| { | |
| "best_metric": 1.1021808385849, | |
| "best_model_checkpoint": "./0.4b_finetuned_results/checkpoint-500", | |
| "epoch": 0.7485029940119761, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014970059880239521, | |
| "grad_norm": 4.375, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.8882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029940119760479042, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 3.2257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04491017964071856, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 0.0002, | |
| "loss": 2.92, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.059880239520958084, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 0.00019999938668382333, | |
| "loss": 2.3984, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0748502994011976, | |
| "grad_norm": 1.484375, | |
| "learning_rate": 0.00019999754674281632, | |
| "loss": 2.1626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08982035928143713, | |
| "grad_norm": 3.375, | |
| "learning_rate": 0.0001999944801995484, | |
| "loss": 2.0388, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10479041916167664, | |
| "grad_norm": 1.7890625, | |
| "learning_rate": 0.0001999901870916347, | |
| "loss": 2.0121, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 0.00019998466747173592, | |
| "loss": 1.8579, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1347305389221557, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 0.00019997792140755746, | |
| "loss": 1.8254, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1497005988023952, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 0.0001999699489818488, | |
| "loss": 1.7037, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16467065868263472, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 0.00019996075029240219, | |
| "loss": 1.6647, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17964071856287425, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 0.0001999503254520518, | |
| "loss": 1.5988, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.19461077844311378, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 0.00019993867458867207, | |
| "loss": 1.6197, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20958083832335328, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 0.00019992579784517626, | |
| "loss": 1.5954, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2245508982035928, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 0.00019991169537951468, | |
| "loss": 1.5666, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.00019989636736467278, | |
| "loss": 1.5227, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.25449101796407186, | |
| "grad_norm": 0.34375, | |
| "learning_rate": 0.00019987981398866887, | |
| "loss": 1.5048, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2694610778443114, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 0.00019986203545455203, | |
| "loss": 1.4755, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2844311377245509, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 0.0001998430319803996, | |
| "loss": 1.4505, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2994011976047904, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 0.00019982280379931422, | |
| "loss": 1.4295, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3143712574850299, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 0.00019980135115942136, | |
| "loss": 1.4683, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.32934131736526945, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 0.00019977867432386604, | |
| "loss": 1.4427, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.344311377245509, | |
| "grad_norm": 0.357421875, | |
| "learning_rate": 0.00019975477357080966, | |
| "loss": 1.3852, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 0.00019972964919342663, | |
| "loss": 1.427, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.37425149700598803, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 0.00019970330149990062, | |
| "loss": 1.3759, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.38922155688622756, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 1.3559, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4041916167664671, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 0.00019964693747217874, | |
| "loss": 1.3715, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.41916167664670656, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 0.00019961692182936225, | |
| "loss": 1.2932, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4341317365269461, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 0.00019958568425315314, | |
| "loss": 1.3086, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4491017964071856, | |
| "grad_norm": 0.291015625, | |
| "learning_rate": 0.00019955322512672162, | |
| "loss": 1.3091, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.46407185628742514, | |
| "grad_norm": 0.248046875, | |
| "learning_rate": 0.00019951954484822182, | |
| "loss": 1.3196, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 0.00019948464383078696, | |
| "loss": 1.2944, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4940119760479042, | |
| "grad_norm": 0.375, | |
| "learning_rate": 0.00019944852250252418, | |
| "loss": 1.3461, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5089820359281437, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 0.00019941118130650942, | |
| "loss": 1.3221, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5239520958083832, | |
| "grad_norm": 0.23828125, | |
| "learning_rate": 0.00019937262070078183, | |
| "loss": 1.3111, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5389221556886228, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 0.0001993328411583383, | |
| "loss": 1.3128, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5538922155688623, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 0.00019929184316712758, | |
| "loss": 1.2618, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5688622754491018, | |
| "grad_norm": 0.29296875, | |
| "learning_rate": 0.00019924962723004425, | |
| "loss": 1.2893, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5838323353293413, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 0.0001992061938649227, | |
| "loss": 1.2727, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "grad_norm": 0.3359375, | |
| "learning_rate": 0.0001991615436045306, | |
| "loss": 1.293, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6137724550898204, | |
| "grad_norm": 0.314453125, | |
| "learning_rate": 0.0001991156769965625, | |
| "loss": 1.2692, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6287425149700598, | |
| "grad_norm": 0.326171875, | |
| "learning_rate": 0.00019906859460363307, | |
| "loss": 1.2588, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6437125748502994, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 0.00019902029700327018, | |
| "loss": 1.2576, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6586826347305389, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 0.0001989707847879078, | |
| "loss": 1.2595, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6736526946107785, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 0.00019892005856487878, | |
| "loss": 1.2331, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.688622754491018, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 0.0001988681189564074, | |
| "loss": 1.2161, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7035928143712575, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 0.0001988149665996017, | |
| "loss": 1.2675, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.718562874251497, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 0.00019876060214644566, | |
| "loss": 1.269, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7335329341317365, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 0.00019870502626379127, | |
| "loss": 1.2342, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7485029940119761, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 0.00019864823963335033, | |
| "loss": 1.2351, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7485029940119761, | |
| "eval_loss": 1.1021808385849, | |
| "eval_runtime": 109.4058, | |
| "eval_samples_per_second": 9.14, | |
| "eval_steps_per_second": 1.143, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 14, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.479612424192e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |