| { | |
| "best_metric": 0.21225065, | |
| "best_model_checkpoint": "/workspace/output/molmo-7b-d/v1-20250103-233013/checkpoint-414", | |
| "epoch": 3.0, | |
| "eval_steps": 200, | |
| "global_step": 414, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.93268561, | |
| "epoch": 0.007272727272727273, | |
| "grad_norm": 4.360905168604235, | |
| "learning_rate": 0.0, | |
| "loss": 0.15919656, | |
| "memory(GiB)": 131.1, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.051814 | |
| }, | |
| { | |
| "acc": 0.93592656, | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 5.722024176509264, | |
| "learning_rate": 4.829949384917788e-06, | |
| "loss": 0.16946605, | |
| "memory(GiB)": 131.7, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.164947 | |
| }, | |
| { | |
| "acc": 0.92745094, | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 5.449760109713864, | |
| "learning_rate": 6.910095361682884e-06, | |
| "loss": 0.19423571, | |
| "memory(GiB)": 131.7, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.228063 | |
| }, | |
| { | |
| "acc": 0.9191308, | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": 5.591882854054257, | |
| "learning_rate": 8.126902754116446e-06, | |
| "loss": 0.2132081, | |
| "memory(GiB)": 131.7, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.262462 | |
| }, | |
| { | |
| "acc": 0.91665707, | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 8.643333147328232, | |
| "learning_rate": 8.990241338447979e-06, | |
| "loss": 0.2489913, | |
| "memory(GiB)": 132.85, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.283686 | |
| }, | |
| { | |
| "acc": 0.92767944, | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 5.521300358752013, | |
| "learning_rate": 9.659898769835576e-06, | |
| "loss": 0.20275159, | |
| "memory(GiB)": 100.16, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.297772 | |
| }, | |
| { | |
| "acc": 0.91237392, | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 4.691287833576054, | |
| "learning_rate": 9.999635040777627e-06, | |
| "loss": 0.24152677, | |
| "memory(GiB)": 100.16, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.306552 | |
| }, | |
| { | |
| "acc": 0.89811802, | |
| "epoch": 0.2545454545454545, | |
| "grad_norm": 2.3267326177072176, | |
| "learning_rate": 9.995529861428146e-06, | |
| "loss": 0.2682821, | |
| "memory(GiB)": 100.16, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.312152 | |
| }, | |
| { | |
| "acc": 0.91184635, | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 3.241573273096398, | |
| "learning_rate": 9.986867061882612e-06, | |
| "loss": 0.23578806, | |
| "memory(GiB)": 100.16, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.314978 | |
| }, | |
| { | |
| "acc": 0.9012291, | |
| "epoch": 0.32727272727272727, | |
| "grad_norm": 2.3552152207973713, | |
| "learning_rate": 9.973654546348053e-06, | |
| "loss": 0.25761139, | |
| "memory(GiB)": 100.16, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.319208 | |
| }, | |
| { | |
| "acc": 0.9016325, | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 3.1153181076119703, | |
| "learning_rate": 9.955904370333514e-06, | |
| "loss": 0.24715631, | |
| "memory(GiB)": 100.16, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.32296 | |
| }, | |
| { | |
| "acc": 0.89749699, | |
| "epoch": 0.4, | |
| "grad_norm": 2.4498466601081943, | |
| "learning_rate": 9.933632729650212e-06, | |
| "loss": 0.25689688, | |
| "memory(GiB)": 100.16, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.325846 | |
| }, | |
| { | |
| "acc": 0.88724833, | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 4.364723865759911, | |
| "learning_rate": 9.906859945633999e-06, | |
| "loss": 0.28743353, | |
| "memory(GiB)": 100.16, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.328247 | |
| }, | |
| { | |
| "acc": 0.90578156, | |
| "epoch": 0.4727272727272727, | |
| "grad_norm": 3.243778418144708, | |
| "learning_rate": 9.875610446603524e-06, | |
| "loss": 0.26308877, | |
| "memory(GiB)": 100.16, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.330485 | |
| }, | |
| { | |
| "acc": 0.89676228, | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 3.4165598224968274, | |
| "learning_rate": 9.83991274557109e-06, | |
| "loss": 0.26372042, | |
| "memory(GiB)": 127.96, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.332413 | |
| }, | |
| { | |
| "acc": 0.9054903, | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 3.814636181453338, | |
| "learning_rate": 9.7997994142265e-06, | |
| "loss": 0.25466361, | |
| "memory(GiB)": 127.96, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.334379 | |
| }, | |
| { | |
| "acc": 0.90086946, | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 3.9972259822599243, | |
| "learning_rate": 9.755307053217622e-06, | |
| "loss": 0.27588401, | |
| "memory(GiB)": 127.96, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.336004 | |
| }, | |
| { | |
| "acc": 0.89949837, | |
| "epoch": 0.6181818181818182, | |
| "grad_norm": 5.998240972031008, | |
| "learning_rate": 9.706476258754834e-06, | |
| "loss": 0.25472341, | |
| "memory(GiB)": 127.96, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.337291 | |
| }, | |
| { | |
| "acc": 0.88558121, | |
| "epoch": 0.6545454545454545, | |
| "grad_norm": 2.7186082929792574, | |
| "learning_rate": 9.653351585569786e-06, | |
| "loss": 0.28254557, | |
| "memory(GiB)": 127.96, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.337576 | |
| }, | |
| { | |
| "acc": 0.90562687, | |
| "epoch": 0.6909090909090909, | |
| "grad_norm": 1.6880555029124777, | |
| "learning_rate": 9.595981506262264e-06, | |
| "loss": 0.25460241, | |
| "memory(GiB)": 127.96, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.338319 | |
| }, | |
| { | |
| "acc": 0.90238457, | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 1.824873702466673, | |
| "learning_rate": 9.534418367072303e-06, | |
| "loss": 0.25135682, | |
| "memory(GiB)": 127.96, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.33935 | |
| }, | |
| { | |
| "acc": 0.90719824, | |
| "epoch": 0.7636363636363637, | |
| "grad_norm": 3.0523518026276926, | |
| "learning_rate": 9.468718340117846e-06, | |
| "loss": 0.23181794, | |
| "memory(GiB)": 127.96, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.340475 | |
| }, | |
| { | |
| "acc": 0.89296656, | |
| "epoch": 0.8, | |
| "grad_norm": 3.6744833597367514, | |
| "learning_rate": 9.398941372141562e-06, | |
| "loss": 0.27924564, | |
| "memory(GiB)": 127.96, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.341456 | |
| }, | |
| { | |
| "acc": 0.89754677, | |
| "epoch": 0.8363636363636363, | |
| "grad_norm": 3.250222318126925, | |
| "learning_rate": 9.325151129813582e-06, | |
| "loss": 0.26513102, | |
| "memory(GiB)": 127.96, | |
| "step": 115, | |
| "train_speed(iter/s)": 0.342153 | |
| }, | |
| { | |
| "acc": 0.88903837, | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 2.376728799007849, | |
| "learning_rate": 9.247414941640045e-06, | |
| "loss": 0.30169072, | |
| "memory(GiB)": 133.76, | |
| "step": 120, | |
| "train_speed(iter/s)": 0.342998 | |
| }, | |
| { | |
| "acc": 0.89329395, | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 4.889478322316845, | |
| "learning_rate": 9.165803736530492e-06, | |
| "loss": 0.28302565, | |
| "memory(GiB)": 100.58, | |
| "step": 125, | |
| "train_speed(iter/s)": 0.343779 | |
| }, | |
| { | |
| "acc": 0.89977417, | |
| "epoch": 0.9454545454545454, | |
| "grad_norm": 2.0057917841024633, | |
| "learning_rate": 9.080391979080116e-06, | |
| "loss": 0.2668047, | |
| "memory(GiB)": 100.58, | |
| "step": 130, | |
| "train_speed(iter/s)": 0.344351 | |
| }, | |
| { | |
| "acc": 0.90148487, | |
| "epoch": 0.9818181818181818, | |
| "grad_norm": 2.470715179920895, | |
| "learning_rate": 8.991257601625973e-06, | |
| "loss": 0.25751991, | |
| "memory(GiB)": 100.58, | |
| "step": 135, | |
| "train_speed(iter/s)": 0.345171 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_acc": 0.9078246620237608, | |
| "eval_loss": 0.2361508309841156, | |
| "eval_runtime": 10.278, | |
| "eval_samples_per_second": 11.286, | |
| "eval_steps_per_second": 1.459, | |
| "step": 138 | |
| }, | |
| { | |
| "acc": 0.8134038, | |
| "epoch": 1.0145454545454546, | |
| "grad_norm": 1.9385369249323439, | |
| "learning_rate": 8.917324354080927e-06, | |
| "loss": 0.254459, | |
| "memory(GiB)": 100.58, | |
| "step": 140, | |
| "train_speed(iter/s)": 0.309598 | |
| }, | |
| { | |
| "acc": 0.90728855, | |
| "epoch": 1.050909090909091, | |
| "grad_norm": 76.54794008048425, | |
| "learning_rate": 8.82169644486897e-06, | |
| "loss": 0.23623853, | |
| "memory(GiB)": 100.58, | |
| "step": 145, | |
| "train_speed(iter/s)": 0.311044 | |
| }, | |
| { | |
| "acc": 0.91997566, | |
| "epoch": 1.0872727272727274, | |
| "grad_norm": 1.727673298537959, | |
| "learning_rate": 8.722581957483633e-06, | |
| "loss": 0.21817675, | |
| "memory(GiB)": 100.58, | |
| "step": 150, | |
| "train_speed(iter/s)": 0.31275 | |
| }, | |
| { | |
| "acc": 0.91184559, | |
| "epoch": 1.1236363636363635, | |
| "grad_norm": 2.4370845690665974, | |
| "learning_rate": 8.620071327057833e-06, | |
| "loss": 0.22411692, | |
| "memory(GiB)": 100.58, | |
| "step": 155, | |
| "train_speed(iter/s)": 0.314364 | |
| }, | |
| { | |
| "acc": 0.91105995, | |
| "epoch": 1.16, | |
| "grad_norm": 4.474578962221848, | |
| "learning_rate": 8.514258087470745e-06, | |
| "loss": 0.22455444, | |
| "memory(GiB)": 100.58, | |
| "step": 160, | |
| "train_speed(iter/s)": 0.315941 | |
| }, | |
| { | |
| "acc": 0.92596989, | |
| "epoch": 1.1963636363636363, | |
| "grad_norm": 2.27714865436083, | |
| "learning_rate": 8.405238786004592e-06, | |
| "loss": 0.19618599, | |
| "memory(GiB)": 100.58, | |
| "step": 165, | |
| "train_speed(iter/s)": 0.317423 | |
| }, | |
| { | |
| "acc": 0.91807003, | |
| "epoch": 1.2327272727272727, | |
| "grad_norm": 3.476526282944283, | |
| "learning_rate": 8.293112895251915e-06, | |
| "loss": 0.21812358, | |
| "memory(GiB)": 100.58, | |
| "step": 170, | |
| "train_speed(iter/s)": 0.318837 | |
| }, | |
| { | |
| "acc": 0.91757879, | |
| "epoch": 1.269090909090909, | |
| "grad_norm": 2.812345046742586, | |
| "learning_rate": 8.177982722353686e-06, | |
| "loss": 0.20932765, | |
| "memory(GiB)": 100.58, | |
| "step": 175, | |
| "train_speed(iter/s)": 0.319897 | |
| }, | |
| { | |
| "acc": 0.9130724, | |
| "epoch": 1.3054545454545454, | |
| "grad_norm": 1.909403498812979, | |
| "learning_rate": 8.059953315651102e-06, | |
| "loss": 0.22100675, | |
| "memory(GiB)": 100.58, | |
| "step": 180, | |
| "train_speed(iter/s)": 0.320821 | |
| }, | |
| { | |
| "acc": 0.91083689, | |
| "epoch": 1.3418181818181818, | |
| "grad_norm": 3.7534483781265853, | |
| "learning_rate": 7.93913236883622e-06, | |
| "loss": 0.22075479, | |
| "memory(GiB)": 100.58, | |
| "step": 185, | |
| "train_speed(iter/s)": 0.321724 | |
| }, | |
| { | |
| "acc": 0.90749474, | |
| "epoch": 1.3781818181818182, | |
| "grad_norm": 3.0657460772043805, | |
| "learning_rate": 7.815630122688893e-06, | |
| "loss": 0.22630196, | |
| "memory(GiB)": 100.58, | |
| "step": 190, | |
| "train_speed(iter/s)": 0.3226 | |
| }, | |
| { | |
| "acc": 0.92584915, | |
| "epoch": 1.4145454545454546, | |
| "grad_norm": 5.821099128946982, | |
| "learning_rate": 7.689559264489661e-06, | |
| "loss": 0.21087196, | |
| "memory(GiB)": 100.58, | |
| "step": 195, | |
| "train_speed(iter/s)": 0.32333 | |
| }, | |
| { | |
| "acc": 0.90973835, | |
| "epoch": 1.450909090909091, | |
| "grad_norm": 1.830285233435649, | |
| "learning_rate": 7.5610348252003814e-06, | |
| "loss": 0.24081864, | |
| "memory(GiB)": 100.58, | |
| "step": 200, | |
| "train_speed(iter/s)": 0.323755 | |
| }, | |
| { | |
| "acc": 0.91908627, | |
| "epoch": 1.4872727272727273, | |
| "grad_norm": 3.46434543645635, | |
| "learning_rate": 7.43017407450641e-06, | |
| "loss": 0.21430855, | |
| "memory(GiB)": 100.58, | |
| "step": 205, | |
| "train_speed(iter/s)": 0.324304 | |
| }, | |
| { | |
| "acc": 0.90855217, | |
| "epoch": 1.5236363636363637, | |
| "grad_norm": 1.6445934060533671, | |
| "learning_rate": 7.2970964138161006e-06, | |
| "loss": 0.2204694, | |
| "memory(GiB)": 100.58, | |
| "step": 210, | |
| "train_speed(iter/s)": 0.325137 | |
| }, | |
| { | |
| "acc": 0.9202652, | |
| "epoch": 1.56, | |
| "grad_norm": 2.685739587728944, | |
| "learning_rate": 7.161923267315262e-06, | |
| "loss": 0.20784543, | |
| "memory(GiB)": 100.58, | |
| "step": 215, | |
| "train_speed(iter/s)": 0.325877 | |
| }, | |
| { | |
| "acc": 0.92430801, | |
| "epoch": 1.5963636363636362, | |
| "grad_norm": 3.4665236755524202, | |
| "learning_rate": 7.0247779711759566e-06, | |
| "loss": 0.2091445, | |
| "memory(GiB)": 100.58, | |
| "step": 220, | |
| "train_speed(iter/s)": 0.326598 | |
| }, | |
| { | |
| "acc": 0.91858587, | |
| "epoch": 1.6327272727272728, | |
| "grad_norm": 3.0400419237318674, | |
| "learning_rate": 6.885785661020759e-06, | |
| "loss": 0.22234173, | |
| "memory(GiB)": 100.58, | |
| "step": 225, | |
| "train_speed(iter/s)": 0.32754 | |
| }, | |
| { | |
| "acc": 0.91896229, | |
| "epoch": 1.669090909090909, | |
| "grad_norm": 2.50023791606214, | |
| "learning_rate": 6.7450731577451255e-06, | |
| "loss": 0.20558548, | |
| "memory(GiB)": 100.58, | |
| "step": 230, | |
| "train_speed(iter/s)": 0.328407 | |
| }, | |
| { | |
| "acc": 0.92307997, | |
| "epoch": 1.7054545454545456, | |
| "grad_norm": 2.789509587118081, | |
| "learning_rate": 6.602768851802077e-06, | |
| "loss": 0.21382501, | |
| "memory(GiB)": 100.58, | |
| "step": 235, | |
| "train_speed(iter/s)": 0.329247 | |
| }, | |
| { | |
| "acc": 0.91400127, | |
| "epoch": 1.7418181818181817, | |
| "grad_norm": 2.3889266426439173, | |
| "learning_rate": 6.45900258605477e-06, | |
| "loss": 0.21889751, | |
| "memory(GiB)": 100.58, | |
| "step": 240, | |
| "train_speed(iter/s)": 0.330086 | |
| }, | |
| { | |
| "acc": 0.90683708, | |
| "epoch": 1.7781818181818183, | |
| "grad_norm": 3.3107240552086465, | |
| "learning_rate": 6.313905537303837e-06, | |
| "loss": 0.21690502, | |
| "memory(GiB)": 100.58, | |
| "step": 245, | |
| "train_speed(iter/s)": 0.330898 | |
| }, | |
| { | |
| "acc": 0.91603336, | |
| "epoch": 1.8145454545454545, | |
| "grad_norm": 2.8852486239120547, | |
| "learning_rate": 6.167610096597601e-06, | |
| "loss": 0.2154119, | |
| "memory(GiB)": 100.58, | |
| "step": 250, | |
| "train_speed(iter/s)": 0.331673 | |
| }, | |
| { | |
| "acc": 0.91818409, | |
| "epoch": 1.850909090909091, | |
| "grad_norm": 2.0440810660323585, | |
| "learning_rate": 6.020249748434384e-06, | |
| "loss": 0.21951377, | |
| "memory(GiB)": 100.58, | |
| "step": 255, | |
| "train_speed(iter/s)": 0.332356 | |
| }, | |
| { | |
| "acc": 0.90970173, | |
| "epoch": 1.8872727272727272, | |
| "grad_norm": 3.8117037313040574, | |
| "learning_rate": 5.871958948967106e-06, | |
| "loss": 0.23594971, | |
| "memory(GiB)": 100.58, | |
| "step": 260, | |
| "train_speed(iter/s)": 0.33293 | |
| }, | |
| { | |
| "acc": 0.92123165, | |
| "epoch": 1.9236363636363636, | |
| "grad_norm": 3.4855685769436375, | |
| "learning_rate": 5.722873003321322e-06, | |
| "loss": 0.21117101, | |
| "memory(GiB)": 100.58, | |
| "step": 265, | |
| "train_speed(iter/s)": 0.333662 | |
| }, | |
| { | |
| "acc": 0.91777382, | |
| "epoch": 1.96, | |
| "grad_norm": 2.497000906964384, | |
| "learning_rate": 5.573127942138622e-06, | |
| "loss": 0.21624155, | |
| "memory(GiB)": 100.58, | |
| "step": 270, | |
| "train_speed(iter/s)": 0.334225 | |
| }, | |
| { | |
| "acc": 0.9166666, | |
| "epoch": 1.9963636363636363, | |
| "grad_norm": 4.782654736901845, | |
| "learning_rate": 5.422860397458064e-06, | |
| "loss": 0.21392875, | |
| "memory(GiB)": 100.58, | |
| "step": 275, | |
| "train_speed(iter/s)": 0.334671 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_acc": 0.9098730028676771, | |
| "eval_loss": 0.2191523164510727, | |
| "eval_runtime": 10.1618, | |
| "eval_samples_per_second": 11.415, | |
| "eval_steps_per_second": 1.476, | |
| "step": 276 | |
| }, | |
| { | |
| "acc": 0.84443541, | |
| "epoch": 2.0290909090909093, | |
| "grad_norm": 3.015403395241152, | |
| "learning_rate": 5.27220747804885e-06, | |
| "loss": 0.17099829, | |
| "memory(GiB)": 100.58, | |
| "step": 280, | |
| "train_speed(iter/s)": 0.317633 | |
| }, | |
| { | |
| "acc": 0.93253222, | |
| "epoch": 2.0654545454545454, | |
| "grad_norm": 2.167435558475328, | |
| "learning_rate": 5.121306644308045e-06, | |
| "loss": 0.18818057, | |
| "memory(GiB)": 100.58, | |
| "step": 285, | |
| "train_speed(iter/s)": 0.3185 | |
| }, | |
| { | |
| "acc": 0.94647446, | |
| "epoch": 2.101818181818182, | |
| "grad_norm": 2.1487311628542898, | |
| "learning_rate": 4.9702955828374385e-06, | |
| "loss": 0.15134431, | |
| "memory(GiB)": 100.58, | |
| "step": 290, | |
| "train_speed(iter/s)": 0.319277 | |
| }, | |
| { | |
| "acc": 0.93036728, | |
| "epoch": 2.138181818181818, | |
| "grad_norm": 4.174051904681519, | |
| "learning_rate": 4.8193120808140185e-06, | |
| "loss": 0.16832316, | |
| "memory(GiB)": 100.58, | |
| "step": 295, | |
| "train_speed(iter/s)": 0.320077 | |
| }, | |
| { | |
| "acc": 0.93621769, | |
| "epoch": 2.174545454545455, | |
| "grad_norm": 2.3866390406657896, | |
| "learning_rate": 4.668493900268684e-06, | |
| "loss": 0.16947901, | |
| "memory(GiB)": 100.58, | |
| "step": 300, | |
| "train_speed(iter/s)": 0.320854 | |
| }, | |
| { | |
| "acc": 0.93184824, | |
| "epoch": 2.210909090909091, | |
| "grad_norm": 2.7745369730901595, | |
| "learning_rate": 4.517978652387882e-06, | |
| "loss": 0.16975009, | |
| "memory(GiB)": 100.58, | |
| "step": 305, | |
| "train_speed(iter/s)": 0.321626 | |
| }, | |
| { | |
| "acc": 0.93711929, | |
| "epoch": 2.247272727272727, | |
| "grad_norm": 4.606104787695004, | |
| "learning_rate": 4.367903671952906e-06, | |
| "loss": 0.16885712, | |
| "memory(GiB)": 100.58, | |
| "step": 310, | |
| "train_speed(iter/s)": 0.322203 | |
| }, | |
| { | |
| "acc": 0.93099174, | |
| "epoch": 2.2836363636363637, | |
| "grad_norm": 8.944877147631175, | |
| "learning_rate": 4.218405892031366e-06, | |
| "loss": 0.17090337, | |
| "memory(GiB)": 100.58, | |
| "step": 315, | |
| "train_speed(iter/s)": 0.322833 | |
| }, | |
| { | |
| "acc": 0.93137035, | |
| "epoch": 2.32, | |
| "grad_norm": 4.336121777570645, | |
| "learning_rate": 4.069621719035229e-06, | |
| "loss": 0.1658249, | |
| "memory(GiB)": 100.58, | |
| "step": 320, | |
| "train_speed(iter/s)": 0.323508 | |
| }, | |
| { | |
| "acc": 0.9393259, | |
| "epoch": 2.3563636363636364, | |
| "grad_norm": 6.921537975970479, | |
| "learning_rate": 3.921686908259354e-06, | |
| "loss": 0.15576041, | |
| "memory(GiB)": 100.58, | |
| "step": 325, | |
| "train_speed(iter/s)": 0.324182 | |
| }, | |
| { | |
| "acc": 0.93962708, | |
| "epoch": 2.3927272727272726, | |
| "grad_norm": 3.5886891547630877, | |
| "learning_rate": 3.7747364400141726e-06, | |
| "loss": 0.16867373, | |
| "memory(GiB)": 100.58, | |
| "step": 330, | |
| "train_speed(iter/s)": 0.324849 | |
| }, | |
| { | |
| "acc": 0.93609505, | |
| "epoch": 2.429090909090909, | |
| "grad_norm": 2.686999433312404, | |
| "learning_rate": 3.6289043964654526e-06, | |
| "loss": 0.15810946, | |
| "memory(GiB)": 100.58, | |
| "step": 335, | |
| "train_speed(iter/s)": 0.325493 | |
| }, | |
| { | |
| "acc": 0.92649899, | |
| "epoch": 2.4654545454545453, | |
| "grad_norm": 2.591872854237207, | |
| "learning_rate": 3.484323839293575e-06, | |
| "loss": 0.17918372, | |
| "memory(GiB)": 100.58, | |
| "step": 340, | |
| "train_speed(iter/s)": 0.326123 | |
| }, | |
| { | |
| "acc": 0.93626881, | |
| "epoch": 2.501818181818182, | |
| "grad_norm": 2.5738296672570233, | |
| "learning_rate": 3.341126688283922e-06, | |
| "loss": 0.16855428, | |
| "memory(GiB)": 100.58, | |
| "step": 345, | |
| "train_speed(iter/s)": 0.326743 | |
| }, | |
| { | |
| "acc": 0.93825417, | |
| "epoch": 2.538181818181818, | |
| "grad_norm": 2.7529925608546466, | |
| "learning_rate": 3.19944360095919e-06, | |
| "loss": 0.16165339, | |
| "memory(GiB)": 100.58, | |
| "step": 350, | |
| "train_speed(iter/s)": 0.327363 | |
| }, | |
| { | |
| "acc": 0.94702225, | |
| "epoch": 2.5745454545454547, | |
| "grad_norm": 2.9545927202945315, | |
| "learning_rate": 3.059403853363393e-06, | |
| "loss": 0.14523516, | |
| "memory(GiB)": 100.58, | |
| "step": 355, | |
| "train_speed(iter/s)": 0.327926 | |
| }, | |
| { | |
| "acc": 0.94346981, | |
| "epoch": 2.610909090909091, | |
| "grad_norm": 4.047109124196383, | |
| "learning_rate": 2.9211352221063987e-06, | |
| "loss": 0.14715908, | |
| "memory(GiB)": 100.58, | |
| "step": 360, | |
| "train_speed(iter/s)": 0.328285 | |
| }, | |
| { | |
| "acc": 0.94318542, | |
| "epoch": 2.6472727272727274, | |
| "grad_norm": 2.3923230638690143, | |
| "learning_rate": 2.7847638677765936e-06, | |
| "loss": 0.1494684, | |
| "memory(GiB)": 100.58, | |
| "step": 365, | |
| "train_speed(iter/s)": 0.328722 | |
| }, | |
| { | |
| "acc": 0.95623245, | |
| "epoch": 2.6836363636363636, | |
| "grad_norm": 2.457260493406828, | |
| "learning_rate": 2.650414219828032e-06, | |
| "loss": 0.11759402, | |
| "memory(GiB)": 100.58, | |
| "step": 370, | |
| "train_speed(iter/s)": 0.329264 | |
| }, | |
| { | |
| "acc": 0.94435921, | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 1.5322367904545142, | |
| "learning_rate": 2.5182088630471517e-06, | |
| "loss": 0.13577256, | |
| "memory(GiB)": 100.58, | |
| "step": 375, | |
| "train_speed(iter/s)": 0.329788 | |
| }, | |
| { | |
| "acc": 0.94585953, | |
| "epoch": 2.7563636363636363, | |
| "grad_norm": 2.8650025435958666, | |
| "learning_rate": 2.388268425702614e-06, | |
| "loss": 0.14076474, | |
| "memory(GiB)": 100.58, | |
| "step": 380, | |
| "train_speed(iter/s)": 0.330302 | |
| }, | |
| { | |
| "acc": 0.9413455, | |
| "epoch": 2.792727272727273, | |
| "grad_norm": 4.510750432829035, | |
| "learning_rate": 2.2607114694803263e-06, | |
| "loss": 0.1642381, | |
| "memory(GiB)": 100.58, | |
| "step": 385, | |
| "train_speed(iter/s)": 0.330731 | |
| }, | |
| { | |
| "acc": 0.93006382, | |
| "epoch": 2.829090909090909, | |
| "grad_norm": 2.908591189518448, | |
| "learning_rate": 2.1356543813040863e-06, | |
| "loss": 0.17094066, | |
| "memory(GiB)": 100.58, | |
| "step": 390, | |
| "train_speed(iter/s)": 0.331119 | |
| }, | |
| { | |
| "acc": 0.94227448, | |
| "epoch": 2.8654545454545453, | |
| "grad_norm": 2.331626905910975, | |
| "learning_rate": 2.0132112671405244e-06, | |
| "loss": 0.14904225, | |
| "memory(GiB)": 100.58, | |
| "step": 395, | |
| "train_speed(iter/s)": 0.331532 | |
| }, | |
| { | |
| "acc": 0.93090382, | |
| "epoch": 2.901818181818182, | |
| "grad_norm": 4.223665768837086, | |
| "learning_rate": 1.8934938478853108e-06, | |
| "loss": 0.17768097, | |
| "memory(GiB)": 100.58, | |
| "step": 400, | |
| "train_speed(iter/s)": 0.331963 | |
| }, | |
| { | |
| "acc": 0.93722563, | |
| "epoch": 2.9381818181818184, | |
| "grad_norm": 2.7247775486261734, | |
| "learning_rate": 1.7766113574255145e-06, | |
| "loss": 0.15059752, | |
| "memory(GiB)": 100.58, | |
| "step": 405, | |
| "train_speed(iter/s)": 0.332266 | |
| }, | |
| { | |
| "acc": 0.94374504, | |
| "epoch": 2.9745454545454546, | |
| "grad_norm": 2.9951618135706055, | |
| "learning_rate": 1.6626704429712411e-06, | |
| "loss": 0.14953468, | |
| "memory(GiB)": 100.58, | |
| "step": 410, | |
| "train_speed(iter/s)": 0.332599 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_acc": 0.9192953707496927, | |
| "eval_loss": 0.21225064992904663, | |
| "eval_runtime": 9.5239, | |
| "eval_samples_per_second": 12.18, | |
| "eval_steps_per_second": 1.575, | |
| "step": 414 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.931788793840435e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |