| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.014284056314892022, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.5710140787230054e-05, |
| "eval_loss": 3.6428475379943848, |
| "eval_runtime": 937.0093, |
| "eval_samples_per_second": 12.584, |
| "eval_steps_per_second": 6.292, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00017855070393615026, |
| "grad_norm": 38.791404724121094, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 11.968, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0003571014078723005, |
| "grad_norm": 35.7210693359375, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 11.3643, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0005356521118084508, |
| "grad_norm": 51.62553405761719, |
| "learning_rate": 5e-05, |
| "loss": 11.0627, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.000714202815744601, |
| "grad_norm": 33.5948486328125, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 10.9834, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0008927535196807514, |
| "grad_norm": 26.09846305847168, |
| "learning_rate": 8.333333333333334e-05, |
| "loss": 9.9911, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0010713042236169016, |
| "grad_norm": 25.926218032836914, |
| "learning_rate": 0.0001, |
| "loss": 8.5237, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0012498549275530518, |
| "grad_norm": 28.499187469482422, |
| "learning_rate": 9.995494831023409e-05, |
| "loss": 8.7897, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.001428405631489202, |
| "grad_norm": 23.874563217163086, |
| "learning_rate": 9.981987442712633e-05, |
| "loss": 8.4972, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0016069563354253525, |
| "grad_norm": 42.67042541503906, |
| "learning_rate": 9.959502176294383e-05, |
| "loss": 6.3415, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0017855070393615028, |
| "grad_norm": 39.73894119262695, |
| "learning_rate": 9.928079551738543e-05, |
| "loss": 8.4446, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.001964057743297653, |
| "grad_norm": 12.979087829589844, |
| "learning_rate": 9.887776194738432e-05, |
| "loss": 8.0323, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.002142608447233803, |
| "grad_norm": 14.714144706726074, |
| "learning_rate": 9.838664734667495e-05, |
| "loss": 8.7265, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0023211591511699534, |
| "grad_norm": 15.2055025100708, |
| "learning_rate": 9.780833673696254e-05, |
| "loss": 8.29, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.0024997098551061037, |
| "grad_norm": 13.198466300964355, |
| "learning_rate": 9.714387227305422e-05, |
| "loss": 7.7719, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.002678260559042254, |
| "grad_norm": 13.788397789001465, |
| "learning_rate": 9.639445136482548e-05, |
| "loss": 7.7218, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.002856811262978404, |
| "grad_norm": 13.282957077026367, |
| "learning_rate": 9.55614245194068e-05, |
| "loss": 7.6602, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0030353619669145544, |
| "grad_norm": 25.1441650390625, |
| "learning_rate": 9.464629290747842e-05, |
| "loss": 7.1881, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.003213912670850705, |
| "grad_norm": 27.624034881591797, |
| "learning_rate": 9.365070565805941e-05, |
| "loss": 7.9707, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.0033924633747868553, |
| "grad_norm": 22.605091094970703, |
| "learning_rate": 9.257645688666556e-05, |
| "loss": 6.7703, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.0035710140787230055, |
| "grad_norm": 32.28632736206055, |
| "learning_rate": 9.142548246219212e-05, |
| "loss": 7.0126, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0035710140787230055, |
| "eval_loss": 1.9531031847000122, |
| "eval_runtime": 941.1342, |
| "eval_samples_per_second": 12.529, |
| "eval_steps_per_second": 6.265, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0037495647826591557, |
| "grad_norm": 12.703049659729004, |
| "learning_rate": 9.019985651834703e-05, |
| "loss": 8.9811, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.003928115486595306, |
| "grad_norm": 11.499811172485352, |
| "learning_rate": 8.890178771592199e-05, |
| "loss": 8.2825, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.004106666190531456, |
| "grad_norm": 13.487603187561035, |
| "learning_rate": 8.753361526263621e-05, |
| "loss": 8.3682, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.004285216894467606, |
| "grad_norm": 11.988139152526855, |
| "learning_rate": 8.609780469772623e-05, |
| "loss": 7.4035, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.004463767598403757, |
| "grad_norm": 14.901617050170898, |
| "learning_rate": 8.459694344887732e-05, |
| "loss": 7.1697, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.004642318302339907, |
| "grad_norm": 18.64742088317871, |
| "learning_rate": 8.303373616950408e-05, |
| "loss": 7.3505, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.004820869006276057, |
| "grad_norm": 18.702434539794922, |
| "learning_rate": 8.141099986478212e-05, |
| "loss": 7.5959, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.004999419710212207, |
| "grad_norm": 18.720998764038086, |
| "learning_rate": 7.973165881521434e-05, |
| "loss": 7.286, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.005177970414148358, |
| "grad_norm": 28.588218688964844, |
| "learning_rate": 7.799873930687978e-05, |
| "loss": 7.4316, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.005356521118084508, |
| "grad_norm": 28.344491958618164, |
| "learning_rate": 7.621536417786159e-05, |
| "loss": 6.0416, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.005535071822020658, |
| "grad_norm": 10.961862564086914, |
| "learning_rate": 7.438474719068173e-05, |
| "loss": 8.0463, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.005713622525956808, |
| "grad_norm": 10.041893005371094, |
| "learning_rate": 7.251018724088367e-05, |
| "loss": 7.8733, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.0058921732298929585, |
| "grad_norm": 12.03637409210205, |
| "learning_rate": 7.059506241219965e-05, |
| "loss": 7.9375, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.006070723933829109, |
| "grad_norm": 10.636992454528809, |
| "learning_rate": 6.864282388901544e-05, |
| "loss": 6.9809, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.006249274637765259, |
| "grad_norm": 12.5416259765625, |
| "learning_rate": 6.665698973710288e-05, |
| "loss": 7.0759, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.00642782534170141, |
| "grad_norm": 12.943763732910156, |
| "learning_rate": 6.464113856382752e-05, |
| "loss": 8.2749, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.00660637604563756, |
| "grad_norm": 23.98349380493164, |
| "learning_rate": 6.259890306925627e-05, |
| "loss": 8.2475, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.0067849267495737105, |
| "grad_norm": 17.99372673034668, |
| "learning_rate": 6.0533963499786314e-05, |
| "loss": 7.7457, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.006963477453509861, |
| "grad_norm": 138.98828125, |
| "learning_rate": 5.8450041016092464e-05, |
| "loss": 6.9963, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.007142028157446011, |
| "grad_norm": 66.58040618896484, |
| "learning_rate": 5.6350890987343944e-05, |
| "loss": 7.6597, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.007142028157446011, |
| "eval_loss": 1.931018352508545, |
| "eval_runtime": 940.4445, |
| "eval_samples_per_second": 12.538, |
| "eval_steps_per_second": 6.269, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.007320578861382161, |
| "grad_norm": 10.602204322814941, |
| "learning_rate": 5.4240296223775465e-05, |
| "loss": 8.5977, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.0074991295653183115, |
| "grad_norm": 9.361373901367188, |
| "learning_rate": 5.212206015980742e-05, |
| "loss": 8.1387, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.007677680269254462, |
| "grad_norm": 12.178308486938477, |
| "learning_rate": 5e-05, |
| "loss": 8.6586, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.007856230973190612, |
| "grad_norm": 11.601183891296387, |
| "learning_rate": 4.78779398401926e-05, |
| "loss": 7.8519, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.008034781677126762, |
| "grad_norm": 10.347457885742188, |
| "learning_rate": 4.575970377622456e-05, |
| "loss": 8.2135, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.008213332381062912, |
| "grad_norm": 20.473297119140625, |
| "learning_rate": 4.364910901265606e-05, |
| "loss": 7.7113, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.008391883084999063, |
| "grad_norm": 23.3872013092041, |
| "learning_rate": 4.1549958983907555e-05, |
| "loss": 7.4215, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.008570433788935213, |
| "grad_norm": 14.155945777893066, |
| "learning_rate": 3.94660365002137e-05, |
| "loss": 7.2813, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.008748984492871363, |
| "grad_norm": 20.56569480895996, |
| "learning_rate": 3.740109693074375e-05, |
| "loss": 7.1628, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.008927535196807513, |
| "grad_norm": 39.14048767089844, |
| "learning_rate": 3.5358861436172485e-05, |
| "loss": 6.7286, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.009106085900743664, |
| "grad_norm": 10.889725685119629, |
| "learning_rate": 3.334301026289712e-05, |
| "loss": 8.241, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.009284636604679814, |
| "grad_norm": 11.478461265563965, |
| "learning_rate": 3.135717611098458e-05, |
| "loss": 7.8557, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.009463187308615964, |
| "grad_norm": 10.177154541015625, |
| "learning_rate": 2.9404937587800375e-05, |
| "loss": 7.7535, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.009641738012552114, |
| "grad_norm": 13.540087699890137, |
| "learning_rate": 2.748981275911633e-05, |
| "loss": 7.5926, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.009820288716488264, |
| "grad_norm": 14.206275939941406, |
| "learning_rate": 2.5615252809318284e-05, |
| "loss": 7.7778, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.009998839420424415, |
| "grad_norm": 12.470731735229492, |
| "learning_rate": 2.3784635822138424e-05, |
| "loss": 7.5519, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.010177390124360565, |
| "grad_norm": 12.996101379394531, |
| "learning_rate": 2.2001260693120233e-05, |
| "loss": 7.4359, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.010355940828296715, |
| "grad_norm": 19.329702377319336, |
| "learning_rate": 2.026834118478567e-05, |
| "loss": 7.4877, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.010534491532232865, |
| "grad_norm": 20.063732147216797, |
| "learning_rate": 1.858900013521788e-05, |
| "loss": 6.4413, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.010713042236169016, |
| "grad_norm": 30.000850677490234, |
| "learning_rate": 1.6966263830495936e-05, |
| "loss": 6.3928, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.010713042236169016, |
| "eval_loss": 1.8319700956344604, |
| "eval_runtime": 940.4975, |
| "eval_samples_per_second": 12.537, |
| "eval_steps_per_second": 6.269, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.010891592940105166, |
| "grad_norm": 11.116142272949219, |
| "learning_rate": 1.5403056551122697e-05, |
| "loss": 7.8649, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.011070143644041316, |
| "grad_norm": 10.031145095825195, |
| "learning_rate": 1.3902195302273779e-05, |
| "loss": 7.8468, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.011248694347977466, |
| "grad_norm": 10.915895462036133, |
| "learning_rate": 1.246638473736378e-05, |
| "loss": 8.6783, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.011427245051913617, |
| "grad_norm": 12.510370254516602, |
| "learning_rate": 1.1098212284078036e-05, |
| "loss": 7.5022, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.011605795755849767, |
| "grad_norm": 11.837886810302734, |
| "learning_rate": 9.800143481652979e-06, |
| "loss": 7.7391, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.011784346459785917, |
| "grad_norm": 17.98138427734375, |
| "learning_rate": 8.574517537807897e-06, |
| "loss": 7.7047, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.011962897163722067, |
| "grad_norm": 11.747542381286621, |
| "learning_rate": 7.423543113334436e-06, |
| "loss": 6.1822, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.012141447867658217, |
| "grad_norm": 20.17440414428711, |
| "learning_rate": 6.349294341940593e-06, |
| "loss": 7.4627, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.012319998571594368, |
| "grad_norm": 15.974550247192383, |
| "learning_rate": 5.353707092521582e-06, |
| "loss": 6.0153, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.012498549275530518, |
| "grad_norm": 17.395343780517578, |
| "learning_rate": 4.43857548059321e-06, |
| "loss": 5.7713, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.012677099979466668, |
| "grad_norm": 9.948678970336914, |
| "learning_rate": 3.605548635174533e-06, |
| "loss": 7.4623, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.01285565068340282, |
| "grad_norm": 12.097657203674316, |
| "learning_rate": 2.85612772694579e-06, |
| "loss": 8.4925, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.01303420138733897, |
| "grad_norm": 9.868169784545898, |
| "learning_rate": 2.191663263037458e-06, |
| "loss": 8.0455, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.01321275209127512, |
| "grad_norm": 10.206999778747559, |
| "learning_rate": 1.6133526533250565e-06, |
| "loss": 7.8219, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.01339130279521127, |
| "grad_norm": 11.312124252319336, |
| "learning_rate": 1.1222380526156928e-06, |
| "loss": 7.3541, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.013569853499147421, |
| "grad_norm": 17.35927963256836, |
| "learning_rate": 7.192044826145771e-07, |
| "loss": 6.85, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.013748404203083571, |
| "grad_norm": 13.923419952392578, |
| "learning_rate": 4.049782370561583e-07, |
| "loss": 7.0878, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.013926954907019722, |
| "grad_norm": 14.711668968200684, |
| "learning_rate": 1.8012557287367392e-07, |
| "loss": 6.3097, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.014105505610955872, |
| "grad_norm": 13.454591751098633, |
| "learning_rate": 4.5051689765929214e-08, |
| "loss": 5.6845, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.014284056314892022, |
| "grad_norm": 45.98155212402344, |
| "learning_rate": 0.0, |
| "loss": 7.6137, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.014284056314892022, |
| "eval_loss": 1.823633074760437, |
| "eval_runtime": 941.154, |
| "eval_samples_per_second": 12.528, |
| "eval_steps_per_second": 6.265, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 400, |
| "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": 1.402161598562304e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
