| { | |
| "best_metric": 0.9609226586529557, | |
| "best_model_checkpoint": "test/checkpoint-1000", | |
| "epoch": 19.169329073482427, | |
| "eval_steps": 100, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2779552715654952, | |
| "eval_accuracy": 0.9816936117791817, | |
| "eval_f1": 0.9385833639194645, | |
| "eval_loss": 0.05918360874056816, | |
| "eval_precision": 0.9250824202462911, | |
| "eval_recall": 0.9524842180444199, | |
| "eval_runtime": 165.0893, | |
| "eval_samples_per_second": 2.102, | |
| "eval_steps_per_second": 1.054, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5559105431309903, | |
| "eval_accuracy": 0.9845452196763693, | |
| "eval_f1": 0.9493651456881923, | |
| "eval_loss": 0.05179167166352272, | |
| "eval_precision": 0.9371622417885823, | |
| "eval_recall": 0.9618900331766658, | |
| "eval_runtime": 165.8874, | |
| "eval_samples_per_second": 2.092, | |
| "eval_steps_per_second": 1.049, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.8338658146964857, | |
| "eval_accuracy": 0.9859493975213447, | |
| "eval_f1": 0.9534633937694555, | |
| "eval_loss": 0.05195005238056183, | |
| "eval_precision": 0.9441491113968228, | |
| "eval_recall": 0.9629632829539521, | |
| "eval_runtime": 165.8659, | |
| "eval_samples_per_second": 2.092, | |
| "eval_steps_per_second": 1.049, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.111821086261981, | |
| "eval_accuracy": 0.9867111571310738, | |
| "eval_f1": 0.9563248176638556, | |
| "eval_loss": 0.05341144651174545, | |
| "eval_precision": 0.9464087629117955, | |
| "eval_recall": 0.9664508647436488, | |
| "eval_runtime": 165.8661, | |
| "eval_samples_per_second": 2.092, | |
| "eval_steps_per_second": 1.049, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.389776357827476, | |
| "grad_norm": 1.3225843906402588, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0581, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.389776357827476, | |
| "eval_accuracy": 0.9881758012724539, | |
| "eval_f1": 0.9607765866129376, | |
| "eval_loss": 0.05545532703399658, | |
| "eval_precision": 0.9561740033258127, | |
| "eval_recall": 0.9654236936687863, | |
| "eval_runtime": 166.1394, | |
| "eval_samples_per_second": 2.089, | |
| "eval_steps_per_second": 1.047, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.667731629392971, | |
| "eval_accuracy": 0.9876475167880766, | |
| "eval_f1": 0.9593047596775092, | |
| "eval_loss": 0.05594188719987869, | |
| "eval_precision": 0.9519859864988651, | |
| "eval_recall": 0.9667369366878629, | |
| "eval_runtime": 165.0742, | |
| "eval_samples_per_second": 2.102, | |
| "eval_steps_per_second": 1.054, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.945686900958467, | |
| "eval_accuracy": 0.9861775203668713, | |
| "eval_f1": 0.9541556967684495, | |
| "eval_loss": 0.06466494500637054, | |
| "eval_precision": 0.9495223935082022, | |
| "eval_recall": 0.9588344392221915, | |
| "eval_runtime": 165.512, | |
| "eval_samples_per_second": 2.097, | |
| "eval_steps_per_second": 1.051, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.223642172523961, | |
| "eval_accuracy": 0.987931766243663, | |
| "eval_f1": 0.9600553547912903, | |
| "eval_loss": 0.07039085775613785, | |
| "eval_precision": 0.9571241565658107, | |
| "eval_recall": 0.9630045617915399, | |
| "eval_runtime": 165.1633, | |
| "eval_samples_per_second": 2.101, | |
| "eval_steps_per_second": 1.054, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.501597444089457, | |
| "eval_accuracy": 0.9873081533159109, | |
| "eval_f1": 0.957732138438941, | |
| "eval_loss": 0.072791688144207, | |
| "eval_precision": 0.9476758884291113, | |
| "eval_recall": 0.9680041010045157, | |
| "eval_runtime": 166.1498, | |
| "eval_samples_per_second": 2.088, | |
| "eval_steps_per_second": 1.047, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.779552715654953, | |
| "grad_norm": 1.008128046989441, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0113, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.779552715654953, | |
| "eval_accuracy": 0.9883580680989368, | |
| "eval_f1": 0.9609226586529557, | |
| "eval_loss": 0.070257768034935, | |
| "eval_precision": 0.9555934230761928, | |
| "eval_recall": 0.9663116686634105, | |
| "eval_runtime": 165.5164, | |
| "eval_samples_per_second": 2.096, | |
| "eval_steps_per_second": 1.051, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.057507987220447, | |
| "eval_accuracy": 0.9876378248219065, | |
| "eval_f1": 0.9585960793498106, | |
| "eval_loss": 0.07850438356399536, | |
| "eval_precision": 0.9469678165075398, | |
| "eval_recall": 0.9705134703406753, | |
| "eval_runtime": 165.1708, | |
| "eval_samples_per_second": 2.101, | |
| "eval_steps_per_second": 1.053, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.335463258785943, | |
| "eval_accuracy": 0.9870376462004166, | |
| "eval_f1": 0.9562580148084375, | |
| "eval_loss": 0.0813131257891655, | |
| "eval_precision": 0.9487462712234356, | |
| "eval_recall": 0.9638896568672626, | |
| "eval_runtime": 165.2596, | |
| "eval_samples_per_second": 2.1, | |
| "eval_steps_per_second": 1.053, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.61341853035144, | |
| "eval_accuracy": 0.9879028350013641, | |
| "eval_f1": 0.9592724777593, | |
| "eval_loss": 0.0847664400935173, | |
| "eval_precision": 0.9523574792749595, | |
| "eval_recall": 0.9662886293121986, | |
| "eval_runtime": 166.5822, | |
| "eval_samples_per_second": 2.083, | |
| "eval_steps_per_second": 1.045, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 17.891373801916934, | |
| "eval_accuracy": 0.9879352379927389, | |
| "eval_f1": 0.9593296707640014, | |
| "eval_loss": 0.08636707812547684, | |
| "eval_precision": 0.9518098587623206, | |
| "eval_recall": 0.9669692501459158, | |
| "eval_runtime": 165.8109, | |
| "eval_samples_per_second": 2.093, | |
| "eval_steps_per_second": 1.049, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.169329073482427, | |
| "grad_norm": 0.3258835971355438, | |
| "learning_rate": 0.0, | |
| "loss": 0.0039, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 19.169329073482427, | |
| "eval_accuracy": 0.98795664711204, | |
| "eval_f1": 0.959393611777229, | |
| "eval_loss": 0.08625596016645432, | |
| "eval_precision": 0.9520241523929792, | |
| "eval_recall": 0.9668780527140356, | |
| "eval_runtime": 164.9718, | |
| "eval_samples_per_second": 2.103, | |
| "eval_steps_per_second": 1.055, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 3163207421952000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |