| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03673094582185491, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036730945821854912, | |
| "grad_norm": 3.601872444152832, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036730945821854912, | |
| "eval_loss": 3.481534481048584, | |
| "eval_runtime": 3.4183, | |
| "eval_samples_per_second": 33.642, | |
| "eval_steps_per_second": 16.967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "grad_norm": 3.4403226375579834, | |
| "learning_rate": 4e-05, | |
| "loss": 3.6684, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011019283746556474, | |
| "grad_norm": 2.7640533447265625, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2225, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011019283746556474, | |
| "eval_loss": 3.4582302570343018, | |
| "eval_runtime": 2.1134, | |
| "eval_samples_per_second": 54.415, | |
| "eval_steps_per_second": 27.444, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014692378328741965, | |
| "grad_norm": 2.394775867462158, | |
| "learning_rate": 8e-05, | |
| "loss": 3.3265, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018365472910927456, | |
| "grad_norm": 2.141361951828003, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 1.9102329015731812, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4038, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "eval_loss": 3.2603423595428467, | |
| "eval_runtime": 2.1406, | |
| "eval_samples_per_second": 53.722, | |
| "eval_steps_per_second": 27.095, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025711662075298437, | |
| "grad_norm": 1.3573756217956543, | |
| "learning_rate": 0.00014, | |
| "loss": 3.2466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02938475665748393, | |
| "grad_norm": 0.9463903307914734, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0153, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "grad_norm": 1.450535535812378, | |
| "learning_rate": 0.00018, | |
| "loss": 3.2902, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "eval_loss": 3.0791194438934326, | |
| "eval_runtime": 2.1398, | |
| "eval_samples_per_second": 53.744, | |
| "eval_steps_per_second": 27.106, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03673094582185491, | |
| "grad_norm": 1.1837118864059448, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0826, | |
| "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": 88232372994048.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |