| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006874033339061694, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001374806667812339, | |
| "grad_norm": 2.4402599334716797, | |
| "learning_rate": 1e-05, | |
| "loss": 28.0132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001374806667812339, | |
| "eval_loss": 1.7287589311599731, | |
| "eval_runtime": 94.6158, | |
| "eval_samples_per_second": 12.958, | |
| "eval_steps_per_second": 6.479, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002749613335624678, | |
| "grad_norm": 2.561180353164673, | |
| "learning_rate": 2e-05, | |
| "loss": 27.1881, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002749613335624678, | |
| "eval_loss": 1.7115710973739624, | |
| "eval_runtime": 43.4828, | |
| "eval_samples_per_second": 28.195, | |
| "eval_steps_per_second": 14.098, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041244200034370165, | |
| "grad_norm": 2.4208297729492188, | |
| "learning_rate": 3e-05, | |
| "loss": 26.9142, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005499226671249356, | |
| "grad_norm": 2.5348944664001465, | |
| "learning_rate": 4e-05, | |
| "loss": 27.3209, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005499226671249356, | |
| "eval_loss": 1.7024955749511719, | |
| "eval_runtime": 43.582, | |
| "eval_samples_per_second": 28.131, | |
| "eval_steps_per_second": 14.065, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006874033339061694, | |
| "grad_norm": 2.561366081237793, | |
| "learning_rate": 5e-05, | |
| "loss": 27.0795, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6332448610713600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |