| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008194855451855224, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009105394946505805, | |
| "grad_norm": 4.183896541595459, | |
| "learning_rate": 2e-05, | |
| "loss": 4.0761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009105394946505805, | |
| "eval_loss": 3.742192268371582, | |
| "eval_runtime": 29.8122, | |
| "eval_samples_per_second": 15.531, | |
| "eval_steps_per_second": 7.782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001821078989301161, | |
| "grad_norm": 3.9799764156341553, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7619, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027316184839517414, | |
| "grad_norm": 2.859077215194702, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2922, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027316184839517414, | |
| "eval_loss": 3.734231948852539, | |
| "eval_runtime": 28.4411, | |
| "eval_samples_per_second": 16.279, | |
| "eval_steps_per_second": 8.157, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003642157978602322, | |
| "grad_norm": 3.7126123905181885, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8381, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004552697473252903, | |
| "grad_norm": 4.297725200653076, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2354, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005463236967903483, | |
| "grad_norm": 3.5856192111968994, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3092, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005463236967903483, | |
| "eval_loss": 3.567816734313965, | |
| "eval_runtime": 28.4363, | |
| "eval_samples_per_second": 16.282, | |
| "eval_steps_per_second": 8.159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006373776462554063, | |
| "grad_norm": 4.350411891937256, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007284315957204644, | |
| "grad_norm": 4.595995903015137, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7996, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008194855451855224, | |
| "grad_norm": 4.9837965965271, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3219, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008194855451855224, | |
| "eval_loss": 2.759291887283325, | |
| "eval_runtime": 28.3772, | |
| "eval_samples_per_second": 16.316, | |
| "eval_steps_per_second": 8.176, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1664607823331328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |