| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.955555555555556, |
| "eval_steps": 50, |
| "global_step": 280, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 7.329732894897461, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 0.6531, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 8.706786155700684, |
| "learning_rate": 7.142857142857143e-05, |
| "loss": 0.4865, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 4.010909080505371, |
| "learning_rate": 9.998445910004082e-05, |
| "loss": 0.4045, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 6.512356281280518, |
| "learning_rate": 9.944154131125642e-05, |
| "loss": 0.265, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 5.565410137176514, |
| "learning_rate": 9.81312123475006e-05, |
| "loss": 0.2705, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "eval_accuracy": 0.9, |
| "eval_loss": 0.23454897105693817, |
| "eval_runtime": 3.5018, |
| "eval_samples_per_second": 28.556, |
| "eval_steps_per_second": 7.139, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 2.5253825187683105, |
| "learning_rate": 9.607381059352038e-05, |
| "loss": 0.1875, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 5.666724681854248, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.0772, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 7.440430164337158, |
| "learning_rate": 8.985662536114613e-05, |
| "loss": 0.1589, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 1.9519225358963013, |
| "learning_rate": 8.579334246298593e-05, |
| "loss": 0.0214, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.20509658753871918, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0559, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_accuracy": 0.88, |
| "eval_loss": 0.6940509676933289, |
| "eval_runtime": 3.5087, |
| "eval_samples_per_second": 28.5, |
| "eval_steps_per_second": 7.125, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 1.2840397357940674, |
| "learning_rate": 7.60717601689749e-05, |
| "loss": 0.0057, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 1.4887982606887817, |
| "learning_rate": 7.056435515653059e-05, |
| "loss": 0.0182, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.001216607284732163, |
| "learning_rate": 6.473775872054521e-05, |
| "loss": 0.0006, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.977777777777778, |
| "grad_norm": 11.006356239318848, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.0709, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "grad_norm": 0.008083873428404331, |
| "learning_rate": 5.249229428303486e-05, |
| "loss": 0.0063, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "eval_accuracy": 0.89, |
| "eval_loss": 0.9227009415626526, |
| "eval_runtime": 3.5005, |
| "eval_samples_per_second": 28.567, |
| "eval_steps_per_second": 7.142, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.688888888888889, |
| "grad_norm": 0.06849438697099686, |
| "learning_rate": 4.626349532067879e-05, |
| "loss": 0.0024, |
| "step": 160 |
| }, |
| { |
| "epoch": 6.044444444444444, |
| "grad_norm": 0.0030830150935798883, |
| "learning_rate": 4.0092692840030134e-05, |
| "loss": 0.0004, |
| "step": 170 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 0.00013647924060933292, |
| "learning_rate": 3.4075667487415785e-05, |
| "loss": 0.0001, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.7555555555555555, |
| "grad_norm": 0.004931746982038021, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "grad_norm": 0.00014362263027578592, |
| "learning_rate": 2.2872686806712035e-05, |
| "loss": 0.0115, |
| "step": 200 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "eval_accuracy": 0.88, |
| "eval_loss": 1.2607765197753906, |
| "eval_runtime": 3.5114, |
| "eval_samples_per_second": 28.479, |
| "eval_steps_per_second": 7.12, |
| "step": 200 |
| }, |
| { |
| "epoch": 7.466666666666667, |
| "grad_norm": 0.00021143814956303686, |
| "learning_rate": 1.7860619515673033e-05, |
| "loss": 0.0028, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.822222222222222, |
| "grad_norm": 0.0045998492278158665, |
| "learning_rate": 1.3347406408508695e-05, |
| "loss": 0.0001, |
| "step": 220 |
| }, |
| { |
| "epoch": 8.177777777777777, |
| "grad_norm": 0.009200682863593102, |
| "learning_rate": 9.403099714207175e-06, |
| "loss": 0.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.533333333333333, |
| "grad_norm": 3.014660478584119e-06, |
| "learning_rate": 6.088921331488568e-06, |
| "loss": 0.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 9.906059131026268e-05, |
| "learning_rate": 3.4563125677897932e-06, |
| "loss": 0.0025, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "eval_accuracy": 0.89, |
| "eval_loss": 1.2526733875274658, |
| "eval_runtime": 3.504, |
| "eval_samples_per_second": 28.539, |
| "eval_steps_per_second": 7.135, |
| "step": 250 |
| }, |
| { |
| "epoch": 9.244444444444444, |
| "grad_norm": 4.950571747031063e-05, |
| "learning_rate": 1.5461356885461075e-06, |
| "loss": 0.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.0026052340399473906, |
| "learning_rate": 3.8803966999139684e-07, |
| "loss": 0.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 9.955555555555556, |
| "grad_norm": 0.0014641884481534362, |
| "learning_rate": 0.0, |
| "loss": 0.0013, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.955555555555556, |
| "step": 280, |
| "total_flos": 0.0, |
| "train_loss": 0.09654608053981195, |
| "train_runtime": 1003.5439, |
| "train_samples_per_second": 8.968, |
| "train_steps_per_second": 0.279 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 280, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
