| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06229235880398671, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008305647840531562, | |
| "grad_norm": 2.7521727085113525, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.8783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008305647840531562, | |
| "eval_loss": 2.65358567237854, | |
| "eval_runtime": 71.8689, | |
| "eval_samples_per_second": 14.109, | |
| "eval_steps_per_second": 7.055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016611295681063123, | |
| "grad_norm": 2.534353256225586, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.5571, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024916943521594683, | |
| "grad_norm": 2.619391918182373, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5198, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033222591362126247, | |
| "grad_norm": 2.480504274368286, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.3843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004152823920265781, | |
| "grad_norm": 2.3676488399505615, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.4082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0049833887043189366, | |
| "grad_norm": 2.171743154525757, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7348, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005813953488372093, | |
| "grad_norm": 2.1443028450012207, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.6026, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006644518272425249, | |
| "grad_norm": 2.2254693508148193, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.7396, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007475083056478406, | |
| "grad_norm": 2.5551085472106934, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0664, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008305647840531562, | |
| "grad_norm": 2.318112373352051, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.6275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009136212624584718, | |
| "grad_norm": 2.318878412246704, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009966777408637873, | |
| "grad_norm": 2.1796483993530273, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01079734219269103, | |
| "grad_norm": 2.200101852416992, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.6143, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011627906976744186, | |
| "grad_norm": 1.9241218566894531, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.4271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012458471760797342, | |
| "grad_norm": 2.12858510017395, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "grad_norm": 2.173638343811035, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.746, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014119601328903655, | |
| "grad_norm": 1.947255253791809, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.689, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014950166112956811, | |
| "grad_norm": 2.135347604751587, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0612, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015780730897009966, | |
| "grad_norm": 1.937851071357727, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.8322, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016611295681063124, | |
| "grad_norm": 2.0472640991210938, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01744186046511628, | |
| "grad_norm": 1.8501553535461426, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018272425249169437, | |
| "grad_norm": 1.7711646556854248, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.7159, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01910299003322259, | |
| "grad_norm": 2.242205858230591, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.7749, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019933554817275746, | |
| "grad_norm": 1.9537017345428467, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7306, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020764119601328904, | |
| "grad_norm": 2.3009982109069824, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.8783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020764119601328904, | |
| "eval_loss": 2.0330841541290283, | |
| "eval_runtime": 71.4667, | |
| "eval_samples_per_second": 14.188, | |
| "eval_steps_per_second": 7.094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02159468438538206, | |
| "grad_norm": 1.8611646890640259, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 1.6921, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022425249169435217, | |
| "grad_norm": 1.7114734649658203, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5121, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023255813953488372, | |
| "grad_norm": 1.9501327276229858, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.0156, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02408637873754153, | |
| "grad_norm": 1.7911945581436157, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.5041, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024916943521594685, | |
| "grad_norm": 1.709389090538025, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6483, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02574750830564784, | |
| "grad_norm": 1.8848737478256226, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.8492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026578073089700997, | |
| "grad_norm": 2.078946113586426, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 1.6023, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027408637873754152, | |
| "grad_norm": 2.286283254623413, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.7772, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02823920265780731, | |
| "grad_norm": 2.291384696960449, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.9919, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.029069767441860465, | |
| "grad_norm": 2.2174739837646484, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.8295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029900332225913623, | |
| "grad_norm": 2.378859758377075, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8642, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030730897009966777, | |
| "grad_norm": 2.1495234966278076, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 2.3204, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03156146179401993, | |
| "grad_norm": 2.106130599975586, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.7387, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03239202657807309, | |
| "grad_norm": 2.0906083583831787, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9952, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03322259136212625, | |
| "grad_norm": 2.5236432552337646, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 2.3975, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0340531561461794, | |
| "grad_norm": 2.412330150604248, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 2.3625, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03488372093023256, | |
| "grad_norm": 2.1376240253448486, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.1484, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 2.4796907901763916, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8789, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.036544850498338874, | |
| "grad_norm": 2.7524349689483643, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 2.6193, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03737541528239203, | |
| "grad_norm": 3.215737819671631, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.7779, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03820598006644518, | |
| "grad_norm": 3.4973068237304688, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 2.6296, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03903654485049834, | |
| "grad_norm": 3.1748504638671875, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 2.3609, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03986710963455149, | |
| "grad_norm": 3.053208112716675, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.0583, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.040697674418604654, | |
| "grad_norm": 4.208493232727051, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 2.95, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04152823920265781, | |
| "grad_norm": 3.1799519062042236, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 3.212, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04152823920265781, | |
| "eval_loss": 1.978314757347107, | |
| "eval_runtime": 71.6979, | |
| "eval_samples_per_second": 14.143, | |
| "eval_steps_per_second": 7.071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04235880398671096, | |
| "grad_norm": 3.037964344024658, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2274, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04318936877076412, | |
| "grad_norm": 2.001744270324707, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 1.8772, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04401993355481727, | |
| "grad_norm": 2.270850419998169, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 1.8247, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.044850498338870434, | |
| "grad_norm": 2.272608518600464, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.4002, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04568106312292359, | |
| "grad_norm": 1.9296989440917969, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 2.2143, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.046511627906976744, | |
| "grad_norm": 1.6859852075576782, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.6857, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0473421926910299, | |
| "grad_norm": 1.8581290245056152, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6804, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04817275747508306, | |
| "grad_norm": 1.8868964910507202, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 1.6223, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.049003322259136214, | |
| "grad_norm": 1.9600261449813843, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.6922, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.04983388704318937, | |
| "grad_norm": 1.9007118940353394, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.804, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.050664451827242524, | |
| "grad_norm": 1.7296816110610962, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.6008, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05149501661129568, | |
| "grad_norm": 1.7615364789962769, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.5411, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05232558139534884, | |
| "grad_norm": 1.64870023727417, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.531, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 1.8037062883377075, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.7586, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05398671096345515, | |
| "grad_norm": 1.8290114402770996, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.7702, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.054817275747508304, | |
| "grad_norm": 1.5939185619354248, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7454, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05564784053156146, | |
| "grad_norm": 1.5866504907608032, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5255, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05647840531561462, | |
| "grad_norm": 1.9439473152160645, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.767, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.057308970099667775, | |
| "grad_norm": 1.8197013139724731, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6518, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 1.836192011833191, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 1.5788, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.058970099667774084, | |
| "grad_norm": 1.8220064640045166, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.8797, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.059800664451827246, | |
| "grad_norm": 1.953622579574585, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.8, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0606312292358804, | |
| "grad_norm": 1.840462565422058, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.8579, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.061461794019933555, | |
| "grad_norm": 1.8298439979553223, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 1.8466, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06229235880398671, | |
| "grad_norm": 1.7909139394760132, | |
| "learning_rate": 0.0, | |
| "loss": 1.7919, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06229235880398671, | |
| "eval_loss": 1.9671133756637573, | |
| "eval_runtime": 72.2963, | |
| "eval_samples_per_second": 14.026, | |
| "eval_steps_per_second": 7.013, | |
| "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": 1.5195925660041216e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |