| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 200.0, |
| "global_step": 354, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005649717514124294, |
| "grad_norm": 1.8059313297271729, |
| "learning_rate": 4.999901553476555e-05, |
| "loss": 0.4717830717563629, |
| "step": 1, |
| "token_acc": 0.924627166465135 |
| }, |
| { |
| "epoch": 0.05649717514124294, |
| "grad_norm": 0.1542048305273056, |
| "learning_rate": 4.9901617425775067e-05, |
| "loss": 0.33008625772264266, |
| "step": 10, |
| "token_acc": 0.9219071687140808 |
| }, |
| { |
| "epoch": 0.11299435028248588, |
| "grad_norm": 0.11267846822738647, |
| "learning_rate": 4.9607244033573156e-05, |
| "loss": 0.25351030826568605, |
| "step": 20, |
| "token_acc": 0.9264000170247177 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 0.09091860800981522, |
| "learning_rate": 4.91191967203629e-05, |
| "loss": 0.22513890266418457, |
| "step": 30, |
| "token_acc": 0.9317765577689588 |
| }, |
| { |
| "epoch": 0.22598870056497175, |
| "grad_norm": 0.08639991283416748, |
| "learning_rate": 4.84413167142257e-05, |
| "loss": 0.20885028839111328, |
| "step": 40, |
| "token_acc": 0.9359174715592828 |
| }, |
| { |
| "epoch": 0.2824858757062147, |
| "grad_norm": 0.09375399351119995, |
| "learning_rate": 4.7578939341563095e-05, |
| "loss": 0.19784480333328247, |
| "step": 50, |
| "token_acc": 0.9384661788621316 |
| }, |
| { |
| "epoch": 0.3389830508474576, |
| "grad_norm": 0.08870115131139755, |
| "learning_rate": 4.653885203484515e-05, |
| "loss": 0.18448562622070314, |
| "step": 60, |
| "token_acc": 0.9420314698252165 |
| }, |
| { |
| "epoch": 0.3954802259887006, |
| "grad_norm": 0.11067840456962585, |
| "learning_rate": 4.532924091140417e-05, |
| "loss": 0.18294379711151124, |
| "step": 70, |
| "token_acc": 0.9418481147105683 |
| }, |
| { |
| "epoch": 0.4519774011299435, |
| "grad_norm": 0.09862152487039566, |
| "learning_rate": 4.395962634373097e-05, |
| "loss": 0.17243103981018065, |
| "step": 80, |
| "token_acc": 0.9446352200693965 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 0.10678666085004807, |
| "learning_rate": 4.2440788028374624e-05, |
| "loss": 0.1731430172920227, |
| "step": 90, |
| "token_acc": 0.9447363875815018 |
| }, |
| { |
| "epoch": 0.5649717514124294, |
| "grad_norm": 0.10532315075397491, |
| "learning_rate": 4.0784680143198836e-05, |
| "loss": 0.17281131744384765, |
| "step": 100, |
| "token_acc": 0.9447437022704439 |
| }, |
| { |
| "epoch": 0.6214689265536724, |
| "grad_norm": 0.11211931705474854, |
| "learning_rate": 3.900433726075865e-05, |
| "loss": 0.16182489395141603, |
| "step": 110, |
| "token_acc": 0.9481675818843257 |
| }, |
| { |
| "epoch": 0.6779661016949152, |
| "grad_norm": 0.10726941376924515, |
| "learning_rate": 3.711377175831626e-05, |
| "loss": 0.16202739477157593, |
| "step": 120, |
| "token_acc": 0.9479687034245692 |
| }, |
| { |
| "epoch": 0.7344632768361582, |
| "grad_norm": 0.10400757193565369, |
| "learning_rate": 3.512786353194134e-05, |
| "loss": 0.15924739837646484, |
| "step": 130, |
| "token_acc": 0.9486699455285843 |
| }, |
| { |
| "epoch": 0.7909604519774012, |
| "grad_norm": 0.10787644982337952, |
| "learning_rate": 3.3062242882712724e-05, |
| "loss": 0.15439069271087646, |
| "step": 140, |
| "token_acc": 0.9498849158473873 |
| }, |
| { |
| "epoch": 0.847457627118644, |
| "grad_norm": 0.10836105048656464, |
| "learning_rate": 3.093316749677788e-05, |
| "loss": 0.15822217464447022, |
| "step": 150, |
| "token_acc": 0.9487123526844173 |
| }, |
| { |
| "epoch": 0.903954802259887, |
| "grad_norm": 0.10872391611337662, |
| "learning_rate": 2.875739448751176e-05, |
| "loss": 0.15569958686828614, |
| "step": 160, |
| "token_acc": 0.9491473105803542 |
| }, |
| { |
| "epoch": 0.96045197740113, |
| "grad_norm": 0.11218578368425369, |
| "learning_rate": 2.655204850688085e-05, |
| "loss": 0.15528473854064942, |
| "step": 170, |
| "token_acc": 0.9494661997922623 |
| }, |
| { |
| "epoch": 1.0169491525423728, |
| "grad_norm": 0.13003411889076233, |
| "learning_rate": 2.433448696405563e-05, |
| "loss": 0.1492830991744995, |
| "step": 180, |
| "token_acc": 0.9511860316683133 |
| }, |
| { |
| "epoch": 1.073446327683616, |
| "grad_norm": 0.12652547657489777, |
| "learning_rate": 2.2122163412082927e-05, |
| "loss": 0.14996984004974365, |
| "step": 190, |
| "token_acc": 0.9509753894028877 |
| }, |
| { |
| "epoch": 1.1299435028248588, |
| "grad_norm": 0.11710216104984283, |
| "learning_rate": 1.993249017784766e-05, |
| "loss": 0.149368953704834, |
| "step": 200, |
| "token_acc": 0.9509840746795515 |
| }, |
| { |
| "epoch": 1.1864406779661016, |
| "grad_norm": 0.12813611328601837, |
| "learning_rate": 1.778270131650948e-05, |
| "loss": 0.1482247829437256, |
| "step": 210, |
| "token_acc": 0.9514638991717056 |
| }, |
| { |
| "epoch": 1.2429378531073447, |
| "grad_norm": 0.12335359305143356, |
| "learning_rate": 1.5689716969045848e-05, |
| "loss": 0.14458421468734742, |
| "step": 220, |
| "token_acc": 0.9528204997080846 |
| }, |
| { |
| "epoch": 1.2994350282485876, |
| "grad_norm": 0.1252630650997162, |
| "learning_rate": 1.3670010190490073e-05, |
| "loss": 0.14932241439819335, |
| "step": 230, |
| "token_acc": 0.950983923940499 |
| }, |
| { |
| "epoch": 1.3559322033898304, |
| "grad_norm": 0.12602832913398743, |
| "learning_rate": 1.173947729700644e-05, |
| "loss": 0.14413282871246338, |
| "step": 240, |
| "token_acc": 0.9524894618411184 |
| }, |
| { |
| "epoch": 1.4124293785310735, |
| "grad_norm": 0.1404254138469696, |
| "learning_rate": 9.913312752249903e-06, |
| "loss": 0.14448442459106445, |
| "step": 250, |
| "token_acc": 0.9523784878342272 |
| }, |
| { |
| "epoch": 1.4689265536723164, |
| "grad_norm": 0.1297323852777481, |
| "learning_rate": 8.20588957773018e-06, |
| "loss": 0.1442911744117737, |
| "step": 260, |
| "token_acc": 0.9526485262065045 |
| }, |
| { |
| "epoch": 1.5254237288135593, |
| "grad_norm": 0.1164567619562149, |
| "learning_rate": 6.6306462284233234e-06, |
| "loss": 0.1476944088935852, |
| "step": 270, |
| "token_acc": 0.9516979818914234 |
| }, |
| { |
| "epoch": 1.5819209039548023, |
| "grad_norm": 0.12876106798648834, |
| "learning_rate": 5.199980823988157e-06, |
| "loss": 0.14429720640182495, |
| "step": 280, |
| "token_acc": 0.9527345847326476 |
| }, |
| { |
| "epoch": 1.6384180790960452, |
| "grad_norm": 0.12522290647029877, |
| "learning_rate": 3.925153568052123e-06, |
| "loss": 0.14247846603393555, |
| "step": 290, |
| "token_acc": 0.952577761791889 |
| }, |
| { |
| "epoch": 1.694915254237288, |
| "grad_norm": 0.1215895265340805, |
| "learning_rate": 2.8161981235857143e-06, |
| "loss": 0.14371044635772706, |
| "step": 300, |
| "token_acc": 0.9530261029770724 |
| }, |
| { |
| "epoch": 1.7514124293785311, |
| "grad_norm": 0.13429652154445648, |
| "learning_rate": 1.881842641895104e-06, |
| "loss": 0.1435616970062256, |
| "step": 310, |
| "token_acc": 0.9526384206465796 |
| }, |
| { |
| "epoch": 1.807909604519774, |
| "grad_norm": 0.12633894383907318, |
| "learning_rate": 1.129441066782702e-06, |
| "loss": 0.14912809133529664, |
| "step": 320, |
| "token_acc": 0.9509201261393581 |
| }, |
| { |
| "epoch": 1.8644067796610169, |
| "grad_norm": 0.12346093356609344, |
| "learning_rate": 5.649152545533332e-07, |
| "loss": 0.14490561485290526, |
| "step": 330, |
| "token_acc": 0.9519967728922952 |
| }, |
| { |
| "epoch": 1.92090395480226, |
| "grad_norm": 0.123548224568367, |
| "learning_rate": 1.927083654168854e-07, |
| "loss": 0.14034559726715087, |
| "step": 340, |
| "token_acc": 0.9537333066731213 |
| }, |
| { |
| "epoch": 1.9774011299435028, |
| "grad_norm": 0.1290796846151352, |
| "learning_rate": 1.5749893125160954e-08, |
| "loss": 0.14156577587127686, |
| "step": 350, |
| "token_acc": 0.9530219643471618 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 354, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.089589125686231e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
