| { | |
| "best_metric": 0.7, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-ADC-4cls-0922/checkpoint-122", | |
| "epoch": 200.0, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9655490517616272, | |
| "eval_runtime": 0.8298, | |
| "eval_samples_per_second": 84.356, | |
| "eval_steps_per_second": 2.41, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9653854370117188, | |
| "eval_runtime": 0.6383, | |
| "eval_samples_per_second": 109.671, | |
| "eval_steps_per_second": 3.133, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9650949835777283, | |
| "eval_runtime": 0.6412, | |
| "eval_samples_per_second": 109.167, | |
| "eval_steps_per_second": 3.119, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9646532535552979, | |
| "eval_runtime": 0.8218, | |
| "eval_samples_per_second": 85.18, | |
| "eval_steps_per_second": 2.434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.0064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9641380310058594, | |
| "eval_runtime": 0.6452, | |
| "eval_samples_per_second": 108.491, | |
| "eval_steps_per_second": 3.1, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9635317921638489, | |
| "eval_runtime": 0.6347, | |
| "eval_samples_per_second": 110.284, | |
| "eval_steps_per_second": 3.151, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9628700017929077, | |
| "eval_runtime": 0.8273, | |
| "eval_samples_per_second": 84.611, | |
| "eval_steps_per_second": 2.417, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9623274803161621, | |
| "eval_runtime": 0.6551, | |
| "eval_samples_per_second": 106.859, | |
| "eval_steps_per_second": 3.053, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9616996645927429, | |
| "eval_runtime": 0.646, | |
| "eval_samples_per_second": 108.363, | |
| "eval_steps_per_second": 3.096, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9611372947692871, | |
| "eval_runtime": 0.8313, | |
| "eval_samples_per_second": 84.202, | |
| "eval_steps_per_second": 2.406, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9607454538345337, | |
| "eval_runtime": 0.8335, | |
| "eval_samples_per_second": 83.985, | |
| "eval_steps_per_second": 2.4, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9604489207267761, | |
| "eval_runtime": 0.8194, | |
| "eval_samples_per_second": 85.429, | |
| "eval_steps_per_second": 2.441, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9601203799247742, | |
| "eval_runtime": 0.8211, | |
| "eval_samples_per_second": 85.256, | |
| "eval_steps_per_second": 2.436, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9597390294075012, | |
| "eval_runtime": 0.6563, | |
| "eval_samples_per_second": 106.663, | |
| "eval_steps_per_second": 3.048, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.0278, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9591529965400696, | |
| "eval_runtime": 0.6495, | |
| "eval_samples_per_second": 107.778, | |
| "eval_steps_per_second": 3.079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9581246376037598, | |
| "eval_runtime": 0.791, | |
| "eval_samples_per_second": 88.495, | |
| "eval_steps_per_second": 2.528, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9566996097564697, | |
| "eval_runtime": 0.6461, | |
| "eval_samples_per_second": 108.347, | |
| "eval_steps_per_second": 3.096, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9551236629486084, | |
| "eval_runtime": 0.6456, | |
| "eval_samples_per_second": 108.429, | |
| "eval_steps_per_second": 3.098, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9534342288970947, | |
| "eval_runtime": 0.8038, | |
| "eval_samples_per_second": 87.083, | |
| "eval_steps_per_second": 2.488, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9986, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9513913989067078, | |
| "eval_runtime": 0.6423, | |
| "eval_samples_per_second": 108.98, | |
| "eval_steps_per_second": 3.114, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9493252635002136, | |
| "eval_runtime": 0.6401, | |
| "eval_samples_per_second": 109.357, | |
| "eval_steps_per_second": 3.124, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9471749663352966, | |
| "eval_runtime": 0.7957, | |
| "eval_samples_per_second": 87.97, | |
| "eval_steps_per_second": 2.513, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9451875686645508, | |
| "eval_runtime": 0.6379, | |
| "eval_samples_per_second": 109.728, | |
| "eval_steps_per_second": 3.135, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.943417489528656, | |
| "eval_runtime": 0.6466, | |
| "eval_samples_per_second": 108.259, | |
| "eval_steps_per_second": 3.093, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 6.25e-05, | |
| "loss": 0.9973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9419717788696289, | |
| "eval_runtime": 0.8115, | |
| "eval_samples_per_second": 86.264, | |
| "eval_steps_per_second": 2.465, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9404588937759399, | |
| "eval_runtime": 0.6332, | |
| "eval_samples_per_second": 110.551, | |
| "eval_steps_per_second": 3.159, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6285714285714286, | |
| "eval_loss": 0.9387302994728088, | |
| "eval_runtime": 0.64, | |
| "eval_samples_per_second": 109.375, | |
| "eval_steps_per_second": 3.125, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6285714285714286, | |
| "eval_loss": 0.9375677704811096, | |
| "eval_runtime": 0.8312, | |
| "eval_samples_per_second": 84.219, | |
| "eval_steps_per_second": 2.406, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9368333220481873, | |
| "eval_runtime": 0.6385, | |
| "eval_samples_per_second": 109.629, | |
| "eval_steps_per_second": 3.132, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9936, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9361710548400879, | |
| "eval_runtime": 0.6573, | |
| "eval_samples_per_second": 106.497, | |
| "eval_steps_per_second": 3.043, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9361298680305481, | |
| "eval_runtime": 0.7944, | |
| "eval_samples_per_second": 88.115, | |
| "eval_steps_per_second": 2.518, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9364449381828308, | |
| "eval_runtime": 0.6554, | |
| "eval_samples_per_second": 106.808, | |
| "eval_steps_per_second": 3.052, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9371016621589661, | |
| "eval_runtime": 0.6483, | |
| "eval_samples_per_second": 107.97, | |
| "eval_steps_per_second": 3.085, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.9379546046257019, | |
| "eval_runtime": 0.8119, | |
| "eval_samples_per_second": 86.219, | |
| "eval_steps_per_second": 2.463, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 8.75e-05, | |
| "loss": 0.9746, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9379692077636719, | |
| "eval_runtime": 0.6362, | |
| "eval_samples_per_second": 110.031, | |
| "eval_steps_per_second": 3.144, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9374780654907227, | |
| "eval_runtime": 0.639, | |
| "eval_samples_per_second": 109.543, | |
| "eval_steps_per_second": 3.13, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9379698634147644, | |
| "eval_runtime": 0.8343, | |
| "eval_samples_per_second": 83.899, | |
| "eval_steps_per_second": 2.397, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9375231862068176, | |
| "eval_runtime": 0.6395, | |
| "eval_samples_per_second": 109.457, | |
| "eval_steps_per_second": 3.127, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9369739890098572, | |
| "eval_runtime": 0.6333, | |
| "eval_samples_per_second": 110.536, | |
| "eval_steps_per_second": 3.158, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0113, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9361743330955505, | |
| "eval_runtime": 0.7993, | |
| "eval_samples_per_second": 87.579, | |
| "eval_steps_per_second": 2.502, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9340663552284241, | |
| "eval_runtime": 0.6461, | |
| "eval_samples_per_second": 108.348, | |
| "eval_steps_per_second": 3.096, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.9300563335418701, | |
| "eval_runtime": 0.636, | |
| "eval_samples_per_second": 110.058, | |
| "eval_steps_per_second": 3.145, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9259787201881409, | |
| "eval_runtime": 0.8154, | |
| "eval_samples_per_second": 85.845, | |
| "eval_steps_per_second": 2.453, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9224489331245422, | |
| "eval_runtime": 0.6369, | |
| "eval_samples_per_second": 109.903, | |
| "eval_steps_per_second": 3.14, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 9.687500000000001e-05, | |
| "loss": 0.9756, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9190067648887634, | |
| "eval_runtime": 0.6388, | |
| "eval_samples_per_second": 109.577, | |
| "eval_steps_per_second": 3.131, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9154108166694641, | |
| "eval_runtime": 0.7966, | |
| "eval_samples_per_second": 87.873, | |
| "eval_steps_per_second": 2.511, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.912346363067627, | |
| "eval_runtime": 0.6406, | |
| "eval_samples_per_second": 109.268, | |
| "eval_steps_per_second": 3.122, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9091367721557617, | |
| "eval_runtime": 0.6398, | |
| "eval_samples_per_second": 109.41, | |
| "eval_steps_per_second": 3.126, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9070726037025452, | |
| "eval_runtime": 0.8188, | |
| "eval_samples_per_second": 85.488, | |
| "eval_steps_per_second": 2.443, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 9.375e-05, | |
| "loss": 0.9721, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9055730700492859, | |
| "eval_runtime": 0.6361, | |
| "eval_samples_per_second": 110.054, | |
| "eval_steps_per_second": 3.144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9046576619148254, | |
| "eval_runtime": 0.6407, | |
| "eval_samples_per_second": 109.252, | |
| "eval_steps_per_second": 3.121, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.9038794636726379, | |
| "eval_runtime": 0.8178, | |
| "eval_samples_per_second": 85.592, | |
| "eval_steps_per_second": 2.445, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9030665755271912, | |
| "eval_runtime": 0.6283, | |
| "eval_samples_per_second": 111.419, | |
| "eval_steps_per_second": 3.183, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.902490496635437, | |
| "eval_runtime": 0.8366, | |
| "eval_samples_per_second": 83.669, | |
| "eval_steps_per_second": 2.391, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 9.062500000000001e-05, | |
| "loss": 0.9698, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.902264416217804, | |
| "eval_runtime": 0.9891, | |
| "eval_samples_per_second": 70.774, | |
| "eval_steps_per_second": 2.022, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.9011555314064026, | |
| "eval_runtime": 0.6498, | |
| "eval_samples_per_second": 107.729, | |
| "eval_steps_per_second": 3.078, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8996686935424805, | |
| "eval_runtime": 0.8289, | |
| "eval_samples_per_second": 84.447, | |
| "eval_steps_per_second": 2.413, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8982025980949402, | |
| "eval_runtime": 0.6375, | |
| "eval_samples_per_second": 109.798, | |
| "eval_steps_per_second": 3.137, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8969982266426086, | |
| "eval_runtime": 0.6483, | |
| "eval_samples_per_second": 107.97, | |
| "eval_steps_per_second": 3.085, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 8.75e-05, | |
| "loss": 0.9341, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8956836462020874, | |
| "eval_runtime": 0.8303, | |
| "eval_samples_per_second": 84.307, | |
| "eval_steps_per_second": 2.409, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8946982622146606, | |
| "eval_runtime": 0.6483, | |
| "eval_samples_per_second": 107.981, | |
| "eval_steps_per_second": 3.085, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8940390348434448, | |
| "eval_runtime": 0.6421, | |
| "eval_samples_per_second": 109.023, | |
| "eval_steps_per_second": 3.115, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8940520286560059, | |
| "eval_runtime": 0.8356, | |
| "eval_samples_per_second": 83.773, | |
| "eval_steps_per_second": 2.394, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8934383988380432, | |
| "eval_runtime": 0.6317, | |
| "eval_samples_per_second": 110.812, | |
| "eval_steps_per_second": 3.166, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 8.4375e-05, | |
| "loss": 0.9717, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8916982412338257, | |
| "eval_runtime": 0.6456, | |
| "eval_samples_per_second": 108.418, | |
| "eval_steps_per_second": 3.098, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8898113369941711, | |
| "eval_runtime": 0.8145, | |
| "eval_samples_per_second": 85.937, | |
| "eval_steps_per_second": 2.455, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8883917927742004, | |
| "eval_runtime": 0.6387, | |
| "eval_samples_per_second": 109.599, | |
| "eval_steps_per_second": 3.131, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8869962692260742, | |
| "eval_runtime": 0.6406, | |
| "eval_samples_per_second": 109.266, | |
| "eval_steps_per_second": 3.122, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8853691816329956, | |
| "eval_runtime": 0.8216, | |
| "eval_samples_per_second": 85.2, | |
| "eval_steps_per_second": 2.434, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 8.125000000000001e-05, | |
| "loss": 0.9655, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8840075731277466, | |
| "eval_runtime": 0.6378, | |
| "eval_samples_per_second": 109.751, | |
| "eval_steps_per_second": 3.136, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8826519250869751, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 109.644, | |
| "eval_steps_per_second": 3.133, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8813565373420715, | |
| "eval_runtime": 0.8402, | |
| "eval_samples_per_second": 83.313, | |
| "eval_steps_per_second": 2.38, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8805155754089355, | |
| "eval_runtime": 0.6428, | |
| "eval_samples_per_second": 108.905, | |
| "eval_steps_per_second": 3.112, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8803040385246277, | |
| "eval_runtime": 0.649, | |
| "eval_samples_per_second": 107.857, | |
| "eval_steps_per_second": 3.082, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 7.8125e-05, | |
| "loss": 0.9458, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8801725506782532, | |
| "eval_runtime": 0.82, | |
| "eval_samples_per_second": 85.365, | |
| "eval_steps_per_second": 2.439, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8797475695610046, | |
| "eval_runtime": 0.6476, | |
| "eval_samples_per_second": 108.085, | |
| "eval_steps_per_second": 3.088, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8793725967407227, | |
| "eval_runtime": 0.6468, | |
| "eval_samples_per_second": 108.22, | |
| "eval_steps_per_second": 3.092, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8795827031135559, | |
| "eval_runtime": 0.8346, | |
| "eval_samples_per_second": 83.873, | |
| "eval_steps_per_second": 2.396, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8807878494262695, | |
| "eval_runtime": 0.6453, | |
| "eval_samples_per_second": 108.479, | |
| "eval_steps_per_second": 3.099, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9094, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8817013502120972, | |
| "eval_runtime": 0.6393, | |
| "eval_samples_per_second": 109.492, | |
| "eval_steps_per_second": 3.128, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8828238844871521, | |
| "eval_runtime": 0.8346, | |
| "eval_samples_per_second": 83.868, | |
| "eval_steps_per_second": 2.396, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8835611939430237, | |
| "eval_runtime": 0.636, | |
| "eval_samples_per_second": 110.07, | |
| "eval_steps_per_second": 3.145, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8830356001853943, | |
| "eval_runtime": 0.6535, | |
| "eval_samples_per_second": 107.117, | |
| "eval_steps_per_second": 3.06, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8820751905441284, | |
| "eval_runtime": 0.8384, | |
| "eval_samples_per_second": 83.495, | |
| "eval_steps_per_second": 2.386, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 7.1875e-05, | |
| "loss": 0.8719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8812506794929504, | |
| "eval_runtime": 0.6519, | |
| "eval_samples_per_second": 107.372, | |
| "eval_steps_per_second": 3.068, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8804309368133545, | |
| "eval_runtime": 0.6326, | |
| "eval_samples_per_second": 110.652, | |
| "eval_steps_per_second": 3.161, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8798118829727173, | |
| "eval_runtime": 0.8338, | |
| "eval_samples_per_second": 83.95, | |
| "eval_steps_per_second": 2.399, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8787184953689575, | |
| "eval_runtime": 0.64, | |
| "eval_samples_per_second": 109.38, | |
| "eval_steps_per_second": 3.125, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 0.8769770264625549, | |
| "eval_runtime": 0.6382, | |
| "eval_samples_per_second": 109.679, | |
| "eval_steps_per_second": 3.134, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 6.875e-05, | |
| "loss": 0.9288, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8752025961875916, | |
| "eval_runtime": 0.8649, | |
| "eval_samples_per_second": 80.934, | |
| "eval_steps_per_second": 2.312, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8721939921379089, | |
| "eval_runtime": 0.6536, | |
| "eval_samples_per_second": 107.101, | |
| "eval_steps_per_second": 3.06, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8693682551383972, | |
| "eval_runtime": 0.6434, | |
| "eval_samples_per_second": 108.799, | |
| "eval_steps_per_second": 3.109, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8670406937599182, | |
| "eval_runtime": 0.8337, | |
| "eval_samples_per_second": 83.963, | |
| "eval_steps_per_second": 2.399, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8644655346870422, | |
| "eval_runtime": 0.6432, | |
| "eval_samples_per_second": 108.826, | |
| "eval_steps_per_second": 3.109, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 6.562500000000001e-05, | |
| "loss": 0.9039, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8624207973480225, | |
| "eval_runtime": 0.6482, | |
| "eval_samples_per_second": 107.999, | |
| "eval_steps_per_second": 3.086, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8603058457374573, | |
| "eval_runtime": 0.8409, | |
| "eval_samples_per_second": 83.249, | |
| "eval_steps_per_second": 2.379, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8583868741989136, | |
| "eval_runtime": 0.6484, | |
| "eval_samples_per_second": 107.951, | |
| "eval_steps_per_second": 3.084, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8566268086433411, | |
| "eval_runtime": 0.6949, | |
| "eval_samples_per_second": 100.728, | |
| "eval_steps_per_second": 2.878, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8553413152694702, | |
| "eval_runtime": 0.8276, | |
| "eval_samples_per_second": 84.585, | |
| "eval_steps_per_second": 2.417, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 6.25e-05, | |
| "loss": 0.9081, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8549684286117554, | |
| "eval_runtime": 0.6594, | |
| "eval_samples_per_second": 106.164, | |
| "eval_steps_per_second": 3.033, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8551309108734131, | |
| "eval_runtime": 0.6588, | |
| "eval_samples_per_second": 106.255, | |
| "eval_steps_per_second": 3.036, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8556391000747681, | |
| "eval_runtime": 0.8474, | |
| "eval_samples_per_second": 82.605, | |
| "eval_steps_per_second": 2.36, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8558002710342407, | |
| "eval_runtime": 0.6568, | |
| "eval_samples_per_second": 106.577, | |
| "eval_steps_per_second": 3.045, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8554455637931824, | |
| "eval_runtime": 0.6448, | |
| "eval_samples_per_second": 108.569, | |
| "eval_steps_per_second": 3.102, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 5.9375e-05, | |
| "loss": 0.9142, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8551297783851624, | |
| "eval_runtime": 0.8226, | |
| "eval_samples_per_second": 85.093, | |
| "eval_steps_per_second": 2.431, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8553109169006348, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 107.668, | |
| "eval_steps_per_second": 3.076, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.855134904384613, | |
| "eval_runtime": 0.637, | |
| "eval_samples_per_second": 109.882, | |
| "eval_steps_per_second": 3.139, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8549013137817383, | |
| "eval_runtime": 0.8378, | |
| "eval_samples_per_second": 83.557, | |
| "eval_steps_per_second": 2.387, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.854942798614502, | |
| "eval_runtime": 0.6596, | |
| "eval_samples_per_second": 106.131, | |
| "eval_steps_per_second": 3.032, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 5.6250000000000005e-05, | |
| "loss": 0.9347, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8551362752914429, | |
| "eval_runtime": 0.6674, | |
| "eval_samples_per_second": 104.886, | |
| "eval_steps_per_second": 2.997, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8553721308708191, | |
| "eval_runtime": 0.8336, | |
| "eval_samples_per_second": 83.974, | |
| "eval_steps_per_second": 2.399, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8548364639282227, | |
| "eval_runtime": 0.6506, | |
| "eval_samples_per_second": 107.599, | |
| "eval_steps_per_second": 3.074, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.853795051574707, | |
| "eval_runtime": 0.6756, | |
| "eval_samples_per_second": 103.611, | |
| "eval_steps_per_second": 2.96, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8524832129478455, | |
| "eval_runtime": 0.8168, | |
| "eval_samples_per_second": 85.696, | |
| "eval_steps_per_second": 2.448, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "learning_rate": 5.3125000000000004e-05, | |
| "loss": 0.8922, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8512247204780579, | |
| "eval_runtime": 0.6476, | |
| "eval_samples_per_second": 108.096, | |
| "eval_steps_per_second": 3.088, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8505221009254456, | |
| "eval_runtime": 0.6563, | |
| "eval_samples_per_second": 106.655, | |
| "eval_steps_per_second": 3.047, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.849509596824646, | |
| "eval_runtime": 0.8193, | |
| "eval_samples_per_second": 85.434, | |
| "eval_steps_per_second": 2.441, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8483795523643494, | |
| "eval_runtime": 0.6476, | |
| "eval_samples_per_second": 108.094, | |
| "eval_steps_per_second": 3.088, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8471851944923401, | |
| "eval_runtime": 0.6472, | |
| "eval_samples_per_second": 108.158, | |
| "eval_steps_per_second": 3.09, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8897, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8455559611320496, | |
| "eval_runtime": 0.8155, | |
| "eval_samples_per_second": 85.837, | |
| "eval_steps_per_second": 2.452, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8439861536026001, | |
| "eval_runtime": 0.6794, | |
| "eval_samples_per_second": 103.026, | |
| "eval_steps_per_second": 2.944, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8426181674003601, | |
| "eval_runtime": 0.6386, | |
| "eval_samples_per_second": 109.616, | |
| "eval_steps_per_second": 3.132, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8412323594093323, | |
| "eval_runtime": 0.8222, | |
| "eval_samples_per_second": 85.135, | |
| "eval_steps_per_second": 2.432, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8395997881889343, | |
| "eval_runtime": 0.6405, | |
| "eval_samples_per_second": 109.29, | |
| "eval_steps_per_second": 3.123, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.8829, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8383906483650208, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 109.656, | |
| "eval_steps_per_second": 3.133, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8372732996940613, | |
| "eval_runtime": 0.8007, | |
| "eval_samples_per_second": 87.425, | |
| "eval_steps_per_second": 2.498, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8365365266799927, | |
| "eval_runtime": 0.6412, | |
| "eval_samples_per_second": 109.171, | |
| "eval_steps_per_second": 3.119, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.835951030254364, | |
| "eval_runtime": 0.6518, | |
| "eval_samples_per_second": 107.389, | |
| "eval_steps_per_second": 3.068, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8352962732315063, | |
| "eval_runtime": 0.8209, | |
| "eval_samples_per_second": 85.273, | |
| "eval_steps_per_second": 2.436, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.8744, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8344349265098572, | |
| "eval_runtime": 0.6608, | |
| "eval_samples_per_second": 105.932, | |
| "eval_steps_per_second": 3.027, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8336659669876099, | |
| "eval_runtime": 0.6503, | |
| "eval_samples_per_second": 107.635, | |
| "eval_steps_per_second": 3.075, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8329463601112366, | |
| "eval_runtime": 0.824, | |
| "eval_samples_per_second": 84.952, | |
| "eval_steps_per_second": 2.427, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8324605822563171, | |
| "eval_runtime": 0.6594, | |
| "eval_samples_per_second": 106.156, | |
| "eval_steps_per_second": 3.033, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8318061232566833, | |
| "eval_runtime": 0.6395, | |
| "eval_samples_per_second": 109.457, | |
| "eval_steps_per_second": 3.127, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.8657, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8312056660652161, | |
| "eval_runtime": 0.8064, | |
| "eval_samples_per_second": 86.802, | |
| "eval_steps_per_second": 2.48, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8306312561035156, | |
| "eval_runtime": 0.645, | |
| "eval_samples_per_second": 108.533, | |
| "eval_steps_per_second": 3.101, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8299986720085144, | |
| "eval_runtime": 0.6678, | |
| "eval_samples_per_second": 104.823, | |
| "eval_steps_per_second": 2.995, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8296393752098083, | |
| "eval_runtime": 0.8159, | |
| "eval_samples_per_second": 85.792, | |
| "eval_steps_per_second": 2.451, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8294458389282227, | |
| "eval_runtime": 0.6396, | |
| "eval_samples_per_second": 109.442, | |
| "eval_steps_per_second": 3.127, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.9421, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8292441368103027, | |
| "eval_runtime": 0.6515, | |
| "eval_samples_per_second": 107.445, | |
| "eval_steps_per_second": 3.07, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8291121125221252, | |
| "eval_runtime": 0.8194, | |
| "eval_samples_per_second": 85.428, | |
| "eval_steps_per_second": 2.441, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_accuracy": 0.6714285714285714, | |
| "eval_loss": 0.8290067315101624, | |
| "eval_runtime": 0.9452, | |
| "eval_samples_per_second": 74.057, | |
| "eval_steps_per_second": 2.116, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8290221095085144, | |
| "eval_runtime": 0.6854, | |
| "eval_samples_per_second": 102.129, | |
| "eval_steps_per_second": 2.918, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8288514018058777, | |
| "eval_runtime": 0.6741, | |
| "eval_samples_per_second": 103.846, | |
| "eval_steps_per_second": 2.967, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 0.9066, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8286876082420349, | |
| "eval_runtime": 0.6545, | |
| "eval_samples_per_second": 106.944, | |
| "eval_steps_per_second": 3.056, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8290360569953918, | |
| "eval_runtime": 0.6611, | |
| "eval_samples_per_second": 105.889, | |
| "eval_steps_per_second": 3.025, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8293396830558777, | |
| "eval_runtime": 0.6543, | |
| "eval_samples_per_second": 106.98, | |
| "eval_steps_per_second": 3.057, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8294445872306824, | |
| "eval_runtime": 0.6455, | |
| "eval_samples_per_second": 108.45, | |
| "eval_steps_per_second": 3.099, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8294763565063477, | |
| "eval_runtime": 0.9727, | |
| "eval_samples_per_second": 71.966, | |
| "eval_steps_per_second": 2.056, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.9068, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8295239210128784, | |
| "eval_runtime": 0.9775, | |
| "eval_samples_per_second": 71.611, | |
| "eval_steps_per_second": 2.046, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8294230699539185, | |
| "eval_runtime": 0.6644, | |
| "eval_samples_per_second": 105.363, | |
| "eval_steps_per_second": 3.01, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.829305112361908, | |
| "eval_runtime": 0.6604, | |
| "eval_samples_per_second": 105.994, | |
| "eval_steps_per_second": 3.028, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8293172717094421, | |
| "eval_runtime": 0.8353, | |
| "eval_samples_per_second": 83.803, | |
| "eval_steps_per_second": 2.394, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8289957046508789, | |
| "eval_runtime": 0.6575, | |
| "eval_samples_per_second": 106.469, | |
| "eval_steps_per_second": 3.042, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 0.8715, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8286699056625366, | |
| "eval_runtime": 0.6466, | |
| "eval_samples_per_second": 108.266, | |
| "eval_steps_per_second": 3.093, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8283028602600098, | |
| "eval_runtime": 0.8251, | |
| "eval_samples_per_second": 84.843, | |
| "eval_steps_per_second": 2.424, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8276944160461426, | |
| "eval_runtime": 0.6461, | |
| "eval_samples_per_second": 108.335, | |
| "eval_steps_per_second": 3.095, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.827368438243866, | |
| "eval_runtime": 0.6771, | |
| "eval_samples_per_second": 103.379, | |
| "eval_steps_per_second": 2.954, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8269255757331848, | |
| "eval_runtime": 0.8454, | |
| "eval_samples_per_second": 82.804, | |
| "eval_steps_per_second": 2.366, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.8921, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.826560914516449, | |
| "eval_runtime": 0.6462, | |
| "eval_samples_per_second": 108.325, | |
| "eval_steps_per_second": 3.095, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8263527154922485, | |
| "eval_runtime": 0.6718, | |
| "eval_samples_per_second": 104.193, | |
| "eval_steps_per_second": 2.977, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.826131284236908, | |
| "eval_runtime": 0.8359, | |
| "eval_samples_per_second": 83.747, | |
| "eval_steps_per_second": 2.393, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8259814977645874, | |
| "eval_runtime": 0.6618, | |
| "eval_samples_per_second": 105.778, | |
| "eval_steps_per_second": 3.022, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8257696032524109, | |
| "eval_runtime": 0.6625, | |
| "eval_samples_per_second": 105.664, | |
| "eval_steps_per_second": 3.019, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 0.8768, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.825222373008728, | |
| "eval_runtime": 0.8436, | |
| "eval_samples_per_second": 82.974, | |
| "eval_steps_per_second": 2.371, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8247527480125427, | |
| "eval_runtime": 0.6665, | |
| "eval_samples_per_second": 105.023, | |
| "eval_steps_per_second": 3.001, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8242577910423279, | |
| "eval_runtime": 0.6669, | |
| "eval_samples_per_second": 104.971, | |
| "eval_steps_per_second": 2.999, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 168.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8237206339836121, | |
| "eval_runtime": 0.8327, | |
| "eval_samples_per_second": 84.06, | |
| "eval_steps_per_second": 2.402, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 169.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8231467604637146, | |
| "eval_runtime": 0.6532, | |
| "eval_samples_per_second": 107.163, | |
| "eval_steps_per_second": 3.062, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 170.0, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.8519, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 170.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8226965665817261, | |
| "eval_runtime": 0.6591, | |
| "eval_samples_per_second": 106.199, | |
| "eval_steps_per_second": 3.034, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 171.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.822342038154602, | |
| "eval_runtime": 0.8214, | |
| "eval_samples_per_second": 85.216, | |
| "eval_steps_per_second": 2.435, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 172.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.822126030921936, | |
| "eval_runtime": 0.6612, | |
| "eval_samples_per_second": 105.861, | |
| "eval_steps_per_second": 3.025, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 173.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8220161199569702, | |
| "eval_runtime": 0.6469, | |
| "eval_samples_per_second": 108.212, | |
| "eval_steps_per_second": 3.092, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 174.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8218111991882324, | |
| "eval_runtime": 0.8067, | |
| "eval_samples_per_second": 86.769, | |
| "eval_steps_per_second": 2.479, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.92, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.821461021900177, | |
| "eval_runtime": 0.6484, | |
| "eval_samples_per_second": 107.962, | |
| "eval_steps_per_second": 3.085, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 176.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8210566639900208, | |
| "eval_runtime": 0.6645, | |
| "eval_samples_per_second": 105.342, | |
| "eval_steps_per_second": 3.01, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 177.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8207017183303833, | |
| "eval_runtime": 0.8152, | |
| "eval_samples_per_second": 85.873, | |
| "eval_steps_per_second": 2.454, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 178.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8204047679901123, | |
| "eval_runtime": 0.7773, | |
| "eval_samples_per_second": 90.05, | |
| "eval_steps_per_second": 2.573, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 179.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8200381398200989, | |
| "eval_runtime": 0.6533, | |
| "eval_samples_per_second": 107.15, | |
| "eval_steps_per_second": 3.061, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 180.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.879, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 180.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8197112083435059, | |
| "eval_runtime": 0.8254, | |
| "eval_samples_per_second": 84.803, | |
| "eval_steps_per_second": 2.423, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 181.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8194140195846558, | |
| "eval_runtime": 0.6736, | |
| "eval_samples_per_second": 103.918, | |
| "eval_steps_per_second": 2.969, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 182.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8190609812736511, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 107.669, | |
| "eval_steps_per_second": 3.076, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 183.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.8187218308448792, | |
| "eval_runtime": 0.7205, | |
| "eval_samples_per_second": 97.148, | |
| "eval_steps_per_second": 2.776, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 184.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8184635639190674, | |
| "eval_runtime": 0.656, | |
| "eval_samples_per_second": 106.712, | |
| "eval_steps_per_second": 3.049, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 185.0, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.8893, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 185.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8182028532028198, | |
| "eval_runtime": 0.6563, | |
| "eval_samples_per_second": 106.666, | |
| "eval_steps_per_second": 3.048, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 186.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8179557919502258, | |
| "eval_runtime": 0.6961, | |
| "eval_samples_per_second": 100.563, | |
| "eval_steps_per_second": 2.873, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 187.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8177469372749329, | |
| "eval_runtime": 0.6584, | |
| "eval_samples_per_second": 106.311, | |
| "eval_steps_per_second": 3.037, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 188.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8175888657569885, | |
| "eval_runtime": 0.6728, | |
| "eval_samples_per_second": 104.046, | |
| "eval_steps_per_second": 2.973, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 189.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8174628615379333, | |
| "eval_runtime": 0.661, | |
| "eval_samples_per_second": 105.894, | |
| "eval_steps_per_second": 3.026, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 190.0, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.8501, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 190.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8172903656959534, | |
| "eval_runtime": 0.6643, | |
| "eval_samples_per_second": 105.379, | |
| "eval_steps_per_second": 3.011, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 191.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8171139359474182, | |
| "eval_runtime": 0.7224, | |
| "eval_samples_per_second": 96.898, | |
| "eval_steps_per_second": 2.769, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 192.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8169858455657959, | |
| "eval_runtime": 0.6822, | |
| "eval_samples_per_second": 102.605, | |
| "eval_steps_per_second": 2.932, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 193.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8169211149215698, | |
| "eval_runtime": 0.6488, | |
| "eval_samples_per_second": 107.887, | |
| "eval_steps_per_second": 3.082, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 194.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8168790340423584, | |
| "eval_runtime": 0.8355, | |
| "eval_samples_per_second": 83.778, | |
| "eval_steps_per_second": 2.394, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 195.0, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.8611, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 195.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8168440461158752, | |
| "eval_runtime": 0.6488, | |
| "eval_samples_per_second": 107.884, | |
| "eval_steps_per_second": 3.082, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 196.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8168230056762695, | |
| "eval_runtime": 0.6602, | |
| "eval_samples_per_second": 106.026, | |
| "eval_steps_per_second": 3.029, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 197.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8167951107025146, | |
| "eval_runtime": 0.8588, | |
| "eval_samples_per_second": 81.511, | |
| "eval_steps_per_second": 2.329, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 198.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8167835474014282, | |
| "eval_runtime": 0.6762, | |
| "eval_samples_per_second": 103.513, | |
| "eval_steps_per_second": 2.958, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 199.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8167732954025269, | |
| "eval_runtime": 0.6596, | |
| "eval_samples_per_second": 106.128, | |
| "eval_steps_per_second": 3.032, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.8881, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8167622089385986, | |
| "eval_runtime": 0.844, | |
| "eval_samples_per_second": 82.939, | |
| "eval_steps_per_second": 2.37, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "step": 400, | |
| "total_flos": 2.2371640252416e+18, | |
| "train_loss": 0.9259392237663269, | |
| "train_runtime": 1042.9233, | |
| "train_samples_per_second": 86.296, | |
| "train_steps_per_second": 0.384 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 2.2371640252416e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |