| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.774057048004438, | |
| "global_step": 180000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.892535079835384e-05, | |
| "loss": 3.2017, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.4179681193308354, | |
| "eval_loss": 2.969822883605957, | |
| "eval_runtime": 1929.4803, | |
| "eval_samples_per_second": 19.496, | |
| "eval_steps_per_second": 2.437, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.785070159670768e-05, | |
| "loss": 2.9116, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.4297956163670618, | |
| "eval_loss": 2.8731179237365723, | |
| "eval_runtime": 1919.4124, | |
| "eval_samples_per_second": 19.598, | |
| "eval_steps_per_second": 2.45, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.677605239506152e-05, | |
| "loss": 2.8412, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.4368075611910975, | |
| "eval_loss": 2.81874942779541, | |
| "eval_runtime": 2015.9454, | |
| "eval_samples_per_second": 18.66, | |
| "eval_steps_per_second": 2.333, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5701403193415356e-05, | |
| "loss": 2.7937, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.44204520475458375, | |
| "eval_loss": 2.778646230697632, | |
| "eval_runtime": 1919.08, | |
| "eval_samples_per_second": 19.602, | |
| "eval_steps_per_second": 2.451, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4626753991769196e-05, | |
| "loss": 2.7614, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.44610035327770187, | |
| "eval_loss": 2.7471842765808105, | |
| "eval_runtime": 1919.775, | |
| "eval_samples_per_second": 19.594, | |
| "eval_steps_per_second": 2.45, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.355188977427636e-05, | |
| "loss": 2.7295, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.4501440419543679, | |
| "eval_loss": 2.7196261882781982, | |
| "eval_runtime": 1928.9026, | |
| "eval_samples_per_second": 19.502, | |
| "eval_steps_per_second": 2.438, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.24772405726302e-05, | |
| "loss": 2.7008, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.45296033170252703, | |
| "eval_loss": 2.6961302757263184, | |
| "eval_runtime": 1926.8386, | |
| "eval_samples_per_second": 19.523, | |
| "eval_steps_per_second": 2.441, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.140237635513737e-05, | |
| "loss": 2.6827, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.4561378015092748, | |
| "eval_loss": 2.6738195419311523, | |
| "eval_runtime": 1920.5318, | |
| "eval_samples_per_second": 19.587, | |
| "eval_steps_per_second": 2.449, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.032772715349121e-05, | |
| "loss": 2.6545, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.4590067649734393, | |
| "eval_loss": 2.6545751094818115, | |
| "eval_runtime": 1933.7083, | |
| "eval_samples_per_second": 19.453, | |
| "eval_steps_per_second": 2.432, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9252862935998384e-05, | |
| "loss": 2.6419, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.4616434651550895, | |
| "eval_loss": 2.635937452316284, | |
| "eval_runtime": 1931.385, | |
| "eval_samples_per_second": 19.477, | |
| "eval_steps_per_second": 2.435, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8178213734352224e-05, | |
| "loss": 2.6208, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.4644954077588773, | |
| "eval_loss": 2.617478847503662, | |
| "eval_runtime": 1935.6188, | |
| "eval_samples_per_second": 19.434, | |
| "eval_steps_per_second": 2.43, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7103564532706064e-05, | |
| "loss": 2.604, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.4666273030036154, | |
| "eval_loss": 2.6017534732818604, | |
| "eval_runtime": 1934.3532, | |
| "eval_samples_per_second": 19.447, | |
| "eval_steps_per_second": 2.431, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.60289153310599e-05, | |
| "loss": 2.5883, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.4690363654190064, | |
| "eval_loss": 2.5858962535858154, | |
| "eval_runtime": 1937.9051, | |
| "eval_samples_per_second": 19.411, | |
| "eval_steps_per_second": 2.427, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.495426612941374e-05, | |
| "loss": 2.5733, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.47110511457104925, | |
| "eval_loss": 2.5711781978607178, | |
| "eval_runtime": 1929.1817, | |
| "eval_samples_per_second": 19.499, | |
| "eval_steps_per_second": 2.438, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.387940191192091e-05, | |
| "loss": 2.5603, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.4735584312234197, | |
| "eval_loss": 2.5554990768432617, | |
| "eval_runtime": 1924.3705, | |
| "eval_samples_per_second": 19.548, | |
| "eval_steps_per_second": 2.444, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.280475271027475e-05, | |
| "loss": 2.5462, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.4755388538038284, | |
| "eval_loss": 2.541663646697998, | |
| "eval_runtime": 1932.1982, | |
| "eval_samples_per_second": 19.469, | |
| "eval_steps_per_second": 2.434, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.173010350862859e-05, | |
| "loss": 2.5267, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.47766700705788817, | |
| "eval_loss": 2.528374433517456, | |
| "eval_runtime": 1933.9592, | |
| "eval_samples_per_second": 19.451, | |
| "eval_steps_per_second": 2.432, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.0655454306982425e-05, | |
| "loss": 2.5153, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.47989050311610376, | |
| "eval_loss": 2.514660596847534, | |
| "eval_runtime": 1929.164, | |
| "eval_samples_per_second": 19.499, | |
| "eval_steps_per_second": 2.438, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9580805105336262e-05, | |
| "loss": 2.5028, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.481903668114947, | |
| "eval_loss": 2.501615285873413, | |
| "eval_runtime": 1929.1634, | |
| "eval_samples_per_second": 19.499, | |
| "eval_steps_per_second": 2.438, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8505940887843435e-05, | |
| "loss": 2.4881, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.4839338799602133, | |
| "eval_loss": 2.488723039627075, | |
| "eval_runtime": 1930.4001, | |
| "eval_samples_per_second": 19.487, | |
| "eval_steps_per_second": 2.436, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7431291686197276e-05, | |
| "loss": 2.4758, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.48596689829848827, | |
| "eval_loss": 2.475806951522827, | |
| "eval_runtime": 1923.9804, | |
| "eval_samples_per_second": 19.552, | |
| "eval_steps_per_second": 2.444, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6356642484551112e-05, | |
| "loss": 2.4632, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.4880078683669545, | |
| "eval_loss": 2.463679552078247, | |
| "eval_runtime": 1943.6457, | |
| "eval_samples_per_second": 19.354, | |
| "eval_steps_per_second": 2.42, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5281993282904953e-05, | |
| "loss": 2.4543, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.4898118976645586, | |
| "eval_loss": 2.4515490531921387, | |
| "eval_runtime": 1940.3072, | |
| "eval_samples_per_second": 19.387, | |
| "eval_steps_per_second": 2.424, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4206914049565453e-05, | |
| "loss": 2.4416, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.49199028194626443, | |
| "eval_loss": 2.4388370513916016, | |
| "eval_runtime": 1928.5903, | |
| "eval_samples_per_second": 19.505, | |
| "eval_steps_per_second": 2.439, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.313247986376596e-05, | |
| "loss": 2.4256, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.49386564294117247, | |
| "eval_loss": 2.4272964000701904, | |
| "eval_runtime": 1927.1096, | |
| "eval_samples_per_second": 19.52, | |
| "eval_steps_per_second": 2.44, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.20578306621198e-05, | |
| "loss": 2.4166, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.4959010260096677, | |
| "eval_loss": 2.4158496856689453, | |
| "eval_runtime": 1932.6805, | |
| "eval_samples_per_second": 19.464, | |
| "eval_steps_per_second": 2.433, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.0982751428780303e-05, | |
| "loss": 2.4052, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.4977953568184306, | |
| "eval_loss": 2.4038643836975098, | |
| "eval_runtime": 1925.4197, | |
| "eval_samples_per_second": 19.537, | |
| "eval_steps_per_second": 2.443, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.990831724298081e-05, | |
| "loss": 2.3936, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.49973316228278164, | |
| "eval_loss": 2.392191171646118, | |
| "eval_runtime": 1928.0691, | |
| "eval_samples_per_second": 19.51, | |
| "eval_steps_per_second": 2.439, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8833668041334647e-05, | |
| "loss": 2.379, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.5019234221876816, | |
| "eval_loss": 2.38037371635437, | |
| "eval_runtime": 1923.4067, | |
| "eval_samples_per_second": 19.557, | |
| "eval_steps_per_second": 2.445, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7759018839688484e-05, | |
| "loss": 2.3659, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.5037539832386363, | |
| "eval_loss": 2.3692569732666016, | |
| "eval_runtime": 1925.9734, | |
| "eval_samples_per_second": 19.531, | |
| "eval_steps_per_second": 2.442, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6684154622195657e-05, | |
| "loss": 2.3588, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.5057738006653519, | |
| "eval_loss": 2.357806444168091, | |
| "eval_runtime": 1927.4777, | |
| "eval_samples_per_second": 19.516, | |
| "eval_steps_per_second": 2.44, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5609505420549494e-05, | |
| "loss": 2.3529, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.5079495603563737, | |
| "eval_loss": 2.3464465141296387, | |
| "eval_runtime": 1926.6683, | |
| "eval_samples_per_second": 19.524, | |
| "eval_steps_per_second": 2.441, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4535071234750002e-05, | |
| "loss": 2.3338, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.5098386939558613, | |
| "eval_loss": 2.335519313812256, | |
| "eval_runtime": 1925.6719, | |
| "eval_samples_per_second": 19.534, | |
| "eval_steps_per_second": 2.442, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3460422033103839e-05, | |
| "loss": 2.3238, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.5118405290384843, | |
| "eval_loss": 2.3250160217285156, | |
| "eval_runtime": 1925.0126, | |
| "eval_samples_per_second": 19.541, | |
| "eval_steps_per_second": 2.443, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2385557815611011e-05, | |
| "loss": 2.3139, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.5137200997729053, | |
| "eval_loss": 2.314518451690674, | |
| "eval_runtime": 1927.2965, | |
| "eval_samples_per_second": 19.518, | |
| "eval_steps_per_second": 2.44, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1311123629811518e-05, | |
| "loss": 2.3035, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.5153991621734844, | |
| "eval_loss": 2.3050577640533447, | |
| "eval_runtime": 1927.482, | |
| "eval_samples_per_second": 19.516, | |
| "eval_steps_per_second": 2.44, | |
| "step": 180000 | |
| } | |
| ], | |
| "max_steps": 232541, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.138588502294528e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |