| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012511729746637473, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012511729746637473, | |
| "grad_norm": 2.706839084625244, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012511729746637473, | |
| "eval_loss": 5.333587169647217, | |
| "eval_runtime": 13.4763, | |
| "eval_samples_per_second": 25.007, | |
| "eval_steps_per_second": 12.541, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025023459493274947, | |
| "grad_norm": 2.674034833908081, | |
| "learning_rate": 4e-05, | |
| "loss": 5.6424, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003753518923991242, | |
| "grad_norm": 2.413527011871338, | |
| "learning_rate": 6e-05, | |
| "loss": 5.1365, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003753518923991242, | |
| "eval_loss": 5.324682235717773, | |
| "eval_runtime": 9.7462, | |
| "eval_samples_per_second": 34.577, | |
| "eval_steps_per_second": 17.34, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005004691898654989, | |
| "grad_norm": 2.4288065433502197, | |
| "learning_rate": 8e-05, | |
| "loss": 5.3042, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006255864873318737, | |
| "grad_norm": 2.518660545349121, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1933, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007507037847982484, | |
| "grad_norm": 2.6484947204589844, | |
| "learning_rate": 0.00012, | |
| "loss": 4.8765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007507037847982484, | |
| "eval_loss": 5.028453826904297, | |
| "eval_runtime": 9.774, | |
| "eval_samples_per_second": 34.479, | |
| "eval_steps_per_second": 17.291, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008758210822646231, | |
| "grad_norm": 3.5504117012023926, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7697, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010009383797309979, | |
| "grad_norm": 3.5056967735290527, | |
| "learning_rate": 0.00016, | |
| "loss": 4.9152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011260556771973726, | |
| "grad_norm": 3.492283582687378, | |
| "learning_rate": 0.00018, | |
| "loss": 4.0476, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011260556771973726, | |
| "eval_loss": 3.841667890548706, | |
| "eval_runtime": 9.7726, | |
| "eval_samples_per_second": 34.484, | |
| "eval_steps_per_second": 17.293, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012511729746637473, | |
| "grad_norm": 3.3424651622772217, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7765, | |
| "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": 1742636046090240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |