| { |
| "best_global_step": 40, |
| "best_metric": 0.43451955914497375, |
| "best_model_checkpoint": "ft_checkpoints/fold4_CU3/checkpoint-40", |
| "epoch": 1.7391304347826086, |
| "eval_steps": 10, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 0.6149529814720154, |
| "learning_rate": 8e-05, |
| "loss": 0.4473, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 1.3481638431549072, |
| "learning_rate": 0.00018, |
| "loss": 0.2751, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "eval_loss": 0.4551287293434143, |
| "eval_runtime": 4.9349, |
| "eval_samples_per_second": 43.567, |
| "eval_steps_per_second": 5.471, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 0.7840824127197266, |
| "learning_rate": 0.0001864406779661017, |
| "loss": 0.5286, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.8211029767990112, |
| "learning_rate": 0.00016949152542372882, |
| "loss": 0.497, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "eval_loss": 0.4426790177822113, |
| "eval_runtime": 5.1609, |
| "eval_samples_per_second": 41.659, |
| "eval_steps_per_second": 5.232, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 0.8198596835136414, |
| "learning_rate": 0.00015254237288135592, |
| "loss": 0.5088, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 0.8266681432723999, |
| "learning_rate": 0.00013559322033898305, |
| "loss": 0.368, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "eval_loss": 0.4371105134487152, |
| "eval_runtime": 4.9664, |
| "eval_samples_per_second": 43.291, |
| "eval_steps_per_second": 5.437, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.5217391304347827, |
| "grad_norm": 0.9265542030334473, |
| "learning_rate": 0.00011864406779661017, |
| "loss": 0.325, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 0.8554236888885498, |
| "learning_rate": 0.00010169491525423729, |
| "loss": 0.36, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "eval_loss": 0.43451955914497375, |
| "eval_runtime": 5.1657, |
| "eval_samples_per_second": 41.621, |
| "eval_steps_per_second": 5.227, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 69, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7911388407250944.0, |
| "train_batch_size": 40, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
