| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 2000, |
| "global_step": 9764, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00020491803278688525, |
| "grad_norm": 7.146026134490967, |
| "learning_rate": 0.0, |
| "loss": 5.3596, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "grad_norm": 3.285043954849243, |
| "learning_rate": 1.2291453166632506e-05, |
| "loss": 3.8653, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "eval_cosine_accuracy": 0.9486149549484253, |
| "eval_loss": 1.1072193384170532, |
| "eval_runtime": 23.3961, |
| "eval_samples_per_second": 404.255, |
| "eval_steps_per_second": 1.581, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.819672131147541, |
| "grad_norm": 3.012749671936035, |
| "learning_rate": 2.4589055134248825e-05, |
| "loss": 3.0105, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.819672131147541, |
| "eval_cosine_accuracy": 0.9498836994171143, |
| "eval_loss": 1.038019061088562, |
| "eval_runtime": 22.8225, |
| "eval_samples_per_second": 414.416, |
| "eval_steps_per_second": 1.621, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.2293202293202294, |
| "grad_norm": 3.132009267807007, |
| "learning_rate": 2.9569679354976812e-05, |
| "loss": 2.6189, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.2293202293202294, |
| "eval_cosine_accuracy": 0.955910325050354, |
| "eval_loss": 1.0144742727279663, |
| "eval_runtime": 22.4633, |
| "eval_samples_per_second": 421.042, |
| "eval_steps_per_second": 1.647, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.6388206388206388, |
| "grad_norm": 2.9897189140319824, |
| "learning_rate": 2.6766216489460155e-05, |
| "loss": 2.4043, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.6388206388206388, |
| "eval_cosine_accuracy": 0.9584478735923767, |
| "eval_loss": 0.9785193204879761, |
| "eval_runtime": 22.6802, |
| "eval_samples_per_second": 417.016, |
| "eval_steps_per_second": 1.631, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 19520, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
