| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11285266457680251, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025078369905956114, | |
| "eval_loss": 2.34328031539917, | |
| "eval_runtime": 49.0034, | |
| "eval_samples_per_second": 13.713, | |
| "eval_steps_per_second": 1.714, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007523510971786834, | |
| "grad_norm": 1.412799596786499, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012539184952978056, | |
| "eval_loss": 2.1037039756774902, | |
| "eval_runtime": 49.6313, | |
| "eval_samples_per_second": 13.54, | |
| "eval_steps_per_second": 1.692, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015047021943573668, | |
| "grad_norm": 1.2794967889785767, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2497, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0225705329153605, | |
| "grad_norm": 0.7042816281318665, | |
| "learning_rate": 9e-05, | |
| "loss": 1.9238, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025078369905956112, | |
| "eval_loss": 1.7871791124343872, | |
| "eval_runtime": 49.7536, | |
| "eval_samples_per_second": 13.507, | |
| "eval_steps_per_second": 1.688, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030094043887147336, | |
| "grad_norm": 0.6223757266998291, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.7599, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03761755485893417, | |
| "grad_norm": 0.5316658020019531, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7352, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03761755485893417, | |
| "eval_loss": 1.6541856527328491, | |
| "eval_runtime": 49.8208, | |
| "eval_samples_per_second": 13.488, | |
| "eval_steps_per_second": 1.686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.045141065830721, | |
| "grad_norm": 0.4628920555114746, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.663, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.050156739811912224, | |
| "eval_loss": 1.6090316772460938, | |
| "eval_runtime": 49.8182, | |
| "eval_samples_per_second": 13.489, | |
| "eval_steps_per_second": 1.686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.052664576802507836, | |
| "grad_norm": 0.3976956307888031, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.6016, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06018808777429467, | |
| "grad_norm": 0.3693683445453644, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.6029, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06269592476489028, | |
| "eval_loss": 1.5837934017181396, | |
| "eval_runtime": 49.7929, | |
| "eval_samples_per_second": 13.496, | |
| "eval_steps_per_second": 1.687, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0677115987460815, | |
| "grad_norm": 0.3791425824165344, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.5915, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07523510971786834, | |
| "grad_norm": 0.36740052700042725, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5772, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07523510971786834, | |
| "eval_loss": 1.5675104856491089, | |
| "eval_runtime": 49.7922, | |
| "eval_samples_per_second": 13.496, | |
| "eval_steps_per_second": 1.687, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 0.427331805229187, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.5755, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0877742946708464, | |
| "eval_loss": 1.5577967166900635, | |
| "eval_runtime": 49.8174, | |
| "eval_samples_per_second": 13.489, | |
| "eval_steps_per_second": 1.686, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.090282131661442, | |
| "grad_norm": 0.33437755703926086, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.5904, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09780564263322884, | |
| "grad_norm": 0.3643655776977539, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.5416, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10031347962382445, | |
| "eval_loss": 1.5517269372940063, | |
| "eval_runtime": 49.7995, | |
| "eval_samples_per_second": 13.494, | |
| "eval_steps_per_second": 1.687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10532915360501567, | |
| "grad_norm": 0.34911882877349854, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.5553, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11285266457680251, | |
| "grad_norm": 0.38676726818084717, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5355, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11285266457680251, | |
| "eval_loss": 1.5492891073226929, | |
| "eval_runtime": 49.8004, | |
| "eval_samples_per_second": 13.494, | |
| "eval_steps_per_second": 1.687, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.0895984091136e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |