| { |
| "best_metric": 0.8996119975479232, |
| "best_model_checkpoint": "distilbert-type-classifier/checkpoint-3296", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 3296, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06067961165048544, |
| "grad_norm": 7.083491325378418, |
| "learning_rate": 1.959546925566343e-05, |
| "loss": 1.3291, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.12135922330097088, |
| "grad_norm": 5.435772895812988, |
| "learning_rate": 1.919093851132686e-05, |
| "loss": 0.7948, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1820388349514563, |
| "grad_norm": 5.531534671783447, |
| "learning_rate": 1.8786407766990295e-05, |
| "loss": 0.59, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.24271844660194175, |
| "grad_norm": 5.0550031661987305, |
| "learning_rate": 1.838187702265372e-05, |
| "loss": 0.5483, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.30339805825242716, |
| "grad_norm": 9.326889038085938, |
| "learning_rate": 1.7977346278317155e-05, |
| "loss": 0.472, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3640776699029126, |
| "grad_norm": 11.223947525024414, |
| "learning_rate": 1.7572815533980585e-05, |
| "loss": 0.4334, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.42475728155339804, |
| "grad_norm": 6.310647487640381, |
| "learning_rate": 1.7168284789644015e-05, |
| "loss": 0.3993, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4854368932038835, |
| "grad_norm": 13.495203018188477, |
| "learning_rate": 1.6763754045307445e-05, |
| "loss": 0.3976, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5461165048543689, |
| "grad_norm": 9.985793113708496, |
| "learning_rate": 1.6359223300970874e-05, |
| "loss": 0.4045, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.6067961165048543, |
| "grad_norm": 5.920831203460693, |
| "learning_rate": 1.5954692556634304e-05, |
| "loss": 0.3661, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6674757281553398, |
| "grad_norm": 7.346311092376709, |
| "learning_rate": 1.5550161812297734e-05, |
| "loss": 0.3527, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.7281553398058253, |
| "grad_norm": 7.223079681396484, |
| "learning_rate": 1.5145631067961166e-05, |
| "loss": 0.361, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7888349514563107, |
| "grad_norm": 5.1326799392700195, |
| "learning_rate": 1.4741100323624598e-05, |
| "loss": 0.3892, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.8495145631067961, |
| "grad_norm": 7.782454967498779, |
| "learning_rate": 1.4336569579288026e-05, |
| "loss": 0.3502, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.9101941747572816, |
| "grad_norm": 8.951793670654297, |
| "learning_rate": 1.3932038834951458e-05, |
| "loss": 0.2934, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 9.385202407836914, |
| "learning_rate": 1.3527508090614887e-05, |
| "loss": 0.3436, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8803116147308782, |
| "eval_f1": 0.87963672068735, |
| "eval_loss": 0.30396342277526855, |
| "eval_precision": 0.8827457335389428, |
| "eval_recall": 0.8803116147308782, |
| "eval_runtime": 21.997, |
| "eval_samples_per_second": 256.762, |
| "eval_steps_per_second": 16.048, |
| "step": 1648 |
| }, |
| { |
| "epoch": 1.0315533980582525, |
| "grad_norm": 11.795103073120117, |
| "learning_rate": 1.3122977346278319e-05, |
| "loss": 0.2579, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.0922330097087378, |
| "grad_norm": 3.647850751876831, |
| "learning_rate": 1.2718446601941749e-05, |
| "loss": 0.2231, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.1529126213592233, |
| "grad_norm": 6.818081855773926, |
| "learning_rate": 1.2313915857605179e-05, |
| "loss": 0.2381, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.2135922330097086, |
| "grad_norm": 25.645702362060547, |
| "learning_rate": 1.190938511326861e-05, |
| "loss": 0.2778, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.2742718446601942, |
| "grad_norm": 20.234249114990234, |
| "learning_rate": 1.1504854368932039e-05, |
| "loss": 0.2127, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.3349514563106797, |
| "grad_norm": 5.801571846008301, |
| "learning_rate": 1.110032362459547e-05, |
| "loss": 0.2406, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.395631067961165, |
| "grad_norm": 3.5099356174468994, |
| "learning_rate": 1.0695792880258899e-05, |
| "loss": 0.2109, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.4563106796116505, |
| "grad_norm": 13.334369659423828, |
| "learning_rate": 1.029126213592233e-05, |
| "loss": 0.2268, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.516990291262136, |
| "grad_norm": 1.7576143741607666, |
| "learning_rate": 9.88673139158576e-06, |
| "loss": 0.2549, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.5776699029126213, |
| "grad_norm": 6.285398006439209, |
| "learning_rate": 9.482200647249192e-06, |
| "loss": 0.2078, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.6383495145631068, |
| "grad_norm": 10.36067008972168, |
| "learning_rate": 9.077669902912622e-06, |
| "loss": 0.2391, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.6990291262135924, |
| "grad_norm": 7.475758075714111, |
| "learning_rate": 8.673139158576054e-06, |
| "loss": 0.2334, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.7597087378640777, |
| "grad_norm": 16.30022430419922, |
| "learning_rate": 8.268608414239483e-06, |
| "loss": 0.2316, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.820388349514563, |
| "grad_norm": 4.486410617828369, |
| "learning_rate": 7.864077669902913e-06, |
| "loss": 0.2239, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.8810679611650487, |
| "grad_norm": 24.858966827392578, |
| "learning_rate": 7.459546925566343e-06, |
| "loss": 0.2162, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.941747572815534, |
| "grad_norm": 18.323312759399414, |
| "learning_rate": 7.055016181229773e-06, |
| "loss": 0.2452, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9008498583569405, |
| "eval_f1": 0.8996119975479232, |
| "eval_loss": 0.2864818572998047, |
| "eval_precision": 0.9011561063745416, |
| "eval_recall": 0.9008498583569405, |
| "eval_runtime": 22.0341, |
| "eval_samples_per_second": 256.33, |
| "eval_steps_per_second": 16.021, |
| "step": 3296 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 4944, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1745811035916288.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
