| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.08343360002810395, |
| "eval_steps": 1000, |
| "global_step": 9500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 8.782484213484626e-06, |
| "grad_norm": 3.6796653270721436, |
| "learning_rate": 3e-06, |
| "loss": 2.5344, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.008782484213484626, |
| "grad_norm": 8.691473007202148, |
| "learning_rate": 2.9736788948121867e-06, |
| "loss": 1.0666, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.008782484213484626, |
| "eval_accuracy": 0.8495979309082031, |
| "eval_loss": 0.7292845845222473, |
| "eval_runtime": 85.0016, |
| "eval_samples_per_second": 108.257, |
| "eval_steps_per_second": 13.541, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.017564968426969252, |
| "grad_norm": 6.969796657562256, |
| "learning_rate": 2.9473314421717326e-06, |
| "loss": 0.6516, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.017564968426969252, |
| "eval_accuracy": 0.8538361191749573, |
| "eval_loss": 0.6177436113357544, |
| "eval_runtime": 82.38, |
| "eval_samples_per_second": 111.702, |
| "eval_steps_per_second": 13.972, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.026347452640453878, |
| "grad_norm": 19.85172462463379, |
| "learning_rate": 2.920983989531279e-06, |
| "loss": 0.6072, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.026347452640453878, |
| "eval_accuracy": 0.8620952367782593, |
| "eval_loss": 0.5767402648925781, |
| "eval_runtime": 84.8181, |
| "eval_samples_per_second": 108.491, |
| "eval_steps_per_second": 13.57, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.035129936853938504, |
| "grad_norm": 10.813929557800293, |
| "learning_rate": 2.8946365368908247e-06, |
| "loss": 0.5674, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.035129936853938504, |
| "eval_accuracy": 0.8662247657775879, |
| "eval_loss": 0.5505204200744629, |
| "eval_runtime": 79.8645, |
| "eval_samples_per_second": 115.22, |
| "eval_steps_per_second": 14.412, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.04391242106742313, |
| "grad_norm": 7.621878623962402, |
| "learning_rate": 2.868289084250371e-06, |
| "loss": 0.5299, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.04391242106742313, |
| "eval_accuracy": 0.8677461743354797, |
| "eval_loss": 0.5321353077888489, |
| "eval_runtime": 93.9377, |
| "eval_samples_per_second": 97.959, |
| "eval_steps_per_second": 12.253, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.052694905280907756, |
| "grad_norm": 7.295602321624756, |
| "learning_rate": 2.8419416316099173e-06, |
| "loss": 0.5388, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.052694905280907756, |
| "eval_accuracy": 0.8685068488121033, |
| "eval_loss": 0.5172874331474304, |
| "eval_runtime": 77.0511, |
| "eval_samples_per_second": 119.427, |
| "eval_steps_per_second": 14.938, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.06147738949439238, |
| "grad_norm": 21.50514030456543, |
| "learning_rate": 2.8155941789694636e-06, |
| "loss": 0.5005, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.06147738949439238, |
| "eval_accuracy": 0.871549665927887, |
| "eval_loss": 0.49886903166770935, |
| "eval_runtime": 80.8123, |
| "eval_samples_per_second": 113.869, |
| "eval_steps_per_second": 14.243, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.07025987370787701, |
| "grad_norm": 12.609434127807617, |
| "learning_rate": 2.7892467263290094e-06, |
| "loss": 0.4776, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.07025987370787701, |
| "eval_accuracy": 0.874266505241394, |
| "eval_loss": 0.48554736375808716, |
| "eval_runtime": 79.5335, |
| "eval_samples_per_second": 115.7, |
| "eval_steps_per_second": 14.472, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.07904235792136163, |
| "grad_norm": 12.605308532714844, |
| "learning_rate": 2.7628992736885557e-06, |
| "loss": 0.4744, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.07904235792136163, |
| "eval_accuracy": 0.87557053565979, |
| "eval_loss": 0.4739709198474884, |
| "eval_runtime": 83.1212, |
| "eval_samples_per_second": 110.706, |
| "eval_steps_per_second": 13.847, |
| "step": 9000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 113863, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
