| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.888888888888889, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 1.7930933237075806, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 2.1674394607543945, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9768, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.868736982345581, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2561, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 2.0688636302948, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7526, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.9057183265686035, | |
| "learning_rate": 0.0002, | |
| "loss": 2.889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.6972851753234863, | |
| "learning_rate": 0.0001942857142857143, | |
| "loss": 2.4989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 3.0725390911102295, | |
| "learning_rate": 0.00018857142857142857, | |
| "loss": 3.584, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 2.9980862140655518, | |
| "learning_rate": 0.00018285714285714286, | |
| "loss": 2.9159, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.3923017978668213, | |
| "learning_rate": 0.00017714285714285713, | |
| "loss": 2.7993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.8530240058898926, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 2.0731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 2.3305249214172363, | |
| "learning_rate": 0.00016571428571428575, | |
| "loss": 2.4704, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 2.562769889831543, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1706, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "grad_norm": 2.4493045806884766, | |
| "learning_rate": 0.0001542857142857143, | |
| "loss": 2.2292, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.4787449836730957, | |
| "learning_rate": 0.00014857142857142857, | |
| "loss": 2.1731, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 2.0056028366088867, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 1.937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1481481481481481, | |
| "grad_norm": 1.9762787818908691, | |
| "learning_rate": 0.00013714285714285716, | |
| "loss": 1.644, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 2.3070919513702393, | |
| "learning_rate": 0.00013142857142857143, | |
| "loss": 2.0248, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2962962962962963, | |
| "grad_norm": 2.3103995323181152, | |
| "learning_rate": 0.00012571428571428572, | |
| "loss": 1.9342, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 2.19228458404541, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5943, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 2.453838586807251, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 1.7512, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 2.177041530609131, | |
| "learning_rate": 0.00010857142857142856, | |
| "loss": 1.7153, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5925925925925926, | |
| "grad_norm": 2.134157419204712, | |
| "learning_rate": 0.00010285714285714286, | |
| "loss": 1.6687, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 2.4414138793945312, | |
| "learning_rate": 9.714285714285715e-05, | |
| "loss": 1.9473, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7407407407407407, | |
| "grad_norm": 2.073535680770874, | |
| "learning_rate": 9.142857142857143e-05, | |
| "loss": 1.6294, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8148148148148149, | |
| "grad_norm": 2.7250802516937256, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 2.0007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 2.2123806476593018, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7899, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.9629629629629628, | |
| "grad_norm": 2.318277597427368, | |
| "learning_rate": 7.428571428571429e-05, | |
| "loss": 1.6948, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.404044151306152, | |
| "learning_rate": 6.857142857142858e-05, | |
| "loss": 2.0492, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 1.9140400886535645, | |
| "learning_rate": 6.285714285714286e-05, | |
| "loss": 1.4584, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.148148148148148, | |
| "grad_norm": 2.488027334213257, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.7693, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 2.41856050491333, | |
| "learning_rate": 5.142857142857143e-05, | |
| "loss": 1.8544, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2962962962962963, | |
| "grad_norm": 1.8152332305908203, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 1.3501, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 1.9145673513412476, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3809, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 2.48303484916687, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 1.708, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.5185185185185186, | |
| "grad_norm": 2.4277076721191406, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.6578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5925925925925926, | |
| "grad_norm": 2.0969839096069336, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 1.4353, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.2218620777130127, | |
| "learning_rate": 1.7142857142857145e-05, | |
| "loss": 1.565, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.7407407407407405, | |
| "grad_norm": 1.8250045776367188, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 1.3109, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.814814814814815, | |
| "grad_norm": 1.8353327512741089, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.4105, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 2.04841947555542, | |
| "learning_rate": 0.0, | |
| "loss": 1.4229, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1271040566378496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |