| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007349023498502636, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.349023498502637e-05, | |
| "grad_norm": 7.747332572937012, | |
| "learning_rate": 2e-05, | |
| "loss": 14.5233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.349023498502637e-05, | |
| "eval_loss": 3.512305736541748, | |
| "eval_runtime": 43.3878, | |
| "eval_samples_per_second": 132.065, | |
| "eval_steps_per_second": 66.032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014698046997005273, | |
| "grad_norm": 7.784502029418945, | |
| "learning_rate": 4e-05, | |
| "loss": 12.8721, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002204707049550791, | |
| "grad_norm": 7.862401962280273, | |
| "learning_rate": 6e-05, | |
| "loss": 14.4835, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002204707049550791, | |
| "eval_loss": 3.5023274421691895, | |
| "eval_runtime": 42.2514, | |
| "eval_samples_per_second": 135.617, | |
| "eval_steps_per_second": 67.808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029396093994010547, | |
| "grad_norm": 7.31413459777832, | |
| "learning_rate": 8e-05, | |
| "loss": 14.0422, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003674511749251318, | |
| "grad_norm": 9.078619956970215, | |
| "learning_rate": 0.0001, | |
| "loss": 14.5767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004409414099101582, | |
| "grad_norm": 6.94755220413208, | |
| "learning_rate": 0.00012, | |
| "loss": 13.9467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004409414099101582, | |
| "eval_loss": 3.443692684173584, | |
| "eval_runtime": 43.1827, | |
| "eval_samples_per_second": 132.692, | |
| "eval_steps_per_second": 66.346, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005144316448951845, | |
| "grad_norm": 7.660728931427002, | |
| "learning_rate": 0.00014, | |
| "loss": 14.763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005879218798802109, | |
| "grad_norm": 6.398442268371582, | |
| "learning_rate": 0.00016, | |
| "loss": 13.3612, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006614121148652373, | |
| "grad_norm": 7.0156145095825195, | |
| "learning_rate": 0.00018, | |
| "loss": 12.6919, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006614121148652373, | |
| "eval_loss": 3.3300187587738037, | |
| "eval_runtime": 43.082, | |
| "eval_samples_per_second": 133.002, | |
| "eval_steps_per_second": 66.501, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007349023498502636, | |
| "grad_norm": 7.406718730926514, | |
| "learning_rate": 0.0002, | |
| "loss": 14.0833, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21229511639040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |