| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03128802363984008, | |
| "eval_steps": 150, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006952894142186686, | |
| "grad_norm": 5.413117383066536, | |
| "learning_rate": 6.944444444444445e-07, | |
| "loss": 2.3653, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013905788284373371, | |
| "grad_norm": 5.092870612337868, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 2.5001, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020858682426560054, | |
| "grad_norm": 3.6285625961711943, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 2.3759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027811576568746743, | |
| "grad_norm": 2.5025911526151075, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 1.944, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034764470710933427, | |
| "grad_norm": 3.077266049542496, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 2.2504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004171736485312011, | |
| "grad_norm": 4.068243939187174, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 2.0637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00486702589953068, | |
| "grad_norm": 3.511444738830971, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 2.3604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0055623153137493485, | |
| "grad_norm": 5.925744892256934, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 2.6528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0062576047279680165, | |
| "grad_norm": 2.7950114871483405, | |
| "learning_rate": 6.25e-06, | |
| "loss": 2.3229, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006952894142186685, | |
| "grad_norm": 6.586211843766182, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 2.342, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0076481835564053535, | |
| "grad_norm": 4.902839955269193, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 2.4188, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008343472970624021, | |
| "grad_norm": 4.257062809771645, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.7957, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009038762384842691, | |
| "grad_norm": 4.460352004615699, | |
| "learning_rate": 9.027777777777777e-06, | |
| "loss": 2.0726, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00973405179906136, | |
| "grad_norm": 5.858061506133739, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 2.0455, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010429341213280027, | |
| "grad_norm": 4.331946668100709, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.7645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011124630627498697, | |
| "grad_norm": 5.428742204187391, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.7446, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011819920041717365, | |
| "grad_norm": 2.485909286541028, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 1.5885, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012515209455936033, | |
| "grad_norm": 3.2602949308730222, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.1014, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013210498870154701, | |
| "grad_norm": 4.962187747415964, | |
| "learning_rate": 1.3194444444444446e-05, | |
| "loss": 1.3588, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01390578828437337, | |
| "grad_norm": 7.627756894198461, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.4014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014601077698592039, | |
| "grad_norm": 2.821848388410092, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 1.0959, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015296367112810707, | |
| "grad_norm": 10.989320944549025, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 1.739, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015991656527029375, | |
| "grad_norm": 4.300936602591115, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 1.1078, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.016686945941248043, | |
| "grad_norm": 3.7539663261019856, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.2701, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017382235355466714, | |
| "grad_norm": 2.589248169352173, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 1.4452, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018077524769685382, | |
| "grad_norm": 3.6679301322156177, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 1.4243, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01877281418390405, | |
| "grad_norm": 2.0885660923860074, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.4453, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01946810359812272, | |
| "grad_norm": 2.955353237610474, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 1.5388, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.020163393012341387, | |
| "grad_norm": 3.0527006398487018, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 1.4043, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.020858682426560055, | |
| "grad_norm": 1.9862208864154767, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.1007, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.021553971840778723, | |
| "grad_norm": 2.347361178472164, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 0.9291, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.022249261254997394, | |
| "grad_norm": 2.4812993223105995, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.9592, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.022944550669216062, | |
| "grad_norm": 1.639333831845777, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 1.0645, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02363984008343473, | |
| "grad_norm": 2.92858351082494, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 1.4269, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.024335129497653398, | |
| "grad_norm": 2.8503434812871604, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.7829, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.025030418911872066, | |
| "grad_norm": 2.4875590459354107, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9733, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.025725708326090734, | |
| "grad_norm": 5.2567545525905075, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 1.3559, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.026420997740309402, | |
| "grad_norm": 4.68745753567611, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 1.1499, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.027116287154528074, | |
| "grad_norm": 2.810345453706711, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.8636, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02781157656874674, | |
| "grad_norm": 3.0144493626195388, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.9274, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02850686598296541, | |
| "grad_norm": 2.3263036535508523, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 1.3979, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.029202155397184078, | |
| "grad_norm": 1.6009019341419857, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.9039, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.029897444811402746, | |
| "grad_norm": 2.0637506891442294, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 1.5187, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.030592734225621414, | |
| "grad_norm": 1.5533001268209932, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.8937, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.03128802363984008, | |
| "grad_norm": 1.9974857545819733, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.8218, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 5752, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 90, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 356771416768512.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |