| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004245783700908126, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047175374454534735, | |
| "grad_norm": 0.022478384897112846, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3884, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009435074890906947, | |
| "grad_norm": 0.05584430694580078, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3796, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001415261233636042, | |
| "grad_norm": 0.02903936803340912, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001415261233636042, | |
| "eval_loss": 10.383217811584473, | |
| "eval_runtime": 13.8352, | |
| "eval_samples_per_second": 64.546, | |
| "eval_steps_per_second": 32.309, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018870149781813894, | |
| "grad_norm": 0.026352746412158012, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3762, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023587687227267368, | |
| "grad_norm": 0.03207406401634216, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3863, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002830522467272084, | |
| "grad_norm": 0.027389129623770714, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3768, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002830522467272084, | |
| "eval_loss": 10.383142471313477, | |
| "eval_runtime": 17.7035, | |
| "eval_samples_per_second": 50.442, | |
| "eval_steps_per_second": 25.249, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033022762118174315, | |
| "grad_norm": 0.021352829411625862, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3891, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003774029956362779, | |
| "grad_norm": 0.027664244174957275, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3855, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004245783700908126, | |
| "grad_norm": 0.022455623373389244, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004245783700908126, | |
| "eval_loss": 10.38300895690918, | |
| "eval_runtime": 15.2241, | |
| "eval_samples_per_second": 58.657, | |
| "eval_steps_per_second": 29.361, | |
| "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": 232756346880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |