| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 35400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.005915423728813559, | |
| "loss": 0.9831, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6217125382262997, | |
| "eval_loss": 0.8378309011459351, | |
| "eval_runtime": 43.2844, | |
| "eval_samples_per_second": 75.547, | |
| "eval_steps_per_second": 9.449, | |
| "step": 590 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 1.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.005830847457627119, | |
| "loss": 0.965, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3782874617737003, | |
| "eval_loss": 1.149783968925476, | |
| "eval_runtime": 43.2275, | |
| "eval_samples_per_second": 75.646, | |
| "eval_steps_per_second": 9.462, | |
| "step": 1180 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 2.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.005746101694915255, | |
| "loss": 0.8937, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6217125382262997, | |
| "eval_loss": 1.2835785150527954, | |
| "eval_runtime": 43.2406, | |
| "eval_samples_per_second": 75.623, | |
| "eval_steps_per_second": 9.459, | |
| "step": 1770 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 3.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00566135593220339, | |
| "loss": 0.9435, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6217125382262997, | |
| "eval_loss": 0.8481320142745972, | |
| "eval_runtime": 43.2628, | |
| "eval_samples_per_second": 75.585, | |
| "eval_steps_per_second": 9.454, | |
| "step": 2360 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 4.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 0.005576779661016949, | |
| "loss": 0.8566, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3834862385321101, | |
| "eval_loss": 0.9289329648017883, | |
| "eval_runtime": 43.2414, | |
| "eval_samples_per_second": 75.622, | |
| "eval_steps_per_second": 9.459, | |
| "step": 2950 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 5.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.005492033898305085, | |
| "loss": 0.8917, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.00540728813559322, | |
| "loss": 0.8868, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.591743119266055, | |
| "eval_loss": 0.651913583278656, | |
| "eval_runtime": 43.1168, | |
| "eval_samples_per_second": 75.84, | |
| "eval_steps_per_second": 9.486, | |
| "step": 3540 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 6.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.0053225423728813556, | |
| "loss": 0.8905, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3785932721712538, | |
| "eval_loss": 1.771241307258606, | |
| "eval_runtime": 43.2692, | |
| "eval_samples_per_second": 75.573, | |
| "eval_steps_per_second": 9.452, | |
| "step": 4130 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 7.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.005237796610169492, | |
| "loss": 0.84, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6217125382262997, | |
| "eval_loss": 0.9782317876815796, | |
| "eval_runtime": 43.2151, | |
| "eval_samples_per_second": 75.668, | |
| "eval_steps_per_second": 9.464, | |
| "step": 4720 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.6217125382262997, | |
| "epoch": 8.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 0.005153220338983051, | |
| "loss": 0.7962, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6568807339449542, | |
| "eval_loss": 0.6086090803146362, | |
| "eval_runtime": 43.139, | |
| "eval_samples_per_second": 75.801, | |
| "eval_steps_per_second": 9.481, | |
| "step": 5310 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6568807339449542, | |
| "epoch": 9.0, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 0.005068474576271187, | |
| "loss": 0.8003, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6220183486238532, | |
| "eval_loss": 0.8011331558227539, | |
| "eval_runtime": 43.025, | |
| "eval_samples_per_second": 76.002, | |
| "eval_steps_per_second": 9.506, | |
| "step": 5900 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6568807339449542, | |
| "epoch": 10.0, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.004983728813559322, | |
| "loss": 0.793, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.6698857545852661, | |
| "eval_runtime": 43.1878, | |
| "eval_samples_per_second": 75.716, | |
| "eval_steps_per_second": 9.47, | |
| "step": 6490 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6568807339449542, | |
| "epoch": 11.0, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.004899152542372881, | |
| "loss": 0.7706, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 0.004814406779661017, | |
| "loss": 0.7558, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6244648318042814, | |
| "eval_loss": 0.670046329498291, | |
| "eval_runtime": 43.1604, | |
| "eval_samples_per_second": 75.764, | |
| "eval_steps_per_second": 9.476, | |
| "step": 7080 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6568807339449542, | |
| "epoch": 12.0, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 0.004729661016949153, | |
| "loss": 0.7947, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.43149847094801225, | |
| "eval_loss": 1.0037223100662231, | |
| "eval_runtime": 43.2404, | |
| "eval_samples_per_second": 75.624, | |
| "eval_steps_per_second": 9.459, | |
| "step": 7670 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6568807339449542, | |
| "epoch": 13.0, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 0.004644915254237288, | |
| "loss": 0.7465, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6902140672782875, | |
| "eval_loss": 0.6232324242591858, | |
| "eval_runtime": 43.2231, | |
| "eval_samples_per_second": 75.654, | |
| "eval_steps_per_second": 9.463, | |
| "step": 8260 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6902140672782875, | |
| "epoch": 14.0, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 0.004560169491525424, | |
| "loss": 0.6835, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6889908256880733, | |
| "eval_loss": 0.6589847207069397, | |
| "eval_runtime": 43.0731, | |
| "eval_samples_per_second": 75.917, | |
| "eval_steps_per_second": 9.495, | |
| "step": 8850 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6902140672782875, | |
| "epoch": 15.0, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 0.004475593220338983, | |
| "loss": 0.7494, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6862385321100918, | |
| "eval_loss": 0.7069215178489685, | |
| "eval_runtime": 43.2435, | |
| "eval_samples_per_second": 75.618, | |
| "eval_steps_per_second": 9.458, | |
| "step": 9440 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6902140672782875, | |
| "epoch": 16.0, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 0.004390847457627119, | |
| "loss": 0.7499, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 0.004306101694915254, | |
| "loss": 0.6775, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4856269113149847, | |
| "eval_loss": 0.9627411365509033, | |
| "eval_runtime": 43.2672, | |
| "eval_samples_per_second": 75.577, | |
| "eval_steps_per_second": 9.453, | |
| "step": 10030 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6902140672782875, | |
| "epoch": 17.0, | |
| "step": 10030 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 0.0042213559322033896, | |
| "loss": 0.6928, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5663608562691131, | |
| "eval_loss": 1.088120460510254, | |
| "eval_runtime": 43.2117, | |
| "eval_samples_per_second": 75.674, | |
| "eval_steps_per_second": 9.465, | |
| "step": 10620 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6902140672782875, | |
| "epoch": 18.0, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.004136610169491526, | |
| "loss": 0.6991, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7024464831804281, | |
| "eval_loss": 0.5778092741966248, | |
| "eval_runtime": 43.3502, | |
| "eval_samples_per_second": 75.432, | |
| "eval_steps_per_second": 9.435, | |
| "step": 11210 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 19.0, | |
| "step": 11210 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 0.004051864406779661, | |
| "loss": 0.6594, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6051987767584098, | |
| "eval_loss": 0.7909632325172424, | |
| "eval_runtime": 43.1541, | |
| "eval_samples_per_second": 75.775, | |
| "eval_steps_per_second": 9.478, | |
| "step": 11800 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 20.0, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 20.34, | |
| "learning_rate": 0.003967118644067796, | |
| "loss": 0.6327, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6966360856269113, | |
| "eval_loss": 0.6203939914703369, | |
| "eval_runtime": 43.0351, | |
| "eval_samples_per_second": 75.984, | |
| "eval_steps_per_second": 9.504, | |
| "step": 12390 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 21.0, | |
| "step": 12390 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 0.0038823728813559325, | |
| "loss": 0.6201, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6792048929663609, | |
| "eval_loss": 0.5992993712425232, | |
| "eval_runtime": 43.2326, | |
| "eval_samples_per_second": 75.637, | |
| "eval_steps_per_second": 9.46, | |
| "step": 12980 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 22.0, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 0.0037977966101694917, | |
| "loss": 0.629, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 0.0037130508474576274, | |
| "loss": 0.6026, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6633027522935779, | |
| "eval_loss": 0.6735050082206726, | |
| "eval_runtime": 43.216, | |
| "eval_samples_per_second": 75.666, | |
| "eval_steps_per_second": 9.464, | |
| "step": 13570 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 23.0, | |
| "step": 13570 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 0.0036283050847457626, | |
| "loss": 0.5826, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6605504587155964, | |
| "eval_loss": 0.6619319319725037, | |
| "eval_runtime": 43.1433, | |
| "eval_samples_per_second": 75.794, | |
| "eval_steps_per_second": 9.48, | |
| "step": 14160 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7024464831804281, | |
| "epoch": 24.0, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 0.0035435593220338986, | |
| "loss": 0.5831, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7073394495412844, | |
| "eval_loss": 0.7766701579093933, | |
| "eval_runtime": 43.2655, | |
| "eval_samples_per_second": 75.58, | |
| "eval_steps_per_second": 9.453, | |
| "step": 14750 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7073394495412844, | |
| "epoch": 25.0, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 0.003458813559322034, | |
| "loss": 0.5809, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5425076452599389, | |
| "eval_loss": 1.2840725183486938, | |
| "eval_runtime": 43.2156, | |
| "eval_samples_per_second": 75.667, | |
| "eval_steps_per_second": 9.464, | |
| "step": 15340 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7073394495412844, | |
| "epoch": 26.0, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 26.27, | |
| "learning_rate": 0.0033740677966101694, | |
| "loss": 0.6095, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6400611620795107, | |
| "eval_loss": 0.8816479444503784, | |
| "eval_runtime": 43.1544, | |
| "eval_samples_per_second": 75.774, | |
| "eval_steps_per_second": 9.478, | |
| "step": 15930 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7073394495412844, | |
| "epoch": 27.0, | |
| "step": 15930 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 0.0032893220338983055, | |
| "loss": 0.5729, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 27.97, | |
| "learning_rate": 0.0032045762711864407, | |
| "loss": 0.5478, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7189602446483181, | |
| "eval_loss": 0.6825653910636902, | |
| "eval_runtime": 43.238, | |
| "eval_samples_per_second": 75.628, | |
| "eval_steps_per_second": 9.459, | |
| "step": 16520 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 28.0, | |
| "step": 16520 | |
| }, | |
| { | |
| "epoch": 28.81, | |
| "learning_rate": 0.0031198305084745763, | |
| "loss": 0.5516, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7168195718654434, | |
| "eval_loss": 0.6076229214668274, | |
| "eval_runtime": 43.2007, | |
| "eval_samples_per_second": 75.693, | |
| "eval_steps_per_second": 9.467, | |
| "step": 17110 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 29.0, | |
| "step": 17110 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "learning_rate": 0.0030352542372881356, | |
| "loss": 0.5538, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6859327217125383, | |
| "eval_loss": 0.9477331042289734, | |
| "eval_runtime": 43.2891, | |
| "eval_samples_per_second": 75.539, | |
| "eval_steps_per_second": 9.448, | |
| "step": 17700 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 30.0, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 30.51, | |
| "learning_rate": 0.002950508474576271, | |
| "loss": 0.5516, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7137614678899082, | |
| "eval_loss": 0.6786766052246094, | |
| "eval_runtime": 43.2599, | |
| "eval_samples_per_second": 75.59, | |
| "eval_steps_per_second": 9.454, | |
| "step": 18290 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 31.0, | |
| "step": 18290 | |
| }, | |
| { | |
| "epoch": 31.36, | |
| "learning_rate": 0.002865762711864407, | |
| "loss": 0.5296, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7006116207951071, | |
| "eval_loss": 0.8120760917663574, | |
| "eval_runtime": 43.2461, | |
| "eval_samples_per_second": 75.614, | |
| "eval_steps_per_second": 9.458, | |
| "step": 18880 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 32.0, | |
| "step": 18880 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 0.002781186440677966, | |
| "loss": 0.5209, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7018348623853211, | |
| "eval_loss": 0.8754389882087708, | |
| "eval_runtime": 43.2296, | |
| "eval_samples_per_second": 75.643, | |
| "eval_steps_per_second": 9.461, | |
| "step": 19470 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 33.0, | |
| "step": 19470 | |
| }, | |
| { | |
| "epoch": 33.05, | |
| "learning_rate": 0.0026964406779661017, | |
| "loss": 0.5172, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 33.9, | |
| "learning_rate": 0.0026116949152542373, | |
| "loss": 0.4932, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7097859327217125, | |
| "eval_loss": 0.6252529621124268, | |
| "eval_runtime": 43.3313, | |
| "eval_samples_per_second": 75.465, | |
| "eval_steps_per_second": 9.439, | |
| "step": 20060 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 34.0, | |
| "step": 20060 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "learning_rate": 0.002527118644067797, | |
| "loss": 0.4914, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7039755351681957, | |
| "eval_loss": 0.6481243968009949, | |
| "eval_runtime": 43.2111, | |
| "eval_samples_per_second": 75.675, | |
| "eval_steps_per_second": 9.465, | |
| "step": 20650 | |
| }, | |
| { | |
| "best_epoch": 27, | |
| "best_eval_accuracy": 0.7189602446483181, | |
| "epoch": 35.0, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 35.59, | |
| "learning_rate": 0.002442372881355932, | |
| "loss": 0.4845, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7207951070336391, | |
| "eval_loss": 0.6696820855140686, | |
| "eval_runtime": 43.2359, | |
| "eval_samples_per_second": 75.632, | |
| "eval_steps_per_second": 9.46, | |
| "step": 21240 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7207951070336391, | |
| "epoch": 36.0, | |
| "step": 21240 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 0.002357627118644068, | |
| "loss": 0.4836, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7363914373088685, | |
| "eval_loss": 0.6275990605354309, | |
| "eval_runtime": 43.254, | |
| "eval_samples_per_second": 75.6, | |
| "eval_steps_per_second": 9.456, | |
| "step": 21830 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.7363914373088685, | |
| "epoch": 37.0, | |
| "step": 21830 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 0.0022728813559322034, | |
| "loss": 0.4592, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7342507645259939, | |
| "eval_loss": 0.5963826775550842, | |
| "eval_runtime": 43.2046, | |
| "eval_samples_per_second": 75.686, | |
| "eval_steps_per_second": 9.467, | |
| "step": 22420 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.7363914373088685, | |
| "epoch": 38.0, | |
| "step": 22420 | |
| }, | |
| { | |
| "epoch": 38.14, | |
| "learning_rate": 0.002188135593220339, | |
| "loss": 0.4692, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 38.98, | |
| "learning_rate": 0.0021033898305084747, | |
| "loss": 0.4642, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7363914373088685, | |
| "eval_loss": 0.5508460402488708, | |
| "eval_runtime": 43.299, | |
| "eval_samples_per_second": 75.521, | |
| "eval_steps_per_second": 9.446, | |
| "step": 23010 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.7363914373088685, | |
| "epoch": 39.0, | |
| "step": 23010 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "learning_rate": 0.002018813559322034, | |
| "loss": 0.4704, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.708256880733945, | |
| "eval_loss": 0.8355740308761597, | |
| "eval_runtime": 43.2934, | |
| "eval_samples_per_second": 75.531, | |
| "eval_steps_per_second": 9.447, | |
| "step": 23600 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.7363914373088685, | |
| "epoch": 40.0, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 40.68, | |
| "learning_rate": 0.0019340677966101694, | |
| "loss": 0.4556, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7339449541284404, | |
| "eval_loss": 0.6307940483093262, | |
| "eval_runtime": 43.1769, | |
| "eval_samples_per_second": 75.735, | |
| "eval_steps_per_second": 9.473, | |
| "step": 24190 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.7363914373088685, | |
| "epoch": 41.0, | |
| "step": 24190 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 0.0018494915254237288, | |
| "loss": 0.4583, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7373088685015291, | |
| "eval_loss": 0.5991156697273254, | |
| "eval_runtime": 43.2189, | |
| "eval_samples_per_second": 75.661, | |
| "eval_steps_per_second": 9.463, | |
| "step": 24780 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 42.0, | |
| "step": 24780 | |
| }, | |
| { | |
| "epoch": 42.37, | |
| "learning_rate": 0.0017647457627118644, | |
| "loss": 0.4445, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7247706422018348, | |
| "eval_loss": 0.6277905106544495, | |
| "eval_runtime": 43.2757, | |
| "eval_samples_per_second": 75.562, | |
| "eval_steps_per_second": 9.451, | |
| "step": 25370 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 43.0, | |
| "step": 25370 | |
| }, | |
| { | |
| "epoch": 43.22, | |
| "learning_rate": 0.0016800000000000003, | |
| "loss": 0.4298, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6880733944954128, | |
| "eval_loss": 0.7619650363922119, | |
| "eval_runtime": 43.2274, | |
| "eval_samples_per_second": 75.646, | |
| "eval_steps_per_second": 9.462, | |
| "step": 25960 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 44.0, | |
| "step": 25960 | |
| }, | |
| { | |
| "epoch": 44.07, | |
| "learning_rate": 0.0015952542372881355, | |
| "loss": 0.4346, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "learning_rate": 0.0015105084745762713, | |
| "loss": 0.4319, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7311926605504587, | |
| "eval_loss": 0.6154680848121643, | |
| "eval_runtime": 43.3006, | |
| "eval_samples_per_second": 75.519, | |
| "eval_steps_per_second": 9.446, | |
| "step": 26550 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 45.0, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 45.76, | |
| "learning_rate": 0.0014257627118644067, | |
| "loss": 0.4178, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.736085626911315, | |
| "eval_loss": 0.6141914129257202, | |
| "eval_runtime": 43.3021, | |
| "eval_samples_per_second": 75.516, | |
| "eval_steps_per_second": 9.445, | |
| "step": 27140 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 46.0, | |
| "step": 27140 | |
| }, | |
| { | |
| "epoch": 46.61, | |
| "learning_rate": 0.0013410169491525424, | |
| "loss": 0.4204, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7321100917431193, | |
| "eval_loss": 0.6599806547164917, | |
| "eval_runtime": 43.3421, | |
| "eval_samples_per_second": 75.446, | |
| "eval_steps_per_second": 9.437, | |
| "step": 27730 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7373088685015291, | |
| "epoch": 47.0, | |
| "step": 27730 | |
| }, | |
| { | |
| "epoch": 47.46, | |
| "learning_rate": 0.001256271186440678, | |
| "loss": 0.4204, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7403669724770642, | |
| "eval_loss": 0.601150631904602, | |
| "eval_runtime": 43.197, | |
| "eval_samples_per_second": 75.7, | |
| "eval_steps_per_second": 9.468, | |
| "step": 28320 | |
| }, | |
| { | |
| "best_epoch": 47, | |
| "best_eval_accuracy": 0.7403669724770642, | |
| "epoch": 48.0, | |
| "step": 28320 | |
| }, | |
| { | |
| "epoch": 48.31, | |
| "learning_rate": 0.0011715254237288136, | |
| "loss": 0.4038, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7391437308868501, | |
| "eval_loss": 0.6091906428337097, | |
| "eval_runtime": 43.2721, | |
| "eval_samples_per_second": 75.568, | |
| "eval_steps_per_second": 9.452, | |
| "step": 28910 | |
| }, | |
| { | |
| "best_epoch": 47, | |
| "best_eval_accuracy": 0.7403669724770642, | |
| "epoch": 49.0, | |
| "step": 28910 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 0.001086779661016949, | |
| "loss": 0.4017, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0010022033898305085, | |
| "loss": 0.4103, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.6660399436950684, | |
| "eval_runtime": 43.2592, | |
| "eval_samples_per_second": 75.591, | |
| "eval_steps_per_second": 9.455, | |
| "step": 29500 | |
| }, | |
| { | |
| "best_epoch": 47, | |
| "best_eval_accuracy": 0.7403669724770642, | |
| "epoch": 50.0, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 0.000917627118644068, | |
| "loss": 0.3979, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7363914373088685, | |
| "eval_loss": 0.6605736613273621, | |
| "eval_runtime": 43.1587, | |
| "eval_samples_per_second": 75.767, | |
| "eval_steps_per_second": 9.477, | |
| "step": 30090 | |
| }, | |
| { | |
| "best_epoch": 47, | |
| "best_eval_accuracy": 0.7403669724770642, | |
| "epoch": 51.0, | |
| "step": 30090 | |
| }, | |
| { | |
| "epoch": 51.69, | |
| "learning_rate": 0.0008328813559322035, | |
| "loss": 0.3946, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7223241590214067, | |
| "eval_loss": 0.7039574384689331, | |
| "eval_runtime": 43.2757, | |
| "eval_samples_per_second": 75.562, | |
| "eval_steps_per_second": 9.451, | |
| "step": 30680 | |
| }, | |
| { | |
| "best_epoch": 47, | |
| "best_eval_accuracy": 0.7403669724770642, | |
| "epoch": 52.0, | |
| "step": 30680 | |
| }, | |
| { | |
| "epoch": 52.54, | |
| "learning_rate": 0.000748135593220339, | |
| "loss": 0.3857, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7412844036697248, | |
| "eval_loss": 0.6302646398544312, | |
| "eval_runtime": 43.1428, | |
| "eval_samples_per_second": 75.795, | |
| "eval_steps_per_second": 9.48, | |
| "step": 31270 | |
| }, | |
| { | |
| "best_epoch": 52, | |
| "best_eval_accuracy": 0.7412844036697248, | |
| "epoch": 53.0, | |
| "step": 31270 | |
| }, | |
| { | |
| "epoch": 53.39, | |
| "learning_rate": 0.0006633898305084746, | |
| "loss": 0.3837, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7269113149847095, | |
| "eval_loss": 0.6580860614776611, | |
| "eval_runtime": 43.2755, | |
| "eval_samples_per_second": 75.562, | |
| "eval_steps_per_second": 9.451, | |
| "step": 31860 | |
| }, | |
| { | |
| "best_epoch": 52, | |
| "best_eval_accuracy": 0.7412844036697248, | |
| "epoch": 54.0, | |
| "step": 31860 | |
| }, | |
| { | |
| "epoch": 54.24, | |
| "learning_rate": 0.0005786440677966102, | |
| "loss": 0.3803, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7281345565749235, | |
| "eval_loss": 0.6364992260932922, | |
| "eval_runtime": 43.2674, | |
| "eval_samples_per_second": 75.577, | |
| "eval_steps_per_second": 9.453, | |
| "step": 32450 | |
| }, | |
| { | |
| "best_epoch": 52, | |
| "best_eval_accuracy": 0.7412844036697248, | |
| "epoch": 55.0, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 55.08, | |
| "learning_rate": 0.0004938983050847458, | |
| "loss": 0.3847, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 55.93, | |
| "learning_rate": 0.0004091525423728814, | |
| "loss": 0.3792, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7302752293577982, | |
| "eval_loss": 0.6349842548370361, | |
| "eval_runtime": 43.2291, | |
| "eval_samples_per_second": 75.643, | |
| "eval_steps_per_second": 9.461, | |
| "step": 33040 | |
| }, | |
| { | |
| "best_epoch": 52, | |
| "best_eval_accuracy": 0.7412844036697248, | |
| "epoch": 56.0, | |
| "step": 33040 | |
| }, | |
| { | |
| "epoch": 56.78, | |
| "learning_rate": 0.00032440677966101696, | |
| "loss": 0.3826, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7415902140672783, | |
| "eval_loss": 0.6233869791030884, | |
| "eval_runtime": 43.2253, | |
| "eval_samples_per_second": 75.65, | |
| "eval_steps_per_second": 9.462, | |
| "step": 33630 | |
| }, | |
| { | |
| "best_epoch": 56, | |
| "best_eval_accuracy": 0.7415902140672783, | |
| "epoch": 57.0, | |
| "step": 33630 | |
| }, | |
| { | |
| "epoch": 57.63, | |
| "learning_rate": 0.00023966101694915254, | |
| "loss": 0.3784, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.735474006116208, | |
| "eval_loss": 0.6312357187271118, | |
| "eval_runtime": 43.257, | |
| "eval_samples_per_second": 75.595, | |
| "eval_steps_per_second": 9.455, | |
| "step": 34220 | |
| }, | |
| { | |
| "best_epoch": 56, | |
| "best_eval_accuracy": 0.7415902140672783, | |
| "epoch": 58.0, | |
| "step": 34220 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 0.00015491525423728814, | |
| "loss": 0.373, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7403669724770642, | |
| "eval_loss": 0.6151607632637024, | |
| "eval_runtime": 43.2076, | |
| "eval_samples_per_second": 75.681, | |
| "eval_steps_per_second": 9.466, | |
| "step": 34810 | |
| }, | |
| { | |
| "best_epoch": 56, | |
| "best_eval_accuracy": 0.7415902140672783, | |
| "epoch": 59.0, | |
| "step": 34810 | |
| }, | |
| { | |
| "epoch": 59.32, | |
| "learning_rate": 7.016949152542373e-05, | |
| "loss": 0.3713, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.735474006116208, | |
| "eval_loss": 0.6204875707626343, | |
| "eval_runtime": 20.923, | |
| "eval_samples_per_second": 156.287, | |
| "eval_steps_per_second": 19.548, | |
| "step": 35400 | |
| }, | |
| { | |
| "best_epoch": 56, | |
| "best_eval_accuracy": 0.7415902140672783, | |
| "epoch": 60.0, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 35400, | |
| "total_flos": 2.6355950886279168e+17, | |
| "train_loss": 0.581377860031559, | |
| "train_runtime": 12400.4956, | |
| "train_samples_per_second": 45.613, | |
| "train_steps_per_second": 2.855 | |
| } | |
| ], | |
| "max_steps": 35400, | |
| "num_train_epochs": 60, | |
| "total_flos": 2.6355950886279168e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |