| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00038342455642571626, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2780818547523876e-05, | |
| "eval_loss": 4.630336761474609, | |
| "eval_runtime": 3099.0955, | |
| "eval_samples_per_second": 10.631, | |
| "eval_steps_per_second": 5.315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.8342455642571626e-05, | |
| "grad_norm": 1.9508739709854126, | |
| "learning_rate": 6e-05, | |
| "loss": 3.807, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.668491128514325e-05, | |
| "grad_norm": 2.854942798614502, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7372, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010224654838019101, | |
| "eval_loss": 3.7988834381103516, | |
| "eval_runtime": 3098.2536, | |
| "eval_samples_per_second": 10.633, | |
| "eval_steps_per_second": 5.317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00011502736692771489, | |
| "grad_norm": 1.9922499656677246, | |
| "learning_rate": 0.00018, | |
| "loss": 3.7542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001533698225702865, | |
| "grad_norm": 1.7407194375991821, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.5334, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00019171227821285813, | |
| "grad_norm": 1.9099913835525513, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.7354, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00020449309676038202, | |
| "eval_loss": 3.5711941719055176, | |
| "eval_runtime": 3094.6709, | |
| "eval_samples_per_second": 10.646, | |
| "eval_steps_per_second": 5.323, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00023005473385542978, | |
| "grad_norm": 1.8773049116134644, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.6754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0002683971894980014, | |
| "grad_norm": 1.5180472135543823, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.5561, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000306739645140573, | |
| "grad_norm": 1.640310287475586, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.5839, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000306739645140573, | |
| "eval_loss": 3.536977529525757, | |
| "eval_runtime": 3094.5757, | |
| "eval_samples_per_second": 10.646, | |
| "eval_steps_per_second": 5.323, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00034508210078314466, | |
| "grad_norm": 1.7890769243240356, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.471, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00038342455642571626, | |
| "grad_norm": 2.205838918685913, | |
| "learning_rate": 0.0, | |
| "loss": 3.683, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.235418813038592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |