| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.995083579154375, |
| "eval_steps": 100, |
| "global_step": 635, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03933136676499508, |
| "grad_norm": 0.481609046459198, |
| "learning_rate": 0.00015, |
| "loss": 2.0722, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.07866273352999016, |
| "grad_norm": 0.15720224380493164, |
| "learning_rate": 0.0003, |
| "loss": 1.4825, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.11799410029498525, |
| "grad_norm": 0.06716315448284149, |
| "learning_rate": 0.00029759999999999997, |
| "loss": 1.3333, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.15732546705998032, |
| "grad_norm": 0.06133478134870529, |
| "learning_rate": 0.00029519999999999997, |
| "loss": 1.2341, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.19665683382497542, |
| "grad_norm": 0.07264667749404907, |
| "learning_rate": 0.00029279999999999996, |
| "loss": 1.1756, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2359882005899705, |
| "grad_norm": 0.07928217202425003, |
| "learning_rate": 0.00029039999999999996, |
| "loss": 1.1197, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2753195673549656, |
| "grad_norm": 0.09420346468687057, |
| "learning_rate": 0.00028799999999999995, |
| "loss": 1.0834, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.31465093411996065, |
| "grad_norm": 0.0862259566783905, |
| "learning_rate": 0.00028559999999999995, |
| "loss": 1.044, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.35398230088495575, |
| "grad_norm": 0.09086894243955612, |
| "learning_rate": 0.00028319999999999994, |
| "loss": 1.0205, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.39331366764995085, |
| "grad_norm": 0.08469890058040619, |
| "learning_rate": 0.0002808, |
| "loss": 0.9798, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4326450344149459, |
| "grad_norm": 0.10012397915124893, |
| "learning_rate": 0.0002784, |
| "loss": 0.9811, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.471976401179941, |
| "grad_norm": 0.08633492887020111, |
| "learning_rate": 0.000276, |
| "loss": 0.9556, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.511307767944936, |
| "grad_norm": 0.09879346191883087, |
| "learning_rate": 0.0002736, |
| "loss": 0.9446, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5506391347099312, |
| "grad_norm": 0.08795857429504395, |
| "learning_rate": 0.0002712, |
| "loss": 0.9228, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5899705014749262, |
| "grad_norm": 0.0837111845612526, |
| "learning_rate": 0.0002688, |
| "loss": 0.9279, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6293018682399213, |
| "grad_norm": 0.08551318198442459, |
| "learning_rate": 0.00026639999999999997, |
| "loss": 0.9267, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6686332350049164, |
| "grad_norm": 0.08481767773628235, |
| "learning_rate": 0.00026399999999999997, |
| "loss": 0.9082, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7079646017699115, |
| "grad_norm": 0.100365050137043, |
| "learning_rate": 0.00026159999999999996, |
| "loss": 0.9028, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7472959685349065, |
| "grad_norm": 0.08463772386312485, |
| "learning_rate": 0.00025919999999999996, |
| "loss": 0.8866, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.7866273352999017, |
| "grad_norm": 0.09628409892320633, |
| "learning_rate": 0.00025679999999999995, |
| "loss": 0.8787, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7866273352999017, |
| "eval_loss": 0.8853636980056763, |
| "eval_runtime": 24.3719, |
| "eval_samples_per_second": 6.729, |
| "eval_steps_per_second": 0.862, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8259587020648967, |
| "grad_norm": 0.08835043758153915, |
| "learning_rate": 0.00025439999999999995, |
| "loss": 0.8786, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.8652900688298918, |
| "grad_norm": 0.09190791845321655, |
| "learning_rate": 0.00025199999999999995, |
| "loss": 0.8693, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.904621435594887, |
| "grad_norm": 0.08965795487165451, |
| "learning_rate": 0.00024959999999999994, |
| "loss": 0.8772, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.943952802359882, |
| "grad_norm": 0.09055910259485245, |
| "learning_rate": 0.0002472, |
| "loss": 0.867, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.983284169124877, |
| "grad_norm": 0.09172637015581131, |
| "learning_rate": 0.0002448, |
| "loss": 0.8536, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.022615535889872, |
| "grad_norm": 0.10374542325735092, |
| "learning_rate": 0.00024239999999999998, |
| "loss": 0.9888, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.0619469026548674, |
| "grad_norm": 0.08842068910598755, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.8443, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.1012782694198624, |
| "grad_norm": 0.0736837387084961, |
| "learning_rate": 0.0002376, |
| "loss": 0.8457, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.1406096361848574, |
| "grad_norm": 0.07575016468763351, |
| "learning_rate": 0.0002352, |
| "loss": 0.8335, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.1799410029498525, |
| "grad_norm": 0.07092955708503723, |
| "learning_rate": 0.0002328, |
| "loss": 0.8246, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2192723697148475, |
| "grad_norm": 0.077423095703125, |
| "learning_rate": 0.0002304, |
| "loss": 0.823, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.2586037364798428, |
| "grad_norm": 0.07389391213655472, |
| "learning_rate": 0.00022799999999999999, |
| "loss": 0.819, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.2979351032448379, |
| "grad_norm": 0.08229434490203857, |
| "learning_rate": 0.00022559999999999998, |
| "loss": 0.8181, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.337266470009833, |
| "grad_norm": 0.07665972411632538, |
| "learning_rate": 0.00022319999999999998, |
| "loss": 0.8118, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.376597836774828, |
| "grad_norm": 0.09001573175191879, |
| "learning_rate": 0.00022079999999999997, |
| "loss": 0.8157, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.415929203539823, |
| "grad_norm": 0.07965826243162155, |
| "learning_rate": 0.00021839999999999997, |
| "loss": 0.8111, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.455260570304818, |
| "grad_norm": 0.08642959594726562, |
| "learning_rate": 0.00021599999999999996, |
| "loss": 0.8003, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.494591937069813, |
| "grad_norm": 0.0749087929725647, |
| "learning_rate": 0.00021359999999999996, |
| "loss": 0.7975, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.5339233038348081, |
| "grad_norm": 0.08575734496116638, |
| "learning_rate": 0.00021119999999999996, |
| "loss": 0.7888, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.5732546705998034, |
| "grad_norm": 0.0887129157781601, |
| "learning_rate": 0.00020879999999999998, |
| "loss": 0.7857, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.5732546705998034, |
| "eval_loss": 0.8026237487792969, |
| "eval_runtime": 24.2397, |
| "eval_samples_per_second": 6.766, |
| "eval_steps_per_second": 0.866, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6125860373647984, |
| "grad_norm": 0.0926935002207756, |
| "learning_rate": 0.00020639999999999998, |
| "loss": 0.7877, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.6519174041297935, |
| "grad_norm": 0.08537031710147858, |
| "learning_rate": 0.000204, |
| "loss": 0.7767, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.6912487708947888, |
| "grad_norm": 0.0766814798116684, |
| "learning_rate": 0.0002016, |
| "loss": 0.785, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.7305801376597838, |
| "grad_norm": 0.08394207805395126, |
| "learning_rate": 0.0001992, |
| "loss": 0.7832, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.7699115044247788, |
| "grad_norm": 0.0813060775399208, |
| "learning_rate": 0.00019679999999999999, |
| "loss": 0.7766, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.809242871189774, |
| "grad_norm": 0.08242856711149216, |
| "learning_rate": 0.00019439999999999998, |
| "loss": 0.7775, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.848574237954769, |
| "grad_norm": 0.07610878348350525, |
| "learning_rate": 0.00019199999999999998, |
| "loss": 0.7736, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.887905604719764, |
| "grad_norm": 0.08326178044080734, |
| "learning_rate": 0.00018959999999999997, |
| "loss": 0.7753, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.927236971484759, |
| "grad_norm": 0.09425383061170578, |
| "learning_rate": 0.0001872, |
| "loss": 0.7577, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.966568338249754, |
| "grad_norm": 0.08694498240947723, |
| "learning_rate": 0.0001848, |
| "loss": 0.7606, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.005899705014749, |
| "grad_norm": 0.22805309295654297, |
| "learning_rate": 0.0001824, |
| "loss": 0.8871, |
| "step": 255 |
| }, |
| { |
| "epoch": 2.045231071779744, |
| "grad_norm": 0.09610473364591599, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.7315, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.084562438544739, |
| "grad_norm": 0.09666857868432999, |
| "learning_rate": 0.00017759999999999998, |
| "loss": 0.7315, |
| "step": 265 |
| }, |
| { |
| "epoch": 2.1238938053097347, |
| "grad_norm": 0.09328849613666534, |
| "learning_rate": 0.00017519999999999998, |
| "loss": 0.7344, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.1632251720747298, |
| "grad_norm": 0.08137473464012146, |
| "learning_rate": 0.00017279999999999997, |
| "loss": 0.7347, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.202556538839725, |
| "grad_norm": 0.08166103810071945, |
| "learning_rate": 0.00017039999999999997, |
| "loss": 0.7281, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.24188790560472, |
| "grad_norm": 0.08074019104242325, |
| "learning_rate": 0.000168, |
| "loss": 0.7345, |
| "step": 285 |
| }, |
| { |
| "epoch": 2.281219272369715, |
| "grad_norm": 0.08479057997465134, |
| "learning_rate": 0.0001656, |
| "loss": 0.726, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.32055063913471, |
| "grad_norm": 0.08091601729393005, |
| "learning_rate": 0.0001632, |
| "loss": 0.7184, |
| "step": 295 |
| }, |
| { |
| "epoch": 2.359882005899705, |
| "grad_norm": 0.08470489084720612, |
| "learning_rate": 0.0001608, |
| "loss": 0.7233, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.359882005899705, |
| "eval_loss": 0.7612683176994324, |
| "eval_runtime": 24.27, |
| "eval_samples_per_second": 6.757, |
| "eval_steps_per_second": 0.865, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.3992133726647, |
| "grad_norm": 0.08677177131175995, |
| "learning_rate": 0.0001584, |
| "loss": 0.721, |
| "step": 305 |
| }, |
| { |
| "epoch": 2.438544739429695, |
| "grad_norm": 0.08474377542734146, |
| "learning_rate": 0.000156, |
| "loss": 0.7141, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.47787610619469, |
| "grad_norm": 0.08565227687358856, |
| "learning_rate": 0.0001536, |
| "loss": 0.7173, |
| "step": 315 |
| }, |
| { |
| "epoch": 2.5172074729596856, |
| "grad_norm": 0.08714301139116287, |
| "learning_rate": 0.0001512, |
| "loss": 0.7274, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.5565388397246807, |
| "grad_norm": 0.0934271439909935, |
| "learning_rate": 0.00014879999999999998, |
| "loss": 0.7263, |
| "step": 325 |
| }, |
| { |
| "epoch": 2.5958702064896757, |
| "grad_norm": 0.08581375330686569, |
| "learning_rate": 0.00014639999999999998, |
| "loss": 0.7248, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.6352015732546707, |
| "grad_norm": 0.08378680050373077, |
| "learning_rate": 0.00014399999999999998, |
| "loss": 0.721, |
| "step": 335 |
| }, |
| { |
| "epoch": 2.674532940019666, |
| "grad_norm": 0.08449660986661911, |
| "learning_rate": 0.00014159999999999997, |
| "loss": 0.7156, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.713864306784661, |
| "grad_norm": 0.08646751940250397, |
| "learning_rate": 0.0001392, |
| "loss": 0.7094, |
| "step": 345 |
| }, |
| { |
| "epoch": 2.753195673549656, |
| "grad_norm": 0.08911272883415222, |
| "learning_rate": 0.0001368, |
| "loss": 0.709, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.792527040314651, |
| "grad_norm": 0.0970829427242279, |
| "learning_rate": 0.0001344, |
| "loss": 0.7107, |
| "step": 355 |
| }, |
| { |
| "epoch": 2.831858407079646, |
| "grad_norm": 0.0854572132229805, |
| "learning_rate": 0.00013199999999999998, |
| "loss": 0.7148, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.871189773844641, |
| "grad_norm": 0.08210612088441849, |
| "learning_rate": 0.00012959999999999998, |
| "loss": 0.7132, |
| "step": 365 |
| }, |
| { |
| "epoch": 2.910521140609636, |
| "grad_norm": 0.0925467386841774, |
| "learning_rate": 0.00012719999999999997, |
| "loss": 0.7201, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.949852507374631, |
| "grad_norm": 0.09149914979934692, |
| "learning_rate": 0.00012479999999999997, |
| "loss": 0.7086, |
| "step": 375 |
| }, |
| { |
| "epoch": 2.989183874139626, |
| "grad_norm": 0.0827464610338211, |
| "learning_rate": 0.0001224, |
| "loss": 0.7102, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.0285152409046217, |
| "grad_norm": 0.09861475974321365, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.8086, |
| "step": 385 |
| }, |
| { |
| "epoch": 3.0678466076696167, |
| "grad_norm": 0.09810496121644974, |
| "learning_rate": 0.0001176, |
| "loss": 0.6784, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.1071779744346117, |
| "grad_norm": 0.08657824248075485, |
| "learning_rate": 0.0001152, |
| "loss": 0.6818, |
| "step": 395 |
| }, |
| { |
| "epoch": 3.146509341199607, |
| "grad_norm": 0.08861815184354782, |
| "learning_rate": 0.00011279999999999999, |
| "loss": 0.6755, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.146509341199607, |
| "eval_loss": 0.7408613562583923, |
| "eval_runtime": 24.2895, |
| "eval_samples_per_second": 6.752, |
| "eval_steps_per_second": 0.865, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.185840707964602, |
| "grad_norm": 0.09166675060987473, |
| "learning_rate": 0.00011039999999999999, |
| "loss": 0.6797, |
| "step": 405 |
| }, |
| { |
| "epoch": 3.225172074729597, |
| "grad_norm": 0.08929497748613358, |
| "learning_rate": 0.00010799999999999998, |
| "loss": 0.6803, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.264503441494592, |
| "grad_norm": 0.08206567913293839, |
| "learning_rate": 0.00010559999999999998, |
| "loss": 0.674, |
| "step": 415 |
| }, |
| { |
| "epoch": 3.303834808259587, |
| "grad_norm": 0.08605019748210907, |
| "learning_rate": 0.00010319999999999999, |
| "loss": 0.671, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.343166175024582, |
| "grad_norm": 0.09013310074806213, |
| "learning_rate": 0.0001008, |
| "loss": 0.6741, |
| "step": 425 |
| }, |
| { |
| "epoch": 3.382497541789577, |
| "grad_norm": 0.08961386978626251, |
| "learning_rate": 9.839999999999999e-05, |
| "loss": 0.6788, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.421828908554572, |
| "grad_norm": 0.08613158762454987, |
| "learning_rate": 9.599999999999999e-05, |
| "loss": 0.6681, |
| "step": 435 |
| }, |
| { |
| "epoch": 3.4611602753195676, |
| "grad_norm": 0.08968936651945114, |
| "learning_rate": 9.36e-05, |
| "loss": 0.6726, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.5004916420845626, |
| "grad_norm": 0.0898197814822197, |
| "learning_rate": 9.12e-05, |
| "loss": 0.6693, |
| "step": 445 |
| }, |
| { |
| "epoch": 3.5398230088495577, |
| "grad_norm": 0.09239344298839569, |
| "learning_rate": 8.879999999999999e-05, |
| "loss": 0.6648, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.5791543756145527, |
| "grad_norm": 0.08533533662557602, |
| "learning_rate": 8.639999999999999e-05, |
| "loss": 0.6659, |
| "step": 455 |
| }, |
| { |
| "epoch": 3.618485742379548, |
| "grad_norm": 0.08410927653312683, |
| "learning_rate": 8.4e-05, |
| "loss": 0.6725, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.657817109144543, |
| "grad_norm": 0.08881025016307831, |
| "learning_rate": 8.16e-05, |
| "loss": 0.67, |
| "step": 465 |
| }, |
| { |
| "epoch": 3.697148475909538, |
| "grad_norm": 0.08324339985847473, |
| "learning_rate": 7.92e-05, |
| "loss": 0.6722, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.736479842674533, |
| "grad_norm": 0.09193731844425201, |
| "learning_rate": 7.68e-05, |
| "loss": 0.6689, |
| "step": 475 |
| }, |
| { |
| "epoch": 3.775811209439528, |
| "grad_norm": 0.0902351662516594, |
| "learning_rate": 7.439999999999999e-05, |
| "loss": 0.6784, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.815142576204523, |
| "grad_norm": 0.08959916979074478, |
| "learning_rate": 7.199999999999999e-05, |
| "loss": 0.6808, |
| "step": 485 |
| }, |
| { |
| "epoch": 3.854473942969518, |
| "grad_norm": 0.0888456478714943, |
| "learning_rate": 6.96e-05, |
| "loss": 0.6703, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.893805309734513, |
| "grad_norm": 0.08982842415571213, |
| "learning_rate": 6.72e-05, |
| "loss": 0.675, |
| "step": 495 |
| }, |
| { |
| "epoch": 3.933136676499508, |
| "grad_norm": 0.0874968022108078, |
| "learning_rate": 6.479999999999999e-05, |
| "loss": 0.6673, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.933136676499508, |
| "eval_loss": 0.726395308971405, |
| "eval_runtime": 24.2191, |
| "eval_samples_per_second": 6.772, |
| "eval_steps_per_second": 0.867, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.972468043264503, |
| "grad_norm": 0.08432712405920029, |
| "learning_rate": 6.239999999999999e-05, |
| "loss": 0.6747, |
| "step": 505 |
| }, |
| { |
| "epoch": 4.011799410029498, |
| "grad_norm": 0.09498456120491028, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.7806, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.051130776794493, |
| "grad_norm": 0.09371250122785568, |
| "learning_rate": 5.76e-05, |
| "loss": 0.6417, |
| "step": 515 |
| }, |
| { |
| "epoch": 4.090462143559488, |
| "grad_norm": 0.09341807663440704, |
| "learning_rate": 5.519999999999999e-05, |
| "loss": 0.6399, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.129793510324483, |
| "grad_norm": 0.08755338191986084, |
| "learning_rate": 5.279999999999999e-05, |
| "loss": 0.6408, |
| "step": 525 |
| }, |
| { |
| "epoch": 4.169124877089478, |
| "grad_norm": 0.08822200447320938, |
| "learning_rate": 5.04e-05, |
| "loss": 0.6407, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.208456243854474, |
| "grad_norm": 0.08952053636312485, |
| "learning_rate": 4.7999999999999994e-05, |
| "loss": 0.645, |
| "step": 535 |
| }, |
| { |
| "epoch": 4.247787610619469, |
| "grad_norm": 0.0895063579082489, |
| "learning_rate": 4.56e-05, |
| "loss": 0.6409, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.2871189773844645, |
| "grad_norm": 0.08820494264364243, |
| "learning_rate": 4.319999999999999e-05, |
| "loss": 0.6422, |
| "step": 545 |
| }, |
| { |
| "epoch": 4.3264503441494595, |
| "grad_norm": 0.08639927208423615, |
| "learning_rate": 4.08e-05, |
| "loss": 0.6476, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.3657817109144545, |
| "grad_norm": 0.08915071934461594, |
| "learning_rate": 3.84e-05, |
| "loss": 0.6389, |
| "step": 555 |
| }, |
| { |
| "epoch": 4.40511307767945, |
| "grad_norm": 0.08612582087516785, |
| "learning_rate": 3.5999999999999994e-05, |
| "loss": 0.6401, |
| "step": 560 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.08792046457529068, |
| "learning_rate": 3.36e-05, |
| "loss": 0.6479, |
| "step": 565 |
| }, |
| { |
| "epoch": 4.48377581120944, |
| "grad_norm": 0.08458750694990158, |
| "learning_rate": 3.119999999999999e-05, |
| "loss": 0.6448, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.523107177974435, |
| "grad_norm": 0.0890946015715599, |
| "learning_rate": 2.88e-05, |
| "loss": 0.6441, |
| "step": 575 |
| }, |
| { |
| "epoch": 4.56243854473943, |
| "grad_norm": 0.08621781319379807, |
| "learning_rate": 2.6399999999999995e-05, |
| "loss": 0.6422, |
| "step": 580 |
| }, |
| { |
| "epoch": 4.601769911504425, |
| "grad_norm": 0.08367058634757996, |
| "learning_rate": 2.3999999999999997e-05, |
| "loss": 0.6479, |
| "step": 585 |
| }, |
| { |
| "epoch": 4.64110127826942, |
| "grad_norm": 0.08786690980195999, |
| "learning_rate": 2.1599999999999996e-05, |
| "loss": 0.6346, |
| "step": 590 |
| }, |
| { |
| "epoch": 4.680432645034415, |
| "grad_norm": 0.08560498058795929, |
| "learning_rate": 1.92e-05, |
| "loss": 0.6413, |
| "step": 595 |
| }, |
| { |
| "epoch": 4.71976401179941, |
| "grad_norm": 0.08328807353973389, |
| "learning_rate": 1.68e-05, |
| "loss": 0.6399, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.71976401179941, |
| "eval_loss": 0.7229037880897522, |
| "eval_runtime": 24.3039, |
| "eval_samples_per_second": 6.748, |
| "eval_steps_per_second": 0.864, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.759095378564405, |
| "grad_norm": 0.0857938751578331, |
| "learning_rate": 1.44e-05, |
| "loss": 0.6456, |
| "step": 605 |
| }, |
| { |
| "epoch": 4.7984267453294, |
| "grad_norm": 0.08315934240818024, |
| "learning_rate": 1.1999999999999999e-05, |
| "loss": 0.6472, |
| "step": 610 |
| }, |
| { |
| "epoch": 4.837758112094395, |
| "grad_norm": 0.08374597877264023, |
| "learning_rate": 9.6e-06, |
| "loss": 0.6403, |
| "step": 615 |
| }, |
| { |
| "epoch": 4.87708947885939, |
| "grad_norm": 0.08550963550806046, |
| "learning_rate": 7.2e-06, |
| "loss": 0.6409, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.916420845624385, |
| "grad_norm": 0.08283807337284088, |
| "learning_rate": 4.8e-06, |
| "loss": 0.6417, |
| "step": 625 |
| }, |
| { |
| "epoch": 4.95575221238938, |
| "grad_norm": 0.08324795961380005, |
| "learning_rate": 2.4e-06, |
| "loss": 0.6334, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.995083579154375, |
| "grad_norm": 0.08238741010427475, |
| "learning_rate": 0.0, |
| "loss": 0.6412, |
| "step": 635 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 635, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.221402740762188e+19, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
