| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02635393332454869, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003513857776606492, | |
| "grad_norm": 0.40566906332969666, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.8289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003513857776606492, | |
| "eval_loss": 1.173790454864502, | |
| "eval_runtime": 610.791, | |
| "eval_samples_per_second": 3.924, | |
| "eval_steps_per_second": 1.963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007027715553212984, | |
| "grad_norm": 0.5825751423835754, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.7893, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010541573329819476, | |
| "grad_norm": 0.4203815460205078, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0236, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014055431106425968, | |
| "grad_norm": 0.5486876964569092, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.2274, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001756928888303246, | |
| "grad_norm": 0.49067986011505127, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 8.6525, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002108314665963895, | |
| "grad_norm": 0.5652139782905579, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.0269, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002459700443624544, | |
| "grad_norm": 0.6335968375205994, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.0283, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0028110862212851937, | |
| "grad_norm": 0.6399157047271729, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 5.6921, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0031624719989458427, | |
| "grad_norm": 0.7017378807067871, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.5049, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003513857776606492, | |
| "grad_norm": 0.6648010015487671, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 6.5068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003865243554267141, | |
| "grad_norm": 0.7622893452644348, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 6.1024, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00421662933192779, | |
| "grad_norm": 0.8102121353149414, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9054, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00456801510958844, | |
| "grad_norm": 1.0450242757797241, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 8.0875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004919400887249088, | |
| "grad_norm": 1.1724853515625, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 6.9638, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005270786664909738, | |
| "grad_norm": 1.17697012424469, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.5686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005622172442570387, | |
| "grad_norm": 0.9172914624214172, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 6.4815, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005973558220231036, | |
| "grad_norm": 1.8105238676071167, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 7.5522, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0063249439978916855, | |
| "grad_norm": 1.1030470132827759, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 7.9177, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006676329775552334, | |
| "grad_norm": 1.0749439001083374, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 8.2476, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007027715553212984, | |
| "grad_norm": 0.988822877407074, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 8.0408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007379101330873633, | |
| "grad_norm": 1.0468634366989136, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.7576, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007730487108534282, | |
| "grad_norm": 1.0833945274353027, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 7.7106, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008081872886194932, | |
| "grad_norm": 1.1043288707733154, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 7.796, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00843325866385558, | |
| "grad_norm": 1.253221869468689, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.2421, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00878464444151623, | |
| "grad_norm": 1.5644135475158691, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 6.957, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00878464444151623, | |
| "eval_loss": 1.055617094039917, | |
| "eval_runtime": 614.7811, | |
| "eval_samples_per_second": 3.899, | |
| "eval_steps_per_second": 1.95, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00913603021917688, | |
| "grad_norm": 1.6291801929473877, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 7.8515, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009487415996837528, | |
| "grad_norm": 1.4865143299102783, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.6876, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009838801774498177, | |
| "grad_norm": 1.633550763130188, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 9.7649, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010190187552158827, | |
| "grad_norm": 1.6559158563613892, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 7.7611, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010541573329819476, | |
| "grad_norm": 1.56125807762146, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.1391, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010892959107480124, | |
| "grad_norm": 1.4842593669891357, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 7.1128, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011244344885140775, | |
| "grad_norm": 1.9677858352661133, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 8.2545, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011595730662801423, | |
| "grad_norm": 2.1278786659240723, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 8.5091, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011947116440462072, | |
| "grad_norm": 1.7648427486419678, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 6.5063, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01229850221812272, | |
| "grad_norm": 1.6439030170440674, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 8.567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012649887995783371, | |
| "grad_norm": 1.884887456893921, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 8.3356, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01300127377344402, | |
| "grad_norm": 1.6573904752731323, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 7.9903, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.013352659551104668, | |
| "grad_norm": 1.8767001628875732, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 7.5882, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.013704045328765319, | |
| "grad_norm": 2.158738374710083, | |
| "learning_rate": 5e-05, | |
| "loss": 9.144, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014055431106425967, | |
| "grad_norm": 2.622767448425293, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 9.0718, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014406816884086616, | |
| "grad_norm": 2.098249912261963, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 7.5903, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.014758202661747266, | |
| "grad_norm": 2.695885419845581, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 9.2641, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015109588439407915, | |
| "grad_norm": 2.7287509441375732, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 9.99, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.015460974217068563, | |
| "grad_norm": 2.987199068069458, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 9.1632, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015812359994729214, | |
| "grad_norm": 3.6520209312438965, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3929, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016163745772389864, | |
| "grad_norm": 3.4548537731170654, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 10.003, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01651513155005051, | |
| "grad_norm": 5.150744915008545, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 11.3511, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01686651732771116, | |
| "grad_norm": 7.644892692565918, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.2625, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01721790310537181, | |
| "grad_norm": 9.981356620788574, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 11.0407, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01756928888303246, | |
| "grad_norm": 21.54275131225586, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 13.8822, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01756928888303246, | |
| "eval_loss": 1.019070029258728, | |
| "eval_runtime": 614.5764, | |
| "eval_samples_per_second": 3.9, | |
| "eval_steps_per_second": 1.951, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01792067466069311, | |
| "grad_norm": 1.2253239154815674, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.3973, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01827206043835376, | |
| "grad_norm": 0.9925060868263245, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 5.1567, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.018623446216014406, | |
| "grad_norm": 1.3718881607055664, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 7.931, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.018974831993675056, | |
| "grad_norm": 1.1585586071014404, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.9163, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.019326217771335707, | |
| "grad_norm": 1.292351245880127, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 14.2114, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.019677603548996354, | |
| "grad_norm": 0.7819482088088989, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 5.4162, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.020028989326657004, | |
| "grad_norm": 0.9459342956542969, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.4571, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.020380375104317654, | |
| "grad_norm": 0.8447139859199524, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 4.3193, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0207317608819783, | |
| "grad_norm": 0.9083331823348999, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 5.212, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02108314665963895, | |
| "grad_norm": 0.9303866028785706, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 5.864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.021434532437299602, | |
| "grad_norm": 0.9800831079483032, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 5.7093, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.02178591821496025, | |
| "grad_norm": 1.0370510816574097, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 7.2464, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0221373039926209, | |
| "grad_norm": 1.0886764526367188, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 6.793, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02248868977028155, | |
| "grad_norm": 1.2717602252960205, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 7.8938, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.022840075547942196, | |
| "grad_norm": 1.13100004196167, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 6.6839, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.023191461325602847, | |
| "grad_norm": 1.103505253791809, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.4892, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.023542847103263497, | |
| "grad_norm": 1.0577113628387451, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 6.9858, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.023894232880924144, | |
| "grad_norm": 1.1837400197982788, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 7.707, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.024245618658584794, | |
| "grad_norm": 1.2462010383605957, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 8.0216, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.02459700443624544, | |
| "grad_norm": 1.1442655324935913, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 7.1856, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02494839021390609, | |
| "grad_norm": 1.1962558031082153, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 7.0156, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.025299775991566742, | |
| "grad_norm": 1.2656418085098267, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 7.6485, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02565116176922739, | |
| "grad_norm": 1.0747231245040894, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 6.3779, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02600254754688804, | |
| "grad_norm": 1.213733196258545, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 8.1561, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02635393332454869, | |
| "grad_norm": 1.571469783782959, | |
| "learning_rate": 0.0, | |
| "loss": 8.2613, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02635393332454869, | |
| "eval_loss": 1.00751793384552, | |
| "eval_runtime": 614.6938, | |
| "eval_samples_per_second": 3.9, | |
| "eval_steps_per_second": 1.951, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2197502476288e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |