| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 3766, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0002655337227827934, |
| "grad_norm": 5.798187732696533, |
| "learning_rate": 0.0, |
| "loss": 1.8907, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2655337227827934, |
| "grad_norm": 3.392871618270874, |
| "learning_rate": 2.652681890600106e-06, |
| "loss": 1.46, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2655337227827934, |
| "eval_cosine_accuracy": 0.9434220194816589, |
| "eval_loss": 0.5881128311157227, |
| "eval_runtime": 37.2445, |
| "eval_samples_per_second": 255.313, |
| "eval_steps_per_second": 1.02, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5310674455655868, |
| "grad_norm": 4.811636924743652, |
| "learning_rate": 5.30801911842804e-06, |
| "loss": 1.005, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5310674455655868, |
| "eval_cosine_accuracy": 0.9501525163650513, |
| "eval_loss": 0.5147020816802979, |
| "eval_runtime": 34.2592, |
| "eval_samples_per_second": 277.56, |
| "eval_steps_per_second": 1.109, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.7966011683483802, |
| "grad_norm": 4.881891250610352, |
| "learning_rate": 7.963356346255975e-06, |
| "loss": 0.7199, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.7966011683483802, |
| "eval_cosine_accuracy": 0.9585655927658081, |
| "eval_loss": 0.4466570317745209, |
| "eval_runtime": 35.3151, |
| "eval_samples_per_second": 269.262, |
| "eval_steps_per_second": 1.076, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 18830, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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 |
| } |
|
|
