| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.807017543859649, | |
| "eval_steps": 50, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.478505000877347e-05, | |
| "loss": 2.8559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.195713520050049, | |
| "eval_runtime": 14.6436, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.4565713283032112e-05, | |
| "loss": 2.2991, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.9645323753356934, | |
| "eval_runtime": 14.6522, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.4346376557290754e-05, | |
| "loss": 2.1318, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.8834866285324097, | |
| "eval_runtime": 14.646, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.4127039831549393e-05, | |
| "loss": 2.035, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.8372365236282349, | |
| "eval_runtime": 14.6452, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.390770310580804e-05, | |
| "loss": 2.0511, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.8165128231048584, | |
| "eval_runtime": 14.6408, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.3688366380066677e-05, | |
| "loss": 2.0054, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7788053750991821, | |
| "eval_runtime": 14.6416, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.3469029654325323e-05, | |
| "loss": 1.944, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.7566713094711304, | |
| "eval_runtime": 14.6486, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.324969292858396e-05, | |
| "loss": 1.9487, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.7560102939605713, | |
| "eval_runtime": 14.6501, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.3030356202842604e-05, | |
| "loss": 1.9183, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.7329343557357788, | |
| "eval_runtime": 14.6419, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.2811019477101246e-05, | |
| "loss": 1.8684, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.7263619899749756, | |
| "eval_runtime": 14.647, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.2591682751359888e-05, | |
| "loss": 1.9194, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.7277635335922241, | |
| "eval_runtime": 14.6488, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.237234602561853e-05, | |
| "loss": 1.8842, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.728346347808838, | |
| "eval_runtime": 14.6409, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.2153009299877172e-05, | |
| "loss": 1.817, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.709412693977356, | |
| "eval_runtime": 14.6427, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.1933672574135815e-05, | |
| "loss": 1.8139, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.7006276845932007, | |
| "eval_runtime": 14.6444, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.1714335848394457e-05, | |
| "loss": 1.8657, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.688984990119934, | |
| "eval_runtime": 14.6453, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.14949991226531e-05, | |
| "loss": 1.8366, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6756386756896973, | |
| "eval_runtime": 14.6493, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1275662396911738e-05, | |
| "loss": 1.8521, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.6723501682281494, | |
| "eval_runtime": 14.645, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.1056325671170383e-05, | |
| "loss": 1.8357, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6671411991119385, | |
| "eval_runtime": 14.646, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0836988945429022e-05, | |
| "loss": 1.8667, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.6564487218856812, | |
| "eval_runtime": 14.6438, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0617652219687667e-05, | |
| "loss": 1.8163, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.6533170938491821, | |
| "eval_runtime": 14.6431, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.0398315493946306e-05, | |
| "loss": 1.844, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.6446335315704346, | |
| "eval_runtime": 14.6477, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.017897876820495e-05, | |
| "loss": 1.8403, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.6377147436141968, | |
| "eval_runtime": 14.65, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.995964204246359e-05, | |
| "loss": 1.8436, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.6400964260101318, | |
| "eval_runtime": 14.6512, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.9740305316722233e-05, | |
| "loss": 1.8255, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.6376707553863525, | |
| "eval_runtime": 14.6441, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.9520968590980875e-05, | |
| "loss": 1.7917, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.6302813291549683, | |
| "eval_runtime": 14.6397, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.9301631865239517e-05, | |
| "loss": 1.8289, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.6255093812942505, | |
| "eval_runtime": 14.6406, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.9082295139498156e-05, | |
| "loss": 1.8736, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.617380976676941, | |
| "eval_runtime": 14.6455, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.88629584137568e-05, | |
| "loss": 1.748, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.6211485862731934, | |
| "eval_runtime": 14.6529, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.8643621688015444e-05, | |
| "loss": 1.7769, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.6201837062835693, | |
| "eval_runtime": 14.6729, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.8424284962274086e-05, | |
| "loss": 1.7295, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 1.6232948303222656, | |
| "eval_runtime": 14.6843, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.8204948236532728e-05, | |
| "loss": 1.6845, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 1.626202940940857, | |
| "eval_runtime": 14.6738, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.7985611510791367e-05, | |
| "loss": 1.6655, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.617616057395935, | |
| "eval_runtime": 14.6736, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.7766274785050012e-05, | |
| "loss": 1.6687, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.6166654825210571, | |
| "eval_runtime": 14.7006, | |
| "eval_samples_per_second": 1.429, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.754693805930865e-05, | |
| "loss": 1.704, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.6115292310714722, | |
| "eval_runtime": 14.6762, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.7327601333567293e-05, | |
| "loss": 1.6818, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.6096872091293335, | |
| "eval_runtime": 14.6731, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7108264607825935e-05, | |
| "loss": 1.675, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.6069471836090088, | |
| "eval_runtime": 14.6844, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.204, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.6888927882084577e-05, | |
| "loss": 1.6865, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.6076393127441406, | |
| "eval_runtime": 14.648, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.666959115634322e-05, | |
| "loss": 1.6966, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.603057861328125, | |
| "eval_runtime": 14.6382, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.6450254430601862e-05, | |
| "loss": 1.7239, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 1.6086949110031128, | |
| "eval_runtime": 14.6442, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.62309177048605e-05, | |
| "loss": 1.677, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 1.6053651571273804, | |
| "eval_runtime": 14.6414, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.6011580979119146e-05, | |
| "loss": 1.6925, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.5961679220199585, | |
| "eval_runtime": 14.6373, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.5792244253377785e-05, | |
| "loss": 1.7188, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.591933250427246, | |
| "eval_runtime": 14.6374, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.557290752763643e-05, | |
| "loss": 1.6994, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.5993770360946655, | |
| "eval_runtime": 14.6433, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.535357080189507e-05, | |
| "loss": 1.6817, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.5951728820800781, | |
| "eval_runtime": 14.6423, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.5134234076153711e-05, | |
| "loss": 1.6576, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.595167636871338, | |
| "eval_runtime": 14.6398, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.4914897350412355e-05, | |
| "loss": 1.7117, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 1.594815969467163, | |
| "eval_runtime": 14.633, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.4695560624670996e-05, | |
| "loss": 1.6795, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 1.5858888626098633, | |
| "eval_runtime": 14.6449, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.4476223898929636e-05, | |
| "loss": 1.7084, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.584323525428772, | |
| "eval_runtime": 14.6394, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.425688717318828e-05, | |
| "loss": 1.6785, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.5876024961471558, | |
| "eval_runtime": 14.6397, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.403755044744692e-05, | |
| "loss": 1.6863, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.5827977657318115, | |
| "eval_runtime": 14.6332, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.3818213721705564e-05, | |
| "loss": 1.718, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.5843836069107056, | |
| "eval_runtime": 14.6334, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.3598876995964205e-05, | |
| "loss": 1.6811, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.5835539102554321, | |
| "eval_runtime": 14.6371, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.3379540270222845e-05, | |
| "loss": 1.6748, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.5856655836105347, | |
| "eval_runtime": 14.6358, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.3160203544481489e-05, | |
| "loss": 1.6614, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 1.5807286500930786, | |
| "eval_runtime": 14.6393, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.294086681874013e-05, | |
| "loss": 1.6587, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 1.5819549560546875, | |
| "eval_runtime": 14.6411, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.2721530092998773e-05, | |
| "loss": 1.7167, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 1.5828579664230347, | |
| "eval_runtime": 14.6359, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2502193367257414e-05, | |
| "loss": 1.663, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.5743989944458008, | |
| "eval_runtime": 14.6401, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.2282856641516056e-05, | |
| "loss": 1.5641, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.5980640649795532, | |
| "eval_runtime": 14.6296, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.2063519915774696e-05, | |
| "loss": 1.6048, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 1.598111629486084, | |
| "eval_runtime": 14.6392, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.1844183190033339e-05, | |
| "loss": 1.542, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 1.5949300527572632, | |
| "eval_runtime": 14.6318, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.162484646429198e-05, | |
| "loss": 1.5717, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.5896787643432617, | |
| "eval_runtime": 14.6355, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.1405509738550623e-05, | |
| "loss": 1.5775, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 1.5945594310760498, | |
| "eval_runtime": 14.6318, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.1186173012809265e-05, | |
| "loss": 1.5514, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 1.596181035041809, | |
| "eval_runtime": 14.6312, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.0966836287067907e-05, | |
| "loss": 1.5479, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 1.5988695621490479, | |
| "eval_runtime": 14.6305, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.074749956132655e-05, | |
| "loss": 1.5567, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.5939878225326538, | |
| "eval_runtime": 14.6282, | |
| "eval_samples_per_second": 1.436, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.0528162835585192e-05, | |
| "loss": 1.5917, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.5928601026535034, | |
| "eval_runtime": 14.6304, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0308826109843834e-05, | |
| "loss": 1.5635, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 1.5916301012039185, | |
| "eval_runtime": 14.6301, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0089489384102474e-05, | |
| "loss": 1.6097, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 1.5879075527191162, | |
| "eval_runtime": 14.6343, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.870152658361116e-06, | |
| "loss": 1.5256, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 1.5953552722930908, | |
| "eval_runtime": 14.6382, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.650815932619759e-06, | |
| "loss": 1.5758, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 1.5901867151260376, | |
| "eval_runtime": 14.6575, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.4314792068784e-06, | |
| "loss": 1.5924, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 1.592368721961975, | |
| "eval_runtime": 14.6369, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 9.212142481137043e-06, | |
| "loss": 1.5442, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.5874643325805664, | |
| "eval_runtime": 14.6605, | |
| "eval_samples_per_second": 1.432, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.992805755395683e-06, | |
| "loss": 1.5633, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.5897241830825806, | |
| "eval_runtime": 14.6465, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 8.773469029654325e-06, | |
| "loss": 1.5578, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 1.5877512693405151, | |
| "eval_runtime": 14.6433, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 8.554132303912968e-06, | |
| "loss": 1.5486, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 1.5919996500015259, | |
| "eval_runtime": 14.6424, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 8.33479557817161e-06, | |
| "loss": 1.559, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.5883424282073975, | |
| "eval_runtime": 14.6464, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 8.11545885243025e-06, | |
| "loss": 1.5766, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 1.5866857767105103, | |
| "eval_runtime": 14.6428, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.896122126688892e-06, | |
| "loss": 1.5489, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 1.5900993347167969, | |
| "eval_runtime": 14.6566, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.676785400947535e-06, | |
| "loss": 1.5606, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 1.5870875120162964, | |
| "eval_runtime": 14.632, | |
| "eval_samples_per_second": 1.435, | |
| "eval_steps_per_second": 0.205, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.457448675206178e-06, | |
| "loss": 1.5128, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 1.586663007736206, | |
| "eval_runtime": 14.6412, | |
| "eval_samples_per_second": 1.434, | |
| "eval_steps_per_second": 0.205, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5700, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 400, | |
| "total_flos": 7.98304400105472e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |