| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 3122, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00032030749519538755, |
| "grad_norm": 6.107327938079834, |
| "learning_rate": 0.0, |
| "loss": 2.2696, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3203074951953876, |
| "grad_norm": 3.857839345932007, |
| "learning_rate": 2.977933325424131e-05, |
| "loss": 1.6542, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3203074951953876, |
| "eval_cosine_accuracy": 0.9641829133033752, |
| "eval_loss": 0.5915806889533997, |
| "eval_runtime": 28.6636, |
| "eval_samples_per_second": 327.279, |
| "eval_steps_per_second": 1.291, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6406149903907752, |
| "grad_norm": 3.1807026863098145, |
| "learning_rate": 2.6220192193617276e-05, |
| "loss": 1.0828, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.6406149903907752, |
| "eval_cosine_accuracy": 0.9688732624053955, |
| "eval_loss": 0.5482337474822998, |
| "eval_runtime": 27.6361, |
| "eval_samples_per_second": 339.447, |
| "eval_steps_per_second": 1.339, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.9609224855861627, |
| "grad_norm": 4.243162155151367, |
| "learning_rate": 2.2661051132993238e-05, |
| "loss": 0.8294, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.9609224855861627, |
| "eval_cosine_accuracy": 0.971858024597168, |
| "eval_loss": 0.5288547277450562, |
| "eval_runtime": 27.5987, |
| "eval_samples_per_second": 339.908, |
| "eval_steps_per_second": 1.341, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 9366, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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 |
| } |
|
|
