| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 2000, |
| "global_step": 9502, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00021059281878487945, |
| "grad_norm": 5.663685321807861, |
| "learning_rate": 0.0, |
| "loss": 3.071, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "grad_norm": 3.0695738792419434, |
| "learning_rate": 1.2630581297388374e-05, |
| "loss": 2.308, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.42118563756975885, |
| "eval_cosine_accuracy": 0.9454372525215149, |
| "eval_loss": 0.6986740827560425, |
| "eval_runtime": 27.458, |
| "eval_samples_per_second": 344.417, |
| "eval_steps_per_second": 1.348, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "grad_norm": 3.1511430740356445, |
| "learning_rate": 2.5261162594776748e-05, |
| "loss": 1.522, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8423712751395177, |
| "eval_cosine_accuracy": 0.95579993724823, |
| "eval_loss": 0.6609594821929932, |
| "eval_runtime": 24.6873, |
| "eval_samples_per_second": 383.071, |
| "eval_steps_per_second": 1.499, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.2632298790110468, |
| "grad_norm": 2.732968807220459, |
| "learning_rate": 2.943386210681441e-05, |
| "loss": 1.1721, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.2632298790110468, |
| "eval_cosine_accuracy": 0.9589722156524658, |
| "eval_loss": 0.6233465671539307, |
| "eval_runtime": 25.2523, |
| "eval_samples_per_second": 374.5, |
| "eval_steps_per_second": 1.465, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.6840610205155182, |
| "grad_norm": 2.4099602699279785, |
| "learning_rate": 2.6310608286843795e-05, |
| "loss": 0.9996, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.6840610205155182, |
| "eval_cosine_accuracy": 0.9600296020507812, |
| "eval_loss": 0.6062663197517395, |
| "eval_runtime": 24.7031, |
| "eval_samples_per_second": 382.827, |
| "eval_steps_per_second": 1.498, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 2000, |
| "max_steps": 18996, |
| "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 |
| } |
|
|
