| { | |
| "best_metric": 0.369663268327713, | |
| "best_model_checkpoint": "v-mdd-2000-150/checkpoint-1569", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1569, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04780114722753346, | |
| "grad_norm": 24.8793888092041, | |
| "learning_rate": 6.687898089171975e-06, | |
| "loss": 1.391, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09560229445506692, | |
| "grad_norm": 13.04520034790039, | |
| "learning_rate": 1.464968152866242e-05, | |
| "loss": 1.3907, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14340344168260039, | |
| "grad_norm": 12.42558765411377, | |
| "learning_rate": 2.261146496815287e-05, | |
| "loss": 1.3641, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19120458891013384, | |
| "grad_norm": 40.01886749267578, | |
| "learning_rate": 3.057324840764331e-05, | |
| "loss": 1.3144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2390057361376673, | |
| "grad_norm": 16.6850528717041, | |
| "learning_rate": 3.8535031847133766e-05, | |
| "loss": 1.2513, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.28680688336520077, | |
| "grad_norm": 20.78025245666504, | |
| "learning_rate": 4.617834394904459e-05, | |
| "loss": 1.139, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33460803059273425, | |
| "grad_norm": 56.91587448120117, | |
| "learning_rate": 4.9575070821529744e-05, | |
| "loss": 1.0721, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3824091778202677, | |
| "grad_norm": 27.284250259399414, | |
| "learning_rate": 4.868980169971671e-05, | |
| "loss": 1.0102, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43021032504780116, | |
| "grad_norm": 18.555421829223633, | |
| "learning_rate": 4.7804532577903685e-05, | |
| "loss": 0.9647, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4780114722753346, | |
| "grad_norm": 17.996288299560547, | |
| "learning_rate": 4.691926345609066e-05, | |
| "loss": 0.8751, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5258126195028681, | |
| "grad_norm": 16.214096069335938, | |
| "learning_rate": 4.6033994334277626e-05, | |
| "loss": 0.7932, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5736137667304015, | |
| "grad_norm": 12.805717468261719, | |
| "learning_rate": 4.514872521246459e-05, | |
| "loss": 0.8325, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.621414913957935, | |
| "grad_norm": 9.800782203674316, | |
| "learning_rate": 4.426345609065156e-05, | |
| "loss": 0.6662, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6692160611854685, | |
| "grad_norm": 63.53221893310547, | |
| "learning_rate": 4.337818696883853e-05, | |
| "loss": 0.6896, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7170172084130019, | |
| "grad_norm": 3.3974146842956543, | |
| "learning_rate": 4.24929178470255e-05, | |
| "loss": 0.6671, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7648183556405354, | |
| "grad_norm": 20.420568466186523, | |
| "learning_rate": 4.160764872521247e-05, | |
| "loss": 0.6681, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8126195028680688, | |
| "grad_norm": 29.39402198791504, | |
| "learning_rate": 4.0722379603399435e-05, | |
| "loss": 0.7249, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.8604206500956023, | |
| "grad_norm": 2.5485928058624268, | |
| "learning_rate": 3.98371104815864e-05, | |
| "loss": 0.5976, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9082217973231358, | |
| "grad_norm": 20.10879135131836, | |
| "learning_rate": 3.895184135977337e-05, | |
| "loss": 0.7261, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.9560229445506692, | |
| "grad_norm": 20.019594192504883, | |
| "learning_rate": 3.806657223796034e-05, | |
| "loss": 0.6267, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7160611854684512, | |
| "eval_f1_macro": 0.37856670758190913, | |
| "eval_f1_micro": 0.7160611854684512, | |
| "eval_f1_weighted": 0.6476372575798962, | |
| "eval_loss": 0.59242182970047, | |
| "eval_precision_macro": 0.33835803984515156, | |
| "eval_precision_micro": 0.7160611854684512, | |
| "eval_precision_weighted": 0.6202676864244742, | |
| "eval_recall_macro": 0.47908837692380324, | |
| "eval_recall_micro": 0.7160611854684512, | |
| "eval_recall_weighted": 0.7160611854684512, | |
| "eval_runtime": 47.1589, | |
| "eval_samples_per_second": 22.18, | |
| "eval_steps_per_second": 1.4, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.0038240917782026, | |
| "grad_norm": 52.7318229675293, | |
| "learning_rate": 3.718130311614731e-05, | |
| "loss": 0.7421, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.0516252390057361, | |
| "grad_norm": 7.203369617462158, | |
| "learning_rate": 3.629603399433428e-05, | |
| "loss": 0.6477, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0994263862332696, | |
| "grad_norm": 3.6017909049987793, | |
| "learning_rate": 3.5410764872521244e-05, | |
| "loss": 0.5586, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.147227533460803, | |
| "grad_norm": 52.35728073120117, | |
| "learning_rate": 3.452549575070821e-05, | |
| "loss": 0.5506, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1950286806883366, | |
| "grad_norm": 3.721095085144043, | |
| "learning_rate": 3.364022662889519e-05, | |
| "loss": 0.5279, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.24282982791587, | |
| "grad_norm": 4.125187397003174, | |
| "learning_rate": 3.275495750708216e-05, | |
| "loss": 0.6266, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.2906309751434035, | |
| "grad_norm": 15.054932594299316, | |
| "learning_rate": 3.1869688385269126e-05, | |
| "loss": 0.6104, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.338432122370937, | |
| "grad_norm": 12.489537239074707, | |
| "learning_rate": 3.098441926345609e-05, | |
| "loss": 0.6529, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.3862332695984705, | |
| "grad_norm": 7.253444671630859, | |
| "learning_rate": 3.0099150141643063e-05, | |
| "loss": 0.4816, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.4340344168260037, | |
| "grad_norm": 42.50492858886719, | |
| "learning_rate": 2.921388101983003e-05, | |
| "loss": 0.5376, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4818355640535372, | |
| "grad_norm": 38.91421127319336, | |
| "learning_rate": 2.8328611898017e-05, | |
| "loss": 0.6558, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.5296367112810707, | |
| "grad_norm": 10.420364379882812, | |
| "learning_rate": 2.7443342776203968e-05, | |
| "loss": 0.5679, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5774378585086042, | |
| "grad_norm": 121.50483703613281, | |
| "learning_rate": 2.6558073654390935e-05, | |
| "loss": 0.6325, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.6252390057361377, | |
| "grad_norm": 29.850032806396484, | |
| "learning_rate": 2.5672804532577905e-05, | |
| "loss": 0.6696, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.6730401529636711, | |
| "grad_norm": 7.039335250854492, | |
| "learning_rate": 2.4787535410764872e-05, | |
| "loss": 0.5333, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.7208413001912046, | |
| "grad_norm": 18.278392791748047, | |
| "learning_rate": 2.3902266288951843e-05, | |
| "loss": 0.4725, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.7686424474187379, | |
| "grad_norm": 20.07522964477539, | |
| "learning_rate": 2.3016997167138813e-05, | |
| "loss": 0.532, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.8164435946462714, | |
| "grad_norm": 26.724767684936523, | |
| "learning_rate": 2.213172804532578e-05, | |
| "loss": 0.4835, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.8642447418738048, | |
| "grad_norm": 14.43714714050293, | |
| "learning_rate": 2.124645892351275e-05, | |
| "loss": 0.4511, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.9120458891013383, | |
| "grad_norm": 12.802144050598145, | |
| "learning_rate": 2.0361189801699718e-05, | |
| "loss": 0.4632, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.9598470363288718, | |
| "grad_norm": 8.717876434326172, | |
| "learning_rate": 1.9475920679886685e-05, | |
| "loss": 0.481, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.844168260038241, | |
| "eval_f1_macro": 0.6551494818857037, | |
| "eval_f1_micro": 0.844168260038241, | |
| "eval_f1_weighted": 0.8158741281490736, | |
| "eval_loss": 0.40430399775505066, | |
| "eval_precision_macro": 0.7424475164964295, | |
| "eval_precision_micro": 0.844168260038241, | |
| "eval_precision_weighted": 0.8497777860209276, | |
| "eval_recall_macro": 0.6970111110408359, | |
| "eval_recall_micro": 0.844168260038241, | |
| "eval_recall_weighted": 0.844168260038241, | |
| "eval_runtime": 44.9693, | |
| "eval_samples_per_second": 23.26, | |
| "eval_steps_per_second": 1.468, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 2.0076481835564053, | |
| "grad_norm": 3.963388681411743, | |
| "learning_rate": 1.8590651558073655e-05, | |
| "loss": 0.4624, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.0554493307839388, | |
| "grad_norm": 37.179256439208984, | |
| "learning_rate": 1.7705382436260622e-05, | |
| "loss": 0.5283, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.1032504780114722, | |
| "grad_norm": 14.825626373291016, | |
| "learning_rate": 1.6820113314447596e-05, | |
| "loss": 0.4486, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.1510516252390057, | |
| "grad_norm": 11.206725120544434, | |
| "learning_rate": 1.5934844192634563e-05, | |
| "loss": 0.5357, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.198852772466539, | |
| "grad_norm": 14.244481086730957, | |
| "learning_rate": 1.5049575070821532e-05, | |
| "loss": 0.3786, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.2466539196940727, | |
| "grad_norm": 23.3243408203125, | |
| "learning_rate": 1.41643059490085e-05, | |
| "loss": 0.4675, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.294455066921606, | |
| "grad_norm": 13.028168678283691, | |
| "learning_rate": 1.3279036827195467e-05, | |
| "loss": 0.5151, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.3422562141491396, | |
| "grad_norm": 13.557563781738281, | |
| "learning_rate": 1.2393767705382436e-05, | |
| "loss": 0.4448, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.390057361376673, | |
| "grad_norm": 5.000290870666504, | |
| "learning_rate": 1.1508498583569407e-05, | |
| "loss": 0.3802, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.4378585086042066, | |
| "grad_norm": 25.394447326660156, | |
| "learning_rate": 1.0623229461756375e-05, | |
| "loss": 0.4251, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.48565965583174, | |
| "grad_norm": 21.63365364074707, | |
| "learning_rate": 9.737960339943342e-06, | |
| "loss": 0.4564, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.5334608030592736, | |
| "grad_norm": 32.95785140991211, | |
| "learning_rate": 8.852691218130311e-06, | |
| "loss": 0.4532, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.581261950286807, | |
| "grad_norm": 64.51441955566406, | |
| "learning_rate": 7.967422096317281e-06, | |
| "loss": 0.566, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.62906309751434, | |
| "grad_norm": 42.481014251708984, | |
| "learning_rate": 7.08215297450425e-06, | |
| "loss": 0.403, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.676864244741874, | |
| "grad_norm": 4.409757137298584, | |
| "learning_rate": 6.196883852691218e-06, | |
| "loss": 0.4463, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.724665391969407, | |
| "grad_norm": 51.99477767944336, | |
| "learning_rate": 5.347025495750709e-06, | |
| "loss": 0.5211, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.772466539196941, | |
| "grad_norm": 37.646881103515625, | |
| "learning_rate": 4.461756373937677e-06, | |
| "loss": 0.3393, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.820267686424474, | |
| "grad_norm": 33.17749786376953, | |
| "learning_rate": 3.576487252124646e-06, | |
| "loss": 0.4809, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.8680688336520075, | |
| "grad_norm": 16.174297332763672, | |
| "learning_rate": 2.691218130311615e-06, | |
| "loss": 0.4465, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.915869980879541, | |
| "grad_norm": 88.04303741455078, | |
| "learning_rate": 1.8059490084985835e-06, | |
| "loss": 0.4669, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.9636711281070744, | |
| "grad_norm": 6.651047229766846, | |
| "learning_rate": 9.206798866855524e-07, | |
| "loss": 0.4518, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.858508604206501, | |
| "eval_f1_macro": 0.6843075887364951, | |
| "eval_f1_micro": 0.858508604206501, | |
| "eval_f1_weighted": 0.8303295709630173, | |
| "eval_loss": 0.369663268327713, | |
| "eval_precision_macro": 0.8204154992433914, | |
| "eval_precision_micro": 0.858508604206501, | |
| "eval_precision_weighted": 0.882137838723129, | |
| "eval_recall_macro": 0.7169578798305077, | |
| "eval_recall_micro": 0.858508604206501, | |
| "eval_recall_weighted": 0.858508604206501, | |
| "eval_runtime": 44.9545, | |
| "eval_samples_per_second": 23.268, | |
| "eval_steps_per_second": 1.468, | |
| "step": 1569 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1569, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.587712686117929e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |