| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 349, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014352350197344816, | |
| "grad_norm": 11.071812629699707, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.7414, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02870470039468963, | |
| "grad_norm": 7.1317901611328125, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 0.7038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04305705059203445, | |
| "grad_norm": 4.095168113708496, | |
| "learning_rate": 9.998056338091415e-06, | |
| "loss": 0.7009, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05740940078937926, | |
| "grad_norm": 2.938896894454956, | |
| "learning_rate": 9.986183876164412e-06, | |
| "loss": 0.6751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07176175098672408, | |
| "grad_norm": 3.5328586101531982, | |
| "learning_rate": 9.96354437049027e-06, | |
| "loss": 0.6547, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0861141011840689, | |
| "grad_norm": 2.831934690475464, | |
| "learning_rate": 9.930186708264902e-06, | |
| "loss": 0.6616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1004664513814137, | |
| "grad_norm": 2.707149028778076, | |
| "learning_rate": 9.88618292120984e-06, | |
| "loss": 0.6828, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11481880157875853, | |
| "grad_norm": 2.4383013248443604, | |
| "learning_rate": 9.831628030028698e-06, | |
| "loss": 0.6486, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12917115177610333, | |
| "grad_norm": 2.7486937046051025, | |
| "learning_rate": 9.76663983922178e-06, | |
| "loss": 0.6592, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14352350197344815, | |
| "grad_norm": 2.4958226680755615, | |
| "learning_rate": 9.691358682701927e-06, | |
| "loss": 0.6616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15787585217079297, | |
| "grad_norm": 2.9137589931488037, | |
| "learning_rate": 9.605947120760878e-06, | |
| "loss": 0.6479, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1722282023681378, | |
| "grad_norm": 2.6844582557678223, | |
| "learning_rate": 9.510589589040554e-06, | |
| "loss": 0.6677, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1865805525654826, | |
| "grad_norm": 2.127028703689575, | |
| "learning_rate": 9.405492000267228e-06, | |
| "loss": 0.6507, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2009329027628274, | |
| "grad_norm": 2.487703800201416, | |
| "learning_rate": 9.29088129960862e-06, | |
| "loss": 0.6615, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21528525296017223, | |
| "grad_norm": 2.5370140075683594, | |
| "learning_rate": 9.16700497461403e-06, | |
| "loss": 0.6522, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22963760315751705, | |
| "grad_norm": 2.203188896179199, | |
| "learning_rate": 9.034130520795774e-06, | |
| "loss": 0.6521, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24398995335486187, | |
| "grad_norm": 2.402724504470825, | |
| "learning_rate": 8.892544864005899e-06, | |
| "loss": 0.6496, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.25834230355220666, | |
| "grad_norm": 2.3624093532562256, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 0.6378, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2726946537495515, | |
| "grad_norm": 2.36360239982605, | |
| "learning_rate": 8.584481038514573e-06, | |
| "loss": 0.6422, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2870470039468963, | |
| "grad_norm": 2.0742623805999756, | |
| "learning_rate": 8.418668095317912e-06, | |
| "loss": 0.6441, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3013993541442411, | |
| "grad_norm": 2.300394058227539, | |
| "learning_rate": 8.245472963687484e-06, | |
| "loss": 0.6333, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.31575170434158595, | |
| "grad_norm": 2.1633546352386475, | |
| "learning_rate": 8.065269636962765e-06, | |
| "loss": 0.6393, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33010405453893077, | |
| "grad_norm": 2.291600227355957, | |
| "learning_rate": 7.878447241808634e-06, | |
| "loss": 0.647, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3444564047362756, | |
| "grad_norm": 2.0962560176849365, | |
| "learning_rate": 7.685409197944768e-06, | |
| "loss": 0.6226, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35880875493362036, | |
| "grad_norm": 2.4263839721679688, | |
| "learning_rate": 7.486572347010937e-06, | |
| "loss": 0.6442, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3731611051309652, | |
| "grad_norm": 2.1769137382507324, | |
| "learning_rate": 7.282366052449351e-06, | |
| "loss": 0.6434, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.38751345532831, | |
| "grad_norm": 2.181265115737915, | |
| "learning_rate": 7.073231272347714e-06, | |
| "loss": 0.628, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4018658055256548, | |
| "grad_norm": 2.1604084968566895, | |
| "learning_rate": 6.859619607245102e-06, | |
| "loss": 0.6349, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.41621815572299964, | |
| "grad_norm": 2.0021893978118896, | |
| "learning_rate": 6.641992324956776e-06, | |
| "loss": 0.6159, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.43057050592034446, | |
| "grad_norm": 2.3016304969787598, | |
| "learning_rate": 6.4208193645237314e-06, | |
| "loss": 0.6397, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4449228561176893, | |
| "grad_norm": 2.1002519130706787, | |
| "learning_rate": 6.1965783214377895e-06, | |
| "loss": 0.6268, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4592752063150341, | |
| "grad_norm": 4.018091201782227, | |
| "learning_rate": 5.9697534163335645e-06, | |
| "loss": 0.6302, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4736275565123789, | |
| "grad_norm": 1.9025262594223022, | |
| "learning_rate": 5.740834449374237e-06, | |
| "loss": 0.6163, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.48797990670972374, | |
| "grad_norm": 1.9070066213607788, | |
| "learning_rate": 5.510315742589042e-06, | |
| "loss": 0.6243, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5023322569070685, | |
| "grad_norm": 2.002209186553955, | |
| "learning_rate": 5.278695072446342e-06, | |
| "loss": 0.6245, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5166846071044133, | |
| "grad_norm": 1.9884896278381348, | |
| "learning_rate": 5.046472594967279e-06, | |
| "loss": 0.607, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5310369573017582, | |
| "grad_norm": 2.062976837158203, | |
| "learning_rate": 4.814149765701059e-06, | |
| "loss": 0.609, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.545389307499103, | |
| "grad_norm": 1.9803415536880493, | |
| "learning_rate": 4.582228256894093e-06, | |
| "loss": 0.6119, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5597416576964478, | |
| "grad_norm": 1.8966432809829712, | |
| "learning_rate": 4.351208874191192e-06, | |
| "loss": 0.6291, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5740940078937926, | |
| "grad_norm": 2.038236618041992, | |
| "learning_rate": 4.121590475208071e-06, | |
| "loss": 0.6255, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5884463580911374, | |
| "grad_norm": 2.072604179382324, | |
| "learning_rate": 3.8938688923104015e-06, | |
| "loss": 0.6269, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.6027987082884823, | |
| "grad_norm": 2.125389814376831, | |
| "learning_rate": 3.668535861925509e-06, | |
| "loss": 0.6278, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6171510584858271, | |
| "grad_norm": 2.0525448322296143, | |
| "learning_rate": 3.4460779626987186e-06, | |
| "loss": 0.6, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.6315034086831719, | |
| "grad_norm": 1.934063196182251, | |
| "learning_rate": 3.226975564787322e-06, | |
| "loss": 0.5925, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6458557588805167, | |
| "grad_norm": 1.8446972370147705, | |
| "learning_rate": 3.0117017925609802e-06, | |
| "loss": 0.6035, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6602081090778615, | |
| "grad_norm": 2.0047950744628906, | |
| "learning_rate": 2.800721502948506e-06, | |
| "loss": 0.6022, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6745604592752064, | |
| "grad_norm": 1.9434928894042969, | |
| "learning_rate": 2.5944902816371573e-06, | |
| "loss": 0.5966, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6889128094725512, | |
| "grad_norm": 1.9444347620010376, | |
| "learning_rate": 2.3934534592920416e-06, | |
| "loss": 0.5839, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.703265159669896, | |
| "grad_norm": 1.9846431016921997, | |
| "learning_rate": 2.1980451499199262e-06, | |
| "loss": 0.6063, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.7176175098672407, | |
| "grad_norm": 1.8537969589233398, | |
| "learning_rate": 2.0086873134540626e-06, | |
| "loss": 0.6068, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7319698600645855, | |
| "grad_norm": 1.9193341732025146, | |
| "learning_rate": 1.8257888445842026e-06, | |
| "loss": 0.5948, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.7463222102619304, | |
| "grad_norm": 1.9606044292449951, | |
| "learning_rate": 1.6497446897993885e-06, | |
| "loss": 0.5932, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7606745604592752, | |
| "grad_norm": 1.9930768013000488, | |
| "learning_rate": 1.4809349945501422e-06, | |
| "loss": 0.5998, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.77502691065662, | |
| "grad_norm": 1.9653593301773071, | |
| "learning_rate": 1.319724282371664e-06, | |
| "loss": 0.6135, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7893792608539648, | |
| "grad_norm": 1.7707090377807617, | |
| "learning_rate": 1.1664606677406025e-06, | |
| "loss": 0.6069, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.8037316110513096, | |
| "grad_norm": 1.9296361207962036, | |
| "learning_rate": 1.0214751043651582e-06, | |
| "loss": 0.5974, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8180839612486545, | |
| "grad_norm": 1.89194917678833, | |
| "learning_rate": 8.850806705317183e-07, | |
| "loss": 0.5973, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.8324363114459993, | |
| "grad_norm": 1.991350769996643, | |
| "learning_rate": 7.575718930512516e-07, | |
| "loss": 0.5867, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8467886616433441, | |
| "grad_norm": 1.789543867111206, | |
| "learning_rate": 6.392241112653031e-07, | |
| "loss": 0.61, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.8611410118406889, | |
| "grad_norm": 1.8926385641098022, | |
| "learning_rate": 5.302928824849335e-07, | |
| "loss": 0.6084, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8754933620380337, | |
| "grad_norm": 1.8285890817642212, | |
| "learning_rate": 4.3101343014651356e-07, | |
| "loss": 0.599, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.8898457122353786, | |
| "grad_norm": 1.9200646877288818, | |
| "learning_rate": 3.416001358759635e-07, | |
| "loss": 0.5911, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9041980624327234, | |
| "grad_norm": 1.8193855285644531, | |
| "learning_rate": 2.6224607655831236e-07, | |
| "loss": 0.5886, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.9185504126300682, | |
| "grad_norm": 1.7819342613220215, | |
| "learning_rate": 1.9312260741218114e-07, | |
| "loss": 0.5917, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.932902762827413, | |
| "grad_norm": 1.8590822219848633, | |
| "learning_rate": 1.3437899196950765e-07, | |
| "loss": 0.5799, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.9472551130247578, | |
| "grad_norm": 1.7508701086044312, | |
| "learning_rate": 8.614207975952083e-08, | |
| "loss": 0.6015, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9616074632221027, | |
| "grad_norm": 1.8058841228485107, | |
| "learning_rate": 4.851603239296065e-08, | |
| "loss": 0.5848, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.9759598134194475, | |
| "grad_norm": 1.788930892944336, | |
| "learning_rate": 2.158209863804217e-08, | |
| "loss": 0.5879, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9903121636167922, | |
| "grad_norm": 1.9363088607788086, | |
| "learning_rate": 5.398438973845954e-09, | |
| "loss": 0.5836, | |
| "step": 345 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 349, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.871785990877872e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |