| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21447721179624665, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010723860589812333, | |
| "eval_loss": 2.445918560028076, | |
| "eval_runtime": 2.4031, | |
| "eval_samples_per_second": 16.645, | |
| "eval_steps_per_second": 8.323, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032171581769437, | |
| "grad_norm": 0.36872777342796326, | |
| "learning_rate": 6e-05, | |
| "loss": 2.534, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.064343163538874, | |
| "grad_norm": 0.7058968544006348, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5038, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08579088471849866, | |
| "eval_loss": 2.331052303314209, | |
| "eval_runtime": 1.8751, | |
| "eval_samples_per_second": 21.332, | |
| "eval_steps_per_second": 10.666, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09651474530831099, | |
| "grad_norm": 0.5926478505134583, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3774, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.128686327077748, | |
| "grad_norm": 0.4153237044811249, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.2659, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16085790884718498, | |
| "grad_norm": 0.2918945848941803, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.2631, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17158176943699732, | |
| "eval_loss": 2.192939043045044, | |
| "eval_runtime": 1.8804, | |
| "eval_samples_per_second": 21.272, | |
| "eval_steps_per_second": 10.636, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19302949061662197, | |
| "grad_norm": 0.24080850183963776, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1977, | |
| "step": 18 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1305053327523840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |