 3.017, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.187134502923977, | |
| "grad_norm": 349.6673889160156, | |
| "learning_rate": 1.4872e-06, | |
| "loss": 2.5134, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.187134502923977, | |
| "eval_loss": 2.7408220767974854, | |
| "eval_runtime": 47.7358, | |
| "eval_samples_per_second": 3.017, | |
| "eval_steps_per_second": 3.017, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.771929824561404, | |
| "grad_norm": 303.1741943359375, | |
| "learning_rate": 1.4471999999999999e-06, | |
| "loss": 2.4957, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.771929824561404, | |
| "eval_loss": 2.7205865383148193, | |
| "eval_runtime": 47.7327, | |
| "eval_samples_per_second": 3.017, | |
| "eval_steps_per_second": 3.017, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.35672514619883, | |
| "grad_norm": 277.3189697265625, | |
| "learning_rate": 1.4071999999999998e-06, | |
| "loss": 2.4521, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.35672514619883, | |
| "eval_loss": 2.699465036392212, | |
| "eval_runtime": 47.8368, | |
| "eval_samples_per_second": 3.01, | |
| "eval_steps_per_second": 3.01, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.941520467836257, | |
| "grad_norm": 342.6287536621094, | |
| "learning_rate": 1.3672e-06, | |
| "loss": 2.3549, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.941520467836257, | |
| "eval_loss": 2.657285690307617, | |
| "eval_runtime": 47.7948, | |
| "eval_samples_per_second": 3.013, | |
| "eval_steps_per_second": 3.013, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.526315789473685, | |
| "grad_norm": 314.8951416015625, | |
| "learning_rate": 1.3272e-06, | |
| "loss": 2.3118, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.526315789473685, | |
| "eval_loss": 2.6494998931884766, | |
| "eval_runtime": 47.8289, | |
| "eval_samples_per_second": 3.011, | |
| "eval_steps_per_second": 3.011, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 259.777099609375, | |
| "learning_rate": 1.2872e-06, | |
| "loss": 2.2292, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "eval_loss": 2.6447384357452393, | |
| "eval_runtime": 47.7489, | |
| "eval_samples_per_second": 3.016, | |
| "eval_steps_per_second": 3.016, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.695906432748538, | |
| "grad_norm": 298.0020446777344, | |
| "learning_rate": 1.2472e-06, | |
| "loss": 2.191, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.695906432748538, | |
| "eval_loss": 2.6040868759155273, | |
| "eval_runtime": 47.8314, | |
| "eval_samples_per_second": 3.011, | |
| "eval_steps_per_second": 3.011, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.280701754385966, | |
| "grad_norm": 276.3546447753906, | |
| "learning_rate": 1.2072e-06, | |
| "loss": 2.1521, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.280701754385966, | |
| "eval_loss": 2.6078646183013916, | |
| "eval_runtime": 47.8526, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.865497076023392, | |
| "grad_norm": 336.7939453125, | |
| "learning_rate": 1.1672e-06, | |
| "loss": 2.0565, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.865497076023392, | |
| "eval_loss": 2.5721495151519775, | |
| "eval_runtime": 47.7559, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.450292397660819, | |
| "grad_norm": 302.5251770019531, | |
| "learning_rate": 1.1272e-06, | |
| "loss": 2.096, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 13.450292397660819, | |
| "eval_loss": 2.5710203647613525, | |
| "eval_runtime": 47.8318, | |
| "eval_samples_per_second": 3.011, | |
| "eval_steps_per_second": 3.011, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.035087719298245, | |
| "grad_norm": 262.70208740234375, | |
| "learning_rate": 1.0872e-06, | |
| "loss": 1.9957, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.035087719298245, | |
| "eval_loss": 2.561436414718628, | |
| "eval_runtime": 47.868, | |
| "eval_samples_per_second": 3.008, | |
| "eval_steps_per_second": 3.008, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.619883040935672, | |
| "grad_norm": 339.61175537109375, | |
| "learning_rate": 1.0472e-06, | |
| "loss": 1.9382, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 14.619883040935672, | |
| "eval_loss": 2.544802665710449, | |
| "eval_runtime": 47.8634, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 15.2046783625731, | |
| "grad_norm": 259.406005859375, | |
| "learning_rate": 1.0072e-06, | |
| "loss": 1.9409, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 15.2046783625731, | |
| "eval_loss": 2.541916847229004, | |
| "eval_runtime": 47.8691, | |
| "eval_samples_per_second": 3.008, | |
| "eval_steps_per_second": 3.008, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 15.789473684210526, | |
| "grad_norm": 277.8048400878906, | |
| "learning_rate": 9.671999999999998e-07, | |
| "loss": 1.9007, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.789473684210526, | |
| "eval_loss": 2.5277278423309326, | |
| "eval_runtime": 47.8083, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 3.012, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 16.374269005847953, | |
| "grad_norm": 241.31704711914062, | |
| "learning_rate": 9.272e-07, | |
| "loss": 1.9013, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 16.374269005847953, | |
| "eval_loss": 2.5117082595825195, | |
| "eval_runtime": 47.755, | |
| "eval_samples_per_second": 3.015, | |
| "eval_steps_per_second": 3.015, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 16.95906432748538, | |
| "grad_norm": 307.3838806152344, | |
| "learning_rate": 8.872e-07, | |
| "loss": 1.7729, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.95906432748538, | |
| "eval_loss": 2.4952661991119385, | |
| "eval_runtime": 47.9247, | |
| "eval_samples_per_second": 3.005, | |
| "eval_steps_per_second": 3.005, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 17.54385964912281, | |
| "grad_norm": 264.11541748046875, | |
| "learning_rate": 8.471999999999999e-07, | |
| "loss": 1.7591, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 17.54385964912281, | |
| "eval_loss": 2.4815564155578613, | |
| "eval_runtime": 47.8623, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.128654970760234, | |
| "grad_norm": 268.2859802246094, | |
| "learning_rate": 8.072e-07, | |
| "loss": 1.787, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 18.128654970760234, | |
| "eval_loss": 2.4869062900543213, | |
| "eval_runtime": 47.8575, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 18.71345029239766, | |
| "grad_norm": 245.68939208984375, | |
| "learning_rate": 7.671999999999999e-07, | |
| "loss": 1.7344, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.71345029239766, | |
| "eval_loss": 2.4752299785614014, | |
| "eval_runtime": 47.7262, | |
| "eval_samples_per_second": 3.017, | |
| "eval_steps_per_second": 3.017, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 19.29824561403509, | |
| "grad_norm": 328.9492492675781, | |
| "learning_rate": 7.271999999999999e-07, | |
| "loss": 1.6783, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 19.29824561403509, | |
| "eval_loss": 2.4677534103393555, | |
| "eval_runtime": 47.7929, | |
| "eval_samples_per_second": 3.013, | |
| "eval_steps_per_second": 3.013, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 19.883040935672515, | |
| "grad_norm": 271.9133605957031, | |
| "learning_rate": 6.872e-07, | |
| "loss": 1.6848, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.883040935672515, | |
| "eval_loss": 2.458709478378296, | |
| "eval_runtime": 47.8355, | |
| "eval_samples_per_second": 3.01, | |
| "eval_steps_per_second": 3.01, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 20.46783625730994, | |
| "grad_norm": 280.5169372558594, | |
| "learning_rate": 6.471999999999999e-07, | |
| "loss": 1.6688, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 20.46783625730994, | |
| "eval_loss": 2.451404333114624, | |
| "eval_runtime": 47.8049, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 3.012, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 21.05263157894737, | |
| "grad_norm": 255.56361389160156, | |
| "learning_rate": 6.072e-07, | |
| "loss": 1.5875, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 21.05263157894737, | |
| "eval_loss": 2.446828842163086, | |
| "eval_runtime": 47.8033, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 3.012, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 21.637426900584796, | |
| "grad_norm": 307.4700622558594, | |
| "learning_rate": 5.672e-07, | |
| "loss": 1.5884, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 21.637426900584796, | |
| "eval_loss": 2.4349937438964844, | |
| "eval_runtime": 47.8413, | |
| "eval_samples_per_second": 3.01, | |
| "eval_steps_per_second": 3.01, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 283.2776184082031, | |
| "learning_rate": 5.272e-07, | |
| "loss": 1.6004, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "eval_loss": 2.434246063232422, | |
| "eval_runtime": 47.7863, | |
| "eval_samples_per_second": 3.013, | |
| "eval_steps_per_second": 3.013, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 22.80701754385965, | |
| "grad_norm": 250.710693359375, | |
| "learning_rate": 4.872e-07, | |
| "loss": 1.5452, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 22.80701754385965, | |
| "eval_loss": 2.4212119579315186, | |
| "eval_runtime": 47.8378, | |
| "eval_samples_per_second": 3.01, | |
| "eval_steps_per_second": 3.01, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 23.391812865497077, | |
| "grad_norm": 270.8255310058594, | |
| "learning_rate": 4.472e-07, | |
| "loss": 1.541, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 23.391812865497077, | |
| "eval_loss": 2.417588472366333, | |
| "eval_runtime": 47.7987, | |
| "eval_samples_per_second": 3.013, | |
| "eval_steps_per_second": 3.013, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 23.976608187134502, | |
| "grad_norm": 254.624755859375, | |
| "learning_rate": 4.072e-07, | |
| "loss": 1.4856, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 23.976608187134502, | |
| "eval_loss": 2.409721851348877, | |
| "eval_runtime": 47.8588, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 3.009, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 24.56140350877193, | |
| "grad_norm": 317.4898986816406, | |
| "learning_rate": 3.672e-07, | |
| "loss": 1.5132, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 24.56140350877193, | |
| "eval_loss": 2.408442497253418, | |
| "eval_runtime": 47.9177, | |
| "eval_samples_per_second": 3.005, | |
| "eval_steps_per_second": 3.005, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 25.146198830409357, | |
| "grad_norm": 276.2957763671875, | |
| "learning_rate": 3.2719999999999997e-07, | |
| "loss": 1.4667, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 25.146198830409357, | |
| "eval_loss": 2.407714605331421, | |
| "eval_runtime": 47.6759, | |
| "eval_samples_per_second": 3.02, | |
| "eval_steps_per_second": 3.02, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 25.730994152046783, | |
| "grad_norm": 269.7268981933594, | |
| "learning_rate": 2.872e-07, | |
| "loss": 1.4582, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 25.730994152046783, | |
| "eval_loss": 2.3980703353881836, | |
| "eval_runtime": 47.9246, | |
| "eval_samples_per_second": 3.005, | |
| "eval_steps_per_second": 3.005, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 26.31578947368421, | |
| "grad_norm": 259.5769958496094, | |
| "learning_rate": 2.472e-07, | |
| "loss": 1.4627, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 26.31578947368421, | |
| "eval_loss": 2.396810293197632, | |
| "eval_runtime": 47.988, | |
| "eval_samples_per_second": 3.001, | |
| "eval_steps_per_second": 3.001, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 26.900584795321638, | |
| "grad_norm": 229.35121154785156, | |
| "learning_rate": 2.0719999999999998e-07, | |
| "loss": 1.4554, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 26.900584795321638, | |
| "eval_loss": 2.3947181701660156, | |
| "eval_runtime": 47.8901, | |
| "eval_samples_per_second": 3.007, | |
| "eval_steps_per_second": 3.007, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 27.07017543859649, | |
| "step": 2301, | |
| "total_flos": 0.0, | |
| "train_loss": 0.0005499045261348242, | |
| "train_runtime": 49.212, | |
| "train_samples_per_second": 1496.22, | |
| "train_steps_per_second": 46.757 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2301, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 28, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |