| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1062534587714443, |
| "eval_steps": 100, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22136137244050913, |
| "grad_norm": 1.6171875, |
| "learning_rate": 0.00017809734513274337, |
| "loss": 1.2949, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.22136137244050913, |
| "eval_loss": 1.2047334909439087, |
| "eval_mean_token_accuracy": 0.7032503170787163, |
| "eval_num_tokens": 1635208.0, |
| "eval_runtime": 55.1857, |
| "eval_samples_per_second": 23.031, |
| "eval_steps_per_second": 2.881, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.44272274488101826, |
| "grad_norm": 1.5234375, |
| "learning_rate": 0.00015597345132743363, |
| "loss": 1.187, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.44272274488101826, |
| "eval_loss": 1.1497339010238647, |
| "eval_mean_token_accuracy": 0.7146404561756542, |
| "eval_num_tokens": 3271888.0, |
| "eval_runtime": 54.9525, |
| "eval_samples_per_second": 23.129, |
| "eval_steps_per_second": 2.893, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6640841173215274, |
| "grad_norm": 1.4140625, |
| "learning_rate": 0.00013384955752212388, |
| "loss": 1.1394, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6640841173215274, |
| "eval_loss": 1.1108253002166748, |
| "eval_mean_token_accuracy": 0.7227962376936427, |
| "eval_num_tokens": 4908096.0, |
| "eval_runtime": 54.9495, |
| "eval_samples_per_second": 23.13, |
| "eval_steps_per_second": 2.894, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8854454897620365, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.00011172566371681417, |
| "loss": 1.0831, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8854454897620365, |
| "eval_loss": 1.0701380968093872, |
| "eval_mean_token_accuracy": 0.7318694584024777, |
| "eval_num_tokens": 6544993.0, |
| "eval_runtime": 54.9634, |
| "eval_samples_per_second": 23.124, |
| "eval_steps_per_second": 2.893, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.1062534587714443, |
| "grad_norm": 1.296875, |
| "learning_rate": 8.960176991150443e-05, |
| "loss": 0.8872, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.1062534587714443, |
| "eval_loss": 1.084444284439087, |
| "eval_mean_token_accuracy": 0.735802007921087, |
| "eval_num_tokens": 8174028.0, |
| "eval_runtime": 54.9918, |
| "eval_samples_per_second": 23.113, |
| "eval_steps_per_second": 2.891, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 904, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 2.163091277296435e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
