| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 10, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016, | |
| "eval_loss": 1.1534295082092285, | |
| "eval_runtime": 3.0421, | |
| "eval_samples_per_second": 51.28, | |
| "eval_steps_per_second": 2.63, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 20.25132179260254, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.0304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "eval_loss": 1.14567232131958, | |
| "eval_runtime": 3.0142, | |
| "eval_samples_per_second": 51.755, | |
| "eval_steps_per_second": 2.654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 13.503382682800293, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.5982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "eval_loss": 1.1035062074661255, | |
| "eval_runtime": 3.0105, | |
| "eval_samples_per_second": 51.818, | |
| "eval_steps_per_second": 2.657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 6.730069160461426, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.3721, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "eval_loss": 1.038061499595642, | |
| "eval_runtime": 3.0065, | |
| "eval_samples_per_second": 51.887, | |
| "eval_steps_per_second": 2.661, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 5.994906902313232, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.1836, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "eval_loss": 0.9870163202285767, | |
| "eval_runtime": 3.0074, | |
| "eval_samples_per_second": 51.871, | |
| "eval_steps_per_second": 2.66, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.078227996826172, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.1024, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.9939066767692566, | |
| "eval_runtime": 3.0144, | |
| "eval_samples_per_second": 51.751, | |
| "eval_steps_per_second": 2.654, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 2.8209125995635986, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.0809, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "eval_loss": 0.995045006275177, | |
| "eval_runtime": 3.0074, | |
| "eval_samples_per_second": 51.872, | |
| "eval_steps_per_second": 2.66, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 2.684706926345825, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 1.0544, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "eval_loss": 0.9916963577270508, | |
| "eval_runtime": 3.0125, | |
| "eval_samples_per_second": 51.785, | |
| "eval_steps_per_second": 2.656, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 2.3479392528533936, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.0595, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "eval_loss": 0.9863230586051941, | |
| "eval_runtime": 3.0094, | |
| "eval_samples_per_second": 51.838, | |
| "eval_steps_per_second": 2.658, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 2.6608166694641113, | |
| "learning_rate": 2.16e-05, | |
| "loss": 1.0859, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "eval_loss": 0.9974517822265625, | |
| "eval_runtime": 3.012, | |
| "eval_samples_per_second": 51.793, | |
| "eval_steps_per_second": 2.656, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.8634560108184814, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.0728, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.0015454292297363, | |
| "eval_runtime": 3.0065, | |
| "eval_samples_per_second": 51.887, | |
| "eval_steps_per_second": 2.661, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 2.4156150817871094, | |
| "learning_rate": 2.64e-05, | |
| "loss": 1.0752, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "eval_loss": 1.0033469200134277, | |
| "eval_runtime": 3.0157, | |
| "eval_samples_per_second": 51.729, | |
| "eval_steps_per_second": 2.653, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 2.4899582862854004, | |
| "learning_rate": 2.88e-05, | |
| "loss": 1.0586, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "eval_loss": 1.0045567750930786, | |
| "eval_runtime": 3.011, | |
| "eval_samples_per_second": 51.81, | |
| "eval_steps_per_second": 2.657, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 2.4391989707946777, | |
| "learning_rate": 2.9998537860139564e-05, | |
| "loss": 1.0549, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "eval_loss": 1.0204839706420898, | |
| "eval_runtime": 3.0118, | |
| "eval_samples_per_second": 51.797, | |
| "eval_steps_per_second": 2.656, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 2.5839991569519043, | |
| "learning_rate": 2.9986842451482876e-05, | |
| "loss": 1.137, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "eval_loss": 1.0195070505142212, | |
| "eval_runtime": 3.0108, | |
| "eval_samples_per_second": 51.814, | |
| "eval_steps_per_second": 2.657, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 4.575782299041748, | |
| "learning_rate": 2.9963460753897364e-05, | |
| "loss": 1.1321, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.031137228012085, | |
| "eval_runtime": 3.0126, | |
| "eval_samples_per_second": 51.782, | |
| "eval_steps_per_second": 2.656, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 3.309042453765869, | |
| "learning_rate": 2.992841099972747e-05, | |
| "loss": 1.148, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "eval_loss": 1.0269774198532104, | |
| "eval_runtime": 3.0093, | |
| "eval_samples_per_second": 51.839, | |
| "eval_steps_per_second": 2.658, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 2.796513319015503, | |
| "learning_rate": 2.988172051971717e-05, | |
| "loss": 1.0891, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "eval_loss": 1.0196280479431152, | |
| "eval_runtime": 3.0133, | |
| "eval_samples_per_second": 51.77, | |
| "eval_steps_per_second": 2.655, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 3.2158987522125244, | |
| "learning_rate": 2.9823425721698293e-05, | |
| "loss": 1.1017, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "eval_loss": 1.031247615814209, | |
| "eval_runtime": 3.0065, | |
| "eval_samples_per_second": 51.888, | |
| "eval_steps_per_second": 2.661, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 2.686189889907837, | |
| "learning_rate": 2.975357206220079e-05, | |
| "loss": 1.0981, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "eval_loss": 1.0395549535751343, | |
| "eval_runtime": 3.0239, | |
| "eval_samples_per_second": 51.589, | |
| "eval_steps_per_second": 2.646, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.959608316421509, | |
| "learning_rate": 2.9672214011007087e-05, | |
| "loss": 1.0892, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.0621881484985352, | |
| "eval_runtime": 3.01, | |
| "eval_samples_per_second": 51.827, | |
| "eval_steps_per_second": 2.658, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 2.3781332969665527, | |
| "learning_rate": 2.9579415008678196e-05, | |
| "loss": 1.1321, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "eval_loss": 1.0873780250549316, | |
| "eval_runtime": 3.0093, | |
| "eval_samples_per_second": 51.839, | |
| "eval_steps_per_second": 2.658, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 3.1061549186706543, | |
| "learning_rate": 2.9475247417084672e-05, | |
| "loss": 1.1245, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "eval_loss": 1.0836576223373413, | |
| "eval_runtime": 3.0092, | |
| "eval_samples_per_second": 51.842, | |
| "eval_steps_per_second": 2.659, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 3.747018337249756, | |
| "learning_rate": 2.9359792462981007e-05, | |
| "loss": 1.1511, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "eval_loss": 1.0861718654632568, | |
| "eval_runtime": 3.0167, | |
| "eval_samples_per_second": 51.713, | |
| "eval_steps_per_second": 2.652, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 2.8736958503723145, | |
| "learning_rate": 2.923314017466745e-05, | |
| "loss": 1.1321, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "eval_loss": 1.0627102851867676, | |
| "eval_runtime": 3.0136, | |
| "eval_samples_per_second": 51.765, | |
| "eval_steps_per_second": 2.655, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 2.3447535037994385, | |
| "learning_rate": 2.9095389311788626e-05, | |
| "loss": 1.0972, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.0548475980758667, | |
| "eval_runtime": 3.011, | |
| "eval_samples_per_second": 51.811, | |
| "eval_steps_per_second": 2.657, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 2.6532089710235596, | |
| "learning_rate": 2.894664728832377e-05, | |
| "loss": 1.1624, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "eval_loss": 1.059614896774292, | |
| "eval_runtime": 3.0099, | |
| "eval_samples_per_second": 51.829, | |
| "eval_steps_per_second": 2.658, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "grad_norm": 3.049149751663208, | |
| "learning_rate": 2.8787030088828517e-05, | |
| "loss": 1.089, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "eval_loss": 1.0867388248443604, | |
| "eval_runtime": 3.0057, | |
| "eval_samples_per_second": 51.901, | |
| "eval_steps_per_second": 2.662, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 2.3557188510894775, | |
| "learning_rate": 2.8616662177993633e-05, | |
| "loss": 1.0937, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "eval_loss": 1.0865511894226074, | |
| "eval_runtime": 3.0136, | |
| "eval_samples_per_second": 51.766, | |
| "eval_steps_per_second": 2.655, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.232, | |
| "grad_norm": 2.5818262100219727, | |
| "learning_rate": 2.8435676403591193e-05, | |
| "loss": 1.0708, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.232, | |
| "eval_loss": 1.0967109203338623, | |
| "eval_runtime": 3.0116, | |
| "eval_samples_per_second": 51.8, | |
| "eval_steps_per_second": 2.656, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 3.1398000717163086, | |
| "learning_rate": 2.8244213892883907e-05, | |
| "loss": 1.0921, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.1191679239273071, | |
| "eval_runtime": 3.0116, | |
| "eval_samples_per_second": 51.8, | |
| "eval_steps_per_second": 2.656, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.248, | |
| "grad_norm": 2.4209301471710205, | |
| "learning_rate": 2.8042423942578285e-05, | |
| "loss": 1.1155, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.248, | |
| "eval_loss": 1.1559284925460815, | |
| "eval_runtime": 3.0159, | |
| "eval_samples_per_second": 51.725, | |
| "eval_steps_per_second": 2.653, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 2.8402583599090576, | |
| "learning_rate": 2.78304639024076e-05, | |
| "loss": 1.1269, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "eval_loss": 1.1549513339996338, | |
| "eval_runtime": 3.0068, | |
| "eval_samples_per_second": 51.882, | |
| "eval_steps_per_second": 2.661, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.264, | |
| "grad_norm": 2.46132755279541, | |
| "learning_rate": 2.7608499052435265e-05, | |
| "loss": 1.1088, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.264, | |
| "eval_loss": 1.1405725479125977, | |
| "eval_runtime": 3.0049, | |
| "eval_samples_per_second": 51.914, | |
| "eval_steps_per_second": 2.662, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 2.852588176727295, | |
| "learning_rate": 2.7376702474174428e-05, | |
| "loss": 1.0859, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "eval_loss": 1.1068381071090698, | |
| "eval_runtime": 3.0037, | |
| "eval_samples_per_second": 51.936, | |
| "eval_steps_per_second": 2.663, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 2.3993775844573975, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 1.1132, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.1167492866516113, | |
| "eval_runtime": 3.0024, | |
| "eval_samples_per_second": 51.959, | |
| "eval_steps_per_second": 2.665, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 2.4123260974884033, | |
| "learning_rate": 2.688434465032786e-05, | |
| "loss": 1.0702, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "eval_loss": 1.0937358140945435, | |
| "eval_runtime": 3.0087, | |
| "eval_samples_per_second": 51.849, | |
| "eval_steps_per_second": 2.659, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.296, | |
| "grad_norm": 2.667454719543457, | |
| "learning_rate": 2.6624167330562697e-05, | |
| "loss": 1.1427, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.296, | |
| "eval_loss": 1.1052156686782837, | |
| "eval_runtime": 3.0045, | |
| "eval_samples_per_second": 51.922, | |
| "eval_steps_per_second": 2.663, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 2.4109561443328857, | |
| "learning_rate": 2.6354925834776346e-05, | |
| "loss": 1.1124, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "eval_loss": 1.1146537065505981, | |
| "eval_runtime": 3.0047, | |
| "eval_samples_per_second": 51.918, | |
| "eval_steps_per_second": 2.662, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.312, | |
| "grad_norm": 2.661153554916382, | |
| "learning_rate": 2.607683010938826e-05, | |
| "loss": 1.1431, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.312, | |
| "eval_loss": 1.139147400856018, | |
| "eval_runtime": 3.0049, | |
| "eval_samples_per_second": 51.915, | |
| "eval_steps_per_second": 2.662, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.762219190597534, | |
| "learning_rate": 2.5790097005079766e-05, | |
| "loss": 1.1471, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.1363451480865479, | |
| "eval_runtime": 3.012, | |
| "eval_samples_per_second": 51.792, | |
| "eval_steps_per_second": 2.656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.328, | |
| "grad_norm": 2.473832368850708, | |
| "learning_rate": 2.5494950107700482e-05, | |
| "loss": 1.1466, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.328, | |
| "eval_loss": 1.1255215406417847, | |
| "eval_runtime": 3.0084, | |
| "eval_samples_per_second": 51.855, | |
| "eval_steps_per_second": 2.659, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 2.8688554763793945, | |
| "learning_rate": 2.519161956392275e-05, | |
| "loss": 1.0485, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "eval_loss": 1.1306232213974, | |
| "eval_runtime": 3.0061, | |
| "eval_samples_per_second": 51.894, | |
| "eval_steps_per_second": 2.661, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.344, | |
| "grad_norm": 2.7669804096221924, | |
| "learning_rate": 2.4880341901780205e-05, | |
| "loss": 1.0817, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.344, | |
| "eval_loss": 1.124632716178894, | |
| "eval_runtime": 3.0118, | |
| "eval_samples_per_second": 51.797, | |
| "eval_steps_per_second": 2.656, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 2.8019163608551025, | |
| "learning_rate": 2.4561359846230346e-05, | |
| "loss": 1.0918, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "eval_loss": 1.1212003231048584, | |
| "eval_runtime": 3.0142, | |
| "eval_samples_per_second": 51.755, | |
| "eval_steps_per_second": 2.654, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 3.220196485519409, | |
| "learning_rate": 2.4234922129884873e-05, | |
| "loss": 1.0958, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.1051884889602661, | |
| "eval_runtime": 3.0146, | |
| "eval_samples_per_second": 51.748, | |
| "eval_steps_per_second": 2.654, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 2.7096750736236572, | |
| "learning_rate": 2.3901283299055524e-05, | |
| "loss": 1.0681, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "eval_loss": 1.0787197351455688, | |
| "eval_runtime": 3.0111, | |
| "eval_samples_per_second": 51.809, | |
| "eval_steps_per_second": 2.657, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.376, | |
| "grad_norm": 2.8523542881011963, | |
| "learning_rate": 2.356070351526648e-05, | |
| "loss": 1.095, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.376, | |
| "eval_loss": 1.0948532819747925, | |
| "eval_runtime": 3.004, | |
| "eval_samples_per_second": 51.931, | |
| "eval_steps_per_second": 2.663, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 3.2367355823516846, | |
| "learning_rate": 2.3213448352388256e-05, | |
| "loss": 1.0575, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "eval_loss": 1.082040786743164, | |
| "eval_runtime": 3.0033, | |
| "eval_samples_per_second": 51.943, | |
| "eval_steps_per_second": 2.664, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.392, | |
| "grad_norm": 2.410609006881714, | |
| "learning_rate": 2.285978858955119e-05, | |
| "loss": 1.0265, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.392, | |
| "eval_loss": 1.0808920860290527, | |
| "eval_runtime": 3.0115, | |
| "eval_samples_per_second": 51.801, | |
| "eval_steps_per_second": 2.656, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.2114365100860596, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.0819, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.0693764686584473, | |
| "eval_runtime": 3.009, | |
| "eval_samples_per_second": 51.844, | |
| "eval_steps_per_second": 2.659, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.715405190483149e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |