| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02249212775528565, | |
| "eval_steps": 7, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000899685110211426, | |
| "eval_loss": 3.835435390472412, | |
| "eval_runtime": 59.8296, | |
| "eval_samples_per_second": 7.822, | |
| "eval_steps_per_second": 3.911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002699055330634278, | |
| "grad_norm": 2.3686490058898926, | |
| "learning_rate": 6e-05, | |
| "loss": 3.9935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005398110661268556, | |
| "grad_norm": 2.8806848526000977, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006297795771479982, | |
| "eval_loss": 3.3810648918151855, | |
| "eval_runtime": 60.3217, | |
| "eval_samples_per_second": 7.758, | |
| "eval_steps_per_second": 3.879, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008097165991902834, | |
| "grad_norm": 3.384768486022949, | |
| "learning_rate": 0.00018, | |
| "loss": 3.31, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "grad_norm": 3.7593495845794678, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.8503, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012595591542959963, | |
| "eval_loss": 2.4219021797180176, | |
| "eval_runtime": 60.335, | |
| "eval_samples_per_second": 7.757, | |
| "eval_steps_per_second": 3.878, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01349527665317139, | |
| "grad_norm": 4.259631633758545, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.7158, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 2.70001220703125, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.1973, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018893387314439947, | |
| "grad_norm": 4.213700771331787, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.3979, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018893387314439947, | |
| "eval_loss": 2.188023805618286, | |
| "eval_runtime": 60.3275, | |
| "eval_samples_per_second": 7.758, | |
| "eval_steps_per_second": 3.879, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "grad_norm": 2.784543037414551, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.3244, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "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": 9273591044505600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |