| { | |
| "best_metric": 0.4873823821544647, | |
| "best_model_checkpoint": "Model-Meme/Typhoon/Typhoon1.5-Sentiment-Fold1/checkpoint-3824", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 19120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2615062761506276, | |
| "grad_norm": 1.630317211151123, | |
| "learning_rate": 8.710801393728223e-06, | |
| "loss": 0.888, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5230125523012552, | |
| "grad_norm": 1.2002062797546387, | |
| "learning_rate": 9.986987223454062e-06, | |
| "loss": 0.5478, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7845188284518828, | |
| "grad_norm": 1.279449224472046, | |
| "learning_rate": 9.93861382775312e-06, | |
| "loss": 0.551, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.49981698393821716, | |
| "eval_runtime": 106.1621, | |
| "eval_samples_per_second": 9.005, | |
| "eval_steps_per_second": 9.005, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 1.0460251046025104, | |
| "grad_norm": 2.099172830581665, | |
| "learning_rate": 9.854833795480441e-06, | |
| "loss": 0.5293, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.3075313807531381, | |
| "grad_norm": 1.455888032913208, | |
| "learning_rate": 9.736519159090385e-06, | |
| "loss": 0.4982, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.5690376569037658, | |
| "grad_norm": 1.8300031423568726, | |
| "learning_rate": 9.584044234397988e-06, | |
| "loss": 0.49, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.8305439330543933, | |
| "grad_norm": 1.8547563552856445, | |
| "learning_rate": 9.39870470560879e-06, | |
| "loss": 0.4965, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4873823821544647, | |
| "eval_runtime": 106.0089, | |
| "eval_samples_per_second": 9.018, | |
| "eval_steps_per_second": 9.018, | |
| "step": 3824 | |
| }, | |
| { | |
| "epoch": 2.092050209205021, | |
| "grad_norm": 1.9847608804702759, | |
| "learning_rate": 9.181829336130319e-06, | |
| "loss": 0.479, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.3535564853556483, | |
| "grad_norm": 2.7613589763641357, | |
| "learning_rate": 8.934972980757115e-06, | |
| "loss": 0.43, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.6150627615062763, | |
| "grad_norm": 2.3412399291992188, | |
| "learning_rate": 8.660482449775261e-06, | |
| "loss": 0.4243, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.8765690376569037, | |
| "grad_norm": 3.2489728927612305, | |
| "learning_rate": 8.359226157693385e-06, | |
| "loss": 0.4525, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.49290716648101807, | |
| "eval_runtime": 106.1261, | |
| "eval_samples_per_second": 9.008, | |
| "eval_steps_per_second": 9.008, | |
| "step": 5736 | |
| }, | |
| { | |
| "epoch": 3.1380753138075312, | |
| "grad_norm": 3.534010410308838, | |
| "learning_rate": 8.033886407403191e-06, | |
| "loss": 0.4122, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.399581589958159, | |
| "grad_norm": 4.633702754974365, | |
| "learning_rate": 7.686795672489905e-06, | |
| "loss": 0.3837, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.6610878661087867, | |
| "grad_norm": 4.420021057128906, | |
| "learning_rate": 7.320442366896608e-06, | |
| "loss": 0.3789, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.922594142259414, | |
| "grad_norm": 3.9446756839752197, | |
| "learning_rate": 6.93823377901452e-06, | |
| "loss": 0.3822, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5124192237854004, | |
| "eval_runtime": 103.7839, | |
| "eval_samples_per_second": 9.211, | |
| "eval_steps_per_second": 9.211, | |
| "step": 7648 | |
| }, | |
| { | |
| "epoch": 4.184100418410042, | |
| "grad_norm": 3.961578607559204, | |
| "learning_rate": 6.541379114428449e-06, | |
| "loss": 0.3587, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.445606694560669, | |
| "grad_norm": 5.545160293579102, | |
| "learning_rate": 6.13347376800588e-06, | |
| "loss": 0.3221, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.707112970711297, | |
| "grad_norm": 4.203147888183594, | |
| "learning_rate": 5.7174421547466815e-06, | |
| "loss": 0.3245, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.968619246861925, | |
| "grad_norm": 5.057765007019043, | |
| "learning_rate": 5.297112430378265e-06, | |
| "loss": 0.3273, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5422254204750061, | |
| "eval_runtime": 103.666, | |
| "eval_samples_per_second": 9.222, | |
| "eval_steps_per_second": 9.222, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 5.2301255230125525, | |
| "grad_norm": 4.777406215667725, | |
| "learning_rate": 4.873814405549272e-06, | |
| "loss": 0.2841, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.49163179916318, | |
| "grad_norm": 5.399323463439941, | |
| "learning_rate": 4.451421049042024e-06, | |
| "loss": 0.2763, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.7531380753138075, | |
| "grad_norm": 7.916058540344238, | |
| "learning_rate": 4.032960645429033e-06, | |
| "loss": 0.2981, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.595160186290741, | |
| "eval_runtime": 103.9764, | |
| "eval_samples_per_second": 9.194, | |
| "eval_steps_per_second": 9.194, | |
| "step": 11472 | |
| }, | |
| { | |
| "epoch": 6.014644351464435, | |
| "grad_norm": 7.495786190032959, | |
| "learning_rate": 3.6222474467023006e-06, | |
| "loss": 0.2741, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.2761506276150625, | |
| "grad_norm": 5.999951362609863, | |
| "learning_rate": 3.220580839399443e-06, | |
| "loss": 0.2307, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.53765690376569, | |
| "grad_norm": 6.181816101074219, | |
| "learning_rate": 2.8316715056404507e-06, | |
| "loss": 0.242, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.799163179916318, | |
| "grad_norm": 4.290989398956299, | |
| "learning_rate": 2.4583076714174803e-06, | |
| "loss": 0.2416, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.6211022138595581, | |
| "eval_runtime": 103.368, | |
| "eval_samples_per_second": 9.249, | |
| "eval_steps_per_second": 9.249, | |
| "step": 13384 | |
| }, | |
| { | |
| "epoch": 7.060669456066946, | |
| "grad_norm": 7.918560028076172, | |
| "learning_rate": 2.103166111641151e-06, | |
| "loss": 0.2382, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.322175732217573, | |
| "grad_norm": 4.114747524261475, | |
| "learning_rate": 1.7694393589342428e-06, | |
| "loss": 0.2059, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.583682008368201, | |
| "grad_norm": 5.888193130493164, | |
| "learning_rate": 1.4581832353425335e-06, | |
| "loss": 0.2127, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 7.845188284518828, | |
| "grad_norm": 5.456567287445068, | |
| "learning_rate": 1.1723196253920394e-06, | |
| "loss": 0.2116, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6545947194099426, | |
| "eval_runtime": 107.6369, | |
| "eval_samples_per_second": 8.882, | |
| "eval_steps_per_second": 8.882, | |
| "step": 15296 | |
| }, | |
| { | |
| "epoch": 8.106694560669457, | |
| "grad_norm": 7.760040283203125, | |
| "learning_rate": 9.138979845169372e-07, | |
| "loss": 0.1854, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 8.368200836820083, | |
| "grad_norm": 6.356107234954834, | |
| "learning_rate": 6.847710271508462e-07, | |
| "loss": 0.1877, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 8.629707112970712, | |
| "grad_norm": 8.600861549377441, | |
| "learning_rate": 4.865814439740219e-07, | |
| "loss": 0.1922, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 8.891213389121338, | |
| "grad_norm": 9.489436149597168, | |
| "learning_rate": 3.207501248937539e-07, | |
| "loss": 0.188, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6717672944068909, | |
| "eval_runtime": 142.6914, | |
| "eval_samples_per_second": 6.7, | |
| "eval_steps_per_second": 6.7, | |
| "step": 17208 | |
| }, | |
| { | |
| "epoch": 9.152719665271967, | |
| "grad_norm": 4.833051681518555, | |
| "learning_rate": 1.886963892774535e-07, | |
| "loss": 0.1797, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 9.414225941422593, | |
| "grad_norm": 4.518942356109619, | |
| "learning_rate": 9.083801976963458e-08, | |
| "loss": 0.1787, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 9.675732217573222, | |
| "grad_norm": 7.789809703826904, | |
| "learning_rate": 2.8175136316832e-08, | |
| "loss": 0.1768, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 9.93723849372385, | |
| "grad_norm": 5.010494232177734, | |
| "learning_rate": 1.1569908788744423e-09, | |
| "loss": 0.1747, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.6839816570281982, | |
| "eval_runtime": 142.9966, | |
| "eval_samples_per_second": 6.685, | |
| "eval_steps_per_second": 6.685, | |
| "step": 19120 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 19120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 3.7134220695783014e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |