| { |
| "best_global_step": 10000, |
| "best_metric": 0.10736154764890671, |
| "best_model_checkpoint": "myanmar_text_segmentation_model/checkpoint-10000", |
| "epoch": 0.9188642837452908, |
| "eval_steps": 1000, |
| "global_step": 10000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04594321418726454, |
| "grad_norm": 0.577109158039093, |
| "learning_rate": 1.9816594688964442e-05, |
| "loss": 0.1144, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.09188642837452908, |
| "grad_norm": 0.8819814324378967, |
| "learning_rate": 1.9632821832215383e-05, |
| "loss": 0.1133, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.09188642837452908, |
| "eval_accuracy": 0.9564004775738034, |
| "eval_f1": 0.7581789101913106, |
| "eval_loss": 0.11448723077774048, |
| "eval_precision": 0.7703745996379334, |
| "eval_recall": 0.7463633395484631, |
| "eval_runtime": 465.4607, |
| "eval_samples_per_second": 61.528, |
| "eval_steps_per_second": 1.231, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.1378296425617936, |
| "grad_norm": 0.5137984156608582, |
| "learning_rate": 1.9449048975466325e-05, |
| "loss": 0.1119, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.18377285674905816, |
| "grad_norm": 0.6753482222557068, |
| "learning_rate": 1.9265276118717266e-05, |
| "loss": 0.1115, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.18377285674905816, |
| "eval_accuracy": 0.9565513036953667, |
| "eval_f1": 0.7631813253052621, |
| "eval_loss": 0.11509840190410614, |
| "eval_precision": 0.7619568901058112, |
| "eval_recall": 0.7644097020785157, |
| "eval_runtime": 471.4797, |
| "eval_samples_per_second": 60.743, |
| "eval_steps_per_second": 1.215, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.2297160709363227, |
| "grad_norm": 0.46862444281578064, |
| "learning_rate": 1.9081503261968207e-05, |
| "loss": 0.1083, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.2756592851235872, |
| "grad_norm": 0.6514066457748413, |
| "learning_rate": 1.889773040521915e-05, |
| "loss": 0.1085, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.2756592851235872, |
| "eval_accuracy": 0.955793370748351, |
| "eval_f1": 0.7617613129080717, |
| "eval_loss": 0.11627302318811417, |
| "eval_precision": 0.7514122514122514, |
| "eval_recall": 0.7723994268768838, |
| "eval_runtime": 464.541, |
| "eval_samples_per_second": 61.65, |
| "eval_steps_per_second": 1.233, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.3216024993108518, |
| "grad_norm": 0.5837205052375793, |
| "learning_rate": 1.8713957548470093e-05, |
| "loss": 0.1068, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.3675457134981163, |
| "grad_norm": 0.590044379234314, |
| "learning_rate": 1.8530184691721034e-05, |
| "loss": 0.1076, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.3675457134981163, |
| "eval_accuracy": 0.9567566300121167, |
| "eval_f1": 0.7569129075628852, |
| "eval_loss": 0.11681018769741058, |
| "eval_precision": 0.7790560842692136, |
| "eval_recall": 0.7359936967250493, |
| "eval_runtime": 464.1614, |
| "eval_samples_per_second": 61.701, |
| "eval_steps_per_second": 1.234, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.41348892768538087, |
| "grad_norm": 0.43107616901397705, |
| "learning_rate": 1.8346411834971975e-05, |
| "loss": 0.1071, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.4594321418726454, |
| "grad_norm": 0.6132990121841431, |
| "learning_rate": 1.8162638978222916e-05, |
| "loss": 0.1056, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.4594321418726454, |
| "eval_accuracy": 0.9576032842071108, |
| "eval_f1": 0.7661190672004459, |
| "eval_loss": 0.11183962970972061, |
| "eval_precision": 0.7719609680194174, |
| "eval_recall": 0.7603649207638403, |
| "eval_runtime": 473.1438, |
| "eval_samples_per_second": 60.529, |
| "eval_steps_per_second": 1.211, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.5053753560599099, |
| "grad_norm": 0.4892466962337494, |
| "learning_rate": 1.7978866121473858e-05, |
| "loss": 0.1154, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.5513185702471745, |
| "grad_norm": 0.8282744884490967, |
| "learning_rate": 1.7795093264724802e-05, |
| "loss": 0.1141, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.5513185702471745, |
| "eval_accuracy": 0.9580804777765948, |
| "eval_f1": 0.7681685393564336, |
| "eval_loss": 0.11200755834579468, |
| "eval_precision": 0.7751412801894542, |
| "eval_recall": 0.7613201259575663, |
| "eval_runtime": 463.6002, |
| "eval_samples_per_second": 61.775, |
| "eval_steps_per_second": 1.236, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.597261784434439, |
| "grad_norm": 0.44782352447509766, |
| "learning_rate": 1.7611320407975743e-05, |
| "loss": 0.1135, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.6432049986217035, |
| "grad_norm": 0.5544679760932922, |
| "learning_rate": 1.7427547551226684e-05, |
| "loss": 0.1154, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.6432049986217035, |
| "eval_accuracy": 0.9576146912247081, |
| "eval_f1": 0.7686338805157804, |
| "eval_loss": 0.11075501888990402, |
| "eval_precision": 0.7656366294168357, |
| "eval_recall": 0.7716546906241484, |
| "eval_runtime": 472.6577, |
| "eval_samples_per_second": 60.591, |
| "eval_steps_per_second": 1.212, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.6891482128089681, |
| "grad_norm": 0.4101652503013611, |
| "learning_rate": 1.7243774694477626e-05, |
| "loss": 0.1123, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.7350914269962326, |
| "grad_norm": 0.5032928586006165, |
| "learning_rate": 1.7060001837728567e-05, |
| "loss": 0.1128, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.7350914269962326, |
| "eval_accuracy": 0.9583707230021242, |
| "eval_f1": 0.7702898098589065, |
| "eval_loss": 0.10922538489103317, |
| "eval_precision": 0.7744496660220761, |
| "eval_recall": 0.7661744031991279, |
| "eval_runtime": 465.4833, |
| "eval_samples_per_second": 61.525, |
| "eval_steps_per_second": 1.231, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.7810346411834972, |
| "grad_norm": 0.5559138059616089, |
| "learning_rate": 1.687622898097951e-05, |
| "loss": 0.112, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.8269778553707617, |
| "grad_norm": 0.7113578915596008, |
| "learning_rate": 1.6692456124230453e-05, |
| "loss": 0.1082, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.8269778553707617, |
| "eval_accuracy": 0.9588998818739956, |
| "eval_f1": 0.7713698035177239, |
| "eval_loss": 0.10946337133646011, |
| "eval_precision": 0.78099547261026, |
| "eval_recall": 0.7619785159781004, |
| "eval_runtime": 477.2564, |
| "eval_samples_per_second": 60.008, |
| "eval_steps_per_second": 1.201, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.8729210695580263, |
| "grad_norm": 0.4333978593349457, |
| "learning_rate": 1.6508683267481394e-05, |
| "loss": 0.1116, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.9188642837452908, |
| "grad_norm": 0.3579271137714386, |
| "learning_rate": 1.6324910410732335e-05, |
| "loss": 0.1101, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.9188642837452908, |
| "eval_accuracy": 0.9590893651107495, |
| "eval_f1": 0.7721416651417115, |
| "eval_loss": 0.10736154764890671, |
| "eval_precision": 0.7816850586599052, |
| "eval_recall": 0.7628284867013311, |
| "eval_runtime": 478.6898, |
| "eval_samples_per_second": 59.828, |
| "eval_steps_per_second": 1.197, |
| "step": 10000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 54415, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1635827819055621e+17, |
| "train_batch_size": 50, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
