| { |
| "best_metric": 0.9969230769230769, |
| "best_model_checkpoint": "bridalMakeupClassifier/checkpoint-69", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 230, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 5.045365810394287, |
| "learning_rate": 1.0869565217391305e-05, |
| "loss": 0.5777, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 2.5848591327667236, |
| "learning_rate": 2.173913043478261e-05, |
| "loss": 0.4351, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 1.8966680765151978, |
| "learning_rate": 3.260869565217392e-05, |
| "loss": 0.2392, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 1.950931429862976, |
| "learning_rate": 4.347826086956522e-05, |
| "loss": 0.1604, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9846153846153847, |
| "eval_loss": 0.050897907465696335, |
| "eval_runtime": 0.6159, |
| "eval_samples_per_second": 527.667, |
| "eval_steps_per_second": 17.86, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 3.094477891921997, |
| "learning_rate": 4.9516908212560386e-05, |
| "loss": 0.1457, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 3.4824132919311523, |
| "learning_rate": 4.830917874396135e-05, |
| "loss": 0.0999, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.5217391304347827, |
| "grad_norm": 1.870570182800293, |
| "learning_rate": 4.710144927536232e-05, |
| "loss": 0.0597, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 2.119906187057495, |
| "learning_rate": 4.589371980676328e-05, |
| "loss": 0.076, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9565217391304348, |
| "grad_norm": 1.0238789319992065, |
| "learning_rate": 4.4685990338164255e-05, |
| "loss": 0.0837, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9876923076923076, |
| "eval_loss": 0.035339485853910446, |
| "eval_runtime": 0.6194, |
| "eval_samples_per_second": 524.743, |
| "eval_steps_per_second": 17.761, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.1739130434782608, |
| "grad_norm": 1.9959893226623535, |
| "learning_rate": 4.347826086956522e-05, |
| "loss": 0.0421, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.391304347826087, |
| "grad_norm": 1.87074875831604, |
| "learning_rate": 4.2270531400966186e-05, |
| "loss": 0.0812, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.608695652173913, |
| "grad_norm": 2.448767900466919, |
| "learning_rate": 4.106280193236715e-05, |
| "loss": 0.0712, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.8260869565217392, |
| "grad_norm": 0.7633253931999207, |
| "learning_rate": 3.985507246376812e-05, |
| "loss": 0.0588, |
| "step": 65 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9969230769230769, |
| "eval_loss": 0.0326334573328495, |
| "eval_runtime": 0.6252, |
| "eval_samples_per_second": 519.854, |
| "eval_steps_per_second": 17.595, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0434782608695654, |
| "grad_norm": 1.0322834253311157, |
| "learning_rate": 3.864734299516908e-05, |
| "loss": 0.0537, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.260869565217391, |
| "grad_norm": 2.0880322456359863, |
| "learning_rate": 3.743961352657005e-05, |
| "loss": 0.0633, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.4782608695652173, |
| "grad_norm": 0.9349754452705383, |
| "learning_rate": 3.6231884057971014e-05, |
| "loss": 0.0647, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.6956521739130435, |
| "grad_norm": 3.263050079345703, |
| "learning_rate": 3.502415458937198e-05, |
| "loss": 0.0699, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.9130434782608696, |
| "grad_norm": 2.5234551429748535, |
| "learning_rate": 3.381642512077295e-05, |
| "loss": 0.05, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9969230769230769, |
| "eval_loss": 0.030185265466570854, |
| "eval_runtime": 0.6333, |
| "eval_samples_per_second": 513.207, |
| "eval_steps_per_second": 17.37, |
| "step": 92 |
| }, |
| { |
| "epoch": 4.130434782608695, |
| "grad_norm": 2.066303014755249, |
| "learning_rate": 3.260869565217392e-05, |
| "loss": 0.058, |
| "step": 95 |
| }, |
| { |
| "epoch": 4.3478260869565215, |
| "grad_norm": 3.373596429824829, |
| "learning_rate": 3.140096618357488e-05, |
| "loss": 0.0826, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.565217391304348, |
| "grad_norm": 0.9573812484741211, |
| "learning_rate": 3.0193236714975848e-05, |
| "loss": 0.0314, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.782608695652174, |
| "grad_norm": 1.094375729560852, |
| "learning_rate": 2.8985507246376814e-05, |
| "loss": 0.0412, |
| "step": 110 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.668631672859192, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.0284, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9938461538461538, |
| "eval_loss": 0.031306326389312744, |
| "eval_runtime": 0.6258, |
| "eval_samples_per_second": 519.339, |
| "eval_steps_per_second": 17.578, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.217391304347826, |
| "grad_norm": 2.7304937839508057, |
| "learning_rate": 2.6570048309178748e-05, |
| "loss": 0.039, |
| "step": 120 |
| }, |
| { |
| "epoch": 5.434782608695652, |
| "grad_norm": 2.803903341293335, |
| "learning_rate": 2.5362318840579714e-05, |
| "loss": 0.0409, |
| "step": 125 |
| }, |
| { |
| "epoch": 5.6521739130434785, |
| "grad_norm": 2.4052670001983643, |
| "learning_rate": 2.4154589371980676e-05, |
| "loss": 0.0489, |
| "step": 130 |
| }, |
| { |
| "epoch": 5.869565217391305, |
| "grad_norm": 0.9198804497718811, |
| "learning_rate": 2.294685990338164e-05, |
| "loss": 0.0372, |
| "step": 135 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9938461538461538, |
| "eval_loss": 0.02726001664996147, |
| "eval_runtime": 0.6257, |
| "eval_samples_per_second": 519.426, |
| "eval_steps_per_second": 17.581, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.086956521739131, |
| "grad_norm": 1.1955087184906006, |
| "learning_rate": 2.173913043478261e-05, |
| "loss": 0.0498, |
| "step": 140 |
| }, |
| { |
| "epoch": 6.304347826086957, |
| "grad_norm": 1.0752404928207397, |
| "learning_rate": 2.0531400966183576e-05, |
| "loss": 0.0372, |
| "step": 145 |
| }, |
| { |
| "epoch": 6.521739130434782, |
| "grad_norm": 0.4848777651786804, |
| "learning_rate": 1.932367149758454e-05, |
| "loss": 0.0229, |
| "step": 150 |
| }, |
| { |
| "epoch": 6.739130434782608, |
| "grad_norm": 2.153843641281128, |
| "learning_rate": 1.8115942028985507e-05, |
| "loss": 0.0242, |
| "step": 155 |
| }, |
| { |
| "epoch": 6.956521739130435, |
| "grad_norm": 0.9689924120903015, |
| "learning_rate": 1.6908212560386476e-05, |
| "loss": 0.0461, |
| "step": 160 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9969230769230769, |
| "eval_loss": 0.026803696528077126, |
| "eval_runtime": 0.6324, |
| "eval_samples_per_second": 513.955, |
| "eval_steps_per_second": 17.395, |
| "step": 161 |
| }, |
| { |
| "epoch": 7.173913043478261, |
| "grad_norm": 3.230715751647949, |
| "learning_rate": 1.570048309178744e-05, |
| "loss": 0.0415, |
| "step": 165 |
| }, |
| { |
| "epoch": 7.391304347826087, |
| "grad_norm": 1.7875250577926636, |
| "learning_rate": 1.4492753623188407e-05, |
| "loss": 0.0427, |
| "step": 170 |
| }, |
| { |
| "epoch": 7.608695652173913, |
| "grad_norm": 0.38386890292167664, |
| "learning_rate": 1.3285024154589374e-05, |
| "loss": 0.0542, |
| "step": 175 |
| }, |
| { |
| "epoch": 7.826086956521739, |
| "grad_norm": 2.5545527935028076, |
| "learning_rate": 1.2077294685990338e-05, |
| "loss": 0.0338, |
| "step": 180 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9969230769230769, |
| "eval_loss": 0.02585289627313614, |
| "eval_runtime": 0.6295, |
| "eval_samples_per_second": 516.298, |
| "eval_steps_per_second": 17.475, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.043478260869565, |
| "grad_norm": 1.940019965171814, |
| "learning_rate": 1.0869565217391305e-05, |
| "loss": 0.0395, |
| "step": 185 |
| }, |
| { |
| "epoch": 8.26086956521739, |
| "grad_norm": 1.6294324398040771, |
| "learning_rate": 9.66183574879227e-06, |
| "loss": 0.0309, |
| "step": 190 |
| }, |
| { |
| "epoch": 8.478260869565217, |
| "grad_norm": 1.2202316522598267, |
| "learning_rate": 8.454106280193238e-06, |
| "loss": 0.0169, |
| "step": 195 |
| }, |
| { |
| "epoch": 8.695652173913043, |
| "grad_norm": 0.7180597186088562, |
| "learning_rate": 7.246376811594203e-06, |
| "loss": 0.0098, |
| "step": 200 |
| }, |
| { |
| "epoch": 8.91304347826087, |
| "grad_norm": 2.1890971660614014, |
| "learning_rate": 6.038647342995169e-06, |
| "loss": 0.0253, |
| "step": 205 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9938461538461538, |
| "eval_loss": 0.02562897279858589, |
| "eval_runtime": 0.6368, |
| "eval_samples_per_second": 510.384, |
| "eval_steps_per_second": 17.275, |
| "step": 207 |
| }, |
| { |
| "epoch": 9.130434782608695, |
| "grad_norm": 1.944470763206482, |
| "learning_rate": 4.830917874396135e-06, |
| "loss": 0.0497, |
| "step": 210 |
| }, |
| { |
| "epoch": 9.347826086956522, |
| "grad_norm": 1.3670103549957275, |
| "learning_rate": 3.6231884057971017e-06, |
| "loss": 0.0237, |
| "step": 215 |
| }, |
| { |
| "epoch": 9.565217391304348, |
| "grad_norm": 1.2348929643630981, |
| "learning_rate": 2.4154589371980677e-06, |
| "loss": 0.0266, |
| "step": 220 |
| }, |
| { |
| "epoch": 9.782608695652174, |
| "grad_norm": 2.2366175651550293, |
| "learning_rate": 1.2077294685990338e-06, |
| "loss": 0.054, |
| "step": 225 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.43929433822631836, |
| "learning_rate": 0.0, |
| "loss": 0.0326, |
| "step": 230 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9969230769230769, |
| "eval_loss": 0.02662992849946022, |
| "eval_runtime": 0.6361, |
| "eval_samples_per_second": 510.892, |
| "eval_steps_per_second": 17.292, |
| "step": 230 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 230, |
| "total_flos": 7.265405580565709e+17, |
| "train_loss": 0.07611252427425073, |
| "train_runtime": 145.9787, |
| "train_samples_per_second": 200.235, |
| "train_steps_per_second": 1.576 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 230, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 7.265405580565709e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
