| { |
| "best_metric": 0.022366832941770554, |
| "best_model_checkpoint": "tw-cn-context-classifier/checkpoint-314", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 314, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.044585987261146494, |
| "grad_norm": 4.861356258392334, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": 0.6812, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.08917197452229299, |
| "grad_norm": 5.701432228088379, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": 0.6625, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.1337579617834395, |
| "grad_norm": 9.67529010772705, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.6396, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.17834394904458598, |
| "grad_norm": 6.278923034667969, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.6029, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.2229299363057325, |
| "grad_norm": 3.7738094329833984, |
| "learning_rate": 1.1111111111111113e-05, |
| "loss": 0.4799, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.267515923566879, |
| "grad_norm": 4.174890041351318, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.3843, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.31210191082802546, |
| "grad_norm": 5.322546005249023, |
| "learning_rate": 1.555555555555556e-05, |
| "loss": 0.2303, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.35668789808917195, |
| "grad_norm": 1.734724521636963, |
| "learning_rate": 1.7777777777777777e-05, |
| "loss": 0.0953, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.4012738853503185, |
| "grad_norm": 0.5622832775115967, |
| "learning_rate": 2e-05, |
| "loss": 0.0398, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.445859872611465, |
| "grad_norm": 0.2177177220582962, |
| "learning_rate": 1.975221238938053e-05, |
| "loss": 0.0152, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.49044585987261147, |
| "grad_norm": 0.12123537808656693, |
| "learning_rate": 1.9504424778761063e-05, |
| "loss": 0.0076, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.535031847133758, |
| "grad_norm": 0.13101454079151154, |
| "learning_rate": 1.9256637168141596e-05, |
| "loss": 0.0557, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.5796178343949044, |
| "grad_norm": 0.08730276674032211, |
| "learning_rate": 1.9008849557522125e-05, |
| "loss": 0.0035, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.6242038216560509, |
| "grad_norm": 0.07024876028299332, |
| "learning_rate": 1.8761061946902657e-05, |
| "loss": 0.0027, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.6687898089171974, |
| "grad_norm": 0.05537857860326767, |
| "learning_rate": 1.8513274336283186e-05, |
| "loss": 0.0023, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.7133757961783439, |
| "grad_norm": 0.04929512366652489, |
| "learning_rate": 1.826548672566372e-05, |
| "loss": 0.058, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.7579617834394905, |
| "grad_norm": 0.05506855249404907, |
| "learning_rate": 1.8017699115044248e-05, |
| "loss": 0.0018, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.802547770700637, |
| "grad_norm": 0.056426189839839935, |
| "learning_rate": 1.776991150442478e-05, |
| "loss": 0.0016, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.8471337579617835, |
| "grad_norm": 0.11536817252635956, |
| "learning_rate": 1.7522123893805313e-05, |
| "loss": 0.1204, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.89171974522293, |
| "grad_norm": 0.2547154724597931, |
| "learning_rate": 1.7274336283185842e-05, |
| "loss": 0.0542, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9363057324840764, |
| "grad_norm": 0.10147877037525177, |
| "learning_rate": 1.702654867256637e-05, |
| "loss": 0.004, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.9808917197452229, |
| "grad_norm": 0.06237854063510895, |
| "learning_rate": 1.6778761061946903e-05, |
| "loss": 0.0022, |
| "step": 154 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9968152866242038, |
| "eval_auc": 0.9999492880035701, |
| "eval_f1": 0.9968051118210862, |
| "eval_loss": 0.02294245921075344, |
| "eval_precision": 1.0, |
| "eval_recall": 0.9936305732484076, |
| "eval_runtime": 65.0436, |
| "eval_samples_per_second": 9.655, |
| "eval_steps_per_second": 0.307, |
| "step": 157 |
| }, |
| { |
| "epoch": 1.0254777070063694, |
| "grad_norm": 0.04382710158824921, |
| "learning_rate": 1.6530973451327436e-05, |
| "loss": 0.0016, |
| "step": 161 |
| }, |
| { |
| "epoch": 1.070063694267516, |
| "grad_norm": 0.038911979645490646, |
| "learning_rate": 1.628318584070797e-05, |
| "loss": 0.0492, |
| "step": 168 |
| }, |
| { |
| "epoch": 1.1146496815286624, |
| "grad_norm": 0.039950430393218994, |
| "learning_rate": 1.6035398230088498e-05, |
| "loss": 0.0013, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.1592356687898089, |
| "grad_norm": 0.04444283992052078, |
| "learning_rate": 1.5787610619469027e-05, |
| "loss": 0.0541, |
| "step": 182 |
| }, |
| { |
| "epoch": 1.2038216560509554, |
| "grad_norm": 0.8840770721435547, |
| "learning_rate": 1.553982300884956e-05, |
| "loss": 0.002, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.2484076433121019, |
| "grad_norm": 0.0330999530851841, |
| "learning_rate": 1.5292035398230088e-05, |
| "loss": 0.0013, |
| "step": 196 |
| }, |
| { |
| "epoch": 1.2929936305732483, |
| "grad_norm": 0.0437622107565403, |
| "learning_rate": 1.5044247787610619e-05, |
| "loss": 0.0012, |
| "step": 203 |
| }, |
| { |
| "epoch": 1.3375796178343948, |
| "grad_norm": 0.03020174615085125, |
| "learning_rate": 1.4796460176991151e-05, |
| "loss": 0.0011, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.3821656050955413, |
| "grad_norm": 0.02413470856845379, |
| "learning_rate": 1.4548672566371682e-05, |
| "loss": 0.001, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.426751592356688, |
| "grad_norm": 0.033314965665340424, |
| "learning_rate": 1.4300884955752215e-05, |
| "loss": 0.0009, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.4713375796178343, |
| "grad_norm": 0.02173658274114132, |
| "learning_rate": 1.4053097345132744e-05, |
| "loss": 0.0009, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.515923566878981, |
| "grad_norm": 0.02424098365008831, |
| "learning_rate": 1.3805309734513275e-05, |
| "loss": 0.0549, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.5605095541401273, |
| "grad_norm": 0.12424007803201675, |
| "learning_rate": 1.3557522123893807e-05, |
| "loss": 0.0704, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.605095541401274, |
| "grad_norm": 0.0554329939186573, |
| "learning_rate": 1.3309734513274338e-05, |
| "loss": 0.0022, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.6496815286624202, |
| "grad_norm": 0.02428065985441208, |
| "learning_rate": 1.3061946902654867e-05, |
| "loss": 0.0021, |
| "step": 259 |
| }, |
| { |
| "epoch": 1.694267515923567, |
| "grad_norm": 0.03345051407814026, |
| "learning_rate": 1.28141592920354e-05, |
| "loss": 0.059, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.7388535031847132, |
| "grad_norm": 0.04772985354065895, |
| "learning_rate": 1.256637168141593e-05, |
| "loss": 0.0656, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.78343949044586, |
| "grad_norm": 0.07988367229700089, |
| "learning_rate": 1.2318584070796463e-05, |
| "loss": 0.0017, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.8280254777070064, |
| "grad_norm": 0.03602590411901474, |
| "learning_rate": 1.2070796460176992e-05, |
| "loss": 0.0014, |
| "step": 287 |
| }, |
| { |
| "epoch": 1.872611464968153, |
| "grad_norm": 0.030409082770347595, |
| "learning_rate": 1.1823008849557523e-05, |
| "loss": 0.001, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.9171974522292994, |
| "grad_norm": 0.031838107854127884, |
| "learning_rate": 1.1575221238938055e-05, |
| "loss": 0.001, |
| "step": 301 |
| }, |
| { |
| "epoch": 1.9617834394904459, |
| "grad_norm": 0.029339779168367386, |
| "learning_rate": 1.1327433628318584e-05, |
| "loss": 0.0009, |
| "step": 308 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9968152866242038, |
| "eval_auc": 0.9999391456042841, |
| "eval_f1": 0.9968051118210862, |
| "eval_loss": 0.022366832941770554, |
| "eval_precision": 1.0, |
| "eval_recall": 0.9936305732484076, |
| "eval_runtime": 76.7054, |
| "eval_samples_per_second": 8.187, |
| "eval_steps_per_second": 0.261, |
| "step": 314 |
| } |
| ], |
| "logging_steps": 7, |
| "max_steps": 628, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 330467485532160.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
