| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016185594820609658, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005395198273536552, | |
| "eval_loss": 1.9554163217544556, | |
| "eval_runtime": 15.2817, | |
| "eval_samples_per_second": 51.107, | |
| "eval_steps_per_second": 25.586, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016185594820609657, | |
| "grad_norm": 3.3060264587402344, | |
| "learning_rate": 3e-05, | |
| "loss": 7.981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002697599136768276, | |
| "eval_loss": 1.9359668493270874, | |
| "eval_runtime": 15.2945, | |
| "eval_samples_per_second": 51.064, | |
| "eval_steps_per_second": 25.565, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032371189641219314, | |
| "grad_norm": 4.126204013824463, | |
| "learning_rate": 6e-05, | |
| "loss": 7.995, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0048556784461828975, | |
| "grad_norm": 126.12236785888672, | |
| "learning_rate": 9e-05, | |
| "loss": 7.6066, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005395198273536552, | |
| "eval_loss": 1.8610799312591553, | |
| "eval_runtime": 15.2832, | |
| "eval_samples_per_second": 51.102, | |
| "eval_steps_per_second": 25.584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006474237928243863, | |
| "grad_norm": 3.5348870754241943, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 7.6399, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008092797410304829, | |
| "grad_norm": 2.763091564178467, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.1684, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008092797410304829, | |
| "eval_loss": 1.8094102144241333, | |
| "eval_runtime": 15.2652, | |
| "eval_samples_per_second": 51.162, | |
| "eval_steps_per_second": 25.614, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009711356892365795, | |
| "grad_norm": 2.5705695152282715, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 7.411, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010790396547073105, | |
| "eval_loss": 1.7697291374206543, | |
| "eval_runtime": 15.2787, | |
| "eval_samples_per_second": 51.117, | |
| "eval_steps_per_second": 25.591, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01132991637442676, | |
| "grad_norm": 2.7558438777923584, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 7.025, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012948475856487725, | |
| "grad_norm": 2.9869544506073, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 7.2359, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013487995683841382, | |
| "eval_loss": 1.760362982749939, | |
| "eval_runtime": 15.3059, | |
| "eval_samples_per_second": 51.026, | |
| "eval_steps_per_second": 25.546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014567035338548692, | |
| "grad_norm": 2.3133647441864014, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 6.754, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016185594820609658, | |
| "grad_norm": 2.724479913711548, | |
| "learning_rate": 0.0, | |
| "loss": 7.0305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016185594820609658, | |
| "eval_loss": 1.7582391500473022, | |
| "eval_runtime": 15.255, | |
| "eval_samples_per_second": 51.196, | |
| "eval_steps_per_second": 25.631, | |
| "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": 458848619986944.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |