| { |
| "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": 1.458817720413208, |
| "learning_rate": 1e-05, |
| "loss": 1.83203125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 1.204423427581787, |
| "learning_rate": 9.986018985905901e-06, |
| "loss": 1.53271484375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.9860306978225708, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 1.29736328125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.2528539896011353, |
| "learning_rate": 9.874639560909118e-06, |
| "loss": 1.4521484375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 1.0723183155059814, |
| "learning_rate": 9.777864028930705e-06, |
| "loss": 1.25830078125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.7818373441696167, |
| "learning_rate": 9.654368743221022e-06, |
| "loss": 0.97021484375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.7274077534675598, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 0.8818359375, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 1.2297133207321167, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 1.17919921875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.8559923768043518, |
| "learning_rate": 9.131193871579975e-06, |
| "loss": 0.83837890625, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.8592395186424255, |
| "learning_rate": 8.90915741234015e-06, |
| "loss": 0.84228515625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 1.0950394868850708, |
| "learning_rate": 8.665259359149132e-06, |
| "loss": 0.875, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.5367376804351807, |
| "learning_rate": 8.400863688854598e-06, |
| "loss": 0.63134765625, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.6109802722930908, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 0.649169921875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.4308861792087555, |
| "learning_rate": 7.81660029031811e-06, |
| "loss": 0.62451171875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.3806557059288025, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.611083984375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.3664940297603607, |
| "learning_rate": 7.169418695587791e-06, |
| "loss": 0.58203125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 0.24358318746089935, |
| "learning_rate": 6.8267051218319766e-06, |
| "loss": 0.5665283203125, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.1669350415468216, |
| "learning_rate": 6.473775872054522e-06, |
| "loss": 0.513427734375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 0.18984302878379822, |
| "learning_rate": 6.112604669781572e-06, |
| "loss": 0.5347900390625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.09741250425577164, |
| "learning_rate": 5.745211330880872e-06, |
| "loss": 0.39990234375, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.10498647391796112, |
| "learning_rate": 5.373650467932122e-06, |
| "loss": 0.4908447265625, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0476190476190477, |
| "grad_norm": 0.12174811214208603, |
| "learning_rate": 5e-06, |
| "loss": 0.4842529296875, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0952380952380953, |
| "grad_norm": 0.1169494017958641, |
| "learning_rate": 4.626349532067879e-06, |
| "loss": 0.48822021484375, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 0.09415657073259354, |
| "learning_rate": 4.254788669119127e-06, |
| "loss": 0.4603271484375, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.1904761904761905, |
| "grad_norm": 0.09546365588903427, |
| "learning_rate": 3.887395330218429e-06, |
| "loss": 0.4552001953125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.2380952380952381, |
| "grad_norm": 0.10419897735118866, |
| "learning_rate": 3.526224127945479e-06, |
| "loss": 0.46697998046875, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.2857142857142856, |
| "grad_norm": 0.0748233050107956, |
| "learning_rate": 3.173294878168025e-06, |
| "loss": 0.4425048828125, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.07138227671384811, |
| "learning_rate": 2.83058130441221e-06, |
| "loss": 0.43017578125, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.380952380952381, |
| "grad_norm": 0.11345721781253815, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.499267578125, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.08105748146772385, |
| "learning_rate": 2.1833997096818897e-06, |
| "loss": 0.427734375, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4761904761904763, |
| "grad_norm": 0.09030455350875854, |
| "learning_rate": 1.8825509907063328e-06, |
| "loss": 0.48150634765625, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.5238095238095237, |
| "grad_norm": 0.10306616872549057, |
| "learning_rate": 1.5991363111454023e-06, |
| "loss": 0.4969482421875, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.07233192026615143, |
| "learning_rate": 1.3347406408508695e-06, |
| "loss": 0.4508056640625, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.619047619047619, |
| "grad_norm": 0.08430902659893036, |
| "learning_rate": 1.0908425876598512e-06, |
| "loss": 0.4718017578125, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.08449755609035492, |
| "learning_rate": 8.688061284200266e-07, |
| "loss": 0.504638671875, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 0.08751299232244492, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 0.507568359375, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.7619047619047619, |
| "grad_norm": 0.10116951167583466, |
| "learning_rate": 4.951556604879049e-07, |
| "loss": 0.489013671875, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.8095238095238095, |
| "grad_norm": 0.08777820318937302, |
| "learning_rate": 3.4563125677897936e-07, |
| "loss": 0.504150390625, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.8571428571428572, |
| "grad_norm": 0.08049055933952332, |
| "learning_rate": 2.2213597106929608e-07, |
| "loss": 0.4716796875, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 0.09183614701032639, |
| "learning_rate": 1.253604390908819e-07, |
| "loss": 0.490234375, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9523809523809523, |
| "grad_norm": 0.05638575926423073, |
| "learning_rate": 5.584586887435739e-08, |
| "loss": 0.378662109375, |
| "step": 41 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.06774341315031052, |
| "learning_rate": 1.3981014094099354e-08, |
| "loss": 0.47076416015625, |
| "step": 42 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.453369140625, |
| "eval_runtime": 1.0024, |
| "eval_samples_per_second": 3.991, |
| "eval_steps_per_second": 0.998, |
| "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": 1.863673959279493e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
