| { |
| "best_metric": 0.8440366972477065, |
| "best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-528", |
| "epoch": 79.96969696969697, |
| "global_step": 640, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.97, |
| "eval_accuracy": 0.22935779816513763, |
| "eval_f1": 0.21647331951741566, |
| "eval_loss": 1.3854628801345825, |
| "eval_precision": 0.2697355008315897, |
| "eval_recall": 0.22935779816513763, |
| "eval_runtime": 6.0845, |
| "eval_samples_per_second": 17.914, |
| "eval_steps_per_second": 0.329, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.4222, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.97, |
| "eval_accuracy": 0.25688073394495414, |
| "eval_f1": 0.25434987070599063, |
| "eval_loss": 1.3791918754577637, |
| "eval_precision": 0.2807708571335123, |
| "eval_recall": 0.25688073394495414, |
| "eval_runtime": 4.2925, |
| "eval_samples_per_second": 25.393, |
| "eval_steps_per_second": 0.466, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.4183, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.97, |
| "eval_accuracy": 0.3853211009174312, |
| "eval_f1": 0.3511144563688655, |
| "eval_loss": 1.3646042346954346, |
| "eval_precision": 0.4102155235182758, |
| "eval_recall": 0.3853211009174312, |
| "eval_runtime": 4.3579, |
| "eval_samples_per_second": 25.012, |
| "eval_steps_per_second": 0.459, |
| "step": 24 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 5.625e-05, |
| "loss": 1.4097, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.97, |
| "eval_accuracy": 0.41284403669724773, |
| "eval_f1": 0.32452248836490605, |
| "eval_loss": 1.3562716245651245, |
| "eval_precision": 0.5062447369587377, |
| "eval_recall": 0.41284403669724773, |
| "eval_runtime": 4.3612, |
| "eval_samples_per_second": 24.993, |
| "eval_steps_per_second": 0.459, |
| "step": 32 |
| }, |
| { |
| "epoch": 4.97, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 1.3944, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.97, |
| "eval_accuracy": 0.4036697247706422, |
| "eval_f1": 0.293905028882093, |
| "eval_loss": 1.3461558818817139, |
| "eval_precision": 0.3927443217900042, |
| "eval_recall": 0.4036697247706422, |
| "eval_runtime": 4.4159, |
| "eval_samples_per_second": 24.684, |
| "eval_steps_per_second": 0.453, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.97, |
| "eval_accuracy": 0.4036697247706422, |
| "eval_f1": 0.2840541721275666, |
| "eval_loss": 1.322252631187439, |
| "eval_precision": 0.5152005756431013, |
| "eval_recall": 0.4036697247706422, |
| "eval_runtime": 4.2725, |
| "eval_samples_per_second": 25.512, |
| "eval_steps_per_second": 0.468, |
| "step": 48 |
| }, |
| { |
| "epoch": 6.24, |
| "learning_rate": 9.375e-05, |
| "loss": 1.411, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.97, |
| "eval_accuracy": 0.41284403669724773, |
| "eval_f1": 0.29851761513413444, |
| "eval_loss": 1.304025411605835, |
| "eval_precision": 0.44039013993142434, |
| "eval_recall": 0.41284403669724773, |
| "eval_runtime": 4.4737, |
| "eval_samples_per_second": 24.365, |
| "eval_steps_per_second": 0.447, |
| "step": 56 |
| }, |
| { |
| "epoch": 7.48, |
| "learning_rate": 0.0001125, |
| "loss": 1.346, |
| "step": 60 |
| }, |
| { |
| "epoch": 7.97, |
| "eval_accuracy": 0.4954128440366973, |
| "eval_f1": 0.4092687533729088, |
| "eval_loss": 1.2699785232543945, |
| "eval_precision": 0.49603902723168775, |
| "eval_recall": 0.4954128440366973, |
| "eval_runtime": 4.5079, |
| "eval_samples_per_second": 24.18, |
| "eval_steps_per_second": 0.444, |
| "step": 64 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 0.00011875000000000001, |
| "loss": 1.3031, |
| "step": 70 |
| }, |
| { |
| "epoch": 8.97, |
| "eval_accuracy": 0.5596330275229358, |
| "eval_f1": 0.46723852012270245, |
| "eval_loss": 1.2149937152862549, |
| "eval_precision": 0.5440134711415631, |
| "eval_recall": 0.5596330275229358, |
| "eval_runtime": 4.3712, |
| "eval_samples_per_second": 24.936, |
| "eval_steps_per_second": 0.458, |
| "step": 72 |
| }, |
| { |
| "epoch": 9.97, |
| "learning_rate": 0.00011666666666666667, |
| "loss": 1.2371, |
| "step": 80 |
| }, |
| { |
| "epoch": 9.97, |
| "eval_accuracy": 0.5963302752293578, |
| "eval_f1": 0.5100508405791544, |
| "eval_loss": 1.1580270528793335, |
| "eval_precision": 0.5659333353788879, |
| "eval_recall": 0.5963302752293578, |
| "eval_runtime": 4.2133, |
| "eval_samples_per_second": 25.87, |
| "eval_steps_per_second": 0.475, |
| "step": 80 |
| }, |
| { |
| "epoch": 10.97, |
| "eval_accuracy": 0.6055045871559633, |
| "eval_f1": 0.5211004609031267, |
| "eval_loss": 1.066982388496399, |
| "eval_precision": 0.7279186904119446, |
| "eval_recall": 0.6055045871559633, |
| "eval_runtime": 14.5277, |
| "eval_samples_per_second": 7.503, |
| "eval_steps_per_second": 0.138, |
| "step": 88 |
| }, |
| { |
| "epoch": 11.24, |
| "learning_rate": 0.00011458333333333334, |
| "loss": 1.1736, |
| "step": 90 |
| }, |
| { |
| "epoch": 11.97, |
| "eval_accuracy": 0.6605504587155964, |
| "eval_f1": 0.5771675777046106, |
| "eval_loss": 0.9855989813804626, |
| "eval_precision": 0.5536726213674042, |
| "eval_recall": 0.6605504587155964, |
| "eval_runtime": 4.2828, |
| "eval_samples_per_second": 25.451, |
| "eval_steps_per_second": 0.467, |
| "step": 96 |
| }, |
| { |
| "epoch": 12.48, |
| "learning_rate": 0.0001125, |
| "loss": 1.0457, |
| "step": 100 |
| }, |
| { |
| "epoch": 12.97, |
| "eval_accuracy": 0.6697247706422018, |
| "eval_f1": 0.5964926350313968, |
| "eval_loss": 0.896264374256134, |
| "eval_precision": 0.763141515721791, |
| "eval_recall": 0.6697247706422018, |
| "eval_runtime": 4.2315, |
| "eval_samples_per_second": 25.759, |
| "eval_steps_per_second": 0.473, |
| "step": 104 |
| }, |
| { |
| "epoch": 13.73, |
| "learning_rate": 0.00011041666666666666, |
| "loss": 0.953, |
| "step": 110 |
| }, |
| { |
| "epoch": 13.97, |
| "eval_accuracy": 0.6697247706422018, |
| "eval_f1": 0.6081464096911078, |
| "eval_loss": 0.8546512722969055, |
| "eval_precision": 0.6884856947005512, |
| "eval_recall": 0.6697247706422018, |
| "eval_runtime": 4.4534, |
| "eval_samples_per_second": 24.476, |
| "eval_steps_per_second": 0.449, |
| "step": 112 |
| }, |
| { |
| "epoch": 14.97, |
| "learning_rate": 0.00010833333333333334, |
| "loss": 0.8579, |
| "step": 120 |
| }, |
| { |
| "epoch": 14.97, |
| "eval_accuracy": 0.7155963302752294, |
| "eval_f1": 0.6643295304342026, |
| "eval_loss": 0.7848823070526123, |
| "eval_precision": 0.7396182317656428, |
| "eval_recall": 0.7155963302752294, |
| "eval_runtime": 4.1662, |
| "eval_samples_per_second": 26.163, |
| "eval_steps_per_second": 0.48, |
| "step": 120 |
| }, |
| { |
| "epoch": 15.97, |
| "eval_accuracy": 0.7431192660550459, |
| "eval_f1": 0.711852075310986, |
| "eval_loss": 0.7563745379447937, |
| "eval_precision": 0.7371817784661822, |
| "eval_recall": 0.7431192660550459, |
| "eval_runtime": 4.2674, |
| "eval_samples_per_second": 25.542, |
| "eval_steps_per_second": 0.469, |
| "step": 128 |
| }, |
| { |
| "epoch": 16.24, |
| "learning_rate": 0.00010625, |
| "loss": 0.8167, |
| "step": 130 |
| }, |
| { |
| "epoch": 16.97, |
| "eval_accuracy": 0.7614678899082569, |
| "eval_f1": 0.7210716889645992, |
| "eval_loss": 0.7132583260536194, |
| "eval_precision": 0.7506553079947577, |
| "eval_recall": 0.7614678899082569, |
| "eval_runtime": 4.1418, |
| "eval_samples_per_second": 26.317, |
| "eval_steps_per_second": 0.483, |
| "step": 136 |
| }, |
| { |
| "epoch": 17.48, |
| "learning_rate": 0.00010416666666666667, |
| "loss": 0.7273, |
| "step": 140 |
| }, |
| { |
| "epoch": 17.97, |
| "eval_accuracy": 0.7522935779816514, |
| "eval_f1": 0.7202155642522615, |
| "eval_loss": 0.6887747645378113, |
| "eval_precision": 0.7378685592291271, |
| "eval_recall": 0.7522935779816514, |
| "eval_runtime": 4.5118, |
| "eval_samples_per_second": 24.159, |
| "eval_steps_per_second": 0.443, |
| "step": 144 |
| }, |
| { |
| "epoch": 18.73, |
| "learning_rate": 0.00010208333333333334, |
| "loss": 0.6547, |
| "step": 150 |
| }, |
| { |
| "epoch": 18.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7576525411387797, |
| "eval_loss": 0.659186065196991, |
| "eval_precision": 0.7772903701802784, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.3816, |
| "eval_samples_per_second": 24.877, |
| "eval_steps_per_second": 0.456, |
| "step": 152 |
| }, |
| { |
| "epoch": 19.97, |
| "learning_rate": 0.0001, |
| "loss": 0.5963, |
| "step": 160 |
| }, |
| { |
| "epoch": 19.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7550663564666461, |
| "eval_loss": 0.6136144399642944, |
| "eval_precision": 0.764159781184113, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.2561, |
| "eval_samples_per_second": 25.61, |
| "eval_steps_per_second": 0.47, |
| "step": 160 |
| }, |
| { |
| "epoch": 20.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7786916064255194, |
| "eval_loss": 0.5723462700843811, |
| "eval_precision": 0.7801645588430826, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 5.2546, |
| "eval_samples_per_second": 20.744, |
| "eval_steps_per_second": 0.381, |
| "step": 168 |
| }, |
| { |
| "epoch": 21.24, |
| "learning_rate": 9.791666666666667e-05, |
| "loss": 0.551, |
| "step": 170 |
| }, |
| { |
| "epoch": 21.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7780894219567608, |
| "eval_loss": 0.5686229467391968, |
| "eval_precision": 0.776092121476891, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.3144, |
| "eval_samples_per_second": 25.264, |
| "eval_steps_per_second": 0.464, |
| "step": 176 |
| }, |
| { |
| "epoch": 22.48, |
| "learning_rate": 9.583333333333334e-05, |
| "loss": 0.4929, |
| "step": 180 |
| }, |
| { |
| "epoch": 22.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7651464296127533, |
| "eval_loss": 0.5596823692321777, |
| "eval_precision": 0.7649127896435436, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.4326, |
| "eval_samples_per_second": 24.59, |
| "eval_steps_per_second": 0.451, |
| "step": 184 |
| }, |
| { |
| "epoch": 23.73, |
| "learning_rate": 9.375e-05, |
| "loss": 0.4309, |
| "step": 190 |
| }, |
| { |
| "epoch": 23.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.781022184850044, |
| "eval_loss": 0.5233965516090393, |
| "eval_precision": 0.7774110647118855, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.3167, |
| "eval_samples_per_second": 25.251, |
| "eval_steps_per_second": 0.463, |
| "step": 192 |
| }, |
| { |
| "epoch": 24.97, |
| "learning_rate": 9.166666666666667e-05, |
| "loss": 0.3945, |
| "step": 200 |
| }, |
| { |
| "epoch": 24.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7812909567496724, |
| "eval_loss": 0.5007840991020203, |
| "eval_precision": 0.7836723839914905, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.3513, |
| "eval_samples_per_second": 25.05, |
| "eval_steps_per_second": 0.46, |
| "step": 200 |
| }, |
| { |
| "epoch": 25.97, |
| "eval_accuracy": 0.7522935779816514, |
| "eval_f1": 0.7528893125223401, |
| "eval_loss": 0.5289302468299866, |
| "eval_precision": 0.7537344154316632, |
| "eval_recall": 0.7522935779816514, |
| "eval_runtime": 4.3647, |
| "eval_samples_per_second": 24.973, |
| "eval_steps_per_second": 0.458, |
| "step": 208 |
| }, |
| { |
| "epoch": 26.24, |
| "learning_rate": 8.958333333333333e-05, |
| "loss": 0.3704, |
| "step": 210 |
| }, |
| { |
| "epoch": 26.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7962706746091569, |
| "eval_loss": 0.4399118423461914, |
| "eval_precision": 0.7957732392169626, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.2147, |
| "eval_samples_per_second": 25.862, |
| "eval_steps_per_second": 0.475, |
| "step": 216 |
| }, |
| { |
| "epoch": 27.48, |
| "learning_rate": 8.75e-05, |
| "loss": 0.3267, |
| "step": 220 |
| }, |
| { |
| "epoch": 27.97, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_f1": 0.8005365278178692, |
| "eval_loss": 0.4539415240287781, |
| "eval_precision": 0.7983420088683247, |
| "eval_recall": 0.8073394495412844, |
| "eval_runtime": 4.2272, |
| "eval_samples_per_second": 25.785, |
| "eval_steps_per_second": 0.473, |
| "step": 224 |
| }, |
| { |
| "epoch": 28.73, |
| "learning_rate": 8.541666666666668e-05, |
| "loss": 0.2966, |
| "step": 230 |
| }, |
| { |
| "epoch": 28.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7837137974455839, |
| "eval_loss": 0.4734969735145569, |
| "eval_precision": 0.789241175758926, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.2368, |
| "eval_samples_per_second": 25.727, |
| "eval_steps_per_second": 0.472, |
| "step": 232 |
| }, |
| { |
| "epoch": 29.97, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 0.2645, |
| "step": 240 |
| }, |
| { |
| "epoch": 29.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7706422018348624, |
| "eval_loss": 0.4594463109970093, |
| "eval_precision": 0.7706422018348624, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.3943, |
| "eval_samples_per_second": 24.805, |
| "eval_steps_per_second": 0.455, |
| "step": 240 |
| }, |
| { |
| "epoch": 30.97, |
| "eval_accuracy": 0.7522935779816514, |
| "eval_f1": 0.7533140030125614, |
| "eval_loss": 0.4698648750782013, |
| "eval_precision": 0.7554437319096274, |
| "eval_recall": 0.7522935779816514, |
| "eval_runtime": 4.1296, |
| "eval_samples_per_second": 26.394, |
| "eval_steps_per_second": 0.484, |
| "step": 248 |
| }, |
| { |
| "epoch": 31.24, |
| "learning_rate": 8.125000000000001e-05, |
| "loss": 0.2527, |
| "step": 250 |
| }, |
| { |
| "epoch": 31.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7856523955147808, |
| "eval_loss": 0.45513755083084106, |
| "eval_precision": 0.785609816323817, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.1348, |
| "eval_samples_per_second": 26.361, |
| "eval_steps_per_second": 0.484, |
| "step": 256 |
| }, |
| { |
| "epoch": 32.48, |
| "learning_rate": 7.916666666666666e-05, |
| "loss": 0.2202, |
| "step": 260 |
| }, |
| { |
| "epoch": 32.97, |
| "eval_accuracy": 0.8165137614678899, |
| "eval_f1": 0.8170336224601304, |
| "eval_loss": 0.4457748532295227, |
| "eval_precision": 0.8197900424266599, |
| "eval_recall": 0.8165137614678899, |
| "eval_runtime": 5.1689, |
| "eval_samples_per_second": 21.087, |
| "eval_steps_per_second": 0.387, |
| "step": 264 |
| }, |
| { |
| "epoch": 33.73, |
| "learning_rate": 7.708333333333334e-05, |
| "loss": 0.2006, |
| "step": 270 |
| }, |
| { |
| "epoch": 33.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7850412357933325, |
| "eval_loss": 0.46321260929107666, |
| "eval_precision": 0.7940749153601442, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.2326, |
| "eval_samples_per_second": 25.752, |
| "eval_steps_per_second": 0.473, |
| "step": 272 |
| }, |
| { |
| "epoch": 34.97, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.1589, |
| "step": 280 |
| }, |
| { |
| "epoch": 34.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7925041274199247, |
| "eval_loss": 0.46511203050613403, |
| "eval_precision": 0.7993275970140749, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.1566, |
| "eval_samples_per_second": 26.223, |
| "eval_steps_per_second": 0.481, |
| "step": 280 |
| }, |
| { |
| "epoch": 35.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7803733958918072, |
| "eval_loss": 0.45948973298072815, |
| "eval_precision": 0.7823930357635982, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.3202, |
| "eval_samples_per_second": 25.23, |
| "eval_steps_per_second": 0.463, |
| "step": 288 |
| }, |
| { |
| "epoch": 36.24, |
| "learning_rate": 7.291666666666666e-05, |
| "loss": 0.153, |
| "step": 290 |
| }, |
| { |
| "epoch": 36.97, |
| "eval_accuracy": 0.7614678899082569, |
| "eval_f1": 0.7632546001327497, |
| "eval_loss": 0.458363801240921, |
| "eval_precision": 0.7690950187958565, |
| "eval_recall": 0.7614678899082569, |
| "eval_runtime": 4.4275, |
| "eval_samples_per_second": 24.619, |
| "eval_steps_per_second": 0.452, |
| "step": 296 |
| }, |
| { |
| "epoch": 37.48, |
| "learning_rate": 7.083333333333334e-05, |
| "loss": 0.1427, |
| "step": 300 |
| }, |
| { |
| "epoch": 37.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7796360891921739, |
| "eval_loss": 0.46078726649284363, |
| "eval_precision": 0.782995656118911, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.4461, |
| "eval_samples_per_second": 24.516, |
| "eval_steps_per_second": 0.45, |
| "step": 304 |
| }, |
| { |
| "epoch": 38.73, |
| "learning_rate": 6.874999999999999e-05, |
| "loss": 0.113, |
| "step": 310 |
| }, |
| { |
| "epoch": 38.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7898954921921011, |
| "eval_loss": 0.45713570713996887, |
| "eval_precision": 0.7922270390160299, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.3087, |
| "eval_samples_per_second": 25.297, |
| "eval_steps_per_second": 0.464, |
| "step": 312 |
| }, |
| { |
| "epoch": 39.97, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.1146, |
| "step": 320 |
| }, |
| { |
| "epoch": 39.97, |
| "eval_accuracy": 0.7614678899082569, |
| "eval_f1": 0.7612891030218949, |
| "eval_loss": 0.5269873142242432, |
| "eval_precision": 0.765128347697155, |
| "eval_recall": 0.7614678899082569, |
| "eval_runtime": 4.2908, |
| "eval_samples_per_second": 25.403, |
| "eval_steps_per_second": 0.466, |
| "step": 320 |
| }, |
| { |
| "epoch": 40.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7709516996486127, |
| "eval_loss": 0.48878130316734314, |
| "eval_precision": 0.7781771515945828, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.3303, |
| "eval_samples_per_second": 25.171, |
| "eval_steps_per_second": 0.462, |
| "step": 328 |
| }, |
| { |
| "epoch": 41.24, |
| "learning_rate": 6.458333333333334e-05, |
| "loss": 0.1275, |
| "step": 330 |
| }, |
| { |
| "epoch": 41.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7836706749228535, |
| "eval_loss": 0.4523099958896637, |
| "eval_precision": 0.780905883107718, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.2033, |
| "eval_samples_per_second": 25.932, |
| "eval_steps_per_second": 0.476, |
| "step": 336 |
| }, |
| { |
| "epoch": 42.48, |
| "learning_rate": 6.25e-05, |
| "loss": 0.0959, |
| "step": 340 |
| }, |
| { |
| "epoch": 42.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7767063396275014, |
| "eval_loss": 0.46965503692626953, |
| "eval_precision": 0.7753268138589239, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.3242, |
| "eval_samples_per_second": 25.207, |
| "eval_steps_per_second": 0.463, |
| "step": 344 |
| }, |
| { |
| "epoch": 43.73, |
| "learning_rate": 6.041666666666667e-05, |
| "loss": 0.0882, |
| "step": 350 |
| }, |
| { |
| "epoch": 43.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7685729724992435, |
| "eval_loss": 0.4286104738712311, |
| "eval_precision": 0.7685932721712537, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.4175, |
| "eval_samples_per_second": 24.675, |
| "eval_steps_per_second": 0.453, |
| "step": 352 |
| }, |
| { |
| "epoch": 44.97, |
| "learning_rate": 5.833333333333333e-05, |
| "loss": 0.0847, |
| "step": 360 |
| }, |
| { |
| "epoch": 44.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7925041274199247, |
| "eval_loss": 0.5317460298538208, |
| "eval_precision": 0.7993275970140749, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 6.0042, |
| "eval_samples_per_second": 18.154, |
| "eval_steps_per_second": 0.333, |
| "step": 360 |
| }, |
| { |
| "epoch": 45.97, |
| "eval_accuracy": 0.7614678899082569, |
| "eval_f1": 0.7646893115457605, |
| "eval_loss": 0.5431071519851685, |
| "eval_precision": 0.7699552364490537, |
| "eval_recall": 0.7614678899082569, |
| "eval_runtime": 4.3547, |
| "eval_samples_per_second": 25.03, |
| "eval_steps_per_second": 0.459, |
| "step": 368 |
| }, |
| { |
| "epoch": 46.24, |
| "learning_rate": 5.625e-05, |
| "loss": 0.0813, |
| "step": 370 |
| }, |
| { |
| "epoch": 46.97, |
| "eval_accuracy": 0.8256880733944955, |
| "eval_f1": 0.8284158367266842, |
| "eval_loss": 0.44316479563713074, |
| "eval_precision": 0.843538901662607, |
| "eval_recall": 0.8256880733944955, |
| "eval_runtime": 4.2714, |
| "eval_samples_per_second": 25.519, |
| "eval_steps_per_second": 0.468, |
| "step": 376 |
| }, |
| { |
| "epoch": 47.48, |
| "learning_rate": 5.416666666666667e-05, |
| "loss": 0.0768, |
| "step": 380 |
| }, |
| { |
| "epoch": 47.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7955546490941502, |
| "eval_loss": 0.4885597229003906, |
| "eval_precision": 0.8005162605636117, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.2576, |
| "eval_samples_per_second": 25.602, |
| "eval_steps_per_second": 0.47, |
| "step": 384 |
| }, |
| { |
| "epoch": 48.73, |
| "learning_rate": 5.208333333333334e-05, |
| "loss": 0.0627, |
| "step": 390 |
| }, |
| { |
| "epoch": 48.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.8009727230444837, |
| "eval_loss": 0.5372528433799744, |
| "eval_precision": 0.8071912929511652, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.3763, |
| "eval_samples_per_second": 24.907, |
| "eval_steps_per_second": 0.457, |
| "step": 392 |
| }, |
| { |
| "epoch": 49.97, |
| "learning_rate": 5e-05, |
| "loss": 0.0688, |
| "step": 400 |
| }, |
| { |
| "epoch": 49.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7822443312570955, |
| "eval_loss": 0.5896694660186768, |
| "eval_precision": 0.789232725399693, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.3692, |
| "eval_samples_per_second": 24.947, |
| "eval_steps_per_second": 0.458, |
| "step": 400 |
| }, |
| { |
| "epoch": 50.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7992371326578404, |
| "eval_loss": 0.5114642977714539, |
| "eval_precision": 0.8014849021031709, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.3028, |
| "eval_samples_per_second": 25.332, |
| "eval_steps_per_second": 0.465, |
| "step": 408 |
| }, |
| { |
| "epoch": 51.24, |
| "learning_rate": 4.791666666666667e-05, |
| "loss": 0.0676, |
| "step": 410 |
| }, |
| { |
| "epoch": 51.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7977993643940755, |
| "eval_loss": 0.4881470799446106, |
| "eval_precision": 0.7998301588132414, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.3212, |
| "eval_samples_per_second": 25.224, |
| "eval_steps_per_second": 0.463, |
| "step": 416 |
| }, |
| { |
| "epoch": 52.48, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 0.0539, |
| "step": 420 |
| }, |
| { |
| "epoch": 52.97, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_f1": 0.807691055721277, |
| "eval_loss": 0.4819609224796295, |
| "eval_precision": 0.8138503399273244, |
| "eval_recall": 0.8073394495412844, |
| "eval_runtime": 4.3125, |
| "eval_samples_per_second": 25.276, |
| "eval_steps_per_second": 0.464, |
| "step": 424 |
| }, |
| { |
| "epoch": 53.73, |
| "learning_rate": 4.375e-05, |
| "loss": 0.0596, |
| "step": 430 |
| }, |
| { |
| "epoch": 53.97, |
| "eval_accuracy": 0.8256880733944955, |
| "eval_f1": 0.8244465797713664, |
| "eval_loss": 0.4449571669101715, |
| "eval_precision": 0.8245908379614004, |
| "eval_recall": 0.8256880733944955, |
| "eval_runtime": 5.8195, |
| "eval_samples_per_second": 18.73, |
| "eval_steps_per_second": 0.344, |
| "step": 432 |
| }, |
| { |
| "epoch": 54.97, |
| "learning_rate": 4.1666666666666665e-05, |
| "loss": 0.0611, |
| "step": 440 |
| }, |
| { |
| "epoch": 54.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7924465793472197, |
| "eval_loss": 0.5057494044303894, |
| "eval_precision": 0.8008019735410222, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.6616, |
| "eval_samples_per_second": 23.383, |
| "eval_steps_per_second": 0.429, |
| "step": 440 |
| }, |
| { |
| "epoch": 55.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.8008031371900772, |
| "eval_loss": 0.4918478727340698, |
| "eval_precision": 0.8056331161636306, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.8639, |
| "eval_samples_per_second": 22.41, |
| "eval_steps_per_second": 0.411, |
| "step": 448 |
| }, |
| { |
| "epoch": 56.24, |
| "learning_rate": 3.958333333333333e-05, |
| "loss": 0.0643, |
| "step": 450 |
| }, |
| { |
| "epoch": 56.97, |
| "eval_accuracy": 0.7522935779816514, |
| "eval_f1": 0.7545272459450874, |
| "eval_loss": 0.5946044325828552, |
| "eval_precision": 0.7587394976605187, |
| "eval_recall": 0.7522935779816514, |
| "eval_runtime": 4.4153, |
| "eval_samples_per_second": 24.687, |
| "eval_steps_per_second": 0.453, |
| "step": 456 |
| }, |
| { |
| "epoch": 57.48, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.0605, |
| "step": 460 |
| }, |
| { |
| "epoch": 57.97, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_f1": 0.8120936083458042, |
| "eval_loss": 0.4887966513633728, |
| "eval_precision": 0.8238645162528876, |
| "eval_recall": 0.8073394495412844, |
| "eval_runtime": 6.6734, |
| "eval_samples_per_second": 16.334, |
| "eval_steps_per_second": 0.3, |
| "step": 464 |
| }, |
| { |
| "epoch": 58.73, |
| "learning_rate": 3.541666666666667e-05, |
| "loss": 0.063, |
| "step": 470 |
| }, |
| { |
| "epoch": 58.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7936673558168583, |
| "eval_loss": 0.5916518568992615, |
| "eval_precision": 0.8051419661311963, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.2726, |
| "eval_samples_per_second": 25.511, |
| "eval_steps_per_second": 0.468, |
| "step": 472 |
| }, |
| { |
| "epoch": 59.97, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0595, |
| "step": 480 |
| }, |
| { |
| "epoch": 59.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7894285298217145, |
| "eval_loss": 0.5117025375366211, |
| "eval_precision": 0.7904302906815871, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.4288, |
| "eval_samples_per_second": 24.612, |
| "eval_steps_per_second": 0.452, |
| "step": 480 |
| }, |
| { |
| "epoch": 60.97, |
| "eval_accuracy": 0.7614678899082569, |
| "eval_f1": 0.7635438011331693, |
| "eval_loss": 0.549720048904419, |
| "eval_precision": 0.769159484755815, |
| "eval_recall": 0.7614678899082569, |
| "eval_runtime": 4.2635, |
| "eval_samples_per_second": 25.566, |
| "eval_steps_per_second": 0.469, |
| "step": 488 |
| }, |
| { |
| "epoch": 61.24, |
| "learning_rate": 3.125e-05, |
| "loss": 0.0554, |
| "step": 490 |
| }, |
| { |
| "epoch": 61.97, |
| "eval_accuracy": 0.8165137614678899, |
| "eval_f1": 0.812552773801982, |
| "eval_loss": 0.4742366075515747, |
| "eval_precision": 0.8100926678908328, |
| "eval_recall": 0.8165137614678899, |
| "eval_runtime": 4.3801, |
| "eval_samples_per_second": 24.885, |
| "eval_steps_per_second": 0.457, |
| "step": 496 |
| }, |
| { |
| "epoch": 62.48, |
| "learning_rate": 2.9166666666666666e-05, |
| "loss": 0.0557, |
| "step": 500 |
| }, |
| { |
| "epoch": 62.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7886246853481453, |
| "eval_loss": 0.5369319915771484, |
| "eval_precision": 0.7886251828214332, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.4776, |
| "eval_samples_per_second": 24.343, |
| "eval_steps_per_second": 0.447, |
| "step": 504 |
| }, |
| { |
| "epoch": 63.73, |
| "learning_rate": 2.7083333333333335e-05, |
| "loss": 0.0539, |
| "step": 510 |
| }, |
| { |
| "epoch": 63.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7898954921921011, |
| "eval_loss": 0.5439756512641907, |
| "eval_precision": 0.7922270390160299, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.4228, |
| "eval_samples_per_second": 24.645, |
| "eval_steps_per_second": 0.452, |
| "step": 512 |
| }, |
| { |
| "epoch": 64.97, |
| "learning_rate": 2.5e-05, |
| "loss": 0.048, |
| "step": 520 |
| }, |
| { |
| "epoch": 64.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7882784673502429, |
| "eval_loss": 0.5923751592636108, |
| "eval_precision": 0.7878178107535906, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 5.5392, |
| "eval_samples_per_second": 19.678, |
| "eval_steps_per_second": 0.361, |
| "step": 520 |
| }, |
| { |
| "epoch": 65.97, |
| "eval_accuracy": 0.8440366972477065, |
| "eval_f1": 0.8440366972477065, |
| "eval_loss": 0.486260324716568, |
| "eval_precision": 0.8440366972477065, |
| "eval_recall": 0.8440366972477065, |
| "eval_runtime": 4.2084, |
| "eval_samples_per_second": 25.9, |
| "eval_steps_per_second": 0.475, |
| "step": 528 |
| }, |
| { |
| "epoch": 66.24, |
| "learning_rate": 2.2916666666666667e-05, |
| "loss": 0.045, |
| "step": 530 |
| }, |
| { |
| "epoch": 66.97, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_f1": 0.8046694749207712, |
| "eval_loss": 0.5849686861038208, |
| "eval_precision": 0.8076432996157767, |
| "eval_recall": 0.8073394495412844, |
| "eval_runtime": 4.3405, |
| "eval_samples_per_second": 25.112, |
| "eval_steps_per_second": 0.461, |
| "step": 536 |
| }, |
| { |
| "epoch": 67.48, |
| "learning_rate": 2.0833333333333333e-05, |
| "loss": 0.047, |
| "step": 540 |
| }, |
| { |
| "epoch": 67.97, |
| "eval_accuracy": 0.8256880733944955, |
| "eval_f1": 0.8227139701424718, |
| "eval_loss": 0.4938836991786957, |
| "eval_precision": 0.8211639886949021, |
| "eval_recall": 0.8256880733944955, |
| "eval_runtime": 4.2943, |
| "eval_samples_per_second": 25.382, |
| "eval_steps_per_second": 0.466, |
| "step": 544 |
| }, |
| { |
| "epoch": 68.73, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 0.0412, |
| "step": 550 |
| }, |
| { |
| "epoch": 68.97, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_f1": 0.7899819010172877, |
| "eval_loss": 0.4850451946258545, |
| "eval_precision": 0.7911629060252914, |
| "eval_recall": 0.7889908256880734, |
| "eval_runtime": 4.3733, |
| "eval_samples_per_second": 24.924, |
| "eval_steps_per_second": 0.457, |
| "step": 552 |
| }, |
| { |
| "epoch": 69.97, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0392, |
| "step": 560 |
| }, |
| { |
| "epoch": 69.97, |
| "eval_accuracy": 0.8256880733944955, |
| "eval_f1": 0.8257529642156887, |
| "eval_loss": 0.5065794587135315, |
| "eval_precision": 0.8264957264957264, |
| "eval_recall": 0.8256880733944955, |
| "eval_runtime": 4.2901, |
| "eval_samples_per_second": 25.407, |
| "eval_steps_per_second": 0.466, |
| "step": 560 |
| }, |
| { |
| "epoch": 70.97, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_f1": 0.8058135764557783, |
| "eval_loss": 0.49649733304977417, |
| "eval_precision": 0.8053007135575942, |
| "eval_recall": 0.8073394495412844, |
| "eval_runtime": 4.1424, |
| "eval_samples_per_second": 26.313, |
| "eval_steps_per_second": 0.483, |
| "step": 568 |
| }, |
| { |
| "epoch": 71.24, |
| "learning_rate": 1.4583333333333333e-05, |
| "loss": 0.0423, |
| "step": 570 |
| }, |
| { |
| "epoch": 71.97, |
| "eval_accuracy": 0.8348623853211009, |
| "eval_f1": 0.8350885030999028, |
| "eval_loss": 0.47168704867362976, |
| "eval_precision": 0.8376424034680915, |
| "eval_recall": 0.8348623853211009, |
| "eval_runtime": 4.1897, |
| "eval_samples_per_second": 26.016, |
| "eval_steps_per_second": 0.477, |
| "step": 576 |
| }, |
| { |
| "epoch": 72.48, |
| "learning_rate": 1.25e-05, |
| "loss": 0.0471, |
| "step": 580 |
| }, |
| { |
| "epoch": 72.97, |
| "eval_accuracy": 0.8256880733944955, |
| "eval_f1": 0.8295520158325865, |
| "eval_loss": 0.48450949788093567, |
| "eval_precision": 0.837811160528748, |
| "eval_recall": 0.8256880733944955, |
| "eval_runtime": 4.2446, |
| "eval_samples_per_second": 25.68, |
| "eval_steps_per_second": 0.471, |
| "step": 584 |
| }, |
| { |
| "epoch": 73.73, |
| "learning_rate": 1.0416666666666666e-05, |
| "loss": 0.0322, |
| "step": 590 |
| }, |
| { |
| "epoch": 73.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7692886041532689, |
| "eval_loss": 0.5188109278678894, |
| "eval_precision": 0.7689271840647987, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.4833, |
| "eval_samples_per_second": 24.313, |
| "eval_steps_per_second": 0.446, |
| "step": 592 |
| }, |
| { |
| "epoch": 74.97, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.042, |
| "step": 600 |
| }, |
| { |
| "epoch": 74.97, |
| "eval_accuracy": 0.7706422018348624, |
| "eval_f1": 0.7700888306392893, |
| "eval_loss": 0.5242283940315247, |
| "eval_precision": 0.7698942959712803, |
| "eval_recall": 0.7706422018348624, |
| "eval_runtime": 4.4923, |
| "eval_samples_per_second": 24.264, |
| "eval_steps_per_second": 0.445, |
| "step": 600 |
| }, |
| { |
| "epoch": 75.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7803733958918072, |
| "eval_loss": 0.5945499539375305, |
| "eval_precision": 0.7823930357635982, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 5.1633, |
| "eval_samples_per_second": 21.111, |
| "eval_steps_per_second": 0.387, |
| "step": 608 |
| }, |
| { |
| "epoch": 76.24, |
| "learning_rate": 6.25e-06, |
| "loss": 0.0416, |
| "step": 610 |
| }, |
| { |
| "epoch": 76.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7993445642022374, |
| "eval_loss": 0.5432426929473877, |
| "eval_precision": 0.8038185145085823, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.2234, |
| "eval_samples_per_second": 25.809, |
| "eval_steps_per_second": 0.474, |
| "step": 616 |
| }, |
| { |
| "epoch": 77.48, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 0.0399, |
| "step": 620 |
| }, |
| { |
| "epoch": 77.97, |
| "eval_accuracy": 0.7981651376146789, |
| "eval_f1": 0.7994120087594209, |
| "eval_loss": 0.5381362438201904, |
| "eval_precision": 0.8072242548450546, |
| "eval_recall": 0.7981651376146789, |
| "eval_runtime": 4.2152, |
| "eval_samples_per_second": 25.859, |
| "eval_steps_per_second": 0.474, |
| "step": 624 |
| }, |
| { |
| "epoch": 78.73, |
| "learning_rate": 2.0833333333333334e-06, |
| "loss": 0.0439, |
| "step": 630 |
| }, |
| { |
| "epoch": 78.97, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_f1": 0.7827462243679189, |
| "eval_loss": 0.6181262135505676, |
| "eval_precision": 0.7877941763063422, |
| "eval_recall": 0.7798165137614679, |
| "eval_runtime": 4.2424, |
| "eval_samples_per_second": 25.693, |
| "eval_steps_per_second": 0.471, |
| "step": 632 |
| }, |
| { |
| "epoch": 79.97, |
| "learning_rate": 0.0, |
| "loss": 0.0462, |
| "step": 640 |
| }, |
| { |
| "epoch": 79.97, |
| "eval_accuracy": 0.8165137614678899, |
| "eval_f1": 0.8172526992448356, |
| "eval_loss": 0.48008766770362854, |
| "eval_precision": 0.8181998512273742, |
| "eval_recall": 0.8165137614678899, |
| "eval_runtime": 4.18, |
| "eval_samples_per_second": 26.076, |
| "eval_steps_per_second": 0.478, |
| "step": 640 |
| }, |
| { |
| "epoch": 79.97, |
| "step": 640, |
| "total_flos": 3.5167284631649157e+18, |
| "train_loss": 0.37728101573884487, |
| "train_runtime": 2345.4183, |
| "train_samples_per_second": 70.606, |
| "train_steps_per_second": 0.273 |
| } |
| ], |
| "max_steps": 640, |
| "num_train_epochs": 80, |
| "total_flos": 3.5167284631649157e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
