| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 75.0, | |
| "global_step": 187500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.990119762874309e-05, | |
| "loss": 7.6579, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.09562864791743528, | |
| "eval_loss": 7.127312660217285, | |
| "eval_runtime": 239.9352, | |
| "eval_samples_per_second": 20.839, | |
| "eval_steps_per_second": 2.605, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.980119522868549e-05, | |
| "loss": 7.0332, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.11961642364018389, | |
| "eval_loss": 6.915997505187988, | |
| "eval_runtime": 238.3965, | |
| "eval_samples_per_second": 20.973, | |
| "eval_steps_per_second": 2.622, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.970119282862789e-05, | |
| "loss": 6.8887, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.12904858139542238, | |
| "eval_loss": 6.821927547454834, | |
| "eval_runtime": 239.3066, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 2.612, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.960119042857029e-05, | |
| "loss": 6.8053, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.13103776288974772, | |
| "eval_loss": 6.758518695831299, | |
| "eval_runtime": 238.5002, | |
| "eval_samples_per_second": 20.964, | |
| "eval_steps_per_second": 2.621, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.950118802851269e-05, | |
| "loss": 6.7592, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.1364351071286491, | |
| "eval_loss": 6.682760715484619, | |
| "eval_runtime": 238.971, | |
| "eval_samples_per_second": 20.923, | |
| "eval_steps_per_second": 2.615, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.940118562845509e-05, | |
| "loss": 6.6764, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.13949271934969193, | |
| "eval_loss": 6.636216640472412, | |
| "eval_runtime": 238.2351, | |
| "eval_samples_per_second": 20.988, | |
| "eval_steps_per_second": 2.623, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.930118322839748e-05, | |
| "loss": 6.6333, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.1388095837001635, | |
| "eval_loss": 6.624228000640869, | |
| "eval_runtime": 238.5516, | |
| "eval_samples_per_second": 20.96, | |
| "eval_steps_per_second": 2.62, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.920118082833988e-05, | |
| "loss": 6.5896, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.1399531007383465, | |
| "eval_loss": 6.5691633224487305, | |
| "eval_runtime": 239.1652, | |
| "eval_samples_per_second": 20.906, | |
| "eval_steps_per_second": 2.613, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.910117842828228e-05, | |
| "loss": 6.5774, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.14199867302770844, | |
| "eval_loss": 6.539389610290527, | |
| "eval_runtime": 238.2931, | |
| "eval_samples_per_second": 20.983, | |
| "eval_steps_per_second": 2.623, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.9001176028224685e-05, | |
| "loss": 6.5486, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.14192549527631204, | |
| "eval_loss": 6.52717399597168, | |
| "eval_runtime": 238.4964, | |
| "eval_samples_per_second": 20.965, | |
| "eval_steps_per_second": 2.621, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.890117362816708e-05, | |
| "loss": 6.5136, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.14366604383395618, | |
| "eval_loss": 6.514117240905762, | |
| "eval_runtime": 238.2132, | |
| "eval_samples_per_second": 20.99, | |
| "eval_steps_per_second": 2.624, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.880117122810948e-05, | |
| "loss": 6.4988, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.14545551844518384, | |
| "eval_loss": 6.504667282104492, | |
| "eval_runtime": 238.3225, | |
| "eval_samples_per_second": 20.98, | |
| "eval_steps_per_second": 2.622, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.8701168828051874e-05, | |
| "loss": 6.4956, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_accuracy": 0.14478254828400722, | |
| "eval_loss": 6.484868049621582, | |
| "eval_runtime": 238.9391, | |
| "eval_samples_per_second": 20.926, | |
| "eval_steps_per_second": 2.616, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.8601166427994274e-05, | |
| "loss": 6.4848, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_accuracy": 0.14653028416523506, | |
| "eval_loss": 6.466109275817871, | |
| "eval_runtime": 238.6887, | |
| "eval_samples_per_second": 20.948, | |
| "eval_steps_per_second": 2.618, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.8501164027936675e-05, | |
| "loss": 6.4672, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.14503110201270616, | |
| "eval_loss": 6.4636101722717285, | |
| "eval_runtime": 238.5511, | |
| "eval_samples_per_second": 20.96, | |
| "eval_steps_per_second": 2.62, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.840116162787907e-05, | |
| "loss": 6.4398, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.14670060391437695, | |
| "eval_loss": 6.445173263549805, | |
| "eval_runtime": 238.6611, | |
| "eval_samples_per_second": 20.95, | |
| "eval_steps_per_second": 2.619, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.830115922782147e-05, | |
| "loss": 6.4398, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.14309234861721049, | |
| "eval_loss": 6.446484565734863, | |
| "eval_runtime": 238.6523, | |
| "eval_samples_per_second": 20.951, | |
| "eval_steps_per_second": 2.619, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 4.8201156827763864e-05, | |
| "loss": 6.4143, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.1470335800879734, | |
| "eval_loss": 6.419277191162109, | |
| "eval_runtime": 239.0519, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 2.614, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.810115442770627e-05, | |
| "loss": 6.417, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.14629917323469946, | |
| "eval_loss": 6.421440601348877, | |
| "eval_runtime": 238.9987, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 2.615, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.8001152027648666e-05, | |
| "loss": 6.3938, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.14721643768292184, | |
| "eval_loss": 6.402393817901611, | |
| "eval_runtime": 238.7319, | |
| "eval_samples_per_second": 20.944, | |
| "eval_steps_per_second": 2.618, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 4.7901149627591066e-05, | |
| "loss": 6.3577, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.1467791629141584, | |
| "eval_loss": 6.405508041381836, | |
| "eval_runtime": 238.6576, | |
| "eval_samples_per_second": 20.951, | |
| "eval_steps_per_second": 2.619, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.780114722753346e-05, | |
| "loss": 6.3719, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_accuracy": 0.14650020970045946, | |
| "eval_loss": 6.390870094299316, | |
| "eval_runtime": 238.7638, | |
| "eval_samples_per_second": 20.941, | |
| "eval_steps_per_second": 2.618, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.770114482747586e-05, | |
| "loss": 6.3545, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_accuracy": 0.14796731042792302, | |
| "eval_loss": 6.386704921722412, | |
| "eval_runtime": 239.4196, | |
| "eval_samples_per_second": 20.884, | |
| "eval_steps_per_second": 2.61, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.760114242741826e-05, | |
| "loss": 6.3502, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_accuracy": 0.14863574330478854, | |
| "eval_loss": 6.36898136138916, | |
| "eval_runtime": 239.0117, | |
| "eval_samples_per_second": 20.919, | |
| "eval_steps_per_second": 2.615, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.7501140027360656e-05, | |
| "loss": 6.3476, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.14774925794518562, | |
| "eval_loss": 6.374772071838379, | |
| "eval_runtime": 238.4542, | |
| "eval_samples_per_second": 20.968, | |
| "eval_steps_per_second": 2.621, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 4.740113762730306e-05, | |
| "loss": 6.3198, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "eval_accuracy": 0.14550738585638578, | |
| "eval_loss": 6.365925312042236, | |
| "eval_runtime": 239.1139, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 2.614, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 4.730113522724546e-05, | |
| "loss": 6.3145, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "eval_accuracy": 0.14902667786765839, | |
| "eval_loss": 6.340302467346191, | |
| "eval_runtime": 238.6079, | |
| "eval_samples_per_second": 20.955, | |
| "eval_steps_per_second": 2.619, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.720113282718786e-05, | |
| "loss": 6.3114, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "eval_accuracy": 0.1485525671599362, | |
| "eval_loss": 6.338578224182129, | |
| "eval_runtime": 239.046, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 2.615, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 4.710113042713025e-05, | |
| "loss": 6.3071, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_accuracy": 0.14830638357038803, | |
| "eval_loss": 6.3231096267700195, | |
| "eval_runtime": 239.2069, | |
| "eval_samples_per_second": 20.902, | |
| "eval_steps_per_second": 2.613, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.7001128027072646e-05, | |
| "loss": 6.3148, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.15010454322169461, | |
| "eval_loss": 6.31591796875, | |
| "eval_runtime": 238.9169, | |
| "eval_samples_per_second": 20.928, | |
| "eval_steps_per_second": 2.616, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 4.6901125627015054e-05, | |
| "loss": 6.2703, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_accuracy": 0.149010929341272, | |
| "eval_loss": 6.327798366546631, | |
| "eval_runtime": 239.0819, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 2.614, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.680112322695745e-05, | |
| "loss": 6.272, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_accuracy": 0.14926184852480373, | |
| "eval_loss": 6.314311504364014, | |
| "eval_runtime": 239.1891, | |
| "eval_samples_per_second": 20.904, | |
| "eval_steps_per_second": 2.613, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 4.670112082689985e-05, | |
| "loss": 6.2713, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_accuracy": 0.149609282500592, | |
| "eval_loss": 6.310863971710205, | |
| "eval_runtime": 238.9461, | |
| "eval_samples_per_second": 20.925, | |
| "eval_steps_per_second": 2.616, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 4.660111842684224e-05, | |
| "loss": 6.2626, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_accuracy": 0.14950698945650215, | |
| "eval_loss": 6.288058757781982, | |
| "eval_runtime": 238.8827, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 2.616, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.6501116026784644e-05, | |
| "loss": 6.2542, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.15001838460595662, | |
| "eval_loss": 6.285544395446777, | |
| "eval_runtime": 238.7799, | |
| "eval_samples_per_second": 20.94, | |
| "eval_steps_per_second": 2.617, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.6401113626727044e-05, | |
| "loss": 6.226, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_accuracy": 0.15007755457193658, | |
| "eval_loss": 6.284069538116455, | |
| "eval_runtime": 238.9785, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 4.630111122666944e-05, | |
| "loss": 6.2225, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "eval_accuracy": 0.15004452640952928, | |
| "eval_loss": 6.269779682159424, | |
| "eval_runtime": 238.1129, | |
| "eval_samples_per_second": 20.998, | |
| "eval_steps_per_second": 2.625, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 4.620110882661184e-05, | |
| "loss": 6.2073, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "eval_accuracy": 0.1489249056948642, | |
| "eval_loss": 6.264680862426758, | |
| "eval_runtime": 239.8511, | |
| "eval_samples_per_second": 20.846, | |
| "eval_steps_per_second": 2.606, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 4.610110642655424e-05, | |
| "loss": 6.2133, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "eval_accuracy": 0.14988711325252577, | |
| "eval_loss": 6.258930683135986, | |
| "eval_runtime": 238.7682, | |
| "eval_samples_per_second": 20.941, | |
| "eval_steps_per_second": 2.618, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.600110402649664e-05, | |
| "loss": 6.2134, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.1510672200633593, | |
| "eval_loss": 6.249328136444092, | |
| "eval_runtime": 239.5811, | |
| "eval_samples_per_second": 20.87, | |
| "eval_steps_per_second": 2.609, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 4.5901101626439035e-05, | |
| "loss": 6.1887, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "eval_accuracy": 0.1502341927776338, | |
| "eval_loss": 6.242542743682861, | |
| "eval_runtime": 238.4196, | |
| "eval_samples_per_second": 20.971, | |
| "eval_steps_per_second": 2.621, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 4.5801099226381436e-05, | |
| "loss": 6.1822, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_accuracy": 0.15187036444962188, | |
| "eval_loss": 6.232594966888428, | |
| "eval_runtime": 239.3713, | |
| "eval_samples_per_second": 20.888, | |
| "eval_steps_per_second": 2.611, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 4.5701096826323836e-05, | |
| "loss": 6.1752, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_accuracy": 0.1495673710048999, | |
| "eval_loss": 6.239598274230957, | |
| "eval_runtime": 238.3388, | |
| "eval_samples_per_second": 20.979, | |
| "eval_steps_per_second": 2.622, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.560109442626623e-05, | |
| "loss": 6.1705, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "eval_accuracy": 0.15107269620915528, | |
| "eval_loss": 6.23054313659668, | |
| "eval_runtime": 239.3311, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 2.611, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.550109202620863e-05, | |
| "loss": 6.1737, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.15264056342116805, | |
| "eval_loss": 6.201099872589111, | |
| "eval_runtime": 238.7124, | |
| "eval_samples_per_second": 20.946, | |
| "eval_steps_per_second": 2.618, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 4.5401089626151025e-05, | |
| "loss": 6.1468, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_accuracy": 0.15174466124507308, | |
| "eval_loss": 6.213028430938721, | |
| "eval_runtime": 239.0381, | |
| "eval_samples_per_second": 20.917, | |
| "eval_steps_per_second": 2.615, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 4.530108722609343e-05, | |
| "loss": 6.1346, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_accuracy": 0.15341171411043722, | |
| "eval_loss": 6.193819522857666, | |
| "eval_runtime": 238.1389, | |
| "eval_samples_per_second": 20.996, | |
| "eval_steps_per_second": 2.625, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.520108482603583e-05, | |
| "loss": 6.126, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_accuracy": 0.15403517970455113, | |
| "eval_loss": 6.188257217407227, | |
| "eval_runtime": 239.6406, | |
| "eval_samples_per_second": 20.865, | |
| "eval_steps_per_second": 2.608, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 4.510108242597823e-05, | |
| "loss": 6.1265, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_accuracy": 0.1534727219928538, | |
| "eval_loss": 6.178363800048828, | |
| "eval_runtime": 238.9451, | |
| "eval_samples_per_second": 20.925, | |
| "eval_steps_per_second": 2.616, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.500108002592062e-05, | |
| "loss": 6.1141, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.15413779661230084, | |
| "eval_loss": 6.167110919952393, | |
| "eval_runtime": 239.3956, | |
| "eval_samples_per_second": 20.886, | |
| "eval_steps_per_second": 2.611, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 4.490107762586302e-05, | |
| "loss": 6.0804, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "eval_accuracy": 0.15433432565732236, | |
| "eval_loss": 6.159796714782715, | |
| "eval_runtime": 238.255, | |
| "eval_samples_per_second": 20.986, | |
| "eval_steps_per_second": 2.623, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 4.480107522580542e-05, | |
| "loss": 6.0756, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "eval_accuracy": 0.15528530161534182, | |
| "eval_loss": 6.153306484222412, | |
| "eval_runtime": 239.5862, | |
| "eval_samples_per_second": 20.869, | |
| "eval_steps_per_second": 2.609, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 4.470107282574782e-05, | |
| "loss": 6.0657, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "eval_accuracy": 0.1552249733339224, | |
| "eval_loss": 6.150942802429199, | |
| "eval_runtime": 238.6186, | |
| "eval_samples_per_second": 20.954, | |
| "eval_steps_per_second": 2.619, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 4.460107042569022e-05, | |
| "loss": 6.062, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "eval_accuracy": 0.1587447574438766, | |
| "eval_loss": 6.111793041229248, | |
| "eval_runtime": 240.3225, | |
| "eval_samples_per_second": 20.805, | |
| "eval_steps_per_second": 2.601, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.450106802563262e-05, | |
| "loss": 6.051, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.15917448452711824, | |
| "eval_loss": 6.102757930755615, | |
| "eval_runtime": 238.5988, | |
| "eval_samples_per_second": 20.956, | |
| "eval_steps_per_second": 2.619, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.440106562557502e-05, | |
| "loss": 5.9972, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "eval_accuracy": 0.1635643501862021, | |
| "eval_loss": 6.075224876403809, | |
| "eval_runtime": 239.5936, | |
| "eval_samples_per_second": 20.869, | |
| "eval_steps_per_second": 2.609, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.4301063225517413e-05, | |
| "loss": 5.9992, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "eval_accuracy": 0.16585055162650203, | |
| "eval_loss": 6.051377296447754, | |
| "eval_runtime": 238.4053, | |
| "eval_samples_per_second": 20.973, | |
| "eval_steps_per_second": 2.622, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.4201060825459814e-05, | |
| "loss": 5.9786, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "eval_accuracy": 0.16999095102797587, | |
| "eval_loss": 6.0217790603637695, | |
| "eval_runtime": 239.6751, | |
| "eval_samples_per_second": 20.862, | |
| "eval_steps_per_second": 2.608, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.4101058425402215e-05, | |
| "loss": 5.9425, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "eval_accuracy": 0.1729126550711828, | |
| "eval_loss": 5.975002288818359, | |
| "eval_runtime": 238.6151, | |
| "eval_samples_per_second": 20.954, | |
| "eval_steps_per_second": 2.619, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.400105602534461e-05, | |
| "loss": 5.8962, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.17712782712782713, | |
| "eval_loss": 5.941808700561523, | |
| "eval_runtime": 239.9021, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 2.605, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 4.390105362528701e-05, | |
| "loss": 5.8435, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "eval_accuracy": 0.1786500285756687, | |
| "eval_loss": 5.892694473266602, | |
| "eval_runtime": 238.1492, | |
| "eval_samples_per_second": 20.995, | |
| "eval_steps_per_second": 2.624, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.3801051225229404e-05, | |
| "loss": 5.8062, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "eval_accuracy": 0.1884558398438117, | |
| "eval_loss": 5.821302890777588, | |
| "eval_runtime": 238.0587, | |
| "eval_samples_per_second": 21.003, | |
| "eval_steps_per_second": 2.625, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.370104882517181e-05, | |
| "loss": 5.7915, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "eval_accuracy": 0.194766964409799, | |
| "eval_loss": 5.766781330108643, | |
| "eval_runtime": 238.7498, | |
| "eval_samples_per_second": 20.942, | |
| "eval_steps_per_second": 2.618, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4.3601046425114205e-05, | |
| "loss": 5.7237, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_accuracy": 0.2000967307534251, | |
| "eval_loss": 5.707735538482666, | |
| "eval_runtime": 238.212, | |
| "eval_samples_per_second": 20.99, | |
| "eval_steps_per_second": 2.624, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.3501044025056606e-05, | |
| "loss": 5.6816, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.2074816899981318, | |
| "eval_loss": 5.6437764167785645, | |
| "eval_runtime": 238.3771, | |
| "eval_samples_per_second": 20.975, | |
| "eval_steps_per_second": 2.622, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 4.3401041624999e-05, | |
| "loss": 5.5966, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "eval_accuracy": 0.21245663568914436, | |
| "eval_loss": 5.579566478729248, | |
| "eval_runtime": 238.7052, | |
| "eval_samples_per_second": 20.946, | |
| "eval_steps_per_second": 2.618, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 4.33010392249414e-05, | |
| "loss": 5.5319, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "eval_accuracy": 0.2188389812564588, | |
| "eval_loss": 5.523879528045654, | |
| "eval_runtime": 238.3135, | |
| "eval_samples_per_second": 20.981, | |
| "eval_steps_per_second": 2.623, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 4.32010368248838e-05, | |
| "loss": 5.4744, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_accuracy": 0.22693598869200868, | |
| "eval_loss": 5.4436564445495605, | |
| "eval_runtime": 239.2172, | |
| "eval_samples_per_second": 20.902, | |
| "eval_steps_per_second": 2.613, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 4.3101034424826196e-05, | |
| "loss": 5.4245, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "eval_accuracy": 0.23376848720407853, | |
| "eval_loss": 5.3778486251831055, | |
| "eval_runtime": 237.8545, | |
| "eval_samples_per_second": 21.021, | |
| "eval_steps_per_second": 2.628, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.3001032024768597e-05, | |
| "loss": 5.3751, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.23909228078814623, | |
| "eval_loss": 5.325531482696533, | |
| "eval_runtime": 239.3036, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 2.612, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 4.2901029624711e-05, | |
| "loss": 5.2751, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "eval_accuracy": 0.24685205362641527, | |
| "eval_loss": 5.252104759216309, | |
| "eval_runtime": 238.2439, | |
| "eval_samples_per_second": 20.987, | |
| "eval_steps_per_second": 2.623, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 4.28010272246534e-05, | |
| "loss": 5.2219, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "eval_accuracy": 0.2519453843197298, | |
| "eval_loss": 5.184392929077148, | |
| "eval_runtime": 238.9412, | |
| "eval_samples_per_second": 20.926, | |
| "eval_steps_per_second": 2.616, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 4.270102482459579e-05, | |
| "loss": 5.1513, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "eval_accuracy": 0.25571065989847713, | |
| "eval_loss": 5.144058704376221, | |
| "eval_runtime": 239.1692, | |
| "eval_samples_per_second": 20.906, | |
| "eval_steps_per_second": 2.613, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 4.2601022424538186e-05, | |
| "loss": 5.1198, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "eval_accuracy": 0.26201602768533194, | |
| "eval_loss": 5.08328914642334, | |
| "eval_runtime": 239.2967, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.2501020024480594e-05, | |
| "loss": 5.0865, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.26588186321967033, | |
| "eval_loss": 5.031526565551758, | |
| "eval_runtime": 239.4214, | |
| "eval_samples_per_second": 20.884, | |
| "eval_steps_per_second": 2.61, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 4.240101762442299e-05, | |
| "loss": 5.0009, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "eval_accuracy": 0.27209091683735137, | |
| "eval_loss": 4.977504730224609, | |
| "eval_runtime": 238.005, | |
| "eval_samples_per_second": 21.008, | |
| "eval_steps_per_second": 2.626, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 4.230101522436539e-05, | |
| "loss": 4.9533, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "eval_accuracy": 0.2761229329330592, | |
| "eval_loss": 4.92480993270874, | |
| "eval_runtime": 239.2788, | |
| "eval_samples_per_second": 20.896, | |
| "eval_steps_per_second": 2.612, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 4.220101282430778e-05, | |
| "loss": 4.8984, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "eval_accuracy": 0.284984501086343, | |
| "eval_loss": 4.843219757080078, | |
| "eval_runtime": 238.6717, | |
| "eval_samples_per_second": 20.949, | |
| "eval_steps_per_second": 2.619, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 4.210101042425018e-05, | |
| "loss": 4.8225, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "eval_accuracy": 0.2922410149325292, | |
| "eval_loss": 4.7489118576049805, | |
| "eval_runtime": 238.6056, | |
| "eval_samples_per_second": 20.955, | |
| "eval_steps_per_second": 2.619, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.2001008024192584e-05, | |
| "loss": 4.7467, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.3021739816363235, | |
| "eval_loss": 4.653831481933594, | |
| "eval_runtime": 238.1775, | |
| "eval_samples_per_second": 20.993, | |
| "eval_steps_per_second": 2.624, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 4.190100562413498e-05, | |
| "loss": 4.6515, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "eval_accuracy": 0.3053980176966654, | |
| "eval_loss": 4.602191925048828, | |
| "eval_runtime": 238.6405, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 2.619, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 4.180100322407738e-05, | |
| "loss": 4.5913, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "eval_accuracy": 0.31172282596673734, | |
| "eval_loss": 4.532454967498779, | |
| "eval_runtime": 238.4758, | |
| "eval_samples_per_second": 20.966, | |
| "eval_steps_per_second": 2.621, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 4.170100082401977e-05, | |
| "loss": 4.532, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "eval_accuracy": 0.3172949714616906, | |
| "eval_loss": 4.486767292022705, | |
| "eval_runtime": 238.5426, | |
| "eval_samples_per_second": 20.961, | |
| "eval_steps_per_second": 2.62, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.160099842396218e-05, | |
| "loss": 4.4654, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "eval_accuracy": 0.32319931360364396, | |
| "eval_loss": 4.4189629554748535, | |
| "eval_runtime": 238.5096, | |
| "eval_samples_per_second": 20.964, | |
| "eval_steps_per_second": 2.62, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.1500996023904575e-05, | |
| "loss": 4.4093, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.3282410682702511, | |
| "eval_loss": 4.374806880950928, | |
| "eval_runtime": 238.2081, | |
| "eval_samples_per_second": 20.99, | |
| "eval_steps_per_second": 2.624, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 4.1400993623846975e-05, | |
| "loss": 4.3464, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "eval_accuracy": 0.33113666533184927, | |
| "eval_loss": 4.329699516296387, | |
| "eval_runtime": 238.6019, | |
| "eval_samples_per_second": 20.955, | |
| "eval_steps_per_second": 2.619, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 4.130099122378937e-05, | |
| "loss": 4.3109, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "eval_accuracy": 0.33443005394851116, | |
| "eval_loss": 4.298059463500977, | |
| "eval_runtime": 239.4997, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 2.61, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.120098882373177e-05, | |
| "loss": 4.2486, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "eval_accuracy": 0.33968982981534496, | |
| "eval_loss": 4.248338222503662, | |
| "eval_runtime": 238.9263, | |
| "eval_samples_per_second": 20.927, | |
| "eval_steps_per_second": 2.616, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 4.110098642367417e-05, | |
| "loss": 4.2214, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "eval_accuracy": 0.3430102865749281, | |
| "eval_loss": 4.211354732513428, | |
| "eval_runtime": 239.8092, | |
| "eval_samples_per_second": 20.85, | |
| "eval_steps_per_second": 2.606, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.1000984023616565e-05, | |
| "loss": 4.1774, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.3472969219503573, | |
| "eval_loss": 4.166539669036865, | |
| "eval_runtime": 238.982, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 4.0900981623558966e-05, | |
| "loss": 4.1424, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "eval_accuracy": 0.34982222082376263, | |
| "eval_loss": 4.140753269195557, | |
| "eval_runtime": 239.4629, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.61, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 4.0800979223501366e-05, | |
| "loss": 4.1067, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "eval_accuracy": 0.3526568981561805, | |
| "eval_loss": 4.114173412322998, | |
| "eval_runtime": 239.2864, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 4.070097682344377e-05, | |
| "loss": 4.0837, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "eval_accuracy": 0.3564153178049743, | |
| "eval_loss": 4.076625823974609, | |
| "eval_runtime": 238.644, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 2.619, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 4.060097442338616e-05, | |
| "loss": 4.0442, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "eval_accuracy": 0.35937041559006977, | |
| "eval_loss": 4.049180030822754, | |
| "eval_runtime": 238.9064, | |
| "eval_samples_per_second": 20.929, | |
| "eval_steps_per_second": 2.616, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 4.050097202332856e-05, | |
| "loss": 4.0248, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.3630438412177381, | |
| "eval_loss": 4.01298189163208, | |
| "eval_runtime": 239.1093, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 2.614, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.040096962327096e-05, | |
| "loss": 3.9663, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_accuracy": 0.3619489778849462, | |
| "eval_loss": 4.020573616027832, | |
| "eval_runtime": 239.7356, | |
| "eval_samples_per_second": 20.856, | |
| "eval_steps_per_second": 2.607, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 4.030096722321336e-05, | |
| "loss": 3.9401, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "eval_accuracy": 0.3671375300214891, | |
| "eval_loss": 3.970278024673462, | |
| "eval_runtime": 238.9689, | |
| "eval_samples_per_second": 20.923, | |
| "eval_steps_per_second": 2.615, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 4.020096482315576e-05, | |
| "loss": 3.9246, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "eval_accuracy": 0.3694057226705796, | |
| "eval_loss": 3.955792188644409, | |
| "eval_runtime": 237.9835, | |
| "eval_samples_per_second": 21.01, | |
| "eval_steps_per_second": 2.626, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 4.010096242309815e-05, | |
| "loss": 3.9172, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "eval_accuracy": 0.3719208481724609, | |
| "eval_loss": 3.9305856227874756, | |
| "eval_runtime": 239.3028, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 2.612, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.000096002304056e-05, | |
| "loss": 3.8908, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.3750794239951685, | |
| "eval_loss": 3.898867130279541, | |
| "eval_runtime": 239.4161, | |
| "eval_samples_per_second": 20.884, | |
| "eval_steps_per_second": 2.611, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "learning_rate": 3.990095762298295e-05, | |
| "loss": 3.8366, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "eval_accuracy": 0.37685135603364095, | |
| "eval_loss": 3.877788782119751, | |
| "eval_runtime": 239.074, | |
| "eval_samples_per_second": 20.914, | |
| "eval_steps_per_second": 2.614, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 3.9800955222925354e-05, | |
| "loss": 3.8279, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "eval_accuracy": 0.37645562990796916, | |
| "eval_loss": 3.8702280521392822, | |
| "eval_runtime": 239.2592, | |
| "eval_samples_per_second": 20.898, | |
| "eval_steps_per_second": 2.612, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 3.970095282286775e-05, | |
| "loss": 3.7992, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "eval_accuracy": 0.38063372045240457, | |
| "eval_loss": 3.827329397201538, | |
| "eval_runtime": 239.4288, | |
| "eval_samples_per_second": 20.883, | |
| "eval_steps_per_second": 2.61, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.960095042281015e-05, | |
| "loss": 3.7949, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "eval_accuracy": 0.3803827148043566, | |
| "eval_loss": 3.829620599746704, | |
| "eval_runtime": 239.6513, | |
| "eval_samples_per_second": 20.864, | |
| "eval_steps_per_second": 2.608, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.950094802275255e-05, | |
| "loss": 3.7669, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.38461295677917423, | |
| "eval_loss": 3.788926601409912, | |
| "eval_runtime": 240.0632, | |
| "eval_samples_per_second": 20.828, | |
| "eval_steps_per_second": 2.603, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 21.2, | |
| "learning_rate": 3.9400945622694944e-05, | |
| "loss": 3.7173, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 21.2, | |
| "eval_accuracy": 0.3850090819647317, | |
| "eval_loss": 3.7976882457733154, | |
| "eval_runtime": 239.5627, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "learning_rate": 3.9300943222637344e-05, | |
| "loss": 3.7073, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "eval_accuracy": 0.38859488849548585, | |
| "eval_loss": 3.7608718872070312, | |
| "eval_runtime": 238.4323, | |
| "eval_samples_per_second": 20.97, | |
| "eval_steps_per_second": 2.621, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 3.9200940822579745e-05, | |
| "loss": 3.7031, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "eval_accuracy": 0.39072964788576736, | |
| "eval_loss": 3.738675832748413, | |
| "eval_runtime": 239.1766, | |
| "eval_samples_per_second": 20.905, | |
| "eval_steps_per_second": 2.613, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 3.9100938422522146e-05, | |
| "loss": 3.678, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "eval_accuracy": 0.3919720448368493, | |
| "eval_loss": 3.7181637287139893, | |
| "eval_runtime": 238.4998, | |
| "eval_samples_per_second": 20.964, | |
| "eval_steps_per_second": 2.621, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.900093602246454e-05, | |
| "loss": 3.6664, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.39393000929080213, | |
| "eval_loss": 3.6974339485168457, | |
| "eval_runtime": 239.9697, | |
| "eval_samples_per_second": 20.836, | |
| "eval_steps_per_second": 2.604, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 3.890093362240694e-05, | |
| "loss": 3.63, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "eval_accuracy": 0.395838777829905, | |
| "eval_loss": 3.683786630630493, | |
| "eval_runtime": 238.6856, | |
| "eval_samples_per_second": 20.948, | |
| "eval_steps_per_second": 2.619, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 3.880093122234934e-05, | |
| "loss": 3.6072, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "eval_accuracy": 0.39780745729365696, | |
| "eval_loss": 3.668595314025879, | |
| "eval_runtime": 238.9371, | |
| "eval_samples_per_second": 20.926, | |
| "eval_steps_per_second": 2.616, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 22.6, | |
| "learning_rate": 3.8700928822291736e-05, | |
| "loss": 3.5878, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 22.6, | |
| "eval_accuracy": 0.4004617930964775, | |
| "eval_loss": 3.6446495056152344, | |
| "eval_runtime": 238.383, | |
| "eval_samples_per_second": 20.975, | |
| "eval_steps_per_second": 2.622, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 3.8600926422234136e-05, | |
| "loss": 3.5748, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "eval_accuracy": 0.4013079441994284, | |
| "eval_loss": 3.633631706237793, | |
| "eval_runtime": 239.4332, | |
| "eval_samples_per_second": 20.883, | |
| "eval_steps_per_second": 2.61, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 3.850092402217653e-05, | |
| "loss": 3.5668, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4023029638942638, | |
| "eval_loss": 3.618192672729492, | |
| "eval_runtime": 240.1475, | |
| "eval_samples_per_second": 20.821, | |
| "eval_steps_per_second": 2.603, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 3.840092162211894e-05, | |
| "loss": 3.508, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "eval_accuracy": 0.40511161946832847, | |
| "eval_loss": 3.5944156646728516, | |
| "eval_runtime": 240.7097, | |
| "eval_samples_per_second": 20.772, | |
| "eval_steps_per_second": 2.596, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 3.830091922206133e-05, | |
| "loss": 3.5188, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "eval_accuracy": 0.4101088779063732, | |
| "eval_loss": 3.5640573501586914, | |
| "eval_runtime": 238.4535, | |
| "eval_samples_per_second": 20.968, | |
| "eval_steps_per_second": 2.621, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 3.820091682200373e-05, | |
| "loss": 3.4902, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "eval_accuracy": 0.41012237850373057, | |
| "eval_loss": 3.5568885803222656, | |
| "eval_runtime": 239.3958, | |
| "eval_samples_per_second": 20.886, | |
| "eval_steps_per_second": 2.611, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "learning_rate": 3.810091442194613e-05, | |
| "loss": 3.4667, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "eval_accuracy": 0.41220216515450525, | |
| "eval_loss": 3.5408358573913574, | |
| "eval_runtime": 238.5286, | |
| "eval_samples_per_second": 20.962, | |
| "eval_steps_per_second": 2.62, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 3.800091202188853e-05, | |
| "loss": 3.4734, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4146663257801724, | |
| "eval_loss": 3.5163965225219727, | |
| "eval_runtime": 240.0735, | |
| "eval_samples_per_second": 20.827, | |
| "eval_steps_per_second": 2.603, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 3.790090962183093e-05, | |
| "loss": 3.4178, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "eval_accuracy": 0.4166579906298803, | |
| "eval_loss": 3.5096375942230225, | |
| "eval_runtime": 239.0893, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 2.614, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "learning_rate": 3.780090722177332e-05, | |
| "loss": 3.4139, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "eval_accuracy": 0.41929409690187325, | |
| "eval_loss": 3.489515542984009, | |
| "eval_runtime": 240.9991, | |
| "eval_samples_per_second": 20.747, | |
| "eval_steps_per_second": 2.593, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 3.770090482171572e-05, | |
| "loss": 3.4161, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "eval_accuracy": 0.42010133427676133, | |
| "eval_loss": 3.475292682647705, | |
| "eval_runtime": 238.9304, | |
| "eval_samples_per_second": 20.927, | |
| "eval_steps_per_second": 2.616, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 3.7600902421658124e-05, | |
| "loss": 3.3962, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "eval_accuracy": 0.4221688310052524, | |
| "eval_loss": 3.4501795768737793, | |
| "eval_runtime": 240.1731, | |
| "eval_samples_per_second": 20.818, | |
| "eval_steps_per_second": 2.602, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.750090002160052e-05, | |
| "loss": 3.3857, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.42396696829715874, | |
| "eval_loss": 3.4505577087402344, | |
| "eval_runtime": 239.537, | |
| "eval_samples_per_second": 20.874, | |
| "eval_steps_per_second": 2.609, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "learning_rate": 3.740089762154292e-05, | |
| "loss": 3.3437, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "eval_accuracy": 0.42821535707983566, | |
| "eval_loss": 3.4162397384643555, | |
| "eval_runtime": 239.3465, | |
| "eval_samples_per_second": 20.89, | |
| "eval_steps_per_second": 2.611, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 25.4, | |
| "learning_rate": 3.730089522148531e-05, | |
| "loss": 3.3282, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 25.4, | |
| "eval_accuracy": 0.42975245728349876, | |
| "eval_loss": 3.401306629180908, | |
| "eval_runtime": 238.9024, | |
| "eval_samples_per_second": 20.929, | |
| "eval_steps_per_second": 2.616, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 3.720089282142772e-05, | |
| "loss": 3.3285, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "eval_accuracy": 0.4319420899272967, | |
| "eval_loss": 3.3905553817749023, | |
| "eval_runtime": 240.2665, | |
| "eval_samples_per_second": 20.81, | |
| "eval_steps_per_second": 2.601, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "learning_rate": 3.7100890421370114e-05, | |
| "loss": 3.3161, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "eval_accuracy": 0.4342018381086879, | |
| "eval_loss": 3.365351915359497, | |
| "eval_runtime": 239.2968, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 3.7000888021312515e-05, | |
| "loss": 3.3026, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.434839985763914, | |
| "eval_loss": 3.3654284477233887, | |
| "eval_runtime": 239.0653, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 2.614, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "learning_rate": 3.690088562125491e-05, | |
| "loss": 3.2554, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "eval_accuracy": 0.43755692455598844, | |
| "eval_loss": 3.345842123031616, | |
| "eval_runtime": 239.4412, | |
| "eval_samples_per_second": 20.882, | |
| "eval_steps_per_second": 2.61, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 3.680088322119731e-05, | |
| "loss": 3.2426, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "eval_accuracy": 0.4402917592198749, | |
| "eval_loss": 3.334620237350464, | |
| "eval_runtime": 239.2321, | |
| "eval_samples_per_second": 20.9, | |
| "eval_steps_per_second": 2.613, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 26.6, | |
| "learning_rate": 3.670088082113971e-05, | |
| "loss": 3.2419, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 26.6, | |
| "eval_accuracy": 0.4414129103148642, | |
| "eval_loss": 3.3168656826019287, | |
| "eval_runtime": 238.7655, | |
| "eval_samples_per_second": 20.941, | |
| "eval_steps_per_second": 2.618, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 3.6600878421082105e-05, | |
| "loss": 3.2503, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "eval_accuracy": 0.4437969829978306, | |
| "eval_loss": 3.299358606338501, | |
| "eval_runtime": 240.0903, | |
| "eval_samples_per_second": 20.825, | |
| "eval_steps_per_second": 2.603, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 3.6500876021024505e-05, | |
| "loss": 3.234, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4456840349724567, | |
| "eval_loss": 3.290809392929077, | |
| "eval_runtime": 239.1298, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 2.614, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 3.6400873620966906e-05, | |
| "loss": 3.1794, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "eval_accuracy": 0.4489755289834922, | |
| "eval_loss": 3.273737907409668, | |
| "eval_runtime": 239.1064, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 2.614, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 3.630087122090931e-05, | |
| "loss": 3.1827, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "eval_accuracy": 0.44896031733539016, | |
| "eval_loss": 3.2674996852874756, | |
| "eval_runtime": 238.9338, | |
| "eval_samples_per_second": 20.926, | |
| "eval_steps_per_second": 2.616, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 3.62008688208517e-05, | |
| "loss": 3.1748, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "eval_accuracy": 0.4508367080874434, | |
| "eval_loss": 3.253206491470337, | |
| "eval_runtime": 239.5701, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 3.61008664207941e-05, | |
| "loss": 3.1795, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "eval_accuracy": 0.4520478699877418, | |
| "eval_loss": 3.2528598308563232, | |
| "eval_runtime": 238.6747, | |
| "eval_samples_per_second": 20.949, | |
| "eval_steps_per_second": 2.619, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.6000864020736496e-05, | |
| "loss": 3.1664, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.45429478372104043, | |
| "eval_loss": 3.2276272773742676, | |
| "eval_runtime": 239.9976, | |
| "eval_samples_per_second": 20.834, | |
| "eval_steps_per_second": 2.604, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "learning_rate": 3.59008616206789e-05, | |
| "loss": 3.0937, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "eval_accuracy": 0.45732565941802994, | |
| "eval_loss": 3.2136926651000977, | |
| "eval_runtime": 238.8553, | |
| "eval_samples_per_second": 20.933, | |
| "eval_steps_per_second": 2.617, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 3.58008592206213e-05, | |
| "loss": 3.1302, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "eval_accuracy": 0.45828199538748304, | |
| "eval_loss": 3.2121808528900146, | |
| "eval_runtime": 240.2268, | |
| "eval_samples_per_second": 20.814, | |
| "eval_steps_per_second": 2.602, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "learning_rate": 3.570085682056369e-05, | |
| "loss": 3.1121, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "eval_accuracy": 0.45979415210572067, | |
| "eval_loss": 3.2013251781463623, | |
| "eval_runtime": 239.2805, | |
| "eval_samples_per_second": 20.896, | |
| "eval_steps_per_second": 2.612, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.560085442050609e-05, | |
| "loss": 3.1117, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "eval_accuracy": 0.46116117510718196, | |
| "eval_loss": 3.1767895221710205, | |
| "eval_runtime": 240.4898, | |
| "eval_samples_per_second": 20.791, | |
| "eval_steps_per_second": 2.599, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 3.550085202044849e-05, | |
| "loss": 3.0967, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.46315271898609695, | |
| "eval_loss": 3.175037384033203, | |
| "eval_runtime": 239.5716, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "learning_rate": 3.5400849620390894e-05, | |
| "loss": 3.0433, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "eval_accuracy": 0.46477897932081197, | |
| "eval_loss": 3.1635282039642334, | |
| "eval_runtime": 239.7456, | |
| "eval_samples_per_second": 20.855, | |
| "eval_steps_per_second": 2.607, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "learning_rate": 3.530084722033329e-05, | |
| "loss": 3.0561, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "eval_accuracy": 0.46795523906408953, | |
| "eval_loss": 3.1412038803100586, | |
| "eval_runtime": 238.8196, | |
| "eval_samples_per_second": 20.936, | |
| "eval_steps_per_second": 2.617, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 3.520084482027569e-05, | |
| "loss": 3.0527, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "eval_accuracy": 0.46849550206201507, | |
| "eval_loss": 3.1406843662261963, | |
| "eval_runtime": 239.7188, | |
| "eval_samples_per_second": 20.858, | |
| "eval_steps_per_second": 2.607, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 29.8, | |
| "learning_rate": 3.510084242021809e-05, | |
| "loss": 3.0449, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 29.8, | |
| "eval_accuracy": 0.4677367515550262, | |
| "eval_loss": 3.13971209526062, | |
| "eval_runtime": 239.4737, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 2.61, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.500084002016048e-05, | |
| "loss": 3.0446, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.47304644334291035, | |
| "eval_loss": 3.10322642326355, | |
| "eval_runtime": 238.8991, | |
| "eval_samples_per_second": 20.929, | |
| "eval_steps_per_second": 2.616, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 30.2, | |
| "learning_rate": 3.4900837620102884e-05, | |
| "loss": 3.0095, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 30.2, | |
| "eval_accuracy": 0.4724041544924169, | |
| "eval_loss": 3.103961706161499, | |
| "eval_runtime": 240.0302, | |
| "eval_samples_per_second": 20.831, | |
| "eval_steps_per_second": 2.604, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 3.480083522004528e-05, | |
| "loss": 2.9953, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "eval_accuracy": 0.475397151249092, | |
| "eval_loss": 3.088655948638916, | |
| "eval_runtime": 238.9923, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 2.615, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "learning_rate": 3.4700832819987686e-05, | |
| "loss": 2.9744, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "eval_accuracy": 0.4752069375763294, | |
| "eval_loss": 3.0858309268951416, | |
| "eval_runtime": 239.2927, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "learning_rate": 3.460083041993008e-05, | |
| "loss": 2.9941, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "eval_accuracy": 0.4753717486767733, | |
| "eval_loss": 3.087771415710449, | |
| "eval_runtime": 239.4588, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.61, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 3.450082801987248e-05, | |
| "loss": 2.982, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.47787563198971167, | |
| "eval_loss": 3.0625386238098145, | |
| "eval_runtime": 239.7845, | |
| "eval_samples_per_second": 20.852, | |
| "eval_steps_per_second": 2.607, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "learning_rate": 3.4400825619814875e-05, | |
| "loss": 2.9441, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "eval_accuracy": 0.4781303466693604, | |
| "eval_loss": 3.0685055255889893, | |
| "eval_runtime": 239.71, | |
| "eval_samples_per_second": 20.859, | |
| "eval_steps_per_second": 2.607, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "learning_rate": 3.4300823219757275e-05, | |
| "loss": 2.954, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 31.4, | |
| "eval_accuracy": 0.48178897637795276, | |
| "eval_loss": 3.048638105392456, | |
| "eval_runtime": 239.3662, | |
| "eval_samples_per_second": 20.888, | |
| "eval_steps_per_second": 2.611, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 3.4200820819699676e-05, | |
| "loss": 2.9435, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "eval_accuracy": 0.4798843674965247, | |
| "eval_loss": 3.0472371578216553, | |
| "eval_runtime": 239.0072, | |
| "eval_samples_per_second": 20.92, | |
| "eval_steps_per_second": 2.615, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 3.410081841964207e-05, | |
| "loss": 2.9319, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "eval_accuracy": 0.48184346093459357, | |
| "eval_loss": 3.0237534046173096, | |
| "eval_runtime": 239.7344, | |
| "eval_samples_per_second": 20.856, | |
| "eval_steps_per_second": 2.607, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 3.400081601958447e-05, | |
| "loss": 2.9331, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.48462323691055215, | |
| "eval_loss": 3.0231850147247314, | |
| "eval_runtime": 238.7423, | |
| "eval_samples_per_second": 20.943, | |
| "eval_steps_per_second": 2.618, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 3.390081361952687e-05, | |
| "loss": 2.9014, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "eval_accuracy": 0.48449900049580463, | |
| "eval_loss": 3.018786907196045, | |
| "eval_runtime": 238.4212, | |
| "eval_samples_per_second": 20.971, | |
| "eval_steps_per_second": 2.621, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 3.380081121946927e-05, | |
| "loss": 2.8917, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "eval_accuracy": 0.4857029500949358, | |
| "eval_loss": 3.0059878826141357, | |
| "eval_runtime": 239.3143, | |
| "eval_samples_per_second": 20.893, | |
| "eval_steps_per_second": 2.612, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 32.6, | |
| "learning_rate": 3.3700808819411667e-05, | |
| "loss": 2.8968, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 32.6, | |
| "eval_accuracy": 0.4856941143840495, | |
| "eval_loss": 3.0099101066589355, | |
| "eval_runtime": 238.6193, | |
| "eval_samples_per_second": 20.954, | |
| "eval_steps_per_second": 2.619, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 3.360080641935407e-05, | |
| "loss": 2.8961, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "eval_accuracy": 0.4874124592319167, | |
| "eval_loss": 2.9975407123565674, | |
| "eval_runtime": 239.4937, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 2.61, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.350080401929647e-05, | |
| "loss": 2.8857, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.488242813118945, | |
| "eval_loss": 2.9877071380615234, | |
| "eval_runtime": 238.7976, | |
| "eval_samples_per_second": 20.938, | |
| "eval_steps_per_second": 2.617, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 33.2, | |
| "learning_rate": 3.340080161923886e-05, | |
| "loss": 2.8631, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 33.2, | |
| "eval_accuracy": 0.49157931890808476, | |
| "eval_loss": 2.9715187549591064, | |
| "eval_runtime": 238.9736, | |
| "eval_samples_per_second": 20.923, | |
| "eval_steps_per_second": 2.615, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.330079921918126e-05, | |
| "loss": 2.8642, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "eval_accuracy": 0.49055765035247234, | |
| "eval_loss": 2.9709725379943848, | |
| "eval_runtime": 239.361, | |
| "eval_samples_per_second": 20.889, | |
| "eval_steps_per_second": 2.611, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 3.320079681912366e-05, | |
| "loss": 2.859, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "eval_accuracy": 0.4905766366229897, | |
| "eval_loss": 2.974759101867676, | |
| "eval_runtime": 239.3057, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 2.612, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "learning_rate": 3.3100794419066064e-05, | |
| "loss": 2.8308, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "eval_accuracy": 0.4920043569545519, | |
| "eval_loss": 2.9632480144500732, | |
| "eval_runtime": 239.1871, | |
| "eval_samples_per_second": 20.904, | |
| "eval_steps_per_second": 2.613, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.300079201900846e-05, | |
| "loss": 2.8486, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4936041140507698, | |
| "eval_loss": 2.947859048843384, | |
| "eval_runtime": 239.9603, | |
| "eval_samples_per_second": 20.837, | |
| "eval_steps_per_second": 2.605, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "learning_rate": 3.290078961895085e-05, | |
| "loss": 2.8018, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "eval_accuracy": 0.49392006520647136, | |
| "eval_loss": 2.9504497051239014, | |
| "eval_runtime": 239.0602, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 2.614, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 3.280078721889325e-05, | |
| "loss": 2.8078, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "eval_accuracy": 0.49590170397025385, | |
| "eval_loss": 2.939467668533325, | |
| "eval_runtime": 239.5778, | |
| "eval_samples_per_second": 20.87, | |
| "eval_steps_per_second": 2.609, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 34.6, | |
| "learning_rate": 3.2700784818835654e-05, | |
| "loss": 2.8194, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 34.6, | |
| "eval_accuracy": 0.49452836394919286, | |
| "eval_loss": 2.9382665157318115, | |
| "eval_runtime": 239.129, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 2.614, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 34.8, | |
| "learning_rate": 3.2600782418778055e-05, | |
| "loss": 2.8219, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 34.8, | |
| "eval_accuracy": 0.4967188432146814, | |
| "eval_loss": 2.9314422607421875, | |
| "eval_runtime": 239.8662, | |
| "eval_samples_per_second": 20.845, | |
| "eval_steps_per_second": 2.606, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.250078001872045e-05, | |
| "loss": 2.8107, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4967919542148713, | |
| "eval_loss": 2.9249651432037354, | |
| "eval_runtime": 239.2643, | |
| "eval_samples_per_second": 20.897, | |
| "eval_steps_per_second": 2.612, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 3.240077761866285e-05, | |
| "loss": 2.7785, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "eval_accuracy": 0.4987307763864494, | |
| "eval_loss": 2.918447256088257, | |
| "eval_runtime": 238.6175, | |
| "eval_samples_per_second": 20.954, | |
| "eval_steps_per_second": 2.619, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "learning_rate": 3.230077521860525e-05, | |
| "loss": 2.7726, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 35.4, | |
| "eval_accuracy": 0.499268800358809, | |
| "eval_loss": 2.9100756645202637, | |
| "eval_runtime": 239.3281, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 2.611, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "learning_rate": 3.2200772818547644e-05, | |
| "loss": 2.7508, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "eval_accuracy": 0.4988590950922179, | |
| "eval_loss": 2.9117419719696045, | |
| "eval_runtime": 239.6738, | |
| "eval_samples_per_second": 20.862, | |
| "eval_steps_per_second": 2.608, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "learning_rate": 3.2100770418490045e-05, | |
| "loss": 2.7862, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "eval_accuracy": 0.5026493096646942, | |
| "eval_loss": 2.8842239379882812, | |
| "eval_runtime": 239.5089, | |
| "eval_samples_per_second": 20.876, | |
| "eval_steps_per_second": 2.61, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 3.200076801843244e-05, | |
| "loss": 2.7591, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.501588354174561, | |
| "eval_loss": 2.894536018371582, | |
| "eval_runtime": 238.9394, | |
| "eval_samples_per_second": 20.926, | |
| "eval_steps_per_second": 2.616, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 36.2, | |
| "learning_rate": 3.190076561837485e-05, | |
| "loss": 2.737, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 36.2, | |
| "eval_accuracy": 0.5023016269467401, | |
| "eval_loss": 2.872495651245117, | |
| "eval_runtime": 239.9672, | |
| "eval_samples_per_second": 20.836, | |
| "eval_steps_per_second": 2.605, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 36.4, | |
| "learning_rate": 3.180076321831724e-05, | |
| "loss": 2.7336, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 36.4, | |
| "eval_accuracy": 0.5033328195433141, | |
| "eval_loss": 2.881958484649658, | |
| "eval_runtime": 239.4309, | |
| "eval_samples_per_second": 20.883, | |
| "eval_steps_per_second": 2.61, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "learning_rate": 3.170076081825964e-05, | |
| "loss": 2.7505, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "eval_accuracy": 0.5042960942014569, | |
| "eval_loss": 2.8711090087890625, | |
| "eval_runtime": 239.0632, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 2.614, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 3.1600758418202036e-05, | |
| "loss": 2.7342, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "eval_accuracy": 0.5062909670999637, | |
| "eval_loss": 2.8555378913879395, | |
| "eval_runtime": 238.9919, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 2.615, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 3.1500756018144436e-05, | |
| "loss": 2.7344, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.507249352454356, | |
| "eval_loss": 2.843308687210083, | |
| "eval_runtime": 239.4594, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.61, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 3.140075361808684e-05, | |
| "loss": 2.7074, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "eval_accuracy": 0.5069092076602495, | |
| "eval_loss": 2.843485116958618, | |
| "eval_runtime": 238.9804, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 37.4, | |
| "learning_rate": 3.130075121802923e-05, | |
| "loss": 2.7078, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 37.4, | |
| "eval_accuracy": 0.5066123820683948, | |
| "eval_loss": 2.8465309143066406, | |
| "eval_runtime": 239.3346, | |
| "eval_samples_per_second": 20.891, | |
| "eval_steps_per_second": 2.611, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "learning_rate": 3.120074881797163e-05, | |
| "loss": 2.708, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "eval_accuracy": 0.5065022031997726, | |
| "eval_loss": 2.8465352058410645, | |
| "eval_runtime": 239.3543, | |
| "eval_samples_per_second": 20.89, | |
| "eval_steps_per_second": 2.611, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "learning_rate": 3.110074641791403e-05, | |
| "loss": 2.6835, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "eval_accuracy": 0.5073458075648071, | |
| "eval_loss": 2.8454036712646484, | |
| "eval_runtime": 238.5106, | |
| "eval_samples_per_second": 20.963, | |
| "eval_steps_per_second": 2.62, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 3.1000744017856434e-05, | |
| "loss": 2.7154, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5081197929815703, | |
| "eval_loss": 2.8387258052825928, | |
| "eval_runtime": 239.2141, | |
| "eval_samples_per_second": 20.902, | |
| "eval_steps_per_second": 2.613, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 38.2, | |
| "learning_rate": 3.090074161779883e-05, | |
| "loss": 2.6777, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 38.2, | |
| "eval_accuracy": 0.5092756865772764, | |
| "eval_loss": 2.83198618888855, | |
| "eval_runtime": 239.2553, | |
| "eval_samples_per_second": 20.898, | |
| "eval_steps_per_second": 2.612, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 3.080073921774123e-05, | |
| "loss": 2.6722, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "eval_accuracy": 0.5109568775574441, | |
| "eval_loss": 2.820936441421509, | |
| "eval_runtime": 239.1462, | |
| "eval_samples_per_second": 20.908, | |
| "eval_steps_per_second": 2.613, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 38.6, | |
| "learning_rate": 3.070073681768363e-05, | |
| "loss": 2.6708, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 38.6, | |
| "eval_accuracy": 0.5117181222012486, | |
| "eval_loss": 2.8265380859375, | |
| "eval_runtime": 239.0035, | |
| "eval_samples_per_second": 20.92, | |
| "eval_steps_per_second": 2.615, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 38.8, | |
| "learning_rate": 3.060073441762602e-05, | |
| "loss": 2.6511, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 38.8, | |
| "eval_accuracy": 0.5104035925348941, | |
| "eval_loss": 2.8190081119537354, | |
| "eval_runtime": 238.9835, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 3.0500732017568424e-05, | |
| "loss": 2.6588, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.511878533029498, | |
| "eval_loss": 2.8074145317077637, | |
| "eval_runtime": 238.8839, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 2.616, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 3.040072961751082e-05, | |
| "loss": 2.6394, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "eval_accuracy": 0.5138737260593822, | |
| "eval_loss": 2.804438591003418, | |
| "eval_runtime": 239.6863, | |
| "eval_samples_per_second": 20.861, | |
| "eval_steps_per_second": 2.608, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 39.4, | |
| "learning_rate": 3.0300727217453222e-05, | |
| "loss": 2.6258, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 39.4, | |
| "eval_accuracy": 0.5143354155135605, | |
| "eval_loss": 2.796783208847046, | |
| "eval_runtime": 239.0541, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 2.614, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 39.6, | |
| "learning_rate": 3.020072481739562e-05, | |
| "loss": 2.6519, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 39.6, | |
| "eval_accuracy": 0.512845071487533, | |
| "eval_loss": 2.802494525909424, | |
| "eval_runtime": 239.4204, | |
| "eval_samples_per_second": 20.884, | |
| "eval_steps_per_second": 2.61, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 39.8, | |
| "learning_rate": 3.0100722417338017e-05, | |
| "loss": 2.637, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 39.8, | |
| "eval_accuracy": 0.515363185645707, | |
| "eval_loss": 2.787698268890381, | |
| "eval_runtime": 239.9441, | |
| "eval_samples_per_second": 20.838, | |
| "eval_steps_per_second": 2.605, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.0000720017280414e-05, | |
| "loss": 2.641, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5151119273466245, | |
| "eval_loss": 2.7949695587158203, | |
| "eval_runtime": 238.5726, | |
| "eval_samples_per_second": 20.958, | |
| "eval_steps_per_second": 2.62, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 40.2, | |
| "learning_rate": 2.9900717617222812e-05, | |
| "loss": 2.6178, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 40.2, | |
| "eval_accuracy": 0.5161491701558796, | |
| "eval_loss": 2.79156494140625, | |
| "eval_runtime": 239.0536, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 2.614, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "learning_rate": 2.9800715217165216e-05, | |
| "loss": 2.6176, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "eval_accuracy": 0.5171055870046763, | |
| "eval_loss": 2.77885103225708, | |
| "eval_runtime": 238.5263, | |
| "eval_samples_per_second": 20.962, | |
| "eval_steps_per_second": 2.62, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 40.6, | |
| "learning_rate": 2.9700712817107613e-05, | |
| "loss": 2.6063, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 40.6, | |
| "eval_accuracy": 0.5157570081079291, | |
| "eval_loss": 2.7819836139678955, | |
| "eval_runtime": 239.7277, | |
| "eval_samples_per_second": 20.857, | |
| "eval_steps_per_second": 2.607, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "learning_rate": 2.960071041705001e-05, | |
| "loss": 2.6006, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "eval_accuracy": 0.5179590168867658, | |
| "eval_loss": 2.7666218280792236, | |
| "eval_runtime": 239.777, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 2.607, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 2.9500708016992408e-05, | |
| "loss": 2.5968, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5197707375448762, | |
| "eval_loss": 2.7592687606811523, | |
| "eval_runtime": 240.0119, | |
| "eval_samples_per_second": 20.832, | |
| "eval_steps_per_second": 2.604, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "learning_rate": 2.940070561693481e-05, | |
| "loss": 2.5773, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "eval_accuracy": 0.5210189873417721, | |
| "eval_loss": 2.751286745071411, | |
| "eval_runtime": 238.9629, | |
| "eval_samples_per_second": 20.924, | |
| "eval_steps_per_second": 2.615, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 41.4, | |
| "learning_rate": 2.9300703216877206e-05, | |
| "loss": 2.6042, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 41.4, | |
| "eval_accuracy": 0.5182829688096432, | |
| "eval_loss": 2.756362199783325, | |
| "eval_runtime": 238.761, | |
| "eval_samples_per_second": 20.941, | |
| "eval_steps_per_second": 2.618, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "learning_rate": 2.9200700816819604e-05, | |
| "loss": 2.5869, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "eval_accuracy": 0.5194518990938655, | |
| "eval_loss": 2.7505102157592773, | |
| "eval_runtime": 239.377, | |
| "eval_samples_per_second": 20.888, | |
| "eval_steps_per_second": 2.611, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 2.9100698416762e-05, | |
| "loss": 2.5678, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "eval_accuracy": 0.5229825642971183, | |
| "eval_loss": 2.7337899208068848, | |
| "eval_runtime": 239.8535, | |
| "eval_samples_per_second": 20.846, | |
| "eval_steps_per_second": 2.606, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 2.9000696016704405e-05, | |
| "loss": 2.5901, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5217317192506195, | |
| "eval_loss": 2.742098808288574, | |
| "eval_runtime": 239.5301, | |
| "eval_samples_per_second": 20.874, | |
| "eval_steps_per_second": 2.609, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 42.2, | |
| "learning_rate": 2.8900693616646803e-05, | |
| "loss": 2.5389, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 42.2, | |
| "eval_accuracy": 0.5203878282565099, | |
| "eval_loss": 2.750554323196411, | |
| "eval_runtime": 239.9053, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 2.605, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 42.4, | |
| "learning_rate": 2.88006912165892e-05, | |
| "loss": 2.542, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 42.4, | |
| "eval_accuracy": 0.5211733971231627, | |
| "eval_loss": 2.745476007461548, | |
| "eval_runtime": 239.1309, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 2.614, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 42.6, | |
| "learning_rate": 2.8700688816531594e-05, | |
| "loss": 2.5589, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 42.6, | |
| "eval_accuracy": 0.5228571609000146, | |
| "eval_loss": 2.731588363647461, | |
| "eval_runtime": 239.7976, | |
| "eval_samples_per_second": 20.851, | |
| "eval_steps_per_second": 2.606, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 42.8, | |
| "learning_rate": 2.8600686416473998e-05, | |
| "loss": 2.5723, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 42.8, | |
| "eval_accuracy": 0.5228206356006956, | |
| "eval_loss": 2.7301199436187744, | |
| "eval_runtime": 240.5491, | |
| "eval_samples_per_second": 20.786, | |
| "eval_steps_per_second": 2.598, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 2.8500684016416396e-05, | |
| "loss": 2.5388, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5227556727866768, | |
| "eval_loss": 2.7347464561462402, | |
| "eval_runtime": 239.7747, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 2.607, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "learning_rate": 2.8400681616358793e-05, | |
| "loss": 2.5275, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "eval_accuracy": 0.5226272952884897, | |
| "eval_loss": 2.7289857864379883, | |
| "eval_runtime": 239.6863, | |
| "eval_samples_per_second": 20.861, | |
| "eval_steps_per_second": 2.608, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 2.830067921630119e-05, | |
| "loss": 2.5344, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "eval_accuracy": 0.523518819169507, | |
| "eval_loss": 2.724255084991455, | |
| "eval_runtime": 238.5606, | |
| "eval_samples_per_second": 20.959, | |
| "eval_steps_per_second": 2.62, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 2.8200676816243595e-05, | |
| "loss": 2.5322, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "eval_accuracy": 0.5245920745920746, | |
| "eval_loss": 2.7146334648132324, | |
| "eval_runtime": 238.7987, | |
| "eval_samples_per_second": 20.938, | |
| "eval_steps_per_second": 2.617, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 43.8, | |
| "learning_rate": 2.810067441618599e-05, | |
| "loss": 2.5245, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 43.8, | |
| "eval_accuracy": 0.5248407200904217, | |
| "eval_loss": 2.7163941860198975, | |
| "eval_runtime": 238.7952, | |
| "eval_samples_per_second": 20.938, | |
| "eval_steps_per_second": 2.617, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 2.8000672016128386e-05, | |
| "loss": 2.5264, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5245739431165456, | |
| "eval_loss": 2.709345817565918, | |
| "eval_runtime": 240.3791, | |
| "eval_samples_per_second": 20.8, | |
| "eval_steps_per_second": 2.6, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 44.2, | |
| "learning_rate": 2.7900669616070783e-05, | |
| "loss": 2.5049, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 44.2, | |
| "eval_accuracy": 0.5277196208130921, | |
| "eval_loss": 2.7002735137939453, | |
| "eval_runtime": 239.5615, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "learning_rate": 2.7800667216013188e-05, | |
| "loss": 2.4978, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "eval_accuracy": 0.5264407968087224, | |
| "eval_loss": 2.7004919052124023, | |
| "eval_runtime": 238.9114, | |
| "eval_samples_per_second": 20.928, | |
| "eval_steps_per_second": 2.616, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "learning_rate": 2.7700664815955585e-05, | |
| "loss": 2.5084, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "eval_accuracy": 0.5251704545454545, | |
| "eval_loss": 2.7114479541778564, | |
| "eval_runtime": 239.0613, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 2.614, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "learning_rate": 2.7600662415897982e-05, | |
| "loss": 2.5068, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "eval_accuracy": 0.5272083200585458, | |
| "eval_loss": 2.6994175910949707, | |
| "eval_runtime": 239.9458, | |
| "eval_samples_per_second": 20.838, | |
| "eval_steps_per_second": 2.605, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.750066001584038e-05, | |
| "loss": 2.5117, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5278801603168437, | |
| "eval_loss": 2.6876628398895264, | |
| "eval_runtime": 238.9585, | |
| "eval_samples_per_second": 20.924, | |
| "eval_steps_per_second": 2.616, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 45.2, | |
| "learning_rate": 2.740065761578278e-05, | |
| "loss": 2.4844, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 45.2, | |
| "eval_accuracy": 0.5281054209737237, | |
| "eval_loss": 2.6892876625061035, | |
| "eval_runtime": 239.8784, | |
| "eval_samples_per_second": 20.844, | |
| "eval_steps_per_second": 2.605, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 45.4, | |
| "learning_rate": 2.7300655215725178e-05, | |
| "loss": 2.4846, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 45.4, | |
| "eval_accuracy": 0.5291772541468727, | |
| "eval_loss": 2.6861720085144043, | |
| "eval_runtime": 239.6956, | |
| "eval_samples_per_second": 20.86, | |
| "eval_steps_per_second": 2.607, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 2.7200652815667575e-05, | |
| "loss": 2.4671, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "eval_accuracy": 0.5287297495387571, | |
| "eval_loss": 2.6842663288116455, | |
| "eval_runtime": 238.9115, | |
| "eval_samples_per_second": 20.928, | |
| "eval_steps_per_second": 2.616, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 45.8, | |
| "learning_rate": 2.7100650415609973e-05, | |
| "loss": 2.4758, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 45.8, | |
| "eval_accuracy": 0.5284488319441458, | |
| "eval_loss": 2.6910390853881836, | |
| "eval_runtime": 239.5137, | |
| "eval_samples_per_second": 20.876, | |
| "eval_steps_per_second": 2.609, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 2.7000648015552377e-05, | |
| "loss": 2.4827, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5292716595750058, | |
| "eval_loss": 2.6797308921813965, | |
| "eval_runtime": 239.2914, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 46.2, | |
| "learning_rate": 2.6900645615494774e-05, | |
| "loss": 2.4586, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 46.2, | |
| "eval_accuracy": 0.5293859870362431, | |
| "eval_loss": 2.6884403228759766, | |
| "eval_runtime": 239.2735, | |
| "eval_samples_per_second": 20.897, | |
| "eval_steps_per_second": 2.612, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "learning_rate": 2.6800643215437172e-05, | |
| "loss": 2.4539, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "eval_accuracy": 0.5301808865428363, | |
| "eval_loss": 2.6732141971588135, | |
| "eval_runtime": 239.5067, | |
| "eval_samples_per_second": 20.876, | |
| "eval_steps_per_second": 2.61, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "learning_rate": 2.670064081537957e-05, | |
| "loss": 2.4543, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "eval_accuracy": 0.532382243521029, | |
| "eval_loss": 2.6684887409210205, | |
| "eval_runtime": 238.6531, | |
| "eval_samples_per_second": 20.951, | |
| "eval_steps_per_second": 2.619, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 2.660063841532197e-05, | |
| "loss": 2.4635, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "eval_accuracy": 0.5319910740175746, | |
| "eval_loss": 2.6664233207702637, | |
| "eval_runtime": 239.6023, | |
| "eval_samples_per_second": 20.868, | |
| "eval_steps_per_second": 2.608, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 2.6500636015264367e-05, | |
| "loss": 2.4616, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5319308055436347, | |
| "eval_loss": 2.652108907699585, | |
| "eval_runtime": 239.838, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 2.606, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "learning_rate": 2.6400633615206765e-05, | |
| "loss": 2.4322, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "eval_accuracy": 0.5311958432900132, | |
| "eval_loss": 2.6661252975463867, | |
| "eval_runtime": 238.6884, | |
| "eval_samples_per_second": 20.948, | |
| "eval_steps_per_second": 2.618, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 47.4, | |
| "learning_rate": 2.6300631215149162e-05, | |
| "loss": 2.4427, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 47.4, | |
| "eval_accuracy": 0.5323433070866141, | |
| "eval_loss": 2.6600053310394287, | |
| "eval_runtime": 240.0825, | |
| "eval_samples_per_second": 20.826, | |
| "eval_steps_per_second": 2.603, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "learning_rate": 2.6200628815091566e-05, | |
| "loss": 2.4388, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "eval_accuracy": 0.5331623073986071, | |
| "eval_loss": 2.648709535598755, | |
| "eval_runtime": 240.2521, | |
| "eval_samples_per_second": 20.811, | |
| "eval_steps_per_second": 2.601, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 47.8, | |
| "learning_rate": 2.6100626415033964e-05, | |
| "loss": 2.4434, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 47.8, | |
| "eval_accuracy": 0.5311764779890039, | |
| "eval_loss": 2.6652913093566895, | |
| "eval_runtime": 239.5743, | |
| "eval_samples_per_second": 20.87, | |
| "eval_steps_per_second": 2.609, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.600062401497636e-05, | |
| "loss": 2.4288, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5353168737222834, | |
| "eval_loss": 2.6441142559051514, | |
| "eval_runtime": 239.7847, | |
| "eval_samples_per_second": 20.852, | |
| "eval_steps_per_second": 2.607, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 48.2, | |
| "learning_rate": 2.590062161491876e-05, | |
| "loss": 2.4, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 48.2, | |
| "eval_accuracy": 0.5336576378767517, | |
| "eval_loss": 2.6524970531463623, | |
| "eval_runtime": 240.1766, | |
| "eval_samples_per_second": 20.818, | |
| "eval_steps_per_second": 2.602, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "learning_rate": 2.580061921486116e-05, | |
| "loss": 2.4151, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "eval_accuracy": 0.5335010622480515, | |
| "eval_loss": 2.6437137126922607, | |
| "eval_runtime": 240.2765, | |
| "eval_samples_per_second": 20.809, | |
| "eval_steps_per_second": 2.601, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 48.6, | |
| "learning_rate": 2.5700616814803557e-05, | |
| "loss": 2.4238, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 48.6, | |
| "eval_accuracy": 0.5363357667453298, | |
| "eval_loss": 2.6379194259643555, | |
| "eval_runtime": 239.3331, | |
| "eval_samples_per_second": 20.891, | |
| "eval_steps_per_second": 2.611, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 48.8, | |
| "learning_rate": 2.5600614414745954e-05, | |
| "loss": 2.4171, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 48.8, | |
| "eval_accuracy": 0.5340343564481496, | |
| "eval_loss": 2.648090124130249, | |
| "eval_runtime": 240.2867, | |
| "eval_samples_per_second": 20.808, | |
| "eval_steps_per_second": 2.601, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 2.550061201468835e-05, | |
| "loss": 2.4183, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5346044128042008, | |
| "eval_loss": 2.644219160079956, | |
| "eval_runtime": 241.3259, | |
| "eval_samples_per_second": 20.719, | |
| "eval_steps_per_second": 2.59, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 49.2, | |
| "learning_rate": 2.5400609614630756e-05, | |
| "loss": 2.3919, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 49.2, | |
| "eval_accuracy": 0.5362844450065609, | |
| "eval_loss": 2.629089832305908, | |
| "eval_runtime": 239.9635, | |
| "eval_samples_per_second": 20.836, | |
| "eval_steps_per_second": 2.605, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 49.4, | |
| "learning_rate": 2.5300607214573153e-05, | |
| "loss": 2.3972, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 49.4, | |
| "eval_accuracy": 0.5351801935447217, | |
| "eval_loss": 2.6336562633514404, | |
| "eval_runtime": 241.0833, | |
| "eval_samples_per_second": 20.74, | |
| "eval_steps_per_second": 2.592, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 2.520060481451555e-05, | |
| "loss": 2.3952, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "eval_accuracy": 0.5374739972158475, | |
| "eval_loss": 2.619722366333008, | |
| "eval_runtime": 240.3225, | |
| "eval_samples_per_second": 20.805, | |
| "eval_steps_per_second": 2.601, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 49.8, | |
| "learning_rate": 2.5100602414457948e-05, | |
| "loss": 2.3916, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 49.8, | |
| "eval_accuracy": 0.5356588926900613, | |
| "eval_loss": 2.6252872943878174, | |
| "eval_runtime": 238.8695, | |
| "eval_samples_per_second": 20.932, | |
| "eval_steps_per_second": 2.616, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.500060001440035e-05, | |
| "loss": 2.3955, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5384588625208724, | |
| "eval_loss": 2.623581647872925, | |
| "eval_runtime": 239.826, | |
| "eval_samples_per_second": 20.848, | |
| "eval_steps_per_second": 2.606, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 50.2, | |
| "learning_rate": 2.4900597614342746e-05, | |
| "loss": 2.3602, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 50.2, | |
| "eval_accuracy": 0.5353075818087105, | |
| "eval_loss": 2.6330502033233643, | |
| "eval_runtime": 238.9948, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 2.615, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 50.4, | |
| "learning_rate": 2.4800595214285143e-05, | |
| "loss": 2.3826, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 50.4, | |
| "eval_accuracy": 0.536037202954501, | |
| "eval_loss": 2.627243757247925, | |
| "eval_runtime": 239.9878, | |
| "eval_samples_per_second": 20.834, | |
| "eval_steps_per_second": 2.604, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 50.6, | |
| "learning_rate": 2.4700592814227544e-05, | |
| "loss": 2.3774, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 50.6, | |
| "eval_accuracy": 0.538067971866305, | |
| "eval_loss": 2.618502378463745, | |
| "eval_runtime": 239.3755, | |
| "eval_samples_per_second": 20.888, | |
| "eval_steps_per_second": 2.611, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 50.8, | |
| "learning_rate": 2.460059041416994e-05, | |
| "loss": 2.3674, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 50.8, | |
| "eval_accuracy": 0.5392022529377222, | |
| "eval_loss": 2.606363296508789, | |
| "eval_runtime": 239.0192, | |
| "eval_samples_per_second": 20.919, | |
| "eval_steps_per_second": 2.615, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 2.4500588014112342e-05, | |
| "loss": 2.3612, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5381538014980092, | |
| "eval_loss": 2.6098031997680664, | |
| "eval_runtime": 239.4732, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 2.61, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "learning_rate": 2.440058561405474e-05, | |
| "loss": 2.3488, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "eval_accuracy": 0.5395342527125473, | |
| "eval_loss": 2.607774496078491, | |
| "eval_runtime": 238.9635, | |
| "eval_samples_per_second": 20.924, | |
| "eval_steps_per_second": 2.615, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 51.4, | |
| "learning_rate": 2.4300583213997137e-05, | |
| "loss": 2.3546, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 51.4, | |
| "eval_accuracy": 0.5388677484544013, | |
| "eval_loss": 2.614074230194092, | |
| "eval_runtime": 238.9869, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 2.4200580813939535e-05, | |
| "loss": 2.3653, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "eval_accuracy": 0.5410012023997633, | |
| "eval_loss": 2.6000912189483643, | |
| "eval_runtime": 239.3164, | |
| "eval_samples_per_second": 20.893, | |
| "eval_steps_per_second": 2.612, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 2.4100578413881932e-05, | |
| "loss": 2.3517, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "eval_accuracy": 0.5399884734937597, | |
| "eval_loss": 2.603484869003296, | |
| "eval_runtime": 239.7089, | |
| "eval_samples_per_second": 20.859, | |
| "eval_steps_per_second": 2.607, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 2.4000576013824333e-05, | |
| "loss": 2.3592, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5414965001054849, | |
| "eval_loss": 2.5917770862579346, | |
| "eval_runtime": 239.3915, | |
| "eval_samples_per_second": 20.886, | |
| "eval_steps_per_second": 2.611, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 52.2, | |
| "learning_rate": 2.390057361376673e-05, | |
| "loss": 2.3439, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 52.2, | |
| "eval_accuracy": 0.5404831606707972, | |
| "eval_loss": 2.604349136352539, | |
| "eval_runtime": 238.9796, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 52.4, | |
| "learning_rate": 2.380057121370913e-05, | |
| "loss": 2.3341, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 52.4, | |
| "eval_accuracy": 0.5412468175701713, | |
| "eval_loss": 2.5933175086975098, | |
| "eval_runtime": 239.4613, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.61, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 52.6, | |
| "learning_rate": 2.370056881365153e-05, | |
| "loss": 2.3317, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 52.6, | |
| "eval_accuracy": 0.5414899639162706, | |
| "eval_loss": 2.5935215950012207, | |
| "eval_runtime": 239.2429, | |
| "eval_samples_per_second": 20.899, | |
| "eval_steps_per_second": 2.612, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "learning_rate": 2.360056641359393e-05, | |
| "loss": 2.3503, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "eval_accuracy": 0.541917771950174, | |
| "eval_loss": 2.5935444831848145, | |
| "eval_runtime": 239.3726, | |
| "eval_samples_per_second": 20.888, | |
| "eval_steps_per_second": 2.611, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 2.3500564013536323e-05, | |
| "loss": 2.3295, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5435171818164625, | |
| "eval_loss": 2.5758824348449707, | |
| "eval_runtime": 239.7503, | |
| "eval_samples_per_second": 20.855, | |
| "eval_steps_per_second": 2.607, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 53.2, | |
| "learning_rate": 2.3400561613478724e-05, | |
| "loss": 2.3229, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 53.2, | |
| "eval_accuracy": 0.5419268270298838, | |
| "eval_loss": 2.584718942642212, | |
| "eval_runtime": 239.549, | |
| "eval_samples_per_second": 20.873, | |
| "eval_steps_per_second": 2.609, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 53.4, | |
| "learning_rate": 2.330055921342112e-05, | |
| "loss": 2.3174, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 53.4, | |
| "eval_accuracy": 0.5433115780118934, | |
| "eval_loss": 2.579352378845215, | |
| "eval_runtime": 240.0227, | |
| "eval_samples_per_second": 20.831, | |
| "eval_steps_per_second": 2.604, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "learning_rate": 2.3200556813363522e-05, | |
| "loss": 2.3121, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "eval_accuracy": 0.5427292175460517, | |
| "eval_loss": 2.5821499824523926, | |
| "eval_runtime": 239.1079, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 2.614, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 53.8, | |
| "learning_rate": 2.310055441330592e-05, | |
| "loss": 2.3222, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 53.8, | |
| "eval_accuracy": 0.5440522389940277, | |
| "eval_loss": 2.5802907943725586, | |
| "eval_runtime": 238.9623, | |
| "eval_samples_per_second": 20.924, | |
| "eval_steps_per_second": 2.615, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 2.300055201324832e-05, | |
| "loss": 2.3273, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5418589113279378, | |
| "eval_loss": 2.58471941947937, | |
| "eval_runtime": 240.3564, | |
| "eval_samples_per_second": 20.802, | |
| "eval_steps_per_second": 2.6, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 54.2, | |
| "learning_rate": 2.2900549613190718e-05, | |
| "loss": 2.2979, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 54.2, | |
| "eval_accuracy": 0.5431181820766608, | |
| "eval_loss": 2.581387519836426, | |
| "eval_runtime": 239.5645, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "learning_rate": 2.2800547213133115e-05, | |
| "loss": 2.3075, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "eval_accuracy": 0.5456039674552573, | |
| "eval_loss": 2.5715229511260986, | |
| "eval_runtime": 239.5747, | |
| "eval_samples_per_second": 20.87, | |
| "eval_steps_per_second": 2.609, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 54.6, | |
| "learning_rate": 2.2700544813075513e-05, | |
| "loss": 2.2956, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 54.6, | |
| "eval_accuracy": 0.544241455455272, | |
| "eval_loss": 2.5736727714538574, | |
| "eval_runtime": 238.8327, | |
| "eval_samples_per_second": 20.935, | |
| "eval_steps_per_second": 2.617, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 54.8, | |
| "learning_rate": 2.2600542413017913e-05, | |
| "loss": 2.3068, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 54.8, | |
| "eval_accuracy": 0.543567351165669, | |
| "eval_loss": 2.5768492221832275, | |
| "eval_runtime": 239.6828, | |
| "eval_samples_per_second": 20.861, | |
| "eval_steps_per_second": 2.608, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 2.250054001296031e-05, | |
| "loss": 2.2982, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5449586143181261, | |
| "eval_loss": 2.5657105445861816, | |
| "eval_runtime": 239.5684, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.609, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "learning_rate": 2.240053761290271e-05, | |
| "loss": 2.2886, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "eval_accuracy": 0.5452792134123282, | |
| "eval_loss": 2.5683178901672363, | |
| "eval_runtime": 239.1443, | |
| "eval_samples_per_second": 20.908, | |
| "eval_steps_per_second": 2.613, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 55.4, | |
| "learning_rate": 2.230053521284511e-05, | |
| "loss": 2.2807, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 55.4, | |
| "eval_accuracy": 0.5443893773089225, | |
| "eval_loss": 2.5663530826568604, | |
| "eval_runtime": 239.5227, | |
| "eval_samples_per_second": 20.875, | |
| "eval_steps_per_second": 2.609, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 55.6, | |
| "learning_rate": 2.220053281278751e-05, | |
| "loss": 2.2892, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 55.6, | |
| "eval_accuracy": 0.5455853036917409, | |
| "eval_loss": 2.5552079677581787, | |
| "eval_runtime": 239.1742, | |
| "eval_samples_per_second": 20.905, | |
| "eval_steps_per_second": 2.613, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 55.8, | |
| "learning_rate": 2.2100530412729907e-05, | |
| "loss": 2.281, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 55.8, | |
| "eval_accuracy": 0.546019219633517, | |
| "eval_loss": 2.560382843017578, | |
| "eval_runtime": 239.5538, | |
| "eval_samples_per_second": 20.872, | |
| "eval_steps_per_second": 2.609, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 2.2000528012672305e-05, | |
| "loss": 2.2996, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.545175555940259, | |
| "eval_loss": 2.569575071334839, | |
| "eval_runtime": 239.4402, | |
| "eval_samples_per_second": 20.882, | |
| "eval_steps_per_second": 2.61, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 56.2, | |
| "learning_rate": 2.1900525612614702e-05, | |
| "loss": 2.2637, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 56.2, | |
| "eval_accuracy": 0.5446701227486882, | |
| "eval_loss": 2.567713499069214, | |
| "eval_runtime": 239.3563, | |
| "eval_samples_per_second": 20.889, | |
| "eval_steps_per_second": 2.611, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 56.4, | |
| "learning_rate": 2.1800523212557103e-05, | |
| "loss": 2.2616, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 56.4, | |
| "eval_accuracy": 0.5458312504519459, | |
| "eval_loss": 2.560295820236206, | |
| "eval_runtime": 239.7976, | |
| "eval_samples_per_second": 20.851, | |
| "eval_steps_per_second": 2.606, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "learning_rate": 2.17005208124995e-05, | |
| "loss": 2.28, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "eval_accuracy": 0.5473221625039519, | |
| "eval_loss": 2.5473392009735107, | |
| "eval_runtime": 239.703, | |
| "eval_samples_per_second": 20.859, | |
| "eval_steps_per_second": 2.607, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 2.16005184124419e-05, | |
| "loss": 2.2851, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "eval_accuracy": 0.5455403910931405, | |
| "eval_loss": 2.560549736022949, | |
| "eval_runtime": 239.2486, | |
| "eval_samples_per_second": 20.899, | |
| "eval_steps_per_second": 2.612, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 2.1500516012384298e-05, | |
| "loss": 2.2779, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5481797430708371, | |
| "eval_loss": 2.538954019546509, | |
| "eval_runtime": 239.3788, | |
| "eval_samples_per_second": 20.887, | |
| "eval_steps_per_second": 2.611, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 57.2, | |
| "learning_rate": 2.14005136123267e-05, | |
| "loss": 2.2553, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 57.2, | |
| "eval_accuracy": 0.5465248526358569, | |
| "eval_loss": 2.551297903060913, | |
| "eval_runtime": 239.321, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 2.612, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 57.4, | |
| "learning_rate": 2.1300511212269093e-05, | |
| "loss": 2.2577, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 57.4, | |
| "eval_accuracy": 0.5489012757952415, | |
| "eval_loss": 2.541961431503296, | |
| "eval_runtime": 240.0573, | |
| "eval_samples_per_second": 20.828, | |
| "eval_steps_per_second": 2.604, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "learning_rate": 2.1200508812211494e-05, | |
| "loss": 2.2639, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "eval_accuracy": 0.549243428946737, | |
| "eval_loss": 2.5330581665039062, | |
| "eval_runtime": 239.73, | |
| "eval_samples_per_second": 20.857, | |
| "eval_steps_per_second": 2.607, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 57.8, | |
| "learning_rate": 2.110050641215389e-05, | |
| "loss": 2.2646, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 57.8, | |
| "eval_accuracy": 0.5463414171375807, | |
| "eval_loss": 2.553412675857544, | |
| "eval_runtime": 240.2504, | |
| "eval_samples_per_second": 20.812, | |
| "eval_steps_per_second": 2.601, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 2.1000504012096292e-05, | |
| "loss": 2.2502, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5491033816851943, | |
| "eval_loss": 2.537835121154785, | |
| "eval_runtime": 239.3546, | |
| "eval_samples_per_second": 20.89, | |
| "eval_steps_per_second": 2.611, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 58.2, | |
| "learning_rate": 2.090050161203869e-05, | |
| "loss": 2.2341, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 58.2, | |
| "eval_accuracy": 0.5498957186264518, | |
| "eval_loss": 2.5327913761138916, | |
| "eval_runtime": 238.7537, | |
| "eval_samples_per_second": 20.942, | |
| "eval_steps_per_second": 2.618, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "learning_rate": 2.080049921198109e-05, | |
| "loss": 2.2446, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "eval_accuracy": 0.551388546467156, | |
| "eval_loss": 2.524890184402466, | |
| "eval_runtime": 238.6361, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 2.619, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 58.6, | |
| "learning_rate": 2.0700496811923488e-05, | |
| "loss": 2.2413, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 58.6, | |
| "eval_accuracy": 0.5494109926997167, | |
| "eval_loss": 2.5354578495025635, | |
| "eval_runtime": 239.8195, | |
| "eval_samples_per_second": 20.849, | |
| "eval_steps_per_second": 2.606, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 58.8, | |
| "learning_rate": 2.0600494411865885e-05, | |
| "loss": 2.2358, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 58.8, | |
| "eval_accuracy": 0.5500933200499388, | |
| "eval_loss": 2.5274887084960938, | |
| "eval_runtime": 239.5977, | |
| "eval_samples_per_second": 20.868, | |
| "eval_steps_per_second": 2.609, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 2.0500492011808282e-05, | |
| "loss": 2.2515, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5500455346141847, | |
| "eval_loss": 2.530198812484741, | |
| "eval_runtime": 240.0143, | |
| "eval_samples_per_second": 20.832, | |
| "eval_steps_per_second": 2.604, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "learning_rate": 2.0400489611750683e-05, | |
| "loss": 2.2254, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "eval_accuracy": 0.5491007766091739, | |
| "eval_loss": 2.5325417518615723, | |
| "eval_runtime": 239.8311, | |
| "eval_samples_per_second": 20.848, | |
| "eval_steps_per_second": 2.606, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 59.4, | |
| "learning_rate": 2.030048721169308e-05, | |
| "loss": 2.2288, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 59.4, | |
| "eval_accuracy": 0.5502322742638851, | |
| "eval_loss": 2.5338664054870605, | |
| "eval_runtime": 239.0805, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 2.614, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 59.6, | |
| "learning_rate": 2.020048481163548e-05, | |
| "loss": 2.2229, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 59.6, | |
| "eval_accuracy": 0.5492136878089197, | |
| "eval_loss": 2.52840518951416, | |
| "eval_runtime": 239.0571, | |
| "eval_samples_per_second": 20.916, | |
| "eval_steps_per_second": 2.614, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 59.8, | |
| "learning_rate": 2.010048241157788e-05, | |
| "loss": 2.226, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 59.8, | |
| "eval_accuracy": 0.5520625337131285, | |
| "eval_loss": 2.5211117267608643, | |
| "eval_runtime": 239.9761, | |
| "eval_samples_per_second": 20.835, | |
| "eval_steps_per_second": 2.604, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.000048001152028e-05, | |
| "loss": 2.2299, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5512880798568485, | |
| "eval_loss": 2.5254392623901367, | |
| "eval_runtime": 238.9239, | |
| "eval_samples_per_second": 20.927, | |
| "eval_steps_per_second": 2.616, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 60.2, | |
| "learning_rate": 1.9900477611462677e-05, | |
| "loss": 2.2047, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 60.2, | |
| "eval_accuracy": 0.5509219445568596, | |
| "eval_loss": 2.5192694664001465, | |
| "eval_runtime": 239.8776, | |
| "eval_samples_per_second": 20.844, | |
| "eval_steps_per_second": 2.605, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 60.4, | |
| "learning_rate": 1.9800475211405074e-05, | |
| "loss": 2.2143, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 60.4, | |
| "eval_accuracy": 0.5507610195889735, | |
| "eval_loss": 2.5283658504486084, | |
| "eval_runtime": 238.7607, | |
| "eval_samples_per_second": 20.941, | |
| "eval_steps_per_second": 2.618, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 60.6, | |
| "learning_rate": 1.9700472811347472e-05, | |
| "loss": 2.2182, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 60.6, | |
| "eval_accuracy": 0.551352798513339, | |
| "eval_loss": 2.5226526260375977, | |
| "eval_runtime": 239.1735, | |
| "eval_samples_per_second": 20.905, | |
| "eval_steps_per_second": 2.613, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "learning_rate": 1.9600470411289873e-05, | |
| "loss": 2.2085, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "eval_accuracy": 0.5525627969593881, | |
| "eval_loss": 2.5139427185058594, | |
| "eval_runtime": 240.0214, | |
| "eval_samples_per_second": 20.831, | |
| "eval_steps_per_second": 2.604, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 1.950046801123227e-05, | |
| "loss": 2.2209, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.5529032788336304, | |
| "eval_loss": 2.5072460174560547, | |
| "eval_runtime": 240.1385, | |
| "eval_samples_per_second": 20.821, | |
| "eval_steps_per_second": 2.603, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 61.2, | |
| "learning_rate": 1.940046561117467e-05, | |
| "loss": 2.197, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 61.2, | |
| "eval_accuracy": 0.5528882078639463, | |
| "eval_loss": 2.5094316005706787, | |
| "eval_runtime": 239.1412, | |
| "eval_samples_per_second": 20.908, | |
| "eval_steps_per_second": 2.614, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 61.4, | |
| "learning_rate": 1.9300463211117068e-05, | |
| "loss": 2.2029, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 61.4, | |
| "eval_accuracy": 0.552518564768301, | |
| "eval_loss": 2.512848138809204, | |
| "eval_runtime": 239.081, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 2.614, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "learning_rate": 1.920046081105947e-05, | |
| "loss": 2.2026, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "eval_accuracy": 0.5537632882691113, | |
| "eval_loss": 2.500983238220215, | |
| "eval_runtime": 239.906, | |
| "eval_samples_per_second": 20.841, | |
| "eval_steps_per_second": 2.605, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 1.9100458411001866e-05, | |
| "loss": 2.1836, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "eval_accuracy": 0.5522234398340118, | |
| "eval_loss": 2.5177018642425537, | |
| "eval_runtime": 240.0817, | |
| "eval_samples_per_second": 20.826, | |
| "eval_steps_per_second": 2.603, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 1.9000456010944264e-05, | |
| "loss": 2.2043, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.5532023668639053, | |
| "eval_loss": 2.504979372024536, | |
| "eval_runtime": 241.5827, | |
| "eval_samples_per_second": 20.697, | |
| "eval_steps_per_second": 2.587, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 62.2, | |
| "learning_rate": 1.890045361088666e-05, | |
| "loss": 2.1853, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 62.2, | |
| "eval_accuracy": 0.5533680683605509, | |
| "eval_loss": 2.5054237842559814, | |
| "eval_runtime": 238.9823, | |
| "eval_samples_per_second": 20.922, | |
| "eval_steps_per_second": 2.615, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "learning_rate": 1.8800451210829062e-05, | |
| "loss": 2.1735, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "eval_accuracy": 0.5529888819519332, | |
| "eval_loss": 2.501115560531616, | |
| "eval_runtime": 241.4967, | |
| "eval_samples_per_second": 20.704, | |
| "eval_steps_per_second": 2.588, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 62.6, | |
| "learning_rate": 1.870044881077146e-05, | |
| "loss": 2.2014, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 62.6, | |
| "eval_accuracy": 0.5530117516377819, | |
| "eval_loss": 2.513277530670166, | |
| "eval_runtime": 239.8115, | |
| "eval_samples_per_second": 20.85, | |
| "eval_steps_per_second": 2.606, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 62.8, | |
| "learning_rate": 1.860044641071386e-05, | |
| "loss": 2.1819, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 62.8, | |
| "eval_accuracy": 0.5528446296185154, | |
| "eval_loss": 2.509094476699829, | |
| "eval_runtime": 240.0096, | |
| "eval_samples_per_second": 20.832, | |
| "eval_steps_per_second": 2.604, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 1.8500444010656258e-05, | |
| "loss": 2.1891, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.5552905997463995, | |
| "eval_loss": 2.494983196258545, | |
| "eval_runtime": 239.6425, | |
| "eval_samples_per_second": 20.864, | |
| "eval_steps_per_second": 2.608, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "learning_rate": 1.8400441610598655e-05, | |
| "loss": 2.1725, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "eval_accuracy": 0.5525888871738494, | |
| "eval_loss": 2.5135655403137207, | |
| "eval_runtime": 239.4698, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 2.61, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "learning_rate": 1.8300439210541052e-05, | |
| "loss": 2.1627, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "eval_accuracy": 0.5559112693932448, | |
| "eval_loss": 2.4985179901123047, | |
| "eval_runtime": 238.778, | |
| "eval_samples_per_second": 20.94, | |
| "eval_steps_per_second": 2.617, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "learning_rate": 1.8200436810483453e-05, | |
| "loss": 2.1637, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "eval_accuracy": 0.5545219866850771, | |
| "eval_loss": 2.4936916828155518, | |
| "eval_runtime": 239.9514, | |
| "eval_samples_per_second": 20.838, | |
| "eval_steps_per_second": 2.605, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 63.8, | |
| "learning_rate": 1.810043441042585e-05, | |
| "loss": 2.1812, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 63.8, | |
| "eval_accuracy": 0.5547172908406778, | |
| "eval_loss": 2.4982199668884277, | |
| "eval_runtime": 239.8545, | |
| "eval_samples_per_second": 20.846, | |
| "eval_steps_per_second": 2.606, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 1.8000432010368248e-05, | |
| "loss": 2.1813, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.5542093602880088, | |
| "eval_loss": 2.496227741241455, | |
| "eval_runtime": 239.2798, | |
| "eval_samples_per_second": 20.896, | |
| "eval_steps_per_second": 2.612, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 64.2, | |
| "learning_rate": 1.790042961031065e-05, | |
| "loss": 2.1406, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 64.2, | |
| "eval_accuracy": 0.5536167372868017, | |
| "eval_loss": 2.4971325397491455, | |
| "eval_runtime": 238.8834, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 2.616, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 64.4, | |
| "learning_rate": 1.7800427210253046e-05, | |
| "loss": 2.1552, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 64.4, | |
| "eval_accuracy": 0.5572511133344485, | |
| "eval_loss": 2.4775383472442627, | |
| "eval_runtime": 240.2398, | |
| "eval_samples_per_second": 20.813, | |
| "eval_steps_per_second": 2.602, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 64.6, | |
| "learning_rate": 1.7700424810195447e-05, | |
| "loss": 2.1507, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 64.6, | |
| "eval_accuracy": 0.5555152177138546, | |
| "eval_loss": 2.497971773147583, | |
| "eval_runtime": 238.8788, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 2.616, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "learning_rate": 1.7600422410137844e-05, | |
| "loss": 2.1644, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "eval_accuracy": 0.5557170695407047, | |
| "eval_loss": 2.493004322052002, | |
| "eval_runtime": 239.6996, | |
| "eval_samples_per_second": 20.859, | |
| "eval_steps_per_second": 2.607, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.750042001008024e-05, | |
| "loss": 2.1634, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.5560676366496264, | |
| "eval_loss": 2.497638702392578, | |
| "eval_runtime": 239.1488, | |
| "eval_samples_per_second": 20.907, | |
| "eval_steps_per_second": 2.613, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 65.2, | |
| "learning_rate": 1.740041761002264e-05, | |
| "loss": 2.1409, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 65.2, | |
| "eval_accuracy": 0.5558225740583671, | |
| "eval_loss": 2.4956326484680176, | |
| "eval_runtime": 238.3192, | |
| "eval_samples_per_second": 20.98, | |
| "eval_steps_per_second": 2.623, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 65.4, | |
| "learning_rate": 1.730041520996504e-05, | |
| "loss": 2.1453, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 65.4, | |
| "eval_accuracy": 0.5554011908137227, | |
| "eval_loss": 2.487835168838501, | |
| "eval_runtime": 238.4531, | |
| "eval_samples_per_second": 20.968, | |
| "eval_steps_per_second": 2.621, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "learning_rate": 1.7200412809907437e-05, | |
| "loss": 2.1361, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "eval_accuracy": 0.5566455517043989, | |
| "eval_loss": 2.4900457859039307, | |
| "eval_runtime": 239.9045, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 2.605, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 65.8, | |
| "learning_rate": 1.7100410409849838e-05, | |
| "loss": 2.1604, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 65.8, | |
| "eval_accuracy": 0.5581541652045535, | |
| "eval_loss": 2.4757144451141357, | |
| "eval_runtime": 238.296, | |
| "eval_samples_per_second": 20.982, | |
| "eval_steps_per_second": 2.623, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 1.7000408009792235e-05, | |
| "loss": 2.138, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.5568600527817493, | |
| "eval_loss": 2.487783432006836, | |
| "eval_runtime": 241.5368, | |
| "eval_samples_per_second": 20.701, | |
| "eval_steps_per_second": 2.588, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 66.2, | |
| "learning_rate": 1.6900405609734636e-05, | |
| "loss": 2.1241, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 66.2, | |
| "eval_accuracy": 0.5563906690268614, | |
| "eval_loss": 2.4848339557647705, | |
| "eval_runtime": 239.626, | |
| "eval_samples_per_second": 20.866, | |
| "eval_steps_per_second": 2.608, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 66.4, | |
| "learning_rate": 1.6800403209677034e-05, | |
| "loss": 2.1262, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 66.4, | |
| "eval_accuracy": 0.557129026746901, | |
| "eval_loss": 2.477325439453125, | |
| "eval_runtime": 239.431, | |
| "eval_samples_per_second": 20.883, | |
| "eval_steps_per_second": 2.61, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 66.6, | |
| "learning_rate": 1.670040080961943e-05, | |
| "loss": 2.142, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 66.6, | |
| "eval_accuracy": 0.5568254288979674, | |
| "eval_loss": 2.4832918643951416, | |
| "eval_runtime": 239.6217, | |
| "eval_samples_per_second": 20.866, | |
| "eval_steps_per_second": 2.608, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 1.660039840956183e-05, | |
| "loss": 2.1514, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "eval_accuracy": 0.5570819128758042, | |
| "eval_loss": 2.4777631759643555, | |
| "eval_runtime": 239.6322, | |
| "eval_samples_per_second": 20.865, | |
| "eval_steps_per_second": 2.608, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 1.650039600950423e-05, | |
| "loss": 2.1382, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.5591870729198872, | |
| "eval_loss": 2.468890905380249, | |
| "eval_runtime": 238.9575, | |
| "eval_samples_per_second": 20.924, | |
| "eval_steps_per_second": 2.616, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "learning_rate": 1.6400393609446627e-05, | |
| "loss": 2.1222, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "eval_accuracy": 0.5574107995800479, | |
| "eval_loss": 2.4710476398468018, | |
| "eval_runtime": 240.0729, | |
| "eval_samples_per_second": 20.827, | |
| "eval_steps_per_second": 2.603, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 67.4, | |
| "learning_rate": 1.6300391209389027e-05, | |
| "loss": 2.1227, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 67.4, | |
| "eval_accuracy": 0.5587516806483989, | |
| "eval_loss": 2.469508647918701, | |
| "eval_runtime": 239.7738, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 2.607, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 67.6, | |
| "learning_rate": 1.6200388809331425e-05, | |
| "loss": 2.1292, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 67.6, | |
| "eval_accuracy": 0.5585561370499786, | |
| "eval_loss": 2.477346181869507, | |
| "eval_runtime": 239.8749, | |
| "eval_samples_per_second": 20.844, | |
| "eval_steps_per_second": 2.606, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 67.8, | |
| "learning_rate": 1.6100386409273822e-05, | |
| "loss": 2.1263, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 67.8, | |
| "eval_accuracy": 0.5578509387181249, | |
| "eval_loss": 2.474029302597046, | |
| "eval_runtime": 239.6966, | |
| "eval_samples_per_second": 20.86, | |
| "eval_steps_per_second": 2.607, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 1.600038400921622e-05, | |
| "loss": 2.1137, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5601281707259325, | |
| "eval_loss": 2.4593210220336914, | |
| "eval_runtime": 239.2768, | |
| "eval_samples_per_second": 20.896, | |
| "eval_steps_per_second": 2.612, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 68.2, | |
| "learning_rate": 1.590038160915862e-05, | |
| "loss": 2.1064, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 68.2, | |
| "eval_accuracy": 0.5578209157966231, | |
| "eval_loss": 2.4727413654327393, | |
| "eval_runtime": 239.7217, | |
| "eval_samples_per_second": 20.858, | |
| "eval_steps_per_second": 2.607, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "learning_rate": 1.5800379209101018e-05, | |
| "loss": 2.1006, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "eval_accuracy": 0.5591064999321577, | |
| "eval_loss": 2.4696574211120605, | |
| "eval_runtime": 239.6832, | |
| "eval_samples_per_second": 20.861, | |
| "eval_steps_per_second": 2.608, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 68.6, | |
| "learning_rate": 1.570037680904342e-05, | |
| "loss": 2.1024, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 68.6, | |
| "eval_accuracy": 0.5610141279251564, | |
| "eval_loss": 2.456801652908325, | |
| "eval_runtime": 239.2907, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.612, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "learning_rate": 1.5600374408985816e-05, | |
| "loss": 2.1168, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "eval_accuracy": 0.5585552637469694, | |
| "eval_loss": 2.465235948562622, | |
| "eval_runtime": 239.8915, | |
| "eval_samples_per_second": 20.843, | |
| "eval_steps_per_second": 2.605, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 1.5500372008928217e-05, | |
| "loss": 2.1173, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.5599213275657079, | |
| "eval_loss": 2.4659504890441895, | |
| "eval_runtime": 239.7834, | |
| "eval_samples_per_second": 20.852, | |
| "eval_steps_per_second": 2.607, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 69.2, | |
| "learning_rate": 1.5400369608870614e-05, | |
| "loss": 2.1033, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 69.2, | |
| "eval_accuracy": 0.5608148024123105, | |
| "eval_loss": 2.4544801712036133, | |
| "eval_runtime": 239.7783, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 2.607, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 69.4, | |
| "learning_rate": 1.530036720881301e-05, | |
| "loss": 2.1007, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 69.4, | |
| "eval_accuracy": 0.560514818378259, | |
| "eval_loss": 2.454843044281006, | |
| "eval_runtime": 238.5559, | |
| "eval_samples_per_second": 20.959, | |
| "eval_steps_per_second": 2.62, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 69.6, | |
| "learning_rate": 1.520036480875541e-05, | |
| "loss": 2.1084, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 69.6, | |
| "eval_accuracy": 0.5603224959593116, | |
| "eval_loss": 2.450347661972046, | |
| "eval_runtime": 240.0033, | |
| "eval_samples_per_second": 20.833, | |
| "eval_steps_per_second": 2.604, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 69.8, | |
| "learning_rate": 1.510036240869781e-05, | |
| "loss": 2.1022, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 69.8, | |
| "eval_accuracy": 0.5603836619647419, | |
| "eval_loss": 2.459425449371338, | |
| "eval_runtime": 239.0288, | |
| "eval_samples_per_second": 20.918, | |
| "eval_steps_per_second": 2.615, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 1.5000360008640207e-05, | |
| "loss": 2.0954, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.5593701413176825, | |
| "eval_loss": 2.4609487056732178, | |
| "eval_runtime": 239.8644, | |
| "eval_samples_per_second": 20.845, | |
| "eval_steps_per_second": 2.606, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 70.2, | |
| "learning_rate": 1.4900357608582608e-05, | |
| "loss": 2.0732, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 70.2, | |
| "eval_accuracy": 0.562392128702269, | |
| "eval_loss": 2.454357385635376, | |
| "eval_runtime": 238.6067, | |
| "eval_samples_per_second": 20.955, | |
| "eval_steps_per_second": 2.619, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "learning_rate": 1.4800355208525005e-05, | |
| "loss": 2.0784, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "eval_accuracy": 0.5609833085023106, | |
| "eval_loss": 2.4554500579833984, | |
| "eval_runtime": 240.1656, | |
| "eval_samples_per_second": 20.819, | |
| "eval_steps_per_second": 2.602, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 70.6, | |
| "learning_rate": 1.4700352808467404e-05, | |
| "loss": 2.0955, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 70.6, | |
| "eval_accuracy": 0.5613185277510245, | |
| "eval_loss": 2.450934410095215, | |
| "eval_runtime": 239.4126, | |
| "eval_samples_per_second": 20.884, | |
| "eval_steps_per_second": 2.611, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 70.8, | |
| "learning_rate": 1.4600350408409802e-05, | |
| "loss": 2.0918, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 70.8, | |
| "eval_accuracy": 0.5611795024033451, | |
| "eval_loss": 2.4546260833740234, | |
| "eval_runtime": 239.9371, | |
| "eval_samples_per_second": 20.839, | |
| "eval_steps_per_second": 2.605, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 1.4500348008352203e-05, | |
| "loss": 2.0934, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.560534958630708, | |
| "eval_loss": 2.4539401531219482, | |
| "eval_runtime": 239.175, | |
| "eval_samples_per_second": 20.905, | |
| "eval_steps_per_second": 2.613, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "learning_rate": 1.44003456082946e-05, | |
| "loss": 2.0698, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "eval_accuracy": 0.5608924561414544, | |
| "eval_loss": 2.4519293308258057, | |
| "eval_runtime": 239.8395, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 2.606, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 71.4, | |
| "learning_rate": 1.4300343208236999e-05, | |
| "loss": 2.0712, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 71.4, | |
| "eval_accuracy": 0.5619750991633243, | |
| "eval_loss": 2.440948009490967, | |
| "eval_runtime": 239.0587, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 2.614, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 1.4200340808179397e-05, | |
| "loss": 2.0857, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "eval_accuracy": 0.5620386045955454, | |
| "eval_loss": 2.4435293674468994, | |
| "eval_runtime": 239.8911, | |
| "eval_samples_per_second": 20.843, | |
| "eval_steps_per_second": 2.605, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 1.4100338408121797e-05, | |
| "loss": 2.0745, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "eval_accuracy": 0.5632759493830151, | |
| "eval_loss": 2.439894676208496, | |
| "eval_runtime": 239.7702, | |
| "eval_samples_per_second": 20.853, | |
| "eval_steps_per_second": 2.607, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 1.4000336008064193e-05, | |
| "loss": 2.0735, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5619281706515695, | |
| "eval_loss": 2.4514319896698, | |
| "eval_runtime": 239.885, | |
| "eval_samples_per_second": 20.843, | |
| "eval_steps_per_second": 2.605, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 72.2, | |
| "learning_rate": 1.3900333608006594e-05, | |
| "loss": 2.0602, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 72.2, | |
| "eval_accuracy": 0.563163832523804, | |
| "eval_loss": 2.440223455429077, | |
| "eval_runtime": 239.5216, | |
| "eval_samples_per_second": 20.875, | |
| "eval_steps_per_second": 2.609, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 72.4, | |
| "learning_rate": 1.3800331207948991e-05, | |
| "loss": 2.0648, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 72.4, | |
| "eval_accuracy": 0.5628968925704558, | |
| "eval_loss": 2.4417946338653564, | |
| "eval_runtime": 239.1858, | |
| "eval_samples_per_second": 20.904, | |
| "eval_steps_per_second": 2.613, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 72.6, | |
| "learning_rate": 1.370032880789139e-05, | |
| "loss": 2.0672, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 72.6, | |
| "eval_accuracy": 0.561726001922683, | |
| "eval_loss": 2.443669080734253, | |
| "eval_runtime": 239.6521, | |
| "eval_samples_per_second": 20.864, | |
| "eval_steps_per_second": 2.608, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 72.8, | |
| "learning_rate": 1.3600326407833788e-05, | |
| "loss": 2.0801, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 72.8, | |
| "eval_accuracy": 0.5635193038184522, | |
| "eval_loss": 2.431992530822754, | |
| "eval_runtime": 239.4749, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 2.61, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 1.3500324007776188e-05, | |
| "loss": 2.0695, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.5642300019285915, | |
| "eval_loss": 2.4284050464630127, | |
| "eval_runtime": 239.7223, | |
| "eval_samples_per_second": 20.857, | |
| "eval_steps_per_second": 2.607, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 73.2, | |
| "learning_rate": 1.3400321607718586e-05, | |
| "loss": 2.0566, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 73.2, | |
| "eval_accuracy": 0.5618769953465528, | |
| "eval_loss": 2.4493749141693115, | |
| "eval_runtime": 239.4603, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.61, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 73.4, | |
| "learning_rate": 1.3300319207660985e-05, | |
| "loss": 2.0452, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 73.4, | |
| "eval_accuracy": 0.5635672190600917, | |
| "eval_loss": 2.437802314758301, | |
| "eval_runtime": 239.4804, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 2.61, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 1.3200316807603382e-05, | |
| "loss": 2.0548, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "eval_accuracy": 0.562618727556153, | |
| "eval_loss": 2.4448354244232178, | |
| "eval_runtime": 239.389, | |
| "eval_samples_per_second": 20.887, | |
| "eval_steps_per_second": 2.611, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 73.8, | |
| "learning_rate": 1.3100314407545783e-05, | |
| "loss": 2.0671, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 73.8, | |
| "eval_accuracy": 0.5631980095115114, | |
| "eval_loss": 2.429305076599121, | |
| "eval_runtime": 239.8305, | |
| "eval_samples_per_second": 20.848, | |
| "eval_steps_per_second": 2.606, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 1.300031200748818e-05, | |
| "loss": 2.057, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.5637622237233351, | |
| "eval_loss": 2.4316015243530273, | |
| "eval_runtime": 238.715, | |
| "eval_samples_per_second": 20.945, | |
| "eval_steps_per_second": 2.618, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 74.2, | |
| "learning_rate": 1.290030960743058e-05, | |
| "loss": 2.0376, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 74.2, | |
| "eval_accuracy": 0.5624911002749817, | |
| "eval_loss": 2.4484307765960693, | |
| "eval_runtime": 239.8067, | |
| "eval_samples_per_second": 20.85, | |
| "eval_steps_per_second": 2.606, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 74.4, | |
| "learning_rate": 1.2800307207372977e-05, | |
| "loss": 2.0534, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 74.4, | |
| "eval_accuracy": 0.5637550768921247, | |
| "eval_loss": 2.4410548210144043, | |
| "eval_runtime": 239.5552, | |
| "eval_samples_per_second": 20.872, | |
| "eval_steps_per_second": 2.609, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 74.6, | |
| "learning_rate": 1.2700304807315378e-05, | |
| "loss": 2.0499, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 74.6, | |
| "eval_accuracy": 0.5629136359625349, | |
| "eval_loss": 2.4380035400390625, | |
| "eval_runtime": 238.4915, | |
| "eval_samples_per_second": 20.965, | |
| "eval_steps_per_second": 2.621, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 74.8, | |
| "learning_rate": 1.2600302407257775e-05, | |
| "loss": 2.0516, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 74.8, | |
| "eval_accuracy": 0.5635815880554783, | |
| "eval_loss": 2.4365627765655518, | |
| "eval_runtime": 240.1236, | |
| "eval_samples_per_second": 20.823, | |
| "eval_steps_per_second": 2.603, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.2500300007200174e-05, | |
| "loss": 2.0435, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.5636397510428476, | |
| "eval_loss": 2.434795618057251, | |
| "eval_runtime": 238.788, | |
| "eval_samples_per_second": 20.939, | |
| "eval_steps_per_second": 2.617, | |
| "step": 187500 | |
| } | |
| ], | |
| "max_steps": 250000, | |
| "num_train_epochs": 100, | |
| "total_flos": 3.9409573713073645e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |