| { | |
| "best_metric": 0.16949759423732758, | |
| "best_model_checkpoint": "autotrain-sh8gw-ccble/checkpoint-1362", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1362, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05506607929515418, | |
| "grad_norm": 14.598111152648926, | |
| "learning_rate": 8.02919708029197e-06, | |
| "loss": 1.8556, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11013215859030837, | |
| "grad_norm": 20.4303035736084, | |
| "learning_rate": 1.715328467153285e-05, | |
| "loss": 1.6556, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16519823788546256, | |
| "grad_norm": 29.148277282714844, | |
| "learning_rate": 2.6277372262773724e-05, | |
| "loss": 1.3584, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22026431718061673, | |
| "grad_norm": 16.219594955444336, | |
| "learning_rate": 3.5401459854014604e-05, | |
| "loss": 1.09, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2753303964757709, | |
| "grad_norm": 31.08094596862793, | |
| "learning_rate": 4.452554744525548e-05, | |
| "loss": 0.8176, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3303964757709251, | |
| "grad_norm": 58.6417236328125, | |
| "learning_rate": 4.963265306122449e-05, | |
| "loss": 0.6597, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3854625550660793, | |
| "grad_norm": 11.836067199707031, | |
| "learning_rate": 4.8612244897959186e-05, | |
| "loss": 0.5218, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44052863436123346, | |
| "grad_norm": 91.57707977294922, | |
| "learning_rate": 4.759183673469388e-05, | |
| "loss": 0.414, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4955947136563877, | |
| "grad_norm": 2.3629424571990967, | |
| "learning_rate": 4.6571428571428575e-05, | |
| "loss": 0.3714, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5506607929515418, | |
| "grad_norm": 129.56517028808594, | |
| "learning_rate": 4.555102040816327e-05, | |
| "loss": 0.3493, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6057268722466961, | |
| "grad_norm": 48.04598617553711, | |
| "learning_rate": 4.4571428571428574e-05, | |
| "loss": 0.3769, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6607929515418502, | |
| "grad_norm": 47.53449249267578, | |
| "learning_rate": 4.355102040816327e-05, | |
| "loss": 0.477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7158590308370044, | |
| "grad_norm": 17.811521530151367, | |
| "learning_rate": 4.253061224489796e-05, | |
| "loss": 0.4341, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7709251101321586, | |
| "grad_norm": 8.362146377563477, | |
| "learning_rate": 4.151020408163265e-05, | |
| "loss": 0.2695, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8259911894273128, | |
| "grad_norm": 24.986268997192383, | |
| "learning_rate": 4.048979591836735e-05, | |
| "loss": 0.502, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8810572687224669, | |
| "grad_norm": 28.8356876373291, | |
| "learning_rate": 3.9469387755102045e-05, | |
| "loss": 0.3231, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9361233480176211, | |
| "grad_norm": 37.625213623046875, | |
| "learning_rate": 3.844897959183674e-05, | |
| "loss": 0.2708, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9911894273127754, | |
| "grad_norm": 22.338773727416992, | |
| "learning_rate": 3.742857142857143e-05, | |
| "loss": 0.31, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.919746276889134, | |
| "eval_f1_macro": 0.8922845489450274, | |
| "eval_f1_micro": 0.919746276889134, | |
| "eval_f1_weighted": 0.9218831391092777, | |
| "eval_loss": 0.23288899660110474, | |
| "eval_precision_macro": 0.8940334696888717, | |
| "eval_precision_micro": 0.919746276889134, | |
| "eval_precision_weighted": 0.9267204134675875, | |
| "eval_recall_macro": 0.8948346000728363, | |
| "eval_recall_micro": 0.919746276889134, | |
| "eval_recall_weighted": 0.919746276889134, | |
| "eval_runtime": 21.1514, | |
| "eval_samples_per_second": 171.431, | |
| "eval_steps_per_second": 10.732, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.0462555066079295, | |
| "grad_norm": 7.589050769805908, | |
| "learning_rate": 3.640816326530612e-05, | |
| "loss": 0.4484, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.1013215859030836, | |
| "grad_norm": 3.8066580295562744, | |
| "learning_rate": 3.538775510204082e-05, | |
| "loss": 0.332, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1563876651982379, | |
| "grad_norm": 1.0897353887557983, | |
| "learning_rate": 3.436734693877551e-05, | |
| "loss": 0.2705, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.2114537444933922, | |
| "grad_norm": 43.75095748901367, | |
| "learning_rate": 3.3346938775510205e-05, | |
| "loss": 0.2558, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2665198237885462, | |
| "grad_norm": 3.1810498237609863, | |
| "learning_rate": 3.236734693877551e-05, | |
| "loss": 0.3549, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.3215859030837005, | |
| "grad_norm": 0.1776355355978012, | |
| "learning_rate": 3.1346938775510204e-05, | |
| "loss": 0.2123, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3766519823788546, | |
| "grad_norm": 41.68134689331055, | |
| "learning_rate": 3.0326530612244898e-05, | |
| "loss": 0.3495, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.4317180616740088, | |
| "grad_norm": 15.639876365661621, | |
| "learning_rate": 2.9306122448979596e-05, | |
| "loss": 0.4163, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4867841409691631, | |
| "grad_norm": 45.413299560546875, | |
| "learning_rate": 2.8285714285714287e-05, | |
| "loss": 0.3474, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.5418502202643172, | |
| "grad_norm": 18.598854064941406, | |
| "learning_rate": 2.726530612244898e-05, | |
| "loss": 0.38, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5969162995594712, | |
| "grad_norm": 2.7749788761138916, | |
| "learning_rate": 2.6244897959183672e-05, | |
| "loss": 0.4032, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.6519823788546255, | |
| "grad_norm": 12.994845390319824, | |
| "learning_rate": 2.522448979591837e-05, | |
| "loss": 0.3246, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7070484581497798, | |
| "grad_norm": 34.15009307861328, | |
| "learning_rate": 2.420408163265306e-05, | |
| "loss": 0.2937, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.7621145374449338, | |
| "grad_norm": 2.871756076812744, | |
| "learning_rate": 2.3183673469387755e-05, | |
| "loss": 0.2008, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8171806167400881, | |
| "grad_norm": 1.7972595691680908, | |
| "learning_rate": 2.216326530612245e-05, | |
| "loss": 0.4188, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.8722466960352424, | |
| "grad_norm": 15.454833984375, | |
| "learning_rate": 2.1142857142857144e-05, | |
| "loss": 0.2821, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9273127753303965, | |
| "grad_norm": 0.6686480641365051, | |
| "learning_rate": 2.012244897959184e-05, | |
| "loss": 0.3706, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.9823788546255505, | |
| "grad_norm": 13.417647361755371, | |
| "learning_rate": 1.910204081632653e-05, | |
| "loss": 0.3225, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9236072807501379, | |
| "eval_f1_macro": 0.8981028824019618, | |
| "eval_f1_micro": 0.9236072807501379, | |
| "eval_f1_weighted": 0.92638105205174, | |
| "eval_loss": 0.1980753093957901, | |
| "eval_precision_macro": 0.9066084517869921, | |
| "eval_precision_micro": 0.9236072807501379, | |
| "eval_precision_weighted": 0.9360810250439844, | |
| "eval_recall_macro": 0.9009909368364234, | |
| "eval_recall_micro": 0.9236072807501379, | |
| "eval_recall_weighted": 0.9236072807501379, | |
| "eval_runtime": 21.1211, | |
| "eval_samples_per_second": 171.677, | |
| "eval_steps_per_second": 10.748, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 2.037444933920705, | |
| "grad_norm": 28.311424255371094, | |
| "learning_rate": 1.8081632653061227e-05, | |
| "loss": 0.3026, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.092511013215859, | |
| "grad_norm": 38.7237548828125, | |
| "learning_rate": 1.706122448979592e-05, | |
| "loss": 0.2717, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.147577092511013, | |
| "grad_norm": 59.18606948852539, | |
| "learning_rate": 1.6040816326530613e-05, | |
| "loss": 0.2559, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.202643171806167, | |
| "grad_norm": 76.78392791748047, | |
| "learning_rate": 1.5020408163265307e-05, | |
| "loss": 0.3441, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2577092511013217, | |
| "grad_norm": 0.5000678896903992, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.3059, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.3127753303964758, | |
| "grad_norm": 46.82283401489258, | |
| "learning_rate": 1.2979591836734694e-05, | |
| "loss": 0.2467, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.36784140969163, | |
| "grad_norm": 0.16057251393795013, | |
| "learning_rate": 1.1959183673469389e-05, | |
| "loss": 0.3052, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.4229074889867843, | |
| "grad_norm": 3.6819064617156982, | |
| "learning_rate": 1.0938775510204081e-05, | |
| "loss": 0.2848, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.4779735682819384, | |
| "grad_norm": 3.26033878326416, | |
| "learning_rate": 9.918367346938776e-06, | |
| "loss": 0.2358, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.5330396475770924, | |
| "grad_norm": 3.413316488265991, | |
| "learning_rate": 8.89795918367347e-06, | |
| "loss": 0.287, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.5881057268722465, | |
| "grad_norm": 34.6589469909668, | |
| "learning_rate": 7.877551020408164e-06, | |
| "loss": 0.1574, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.643171806167401, | |
| "grad_norm": 17.196468353271484, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 0.2718, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.698237885462555, | |
| "grad_norm": 5.279835224151611, | |
| "learning_rate": 5.8367346938775515e-06, | |
| "loss": 0.27, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.753303964757709, | |
| "grad_norm": 11.918065071105957, | |
| "learning_rate": 4.816326530612245e-06, | |
| "loss": 0.1459, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.8083700440528636, | |
| "grad_norm": 0.6315783858299255, | |
| "learning_rate": 3.7959183673469385e-06, | |
| "loss": 0.203, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.8634361233480177, | |
| "grad_norm": 6.937969207763672, | |
| "learning_rate": 2.775510204081633e-06, | |
| "loss": 0.2701, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9185022026431717, | |
| "grad_norm": 19.936586380004883, | |
| "learning_rate": 1.7551020408163264e-06, | |
| "loss": 0.1779, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.9735682819383262, | |
| "grad_norm": 14.280041694641113, | |
| "learning_rate": 7.346938775510204e-07, | |
| "loss": 0.3115, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9431880860452289, | |
| "eval_f1_macro": 0.921808528788731, | |
| "eval_f1_micro": 0.9431880860452289, | |
| "eval_f1_weighted": 0.9428034220405396, | |
| "eval_loss": 0.16949759423732758, | |
| "eval_precision_macro": 0.9255554286892043, | |
| "eval_precision_micro": 0.9431880860452289, | |
| "eval_precision_weighted": 0.9438687873791154, | |
| "eval_recall_macro": 0.9204182136037321, | |
| "eval_recall_micro": 0.9431880860452289, | |
| "eval_recall_weighted": 0.9431880860452289, | |
| "eval_runtime": 21.1051, | |
| "eval_samples_per_second": 171.807, | |
| "eval_steps_per_second": 10.756, | |
| "step": 1362 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1362, | |
| "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": 2.7382422149074944e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |