| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 2208, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "step": 276, | |
| "train_eval_accuracy": 0.7003401360544218, | |
| "train_eval_f1": 0.6599009769808177, | |
| "train_eval_loss": 1.0742188692092896, | |
| "train_eval_precision": 0.7685367987097715, | |
| "train_eval_recall": 0.7009459009381873, | |
| "train_loss": 1.074218988418579, | |
| "train_runtime": 292.4292, | |
| "train_samples_per_second": 30.161, | |
| "train_steps_per_second": 0.944 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6865079365079365, | |
| "eval_f1": 0.6448401353068663, | |
| "eval_loss": 1.1159266233444214, | |
| "eval_precision": 0.7389370546469851, | |
| "eval_recall": 0.685088186510769, | |
| "eval_runtime": 125.2302, | |
| "eval_samples_per_second": 30.184, | |
| "eval_steps_per_second": 0.95, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 552, | |
| "train_eval_accuracy": 0.9049886621315193, | |
| "train_eval_f1": 0.9047389370162652, | |
| "train_eval_loss": 0.3874468207359314, | |
| "train_eval_precision": 0.9101320070777226, | |
| "train_eval_recall": 0.9053131019265812, | |
| "train_loss": 0.3874468505382538, | |
| "train_runtime": 292.6477, | |
| "train_samples_per_second": 30.139, | |
| "train_steps_per_second": 0.943 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.873015873015873, | |
| "eval_f1": 0.8716046163578155, | |
| "eval_loss": 0.4920203685760498, | |
| "eval_precision": 0.8781278884267814, | |
| "eval_recall": 0.8725450168508944, | |
| "eval_runtime": 125.7044, | |
| "eval_samples_per_second": 30.071, | |
| "eval_steps_per_second": 0.947, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 828, | |
| "train_eval_accuracy": 0.9286848072562358, | |
| "train_eval_f1": 0.9285171455529603, | |
| "train_eval_loss": 0.27065399289131165, | |
| "train_eval_precision": 0.9322649415650033, | |
| "train_eval_recall": 0.9289123109383434, | |
| "train_loss": 0.27065402269363403, | |
| "train_runtime": 292.5422, | |
| "train_samples_per_second": 30.149, | |
| "train_steps_per_second": 0.943 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8973544973544973, | |
| "eval_f1": 0.8961220197070991, | |
| "eval_loss": 0.42477917671203613, | |
| "eval_precision": 0.9011567773926408, | |
| "eval_recall": 0.8971253090647534, | |
| "eval_runtime": 125.1591, | |
| "eval_samples_per_second": 30.202, | |
| "eval_steps_per_second": 0.951, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1104, | |
| "train_eval_accuracy": 0.9471655328798186, | |
| "train_eval_f1": 0.947517595979444, | |
| "train_eval_loss": 0.2088230848312378, | |
| "train_eval_precision": 0.9488916851742717, | |
| "train_eval_recall": 0.9477037054061244, | |
| "train_loss": 0.2088230848312378, | |
| "train_runtime": 292.1312, | |
| "train_samples_per_second": 30.192, | |
| "train_steps_per_second": 0.945 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9010582010582011, | |
| "eval_f1": 0.8999224906052751, | |
| "eval_loss": 0.41053256392478943, | |
| "eval_precision": 0.9025635496532717, | |
| "eval_recall": 0.9002552887231217, | |
| "eval_runtime": 125.1369, | |
| "eval_samples_per_second": 30.207, | |
| "eval_steps_per_second": 0.951, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1380, | |
| "train_eval_accuracy": 0.9515873015873015, | |
| "train_eval_f1": 0.9516673939530801, | |
| "train_eval_loss": 0.17656771838665009, | |
| "train_eval_precision": 0.9539169437133798, | |
| "train_eval_recall": 0.9520537526614696, | |
| "train_loss": 0.1765676885843277, | |
| "train_runtime": 292.8194, | |
| "train_samples_per_second": 30.121, | |
| "train_steps_per_second": 0.943 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9063492063492063, | |
| "eval_f1": 0.9046138481463505, | |
| "eval_loss": 0.41682690382003784, | |
| "eval_precision": 0.9088264652953383, | |
| "eval_recall": 0.9051041885149284, | |
| "eval_runtime": 125.6464, | |
| "eval_samples_per_second": 30.084, | |
| "eval_steps_per_second": 0.947, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1656, | |
| "train_eval_accuracy": 0.9654195011337868, | |
| "train_eval_f1": 0.9656476663607069, | |
| "train_eval_loss": 0.12671761214733124, | |
| "train_eval_precision": 0.9666620904833755, | |
| "train_eval_recall": 0.9657485060432522, | |
| "train_loss": 0.12671762704849243, | |
| "train_runtime": 292.8539, | |
| "train_samples_per_second": 30.117, | |
| "train_steps_per_second": 0.942 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9084656084656084, | |
| "eval_f1": 0.9069212907450369, | |
| "eval_loss": 0.41428086161613464, | |
| "eval_precision": 0.909310676401177, | |
| "eval_recall": 0.9074800568136571, | |
| "eval_runtime": 125.6663, | |
| "eval_samples_per_second": 30.08, | |
| "eval_steps_per_second": 0.947, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1932, | |
| "train_eval_accuracy": 0.9712018140589569, | |
| "train_eval_f1": 0.9713117879463059, | |
| "train_eval_loss": 0.10472333431243896, | |
| "train_eval_precision": 0.9726857205787973, | |
| "train_eval_recall": 0.9716513762432712, | |
| "train_loss": 0.10472334921360016, | |
| "train_runtime": 293.0912, | |
| "train_samples_per_second": 30.093, | |
| "train_steps_per_second": 0.942 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9058201058201059, | |
| "eval_f1": 0.9040971215004513, | |
| "eval_loss": 0.4402031898498535, | |
| "eval_precision": 0.9063334381728124, | |
| "eval_recall": 0.9047346717153943, | |
| "eval_runtime": 125.6961, | |
| "eval_samples_per_second": 30.073, | |
| "eval_steps_per_second": 0.947, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 2208, | |
| "train_eval_accuracy": 0.977437641723356, | |
| "train_eval_f1": 0.9777628423711627, | |
| "train_eval_loss": 0.08053447306156158, | |
| "train_eval_precision": 0.9778969889316966, | |
| "train_eval_recall": 0.9778987153746018, | |
| "train_loss": 0.08053448051214218, | |
| "train_runtime": 293.5192, | |
| "train_samples_per_second": 30.049, | |
| "train_steps_per_second": 0.94 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9031746031746032, | |
| "eval_f1": 0.9017850721426728, | |
| "eval_loss": 0.45825621485710144, | |
| "eval_precision": 0.9036277073612298, | |
| "eval_recall": 0.902066631184587, | |
| "eval_runtime": 125.7628, | |
| "eval_samples_per_second": 30.057, | |
| "eval_steps_per_second": 0.946, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 2208, | |
| "total_flos": 1.85717836136448e+16, | |
| "train_loss": 0.5860137939453125, | |
| "train_runtime": 10564.8969, | |
| "train_samples_per_second": 12.523, | |
| "train_steps_per_second": 0.392 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9031746031746032, | |
| "eval_f1": 0.9017850721426728, | |
| "eval_loss": 0.45825621485710144, | |
| "eval_precision": 0.9036277073612298, | |
| "eval_recall": 0.902066631184587, | |
| "eval_runtime": 125.8523, | |
| "eval_samples_per_second": 30.035, | |
| "eval_steps_per_second": 0.946, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 2208, | |
| "train_en_eval_accuracy": 0.977437641723356, | |
| "train_en_eval_f1": 0.9777628423711627, | |
| "train_en_eval_loss": 0.08053447306156158, | |
| "train_en_eval_precision": 0.9778969889316966, | |
| "train_en_eval_recall": 0.9778987153746018, | |
| "train_en_loss": 0.08053448051214218, | |
| "train_en_runtime": 292.6514, | |
| "train_en_samples_per_second": 30.138, | |
| "train_en_steps_per_second": 0.943 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 2208, | |
| "test_en_eval_accuracy": 0.9031746031746032, | |
| "test_en_eval_f1": 0.9017850721426728, | |
| "test_en_eval_loss": 0.45825621485710144, | |
| "test_en_eval_precision": 0.9036277073612298, | |
| "test_en_eval_recall": 0.902066631184587, | |
| "test_en_loss": 0.45825621485710144, | |
| "test_en_runtime": 125.7293, | |
| "test_en_samples_per_second": 30.065, | |
| "test_en_steps_per_second": 0.946 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 1.85717836136448e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |