| { | |
| "best_metric": 0.5993568897247314, | |
| "best_model_checkpoint": "ckpts/discrim/contrastive_models/gen.t5.large/flan_t5_large_tso/checkpoint-7200", | |
| "epoch": 1.9380888290713325, | |
| "global_step": 7200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.6905829596412554e-06, | |
| "loss": 0.9993, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.381165919282511e-06, | |
| "loss": 0.9989, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.071748878923767e-06, | |
| "loss": 0.9961, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.0762331838565022e-05, | |
| "loss": 0.986, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.979211688041687, | |
| "eval_runtime": 304.3772, | |
| "eval_samples_per_second": 77.296, | |
| "eval_steps_per_second": 9.662, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.345291479820628e-05, | |
| "loss": 0.949, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.6143497757847534e-05, | |
| "loss": 0.8611, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.883408071748879e-05, | |
| "loss": 0.7761, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.1524663677130043e-05, | |
| "loss": 0.7103, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.73173987865448, | |
| "eval_runtime": 304.6199, | |
| "eval_samples_per_second": 77.234, | |
| "eval_steps_per_second": 9.655, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.42152466367713e-05, | |
| "loss": 0.6447, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.690582959641256e-05, | |
| "loss": 0.6239, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.9596412556053812e-05, | |
| "loss": 0.6433, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.228699551569507e-05, | |
| "loss": 0.5925, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.7419408559799194, | |
| "eval_runtime": 305.2185, | |
| "eval_samples_per_second": 77.082, | |
| "eval_steps_per_second": 9.636, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.4977578475336325e-05, | |
| "loss": 0.5665, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.766816143497758e-05, | |
| "loss": 0.5167, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.035874439461884e-05, | |
| "loss": 0.5378, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.304932735426009e-05, | |
| "loss": 0.4876, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.7308951020240784, | |
| "eval_runtime": 305.4422, | |
| "eval_samples_per_second": 77.026, | |
| "eval_steps_per_second": 9.629, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.573991031390134e-05, | |
| "loss": 0.4874, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.84304932735426e-05, | |
| "loss": 0.4476, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.1121076233183856e-05, | |
| "loss": 0.4695, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.381165919282512e-05, | |
| "loss": 0.4334, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.6671885848045349, | |
| "eval_runtime": 305.4747, | |
| "eval_samples_per_second": 77.018, | |
| "eval_steps_per_second": 9.628, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.6502242152466375e-05, | |
| "loss": 0.389, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5.9192825112107625e-05, | |
| "loss": 0.3758, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5.999940510930071e-05, | |
| "loss": 0.3737, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.999649141573284e-05, | |
| "loss": 0.3586, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.6958568096160889, | |
| "eval_runtime": 305.3709, | |
| "eval_samples_per_second": 77.044, | |
| "eval_steps_per_second": 9.631, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5.9991149889189245e-05, | |
| "loss": 0.3154, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5.9983380961998294e-05, | |
| "loss": 0.3202, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5.997318526295544e-05, | |
| "loss": 0.3232, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.996056361727235e-05, | |
| "loss": 0.3016, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.6629464030265808, | |
| "eval_runtime": 305.4391, | |
| "eval_samples_per_second": 77.027, | |
| "eval_steps_per_second": 9.629, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.9945517046510075e-05, | |
| "loss": 0.2673, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.992804676849642e-05, | |
| "loss": 0.2558, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.990815419722729e-05, | |
| "loss": 0.2566, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.988584094275237e-05, | |
| "loss": 0.2496, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.6636276841163635, | |
| "eval_runtime": 305.4888, | |
| "eval_samples_per_second": 77.014, | |
| "eval_steps_per_second": 9.627, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.9861108811044676e-05, | |
| "loss": 0.2273, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.983395980385451e-05, | |
| "loss": 0.2121, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.9804396118547345e-05, | |
| "loss": 0.1966, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.977242014792602e-05, | |
| "loss": 0.1929, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.6448654532432556, | |
| "eval_runtime": 305.5903, | |
| "eval_samples_per_second": 76.989, | |
| "eval_steps_per_second": 9.624, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.9738034480037094e-05, | |
| "loss": 0.1797, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.970124189796133e-05, | |
| "loss": 0.1807, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.966204537958846e-05, | |
| "loss": 0.1438, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.962044809737618e-05, | |
| "loss": 0.1721, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.6665562391281128, | |
| "eval_runtime": 305.4858, | |
| "eval_samples_per_second": 77.015, | |
| "eval_steps_per_second": 9.627, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.957645341809336e-05, | |
| "loss": 0.1555, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.953006490254755e-05, | |
| "loss": 0.1543, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.9481286305296774e-05, | |
| "loss": 0.1498, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.943012157434567e-05, | |
| "loss": 0.1495, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.6751571893692017, | |
| "eval_runtime": 305.7212, | |
| "eval_samples_per_second": 76.956, | |
| "eval_steps_per_second": 9.62, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.9376574850825905e-05, | |
| "loss": 0.1206, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.9320650468661066e-05, | |
| "loss": 0.1261, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 5.926235295421582e-05, | |
| "loss": 0.1173, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.92016870259296e-05, | |
| "loss": 0.1132, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.7012338638305664, | |
| "eval_runtime": 305.6366, | |
| "eval_samples_per_second": 76.977, | |
| "eval_steps_per_second": 9.623, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.9138657593934704e-05, | |
| "loss": 0.1225, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.907326975965887e-05, | |
| "loss": 0.112, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.9005528815412394e-05, | |
| "loss": 0.1105, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.893544024395977e-05, | |
| "loss": 0.1058, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.6904404163360596, | |
| "eval_runtime": 305.6312, | |
| "eval_samples_per_second": 76.978, | |
| "eval_steps_per_second": 9.623, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.886300971807594e-05, | |
| "loss": 0.0855, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.878824310008718e-05, | |
| "loss": 0.088, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.871114644139656e-05, | |
| "loss": 0.0926, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.86317259819942e-05, | |
| "loss": 0.1057, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.6426856517791748, | |
| "eval_runtime": 305.7094, | |
| "eval_samples_per_second": 76.959, | |
| "eval_steps_per_second": 9.62, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.854998814995223e-05, | |
| "loss": 0.0846, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 5.846593956090451e-05, | |
| "loss": 0.0838, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 5.837958701751115e-05, | |
| "loss": 0.0827, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.8290937508907975e-05, | |
| "loss": 0.0818, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.6715692281723022, | |
| "eval_runtime": 305.6575, | |
| "eval_samples_per_second": 76.972, | |
| "eval_steps_per_second": 9.622, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.819999821014079e-05, | |
| "loss": 0.114, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.81067764815847e-05, | |
| "loss": 0.0742, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.801127986834834e-05, | |
| "loss": 0.0764, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.791351609966323e-05, | |
| "loss": 0.0893, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.6607950329780579, | |
| "eval_runtime": 305.6387, | |
| "eval_samples_per_second": 76.977, | |
| "eval_steps_per_second": 9.622, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.781349308825816e-05, | |
| "loss": 0.2025, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.7711218929718786e-05, | |
| "loss": 0.3151, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.760670190183236e-05, | |
| "loss": 0.3307, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 5.74999504639178e-05, | |
| "loss": 0.3306, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.7396358251571655, | |
| "eval_runtime": 305.7093, | |
| "eval_samples_per_second": 76.959, | |
| "eval_steps_per_second": 9.62, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.739097325614097e-05, | |
| "loss": 0.3255, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.727977909881537e-05, | |
| "loss": 0.317, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.716637699168828e-05, | |
| "loss": 0.3187, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.705077611321233e-05, | |
| "loss": 0.3105, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.7177180051803589, | |
| "eval_runtime": 305.5872, | |
| "eval_samples_per_second": 76.989, | |
| "eval_steps_per_second": 9.624, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.69329858198026e-05, | |
| "loss": 0.3129, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.6813015645079355e-05, | |
| "loss": 0.3237, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.6690875299096415e-05, | |
| "loss": 0.2951, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.656657466755528e-05, | |
| "loss": 0.2882, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.7239081263542175, | |
| "eval_runtime": 305.6494, | |
| "eval_samples_per_second": 76.974, | |
| "eval_steps_per_second": 9.622, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.6440123811004955e-05, | |
| "loss": 0.3036, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.631153296402772e-05, | |
| "loss": 0.2988, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.6180812534410734e-05, | |
| "loss": 0.2982, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.604797310230373e-05, | |
| "loss": 0.3034, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.7187855243682861, | |
| "eval_runtime": 305.6191, | |
| "eval_samples_per_second": 76.981, | |
| "eval_steps_per_second": 9.623, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.591302541936257e-05, | |
| "loss": 0.3056, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.577598040787914e-05, | |
| "loss": 0.3106, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 5.5636849159897306e-05, | |
| "loss": 0.3083, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 5.54956429363151e-05, | |
| "loss": 0.2335, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.6692826747894287, | |
| "eval_runtime": 305.6153, | |
| "eval_samples_per_second": 76.982, | |
| "eval_steps_per_second": 9.623, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 5.535237316597337e-05, | |
| "loss": 0.0927, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 5.5207051444730707e-05, | |
| "loss": 0.0937, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 5.505968953452494e-05, | |
| "loss": 0.0998, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 5.4910299362421125e-05, | |
| "loss": 0.0881, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 0.6463451385498047, | |
| "eval_runtime": 305.7621, | |
| "eval_samples_per_second": 76.945, | |
| "eval_steps_per_second": 9.619, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 5.4758893019646234e-05, | |
| "loss": 0.0694, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 5.460548276061054e-05, | |
| "loss": 0.0806, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 5.4450081001915694e-05, | |
| "loss": 0.0735, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 5.429270032134986e-05, | |
| "loss": 0.0686, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.7035936117172241, | |
| "eval_runtime": 305.6859, | |
| "eval_samples_per_second": 76.965, | |
| "eval_steps_per_second": 9.621, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5.413335345686963e-05, | |
| "loss": 0.0751, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 5.397205330556912e-05, | |
| "loss": 0.0794, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 5.380881292263602e-05, | |
| "loss": 0.0738, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 5.364364552029504e-05, | |
| "loss": 0.07, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.6865878701210022, | |
| "eval_runtime": 305.6253, | |
| "eval_samples_per_second": 76.98, | |
| "eval_steps_per_second": 9.623, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5.347656446673849e-05, | |
| "loss": 0.0601, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.330758328504432e-05, | |
| "loss": 0.0622, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.313671565208157e-05, | |
| "loss": 0.0617, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.296397539740344e-05, | |
| "loss": 0.0655, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.6813921332359314, | |
| "eval_runtime": 305.6628, | |
| "eval_samples_per_second": 76.97, | |
| "eval_steps_per_second": 9.622, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.2789376502127956e-05, | |
| "loss": 0.0621, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.261293309780635e-05, | |
| "loss": 0.0651, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.243465946527933e-05, | |
| "loss": 0.0529, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.225457003352119e-05, | |
| "loss": 0.0483, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.6487281322479248, | |
| "eval_runtime": 305.6821, | |
| "eval_samples_per_second": 76.966, | |
| "eval_steps_per_second": 9.621, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.207267937847198e-05, | |
| "loss": 0.0554, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.188900222185781e-05, | |
| "loss": 0.066, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.170355342999926e-05, | |
| "loss": 0.0502, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.151634801260815e-05, | |
| "loss": 0.0467, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.6819436550140381, | |
| "eval_runtime": 305.7363, | |
| "eval_samples_per_second": 76.952, | |
| "eval_steps_per_second": 9.619, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.132740112157274e-05, | |
| "loss": 0.0439, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.1136728049731315e-05, | |
| "loss": 0.0467, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.0944344229634474e-05, | |
| "loss": 0.0454, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.075026523229604e-05, | |
| "loss": 0.0461, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.6921408176422119, | |
| "eval_runtime": 305.7277, | |
| "eval_samples_per_second": 76.954, | |
| "eval_steps_per_second": 9.62, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.055450676593277e-05, | |
| "loss": 0.0496, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.0357084674693044e-05, | |
| "loss": 0.0376, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.015801493737437e-05, | |
| "loss": 0.0465, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.995731366613022e-05, | |
| "loss": 0.0473, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.6527886986732483, | |
| "eval_runtime": 305.6041, | |
| "eval_samples_per_second": 76.985, | |
| "eval_steps_per_second": 9.624, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.975499710516589e-05, | |
| "loss": 0.0377, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.9551081629423734e-05, | |
| "loss": 0.0462, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.934558374325787e-05, | |
| "loss": 0.0378, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.913852007909832e-05, | |
| "loss": 0.0477, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.6821478605270386, | |
| "eval_runtime": 305.5702, | |
| "eval_samples_per_second": 76.994, | |
| "eval_steps_per_second": 9.625, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.8929907396104834e-05, | |
| "loss": 0.0443, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.871976257881049e-05, | |
| "loss": 0.0551, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.850810263575504e-05, | |
| "loss": 0.0518, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.829494469810834e-05, | |
| "loss": 0.0343, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.6623004078865051, | |
| "eval_runtime": 305.5922, | |
| "eval_samples_per_second": 76.988, | |
| "eval_steps_per_second": 9.624, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.808030601828378e-05, | |
| "loss": 0.0461, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.7864203968541914e-05, | |
| "loss": 0.0404, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.7646656039584416e-05, | |
| "loss": 0.0303, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.742767983913842e-05, | |
| "loss": 0.0376, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.653499186038971, | |
| "eval_runtime": 305.6562, | |
| "eval_samples_per_second": 76.972, | |
| "eval_steps_per_second": 9.622, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.720729309053138e-05, | |
| "loss": 0.0402, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.698551363125665e-05, | |
| "loss": 0.0254, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.67623594115297e-05, | |
| "loss": 0.0386, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 4.6537848492835324e-05, | |
| "loss": 0.033, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.696467399597168, | |
| "eval_runtime": 305.7738, | |
| "eval_samples_per_second": 76.943, | |
| "eval_steps_per_second": 9.618, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.631199904646576e-05, | |
| "loss": 0.0262, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.608482935204997e-05, | |
| "loss": 0.0298, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.585635779607416e-05, | |
| "loss": 0.0288, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.562660287039358e-05, | |
| "loss": 0.044, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.6436501741409302, | |
| "eval_runtime": 305.7319, | |
| "eval_samples_per_second": 76.953, | |
| "eval_steps_per_second": 9.62, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.539558317073588e-05, | |
| "loss": 0.0322, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 4.516331739519603e-05, | |
| "loss": 0.0363, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.492982434272291e-05, | |
| "loss": 0.0285, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.469512291159781e-05, | |
| "loss": 0.0305, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.6893681287765503, | |
| "eval_runtime": 305.7064, | |
| "eval_samples_per_second": 76.959, | |
| "eval_steps_per_second": 9.62, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.4459232097904836e-05, | |
| "loss": 0.0292, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.4222170993993444e-05, | |
| "loss": 0.0346, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.3983958786933116e-05, | |
| "loss": 0.0296, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 4.374461475696044e-05, | |
| "loss": 0.0363, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.5993568897247314, | |
| "eval_runtime": 305.6394, | |
| "eval_samples_per_second": 76.976, | |
| "eval_steps_per_second": 9.622, | |
| "step": 7200 | |
| } | |
| ], | |
| "max_steps": 18575, | |
| "num_train_epochs": 5, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |