| { | |
| "best_metric": 0.34203216433525085, | |
| "best_model_checkpoint": "autotrain-7ejr4-3wbhb/checkpoint-446", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 446, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04932735426008968, | |
| "grad_norm": 5.397119045257568, | |
| "learning_rate": 8.208955223880597e-06, | |
| "loss": 1.6001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09865470852017937, | |
| "grad_norm": 10.270828247070312, | |
| "learning_rate": 1.6417910447761194e-05, | |
| "loss": 1.6421, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14798206278026907, | |
| "grad_norm": 6.842929363250732, | |
| "learning_rate": 2.4626865671641793e-05, | |
| "loss": 1.5659, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19730941704035873, | |
| "grad_norm": 14.523164749145508, | |
| "learning_rate": 3.208955223880597e-05, | |
| "loss": 1.2199, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.24663677130044842, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3.9552238805970146e-05, | |
| "loss": 0.9104, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.29596412556053814, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.7014925373134335e-05, | |
| "loss": 0.6866, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3452914798206278, | |
| "grad_norm": 39.58903884887695, | |
| "learning_rate": 4.941860465116279e-05, | |
| "loss": 0.9257, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.39461883408071746, | |
| "grad_norm": 38.08815383911133, | |
| "learning_rate": 4.8504983388704325e-05, | |
| "loss": 0.5447, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.4439461883408072, | |
| "grad_norm": 32.093482971191406, | |
| "learning_rate": 4.7674418604651164e-05, | |
| "loss": 0.5951, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.49327354260089684, | |
| "grad_norm": 9.36325454711914, | |
| "learning_rate": 4.684385382059801e-05, | |
| "loss": 0.4972, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5426008968609866, | |
| "grad_norm": 16.48912811279297, | |
| "learning_rate": 4.593023255813954e-05, | |
| "loss": 0.5117, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5919282511210763, | |
| "grad_norm": 15.17750072479248, | |
| "learning_rate": 4.5016611295681064e-05, | |
| "loss": 0.5249, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6412556053811659, | |
| "grad_norm": 73.44496154785156, | |
| "learning_rate": 4.410299003322259e-05, | |
| "loss": 0.2932, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6905829596412556, | |
| "grad_norm": 7.012796878814697, | |
| "learning_rate": 4.3189368770764125e-05, | |
| "loss": 0.3703, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7399103139013453, | |
| "grad_norm": 36.769142150878906, | |
| "learning_rate": 4.227574750830565e-05, | |
| "loss": 0.384, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7892376681614349, | |
| "grad_norm": 0.5750433206558228, | |
| "learning_rate": 4.136212624584718e-05, | |
| "loss": 0.2024, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8385650224215246, | |
| "grad_norm": 0.8097955584526062, | |
| "learning_rate": 4.0448504983388706e-05, | |
| "loss": 0.2261, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8878923766816144, | |
| "grad_norm": 0.3052847683429718, | |
| "learning_rate": 3.953488372093023e-05, | |
| "loss": 0.3784, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9372197309417041, | |
| "grad_norm": 9.378923416137695, | |
| "learning_rate": 3.862126245847176e-05, | |
| "loss": 0.334, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9865470852017937, | |
| "grad_norm": 57.845924377441406, | |
| "learning_rate": 3.7707641196013294e-05, | |
| "loss": 0.5124, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8337078651685393, | |
| "eval_f1_macro": 0.8277707222765114, | |
| "eval_f1_micro": 0.8337078651685393, | |
| "eval_f1_weighted": 0.8270484241051885, | |
| "eval_loss": 0.6007972359657288, | |
| "eval_precision_macro": 0.8743021944472813, | |
| "eval_precision_micro": 0.8337078651685393, | |
| "eval_precision_weighted": 0.8814664248669926, | |
| "eval_recall_macro": 0.8408823529411764, | |
| "eval_recall_micro": 0.8337078651685393, | |
| "eval_recall_weighted": 0.8337078651685393, | |
| "eval_runtime": 1.7336, | |
| "eval_samples_per_second": 256.693, | |
| "eval_steps_per_second": 16.151, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.0358744394618835, | |
| "grad_norm": 4.146377086639404, | |
| "learning_rate": 3.679401993355482e-05, | |
| "loss": 0.4657, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.0852017937219731, | |
| "grad_norm": 2.958444833755493, | |
| "learning_rate": 3.588039867109635e-05, | |
| "loss": 0.2262, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.1345291479820627, | |
| "grad_norm": 18.36431312561035, | |
| "learning_rate": 3.4966777408637875e-05, | |
| "loss": 0.2503, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.1838565022421526, | |
| "grad_norm": 0.3763713538646698, | |
| "learning_rate": 3.40531561461794e-05, | |
| "loss": 0.1309, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.2331838565022422, | |
| "grad_norm": 0.1498165726661682, | |
| "learning_rate": 3.313953488372093e-05, | |
| "loss": 0.1149, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.2825112107623318, | |
| "grad_norm": 0.13080233335494995, | |
| "learning_rate": 3.222591362126246e-05, | |
| "loss": 0.2224, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.3318385650224216, | |
| "grad_norm": 6.366682052612305, | |
| "learning_rate": 3.131229235880399e-05, | |
| "loss": 0.3254, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.3811659192825112, | |
| "grad_norm": 0.08186858147382736, | |
| "learning_rate": 3.0398671096345517e-05, | |
| "loss": 0.0981, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.4304932735426008, | |
| "grad_norm": 0.14895343780517578, | |
| "learning_rate": 2.9485049833887047e-05, | |
| "loss": 0.1536, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.4798206278026906, | |
| "grad_norm": 0.07964171469211578, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0458, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.5291479820627802, | |
| "grad_norm": 0.16557298600673676, | |
| "learning_rate": 2.76578073089701e-05, | |
| "loss": 0.2189, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.57847533632287, | |
| "grad_norm": 13.367328643798828, | |
| "learning_rate": 2.674418604651163e-05, | |
| "loss": 0.2818, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.6278026905829597, | |
| "grad_norm": 0.042071498930454254, | |
| "learning_rate": 2.591362126245847e-05, | |
| "loss": 0.1282, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.6771300448430493, | |
| "grad_norm": 0.0784522220492363, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2491, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.726457399103139, | |
| "grad_norm": 0.17997685074806213, | |
| "learning_rate": 2.4086378737541528e-05, | |
| "loss": 0.022, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.7757847533632287, | |
| "grad_norm": 36.073631286621094, | |
| "learning_rate": 2.3172757475083055e-05, | |
| "loss": 0.1468, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.8251121076233185, | |
| "grad_norm": 46.98909378051758, | |
| "learning_rate": 2.2259136212624586e-05, | |
| "loss": 0.2726, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.8744394618834082, | |
| "grad_norm": 0.6519285440444946, | |
| "learning_rate": 2.1345514950166116e-05, | |
| "loss": 0.0038, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.9237668161434978, | |
| "grad_norm": 29.345619201660156, | |
| "learning_rate": 2.0431893687707643e-05, | |
| "loss": 0.251, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.9730941704035874, | |
| "grad_norm": 0.05096792057156563, | |
| "learning_rate": 1.951827242524917e-05, | |
| "loss": 0.3514, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.946067415730337, | |
| "eval_f1_macro": 0.9457020850649197, | |
| "eval_f1_micro": 0.946067415730337, | |
| "eval_f1_weighted": 0.9461015789750475, | |
| "eval_loss": 0.34203216433525085, | |
| "eval_precision_macro": 0.9447370569809594, | |
| "eval_precision_micro": 0.946067415730337, | |
| "eval_precision_weighted": 0.9466487598452521, | |
| "eval_recall_macro": 0.9472065189712249, | |
| "eval_recall_micro": 0.946067415730337, | |
| "eval_recall_weighted": 0.946067415730337, | |
| "eval_runtime": 1.7697, | |
| "eval_samples_per_second": 251.457, | |
| "eval_steps_per_second": 15.822, | |
| "step": 446 | |
| } | |
| ], | |
| "logging_steps": 11, | |
| "max_steps": 669, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 234175146792960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |