| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 1750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9971428571428576e-05, | |
| "loss": 3.1194, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9e-05, | |
| "loss": 3.222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6869668960571289, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 240.1814, | |
| "eval_samples_per_second": 12.491, | |
| "eval_steps_per_second": 1.561, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.7052, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.0, | |
| "eval_loss": 2.0989105701446533, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 240.275, | |
| "eval_samples_per_second": 12.486, | |
| "eval_steps_per_second": 1.561, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.4622, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.706234872341156, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 240.4103, | |
| "eval_samples_per_second": 12.479, | |
| "eval_steps_per_second": 1.56, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.9345, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.514, | |
| "eval_f1": 0.6729475100942127, | |
| "eval_loss": 0.7361006140708923, | |
| "eval_precision": 0.5070993914807302, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 240.3366, | |
| "eval_samples_per_second": 12.482, | |
| "eval_steps_per_second": 1.56, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.3471, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.5063333333333333, | |
| "eval_f1": 0.6693458361241348, | |
| "eval_loss": 0.7378450632095337, | |
| "eval_precision": 0.5031889895938234, | |
| "eval_recall": 0.9993333333333333, | |
| "eval_runtime": 240.3903, | |
| "eval_samples_per_second": 12.48, | |
| "eval_steps_per_second": 1.56, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.0776, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.502, | |
| "eval_f1": 0.6675567423230975, | |
| "eval_loss": 1.2094249725341797, | |
| "eval_precision": 0.501002004008016, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 241.2524, | |
| "eval_samples_per_second": 12.435, | |
| "eval_steps_per_second": 1.554, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.7897, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.818, | |
| "eval_f1": 0.8189655172413793, | |
| "eval_loss": 0.42468851804733276, | |
| "eval_precision": 0.8146437994722955, | |
| "eval_recall": 0.8233333333333334, | |
| "eval_runtime": 240.4771, | |
| "eval_samples_per_second": 12.475, | |
| "eval_steps_per_second": 1.559, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.8229, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6603333333333333, | |
| "eval_f1": 0.7405143875732112, | |
| "eval_loss": 0.7496446967124939, | |
| "eval_precision": 0.5990935311083643, | |
| "eval_recall": 0.9693333333333334, | |
| "eval_runtime": 241.2847, | |
| "eval_samples_per_second": 12.433, | |
| "eval_steps_per_second": 1.554, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.8056, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.653, | |
| "eval_f1": 0.7400749063670412, | |
| "eval_loss": 0.7388193607330322, | |
| "eval_precision": 0.5916167664670658, | |
| "eval_recall": 0.988, | |
| "eval_runtime": 240.4851, | |
| "eval_samples_per_second": 12.475, | |
| "eval_steps_per_second": 1.559, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4e-05, | |
| "loss": 0.831, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.7976666666666666, | |
| "eval_f1": 0.7876880027981812, | |
| "eval_loss": 0.45541757345199585, | |
| "eval_precision": 0.8285504047093452, | |
| "eval_recall": 0.7506666666666667, | |
| "eval_runtime": 240.8878, | |
| "eval_samples_per_second": 12.454, | |
| "eval_steps_per_second": 1.557, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.3693, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.764, | |
| "eval_f1": 0.7972508591065293, | |
| "eval_loss": 0.567838191986084, | |
| "eval_precision": 0.6987951807228916, | |
| "eval_recall": 0.928, | |
| "eval_runtime": 240.8981, | |
| "eval_samples_per_second": 12.453, | |
| "eval_steps_per_second": 1.557, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.7178, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.8273333333333334, | |
| "eval_f1": 0.832579185520362, | |
| "eval_loss": 0.4122844934463501, | |
| "eval_precision": 0.8080301129234629, | |
| "eval_recall": 0.8586666666666667, | |
| "eval_runtime": 240.7253, | |
| "eval_samples_per_second": 12.462, | |
| "eval_steps_per_second": 1.558, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.5769, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.8406666666666667, | |
| "eval_f1": 0.8505315822388994, | |
| "eval_loss": 0.3792554438114166, | |
| "eval_precision": 0.800942285041225, | |
| "eval_recall": 0.9066666666666666, | |
| "eval_runtime": 240.7257, | |
| "eval_samples_per_second": 12.462, | |
| "eval_steps_per_second": 1.558, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.5896, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.6713333333333333, | |
| "eval_f1": 0.7512613521695257, | |
| "eval_loss": 0.8622921705245972, | |
| "eval_precision": 0.604301948051948, | |
| "eval_recall": 0.9926666666666667, | |
| "eval_runtime": 240.7579, | |
| "eval_samples_per_second": 12.461, | |
| "eval_steps_per_second": 1.558, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.4586, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.8066666666666666, | |
| "eval_f1": 0.791816223977028, | |
| "eval_loss": 0.5524763464927673, | |
| "eval_precision": 0.8576982892690513, | |
| "eval_recall": 0.7353333333333333, | |
| "eval_runtime": 241.0103, | |
| "eval_samples_per_second": 12.448, | |
| "eval_steps_per_second": 1.556, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.5359, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.5066666666666667, | |
| "eval_f1": 0.6696428571428572, | |
| "eval_loss": 2.7870869636535645, | |
| "eval_precision": 0.5033557046979866, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 240.5172, | |
| "eval_samples_per_second": 12.473, | |
| "eval_steps_per_second": 1.559, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.4746, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.728, | |
| "eval_f1": 0.7827476038338658, | |
| "eval_loss": 0.8008346557617188, | |
| "eval_precision": 0.651595744680851, | |
| "eval_recall": 0.98, | |
| "eval_runtime": 241.3279, | |
| "eval_samples_per_second": 12.431, | |
| "eval_steps_per_second": 1.554, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.4525, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.819, | |
| "eval_f1": 0.831104199066874, | |
| "eval_loss": 0.4293590486049652, | |
| "eval_precision": 0.7790087463556852, | |
| "eval_recall": 0.8906666666666667, | |
| "eval_runtime": 240.4794, | |
| "eval_samples_per_second": 12.475, | |
| "eval_steps_per_second": 1.559, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.5492, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.8193333333333334, | |
| "eval_f1": 0.7991104521868051, | |
| "eval_loss": 0.6366798281669617, | |
| "eval_precision": 0.8998330550918197, | |
| "eval_recall": 0.7186666666666667, | |
| "eval_runtime": 240.7182, | |
| "eval_samples_per_second": 12.463, | |
| "eval_steps_per_second": 1.558, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3315, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.8446666666666667, | |
| "eval_f1": 0.8411724608043626, | |
| "eval_loss": 0.44469600915908813, | |
| "eval_precision": 0.8605299860529986, | |
| "eval_recall": 0.8226666666666667, | |
| "eval_runtime": 240.3073, | |
| "eval_samples_per_second": 12.484, | |
| "eval_steps_per_second": 1.561, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.5122, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.723, | |
| "eval_f1": 0.7735077677841373, | |
| "eval_loss": 0.7516367435455322, | |
| "eval_precision": 0.6542185338865837, | |
| "eval_recall": 0.946, | |
| "eval_runtime": 240.4309, | |
| "eval_samples_per_second": 12.478, | |
| "eval_steps_per_second": 1.56, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.4712, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.7073333333333334, | |
| "eval_f1": 0.7701570680628271, | |
| "eval_loss": 0.7024486660957336, | |
| "eval_precision": 0.634051724137931, | |
| "eval_recall": 0.9806666666666667, | |
| "eval_runtime": 240.5793, | |
| "eval_samples_per_second": 12.47, | |
| "eval_steps_per_second": 1.559, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.5167, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.637, | |
| "eval_f1": 0.7323666748586877, | |
| "eval_loss": 1.0258432626724243, | |
| "eval_precision": 0.5799922148695991, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_runtime": 240.5552, | |
| "eval_samples_per_second": 12.471, | |
| "eval_steps_per_second": 1.559, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.3025, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7826666666666666, | |
| "eval_f1": 0.8170594837261503, | |
| "eval_loss": 0.5468646883964539, | |
| "eval_precision": 0.7054263565891473, | |
| "eval_recall": 0.9706666666666667, | |
| "eval_runtime": 240.9803, | |
| "eval_samples_per_second": 12.449, | |
| "eval_steps_per_second": 1.556, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3937, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.7956666666666666, | |
| "eval_f1": 0.8233938346297897, | |
| "eval_loss": 0.5975732207298279, | |
| "eval_precision": 0.7250126839167935, | |
| "eval_recall": 0.9526666666666667, | |
| "eval_runtime": 240.6768, | |
| "eval_samples_per_second": 12.465, | |
| "eval_steps_per_second": 1.558, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3635, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.7516666666666667, | |
| "eval_f1": 0.7974993204675184, | |
| "eval_loss": 0.681395411491394, | |
| "eval_precision": 0.6732446076181735, | |
| "eval_recall": 0.978, | |
| "eval_runtime": 243.1168, | |
| "eval_samples_per_second": 12.34, | |
| "eval_steps_per_second": 1.542, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.3354, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.6006666666666667, | |
| "eval_f1": 0.7139446036294174, | |
| "eval_loss": 1.097399115562439, | |
| "eval_precision": 0.5561755952380952, | |
| "eval_recall": 0.9966666666666667, | |
| "eval_runtime": 240.1778, | |
| "eval_samples_per_second": 12.491, | |
| "eval_steps_per_second": 1.561, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.2047, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.5143333333333333, | |
| "eval_f1": 0.6729517396184064, | |
| "eval_loss": 1.91347074508667, | |
| "eval_precision": 0.5072758037225042, | |
| "eval_recall": 0.9993333333333333, | |
| "eval_runtime": 240.5169, | |
| "eval_samples_per_second": 12.473, | |
| "eval_steps_per_second": 1.559, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.4875, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.8083333333333333, | |
| "eval_f1": 0.833574529667149, | |
| "eval_loss": 0.5008577704429626, | |
| "eval_precision": 0.7365728900255755, | |
| "eval_recall": 0.96, | |
| "eval_runtime": 240.1154, | |
| "eval_samples_per_second": 12.494, | |
| "eval_steps_per_second": 1.562, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2811, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.8413333333333334, | |
| "eval_f1": 0.8487928843710293, | |
| "eval_loss": 0.3812311887741089, | |
| "eval_precision": 0.8106796116504854, | |
| "eval_recall": 0.8906666666666667, | |
| "eval_runtime": 240.4478, | |
| "eval_samples_per_second": 12.477, | |
| "eval_steps_per_second": 1.56, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.2227, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.8606666666666667, | |
| "eval_f1": 0.862137203166227, | |
| "eval_loss": 0.36810368299484253, | |
| "eval_precision": 0.8531331592689295, | |
| "eval_recall": 0.8713333333333333, | |
| "eval_runtime": 240.5301, | |
| "eval_samples_per_second": 12.472, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.3917, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.8543333333333333, | |
| "eval_f1": 0.8612257859637981, | |
| "eval_loss": 0.4265972375869751, | |
| "eval_precision": 0.8223165554881746, | |
| "eval_recall": 0.904, | |
| "eval_runtime": 241.0329, | |
| "eval_samples_per_second": 12.446, | |
| "eval_steps_per_second": 1.556, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.3635, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.6436666666666667, | |
| "eval_f1": 0.736374845869297, | |
| "eval_loss": 1.1040711402893066, | |
| "eval_precision": 0.5843444227005871, | |
| "eval_recall": 0.9953333333333333, | |
| "eval_runtime": 240.5878, | |
| "eval_samples_per_second": 12.469, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.4145, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.8136666666666666, | |
| "eval_f1": 0.8390440541318746, | |
| "eval_loss": 0.5226981043815613, | |
| "eval_precision": 0.7384693360364927, | |
| "eval_recall": 0.9713333333333334, | |
| "eval_runtime": 240.5513, | |
| "eval_samples_per_second": 12.471, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.4154, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.6573333333333333, | |
| "eval_f1": 0.7438963627304432, | |
| "eval_loss": 0.8615061640739441, | |
| "eval_precision": 0.5938743038981702, | |
| "eval_recall": 0.9953333333333333, | |
| "eval_runtime": 241.311, | |
| "eval_samples_per_second": 12.432, | |
| "eval_steps_per_second": 1.554, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.2322, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.627, | |
| "eval_f1": 0.7275383491599707, | |
| "eval_loss": 1.0941112041473389, | |
| "eval_precision": 0.57307249712313, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 240.2621, | |
| "eval_samples_per_second": 12.486, | |
| "eval_steps_per_second": 1.561, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.3221, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.722, | |
| "eval_f1": 0.7807570977917981, | |
| "eval_loss": 0.7642508149147034, | |
| "eval_precision": 0.64453125, | |
| "eval_recall": 0.99, | |
| "eval_runtime": 240.1026, | |
| "eval_samples_per_second": 12.495, | |
| "eval_steps_per_second": 1.562, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2182, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.8256666666666667, | |
| "eval_f1": 0.847477398658501, | |
| "eval_loss": 0.4936087727546692, | |
| "eval_precision": 0.7532400207361327, | |
| "eval_recall": 0.9686666666666667, | |
| "eval_runtime": 240.5209, | |
| "eval_samples_per_second": 12.473, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.2608, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.7696666666666667, | |
| "eval_f1": 0.8104252400548698, | |
| "eval_loss": 0.6222155690193176, | |
| "eval_precision": 0.6885780885780886, | |
| "eval_recall": 0.9846666666666667, | |
| "eval_runtime": 242.2988, | |
| "eval_samples_per_second": 12.381, | |
| "eval_steps_per_second": 1.548, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3251, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.8256666666666667, | |
| "eval_f1": 0.8467623791385878, | |
| "eval_loss": 0.4772394299507141, | |
| "eval_precision": 0.7553580763199164, | |
| "eval_recall": 0.9633333333333334, | |
| "eval_runtime": 240.46, | |
| "eval_samples_per_second": 12.476, | |
| "eval_steps_per_second": 1.56, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9e-06, | |
| "loss": 0.1763, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.7433333333333333, | |
| "eval_f1": 0.7941176470588235, | |
| "eval_loss": 0.6803577542304993, | |
| "eval_precision": 0.6629464285714286, | |
| "eval_recall": 0.99, | |
| "eval_runtime": 240.563, | |
| "eval_samples_per_second": 12.471, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2904, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.7246666666666667, | |
| "eval_f1": 0.7827459231983166, | |
| "eval_loss": 0.727342426776886, | |
| "eval_precision": 0.6463944396177237, | |
| "eval_recall": 0.992, | |
| "eval_runtime": 241.4946, | |
| "eval_samples_per_second": 12.423, | |
| "eval_steps_per_second": 1.553, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.2758, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.689, | |
| "eval_f1": 0.7615640173779707, | |
| "eval_loss": 0.8572436571121216, | |
| "eval_precision": 0.6174886033982594, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_runtime": 240.6981, | |
| "eval_samples_per_second": 12.464, | |
| "eval_steps_per_second": 1.558, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3054, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.6446666666666667, | |
| "eval_f1": 0.7369200394866732, | |
| "eval_loss": 0.9957032799720764, | |
| "eval_precision": 0.5850313479623824, | |
| "eval_recall": 0.9953333333333333, | |
| "eval_runtime": 240.6892, | |
| "eval_samples_per_second": 12.464, | |
| "eval_steps_per_second": 1.558, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2433, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.7466666666666667, | |
| "eval_f1": 0.7960279119699409, | |
| "eval_loss": 0.6531896591186523, | |
| "eval_precision": 0.6662174303683738, | |
| "eval_recall": 0.9886666666666667, | |
| "eval_runtime": 242.6474, | |
| "eval_samples_per_second": 12.364, | |
| "eval_steps_per_second": 1.545, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.2869, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.816, | |
| "eval_f1": 0.8410138248847926, | |
| "eval_loss": 0.45964765548706055, | |
| "eval_precision": 0.7403651115618661, | |
| "eval_recall": 0.9733333333333334, | |
| "eval_runtime": 240.842, | |
| "eval_samples_per_second": 12.456, | |
| "eval_steps_per_second": 1.557, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3e-06, | |
| "loss": 0.119, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.727, | |
| "eval_f1": 0.7838479809976248, | |
| "eval_loss": 0.7068488001823425, | |
| "eval_precision": 0.6487549148099607, | |
| "eval_recall": 0.99, | |
| "eval_runtime": 240.4825, | |
| "eval_samples_per_second": 12.475, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.2153, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.7513333333333333, | |
| "eval_f1": 0.7988133764832793, | |
| "eval_loss": 0.6478840112686157, | |
| "eval_precision": 0.6707427536231884, | |
| "eval_recall": 0.9873333333333333, | |
| "eval_runtime": 240.4615, | |
| "eval_samples_per_second": 12.476, | |
| "eval_steps_per_second": 1.56, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.2594, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.7313333333333333, | |
| "eval_f1": 0.7866596082583377, | |
| "eval_loss": 0.6965696811676025, | |
| "eval_precision": 0.6523266022827041, | |
| "eval_recall": 0.9906666666666667, | |
| "eval_runtime": 240.2996, | |
| "eval_samples_per_second": 12.484, | |
| "eval_steps_per_second": 1.561, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2108, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7433333333333333, | |
| "eval_f1": 0.7938972162740899, | |
| "eval_loss": 0.6547001004219055, | |
| "eval_precision": 0.6632379248658319, | |
| "eval_recall": 0.9886666666666667, | |
| "eval_runtime": 240.3896, | |
| "eval_samples_per_second": 12.48, | |
| "eval_steps_per_second": 1.56, | |
| "step": 1750 | |
| } | |
| ], | |
| "max_steps": 1750, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.1979933974528e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |