| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "Batch Mean": 3.64324951171875, | |
| "accuracy": 0.6015625, | |
| "epoch": 0, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 6.657606601715088, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 0.6742, | |
| "step": 1 | |
| }, | |
| { | |
| "Batch Mean": 3.58660888671875, | |
| "accuracy": 0.5, | |
| "epoch": 0.0025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 5.2591233253479, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.6808, | |
| "step": 2 | |
| }, | |
| { | |
| "Batch Mean": 3.56298828125, | |
| "accuracy": 0.546875, | |
| "epoch": 0.005, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 5.481376647949219, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.6846, | |
| "step": 3 | |
| }, | |
| { | |
| "Batch Mean": 3.60186767578125, | |
| "accuracy": 0.5625, | |
| "epoch": 0.0075, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 7.51620626449585, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.6892, | |
| "step": 4 | |
| }, | |
| { | |
| "Batch Mean": 3.57855224609375, | |
| "accuracy": 0.453125, | |
| "epoch": 0.01, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 8.899469375610352, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.6956, | |
| "step": 5 | |
| }, | |
| { | |
| "Batch Mean": 3.595703125, | |
| "accuracy": 0.5546875, | |
| "epoch": 0.0125, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 6.726147174835205, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.6839, | |
| "step": 6 | |
| }, | |
| { | |
| "Batch Mean": 3.64105224609375, | |
| "accuracy": 0.453125, | |
| "epoch": 0.015, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 7.116271018981934, | |
| "learning_rate": 1.75e-06, | |
| "loss": 0.7154, | |
| "step": 7 | |
| }, | |
| { | |
| "Batch Mean": 3.6541748046875, | |
| "accuracy": 0.5546875, | |
| "epoch": 0.0175, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 6.190150260925293, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6844, | |
| "step": 8 | |
| }, | |
| { | |
| "Batch Mean": 3.6507568359375, | |
| "accuracy": 0.6015625, | |
| "epoch": 0.02, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 7.176676273345947, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.665, | |
| "step": 9 | |
| }, | |
| { | |
| "Batch Mean": 3.6649169921875, | |
| "accuracy": 0.59375, | |
| "epoch": 0.0225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 5.139154434204102, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6626, | |
| "step": 10 | |
| }, | |
| { | |
| "Batch Mean": 3.70733642578125, | |
| "accuracy": 0.671875, | |
| "epoch": 0.025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 5.621807098388672, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 0.6299, | |
| "step": 11 | |
| }, | |
| { | |
| "Batch Mean": 3.74017333984375, | |
| "accuracy": 0.65625, | |
| "epoch": 0.0275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 5.459871768951416, | |
| "learning_rate": 3e-06, | |
| "loss": 0.6321, | |
| "step": 12 | |
| }, | |
| { | |
| "Batch Mean": 3.8514404296875, | |
| "accuracy": 0.625, | |
| "epoch": 0.03, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 7.757749557495117, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 0.6453, | |
| "step": 13 | |
| }, | |
| { | |
| "Batch Mean": 3.80059814453125, | |
| "accuracy": 0.703125, | |
| "epoch": 0.0325, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 6.681384086608887, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.5769, | |
| "step": 14 | |
| }, | |
| { | |
| "Batch Mean": 3.8978271484375, | |
| "accuracy": 0.6640625, | |
| "epoch": 0.035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 10.110990524291992, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.6354, | |
| "step": 15 | |
| }, | |
| { | |
| "Batch Mean": 3.6146774291992188, | |
| "accuracy": 0.71875, | |
| "epoch": 0.0375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 10.233904838562012, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.6182, | |
| "step": 16 | |
| }, | |
| { | |
| "Batch Mean": 3.5331335067749023, | |
| "accuracy": 0.6328125, | |
| "epoch": 0.04, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 10.035528182983398, | |
| "learning_rate": 4.25e-06, | |
| "loss": 0.6252, | |
| "step": 17 | |
| }, | |
| { | |
| "Batch Mean": 3.0357871055603027, | |
| "accuracy": 0.625, | |
| "epoch": 0.0425, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 9.972918510437012, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.6225, | |
| "step": 18 | |
| }, | |
| { | |
| "Batch Mean": 2.6747031211853027, | |
| "accuracy": 0.6796875, | |
| "epoch": 0.045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 21.3759765625, | |
| "learning_rate": 4.75e-06, | |
| "loss": 0.6328, | |
| "step": 19 | |
| }, | |
| { | |
| "Batch Mean": 2.418215751647949, | |
| "accuracy": 0.6875, | |
| "epoch": 0.0475, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 10.712898254394531, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6352, | |
| "step": 20 | |
| }, | |
| { | |
| "Batch Mean": 1.9824256896972656, | |
| "accuracy": 0.640625, | |
| "epoch": 0.05, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 10.833212852478027, | |
| "learning_rate": 4.986842105263158e-06, | |
| "loss": 0.6244, | |
| "step": 21 | |
| }, | |
| { | |
| "Batch Mean": 1.5567502975463867, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.0525, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 8.710196495056152, | |
| "learning_rate": 4.973684210526316e-06, | |
| "loss": 0.6002, | |
| "step": 22 | |
| }, | |
| { | |
| "Batch Mean": 1.262591004371643, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.055, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 9.207337379455566, | |
| "learning_rate": 4.960526315789474e-06, | |
| "loss": 0.5754, | |
| "step": 23 | |
| }, | |
| { | |
| "Batch Mean": 0.9924072027206421, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.0575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 7.179128170013428, | |
| "learning_rate": 4.947368421052632e-06, | |
| "loss": 0.5446, | |
| "step": 24 | |
| }, | |
| { | |
| "Batch Mean": 0.7883305549621582, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.06, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 7.777095794677734, | |
| "learning_rate": 4.9342105263157895e-06, | |
| "loss": 0.6383, | |
| "step": 25 | |
| }, | |
| { | |
| "Batch Mean": 0.7204087972640991, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.0625, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 6.316252708435059, | |
| "learning_rate": 4.921052631578948e-06, | |
| "loss": 0.5416, | |
| "step": 26 | |
| }, | |
| { | |
| "Batch Mean": 0.7001075744628906, | |
| "accuracy": 0.75, | |
| "epoch": 0.065, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 6.2172017097473145, | |
| "learning_rate": 4.907894736842106e-06, | |
| "loss": 0.5603, | |
| "step": 27 | |
| }, | |
| { | |
| "Batch Mean": 0.4948960542678833, | |
| "accuracy": 0.6640625, | |
| "epoch": 0.0675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 6.071000576019287, | |
| "learning_rate": 4.894736842105264e-06, | |
| "loss": 0.5919, | |
| "step": 28 | |
| }, | |
| { | |
| "Batch Mean": 0.6193783283233643, | |
| "accuracy": 0.609375, | |
| "epoch": 0.07, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 7.123428821563721, | |
| "learning_rate": 4.881578947368422e-06, | |
| "loss": 0.6265, | |
| "step": 29 | |
| }, | |
| { | |
| "Batch Mean": 0.5463962554931641, | |
| "accuracy": 0.6640625, | |
| "epoch": 0.0725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 8.785526275634766, | |
| "learning_rate": 4.8684210526315795e-06, | |
| "loss": 0.6251, | |
| "step": 30 | |
| }, | |
| { | |
| "Batch Mean": 0.6883676052093506, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 6.22755241394043, | |
| "learning_rate": 4.855263157894737e-06, | |
| "loss": 0.5505, | |
| "step": 31 | |
| }, | |
| { | |
| "Batch Mean": 0.8646153211593628, | |
| "accuracy": 0.71875, | |
| "epoch": 0.0775, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 5.980678558349609, | |
| "learning_rate": 4.842105263157895e-06, | |
| "loss": 0.5817, | |
| "step": 32 | |
| }, | |
| { | |
| "Batch Mean": 0.9955297708511353, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.08, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 5.80774450302124, | |
| "learning_rate": 4.828947368421053e-06, | |
| "loss": 0.5697, | |
| "step": 33 | |
| }, | |
| { | |
| "Batch Mean": 1.163506031036377, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 7.277930736541748, | |
| "learning_rate": 4.815789473684211e-06, | |
| "loss": 0.5299, | |
| "step": 34 | |
| }, | |
| { | |
| "Batch Mean": 1.314648151397705, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.085, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 6.664306163787842, | |
| "learning_rate": 4.802631578947369e-06, | |
| "loss": 0.5548, | |
| "step": 35 | |
| }, | |
| { | |
| "Batch Mean": 1.4656352996826172, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 6.886595249176025, | |
| "learning_rate": 4.789473684210527e-06, | |
| "loss": 0.5432, | |
| "step": 36 | |
| }, | |
| { | |
| "Batch Mean": 1.5227254629135132, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.09, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 6.418576717376709, | |
| "learning_rate": 4.7763157894736844e-06, | |
| "loss": 0.5536, | |
| "step": 37 | |
| }, | |
| { | |
| "Batch Mean": 1.631667137145996, | |
| "accuracy": 0.71875, | |
| "epoch": 0.0925, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 8.560834884643555, | |
| "learning_rate": 4.763157894736842e-06, | |
| "loss": 0.569, | |
| "step": 38 | |
| }, | |
| { | |
| "Batch Mean": 1.6476902961730957, | |
| "accuracy": 0.734375, | |
| "epoch": 0.095, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 8.121230125427246, | |
| "learning_rate": 4.75e-06, | |
| "loss": 0.5418, | |
| "step": 39 | |
| }, | |
| { | |
| "Batch Mean": 1.492204189300537, | |
| "accuracy": 0.71875, | |
| "epoch": 0.0975, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 7.698504447937012, | |
| "learning_rate": 4.736842105263158e-06, | |
| "loss": 0.5079, | |
| "step": 40 | |
| }, | |
| { | |
| "Batch Mean": 1.3397908210754395, | |
| "accuracy": 0.75, | |
| "epoch": 0.1, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 8.164704322814941, | |
| "learning_rate": 4.723684210526316e-06, | |
| "loss": 0.5291, | |
| "step": 41 | |
| }, | |
| { | |
| "Batch Mean": 1.4944896697998047, | |
| "accuracy": 0.75, | |
| "epoch": 0.1025, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 7.740182399749756, | |
| "learning_rate": 4.710526315789474e-06, | |
| "loss": 0.5375, | |
| "step": 42 | |
| }, | |
| { | |
| "Batch Mean": 1.322850227355957, | |
| "accuracy": 0.765625, | |
| "epoch": 0.105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 7.922670841217041, | |
| "learning_rate": 4.697368421052632e-06, | |
| "loss": 0.4777, | |
| "step": 43 | |
| }, | |
| { | |
| "Batch Mean": 1.4683116674423218, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.1075, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 8.393726348876953, | |
| "learning_rate": 4.68421052631579e-06, | |
| "loss": 0.4728, | |
| "step": 44 | |
| }, | |
| { | |
| "Batch Mean": 1.6116371154785156, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.11, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 9.989266395568848, | |
| "learning_rate": 4.671052631578948e-06, | |
| "loss": 0.5428, | |
| "step": 45 | |
| }, | |
| { | |
| "Batch Mean": 1.52450692653656, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.1125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 9.131291389465332, | |
| "learning_rate": 4.657894736842106e-06, | |
| "loss": 0.4236, | |
| "step": 46 | |
| }, | |
| { | |
| "Batch Mean": 1.776949405670166, | |
| "accuracy": 0.71875, | |
| "epoch": 0.115, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 11.912744522094727, | |
| "learning_rate": 4.6447368421052635e-06, | |
| "loss": 0.6295, | |
| "step": 47 | |
| }, | |
| { | |
| "Batch Mean": 2.3817920684814453, | |
| "accuracy": 0.6875, | |
| "epoch": 0.1175, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 10.917041778564453, | |
| "learning_rate": 4.631578947368421e-06, | |
| "loss": 0.5316, | |
| "step": 48 | |
| }, | |
| { | |
| "Batch Mean": 2.175340175628662, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.12, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 8.514415740966797, | |
| "learning_rate": 4.618421052631579e-06, | |
| "loss": 0.4724, | |
| "step": 49 | |
| }, | |
| { | |
| "Batch Mean": 2.521066665649414, | |
| "accuracy": 0.65625, | |
| "epoch": 0.1225, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 10.435226440429688, | |
| "learning_rate": 4.605263157894737e-06, | |
| "loss": 0.6361, | |
| "step": 50 | |
| }, | |
| { | |
| "Batch Mean": 2.40045166015625, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1275, | |
| "grad_norm": 7.130827903747559, | |
| "learning_rate": 4.592105263157895e-06, | |
| "loss": 0.4949, | |
| "step": 51 | |
| }, | |
| { | |
| "Batch Mean": 2.7120556831359863, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.1275, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 6.832071304321289, | |
| "learning_rate": 4.578947368421053e-06, | |
| "loss": 0.5509, | |
| "step": 52 | |
| }, | |
| { | |
| "Batch Mean": 2.6350326538085938, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.13, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1325, | |
| "grad_norm": 6.527810096740723, | |
| "learning_rate": 4.565789473684211e-06, | |
| "loss": 0.5334, | |
| "step": 53 | |
| }, | |
| { | |
| "Batch Mean": 2.8320467472076416, | |
| "accuracy": 0.75, | |
| "epoch": 0.1325, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 6.686796188354492, | |
| "learning_rate": 4.552631578947369e-06, | |
| "loss": 0.505, | |
| "step": 54 | |
| }, | |
| { | |
| "Batch Mean": 2.5793724060058594, | |
| "accuracy": 0.71875, | |
| "epoch": 0.135, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1375, | |
| "grad_norm": 6.586344242095947, | |
| "learning_rate": 4.539473684210527e-06, | |
| "loss": 0.5145, | |
| "step": 55 | |
| }, | |
| { | |
| "Batch Mean": 2.652639389038086, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.1375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 7.232706069946289, | |
| "learning_rate": 4.526315789473685e-06, | |
| "loss": 0.4847, | |
| "step": 56 | |
| }, | |
| { | |
| "Batch Mean": 2.7974865436553955, | |
| "accuracy": 0.671875, | |
| "epoch": 0.14, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1425, | |
| "grad_norm": 9.864455223083496, | |
| "learning_rate": 4.513157894736843e-06, | |
| "loss": 0.5848, | |
| "step": 57 | |
| }, | |
| { | |
| "Batch Mean": 2.7397356033325195, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.1425, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 6.654571056365967, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.5149, | |
| "step": 58 | |
| }, | |
| { | |
| "Batch Mean": 3.020786762237549, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.145, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1475, | |
| "grad_norm": 7.521582126617432, | |
| "learning_rate": 4.4868421052631584e-06, | |
| "loss": 0.532, | |
| "step": 59 | |
| }, | |
| { | |
| "Batch Mean": 3.0784976482391357, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.1475, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 7.8287272453308105, | |
| "learning_rate": 4.473684210526316e-06, | |
| "loss": 0.5201, | |
| "step": 60 | |
| }, | |
| { | |
| "Batch Mean": 3.2929041385650635, | |
| "accuracy": 0.6875, | |
| "epoch": 0.15, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1525, | |
| "grad_norm": 7.036741733551025, | |
| "learning_rate": 4.460526315789474e-06, | |
| "loss": 0.5192, | |
| "step": 61 | |
| }, | |
| { | |
| "Batch Mean": 3.2737629413604736, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.1525, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 8.064910888671875, | |
| "learning_rate": 4.447368421052632e-06, | |
| "loss": 0.5094, | |
| "step": 62 | |
| }, | |
| { | |
| "Batch Mean": 3.0026721954345703, | |
| "accuracy": 0.75, | |
| "epoch": 0.155, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1575, | |
| "grad_norm": 8.189529418945312, | |
| "learning_rate": 4.43421052631579e-06, | |
| "loss": 0.4838, | |
| "step": 63 | |
| }, | |
| { | |
| "Batch Mean": 3.0598621368408203, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.1575, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.452142238616943, | |
| "learning_rate": 4.4210526315789476e-06, | |
| "loss": 0.5297, | |
| "step": 64 | |
| }, | |
| { | |
| "Batch Mean": 2.890104293823242, | |
| "accuracy": 0.734375, | |
| "epoch": 0.16, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1625, | |
| "grad_norm": 7.773412227630615, | |
| "learning_rate": 4.407894736842105e-06, | |
| "loss": 0.4938, | |
| "step": 65 | |
| }, | |
| { | |
| "Batch Mean": 2.8558566570281982, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.1625, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 7.888664722442627, | |
| "learning_rate": 4.394736842105263e-06, | |
| "loss": 0.5426, | |
| "step": 66 | |
| }, | |
| { | |
| "Batch Mean": 2.8415894508361816, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.165, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1675, | |
| "grad_norm": 7.992714881896973, | |
| "learning_rate": 4.381578947368421e-06, | |
| "loss": 0.5278, | |
| "step": 67 | |
| }, | |
| { | |
| "Batch Mean": 2.5067033767700195, | |
| "accuracy": 0.71875, | |
| "epoch": 0.1675, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 7.569831848144531, | |
| "learning_rate": 4.368421052631579e-06, | |
| "loss": 0.497, | |
| "step": 68 | |
| }, | |
| { | |
| "Batch Mean": 2.690906047821045, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.17, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1725, | |
| "grad_norm": 8.406615257263184, | |
| "learning_rate": 4.3552631578947375e-06, | |
| "loss": 0.5383, | |
| "step": 69 | |
| }, | |
| { | |
| "Batch Mean": 2.54428768157959, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.1725, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 6.022793292999268, | |
| "learning_rate": 4.342105263157895e-06, | |
| "loss": 0.4619, | |
| "step": 70 | |
| }, | |
| { | |
| "Batch Mean": 2.539039134979248, | |
| "accuracy": 0.75, | |
| "epoch": 0.175, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1775, | |
| "grad_norm": 5.931001663208008, | |
| "learning_rate": 4.328947368421053e-06, | |
| "loss": 0.4643, | |
| "step": 71 | |
| }, | |
| { | |
| "Batch Mean": 2.3624706268310547, | |
| "accuracy": 0.75, | |
| "epoch": 0.1775, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 6.277031898498535, | |
| "learning_rate": 4.315789473684211e-06, | |
| "loss": 0.5027, | |
| "step": 72 | |
| }, | |
| { | |
| "Batch Mean": 2.5795602798461914, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.18, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1825, | |
| "grad_norm": 7.181740760803223, | |
| "learning_rate": 4.302631578947369e-06, | |
| "loss": 0.4652, | |
| "step": 73 | |
| }, | |
| { | |
| "Batch Mean": 2.328335762023926, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.1825, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 6.926029205322266, | |
| "learning_rate": 4.289473684210527e-06, | |
| "loss": 0.4554, | |
| "step": 74 | |
| }, | |
| { | |
| "Batch Mean": 2.195453643798828, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.185, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 7.934150695800781, | |
| "learning_rate": 4.276315789473684e-06, | |
| "loss": 0.5458, | |
| "step": 75 | |
| }, | |
| { | |
| "Batch Mean": 2.7026095390319824, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.1875, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 7.034529209136963, | |
| "learning_rate": 4.2631578947368425e-06, | |
| "loss": 0.5041, | |
| "step": 76 | |
| }, | |
| { | |
| "Batch Mean": 2.611628532409668, | |
| "accuracy": 0.734375, | |
| "epoch": 0.19, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1925, | |
| "grad_norm": 7.741730213165283, | |
| "learning_rate": 4.25e-06, | |
| "loss": 0.4804, | |
| "step": 77 | |
| }, | |
| { | |
| "Batch Mean": 2.5273165702819824, | |
| "accuracy": 0.765625, | |
| "epoch": 0.1925, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 7.251089572906494, | |
| "learning_rate": 4.236842105263158e-06, | |
| "loss": 0.4959, | |
| "step": 78 | |
| }, | |
| { | |
| "Batch Mean": 2.5558762550354004, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.195, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1975, | |
| "grad_norm": 7.240261077880859, | |
| "learning_rate": 4.223684210526316e-06, | |
| "loss": 0.5173, | |
| "step": 79 | |
| }, | |
| { | |
| "Batch Mean": 2.2066729068756104, | |
| "accuracy": 0.78125, | |
| "epoch": 0.1975, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.0953474044799805, | |
| "learning_rate": 4.210526315789474e-06, | |
| "loss": 0.5174, | |
| "step": 80 | |
| }, | |
| { | |
| "Batch Mean": 2.377552032470703, | |
| "accuracy": 0.796875, | |
| "epoch": 0.2, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2025, | |
| "grad_norm": 7.204663276672363, | |
| "learning_rate": 4.197368421052632e-06, | |
| "loss": 0.4628, | |
| "step": 81 | |
| }, | |
| { | |
| "Batch Mean": 2.3107597827911377, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2025, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": 7.396126747131348, | |
| "learning_rate": 4.18421052631579e-06, | |
| "loss": 0.5078, | |
| "step": 82 | |
| }, | |
| { | |
| "Batch Mean": 1.8419753313064575, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.205, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2075, | |
| "grad_norm": 8.316776275634766, | |
| "learning_rate": 4.171052631578948e-06, | |
| "loss": 0.4945, | |
| "step": 83 | |
| }, | |
| { | |
| "Batch Mean": 2.162795066833496, | |
| "accuracy": 0.859375, | |
| "epoch": 0.2075, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 6.570835113525391, | |
| "learning_rate": 4.157894736842106e-06, | |
| "loss": 0.3966, | |
| "step": 84 | |
| }, | |
| { | |
| "Batch Mean": 2.2369089126586914, | |
| "accuracy": 0.765625, | |
| "epoch": 0.21, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2125, | |
| "grad_norm": 7.585580825805664, | |
| "learning_rate": 4.144736842105263e-06, | |
| "loss": 0.5321, | |
| "step": 85 | |
| }, | |
| { | |
| "Batch Mean": 2.4348106384277344, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.2125, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": 7.9683098793029785, | |
| "learning_rate": 4.1315789473684216e-06, | |
| "loss": 0.5224, | |
| "step": 86 | |
| }, | |
| { | |
| "Batch Mean": 2.9450817108154297, | |
| "accuracy": 0.8125, | |
| "epoch": 0.215, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2175, | |
| "grad_norm": 7.830796718597412, | |
| "learning_rate": 4.118421052631579e-06, | |
| "loss": 0.4866, | |
| "step": 87 | |
| }, | |
| { | |
| "Batch Mean": 2.9916036128997803, | |
| "accuracy": 0.765625, | |
| "epoch": 0.2175, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 9.743931770324707, | |
| "learning_rate": 4.105263157894737e-06, | |
| "loss": 0.5408, | |
| "step": 88 | |
| }, | |
| { | |
| "Batch Mean": 3.0171022415161133, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.22, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2225, | |
| "grad_norm": 7.245960235595703, | |
| "learning_rate": 4.092105263157895e-06, | |
| "loss": 0.4232, | |
| "step": 89 | |
| }, | |
| { | |
| "Batch Mean": 3.2700085639953613, | |
| "accuracy": 0.75, | |
| "epoch": 0.2225, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 7.346113681793213, | |
| "learning_rate": 4.078947368421053e-06, | |
| "loss": 0.4981, | |
| "step": 90 | |
| }, | |
| { | |
| "Batch Mean": 3.375551700592041, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.225, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2275, | |
| "grad_norm": 8.201985359191895, | |
| "learning_rate": 4.065789473684211e-06, | |
| "loss": 0.4761, | |
| "step": 91 | |
| }, | |
| { | |
| "Batch Mean": 3.438584327697754, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.2275, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 8.22840690612793, | |
| "learning_rate": 4.052631578947368e-06, | |
| "loss": 0.5708, | |
| "step": 92 | |
| }, | |
| { | |
| "Batch Mean": 3.2276859283447266, | |
| "accuracy": 0.71875, | |
| "epoch": 0.23, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2325, | |
| "grad_norm": 7.885838508605957, | |
| "learning_rate": 4.0394736842105265e-06, | |
| "loss": 0.5382, | |
| "step": 93 | |
| }, | |
| { | |
| "Batch Mean": 3.2703161239624023, | |
| "accuracy": 0.765625, | |
| "epoch": 0.2325, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.235, | |
| "grad_norm": 5.956949234008789, | |
| "learning_rate": 4.026315789473684e-06, | |
| "loss": 0.4753, | |
| "step": 94 | |
| }, | |
| { | |
| "Batch Mean": 2.999190330505371, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.235, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2375, | |
| "grad_norm": 6.309754848480225, | |
| "learning_rate": 4.013157894736842e-06, | |
| "loss": 0.5308, | |
| "step": 95 | |
| }, | |
| { | |
| "Batch Mean": 2.9133434295654297, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2375, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 7.293734073638916, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.4746, | |
| "step": 96 | |
| }, | |
| { | |
| "Batch Mean": 2.940767288208008, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.24, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2425, | |
| "grad_norm": 5.970653533935547, | |
| "learning_rate": 3.986842105263158e-06, | |
| "loss": 0.4666, | |
| "step": 97 | |
| }, | |
| { | |
| "Batch Mean": 2.4930241107940674, | |
| "accuracy": 0.828125, | |
| "epoch": 0.2425, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.245, | |
| "grad_norm": 5.983125686645508, | |
| "learning_rate": 3.9736842105263165e-06, | |
| "loss": 0.4405, | |
| "step": 98 | |
| }, | |
| { | |
| "Batch Mean": 2.768970012664795, | |
| "accuracy": 0.6875, | |
| "epoch": 0.245, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2475, | |
| "grad_norm": 7.222211837768555, | |
| "learning_rate": 3.960526315789474e-06, | |
| "loss": 0.5831, | |
| "step": 99 | |
| }, | |
| { | |
| "Batch Mean": 2.600813150405884, | |
| "accuracy": 0.8125, | |
| "epoch": 0.2475, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 6.174572944641113, | |
| "learning_rate": 3.947368421052632e-06, | |
| "loss": 0.3996, | |
| "step": 100 | |
| }, | |
| { | |
| "Batch Mean": 2.7795987129211426, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.25, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2525, | |
| "grad_norm": 6.83671236038208, | |
| "learning_rate": 3.93421052631579e-06, | |
| "loss": 0.5049, | |
| "step": 101 | |
| }, | |
| { | |
| "Batch Mean": 3.153959274291992, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.2525, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.255, | |
| "grad_norm": 7.497275352478027, | |
| "learning_rate": 3.921052631578947e-06, | |
| "loss": 0.4726, | |
| "step": 102 | |
| }, | |
| { | |
| "Batch Mean": 3.3440189361572266, | |
| "accuracy": 0.8125, | |
| "epoch": 0.255, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2575, | |
| "grad_norm": 6.329479217529297, | |
| "learning_rate": 3.907894736842106e-06, | |
| "loss": 0.3769, | |
| "step": 103 | |
| }, | |
| { | |
| "Batch Mean": 3.1725075244903564, | |
| "accuracy": 0.765625, | |
| "epoch": 0.2575, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 7.60507869720459, | |
| "learning_rate": 3.894736842105263e-06, | |
| "loss": 0.4352, | |
| "step": 104 | |
| }, | |
| { | |
| "Batch Mean": 3.409212827682495, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.26, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2625, | |
| "grad_norm": 9.034660339355469, | |
| "learning_rate": 3.8815789473684214e-06, | |
| "loss": 0.4505, | |
| "step": 105 | |
| }, | |
| { | |
| "Batch Mean": 3.7719802856445312, | |
| "accuracy": 0.765625, | |
| "epoch": 0.2625, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.265, | |
| "grad_norm": 8.710013389587402, | |
| "learning_rate": 3.868421052631579e-06, | |
| "loss": 0.4257, | |
| "step": 106 | |
| }, | |
| { | |
| "Batch Mean": 4.079001426696777, | |
| "accuracy": 0.71875, | |
| "epoch": 0.265, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2675, | |
| "grad_norm": 11.614973068237305, | |
| "learning_rate": 3.855263157894737e-06, | |
| "loss": 0.487, | |
| "step": 107 | |
| }, | |
| { | |
| "Batch Mean": 4.675480842590332, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.2675, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 11.474054336547852, | |
| "learning_rate": 3.842105263157895e-06, | |
| "loss": 0.5035, | |
| "step": 108 | |
| }, | |
| { | |
| "Batch Mean": 4.677275657653809, | |
| "accuracy": 0.765625, | |
| "epoch": 0.27, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2725, | |
| "grad_norm": 12.407071113586426, | |
| "learning_rate": 3.828947368421053e-06, | |
| "loss": 0.5013, | |
| "step": 109 | |
| }, | |
| { | |
| "Batch Mean": 5.106083869934082, | |
| "accuracy": 0.8125, | |
| "epoch": 0.2725, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 10.379884719848633, | |
| "learning_rate": 3.815789473684211e-06, | |
| "loss": 0.3935, | |
| "step": 110 | |
| }, | |
| { | |
| "Batch Mean": 5.2830119132995605, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.275, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2775, | |
| "grad_norm": 8.18240737915039, | |
| "learning_rate": 3.802631578947369e-06, | |
| "loss": 0.3212, | |
| "step": 111 | |
| }, | |
| { | |
| "Batch Mean": 4.785458564758301, | |
| "accuracy": 0.84375, | |
| "epoch": 0.2775, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 8.109498977661133, | |
| "learning_rate": 3.789473684210527e-06, | |
| "loss": 0.325, | |
| "step": 112 | |
| }, | |
| { | |
| "Batch Mean": 4.754400730133057, | |
| "accuracy": 0.78125, | |
| "epoch": 0.28, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2825, | |
| "grad_norm": 11.198568344116211, | |
| "learning_rate": 3.7763157894736847e-06, | |
| "loss": 0.477, | |
| "step": 113 | |
| }, | |
| { | |
| "Batch Mean": 4.87004280090332, | |
| "accuracy": 0.796875, | |
| "epoch": 0.2825, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.285, | |
| "grad_norm": 10.391942977905273, | |
| "learning_rate": 3.7631578947368426e-06, | |
| "loss": 0.4144, | |
| "step": 114 | |
| }, | |
| { | |
| "Batch Mean": 5.210759162902832, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.285, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2875, | |
| "grad_norm": 13.044468879699707, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.5755, | |
| "step": 115 | |
| }, | |
| { | |
| "Batch Mean": 4.891458511352539, | |
| "accuracy": 0.75, | |
| "epoch": 0.2875, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 10.2129487991333, | |
| "learning_rate": 3.736842105263158e-06, | |
| "loss": 0.5067, | |
| "step": 116 | |
| }, | |
| { | |
| "Batch Mean": 4.567095756530762, | |
| "accuracy": 0.828125, | |
| "epoch": 0.29, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2925, | |
| "grad_norm": 7.831666469573975, | |
| "learning_rate": 3.723684210526316e-06, | |
| "loss": 0.3706, | |
| "step": 117 | |
| }, | |
| { | |
| "Batch Mean": 4.688891410827637, | |
| "accuracy": 0.8125, | |
| "epoch": 0.2925, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.295, | |
| "grad_norm": 8.019044876098633, | |
| "learning_rate": 3.710526315789474e-06, | |
| "loss": 0.398, | |
| "step": 118 | |
| }, | |
| { | |
| "Batch Mean": 4.864707946777344, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.295, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2975, | |
| "grad_norm": 9.05286979675293, | |
| "learning_rate": 3.6973684210526317e-06, | |
| "loss": 0.5245, | |
| "step": 119 | |
| }, | |
| { | |
| "Batch Mean": 4.6876678466796875, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.2975, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 8.225624084472656, | |
| "learning_rate": 3.6842105263157896e-06, | |
| "loss": 0.442, | |
| "step": 120 | |
| }, | |
| { | |
| "Batch Mean": 4.1729278564453125, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.3, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3025, | |
| "grad_norm": 7.661060810089111, | |
| "learning_rate": 3.6710526315789476e-06, | |
| "loss": 0.4628, | |
| "step": 121 | |
| }, | |
| { | |
| "Batch Mean": 4.011091232299805, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3025, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.305, | |
| "grad_norm": 7.079358100891113, | |
| "learning_rate": 3.657894736842106e-06, | |
| "loss": 0.4218, | |
| "step": 122 | |
| }, | |
| { | |
| "Batch Mean": 4.086966514587402, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.305, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3075, | |
| "grad_norm": 6.512862682342529, | |
| "learning_rate": 3.644736842105264e-06, | |
| "loss": 0.4282, | |
| "step": 123 | |
| }, | |
| { | |
| "Batch Mean": 4.260967254638672, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3075, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 7.515966892242432, | |
| "learning_rate": 3.6315789473684217e-06, | |
| "loss": 0.4666, | |
| "step": 124 | |
| }, | |
| { | |
| "Batch Mean": 4.493681907653809, | |
| "accuracy": 0.71875, | |
| "epoch": 0.31, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 7.867684364318848, | |
| "learning_rate": 3.618421052631579e-06, | |
| "loss": 0.5071, | |
| "step": 125 | |
| }, | |
| { | |
| "Batch Mean": 4.890687942504883, | |
| "accuracy": 0.8125, | |
| "epoch": 0.3125, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.315, | |
| "grad_norm": 7.532710552215576, | |
| "learning_rate": 3.605263157894737e-06, | |
| "loss": 0.4652, | |
| "step": 126 | |
| }, | |
| { | |
| "Batch Mean": 4.562954902648926, | |
| "accuracy": 0.765625, | |
| "epoch": 0.315, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3175, | |
| "grad_norm": 8.537458419799805, | |
| "learning_rate": 3.592105263157895e-06, | |
| "loss": 0.4776, | |
| "step": 127 | |
| }, | |
| { | |
| "Batch Mean": 4.587188720703125, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3175, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 6.799316883087158, | |
| "learning_rate": 3.578947368421053e-06, | |
| "loss": 0.4191, | |
| "step": 128 | |
| }, | |
| { | |
| "Batch Mean": 3.9915571212768555, | |
| "accuracy": 0.75, | |
| "epoch": 0.32, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3225, | |
| "grad_norm": 8.045788764953613, | |
| "learning_rate": 3.565789473684211e-06, | |
| "loss": 0.506, | |
| "step": 129 | |
| }, | |
| { | |
| "Batch Mean": 4.073477745056152, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.3225, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 8.907149314880371, | |
| "learning_rate": 3.5526315789473687e-06, | |
| "loss": 0.4877, | |
| "step": 130 | |
| }, | |
| { | |
| "Batch Mean": 4.1734771728515625, | |
| "accuracy": 0.75, | |
| "epoch": 0.325, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3275, | |
| "grad_norm": 9.162409782409668, | |
| "learning_rate": 3.5394736842105266e-06, | |
| "loss": 0.5122, | |
| "step": 131 | |
| }, | |
| { | |
| "Batch Mean": 3.731600761413574, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.3275, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 6.665674209594727, | |
| "learning_rate": 3.5263157894736846e-06, | |
| "loss": 0.4075, | |
| "step": 132 | |
| }, | |
| { | |
| "Batch Mean": 3.5332088470458984, | |
| "accuracy": 0.765625, | |
| "epoch": 0.33, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3325, | |
| "grad_norm": 7.407108783721924, | |
| "learning_rate": 3.513157894736842e-06, | |
| "loss": 0.4435, | |
| "step": 133 | |
| }, | |
| { | |
| "Batch Mean": 3.2184605598449707, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3325, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.335, | |
| "grad_norm": 8.552702903747559, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.4817, | |
| "step": 134 | |
| }, | |
| { | |
| "Batch Mean": 3.3773207664489746, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.335, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3375, | |
| "grad_norm": 8.001891136169434, | |
| "learning_rate": 3.486842105263158e-06, | |
| "loss": 0.4724, | |
| "step": 135 | |
| }, | |
| { | |
| "Batch Mean": 2.997677803039551, | |
| "accuracy": 0.75, | |
| "epoch": 0.3375, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 9.054019927978516, | |
| "learning_rate": 3.473684210526316e-06, | |
| "loss": 0.4988, | |
| "step": 136 | |
| }, | |
| { | |
| "Batch Mean": 2.929046154022217, | |
| "accuracy": 0.8125, | |
| "epoch": 0.34, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3425, | |
| "grad_norm": 8.104907989501953, | |
| "learning_rate": 3.460526315789474e-06, | |
| "loss": 0.4243, | |
| "step": 137 | |
| }, | |
| { | |
| "Batch Mean": 2.75551176071167, | |
| "accuracy": 0.8125, | |
| "epoch": 0.3425, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.345, | |
| "grad_norm": 8.473715782165527, | |
| "learning_rate": 3.447368421052632e-06, | |
| "loss": 0.4427, | |
| "step": 138 | |
| }, | |
| { | |
| "Batch Mean": 2.5024139881134033, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.345, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3475, | |
| "grad_norm": 9.045927047729492, | |
| "learning_rate": 3.43421052631579e-06, | |
| "loss": 0.4255, | |
| "step": 139 | |
| }, | |
| { | |
| "Batch Mean": 2.417640209197998, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3475, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 7.710657119750977, | |
| "learning_rate": 3.421052631578948e-06, | |
| "loss": 0.443, | |
| "step": 140 | |
| }, | |
| { | |
| "Batch Mean": 2.505678653717041, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.35, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3525, | |
| "grad_norm": 7.663838863372803, | |
| "learning_rate": 3.4078947368421057e-06, | |
| "loss": 0.4049, | |
| "step": 141 | |
| }, | |
| { | |
| "Batch Mean": 3.0147056579589844, | |
| "accuracy": 0.75, | |
| "epoch": 0.3525, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.355, | |
| "grad_norm": 8.560474395751953, | |
| "learning_rate": 3.3947368421052636e-06, | |
| "loss": 0.5149, | |
| "step": 142 | |
| }, | |
| { | |
| "Batch Mean": 2.588562488555908, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.355, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.3575, | |
| "grad_norm": 8.25622272491455, | |
| "learning_rate": 3.381578947368421e-06, | |
| "loss": 0.4934, | |
| "step": 143 | |
| }, | |
| { | |
| "Batch Mean": 2.6298677921295166, | |
| "accuracy": 0.828125, | |
| "epoch": 0.3575, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 7.083525657653809, | |
| "learning_rate": 3.368421052631579e-06, | |
| "loss": 0.4115, | |
| "step": 144 | |
| }, | |
| { | |
| "Batch Mean": 2.7647485733032227, | |
| "accuracy": 0.796875, | |
| "epoch": 0.36, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3625, | |
| "grad_norm": 6.853006362915039, | |
| "learning_rate": 3.355263157894737e-06, | |
| "loss": 0.4469, | |
| "step": 145 | |
| }, | |
| { | |
| "Batch Mean": 2.769733190536499, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3625, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.365, | |
| "grad_norm": 7.704352855682373, | |
| "learning_rate": 3.342105263157895e-06, | |
| "loss": 0.4753, | |
| "step": 146 | |
| }, | |
| { | |
| "Batch Mean": 3.3755264282226562, | |
| "accuracy": 0.765625, | |
| "epoch": 0.365, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.3675, | |
| "grad_norm": 7.600855350494385, | |
| "learning_rate": 3.3289473684210528e-06, | |
| "loss": 0.46, | |
| "step": 147 | |
| }, | |
| { | |
| "Batch Mean": 2.6412248611450195, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.3675, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 8.489302635192871, | |
| "learning_rate": 3.3157894736842107e-06, | |
| "loss": 0.5111, | |
| "step": 148 | |
| }, | |
| { | |
| "Batch Mean": 2.835446357727051, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.37, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3725, | |
| "grad_norm": 7.343207359313965, | |
| "learning_rate": 3.302631578947369e-06, | |
| "loss": 0.5032, | |
| "step": 149 | |
| }, | |
| { | |
| "Batch Mean": 2.8000075817108154, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.3725, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 7.448639869689941, | |
| "learning_rate": 3.289473684210527e-06, | |
| "loss": 0.4456, | |
| "step": 150 | |
| }, | |
| { | |
| "Batch Mean": 2.8405256271362305, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.375, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3775, | |
| "grad_norm": 6.841508865356445, | |
| "learning_rate": 3.276315789473685e-06, | |
| "loss": 0.4306, | |
| "step": 151 | |
| }, | |
| { | |
| "Batch Mean": 2.7483787536621094, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3775, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 7.562384128570557, | |
| "learning_rate": 3.2631578947368423e-06, | |
| "loss": 0.5062, | |
| "step": 152 | |
| }, | |
| { | |
| "Batch Mean": 2.8838186264038086, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.38, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3825, | |
| "grad_norm": 6.867684841156006, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 0.447, | |
| "step": 153 | |
| }, | |
| { | |
| "Batch Mean": 2.926253318786621, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.3825, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.385, | |
| "grad_norm": 8.004990577697754, | |
| "learning_rate": 3.236842105263158e-06, | |
| "loss": 0.464, | |
| "step": 154 | |
| }, | |
| { | |
| "Batch Mean": 3.1090264320373535, | |
| "accuracy": 0.8125, | |
| "epoch": 0.385, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3875, | |
| "grad_norm": 6.201688766479492, | |
| "learning_rate": 3.223684210526316e-06, | |
| "loss": 0.365, | |
| "step": 155 | |
| }, | |
| { | |
| "Batch Mean": 3.2874813079833984, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.3875, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 6.851440906524658, | |
| "learning_rate": 3.210526315789474e-06, | |
| "loss": 0.3668, | |
| "step": 156 | |
| }, | |
| { | |
| "Batch Mean": 3.5518083572387695, | |
| "accuracy": 0.8125, | |
| "epoch": 0.39, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3925, | |
| "grad_norm": 7.0716023445129395, | |
| "learning_rate": 3.197368421052632e-06, | |
| "loss": 0.3978, | |
| "step": 157 | |
| }, | |
| { | |
| "Batch Mean": 3.0985703468322754, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.3925, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.395, | |
| "grad_norm": 8.339123725891113, | |
| "learning_rate": 3.1842105263157898e-06, | |
| "loss": 0.3998, | |
| "step": 158 | |
| }, | |
| { | |
| "Batch Mean": 3.281148910522461, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.395, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3975, | |
| "grad_norm": 8.356124877929688, | |
| "learning_rate": 3.1710526315789477e-06, | |
| "loss": 0.4491, | |
| "step": 159 | |
| }, | |
| { | |
| "Batch Mean": 3.783808708190918, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3975, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 9.633821487426758, | |
| "learning_rate": 3.157894736842105e-06, | |
| "loss": 0.432, | |
| "step": 160 | |
| }, | |
| { | |
| "Batch Mean": 3.9359283447265625, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4025, | |
| "grad_norm": 8.254521369934082, | |
| "learning_rate": 3.144736842105263e-06, | |
| "loss": 0.3891, | |
| "step": 161 | |
| }, | |
| { | |
| "Batch Mean": 4.607031345367432, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.4025, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.405, | |
| "grad_norm": 9.970298767089844, | |
| "learning_rate": 3.131578947368421e-06, | |
| "loss": 0.4982, | |
| "step": 162 | |
| }, | |
| { | |
| "Batch Mean": 4.176942825317383, | |
| "accuracy": 0.8125, | |
| "epoch": 0.405, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4075, | |
| "grad_norm": 12.374481201171875, | |
| "learning_rate": 3.1184210526315793e-06, | |
| "loss": 0.4349, | |
| "step": 163 | |
| }, | |
| { | |
| "Batch Mean": 4.015748977661133, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.4075, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 11.244656562805176, | |
| "learning_rate": 3.1052631578947372e-06, | |
| "loss": 0.421, | |
| "step": 164 | |
| }, | |
| { | |
| "Batch Mean": 4.22213888168335, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.41, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4125, | |
| "grad_norm": 11.150482177734375, | |
| "learning_rate": 3.092105263157895e-06, | |
| "loss": 0.4978, | |
| "step": 165 | |
| }, | |
| { | |
| "Batch Mean": 3.7064056396484375, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4125, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.415, | |
| "grad_norm": 9.92993450164795, | |
| "learning_rate": 3.078947368421053e-06, | |
| "loss": 0.3748, | |
| "step": 166 | |
| }, | |
| { | |
| "Batch Mean": 4.073935508728027, | |
| "accuracy": 0.765625, | |
| "epoch": 0.415, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.4175, | |
| "grad_norm": 9.726029396057129, | |
| "learning_rate": 3.065789473684211e-06, | |
| "loss": 0.3952, | |
| "step": 167 | |
| }, | |
| { | |
| "Batch Mean": 3.741079807281494, | |
| "accuracy": 0.796875, | |
| "epoch": 0.4175, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 10.072457313537598, | |
| "learning_rate": 3.052631578947369e-06, | |
| "loss": 0.4475, | |
| "step": 168 | |
| }, | |
| { | |
| "Batch Mean": 3.423218011856079, | |
| "accuracy": 0.734375, | |
| "epoch": 0.42, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4225, | |
| "grad_norm": 9.74998950958252, | |
| "learning_rate": 3.0394736842105268e-06, | |
| "loss": 0.4507, | |
| "step": 169 | |
| }, | |
| { | |
| "Batch Mean": 3.3439035415649414, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4225, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.425, | |
| "grad_norm": 9.590579986572266, | |
| "learning_rate": 3.0263157894736843e-06, | |
| "loss": 0.4641, | |
| "step": 170 | |
| }, | |
| { | |
| "Batch Mean": 3.2388744354248047, | |
| "accuracy": 0.8828125, | |
| "epoch": 0.425, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4275, | |
| "grad_norm": 7.974471569061279, | |
| "learning_rate": 3.013157894736842e-06, | |
| "loss": 0.2888, | |
| "step": 171 | |
| }, | |
| { | |
| "Batch Mean": 2.912121295928955, | |
| "accuracy": 0.828125, | |
| "epoch": 0.4275, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 8.418153762817383, | |
| "learning_rate": 3e-06, | |
| "loss": 0.4083, | |
| "step": 172 | |
| }, | |
| { | |
| "Batch Mean": 2.921308994293213, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.43, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4325, | |
| "grad_norm": 9.274598121643066, | |
| "learning_rate": 2.986842105263158e-06, | |
| "loss": 0.4237, | |
| "step": 173 | |
| }, | |
| { | |
| "Batch Mean": 2.707150459289551, | |
| "accuracy": 0.765625, | |
| "epoch": 0.4325, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.435, | |
| "grad_norm": 10.08448314666748, | |
| "learning_rate": 2.973684210526316e-06, | |
| "loss": 0.4084, | |
| "step": 174 | |
| }, | |
| { | |
| "Batch Mean": 3.289186477661133, | |
| "accuracy": 0.78125, | |
| "epoch": 0.435, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 10.216947555541992, | |
| "learning_rate": 2.960526315789474e-06, | |
| "loss": 0.4265, | |
| "step": 175 | |
| }, | |
| { | |
| "Batch Mean": 3.0034594535827637, | |
| "accuracy": 0.734375, | |
| "epoch": 0.4375, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 9.921527862548828, | |
| "learning_rate": 2.9473684210526317e-06, | |
| "loss": 0.4555, | |
| "step": 176 | |
| }, | |
| { | |
| "Batch Mean": 3.1962521076202393, | |
| "accuracy": 0.796875, | |
| "epoch": 0.44, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.4425, | |
| "grad_norm": 9.140130043029785, | |
| "learning_rate": 2.93421052631579e-06, | |
| "loss": 0.433, | |
| "step": 177 | |
| }, | |
| { | |
| "Batch Mean": 3.105267286300659, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.4425, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.445, | |
| "grad_norm": 8.577014923095703, | |
| "learning_rate": 2.921052631578948e-06, | |
| "loss": 0.3558, | |
| "step": 178 | |
| }, | |
| { | |
| "Batch Mean": 3.05171799659729, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.445, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.4475, | |
| "grad_norm": 9.902350425720215, | |
| "learning_rate": 2.907894736842106e-06, | |
| "loss": 0.3446, | |
| "step": 179 | |
| }, | |
| { | |
| "Batch Mean": 2.8749771118164062, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.4475, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 8.572197914123535, | |
| "learning_rate": 2.8947368421052634e-06, | |
| "loss": 0.4343, | |
| "step": 180 | |
| }, | |
| { | |
| "Batch Mean": 3.5201892852783203, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.45, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4525, | |
| "grad_norm": 9.538017272949219, | |
| "learning_rate": 2.8815789473684213e-06, | |
| "loss": 0.4501, | |
| "step": 181 | |
| }, | |
| { | |
| "Batch Mean": 3.441112518310547, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.4525, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.455, | |
| "grad_norm": 8.626726150512695, | |
| "learning_rate": 2.868421052631579e-06, | |
| "loss": 0.4032, | |
| "step": 182 | |
| }, | |
| { | |
| "Batch Mean": 3.4753060340881348, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.455, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.4575, | |
| "grad_norm": 11.793852806091309, | |
| "learning_rate": 2.855263157894737e-06, | |
| "loss": 0.5783, | |
| "step": 183 | |
| }, | |
| { | |
| "Batch Mean": 3.088036060333252, | |
| "accuracy": 0.765625, | |
| "epoch": 0.4575, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 9.752645492553711, | |
| "learning_rate": 2.842105263157895e-06, | |
| "loss": 0.4706, | |
| "step": 184 | |
| }, | |
| { | |
| "Batch Mean": 2.640962600708008, | |
| "accuracy": 0.71875, | |
| "epoch": 0.46, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4625, | |
| "grad_norm": 9.9888277053833, | |
| "learning_rate": 2.828947368421053e-06, | |
| "loss": 0.5268, | |
| "step": 185 | |
| }, | |
| { | |
| "Batch Mean": 2.834287405014038, | |
| "accuracy": 0.765625, | |
| "epoch": 0.4625, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.465, | |
| "grad_norm": 8.2410306930542, | |
| "learning_rate": 2.815789473684211e-06, | |
| "loss": 0.4375, | |
| "step": 186 | |
| }, | |
| { | |
| "Batch Mean": 2.8364157676696777, | |
| "accuracy": 0.765625, | |
| "epoch": 0.465, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.4675, | |
| "grad_norm": 7.653415679931641, | |
| "learning_rate": 2.8026315789473683e-06, | |
| "loss": 0.3908, | |
| "step": 187 | |
| }, | |
| { | |
| "Batch Mean": 2.0791072845458984, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4675, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 6.701351165771484, | |
| "learning_rate": 2.789473684210526e-06, | |
| "loss": 0.3761, | |
| "step": 188 | |
| }, | |
| { | |
| "Batch Mean": 2.188058853149414, | |
| "accuracy": 0.8125, | |
| "epoch": 0.47, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.4725, | |
| "grad_norm": 7.052455425262451, | |
| "learning_rate": 2.776315789473684e-06, | |
| "loss": 0.4348, | |
| "step": 189 | |
| }, | |
| { | |
| "Batch Mean": 2.0506675243377686, | |
| "accuracy": 0.828125, | |
| "epoch": 0.4725, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.475, | |
| "grad_norm": 7.033082962036133, | |
| "learning_rate": 2.7631578947368424e-06, | |
| "loss": 0.3651, | |
| "step": 190 | |
| }, | |
| { | |
| "Batch Mean": 2.3128931522369385, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.475, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4775, | |
| "grad_norm": 7.838496685028076, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 0.3981, | |
| "step": 191 | |
| }, | |
| { | |
| "Batch Mean": 2.032851219177246, | |
| "accuracy": 0.875, | |
| "epoch": 0.4775, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 6.573253631591797, | |
| "learning_rate": 2.7368421052631583e-06, | |
| "loss": 0.3628, | |
| "step": 192 | |
| }, | |
| { | |
| "Batch Mean": 2.3109028339385986, | |
| "accuracy": 0.796875, | |
| "epoch": 0.48, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.4825, | |
| "grad_norm": 8.022283554077148, | |
| "learning_rate": 2.723684210526316e-06, | |
| "loss": 0.4369, | |
| "step": 193 | |
| }, | |
| { | |
| "Batch Mean": 2.6557040214538574, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.4825, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.485, | |
| "grad_norm": 8.877519607543945, | |
| "learning_rate": 2.710526315789474e-06, | |
| "loss": 0.4504, | |
| "step": 194 | |
| }, | |
| { | |
| "Batch Mean": 2.9424595832824707, | |
| "accuracy": 0.75, | |
| "epoch": 0.485, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.4875, | |
| "grad_norm": 7.829299449920654, | |
| "learning_rate": 2.697368421052632e-06, | |
| "loss": 0.4254, | |
| "step": 195 | |
| }, | |
| { | |
| "Batch Mean": 2.644308090209961, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.4875, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 9.070138931274414, | |
| "learning_rate": 2.68421052631579e-06, | |
| "loss": 0.4922, | |
| "step": 196 | |
| }, | |
| { | |
| "Batch Mean": 2.4906630516052246, | |
| "accuracy": 0.765625, | |
| "epoch": 0.49, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4925, | |
| "grad_norm": 9.63489818572998, | |
| "learning_rate": 2.6710526315789474e-06, | |
| "loss": 0.4602, | |
| "step": 197 | |
| }, | |
| { | |
| "Batch Mean": 2.2591946125030518, | |
| "accuracy": 0.796875, | |
| "epoch": 0.4925, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.495, | |
| "grad_norm": 8.234044075012207, | |
| "learning_rate": 2.6578947368421053e-06, | |
| "loss": 0.398, | |
| "step": 198 | |
| }, | |
| { | |
| "Batch Mean": 2.6223649978637695, | |
| "accuracy": 0.8125, | |
| "epoch": 0.495, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.4975, | |
| "grad_norm": 7.958437442779541, | |
| "learning_rate": 2.644736842105263e-06, | |
| "loss": 0.3909, | |
| "step": 199 | |
| }, | |
| { | |
| "Batch Mean": 2.5589590072631836, | |
| "accuracy": 0.875, | |
| "epoch": 0.4975, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 7.556171417236328, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.3513, | |
| "step": 200 | |
| }, | |
| { | |
| "Batch Mean": 2.3716750144958496, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.5, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5025, | |
| "grad_norm": 9.392867088317871, | |
| "learning_rate": 2.618421052631579e-06, | |
| "loss": 0.4831, | |
| "step": 201 | |
| }, | |
| { | |
| "Batch Mean": 2.27783203125, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.5025, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.505, | |
| "grad_norm": 8.140517234802246, | |
| "learning_rate": 2.605263157894737e-06, | |
| "loss": 0.3929, | |
| "step": 202 | |
| }, | |
| { | |
| "Batch Mean": 2.535848617553711, | |
| "accuracy": 0.84375, | |
| "epoch": 0.505, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.5075, | |
| "grad_norm": 6.947089195251465, | |
| "learning_rate": 2.592105263157895e-06, | |
| "loss": 0.3478, | |
| "step": 203 | |
| }, | |
| { | |
| "Batch Mean": 2.651693344116211, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.5075, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 8.759857177734375, | |
| "learning_rate": 2.578947368421053e-06, | |
| "loss": 0.4076, | |
| "step": 204 | |
| }, | |
| { | |
| "Batch Mean": 2.571043014526367, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.51, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5125, | |
| "grad_norm": 9.00507926940918, | |
| "learning_rate": 2.565789473684211e-06, | |
| "loss": 0.3996, | |
| "step": 205 | |
| }, | |
| { | |
| "Batch Mean": 2.7687175273895264, | |
| "accuracy": 0.75, | |
| "epoch": 0.5125, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.515, | |
| "grad_norm": 10.412758827209473, | |
| "learning_rate": 2.552631578947369e-06, | |
| "loss": 0.5306, | |
| "step": 206 | |
| }, | |
| { | |
| "Batch Mean": 2.5285263061523438, | |
| "accuracy": 0.84375, | |
| "epoch": 0.515, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.5175, | |
| "grad_norm": 7.771270751953125, | |
| "learning_rate": 2.5394736842105265e-06, | |
| "loss": 0.3507, | |
| "step": 207 | |
| }, | |
| { | |
| "Batch Mean": 2.688607692718506, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.5175, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 8.726874351501465, | |
| "learning_rate": 2.5263157894736844e-06, | |
| "loss": 0.4068, | |
| "step": 208 | |
| }, | |
| { | |
| "Batch Mean": 2.94492244720459, | |
| "accuracy": 0.8125, | |
| "epoch": 0.52, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.5225, | |
| "grad_norm": 8.50943660736084, | |
| "learning_rate": 2.5131578947368423e-06, | |
| "loss": 0.3774, | |
| "step": 209 | |
| }, | |
| { | |
| "Batch Mean": 2.7862486839294434, | |
| "accuracy": 0.796875, | |
| "epoch": 0.5225, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.525, | |
| "grad_norm": 8.98309326171875, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.4266, | |
| "step": 210 | |
| }, | |
| { | |
| "Batch Mean": 2.61392879486084, | |
| "accuracy": 0.765625, | |
| "epoch": 0.525, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5275, | |
| "grad_norm": 10.080408096313477, | |
| "learning_rate": 2.486842105263158e-06, | |
| "loss": 0.4663, | |
| "step": 211 | |
| }, | |
| { | |
| "Batch Mean": 2.9034132957458496, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.5275, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 8.575652122497559, | |
| "learning_rate": 2.473684210526316e-06, | |
| "loss": 0.3926, | |
| "step": 212 | |
| }, | |
| { | |
| "Batch Mean": 2.8661410808563232, | |
| "accuracy": 0.75, | |
| "epoch": 0.53, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5325, | |
| "grad_norm": 10.517654418945312, | |
| "learning_rate": 2.460526315789474e-06, | |
| "loss": 0.5594, | |
| "step": 213 | |
| }, | |
| { | |
| "Batch Mean": 3.062936782836914, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.5325, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.535, | |
| "grad_norm": 9.07347583770752, | |
| "learning_rate": 2.447368421052632e-06, | |
| "loss": 0.433, | |
| "step": 214 | |
| }, | |
| { | |
| "Batch Mean": 2.8995747566223145, | |
| "accuracy": 0.8125, | |
| "epoch": 0.535, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.5375, | |
| "grad_norm": 9.181224822998047, | |
| "learning_rate": 2.4342105263157898e-06, | |
| "loss": 0.4336, | |
| "step": 215 | |
| }, | |
| { | |
| "Batch Mean": 2.7490530014038086, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.5375, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 9.431602478027344, | |
| "learning_rate": 2.4210526315789477e-06, | |
| "loss": 0.4583, | |
| "step": 216 | |
| }, | |
| { | |
| "Batch Mean": 2.801156520843506, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.54, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5425, | |
| "grad_norm": 8.67341423034668, | |
| "learning_rate": 2.4078947368421056e-06, | |
| "loss": 0.4219, | |
| "step": 217 | |
| }, | |
| { | |
| "Batch Mean": 2.785233497619629, | |
| "accuracy": 0.8125, | |
| "epoch": 0.5425, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.545, | |
| "grad_norm": 8.614130973815918, | |
| "learning_rate": 2.3947368421052635e-06, | |
| "loss": 0.4214, | |
| "step": 218 | |
| }, | |
| { | |
| "Batch Mean": 2.322535514831543, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.545, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.5475, | |
| "grad_norm": 8.403548240661621, | |
| "learning_rate": 2.381578947368421e-06, | |
| "loss": 0.425, | |
| "step": 219 | |
| }, | |
| { | |
| "Batch Mean": 2.722550392150879, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.5475, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 8.205376625061035, | |
| "learning_rate": 2.368421052631579e-06, | |
| "loss": 0.3821, | |
| "step": 220 | |
| }, | |
| { | |
| "Batch Mean": 2.360077142715454, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.55, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5525, | |
| "grad_norm": 9.49571418762207, | |
| "learning_rate": 2.355263157894737e-06, | |
| "loss": 0.4661, | |
| "step": 221 | |
| }, | |
| { | |
| "Batch Mean": 3.0066745281219482, | |
| "accuracy": 0.7265625, | |
| "epoch": 0.5525, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.555, | |
| "grad_norm": 9.534995079040527, | |
| "learning_rate": 2.342105263157895e-06, | |
| "loss": 0.5174, | |
| "step": 222 | |
| }, | |
| { | |
| "Batch Mean": 2.9200942516326904, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.555, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.5575, | |
| "grad_norm": 7.970925331115723, | |
| "learning_rate": 2.328947368421053e-06, | |
| "loss": 0.4063, | |
| "step": 223 | |
| }, | |
| { | |
| "Batch Mean": 3.1014528274536133, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.5575, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 7.537857532501221, | |
| "learning_rate": 2.3157894736842105e-06, | |
| "loss": 0.3926, | |
| "step": 224 | |
| }, | |
| { | |
| "Batch Mean": 2.5743775367736816, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.56, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 8.670877456665039, | |
| "learning_rate": 2.3026315789473684e-06, | |
| "loss": 0.4287, | |
| "step": 225 | |
| }, | |
| { | |
| "Batch Mean": 3.103597640991211, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.5625, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.565, | |
| "grad_norm": 7.964511871337891, | |
| "learning_rate": 2.2894736842105263e-06, | |
| "loss": 0.3888, | |
| "step": 226 | |
| }, | |
| { | |
| "Batch Mean": 3.0492055416107178, | |
| "accuracy": 0.859375, | |
| "epoch": 0.565, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.5675, | |
| "grad_norm": 7.54857873916626, | |
| "learning_rate": 2.2763157894736847e-06, | |
| "loss": 0.3208, | |
| "step": 227 | |
| }, | |
| { | |
| "Batch Mean": 3.119175434112549, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.5675, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 7.656146049499512, | |
| "learning_rate": 2.2631578947368426e-06, | |
| "loss": 0.4383, | |
| "step": 228 | |
| }, | |
| { | |
| "Batch Mean": 2.846890449523926, | |
| "accuracy": 0.75, | |
| "epoch": 0.57, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5725, | |
| "grad_norm": 9.830333709716797, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.5166, | |
| "step": 229 | |
| }, | |
| { | |
| "Batch Mean": 2.3330116271972656, | |
| "accuracy": 0.84375, | |
| "epoch": 0.5725, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.575, | |
| "grad_norm": 9.917115211486816, | |
| "learning_rate": 2.236842105263158e-06, | |
| "loss": 0.4154, | |
| "step": 230 | |
| }, | |
| { | |
| "Batch Mean": 3.0601701736450195, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.575, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5775, | |
| "grad_norm": 8.37639331817627, | |
| "learning_rate": 2.223684210526316e-06, | |
| "loss": 0.4456, | |
| "step": 231 | |
| }, | |
| { | |
| "Batch Mean": 2.553410530090332, | |
| "accuracy": 0.78125, | |
| "epoch": 0.5775, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 8.588013648986816, | |
| "learning_rate": 2.2105263157894738e-06, | |
| "loss": 0.4204, | |
| "step": 232 | |
| }, | |
| { | |
| "Batch Mean": 2.790724754333496, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.58, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.5825, | |
| "grad_norm": 8.133465766906738, | |
| "learning_rate": 2.1973684210526317e-06, | |
| "loss": 0.3772, | |
| "step": 233 | |
| }, | |
| { | |
| "Batch Mean": 2.7968082427978516, | |
| "accuracy": 0.84375, | |
| "epoch": 0.5825, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.585, | |
| "grad_norm": 8.12721061706543, | |
| "learning_rate": 2.1842105263157896e-06, | |
| "loss": 0.3624, | |
| "step": 234 | |
| }, | |
| { | |
| "Batch Mean": 3.189887523651123, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.585, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.5875, | |
| "grad_norm": 8.726601600646973, | |
| "learning_rate": 2.1710526315789475e-06, | |
| "loss": 0.4139, | |
| "step": 235 | |
| }, | |
| { | |
| "Batch Mean": 3.4596574306488037, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.5875, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 8.571916580200195, | |
| "learning_rate": 2.1578947368421054e-06, | |
| "loss": 0.4047, | |
| "step": 236 | |
| }, | |
| { | |
| "Batch Mean": 3.403088092803955, | |
| "accuracy": 0.8671875, | |
| "epoch": 0.59, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.5925, | |
| "grad_norm": 8.29578971862793, | |
| "learning_rate": 2.1447368421052633e-06, | |
| "loss": 0.3556, | |
| "step": 237 | |
| }, | |
| { | |
| "Batch Mean": 2.97831654548645, | |
| "accuracy": 0.796875, | |
| "epoch": 0.5925, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.595, | |
| "grad_norm": 9.06924819946289, | |
| "learning_rate": 2.1315789473684212e-06, | |
| "loss": 0.394, | |
| "step": 238 | |
| }, | |
| { | |
| "Batch Mean": 3.729241371154785, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.595, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.5975, | |
| "grad_norm": 9.479219436645508, | |
| "learning_rate": 2.118421052631579e-06, | |
| "loss": 0.3934, | |
| "step": 239 | |
| }, | |
| { | |
| "Batch Mean": 3.851926803588867, | |
| "accuracy": 0.78125, | |
| "epoch": 0.5975, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 11.203536033630371, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 0.4106, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 80, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |