| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 50, |
| "global_step": 290, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3448275862068966, |
| "grad_norm": 6.0372772216796875, |
| "learning_rate": 4.920557351506409e-05, |
| "loss": 0.7, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3448275862068966, |
| "eval_accuracy": 0.5342465753424658, |
| "eval_loss": 0.6736854910850525, |
| "eval_runtime": 102.9585, |
| "eval_samples_per_second": 1.418, |
| "eval_steps_per_second": 0.359, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 4.887221336364746, |
| "learning_rate": 4.141282807014033e-05, |
| "loss": 0.6474, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "eval_accuracy": 0.6575342465753424, |
| "eval_loss": 0.5182708501815796, |
| "eval_runtime": 98.1281, |
| "eval_samples_per_second": 1.488, |
| "eval_steps_per_second": 0.377, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0344827586206897, |
| "grad_norm": 25.287790298461914, |
| "learning_rate": 2.7852503024450622e-05, |
| "loss": 0.6736, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0344827586206897, |
| "eval_accuracy": 0.6712328767123288, |
| "eval_loss": 0.528748631477356, |
| "eval_runtime": 99.358, |
| "eval_samples_per_second": 1.469, |
| "eval_steps_per_second": 0.372, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.3793103448275863, |
| "grad_norm": 3.4326326847076416, |
| "learning_rate": 1.328978898250525e-05, |
| "loss": 0.674, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3793103448275863, |
| "eval_accuracy": 0.636986301369863, |
| "eval_loss": 0.5545393824577332, |
| "eval_runtime": 98.616, |
| "eval_samples_per_second": 1.48, |
| "eval_steps_per_second": 0.375, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.7241379310344827, |
| "grad_norm": 3.971996307373047, |
| "learning_rate": 2.8421228711503127e-06, |
| "loss": 0.5125, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.7241379310344827, |
| "eval_accuracy": 0.6506849315068494, |
| "eval_loss": 0.6218694448471069, |
| "eval_runtime": 95.8081, |
| "eval_samples_per_second": 1.524, |
| "eval_steps_per_second": 0.386, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 290, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.445434923787223e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
