{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 42, "global_step": 42, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.047619047619047616, "grad_norm": 22.37241554260254, "learning_rate": 1e-05, "loss": 4.380859375, "step": 1 }, { "epoch": 0.09523809523809523, "grad_norm": 19.60361671447754, "learning_rate": 9.986018985905901e-06, "loss": 4.0, "step": 2 }, { "epoch": 0.14285714285714285, "grad_norm": 13.838263511657715, "learning_rate": 9.944154131125643e-06, "loss": 2.966796875, "step": 3 }, { "epoch": 0.19047619047619047, "grad_norm": 11.4894380569458, "learning_rate": 9.874639560909118e-06, "loss": 2.7666015625, "step": 4 }, { "epoch": 0.23809523809523808, "grad_norm": 9.826122283935547, "learning_rate": 9.777864028930705e-06, "loss": 2.93994140625, "step": 5 }, { "epoch": 0.2857142857142857, "grad_norm": 7.191762924194336, "learning_rate": 9.654368743221022e-06, "loss": 2.2421875, "step": 6 }, { "epoch": 0.3333333333333333, "grad_norm": 5.491899490356445, "learning_rate": 9.504844339512096e-06, "loss": 2.205078125, "step": 7 }, { "epoch": 0.38095238095238093, "grad_norm": 3.323521375656128, "learning_rate": 9.330127018922195e-06, "loss": 1.89794921875, "step": 8 }, { "epoch": 0.42857142857142855, "grad_norm": 3.0935871601104736, "learning_rate": 9.131193871579975e-06, "loss": 1.951171875, "step": 9 }, { "epoch": 0.47619047619047616, "grad_norm": 4.228043556213379, "learning_rate": 8.90915741234015e-06, "loss": 2.6162109375, "step": 10 }, { "epoch": 0.5238095238095238, "grad_norm": 2.3461997509002686, "learning_rate": 8.665259359149132e-06, "loss": 2.041015625, "step": 11 }, { "epoch": 0.5714285714285714, "grad_norm": 1.5732345581054688, "learning_rate": 8.400863688854598e-06, "loss": 1.80810546875, "step": 12 }, { "epoch": 0.6190476190476191, "grad_norm": 1.688090205192566, "learning_rate": 8.117449009293668e-06, "loss": 2.046875, "step": 13 }, { "epoch": 0.6666666666666666, "grad_norm": 3.0558202266693115, "learning_rate": 7.81660029031811e-06, "loss": 2.32470703125, "step": 14 }, { "epoch": 0.7142857142857143, "grad_norm": 3.692765474319458, "learning_rate": 7.500000000000001e-06, "loss": 2.52880859375, "step": 15 }, { "epoch": 0.7619047619047619, "grad_norm": 1.2358481884002686, "learning_rate": 7.169418695587791e-06, "loss": 1.900390625, "step": 16 }, { "epoch": 0.8095238095238095, "grad_norm": 1.0433543920516968, "learning_rate": 6.8267051218319766e-06, "loss": 1.7958984375, "step": 17 }, { "epoch": 0.8571428571428571, "grad_norm": 0.9277468919754028, "learning_rate": 6.473775872054522e-06, "loss": 2.07763671875, "step": 18 }, { "epoch": 0.9047619047619048, "grad_norm": 2.2380104064941406, "learning_rate": 6.112604669781572e-06, "loss": 2.49365234375, "step": 19 }, { "epoch": 0.9523809523809523, "grad_norm": 0.7635462284088135, "learning_rate": 5.745211330880872e-06, "loss": 1.9228515625, "step": 20 }, { "epoch": 1.0, "grad_norm": 0.709028959274292, "learning_rate": 5.373650467932122e-06, "loss": 2.109375, "step": 21 }, { "epoch": 1.0476190476190477, "grad_norm": 0.667512059211731, "learning_rate": 5e-06, "loss": 2.0908203125, "step": 22 }, { "epoch": 1.0952380952380953, "grad_norm": 0.7330001592636108, "learning_rate": 4.626349532067879e-06, "loss": 2.0748291015625, "step": 23 }, { "epoch": 1.1428571428571428, "grad_norm": 0.7032254338264465, "learning_rate": 4.254788669119127e-06, "loss": 1.7490234375, "step": 24 }, { "epoch": 1.1904761904761905, "grad_norm": 0.4826013445854187, "learning_rate": 3.887395330218429e-06, "loss": 1.83642578125, "step": 25 }, { "epoch": 1.2380952380952381, "grad_norm": 0.5162563323974609, "learning_rate": 3.526224127945479e-06, "loss": 2.123046875, "step": 26 }, { "epoch": 1.2857142857142856, "grad_norm": 0.5667943358421326, "learning_rate": 3.173294878168025e-06, "loss": 1.728515625, "step": 27 }, { "epoch": 1.3333333333333333, "grad_norm": 0.44317901134490967, "learning_rate": 2.83058130441221e-06, "loss": 1.76171875, "step": 28 }, { "epoch": 1.380952380952381, "grad_norm": 0.43383491039276123, "learning_rate": 2.5000000000000015e-06, "loss": 1.57958984375, "step": 29 }, { "epoch": 1.4285714285714286, "grad_norm": 0.4231622517108917, "learning_rate": 2.1833997096818897e-06, "loss": 1.6708984375, "step": 30 }, { "epoch": 1.4761904761904763, "grad_norm": 0.5360862016677856, "learning_rate": 1.8825509907063328e-06, "loss": 2.2705078125, "step": 31 }, { "epoch": 1.5238095238095237, "grad_norm": 0.4170989692211151, "learning_rate": 1.5991363111454023e-06, "loss": 1.828125, "step": 32 }, { "epoch": 1.5714285714285714, "grad_norm": 0.46283450722694397, "learning_rate": 1.3347406408508695e-06, "loss": 1.6494140625, "step": 33 }, { "epoch": 1.619047619047619, "grad_norm": 0.42448610067367554, "learning_rate": 1.0908425876598512e-06, "loss": 1.8916015625, "step": 34 }, { "epoch": 1.6666666666666665, "grad_norm": 0.5700374841690063, "learning_rate": 8.688061284200266e-07, "loss": 2.14208984375, "step": 35 }, { "epoch": 1.7142857142857144, "grad_norm": 0.828970193862915, "learning_rate": 6.698729810778065e-07, "loss": 2.3330078125, "step": 36 }, { "epoch": 1.7619047619047619, "grad_norm": 0.3890222907066345, "learning_rate": 4.951556604879049e-07, "loss": 1.80615234375, "step": 37 }, { "epoch": 1.8095238095238095, "grad_norm": 0.37376007437705994, "learning_rate": 3.4563125677897936e-07, "loss": 1.7119140625, "step": 38 }, { "epoch": 1.8571428571428572, "grad_norm": 0.42672255635261536, "learning_rate": 2.2213597106929608e-07, "loss": 1.99755859375, "step": 39 }, { "epoch": 1.9047619047619047, "grad_norm": 0.9024607539176941, "learning_rate": 1.253604390908819e-07, "loss": 2.39599609375, "step": 40 }, { "epoch": 1.9523809523809523, "grad_norm": 0.3674366772174835, "learning_rate": 5.584586887435739e-08, "loss": 1.86083984375, "step": 41 }, { "epoch": 2.0, "grad_norm": 0.43031445145606995, "learning_rate": 1.3981014094099354e-08, "loss": 2.0537109375, "step": 42 }, { "epoch": 2.0, "eval_loss": 1.890625, "eval_runtime": 9.7275, "eval_samples_per_second": 0.103, "eval_steps_per_second": 0.103, "step": 42 } ], "logging_steps": 1.0, "max_steps": 42, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.653216786127258e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }