| { | |
| "best_metric": 0.7307692307692307, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-ve-UH2\\checkpoint-130", | |
| "epoch": 80.0, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.609081506729126, | |
| "eval_runtime": 0.6703, | |
| "eval_samples_per_second": 77.577, | |
| "eval_steps_per_second": 2.984, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4230769230769231, | |
| "eval_loss": 1.606997013092041, | |
| "eval_runtime": 0.6324, | |
| "eval_samples_per_second": 82.226, | |
| "eval_steps_per_second": 3.163, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.6017448902130127, | |
| "eval_runtime": 0.6243, | |
| "eval_samples_per_second": 83.287, | |
| "eval_steps_per_second": 3.203, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.5911049842834473, | |
| "eval_runtime": 0.6637, | |
| "eval_samples_per_second": 78.353, | |
| "eval_steps_per_second": 3.014, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.6022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.5707097053527832, | |
| "eval_runtime": 0.6399, | |
| "eval_samples_per_second": 81.258, | |
| "eval_steps_per_second": 3.125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.5355277061462402, | |
| "eval_runtime": 0.6579, | |
| "eval_samples_per_second": 79.043, | |
| "eval_steps_per_second": 3.04, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.495114803314209, | |
| "eval_runtime": 0.6253, | |
| "eval_samples_per_second": 83.162, | |
| "eval_steps_per_second": 3.199, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.4528276920318604, | |
| "eval_runtime": 0.6371, | |
| "eval_samples_per_second": 81.621, | |
| "eval_steps_per_second": 3.139, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.4096202850341797, | |
| "eval_runtime": 0.634, | |
| "eval_samples_per_second": 82.019, | |
| "eval_steps_per_second": 3.155, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.4645, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3819681406021118, | |
| "eval_runtime": 0.6319, | |
| "eval_samples_per_second": 82.295, | |
| "eval_steps_per_second": 3.165, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.4055241346359253, | |
| "eval_runtime": 0.6127, | |
| "eval_samples_per_second": 84.869, | |
| "eval_steps_per_second": 3.264, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3765194416046143, | |
| "eval_runtime": 0.6553, | |
| "eval_samples_per_second": 79.349, | |
| "eval_steps_per_second": 3.052, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3820006847381592, | |
| "eval_runtime": 0.6441, | |
| "eval_samples_per_second": 80.727, | |
| "eval_steps_per_second": 3.105, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3712302446365356, | |
| "eval_runtime": 0.6241, | |
| "eval_samples_per_second": 83.319, | |
| "eval_steps_per_second": 3.205, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.3172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3546074628829956, | |
| "eval_runtime": 0.6587, | |
| "eval_samples_per_second": 78.948, | |
| "eval_steps_per_second": 3.036, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.363667607307434, | |
| "eval_runtime": 0.6457, | |
| "eval_samples_per_second": 80.531, | |
| "eval_steps_per_second": 3.097, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3645634651184082, | |
| "eval_runtime": 0.6364, | |
| "eval_samples_per_second": 81.71, | |
| "eval_steps_per_second": 3.143, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3271024227142334, | |
| "eval_runtime": 0.6426, | |
| "eval_samples_per_second": 80.918, | |
| "eval_steps_per_second": 3.112, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3084486722946167, | |
| "eval_runtime": 0.6335, | |
| "eval_samples_per_second": 82.083, | |
| "eval_steps_per_second": 3.157, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.3401799201965332, | |
| "eval_runtime": 0.6187, | |
| "eval_samples_per_second": 84.048, | |
| "eval_steps_per_second": 3.233, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.355008840560913, | |
| "eval_runtime": 0.6297, | |
| "eval_samples_per_second": 82.582, | |
| "eval_steps_per_second": 3.176, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.2677156925201416, | |
| "eval_runtime": 0.6111, | |
| "eval_samples_per_second": 85.09, | |
| "eval_steps_per_second": 3.273, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.40384615384615385, | |
| "eval_loss": 1.2093143463134766, | |
| "eval_runtime": 0.6388, | |
| "eval_samples_per_second": 81.403, | |
| "eval_steps_per_second": 3.131, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4230769230769231, | |
| "eval_loss": 1.2039647102355957, | |
| "eval_runtime": 0.6687, | |
| "eval_samples_per_second": 77.761, | |
| "eval_steps_per_second": 2.991, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 1.2092, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4230769230769231, | |
| "eval_loss": 1.2963263988494873, | |
| "eval_runtime": 0.6352, | |
| "eval_samples_per_second": 81.858, | |
| "eval_steps_per_second": 3.148, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4807692307692308, | |
| "eval_loss": 1.2917104959487915, | |
| "eval_runtime": 0.6338, | |
| "eval_samples_per_second": 82.049, | |
| "eval_steps_per_second": 3.156, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5769230769230769, | |
| "eval_loss": 1.179789662361145, | |
| "eval_runtime": 0.6335, | |
| "eval_samples_per_second": 82.079, | |
| "eval_steps_per_second": 3.157, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6346153846153846, | |
| "eval_loss": 1.104748010635376, | |
| "eval_runtime": 0.6601, | |
| "eval_samples_per_second": 78.78, | |
| "eval_steps_per_second": 3.03, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 1.092299222946167, | |
| "eval_runtime": 0.65, | |
| "eval_samples_per_second": 79.997, | |
| "eval_steps_per_second": 3.077, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 1.1321, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 1.1065970659255981, | |
| "eval_runtime": 0.6585, | |
| "eval_samples_per_second": 78.963, | |
| "eval_steps_per_second": 3.037, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 1.087414026260376, | |
| "eval_runtime": 0.6402, | |
| "eval_samples_per_second": 81.227, | |
| "eval_steps_per_second": 3.124, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 1.0547945499420166, | |
| "eval_runtime": 0.6324, | |
| "eval_samples_per_second": 82.22, | |
| "eval_steps_per_second": 3.162, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 1.0011744499206543, | |
| "eval_runtime": 0.6601, | |
| "eval_samples_per_second": 78.779, | |
| "eval_steps_per_second": 3.03, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.964054524898529, | |
| "eval_runtime": 0.6484, | |
| "eval_samples_per_second": 80.2, | |
| "eval_steps_per_second": 3.085, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.0022, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 0.9795560836791992, | |
| "eval_runtime": 0.5986, | |
| "eval_samples_per_second": 86.869, | |
| "eval_steps_per_second": 3.341, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 0.9631132483482361, | |
| "eval_runtime": 0.6376, | |
| "eval_samples_per_second": 81.556, | |
| "eval_steps_per_second": 3.137, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.9039589762687683, | |
| "eval_runtime": 0.6112, | |
| "eval_samples_per_second": 85.085, | |
| "eval_steps_per_second": 3.272, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.8731460571289062, | |
| "eval_runtime": 0.6395, | |
| "eval_samples_per_second": 81.316, | |
| "eval_steps_per_second": 3.128, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.8960409164428711, | |
| "eval_runtime": 0.8137, | |
| "eval_samples_per_second": 63.905, | |
| "eval_steps_per_second": 2.458, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.8941, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6538461538461539, | |
| "eval_loss": 0.9132604598999023, | |
| "eval_runtime": 0.638, | |
| "eval_samples_per_second": 81.51, | |
| "eval_steps_per_second": 3.135, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.8507206439971924, | |
| "eval_runtime": 0.63, | |
| "eval_samples_per_second": 82.538, | |
| "eval_steps_per_second": 3.175, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.8063971996307373, | |
| "eval_runtime": 0.6434, | |
| "eval_samples_per_second": 80.815, | |
| "eval_steps_per_second": 3.108, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.8075121641159058, | |
| "eval_runtime": 0.6586, | |
| "eval_samples_per_second": 78.958, | |
| "eval_steps_per_second": 3.037, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.8486055731773376, | |
| "eval_runtime": 0.6337, | |
| "eval_samples_per_second": 82.054, | |
| "eval_steps_per_second": 3.156, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.7866, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.8074995875358582, | |
| "eval_runtime": 0.6513, | |
| "eval_samples_per_second": 79.838, | |
| "eval_steps_per_second": 3.071, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7495647072792053, | |
| "eval_runtime": 0.6239, | |
| "eval_samples_per_second": 83.352, | |
| "eval_steps_per_second": 3.206, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7431188225746155, | |
| "eval_runtime": 0.6623, | |
| "eval_samples_per_second": 78.52, | |
| "eval_steps_per_second": 3.02, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7441921830177307, | |
| "eval_runtime": 0.6175, | |
| "eval_samples_per_second": 84.213, | |
| "eval_steps_per_second": 3.239, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7734705805778503, | |
| "eval_runtime": 0.6485, | |
| "eval_samples_per_second": 80.182, | |
| "eval_steps_per_second": 3.084, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.7281, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7750733494758606, | |
| "eval_runtime": 0.6429, | |
| "eval_samples_per_second": 80.889, | |
| "eval_steps_per_second": 3.111, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7370321750640869, | |
| "eval_runtime": 0.6166, | |
| "eval_samples_per_second": 84.335, | |
| "eval_steps_per_second": 3.244, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7230252623558044, | |
| "eval_runtime": 0.6178, | |
| "eval_samples_per_second": 84.169, | |
| "eval_steps_per_second": 3.237, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7314091920852661, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 82.401, | |
| "eval_steps_per_second": 3.169, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7497729063034058, | |
| "eval_runtime": 0.6298, | |
| "eval_samples_per_second": 82.566, | |
| "eval_steps_per_second": 3.176, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.6725, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7556822896003723, | |
| "eval_runtime": 0.6792, | |
| "eval_samples_per_second": 76.566, | |
| "eval_steps_per_second": 2.945, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.7313970923423767, | |
| "eval_runtime": 0.6462, | |
| "eval_samples_per_second": 80.472, | |
| "eval_steps_per_second": 3.095, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.7334386110305786, | |
| "eval_runtime": 0.676, | |
| "eval_samples_per_second": 76.92, | |
| "eval_steps_per_second": 2.958, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.7375408411026001, | |
| "eval_runtime": 0.6333, | |
| "eval_samples_per_second": 82.111, | |
| "eval_steps_per_second": 3.158, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7434028387069702, | |
| "eval_runtime": 0.6832, | |
| "eval_samples_per_second": 76.109, | |
| "eval_steps_per_second": 2.927, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.6526, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7548195719718933, | |
| "eval_runtime": 0.7088, | |
| "eval_samples_per_second": 73.367, | |
| "eval_steps_per_second": 2.822, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.7813425660133362, | |
| "eval_runtime": 0.6138, | |
| "eval_samples_per_second": 84.716, | |
| "eval_steps_per_second": 3.258, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.772243857383728, | |
| "eval_runtime": 0.6244, | |
| "eval_samples_per_second": 83.28, | |
| "eval_steps_per_second": 3.203, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.746929407119751, | |
| "eval_runtime": 0.6441, | |
| "eval_samples_per_second": 80.73, | |
| "eval_steps_per_second": 3.105, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7401729822158813, | |
| "eval_runtime": 0.6493, | |
| "eval_samples_per_second": 80.083, | |
| "eval_steps_per_second": 3.08, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.5915, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7307692307692307, | |
| "eval_loss": 0.7448387742042542, | |
| "eval_runtime": 0.6418, | |
| "eval_samples_per_second": 81.016, | |
| "eval_steps_per_second": 3.116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7466877698898315, | |
| "eval_runtime": 0.6284, | |
| "eval_samples_per_second": 82.756, | |
| "eval_steps_per_second": 3.183, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.749629020690918, | |
| "eval_runtime": 0.6627, | |
| "eval_samples_per_second": 78.466, | |
| "eval_steps_per_second": 3.018, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7307692307692307, | |
| "eval_loss": 0.7518380284309387, | |
| "eval_runtime": 0.6669, | |
| "eval_samples_per_second": 77.97, | |
| "eval_steps_per_second": 2.999, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7115384615384616, | |
| "eval_loss": 0.7453244924545288, | |
| "eval_runtime": 0.6333, | |
| "eval_samples_per_second": 82.105, | |
| "eval_steps_per_second": 3.158, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.578, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7384573817253113, | |
| "eval_runtime": 0.6873, | |
| "eval_samples_per_second": 75.657, | |
| "eval_steps_per_second": 2.91, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7411268949508667, | |
| "eval_runtime": 0.6173, | |
| "eval_samples_per_second": 84.245, | |
| "eval_steps_per_second": 3.24, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7441950440406799, | |
| "eval_runtime": 0.6503, | |
| "eval_samples_per_second": 79.967, | |
| "eval_steps_per_second": 3.076, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7440080642700195, | |
| "eval_runtime": 0.6924, | |
| "eval_samples_per_second": 75.105, | |
| "eval_steps_per_second": 2.889, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7427962422370911, | |
| "eval_runtime": 0.6296, | |
| "eval_samples_per_second": 82.587, | |
| "eval_steps_per_second": 3.176, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.5826, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7414448261260986, | |
| "eval_runtime": 0.7004, | |
| "eval_samples_per_second": 74.245, | |
| "eval_steps_per_second": 2.856, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7416151762008667, | |
| "eval_runtime": 0.6484, | |
| "eval_samples_per_second": 80.199, | |
| "eval_steps_per_second": 3.085, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7413759231567383, | |
| "eval_runtime": 0.6172, | |
| "eval_samples_per_second": 84.256, | |
| "eval_steps_per_second": 3.241, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7412547469139099, | |
| "eval_runtime": 0.6446, | |
| "eval_samples_per_second": 80.673, | |
| "eval_steps_per_second": 3.103, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.6730769230769231, | |
| "eval_loss": 0.7413215637207031, | |
| "eval_runtime": 0.6339, | |
| "eval_samples_per_second": 82.035, | |
| "eval_steps_per_second": 3.155, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5586, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.6923076923076923, | |
| "eval_loss": 0.7414627075195312, | |
| "eval_runtime": 0.6668, | |
| "eval_samples_per_second": 77.986, | |
| "eval_steps_per_second": 2.999, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "step": 160, | |
| "total_flos": 6.195054311689421e+17, | |
| "train_loss": 0.9391910135746002, | |
| "train_runtime": 458.9437, | |
| "train_samples_per_second": 41.487, | |
| "train_steps_per_second": 0.349 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 6.195054311689421e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |