| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09384775808133472, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031282586027111575, | |
| "eval_loss": 2.3120667934417725, | |
| "eval_runtime": 14.5793, | |
| "eval_samples_per_second": 13.855, | |
| "eval_steps_per_second": 6.928, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009384775808133473, | |
| "grad_norm": 3.425058126449585, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2217, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018769551616266946, | |
| "grad_norm": 0.7911273837089539, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02502606882168926, | |
| "eval_loss": 2.1398348808288574, | |
| "eval_runtime": 14.6208, | |
| "eval_samples_per_second": 13.816, | |
| "eval_steps_per_second": 6.908, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028154327424400417, | |
| "grad_norm": 0.801854133605957, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0873, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03753910323253389, | |
| "grad_norm": 0.7535266876220703, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04692387904066736, | |
| "grad_norm": 0.9067060947418213, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05005213764337852, | |
| "eval_loss": 2.041588306427002, | |
| "eval_runtime": 14.6554, | |
| "eval_samples_per_second": 13.783, | |
| "eval_steps_per_second": 6.892, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.056308654848800835, | |
| "grad_norm": 0.8475841879844666, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0277, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06569343065693431, | |
| "grad_norm": 0.7185098528862, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07507820646506778, | |
| "grad_norm": 0.76585453748703, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.9982, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07507820646506778, | |
| "eval_loss": 2.0088443756103516, | |
| "eval_runtime": 14.7377, | |
| "eval_samples_per_second": 13.706, | |
| "eval_steps_per_second": 6.853, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08446298227320125, | |
| "grad_norm": 0.8107510805130005, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0522, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09384775808133472, | |
| "grad_norm": 0.7503340244293213, | |
| "learning_rate": 0.0, | |
| "loss": 1.9216, | |
| "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": 4574107221884928.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |