| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.011471836641046231, |
| "eval_steps": 10, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001147183664104623, |
| "eval_loss": 1.873344898223877, |
| "eval_runtime": 12.7647, |
| "eval_samples_per_second": 515.797, |
| "eval_steps_per_second": 8.069, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002294367328209246, |
| "eval_loss": 1.8726389408111572, |
| "eval_runtime": 12.8667, |
| "eval_samples_per_second": 511.709, |
| "eval_steps_per_second": 8.005, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0034415509923138693, |
| "eval_loss": 1.8714078664779663, |
| "eval_runtime": 12.9103, |
| "eval_samples_per_second": 509.979, |
| "eval_steps_per_second": 7.978, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.004588734656418492, |
| "eval_loss": 1.8696790933609009, |
| "eval_runtime": 12.947, |
| "eval_samples_per_second": 508.534, |
| "eval_steps_per_second": 7.955, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0057359183205231154, |
| "eval_loss": 1.8675329685211182, |
| "eval_runtime": 12.9458, |
| "eval_samples_per_second": 508.582, |
| "eval_steps_per_second": 7.956, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006883101984627739, |
| "eval_loss": 1.8649154901504517, |
| "eval_runtime": 13.0432, |
| "eval_samples_per_second": 504.785, |
| "eval_steps_per_second": 7.897, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008030285648732363, |
| "eval_loss": 1.8619294166564941, |
| "eval_runtime": 13.0638, |
| "eval_samples_per_second": 503.988, |
| "eval_steps_per_second": 7.884, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.009177469312836984, |
| "eval_loss": 1.8583979606628418, |
| "eval_runtime": 13.0482, |
| "eval_samples_per_second": 504.592, |
| "eval_steps_per_second": 7.894, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.010324652976941608, |
| "eval_loss": 1.85438871383667, |
| "eval_runtime": 13.0615, |
| "eval_samples_per_second": 504.075, |
| "eval_steps_per_second": 7.886, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.011471836641046231, |
| "grad_norm": 9.938580513000488, |
| "learning_rate": 3.8226299694189603e-07, |
| "loss": 3.1046, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.011471836641046231, |
| "eval_loss": 1.849947214126587, |
| "eval_runtime": 13.0663, |
| "eval_samples_per_second": 503.89, |
| "eval_steps_per_second": 7.883, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 26151, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "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": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
