| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0007163893974369179, |
| "eval_steps": 3, |
| "global_step": 9, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_loss": 2.839312791824341, |
| "eval_runtime": 118.2817, |
| "eval_samples_per_second": 44.724, |
| "eval_steps_per_second": 22.362, |
| "step": 0 |
| }, |
| { |
| "epoch": 7.959882193743533e-05, |
| "grad_norm": 1.007415533065796, |
| "learning_rate": 0.0, |
| "loss": 2.6187, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00015919764387487066, |
| "grad_norm": 0.9872703552246094, |
| "learning_rate": 2e-05, |
| "loss": 2.7515, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00023879646581230599, |
| "grad_norm": 1.001963496208191, |
| "learning_rate": 4e-05, |
| "loss": 2.7804, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00023879646581230599, |
| "eval_loss": 2.833432912826538, |
| "eval_runtime": 113.4791, |
| "eval_samples_per_second": 46.617, |
| "eval_steps_per_second": 23.308, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0003183952877497413, |
| "grad_norm": 1.1029537916183472, |
| "learning_rate": 6e-05, |
| "loss": 2.7425, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.00039799410968717664, |
| "grad_norm": 1.0702811479568481, |
| "learning_rate": 8e-05, |
| "loss": 2.627, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00047759293162461197, |
| "grad_norm": 1.0418312549591064, |
| "learning_rate": 0.0001, |
| "loss": 2.7474, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00047759293162461197, |
| "eval_loss": 2.7597885131835938, |
| "eval_runtime": 113.454, |
| "eval_samples_per_second": 46.627, |
| "eval_steps_per_second": 23.313, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0005571917535620472, |
| "grad_norm": 1.4329075813293457, |
| "learning_rate": 0.00012, |
| "loss": 3.0091, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0006367905754994826, |
| "grad_norm": 0.8585416674613953, |
| "learning_rate": 0.00014, |
| "loss": 2.3107, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0007163893974369179, |
| "grad_norm": 0.849002480506897, |
| "learning_rate": 0.00016, |
| "loss": 2.6256, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0007163893974369179, |
| "eval_loss": 2.640645980834961, |
| "eval_runtime": 114.3602, |
| "eval_samples_per_second": 46.257, |
| "eval_steps_per_second": 23.129, |
| "step": 9 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 216490963894272.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
