| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018308631211857017, | |
| "eval_steps": 1, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.448997384481256e-05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.448997384481256e-05, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 283.3287, | |
| "eval_samples_per_second": 119.18, | |
| "eval_steps_per_second": 3.311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010897994768962511, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010897994768962511, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 283.1668, | |
| "eval_samples_per_second": 119.248, | |
| "eval_steps_per_second": 3.313, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016346992153443767, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016346992153443767, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 282.1254, | |
| "eval_samples_per_second": 119.688, | |
| "eval_steps_per_second": 3.325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021795989537925023, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021795989537925023, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.3948, | |
| "eval_samples_per_second": 119.999, | |
| "eval_steps_per_second": 3.333, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00027244986922406276, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8594, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00027244986922406276, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.7028, | |
| "eval_samples_per_second": 119.867, | |
| "eval_steps_per_second": 3.33, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00032693984306887534, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00032693984306887534, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 282.539, | |
| "eval_samples_per_second": 119.513, | |
| "eval_steps_per_second": 3.32, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00038142981691368787, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00038142981691368787, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 282.3676, | |
| "eval_samples_per_second": 119.585, | |
| "eval_steps_per_second": 3.322, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00043591979075850045, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00043591979075850045, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.6041, | |
| "eval_samples_per_second": 119.909, | |
| "eval_steps_per_second": 3.331, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000490409764603313, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000490409764603313, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.1865, | |
| "eval_samples_per_second": 120.088, | |
| "eval_steps_per_second": 3.336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005448997384481255, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005448997384481255, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 282.104, | |
| "eval_samples_per_second": 119.697, | |
| "eval_steps_per_second": 3.325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005993897122929382, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005993897122929382, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 280.8618, | |
| "eval_samples_per_second": 120.226, | |
| "eval_steps_per_second": 3.34, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006538796861377507, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006538796861377507, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 280.475, | |
| "eval_samples_per_second": 120.392, | |
| "eval_steps_per_second": 3.344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007083696599825632, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8594, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007083696599825632, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 279.8203, | |
| "eval_samples_per_second": 120.674, | |
| "eval_steps_per_second": 3.352, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007628596338273757, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007628596338273757, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 279.8528, | |
| "eval_samples_per_second": 120.66, | |
| "eval_steps_per_second": 3.352, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008173496076721883, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8594, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008173496076721883, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.1019, | |
| "eval_samples_per_second": 120.124, | |
| "eval_steps_per_second": 3.337, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008718395815170009, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8594, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008718395815170009, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 280.3712, | |
| "eval_samples_per_second": 120.437, | |
| "eval_steps_per_second": 3.346, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009263295553618134, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 10.8672, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0009263295553618134, | |
| "eval_accuracy": 0.004507457682298169, | |
| "eval_loss": 10.8671875, | |
| "eval_runtime": 281.4302, | |
| "eval_samples_per_second": 119.984, | |
| "eval_steps_per_second": 3.333, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.000980819529206626, | |
| "grad_norm": 3.3501086235046387, | |
| "learning_rate": 9.999994551002616e-06, | |
| "loss": 10.8672, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000980819529206626, | |
| "eval_accuracy": 0.008603349021604294, | |
| "eval_loss": 10.8359375, | |
| "eval_runtime": 281.0275, | |
| "eval_samples_per_second": 120.155, | |
| "eval_steps_per_second": 3.338, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010353095030514385, | |
| "grad_norm": 3.1848981380462646, | |
| "learning_rate": 9.999989102005233e-06, | |
| "loss": 10.8359, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0010353095030514385, | |
| "eval_accuracy": 0.010782302884632226, | |
| "eval_loss": 10.8046875, | |
| "eval_runtime": 280.8218, | |
| "eval_samples_per_second": 120.244, | |
| "eval_steps_per_second": 3.34, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001089799476896251, | |
| "grad_norm": 3.103949546813965, | |
| "learning_rate": 9.999983653007848e-06, | |
| "loss": 10.8047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001089799476896251, | |
| "eval_accuracy": 0.011296145649498848, | |
| "eval_loss": 10.7734375, | |
| "eval_runtime": 280.7519, | |
| "eval_samples_per_second": 120.273, | |
| "eval_steps_per_second": 3.341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011442894507410636, | |
| "grad_norm": 3.007913827896118, | |
| "learning_rate": 9.999978204010463e-06, | |
| "loss": 10.7891, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011442894507410636, | |
| "eval_accuracy": 0.011502753864307472, | |
| "eval_loss": 10.75, | |
| "eval_runtime": 282.1403, | |
| "eval_samples_per_second": 119.682, | |
| "eval_steps_per_second": 3.325, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011987794245858763, | |
| "grad_norm": 3.0112082958221436, | |
| "learning_rate": 9.99997275501308e-06, | |
| "loss": 10.7578, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0011987794245858763, | |
| "eval_accuracy": 0.011935742384539025, | |
| "eval_loss": 10.7265625, | |
| "eval_runtime": 280.7974, | |
| "eval_samples_per_second": 120.254, | |
| "eval_steps_per_second": 3.34, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0012532693984306888, | |
| "grad_norm": 3.0085818767547607, | |
| "learning_rate": 9.999967306015694e-06, | |
| "loss": 10.7188, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0012532693984306888, | |
| "eval_accuracy": 0.012902490504692311, | |
| "eval_loss": 10.703125, | |
| "eval_runtime": 279.9507, | |
| "eval_samples_per_second": 120.618, | |
| "eval_steps_per_second": 3.351, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0013077593722755014, | |
| "grad_norm": 2.6498820781707764, | |
| "learning_rate": 9.99996185701831e-06, | |
| "loss": 10.7188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013077593722755014, | |
| "eval_accuracy": 0.014669617484734745, | |
| "eval_loss": 10.6796875, | |
| "eval_runtime": 284.0388, | |
| "eval_samples_per_second": 118.882, | |
| "eval_steps_per_second": 3.302, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013622493461203139, | |
| "grad_norm": 2.525411367416382, | |
| "learning_rate": 9.999956408020926e-06, | |
| "loss": 10.6953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013622493461203139, | |
| "eval_accuracy": 0.017945705260195358, | |
| "eval_loss": 10.6640625, | |
| "eval_runtime": 279.0802, | |
| "eval_samples_per_second": 120.994, | |
| "eval_steps_per_second": 3.361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014167393199651264, | |
| "grad_norm": 2.438088893890381, | |
| "learning_rate": 9.99995095902354e-06, | |
| "loss": 10.6719, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0014167393199651264, | |
| "eval_accuracy": 0.023050523249706075, | |
| "eval_loss": 10.640625, | |
| "eval_runtime": 280.2346, | |
| "eval_samples_per_second": 120.495, | |
| "eval_steps_per_second": 3.347, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001471229293809939, | |
| "grad_norm": 2.2894654273986816, | |
| "learning_rate": 9.999945510026156e-06, | |
| "loss": 10.6562, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001471229293809939, | |
| "eval_accuracy": 0.02863128990948001, | |
| "eval_loss": 10.625, | |
| "eval_runtime": 280.5686, | |
| "eval_samples_per_second": 120.352, | |
| "eval_steps_per_second": 3.343, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0015257192676547515, | |
| "grad_norm": 2.0723860263824463, | |
| "learning_rate": 9.999940061028771e-06, | |
| "loss": 10.6641, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0015257192676547515, | |
| "eval_accuracy": 0.03466305129792195, | |
| "eval_loss": 10.609375, | |
| "eval_runtime": 278.9184, | |
| "eval_samples_per_second": 121.064, | |
| "eval_steps_per_second": 3.363, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001580209241499564, | |
| "grad_norm": 2.0480406284332275, | |
| "learning_rate": 9.999934612031386e-06, | |
| "loss": 10.6328, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001580209241499564, | |
| "eval_accuracy": 0.039908271395015946, | |
| "eval_loss": 10.59375, | |
| "eval_runtime": 278.4399, | |
| "eval_samples_per_second": 121.272, | |
| "eval_steps_per_second": 3.369, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0016346992153443765, | |
| "grad_norm": 2.0142972469329834, | |
| "learning_rate": 9.999929163034003e-06, | |
| "loss": 10.6016, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016346992153443765, | |
| "eval_accuracy": 0.043642156887862514, | |
| "eval_loss": 10.578125, | |
| "eval_runtime": 277.7144, | |
| "eval_samples_per_second": 121.589, | |
| "eval_steps_per_second": 3.378, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016891891891891893, | |
| "grad_norm": 1.8250195980072021, | |
| "learning_rate": 9.999923714036618e-06, | |
| "loss": 10.6016, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0016891891891891893, | |
| "eval_accuracy": 0.046290082739106744, | |
| "eval_loss": 10.5703125, | |
| "eval_runtime": 277.9514, | |
| "eval_samples_per_second": 121.485, | |
| "eval_steps_per_second": 3.375, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0017436791630340018, | |
| "grad_norm": 1.7317852973937988, | |
| "learning_rate": 9.999918265039233e-06, | |
| "loss": 10.5938, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0017436791630340018, | |
| "eval_accuracy": 0.04786212316182883, | |
| "eval_loss": 10.5546875, | |
| "eval_runtime": 278.188, | |
| "eval_samples_per_second": 121.382, | |
| "eval_steps_per_second": 3.372, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0017981691368788143, | |
| "grad_norm": 1.6736972332000732, | |
| "learning_rate": 9.99991281604185e-06, | |
| "loss": 10.5781, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0017981691368788143, | |
| "eval_accuracy": 0.048402714699356676, | |
| "eval_loss": 10.546875, | |
| "eval_runtime": 276.9089, | |
| "eval_samples_per_second": 121.943, | |
| "eval_steps_per_second": 3.387, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0018526591107236269, | |
| "grad_norm": 1.7245711088180542, | |
| "learning_rate": 9.999907367044465e-06, | |
| "loss": 10.5547, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0018526591107236269, | |
| "eval_accuracy": 0.04842535272989897, | |
| "eval_loss": 10.53125, | |
| "eval_runtime": 277.5457, | |
| "eval_samples_per_second": 121.663, | |
| "eval_steps_per_second": 3.38, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0019071490845684394, | |
| "grad_norm": 1.6025965213775635, | |
| "learning_rate": 9.99990191804708e-06, | |
| "loss": 10.5469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0019071490845684394, | |
| "eval_accuracy": 0.04835280681616625, | |
| "eval_loss": 10.5234375, | |
| "eval_runtime": 280.2247, | |
| "eval_samples_per_second": 120.5, | |
| "eval_steps_per_second": 3.347, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001961639058413252, | |
| "grad_norm": 1.5452033281326294, | |
| "learning_rate": 9.999896469049695e-06, | |
| "loss": 10.5391, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001961639058413252, | |
| "eval_accuracy": 0.04815010670125943, | |
| "eval_loss": 10.515625, | |
| "eval_runtime": 278.5802, | |
| "eval_samples_per_second": 121.211, | |
| "eval_steps_per_second": 3.367, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0020161290322580645, | |
| "grad_norm": 1.5433681011199951, | |
| "learning_rate": 9.999891020052312e-06, | |
| "loss": 10.5312, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0020161290322580645, | |
| "eval_accuracy": 0.047523855403661705, | |
| "eval_loss": 10.5078125, | |
| "eval_runtime": 279.3479, | |
| "eval_samples_per_second": 120.878, | |
| "eval_steps_per_second": 3.358, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002070619006102877, | |
| "grad_norm": 1.4813498258590698, | |
| "learning_rate": 9.999885571054927e-06, | |
| "loss": 10.5312, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002070619006102877, | |
| "eval_accuracy": 0.047497569813211064, | |
| "eval_loss": 10.4921875, | |
| "eval_runtime": 279.8874, | |
| "eval_samples_per_second": 120.645, | |
| "eval_steps_per_second": 3.351, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0021251089799476895, | |
| "grad_norm": 1.5266352891921997, | |
| "learning_rate": 9.999880122057542e-06, | |
| "loss": 10.4922, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0021251089799476895, | |
| "eval_accuracy": 0.04756021520719255, | |
| "eval_loss": 10.484375, | |
| "eval_runtime": 278.6312, | |
| "eval_samples_per_second": 121.189, | |
| "eval_steps_per_second": 3.366, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002179598953792502, | |
| "grad_norm": 1.433236837387085, | |
| "learning_rate": 9.999874673060158e-06, | |
| "loss": 10.5078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002179598953792502, | |
| "eval_accuracy": 0.047665212824554305, | |
| "eval_loss": 10.484375, | |
| "eval_runtime": 278.9837, | |
| "eval_samples_per_second": 121.036, | |
| "eval_steps_per_second": 3.362, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022340889276373146, | |
| "grad_norm": 1.4035075902938843, | |
| "learning_rate": 9.999869224062774e-06, | |
| "loss": 10.4922, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0022340889276373146, | |
| "eval_accuracy": 0.048127468670717134, | |
| "eval_loss": 10.4765625, | |
| "eval_runtime": 280.2687, | |
| "eval_samples_per_second": 120.481, | |
| "eval_steps_per_second": 3.347, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002288578901482127, | |
| "grad_norm": 1.392196774482727, | |
| "learning_rate": 9.999863775065389e-06, | |
| "loss": 10.4844, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002288578901482127, | |
| "eval_accuracy": 0.048623971051575024, | |
| "eval_loss": 10.46875, | |
| "eval_runtime": 279.283, | |
| "eval_samples_per_second": 120.906, | |
| "eval_steps_per_second": 3.359, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0023430688753269396, | |
| "grad_norm": 1.4084738492965698, | |
| "learning_rate": 9.999858326068004e-06, | |
| "loss": 10.4766, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0023430688753269396, | |
| "eval_accuracy": 0.0492689812287014, | |
| "eval_loss": 10.4609375, | |
| "eval_runtime": 279.956, | |
| "eval_samples_per_second": 120.615, | |
| "eval_steps_per_second": 3.351, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0023975588491717526, | |
| "grad_norm": 1.3411015272140503, | |
| "learning_rate": 9.999852877070619e-06, | |
| "loss": 10.4844, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0023975588491717526, | |
| "eval_accuracy": 0.04953739531973483, | |
| "eval_loss": 10.453125, | |
| "eval_runtime": 278.5767, | |
| "eval_samples_per_second": 121.213, | |
| "eval_steps_per_second": 3.367, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002452048823016565, | |
| "grad_norm": 1.381066083908081, | |
| "learning_rate": 9.999847428073235e-06, | |
| "loss": 10.4688, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002452048823016565, | |
| "eval_accuracy": 0.05031273339136427, | |
| "eval_loss": 10.4453125, | |
| "eval_runtime": 278.3035, | |
| "eval_samples_per_second": 121.332, | |
| "eval_steps_per_second": 3.37, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0025065387968613777, | |
| "grad_norm": 1.2761576175689697, | |
| "learning_rate": 9.99984197907585e-06, | |
| "loss": 10.4844, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0025065387968613777, | |
| "eval_accuracy": 0.05126917570733207, | |
| "eval_loss": 10.4453125, | |
| "eval_runtime": 278.7818, | |
| "eval_samples_per_second": 121.123, | |
| "eval_steps_per_second": 3.365, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00256102877070619, | |
| "grad_norm": 1.2938231229782104, | |
| "learning_rate": 9.999836530078465e-06, | |
| "loss": 10.4609, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00256102877070619, | |
| "eval_accuracy": 0.05223774760743953, | |
| "eval_loss": 10.4375, | |
| "eval_runtime": 280.01, | |
| "eval_samples_per_second": 120.592, | |
| "eval_steps_per_second": 3.35, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0026155187445510027, | |
| "grad_norm": 1.408036231994629, | |
| "learning_rate": 9.999831081081082e-06, | |
| "loss": 10.4453, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0026155187445510027, | |
| "eval_accuracy": 0.05263593956410096, | |
| "eval_loss": 10.4296875, | |
| "eval_runtime": 279.456, | |
| "eval_samples_per_second": 120.831, | |
| "eval_steps_per_second": 3.357, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0026700087183958152, | |
| "grad_norm": 1.3031139373779297, | |
| "learning_rate": 9.999825632083697e-06, | |
| "loss": 10.4453, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0026700087183958152, | |
| "eval_accuracy": 0.05322177821382523, | |
| "eval_loss": 10.4296875, | |
| "eval_runtime": 279.6217, | |
| "eval_samples_per_second": 120.76, | |
| "eval_steps_per_second": 3.355, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0027244986922406278, | |
| "grad_norm": 1.3556911945343018, | |
| "learning_rate": 9.999820183086312e-06, | |
| "loss": 10.4297, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0027244986922406278, | |
| "eval_accuracy": 0.05367262819805243, | |
| "eval_loss": 10.421875, | |
| "eval_runtime": 278.4251, | |
| "eval_samples_per_second": 121.279, | |
| "eval_steps_per_second": 3.369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0027789886660854403, | |
| "grad_norm": 1.3359757661819458, | |
| "learning_rate": 9.999814734088929e-06, | |
| "loss": 10.4219, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0027789886660854403, | |
| "eval_accuracy": 0.05440648251294645, | |
| "eval_loss": 10.4140625, | |
| "eval_runtime": 278.6487, | |
| "eval_samples_per_second": 121.181, | |
| "eval_steps_per_second": 3.366, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.002833478639930253, | |
| "grad_norm": 1.2961536645889282, | |
| "learning_rate": 9.999809285091544e-06, | |
| "loss": 10.4297, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002833478639930253, | |
| "eval_accuracy": 0.05480528239625927, | |
| "eval_loss": 10.4140625, | |
| "eval_runtime": 278.1813, | |
| "eval_samples_per_second": 121.385, | |
| "eval_steps_per_second": 3.372, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0028879686137750654, | |
| "grad_norm": 1.2359050512313843, | |
| "learning_rate": 9.999803836094159e-06, | |
| "loss": 10.4375, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0028879686137750654, | |
| "eval_accuracy": 0.055358814086795306, | |
| "eval_loss": 10.40625, | |
| "eval_runtime": 279.3681, | |
| "eval_samples_per_second": 120.869, | |
| "eval_steps_per_second": 3.358, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.002942458587619878, | |
| "grad_norm": 1.2747548818588257, | |
| "learning_rate": 9.999798387096776e-06, | |
| "loss": 10.4219, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.002942458587619878, | |
| "eval_accuracy": 0.055845676487895415, | |
| "eval_loss": 10.40625, | |
| "eval_runtime": 280.0513, | |
| "eval_samples_per_second": 120.574, | |
| "eval_steps_per_second": 3.349, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0029969485614646904, | |
| "grad_norm": 1.304934024810791, | |
| "learning_rate": 9.99979293809939e-06, | |
| "loss": 10.4141, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0029969485614646904, | |
| "eval_accuracy": 0.05652635169523676, | |
| "eval_loss": 10.3984375, | |
| "eval_runtime": 280.159, | |
| "eval_samples_per_second": 120.528, | |
| "eval_steps_per_second": 3.348, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.003051438535309503, | |
| "grad_norm": 1.2796216011047363, | |
| "learning_rate": 9.999787489102006e-06, | |
| "loss": 10.4141, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.003051438535309503, | |
| "eval_accuracy": 0.05738361512036325, | |
| "eval_loss": 10.390625, | |
| "eval_runtime": 280.8546, | |
| "eval_samples_per_second": 120.229, | |
| "eval_steps_per_second": 3.34, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0031059285091543155, | |
| "grad_norm": 1.273751974105835, | |
| "learning_rate": 9.999782040104623e-06, | |
| "loss": 10.4219, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0031059285091543155, | |
| "eval_accuracy": 0.05828062536893549, | |
| "eval_loss": 10.390625, | |
| "eval_runtime": 280.5946, | |
| "eval_samples_per_second": 120.341, | |
| "eval_steps_per_second": 3.343, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.003160418482999128, | |
| "grad_norm": 1.2347089052200317, | |
| "learning_rate": 9.999776591107238e-06, | |
| "loss": 10.4219, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.003160418482999128, | |
| "eval_accuracy": 0.05910523444821581, | |
| "eval_loss": 10.3828125, | |
| "eval_runtime": 281.2657, | |
| "eval_samples_per_second": 120.054, | |
| "eval_steps_per_second": 3.335, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0032149084568439405, | |
| "grad_norm": 1.2617988586425781, | |
| "learning_rate": 9.999771142109853e-06, | |
| "loss": 10.3984, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0032149084568439405, | |
| "eval_accuracy": 0.059817348148100545, | |
| "eval_loss": 10.3828125, | |
| "eval_runtime": 279.7299, | |
| "eval_samples_per_second": 120.713, | |
| "eval_steps_per_second": 3.353, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.003269398430688753, | |
| "grad_norm": 1.2854173183441162, | |
| "learning_rate": 9.999765693112468e-06, | |
| "loss": 10.3984, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003269398430688753, | |
| "eval_accuracy": 0.06033486742176367, | |
| "eval_loss": 10.375, | |
| "eval_runtime": 279.8061, | |
| "eval_samples_per_second": 120.68, | |
| "eval_steps_per_second": 3.352, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003323888404533566, | |
| "grad_norm": 1.2649012804031372, | |
| "learning_rate": 9.999760244115083e-06, | |
| "loss": 10.3984, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.003323888404533566, | |
| "eval_accuracy": 0.06070726591907321, | |
| "eval_loss": 10.375, | |
| "eval_runtime": 279.7805, | |
| "eval_samples_per_second": 120.691, | |
| "eval_steps_per_second": 3.353, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0033783783783783786, | |
| "grad_norm": 1.284862756729126, | |
| "learning_rate": 9.9997547951177e-06, | |
| "loss": 10.3906, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0033783783783783786, | |
| "eval_accuracy": 0.061101260286951224, | |
| "eval_loss": 10.3671875, | |
| "eval_runtime": 280.6475, | |
| "eval_samples_per_second": 120.318, | |
| "eval_steps_per_second": 3.342, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.003432868352223191, | |
| "grad_norm": 1.3201900720596313, | |
| "learning_rate": 9.999749346120314e-06, | |
| "loss": 10.3672, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003432868352223191, | |
| "eval_accuracy": 0.06146384511117401, | |
| "eval_loss": 10.3671875, | |
| "eval_runtime": 280.4398, | |
| "eval_samples_per_second": 120.407, | |
| "eval_steps_per_second": 3.345, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0034873583260680036, | |
| "grad_norm": 1.265735387802124, | |
| "learning_rate": 9.99974389712293e-06, | |
| "loss": 10.3906, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0034873583260680036, | |
| "eval_accuracy": 0.0615552078022117, | |
| "eval_loss": 10.359375, | |
| "eval_runtime": 280.4115, | |
| "eval_samples_per_second": 120.419, | |
| "eval_steps_per_second": 3.345, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.003541848299912816, | |
| "grad_norm": 1.2759215831756592, | |
| "learning_rate": 9.999738448125546e-06, | |
| "loss": 10.3828, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.003541848299912816, | |
| "eval_accuracy": 0.061487409506137465, | |
| "eval_loss": 10.359375, | |
| "eval_runtime": 280.0889, | |
| "eval_samples_per_second": 120.558, | |
| "eval_steps_per_second": 3.349, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0035963382737576287, | |
| "grad_norm": 1.2972633838653564, | |
| "learning_rate": 9.999732999128161e-06, | |
| "loss": 10.3594, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0035963382737576287, | |
| "eval_accuracy": 0.06136165553596391, | |
| "eval_loss": 10.3515625, | |
| "eval_runtime": 280.2984, | |
| "eval_samples_per_second": 120.468, | |
| "eval_steps_per_second": 3.346, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.003650828247602441, | |
| "grad_norm": 1.3436386585235596, | |
| "learning_rate": 9.999727550130776e-06, | |
| "loss": 10.3516, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.003650828247602441, | |
| "eval_accuracy": 0.06103861489296974, | |
| "eval_loss": 10.34375, | |
| "eval_runtime": 280.5172, | |
| "eval_samples_per_second": 120.374, | |
| "eval_steps_per_second": 3.344, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0037053182214472537, | |
| "grad_norm": 1.3115813732147217, | |
| "learning_rate": 9.999722101133393e-06, | |
| "loss": 10.3516, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0037053182214472537, | |
| "eval_accuracy": 0.060934138355594886, | |
| "eval_loss": 10.34375, | |
| "eval_runtime": 279.6787, | |
| "eval_samples_per_second": 120.735, | |
| "eval_steps_per_second": 3.354, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0037598081952920663, | |
| "grad_norm": 1.3387259244918823, | |
| "learning_rate": 9.999716652136008e-06, | |
| "loss": 10.3438, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0037598081952920663, | |
| "eval_accuracy": 0.061064147812328176, | |
| "eval_loss": 10.3359375, | |
| "eval_runtime": 279.3007, | |
| "eval_samples_per_second": 120.898, | |
| "eval_steps_per_second": 3.358, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.003814298169136879, | |
| "grad_norm": 1.507016897201538, | |
| "learning_rate": 9.999711203138623e-06, | |
| "loss": 10.3594, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003814298169136879, | |
| "eval_accuracy": 0.061038383301864445, | |
| "eval_loss": 10.3359375, | |
| "eval_runtime": 280.6833, | |
| "eval_samples_per_second": 120.303, | |
| "eval_steps_per_second": 3.342, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0038687881429816913, | |
| "grad_norm": 1.2702033519744873, | |
| "learning_rate": 9.99970575414124e-06, | |
| "loss": 10.3594, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0038687881429816913, | |
| "eval_accuracy": 0.06097628793675803, | |
| "eval_loss": 10.328125, | |
| "eval_runtime": 279.2628, | |
| "eval_samples_per_second": 120.915, | |
| "eval_steps_per_second": 3.359, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.003923278116826504, | |
| "grad_norm": 1.3358463048934937, | |
| "learning_rate": 9.999700305143855e-06, | |
| "loss": 10.3203, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003923278116826504, | |
| "eval_accuracy": 0.06098071711664674, | |
| "eval_loss": 10.328125, | |
| "eval_runtime": 280.3079, | |
| "eval_samples_per_second": 120.464, | |
| "eval_steps_per_second": 3.346, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003977768090671316, | |
| "grad_norm": 1.259023904800415, | |
| "learning_rate": 9.99969485614647e-06, | |
| "loss": 10.3516, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.003977768090671316, | |
| "eval_accuracy": 0.06099933125173458, | |
| "eval_loss": 10.3203125, | |
| "eval_runtime": 280.2434, | |
| "eval_samples_per_second": 120.492, | |
| "eval_steps_per_second": 3.347, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.004032258064516129, | |
| "grad_norm": 1.458150029182434, | |
| "learning_rate": 9.999689407149085e-06, | |
| "loss": 10.3203, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.004032258064516129, | |
| "eval_accuracy": 0.061083225129626606, | |
| "eval_loss": 10.3125, | |
| "eval_runtime": 280.0404, | |
| "eval_samples_per_second": 120.579, | |
| "eval_steps_per_second": 3.35, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0040867480383609414, | |
| "grad_norm": 1.2943834066390991, | |
| "learning_rate": 9.999683958151702e-06, | |
| "loss": 10.3281, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0040867480383609414, | |
| "eval_accuracy": 0.06123138553923716, | |
| "eval_loss": 10.3125, | |
| "eval_runtime": 280.4851, | |
| "eval_samples_per_second": 120.388, | |
| "eval_steps_per_second": 3.344, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004141238012205754, | |
| "grad_norm": 1.2712702751159668, | |
| "learning_rate": 9.999678509154317e-06, | |
| "loss": 10.3438, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.004141238012205754, | |
| "eval_accuracy": 0.061402212928278174, | |
| "eval_loss": 10.3046875, | |
| "eval_runtime": 279.7875, | |
| "eval_samples_per_second": 120.688, | |
| "eval_steps_per_second": 3.353, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0041957279860505665, | |
| "grad_norm": 1.3315693140029907, | |
| "learning_rate": 9.999673060156932e-06, | |
| "loss": 10.2969, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0041957279860505665, | |
| "eval_accuracy": 0.0617529576572429, | |
| "eval_loss": 10.3046875, | |
| "eval_runtime": 280.9468, | |
| "eval_samples_per_second": 120.19, | |
| "eval_steps_per_second": 3.339, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.004250217959895379, | |
| "grad_norm": 1.2693438529968262, | |
| "learning_rate": 9.999667611159547e-06, | |
| "loss": 10.3281, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.004250217959895379, | |
| "eval_accuracy": 0.06221338972345156, | |
| "eval_loss": 10.296875, | |
| "eval_runtime": 280.2001, | |
| "eval_samples_per_second": 120.51, | |
| "eval_steps_per_second": 3.348, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.004304707933740192, | |
| "grad_norm": 1.4125028848648071, | |
| "learning_rate": 9.999662162162162e-06, | |
| "loss": 10.2891, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.004304707933740192, | |
| "eval_accuracy": 0.0628054234352424, | |
| "eval_loss": 10.296875, | |
| "eval_runtime": 280.5046, | |
| "eval_samples_per_second": 120.379, | |
| "eval_steps_per_second": 3.344, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.004359197907585004, | |
| "grad_norm": 1.4127213954925537, | |
| "learning_rate": 9.999656713164779e-06, | |
| "loss": 10.3047, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004359197907585004, | |
| "eval_accuracy": 0.0632026600785945, | |
| "eval_loss": 10.2890625, | |
| "eval_runtime": 281.1308, | |
| "eval_samples_per_second": 120.111, | |
| "eval_steps_per_second": 3.337, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004413687881429817, | |
| "grad_norm": 1.2919211387634277, | |
| "learning_rate": 9.999651264167394e-06, | |
| "loss": 10.2969, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004413687881429817, | |
| "eval_accuracy": 0.06365513120055874, | |
| "eval_loss": 10.28125, | |
| "eval_runtime": 280.4747, | |
| "eval_samples_per_second": 120.392, | |
| "eval_steps_per_second": 3.344, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004468177855274629, | |
| "grad_norm": 1.3636354207992554, | |
| "learning_rate": 9.999645815170009e-06, | |
| "loss": 10.2891, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.004468177855274629, | |
| "eval_accuracy": 0.06432144775937197, | |
| "eval_loss": 10.28125, | |
| "eval_runtime": 280.6686, | |
| "eval_samples_per_second": 120.309, | |
| "eval_steps_per_second": 3.342, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.004522667829119442, | |
| "grad_norm": 1.2588390111923218, | |
| "learning_rate": 9.999640366172625e-06, | |
| "loss": 10.3125, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.004522667829119442, | |
| "eval_accuracy": 0.06491886596436085, | |
| "eval_loss": 10.2734375, | |
| "eval_runtime": 280.7018, | |
| "eval_samples_per_second": 120.295, | |
| "eval_steps_per_second": 3.342, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.004577157802964254, | |
| "grad_norm": 1.2841159105300903, | |
| "learning_rate": 9.99963491717524e-06, | |
| "loss": 10.2891, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.004577157802964254, | |
| "eval_accuracy": 0.0653847114726557, | |
| "eval_loss": 10.2734375, | |
| "eval_runtime": 280.4683, | |
| "eval_samples_per_second": 120.395, | |
| "eval_steps_per_second": 3.344, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.004631647776809067, | |
| "grad_norm": 1.2950408458709717, | |
| "learning_rate": 9.999629468177855e-06, | |
| "loss": 10.2812, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.004631647776809067, | |
| "eval_accuracy": 0.06567657416309995, | |
| "eval_loss": 10.265625, | |
| "eval_runtime": 279.8035, | |
| "eval_samples_per_second": 120.681, | |
| "eval_steps_per_second": 3.352, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.004686137750653879, | |
| "grad_norm": 1.284853458404541, | |
| "learning_rate": 9.999624019180472e-06, | |
| "loss": 10.3047, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.004686137750653879, | |
| "eval_accuracy": 0.06585295973866796, | |
| "eval_loss": 10.265625, | |
| "eval_runtime": 280.2049, | |
| "eval_samples_per_second": 120.508, | |
| "eval_steps_per_second": 3.348, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.004740627724498693, | |
| "grad_norm": 1.229882836341858, | |
| "learning_rate": 9.999618570183087e-06, | |
| "loss": 10.2969, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.004740627724498693, | |
| "eval_accuracy": 0.06600204651269968, | |
| "eval_loss": 10.2578125, | |
| "eval_runtime": 280.4096, | |
| "eval_samples_per_second": 120.42, | |
| "eval_steps_per_second": 3.345, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.004795117698343505, | |
| "grad_norm": 1.3210368156433105, | |
| "learning_rate": 9.999613121185702e-06, | |
| "loss": 10.2578, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.004795117698343505, | |
| "eval_accuracy": 0.06612053431194471, | |
| "eval_loss": 10.25, | |
| "eval_runtime": 280.0298, | |
| "eval_samples_per_second": 120.584, | |
| "eval_steps_per_second": 3.35, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.004849607672188318, | |
| "grad_norm": 1.2671563625335693, | |
| "learning_rate": 9.999607672188319e-06, | |
| "loss": 10.2812, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.004849607672188318, | |
| "eval_accuracy": 0.06618060325487982, | |
| "eval_loss": 10.25, | |
| "eval_runtime": 280.1841, | |
| "eval_samples_per_second": 120.517, | |
| "eval_steps_per_second": 3.348, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.00490409764603313, | |
| "grad_norm": 1.2486541271209717, | |
| "learning_rate": 9.999602223190934e-06, | |
| "loss": 10.2734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.00490409764603313, | |
| "eval_accuracy": 0.06629969898077623, | |
| "eval_loss": 10.2421875, | |
| "eval_runtime": 279.9304, | |
| "eval_samples_per_second": 120.626, | |
| "eval_steps_per_second": 3.351, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004958587619877943, | |
| "grad_norm": 1.219537615776062, | |
| "learning_rate": 9.999596774193549e-06, | |
| "loss": 10.2891, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.004958587619877943, | |
| "eval_accuracy": 0.06638553243417508, | |
| "eval_loss": 10.2421875, | |
| "eval_runtime": 280.2115, | |
| "eval_samples_per_second": 120.505, | |
| "eval_steps_per_second": 3.347, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.005013077593722755, | |
| "grad_norm": 1.3005180358886719, | |
| "learning_rate": 9.999591325196166e-06, | |
| "loss": 10.2578, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.005013077593722755, | |
| "eval_accuracy": 0.06655224908109715, | |
| "eval_loss": 10.234375, | |
| "eval_runtime": 280.5566, | |
| "eval_samples_per_second": 120.357, | |
| "eval_steps_per_second": 3.343, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.005067567567567568, | |
| "grad_norm": 1.2326613664627075, | |
| "learning_rate": 9.99958587619878e-06, | |
| "loss": 10.2734, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.005067567567567568, | |
| "eval_accuracy": 0.06677831094875031, | |
| "eval_loss": 10.234375, | |
| "eval_runtime": 279.0494, | |
| "eval_samples_per_second": 121.007, | |
| "eval_steps_per_second": 3.361, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.00512205754141238, | |
| "grad_norm": 1.343145728111267, | |
| "learning_rate": 9.999580427201396e-06, | |
| "loss": 10.2266, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.00512205754141238, | |
| "eval_accuracy": 0.0670887877742824, | |
| "eval_loss": 10.2265625, | |
| "eval_runtime": 278.9829, | |
| "eval_samples_per_second": 121.036, | |
| "eval_steps_per_second": 3.362, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.005176547515257193, | |
| "grad_norm": 1.2524234056472778, | |
| "learning_rate": 9.999574978204011e-06, | |
| "loss": 10.2578, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.005176547515257193, | |
| "eval_accuracy": 0.06735230950321652, | |
| "eval_loss": 10.2265625, | |
| "eval_runtime": 278.058, | |
| "eval_samples_per_second": 121.439, | |
| "eval_steps_per_second": 3.373, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0052310374891020054, | |
| "grad_norm": 1.232895016670227, | |
| "learning_rate": 9.999569529206626e-06, | |
| "loss": 10.25, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0052310374891020054, | |
| "eval_accuracy": 0.0675672260489275, | |
| "eval_loss": 10.21875, | |
| "eval_runtime": 280.2022, | |
| "eval_samples_per_second": 120.509, | |
| "eval_steps_per_second": 3.348, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.005285527462946818, | |
| "grad_norm": 1.2870153188705444, | |
| "learning_rate": 9.999564080209243e-06, | |
| "loss": 10.2266, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.005285527462946818, | |
| "eval_accuracy": 0.06775721760193143, | |
| "eval_loss": 10.21875, | |
| "eval_runtime": 279.5356, | |
| "eval_samples_per_second": 120.797, | |
| "eval_steps_per_second": 3.356, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0053400174367916305, | |
| "grad_norm": 1.2629221677780151, | |
| "learning_rate": 9.999558631211858e-06, | |
| "loss": 10.2266, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0053400174367916305, | |
| "eval_accuracy": 0.06793869818181586, | |
| "eval_loss": 10.2109375, | |
| "eval_runtime": 279.0624, | |
| "eval_samples_per_second": 121.002, | |
| "eval_steps_per_second": 3.361, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.005394507410636443, | |
| "grad_norm": 1.279175043106079, | |
| "learning_rate": 9.999553182214473e-06, | |
| "loss": 10.2344, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.005394507410636443, | |
| "eval_accuracy": 0.06805782285660043, | |
| "eval_loss": 10.2109375, | |
| "eval_runtime": 278.9598, | |
| "eval_samples_per_second": 121.046, | |
| "eval_steps_per_second": 3.362, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0054489973844812556, | |
| "grad_norm": 1.21150803565979, | |
| "learning_rate": 9.99954773321709e-06, | |
| "loss": 10.2422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0054489973844812556, | |
| "eval_accuracy": 0.0681561332807969, | |
| "eval_loss": 10.203125, | |
| "eval_runtime": 278.9899, | |
| "eval_samples_per_second": 121.033, | |
| "eval_steps_per_second": 3.362, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005503487358326068, | |
| "grad_norm": 1.2411643266677856, | |
| "learning_rate": 9.999542284219704e-06, | |
| "loss": 10.2422, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.005503487358326068, | |
| "eval_accuracy": 0.06829934343053183, | |
| "eval_loss": 10.203125, | |
| "eval_runtime": 278.3501, | |
| "eval_samples_per_second": 121.311, | |
| "eval_steps_per_second": 3.37, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.005557977332170881, | |
| "grad_norm": 1.2620774507522583, | |
| "learning_rate": 9.99953683522232e-06, | |
| "loss": 10.2266, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.005557977332170881, | |
| "eval_accuracy": 0.0684582438776503, | |
| "eval_loss": 10.1953125, | |
| "eval_runtime": 280.5409, | |
| "eval_samples_per_second": 120.364, | |
| "eval_steps_per_second": 3.344, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.005612467306015693, | |
| "grad_norm": 1.2730474472045898, | |
| "learning_rate": 9.999531386224936e-06, | |
| "loss": 10.2188, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.005612467306015693, | |
| "eval_accuracy": 0.06855808859291931, | |
| "eval_loss": 10.1953125, | |
| "eval_runtime": 279.3284, | |
| "eval_samples_per_second": 120.886, | |
| "eval_steps_per_second": 3.358, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.005666957279860506, | |
| "grad_norm": 1.250596046447754, | |
| "learning_rate": 9.999525937227551e-06, | |
| "loss": 10.2109, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.005666957279860506, | |
| "eval_accuracy": 0.06870066186711471, | |
| "eval_loss": 10.1875, | |
| "eval_runtime": 279.5974, | |
| "eval_samples_per_second": 120.77, | |
| "eval_steps_per_second": 3.355, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.005721447253705318, | |
| "grad_norm": 1.3434346914291382, | |
| "learning_rate": 9.999520488230166e-06, | |
| "loss": 10.1797, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.005721447253705318, | |
| "eval_accuracy": 0.06888807696907226, | |
| "eval_loss": 10.1875, | |
| "eval_runtime": 279.5391, | |
| "eval_samples_per_second": 120.795, | |
| "eval_steps_per_second": 3.356, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.005775937227550131, | |
| "grad_norm": 1.28876793384552, | |
| "learning_rate": 9.999515039232783e-06, | |
| "loss": 10.1797, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.005775937227550131, | |
| "eval_accuracy": 0.06907245243777284, | |
| "eval_loss": 10.1796875, | |
| "eval_runtime": 279.0416, | |
| "eval_samples_per_second": 121.011, | |
| "eval_steps_per_second": 3.362, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.005830427201394943, | |
| "grad_norm": 1.3488516807556152, | |
| "learning_rate": 9.999509590235398e-06, | |
| "loss": 10.1719, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.005830427201394943, | |
| "eval_accuracy": 0.06933892695329945, | |
| "eval_loss": 10.1796875, | |
| "eval_runtime": 279.7608, | |
| "eval_samples_per_second": 120.7, | |
| "eval_steps_per_second": 3.353, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.005884917175239756, | |
| "grad_norm": 1.272630214691162, | |
| "learning_rate": 9.999504141238013e-06, | |
| "loss": 10.1875, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.005884917175239756, | |
| "eval_accuracy": 0.06959364822023249, | |
| "eval_loss": 10.171875, | |
| "eval_runtime": 279.3313, | |
| "eval_samples_per_second": 120.885, | |
| "eval_steps_per_second": 3.358, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.005939407149084568, | |
| "grad_norm": 1.275840401649475, | |
| "learning_rate": 9.999498692240628e-06, | |
| "loss": 10.1797, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.005939407149084568, | |
| "eval_accuracy": 0.06980685678154193, | |
| "eval_loss": 10.171875, | |
| "eval_runtime": 279.6516, | |
| "eval_samples_per_second": 120.747, | |
| "eval_steps_per_second": 3.354, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.005993897122929381, | |
| "grad_norm": 1.2549141645431519, | |
| "learning_rate": 9.999493243243245e-06, | |
| "loss": 10.1797, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005993897122929381, | |
| "eval_accuracy": 0.07002058642283829, | |
| "eval_loss": 10.1640625, | |
| "eval_runtime": 279.1415, | |
| "eval_samples_per_second": 120.967, | |
| "eval_steps_per_second": 3.36, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.006048387096774193, | |
| "grad_norm": 1.3456748723983765, | |
| "learning_rate": 9.999487794245858e-06, | |
| "loss": 10.1406, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.006048387096774193, | |
| "eval_accuracy": 0.07022299704886349, | |
| "eval_loss": 10.1640625, | |
| "eval_runtime": 279.1359, | |
| "eval_samples_per_second": 120.97, | |
| "eval_steps_per_second": 3.36, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.006102877070619006, | |
| "grad_norm": 1.2664400339126587, | |
| "learning_rate": 9.999482345248475e-06, | |
| "loss": 10.1719, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.006102877070619006, | |
| "eval_accuracy": 0.07042644983486251, | |
| "eval_loss": 10.1640625, | |
| "eval_runtime": 279.7876, | |
| "eval_samples_per_second": 120.688, | |
| "eval_steps_per_second": 3.353, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.0061573670444638184, | |
| "grad_norm": 1.226805329322815, | |
| "learning_rate": 9.99947689625109e-06, | |
| "loss": 10.1953, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.0061573670444638184, | |
| "eval_accuracy": 0.07062440233211086, | |
| "eval_loss": 10.15625, | |
| "eval_runtime": 280.1774, | |
| "eval_samples_per_second": 120.52, | |
| "eval_steps_per_second": 3.348, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.006211857018308631, | |
| "grad_norm": 1.2513021230697632, | |
| "learning_rate": 9.999471447253705e-06, | |
| "loss": 10.1719, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.006211857018308631, | |
| "eval_accuracy": 0.070792566423441, | |
| "eval_loss": 10.15625, | |
| "eval_runtime": 279.7452, | |
| "eval_samples_per_second": 120.706, | |
| "eval_steps_per_second": 3.353, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0062663469921534435, | |
| "grad_norm": 1.2754563093185425, | |
| "learning_rate": 9.999465998256322e-06, | |
| "loss": 10.1641, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.0062663469921534435, | |
| "eval_accuracy": 0.0709808499920434, | |
| "eval_loss": 10.1484375, | |
| "eval_runtime": 279.6651, | |
| "eval_samples_per_second": 120.741, | |
| "eval_steps_per_second": 3.354, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.006320836965998256, | |
| "grad_norm": 1.2457561492919922, | |
| "learning_rate": 9.999460549258937e-06, | |
| "loss": 10.1719, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.006320836965998256, | |
| "eval_accuracy": 0.07117214424501458, | |
| "eval_loss": 10.1484375, | |
| "eval_runtime": 279.2608, | |
| "eval_samples_per_second": 120.916, | |
| "eval_steps_per_second": 3.359, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.0063753269398430686, | |
| "grad_norm": 1.2697603702545166, | |
| "learning_rate": 9.999455100261552e-06, | |
| "loss": 10.1484, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.0063753269398430686, | |
| "eval_accuracy": 0.07134343481626618, | |
| "eval_loss": 10.140625, | |
| "eval_runtime": 279.2939, | |
| "eval_samples_per_second": 120.901, | |
| "eval_steps_per_second": 3.358, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.006429816913687881, | |
| "grad_norm": 1.2824610471725464, | |
| "learning_rate": 9.999449651264169e-06, | |
| "loss": 10.1562, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.006429816913687881, | |
| "eval_accuracy": 0.07150007725010805, | |
| "eval_loss": 10.140625, | |
| "eval_runtime": 280.6459, | |
| "eval_samples_per_second": 120.319, | |
| "eval_steps_per_second": 3.342, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.006484306887532694, | |
| "grad_norm": 1.2311967611312866, | |
| "learning_rate": 9.999444202266784e-06, | |
| "loss": 10.1562, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.006484306887532694, | |
| "eval_accuracy": 0.07164412691759968, | |
| "eval_loss": 10.1328125, | |
| "eval_runtime": 278.8366, | |
| "eval_samples_per_second": 121.1, | |
| "eval_steps_per_second": 3.364, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.006538796861377506, | |
| "grad_norm": 1.260802984237671, | |
| "learning_rate": 9.999438753269399e-06, | |
| "loss": 10.1484, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.006538796861377506, | |
| "eval_accuracy": 0.07180059565811259, | |
| "eval_loss": 10.1328125, | |
| "eval_runtime": 279.3119, | |
| "eval_samples_per_second": 120.894, | |
| "eval_steps_per_second": 3.358, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.006593286835222319, | |
| "grad_norm": 1.2933627367019653, | |
| "learning_rate": 9.999433304272015e-06, | |
| "loss": 10.1406, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.006593286835222319, | |
| "eval_accuracy": 0.07193274733256984, | |
| "eval_loss": 10.125, | |
| "eval_runtime": 280.0499, | |
| "eval_samples_per_second": 120.575, | |
| "eval_steps_per_second": 3.349, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.006647776809067132, | |
| "grad_norm": 1.2777124643325806, | |
| "learning_rate": 9.99942785527463e-06, | |
| "loss": 10.1328, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.006647776809067132, | |
| "eval_accuracy": 0.07206449372259283, | |
| "eval_loss": 10.125, | |
| "eval_runtime": 278.3594, | |
| "eval_samples_per_second": 121.307, | |
| "eval_steps_per_second": 3.37, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.006702266782911945, | |
| "grad_norm": 1.225155234336853, | |
| "learning_rate": 9.999422406277245e-06, | |
| "loss": 10.1641, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.006702266782911945, | |
| "eval_accuracy": 0.07220330364132721, | |
| "eval_loss": 10.1171875, | |
| "eval_runtime": 279.7375, | |
| "eval_samples_per_second": 120.71, | |
| "eval_steps_per_second": 3.353, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.006756756756756757, | |
| "grad_norm": 1.2431164979934692, | |
| "learning_rate": 9.999416957279862e-06, | |
| "loss": 10.1328, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.006756756756756757, | |
| "eval_accuracy": 0.07233015766925091, | |
| "eval_loss": 10.1171875, | |
| "eval_runtime": 278.5065, | |
| "eval_samples_per_second": 121.243, | |
| "eval_steps_per_second": 3.368, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.00681124673060157, | |
| "grad_norm": 1.2372488975524902, | |
| "learning_rate": 9.999411508282477e-06, | |
| "loss": 10.1484, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.00681124673060157, | |
| "eval_accuracy": 0.07246410417477417, | |
| "eval_loss": 10.109375, | |
| "eval_runtime": 278.7434, | |
| "eval_samples_per_second": 121.14, | |
| "eval_steps_per_second": 3.365, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.006865736704446382, | |
| "grad_norm": 1.2289838790893555, | |
| "learning_rate": 9.999406059285092e-06, | |
| "loss": 10.1406, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.006865736704446382, | |
| "eval_accuracy": 0.07261460944432581, | |
| "eval_loss": 10.109375, | |
| "eval_runtime": 279.5991, | |
| "eval_samples_per_second": 120.769, | |
| "eval_steps_per_second": 3.355, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.006920226678291195, | |
| "grad_norm": 1.231143832206726, | |
| "learning_rate": 9.999400610287709e-06, | |
| "loss": 10.1406, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.006920226678291195, | |
| "eval_accuracy": 0.07277023866708203, | |
| "eval_loss": 10.1015625, | |
| "eval_runtime": 279.4963, | |
| "eval_samples_per_second": 120.814, | |
| "eval_steps_per_second": 3.356, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.006974716652136007, | |
| "grad_norm": 1.3046151399612427, | |
| "learning_rate": 9.999395161290324e-06, | |
| "loss": 10.125, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.006974716652136007, | |
| "eval_accuracy": 0.07291527259677114, | |
| "eval_loss": 10.1015625, | |
| "eval_runtime": 280.7304, | |
| "eval_samples_per_second": 120.283, | |
| "eval_steps_per_second": 3.341, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.00702920662598082, | |
| "grad_norm": 1.2855069637298584, | |
| "learning_rate": 9.999389712292939e-06, | |
| "loss": 10.1172, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.00702920662598082, | |
| "eval_accuracy": 0.07305231663332767, | |
| "eval_loss": 10.09375, | |
| "eval_runtime": 279.8824, | |
| "eval_samples_per_second": 120.647, | |
| "eval_steps_per_second": 3.351, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.007083696599825632, | |
| "grad_norm": 1.282074213027954, | |
| "learning_rate": 9.999384263295554e-06, | |
| "loss": 10.1016, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.007083696599825632, | |
| "eval_accuracy": 0.07317312034362562, | |
| "eval_loss": 10.09375, | |
| "eval_runtime": 279.9541, | |
| "eval_samples_per_second": 120.616, | |
| "eval_steps_per_second": 3.351, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.007138186573670445, | |
| "grad_norm": 1.218042254447937, | |
| "learning_rate": 9.999378814298169e-06, | |
| "loss": 10.1172, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.007138186573670445, | |
| "eval_accuracy": 0.07330454829587883, | |
| "eval_loss": 10.0859375, | |
| "eval_runtime": 280.2317, | |
| "eval_samples_per_second": 120.497, | |
| "eval_steps_per_second": 3.347, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.007192676547515257, | |
| "grad_norm": 1.2612570524215698, | |
| "learning_rate": 9.999373365300786e-06, | |
| "loss": 10.1172, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.007192676547515257, | |
| "eval_accuracy": 0.07344506619901475, | |
| "eval_loss": 10.0859375, | |
| "eval_runtime": 280.7991, | |
| "eval_samples_per_second": 120.253, | |
| "eval_steps_per_second": 3.34, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.00724716652136007, | |
| "grad_norm": 1.2458122968673706, | |
| "learning_rate": 9.999367916303401e-06, | |
| "loss": 10.1172, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.00724716652136007, | |
| "eval_accuracy": 0.07357432298465584, | |
| "eval_loss": 10.0859375, | |
| "eval_runtime": 281.5847, | |
| "eval_samples_per_second": 119.918, | |
| "eval_steps_per_second": 3.331, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.007301656495204882, | |
| "grad_norm": 1.2749879360198975, | |
| "learning_rate": 9.999362467306016e-06, | |
| "loss": 10.0938, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.007301656495204882, | |
| "eval_accuracy": 0.07369055277062427, | |
| "eval_loss": 10.078125, | |
| "eval_runtime": 279.1661, | |
| "eval_samples_per_second": 120.957, | |
| "eval_steps_per_second": 3.36, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.007356146469049695, | |
| "grad_norm": 1.2771598100662231, | |
| "learning_rate": 9.999357018308633e-06, | |
| "loss": 10.1094, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.007356146469049695, | |
| "eval_accuracy": 0.07383138911152996, | |
| "eval_loss": 10.078125, | |
| "eval_runtime": 280.6696, | |
| "eval_samples_per_second": 120.309, | |
| "eval_steps_per_second": 3.342, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0074106364428945075, | |
| "grad_norm": 1.2409011125564575, | |
| "learning_rate": 9.999351569311248e-06, | |
| "loss": 10.1094, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.0074106364428945075, | |
| "eval_accuracy": 0.07399631092738602, | |
| "eval_loss": 10.0703125, | |
| "eval_runtime": 279.9187, | |
| "eval_samples_per_second": 120.631, | |
| "eval_steps_per_second": 3.351, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.00746512641673932, | |
| "grad_norm": 1.3785778284072876, | |
| "learning_rate": 9.999346120313863e-06, | |
| "loss": 10.0703, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.00746512641673932, | |
| "eval_accuracy": 0.07418262597159345, | |
| "eval_loss": 10.0703125, | |
| "eval_runtime": 278.8604, | |
| "eval_samples_per_second": 121.089, | |
| "eval_steps_per_second": 3.364, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.0075196163905841325, | |
| "grad_norm": 1.2543950080871582, | |
| "learning_rate": 9.99934067131648e-06, | |
| "loss": 10.0781, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0075196163905841325, | |
| "eval_accuracy": 0.07433802360324437, | |
| "eval_loss": 10.0625, | |
| "eval_runtime": 278.9667, | |
| "eval_samples_per_second": 121.043, | |
| "eval_steps_per_second": 3.362, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.007574106364428945, | |
| "grad_norm": 1.2550749778747559, | |
| "learning_rate": 9.999335222319094e-06, | |
| "loss": 10.0781, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.007574106364428945, | |
| "eval_accuracy": 0.07445636665804858, | |
| "eval_loss": 10.0625, | |
| "eval_runtime": 280.3577, | |
| "eval_samples_per_second": 120.443, | |
| "eval_steps_per_second": 3.346, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.007628596338273758, | |
| "grad_norm": 1.2808057069778442, | |
| "learning_rate": 9.99932977332171e-06, | |
| "loss": 10.0781, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.007628596338273758, | |
| "eval_accuracy": 0.07457149638626687, | |
| "eval_loss": 10.0546875, | |
| "eval_runtime": 278.8572, | |
| "eval_samples_per_second": 121.091, | |
| "eval_steps_per_second": 3.364, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.00768308631211857, | |
| "grad_norm": 1.2947779893875122, | |
| "learning_rate": 9.999324324324326e-06, | |
| "loss": 10.0625, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.00768308631211857, | |
| "eval_accuracy": 0.0747105089472184, | |
| "eval_loss": 10.0546875, | |
| "eval_runtime": 278.2341, | |
| "eval_samples_per_second": 121.362, | |
| "eval_steps_per_second": 3.371, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.007737576285963383, | |
| "grad_norm": 1.2656594514846802, | |
| "learning_rate": 9.999318875326941e-06, | |
| "loss": 10.0781, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.007737576285963383, | |
| "eval_accuracy": 0.07485380594361782, | |
| "eval_loss": 10.046875, | |
| "eval_runtime": 279.1203, | |
| "eval_samples_per_second": 120.976, | |
| "eval_steps_per_second": 3.361, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.007792066259808195, | |
| "grad_norm": 1.3355940580368042, | |
| "learning_rate": 9.999313426329556e-06, | |
| "loss": 10.0391, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.007792066259808195, | |
| "eval_accuracy": 0.07498022573821908, | |
| "eval_loss": 10.046875, | |
| "eval_runtime": 279.5611, | |
| "eval_samples_per_second": 120.786, | |
| "eval_steps_per_second": 3.355, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.007846556233653008, | |
| "grad_norm": 1.2356702089309692, | |
| "learning_rate": 9.999307977332171e-06, | |
| "loss": 10.0703, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.007846556233653008, | |
| "eval_accuracy": 0.07511967253249303, | |
| "eval_loss": 10.046875, | |
| "eval_runtime": 279.9704, | |
| "eval_samples_per_second": 120.609, | |
| "eval_steps_per_second": 3.35, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.007901046207497821, | |
| "grad_norm": 1.2823630571365356, | |
| "learning_rate": 9.999302528334788e-06, | |
| "loss": 10.0391, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.007901046207497821, | |
| "eval_accuracy": 0.07525402432245056, | |
| "eval_loss": 10.0390625, | |
| "eval_runtime": 279.3818, | |
| "eval_samples_per_second": 120.863, | |
| "eval_steps_per_second": 3.357, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.007955536181342633, | |
| "grad_norm": 1.2719727754592896, | |
| "learning_rate": 9.999297079337401e-06, | |
| "loss": 10.0469, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.007955536181342633, | |
| "eval_accuracy": 0.07538672602578286, | |
| "eval_loss": 10.0390625, | |
| "eval_runtime": 280.0065, | |
| "eval_samples_per_second": 120.594, | |
| "eval_steps_per_second": 3.35, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.008010026155187446, | |
| "grad_norm": 1.2450186014175415, | |
| "learning_rate": 9.999291630340018e-06, | |
| "loss": 10.0547, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.008010026155187446, | |
| "eval_accuracy": 0.07551505644700279, | |
| "eval_loss": 10.03125, | |
| "eval_runtime": 279.889, | |
| "eval_samples_per_second": 120.644, | |
| "eval_steps_per_second": 3.351, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.008064516129032258, | |
| "grad_norm": 1.2184418439865112, | |
| "learning_rate": 9.999286181342633e-06, | |
| "loss": 10.0703, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.008064516129032258, | |
| "eval_accuracy": 0.07562749392862206, | |
| "eval_loss": 10.03125, | |
| "eval_runtime": 278.8225, | |
| "eval_samples_per_second": 121.106, | |
| "eval_steps_per_second": 3.364, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.008119006102877071, | |
| "grad_norm": 1.241905689239502, | |
| "learning_rate": 9.999280732345248e-06, | |
| "loss": 10.0469, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.008119006102877071, | |
| "eval_accuracy": 0.0757480660478147, | |
| "eval_loss": 10.0234375, | |
| "eval_runtime": 279.6408, | |
| "eval_samples_per_second": 120.751, | |
| "eval_steps_per_second": 3.354, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.008173496076721883, | |
| "grad_norm": 1.2825335264205933, | |
| "learning_rate": 9.999275283347865e-06, | |
| "loss": 10.0391, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008173496076721883, | |
| "eval_accuracy": 0.07586571432930304, | |
| "eval_loss": 10.0234375, | |
| "eval_runtime": 279.96, | |
| "eval_samples_per_second": 120.614, | |
| "eval_steps_per_second": 3.35, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008227986050566696, | |
| "grad_norm": 1.2704492807388306, | |
| "learning_rate": 9.99926983435048e-06, | |
| "loss": 10.0391, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.008227986050566696, | |
| "eval_accuracy": 0.07599531850160207, | |
| "eval_loss": 10.015625, | |
| "eval_runtime": 278.0769, | |
| "eval_samples_per_second": 121.43, | |
| "eval_steps_per_second": 3.373, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.008282476024411508, | |
| "grad_norm": 1.2123051881790161, | |
| "learning_rate": 9.999264385353095e-06, | |
| "loss": 10.0391, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.008282476024411508, | |
| "eval_accuracy": 0.07611594851857105, | |
| "eval_loss": 10.015625, | |
| "eval_runtime": 279.8596, | |
| "eval_samples_per_second": 120.657, | |
| "eval_steps_per_second": 3.352, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.008336965998256321, | |
| "grad_norm": 1.258999228477478, | |
| "learning_rate": 9.999258936355712e-06, | |
| "loss": 10.0391, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.008336965998256321, | |
| "eval_accuracy": 0.07623133878678279, | |
| "eval_loss": 10.015625, | |
| "eval_runtime": 279.3191, | |
| "eval_samples_per_second": 120.89, | |
| "eval_steps_per_second": 3.358, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.008391455972101133, | |
| "grad_norm": 1.194441795349121, | |
| "learning_rate": 9.999253487358327e-06, | |
| "loss": 10.0469, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.008391455972101133, | |
| "eval_accuracy": 0.07634800280607362, | |
| "eval_loss": 10.0078125, | |
| "eval_runtime": 279.5107, | |
| "eval_samples_per_second": 120.808, | |
| "eval_steps_per_second": 3.356, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.008445945945945946, | |
| "grad_norm": 1.289880633354187, | |
| "learning_rate": 9.999248038360942e-06, | |
| "loss": 10.0312, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.008445945945945946, | |
| "eval_accuracy": 0.07645618480113316, | |
| "eval_loss": 10.0078125, | |
| "eval_runtime": 279.6787, | |
| "eval_samples_per_second": 120.735, | |
| "eval_steps_per_second": 3.354, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.008500435919790758, | |
| "grad_norm": 1.318518042564392, | |
| "learning_rate": 9.999242589363559e-06, | |
| "loss": 9.9844, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.008500435919790758, | |
| "eval_accuracy": 0.07656841964053529, | |
| "eval_loss": 10.0, | |
| "eval_runtime": 279.7302, | |
| "eval_samples_per_second": 120.713, | |
| "eval_steps_per_second": 3.353, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.008554925893635571, | |
| "grad_norm": 1.3092557191848755, | |
| "learning_rate": 9.999237140366174e-06, | |
| "loss": 10.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.008554925893635571, | |
| "eval_accuracy": 0.0766785701599898, | |
| "eval_loss": 10.0, | |
| "eval_runtime": 279.5756, | |
| "eval_samples_per_second": 120.779, | |
| "eval_steps_per_second": 3.355, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.008609415867480383, | |
| "grad_norm": 1.2869155406951904, | |
| "learning_rate": 9.999231691368789e-06, | |
| "loss": 10.0078, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.008609415867480383, | |
| "eval_accuracy": 0.07677942808634446, | |
| "eval_loss": 9.9921875, | |
| "eval_runtime": 281.549, | |
| "eval_samples_per_second": 119.933, | |
| "eval_steps_per_second": 3.332, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.008663905841325197, | |
| "grad_norm": 1.2500320672988892, | |
| "learning_rate": 9.999226242371405e-06, | |
| "loss": 10.0078, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.008663905841325197, | |
| "eval_accuracy": 0.07687990967715302, | |
| "eval_loss": 9.9921875, | |
| "eval_runtime": 280.7605, | |
| "eval_samples_per_second": 120.27, | |
| "eval_steps_per_second": 3.341, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.008718395815170008, | |
| "grad_norm": 1.2038897275924683, | |
| "learning_rate": 9.99922079337402e-06, | |
| "loss": 10.0234, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.008718395815170008, | |
| "eval_accuracy": 0.07697283560815144, | |
| "eval_loss": 9.9921875, | |
| "eval_runtime": 278.5618, | |
| "eval_samples_per_second": 121.219, | |
| "eval_steps_per_second": 3.367, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.008772885789014822, | |
| "grad_norm": 1.2646440267562866, | |
| "learning_rate": 9.999215344376635e-06, | |
| "loss": 9.9922, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.008772885789014822, | |
| "eval_accuracy": 0.07707207239676907, | |
| "eval_loss": 9.984375, | |
| "eval_runtime": 279.0044, | |
| "eval_samples_per_second": 121.027, | |
| "eval_steps_per_second": 3.362, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.008827375762859633, | |
| "grad_norm": 1.2453374862670898, | |
| "learning_rate": 9.999209895379252e-06, | |
| "loss": 9.9922, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.008827375762859633, | |
| "eval_accuracy": 0.07716395616779366, | |
| "eval_loss": 9.984375, | |
| "eval_runtime": 280.4701, | |
| "eval_samples_per_second": 120.394, | |
| "eval_steps_per_second": 3.344, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.008881865736704447, | |
| "grad_norm": 1.3001788854599, | |
| "learning_rate": 9.999204446381865e-06, | |
| "loss": 9.9766, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.008881865736704447, | |
| "eval_accuracy": 0.07725401615886408, | |
| "eval_loss": 9.9765625, | |
| "eval_runtime": 280.3097, | |
| "eval_samples_per_second": 120.463, | |
| "eval_steps_per_second": 3.346, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.008936355710549258, | |
| "grad_norm": 1.2622265815734863, | |
| "learning_rate": 9.999198997384482e-06, | |
| "loss": 9.9922, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.008936355710549258, | |
| "eval_accuracy": 0.07734222342109218, | |
| "eval_loss": 9.9765625, | |
| "eval_runtime": 279.8973, | |
| "eval_samples_per_second": 120.641, | |
| "eval_steps_per_second": 3.351, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.008990845684394072, | |
| "grad_norm": 1.3013081550598145, | |
| "learning_rate": 9.999193548387097e-06, | |
| "loss": 9.9766, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.008990845684394072, | |
| "eval_accuracy": 0.07743468616988, | |
| "eval_loss": 9.96875, | |
| "eval_runtime": 280.2864, | |
| "eval_samples_per_second": 120.473, | |
| "eval_steps_per_second": 3.347, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.009045335658238883, | |
| "grad_norm": 1.258622407913208, | |
| "learning_rate": 9.999188099389712e-06, | |
| "loss": 9.9844, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.009045335658238883, | |
| "eval_accuracy": 0.07752159073214084, | |
| "eval_loss": 9.96875, | |
| "eval_runtime": 280.7557, | |
| "eval_samples_per_second": 120.272, | |
| "eval_steps_per_second": 3.341, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.009099825632083697, | |
| "grad_norm": 1.2523554563522339, | |
| "learning_rate": 9.999182650392329e-06, | |
| "loss": 9.9766, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.009099825632083697, | |
| "eval_accuracy": 0.07759642360803831, | |
| "eval_loss": 9.96875, | |
| "eval_runtime": 281.1831, | |
| "eval_samples_per_second": 120.089, | |
| "eval_steps_per_second": 3.336, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.009154315605928508, | |
| "grad_norm": 1.2290598154067993, | |
| "learning_rate": 9.999177201394944e-06, | |
| "loss": 9.9844, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.009154315605928508, | |
| "eval_accuracy": 0.07767707521045625, | |
| "eval_loss": 9.9609375, | |
| "eval_runtime": 281.1351, | |
| "eval_samples_per_second": 120.11, | |
| "eval_steps_per_second": 3.336, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.009208805579773322, | |
| "grad_norm": 1.2900922298431396, | |
| "learning_rate": 9.999171752397559e-06, | |
| "loss": 9.9609, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.009208805579773322, | |
| "eval_accuracy": 0.07775179229080108, | |
| "eval_loss": 9.9609375, | |
| "eval_runtime": 280.4797, | |
| "eval_samples_per_second": 120.39, | |
| "eval_steps_per_second": 3.344, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.009263295553618133, | |
| "grad_norm": 1.246096134185791, | |
| "learning_rate": 9.999166303400176e-06, | |
| "loss": 9.9766, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.009263295553618133, | |
| "eval_accuracy": 0.07782975164662, | |
| "eval_loss": 9.953125, | |
| "eval_runtime": 278.9976, | |
| "eval_samples_per_second": 121.03, | |
| "eval_steps_per_second": 3.362, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.009317785527462947, | |
| "grad_norm": 1.2970362901687622, | |
| "learning_rate": 9.99916085440279e-06, | |
| "loss": 9.9531, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.009317785527462947, | |
| "eval_accuracy": 0.07790701622912304, | |
| "eval_loss": 9.953125, | |
| "eval_runtime": 281.1285, | |
| "eval_samples_per_second": 120.112, | |
| "eval_steps_per_second": 3.337, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.009372275501307759, | |
| "grad_norm": 1.204124093055725, | |
| "learning_rate": 9.999155405405406e-06, | |
| "loss": 9.9922, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.009372275501307759, | |
| "eval_accuracy": 0.07798121222948096, | |
| "eval_loss": 9.953125, | |
| "eval_runtime": 280.5802, | |
| "eval_samples_per_second": 120.347, | |
| "eval_steps_per_second": 3.343, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.009426765475152572, | |
| "grad_norm": 1.29256010055542, | |
| "learning_rate": 9.999149956408023e-06, | |
| "loss": 9.9531, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.009426765475152572, | |
| "eval_accuracy": 0.07805448186541772, | |
| "eval_loss": 9.9453125, | |
| "eval_runtime": 279.9622, | |
| "eval_samples_per_second": 120.613, | |
| "eval_steps_per_second": 3.35, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.009481255448997385, | |
| "grad_norm": 1.3079378604888916, | |
| "learning_rate": 9.999144507410638e-06, | |
| "loss": 9.9375, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.009481255448997385, | |
| "eval_accuracy": 0.07812670934138066, | |
| "eval_loss": 9.9453125, | |
| "eval_runtime": 281.3535, | |
| "eval_samples_per_second": 120.016, | |
| "eval_steps_per_second": 3.334, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.009535745422842197, | |
| "grad_norm": 1.2296249866485596, | |
| "learning_rate": 9.999139058413253e-06, | |
| "loss": 9.9688, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.009535745422842197, | |
| "eval_accuracy": 0.07820545031717994, | |
| "eval_loss": 9.9375, | |
| "eval_runtime": 281.384, | |
| "eval_samples_per_second": 120.003, | |
| "eval_steps_per_second": 3.334, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.00959023539668701, | |
| "grad_norm": 1.2954541444778442, | |
| "learning_rate": 9.99913360941587e-06, | |
| "loss": 9.9453, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.00959023539668701, | |
| "eval_accuracy": 0.07826963000223398, | |
| "eval_loss": 9.9375, | |
| "eval_runtime": 281.0155, | |
| "eval_samples_per_second": 120.161, | |
| "eval_steps_per_second": 3.338, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.009644725370531822, | |
| "grad_norm": 1.2820461988449097, | |
| "learning_rate": 9.999128160418484e-06, | |
| "loss": 9.9375, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.009644725370531822, | |
| "eval_accuracy": 0.0783392520782624, | |
| "eval_loss": 9.9375, | |
| "eval_runtime": 280.6598, | |
| "eval_samples_per_second": 120.313, | |
| "eval_steps_per_second": 3.342, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.009699215344376635, | |
| "grad_norm": 1.278702974319458, | |
| "learning_rate": 9.9991227114211e-06, | |
| "loss": 9.9375, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.009699215344376635, | |
| "eval_accuracy": 0.07841200063421225, | |
| "eval_loss": 9.9296875, | |
| "eval_runtime": 279.7691, | |
| "eval_samples_per_second": 120.696, | |
| "eval_steps_per_second": 3.353, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.009753705318221447, | |
| "grad_norm": 1.253942847251892, | |
| "learning_rate": 9.999117262423716e-06, | |
| "loss": 9.9453, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.009753705318221447, | |
| "eval_accuracy": 0.07850298698970383, | |
| "eval_loss": 9.9296875, | |
| "eval_runtime": 279.9236, | |
| "eval_samples_per_second": 120.629, | |
| "eval_steps_per_second": 3.351, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.00980819529206626, | |
| "grad_norm": 1.2406857013702393, | |
| "learning_rate": 9.99911181342633e-06, | |
| "loss": 9.9453, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.00980819529206626, | |
| "eval_accuracy": 0.078591744280807, | |
| "eval_loss": 9.921875, | |
| "eval_runtime": 280.2024, | |
| "eval_samples_per_second": 120.509, | |
| "eval_steps_per_second": 3.348, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.009862685265911072, | |
| "grad_norm": 1.2425099611282349, | |
| "learning_rate": 9.999106364428946e-06, | |
| "loss": 9.9297, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.009862685265911072, | |
| "eval_accuracy": 0.07866854568109945, | |
| "eval_loss": 9.921875, | |
| "eval_runtime": 278.8945, | |
| "eval_samples_per_second": 121.074, | |
| "eval_steps_per_second": 3.363, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.009917175239755886, | |
| "grad_norm": 1.2617361545562744, | |
| "learning_rate": 9.999100915431561e-06, | |
| "loss": 9.9375, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.009917175239755886, | |
| "eval_accuracy": 0.07874769194133299, | |
| "eval_loss": 9.9140625, | |
| "eval_runtime": 281.1799, | |
| "eval_samples_per_second": 120.09, | |
| "eval_steps_per_second": 3.336, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.009971665213600697, | |
| "grad_norm": 1.2626757621765137, | |
| "learning_rate": 9.999095466434176e-06, | |
| "loss": 9.9375, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.009971665213600697, | |
| "eval_accuracy": 0.07882507231938868, | |
| "eval_loss": 9.9140625, | |
| "eval_runtime": 280.0578, | |
| "eval_samples_per_second": 120.572, | |
| "eval_steps_per_second": 3.349, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.01002615518744551, | |
| "grad_norm": 1.312477469444275, | |
| "learning_rate": 9.999090017436791e-06, | |
| "loss": 9.8984, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.01002615518744551, | |
| "eval_accuracy": 0.07890256849299702, | |
| "eval_loss": 9.9140625, | |
| "eval_runtime": 279.5807, | |
| "eval_samples_per_second": 120.777, | |
| "eval_steps_per_second": 3.355, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.010080645161290322, | |
| "grad_norm": 1.2198225259780884, | |
| "learning_rate": 9.999084568439408e-06, | |
| "loss": 9.9375, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.010080645161290322, | |
| "eval_accuracy": 0.07897815403998669, | |
| "eval_loss": 9.90625, | |
| "eval_runtime": 281.1433, | |
| "eval_samples_per_second": 120.106, | |
| "eval_steps_per_second": 3.336, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.010135135135135136, | |
| "grad_norm": 1.2455923557281494, | |
| "learning_rate": 9.999079119442023e-06, | |
| "loss": 9.9297, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.010135135135135136, | |
| "eval_accuracy": 0.07905443436029225, | |
| "eval_loss": 9.90625, | |
| "eval_runtime": 280.4858, | |
| "eval_samples_per_second": 120.388, | |
| "eval_steps_per_second": 3.344, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.010189625108979947, | |
| "grad_norm": 1.2409745454788208, | |
| "learning_rate": 9.999073670444638e-06, | |
| "loss": 9.9297, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.010189625108979947, | |
| "eval_accuracy": 0.07912625655182093, | |
| "eval_loss": 9.8984375, | |
| "eval_runtime": 280.6787, | |
| "eval_samples_per_second": 120.305, | |
| "eval_steps_per_second": 3.342, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.01024411508282476, | |
| "grad_norm": 1.2540324926376343, | |
| "learning_rate": 9.999068221447255e-06, | |
| "loss": 9.9141, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.01024411508282476, | |
| "eval_accuracy": 0.07919081257242107, | |
| "eval_loss": 9.8984375, | |
| "eval_runtime": 281.0078, | |
| "eval_samples_per_second": 120.164, | |
| "eval_steps_per_second": 3.338, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.010298605056669572, | |
| "grad_norm": 1.2172249555587769, | |
| "learning_rate": 9.99906277244987e-06, | |
| "loss": 9.9219, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.010298605056669572, | |
| "eval_accuracy": 0.07925064992425089, | |
| "eval_loss": 9.8984375, | |
| "eval_runtime": 280.6094, | |
| "eval_samples_per_second": 120.335, | |
| "eval_steps_per_second": 3.343, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.010353095030514386, | |
| "grad_norm": 1.2848864793777466, | |
| "learning_rate": 9.999057323452485e-06, | |
| "loss": 9.8984, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.010353095030514386, | |
| "eval_accuracy": 0.07933312530662301, | |
| "eval_loss": 9.890625, | |
| "eval_runtime": 280.1069, | |
| "eval_samples_per_second": 120.55, | |
| "eval_steps_per_second": 3.349, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.010407585004359197, | |
| "grad_norm": 1.3001790046691895, | |
| "learning_rate": 9.999051874455102e-06, | |
| "loss": 9.8828, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.010407585004359197, | |
| "eval_accuracy": 0.07942619598206223, | |
| "eval_loss": 9.890625, | |
| "eval_runtime": 279.216, | |
| "eval_samples_per_second": 120.935, | |
| "eval_steps_per_second": 3.359, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.010462074978204011, | |
| "grad_norm": 1.2808548212051392, | |
| "learning_rate": 9.999046425457717e-06, | |
| "loss": 9.8984, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.010462074978204011, | |
| "eval_accuracy": 0.07953382794824668, | |
| "eval_loss": 9.8828125, | |
| "eval_runtime": 279.7965, | |
| "eval_samples_per_second": 120.684, | |
| "eval_steps_per_second": 3.352, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.010516564952048823, | |
| "grad_norm": 1.2758278846740723, | |
| "learning_rate": 9.999040976460332e-06, | |
| "loss": 9.8906, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.010516564952048823, | |
| "eval_accuracy": 0.07961514537509233, | |
| "eval_loss": 9.8828125, | |
| "eval_runtime": 280.4068, | |
| "eval_samples_per_second": 120.421, | |
| "eval_steps_per_second": 3.345, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.010571054925893636, | |
| "grad_norm": 1.2733352184295654, | |
| "learning_rate": 9.999035527462949e-06, | |
| "loss": 9.9062, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.010571054925893636, | |
| "eval_accuracy": 0.07969660754637879, | |
| "eval_loss": 9.8828125, | |
| "eval_runtime": 280.0801, | |
| "eval_samples_per_second": 120.562, | |
| "eval_steps_per_second": 3.349, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.010625544899738448, | |
| "grad_norm": 1.3207552433013916, | |
| "learning_rate": 9.999030078465564e-06, | |
| "loss": 9.875, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.010625544899738448, | |
| "eval_accuracy": 0.07977876449098113, | |
| "eval_loss": 9.875, | |
| "eval_runtime": 279.7352, | |
| "eval_samples_per_second": 120.711, | |
| "eval_steps_per_second": 3.353, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.010680034873583261, | |
| "grad_norm": 1.3311365842819214, | |
| "learning_rate": 9.999024629468179e-06, | |
| "loss": 9.8594, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.010680034873583261, | |
| "eval_accuracy": 0.07984216255605482, | |
| "eval_loss": 9.875, | |
| "eval_runtime": 280.0513, | |
| "eval_samples_per_second": 120.574, | |
| "eval_steps_per_second": 3.349, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.010734524847428073, | |
| "grad_norm": 1.2795319557189941, | |
| "learning_rate": 9.999019180470794e-06, | |
| "loss": 9.8828, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.010734524847428073, | |
| "eval_accuracy": 0.07991207412096483, | |
| "eval_loss": 9.875, | |
| "eval_runtime": 279.4752, | |
| "eval_samples_per_second": 120.823, | |
| "eval_steps_per_second": 3.356, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.010789014821272886, | |
| "grad_norm": 1.2289413213729858, | |
| "learning_rate": 9.999013731473409e-06, | |
| "loss": 9.8984, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.010789014821272886, | |
| "eval_accuracy": 0.07998430159692778, | |
| "eval_loss": 9.8671875, | |
| "eval_runtime": 279.5837, | |
| "eval_samples_per_second": 120.776, | |
| "eval_steps_per_second": 3.355, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.010843504795117698, | |
| "grad_norm": 1.233830451965332, | |
| "learning_rate": 9.999008282476025e-06, | |
| "loss": 9.8906, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.010843504795117698, | |
| "eval_accuracy": 0.0800536920818509, | |
| "eval_loss": 9.8671875, | |
| "eval_runtime": 279.9047, | |
| "eval_samples_per_second": 120.637, | |
| "eval_steps_per_second": 3.351, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.010897994768962511, | |
| "grad_norm": 1.2242302894592285, | |
| "learning_rate": 9.99900283347864e-06, | |
| "loss": 9.9062, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.010897994768962511, | |
| "eval_accuracy": 0.08014829704836268, | |
| "eval_loss": 9.859375, | |
| "eval_runtime": 278.8987, | |
| "eval_samples_per_second": 121.073, | |
| "eval_steps_per_second": 3.363, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.010952484742807323, | |
| "grad_norm": 1.2602059841156006, | |
| "learning_rate": 9.998997384481255e-06, | |
| "loss": 9.8672, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.010952484742807323, | |
| "eval_accuracy": 0.08021710855552257, | |
| "eval_loss": 9.859375, | |
| "eval_runtime": 279.1708, | |
| "eval_samples_per_second": 120.955, | |
| "eval_steps_per_second": 3.36, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.011006974716652136, | |
| "grad_norm": 1.2747395038604736, | |
| "learning_rate": 9.998991935483872e-06, | |
| "loss": 9.8672, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.011006974716652136, | |
| "eval_accuracy": 0.08028279358276101, | |
| "eval_loss": 9.859375, | |
| "eval_runtime": 279.6011, | |
| "eval_samples_per_second": 120.768, | |
| "eval_steps_per_second": 3.355, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.011061464690496948, | |
| "grad_norm": 1.2887182235717773, | |
| "learning_rate": 9.998986486486487e-06, | |
| "loss": 9.8906, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.011061464690496948, | |
| "eval_accuracy": 0.08035612111647408, | |
| "eval_loss": 9.8515625, | |
| "eval_runtime": 278.7511, | |
| "eval_samples_per_second": 121.137, | |
| "eval_steps_per_second": 3.365, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.011115954664341761, | |
| "grad_norm": 1.2620630264282227, | |
| "learning_rate": 9.998981037489102e-06, | |
| "loss": 9.8828, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.011115954664341761, | |
| "eval_accuracy": 0.08042151665483091, | |
| "eval_loss": 9.8515625, | |
| "eval_runtime": 280.8141, | |
| "eval_samples_per_second": 120.247, | |
| "eval_steps_per_second": 3.34, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.011170444638186573, | |
| "grad_norm": 1.204312801361084, | |
| "learning_rate": 9.998975588491719e-06, | |
| "loss": 9.8906, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.011170444638186573, | |
| "eval_accuracy": 0.08048413309992423, | |
| "eval_loss": 9.84375, | |
| "eval_runtime": 278.2837, | |
| "eval_samples_per_second": 121.34, | |
| "eval_steps_per_second": 3.371, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.011224934612031386, | |
| "grad_norm": 1.2498817443847656, | |
| "learning_rate": 9.998970139494334e-06, | |
| "loss": 9.8828, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.011224934612031386, | |
| "eval_accuracy": 0.08053965706741799, | |
| "eval_loss": 9.84375, | |
| "eval_runtime": 280.6201, | |
| "eval_samples_per_second": 120.33, | |
| "eval_steps_per_second": 3.343, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.011279424585876198, | |
| "grad_norm": 1.2628120183944702, | |
| "learning_rate": 9.998964690496949e-06, | |
| "loss": 9.8594, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.011279424585876198, | |
| "eval_accuracy": 0.08057526419985664, | |
| "eval_loss": 9.84375, | |
| "eval_runtime": 281.1793, | |
| "eval_samples_per_second": 120.091, | |
| "eval_steps_per_second": 3.336, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.011333914559721011, | |
| "grad_norm": 1.286372184753418, | |
| "learning_rate": 9.998959241499566e-06, | |
| "loss": 9.875, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.011333914559721011, | |
| "eval_accuracy": 0.0806213797786979, | |
| "eval_loss": 9.8359375, | |
| "eval_runtime": 279.1646, | |
| "eval_samples_per_second": 120.957, | |
| "eval_steps_per_second": 3.36, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.011388404533565825, | |
| "grad_norm": 1.2716000080108643, | |
| "learning_rate": 9.99895379250218e-06, | |
| "loss": 9.8594, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.011388404533565825, | |
| "eval_accuracy": 0.0807168821607427, | |
| "eval_loss": 9.8359375, | |
| "eval_runtime": 279.4887, | |
| "eval_samples_per_second": 120.817, | |
| "eval_steps_per_second": 3.356, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.011442894507410636, | |
| "grad_norm": 1.2634248733520508, | |
| "learning_rate": 9.998948343504796e-06, | |
| "loss": 9.8516, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.011442894507410636, | |
| "eval_accuracy": 0.08081287667388623, | |
| "eval_loss": 9.828125, | |
| "eval_runtime": 280.2441, | |
| "eval_samples_per_second": 120.491, | |
| "eval_steps_per_second": 3.347, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01149738448125545, | |
| "grad_norm": 1.2706140279769897, | |
| "learning_rate": 9.998942894507413e-06, | |
| "loss": 9.8359, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.01149738448125545, | |
| "eval_accuracy": 0.08091327141803031, | |
| "eval_loss": 9.828125, | |
| "eval_runtime": 279.7835, | |
| "eval_samples_per_second": 120.69, | |
| "eval_steps_per_second": 3.353, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.011551874455100261, | |
| "grad_norm": 1.3309648036956787, | |
| "learning_rate": 9.998937445510028e-06, | |
| "loss": 9.8281, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.011551874455100261, | |
| "eval_accuracy": 0.08096497413228675, | |
| "eval_loss": 9.828125, | |
| "eval_runtime": 279.8407, | |
| "eval_samples_per_second": 120.665, | |
| "eval_steps_per_second": 3.352, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.011606364428945075, | |
| "grad_norm": 1.228298544883728, | |
| "learning_rate": 9.998931996512643e-06, | |
| "loss": 9.8516, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.011606364428945075, | |
| "eval_accuracy": 0.08100848431119348, | |
| "eval_loss": 9.8203125, | |
| "eval_runtime": 278.724, | |
| "eval_samples_per_second": 121.149, | |
| "eval_steps_per_second": 3.365, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.011660854402789887, | |
| "grad_norm": 1.2184377908706665, | |
| "learning_rate": 9.998926547515258e-06, | |
| "loss": 9.8516, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.011660854402789887, | |
| "eval_accuracy": 0.0810596080476867, | |
| "eval_loss": 9.8203125, | |
| "eval_runtime": 279.3251, | |
| "eval_samples_per_second": 120.888, | |
| "eval_steps_per_second": 3.358, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.0117153443766347, | |
| "grad_norm": 1.311761498451233, | |
| "learning_rate": 9.998921098517873e-06, | |
| "loss": 9.8281, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.0117153443766347, | |
| "eval_accuracy": 0.08114680209882913, | |
| "eval_loss": 9.8203125, | |
| "eval_runtime": 279.8598, | |
| "eval_samples_per_second": 120.657, | |
| "eval_steps_per_second": 3.352, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.011769834350479512, | |
| "grad_norm": 1.2210040092468262, | |
| "learning_rate": 9.99891564952049e-06, | |
| "loss": 9.8438, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.011769834350479512, | |
| "eval_accuracy": 0.08124644417188101, | |
| "eval_loss": 9.8125, | |
| "eval_runtime": 280.305, | |
| "eval_samples_per_second": 120.465, | |
| "eval_steps_per_second": 3.346, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.011824324324324325, | |
| "grad_norm": 1.2239922285079956, | |
| "learning_rate": 9.998910200523105e-06, | |
| "loss": 9.8359, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.011824324324324325, | |
| "eval_accuracy": 0.08132301398106818, | |
| "eval_loss": 9.8125, | |
| "eval_runtime": 280.4951, | |
| "eval_samples_per_second": 120.384, | |
| "eval_steps_per_second": 3.344, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.011878814298169137, | |
| "grad_norm": 1.26374089717865, | |
| "learning_rate": 9.99890475152572e-06, | |
| "loss": 9.8281, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.011878814298169137, | |
| "eval_accuracy": 0.08139370716595856, | |
| "eval_loss": 9.8046875, | |
| "eval_runtime": 280.3905, | |
| "eval_samples_per_second": 120.428, | |
| "eval_steps_per_second": 3.345, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.01193330427201395, | |
| "grad_norm": 1.255954384803772, | |
| "learning_rate": 9.998899302528335e-06, | |
| "loss": 9.8281, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.01193330427201395, | |
| "eval_accuracy": 0.08145580253106498, | |
| "eval_loss": 9.8046875, | |
| "eval_runtime": 278.85, | |
| "eval_samples_per_second": 121.094, | |
| "eval_steps_per_second": 3.364, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.011987794245858762, | |
| "grad_norm": 1.2596890926361084, | |
| "learning_rate": 9.998893853530951e-06, | |
| "loss": 9.8281, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.011987794245858762, | |
| "eval_accuracy": 0.08151057382746654, | |
| "eval_loss": 9.8046875, | |
| "eval_runtime": 280.1905, | |
| "eval_samples_per_second": 120.514, | |
| "eval_steps_per_second": 3.348, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.012042284219703575, | |
| "grad_norm": 1.3286200761795044, | |
| "learning_rate": 9.998888404533566e-06, | |
| "loss": 9.7969, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.012042284219703575, | |
| "eval_accuracy": 0.08155735523073553, | |
| "eval_loss": 9.796875, | |
| "eval_runtime": 279.7838, | |
| "eval_samples_per_second": 120.69, | |
| "eval_steps_per_second": 3.353, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.012096774193548387, | |
| "grad_norm": 1.2406117916107178, | |
| "learning_rate": 9.998882955536181e-06, | |
| "loss": 9.8281, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.012096774193548387, | |
| "eval_accuracy": 0.08160451296955061, | |
| "eval_loss": 9.796875, | |
| "eval_runtime": 279.2237, | |
| "eval_samples_per_second": 120.932, | |
| "eval_steps_per_second": 3.359, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.0121512641673932, | |
| "grad_norm": 1.2828328609466553, | |
| "learning_rate": 9.998877506538798e-06, | |
| "loss": 9.8047, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.0121512641673932, | |
| "eval_accuracy": 0.08167708783217148, | |
| "eval_loss": 9.7890625, | |
| "eval_runtime": 280.1502, | |
| "eval_samples_per_second": 120.532, | |
| "eval_steps_per_second": 3.348, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.012205754141238012, | |
| "grad_norm": 1.3072834014892578, | |
| "learning_rate": 9.998872057541413e-06, | |
| "loss": 9.8047, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.012205754141238012, | |
| "eval_accuracy": 0.08175794207680655, | |
| "eval_loss": 9.7890625, | |
| "eval_runtime": 279.8278, | |
| "eval_samples_per_second": 120.671, | |
| "eval_steps_per_second": 3.352, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.012260244115082825, | |
| "grad_norm": 1.2602524757385254, | |
| "learning_rate": 9.998866608544028e-06, | |
| "loss": 9.8047, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.012260244115082825, | |
| "eval_accuracy": 0.0818193426685971, | |
| "eval_loss": 9.7890625, | |
| "eval_runtime": 279.4782, | |
| "eval_samples_per_second": 120.822, | |
| "eval_steps_per_second": 3.356, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.012314734088927637, | |
| "grad_norm": 1.2501016855239868, | |
| "learning_rate": 9.998861159546645e-06, | |
| "loss": 9.8047, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.012314734088927637, | |
| "eval_accuracy": 0.08185301022552892, | |
| "eval_loss": 9.78125, | |
| "eval_runtime": 279.6131, | |
| "eval_samples_per_second": 120.763, | |
| "eval_steps_per_second": 3.355, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.01236922406277245, | |
| "grad_norm": 1.2058792114257812, | |
| "learning_rate": 9.99885571054926e-06, | |
| "loss": 9.8281, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.01236922406277245, | |
| "eval_accuracy": 0.08187451924943291, | |
| "eval_loss": 9.78125, | |
| "eval_runtime": 279.6288, | |
| "eval_samples_per_second": 120.757, | |
| "eval_steps_per_second": 3.354, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.012423714036617262, | |
| "grad_norm": 1.2502729892730713, | |
| "learning_rate": 9.998850261551875e-06, | |
| "loss": 9.7812, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.012423714036617262, | |
| "eval_accuracy": 0.08191142908183882, | |
| "eval_loss": 9.78125, | |
| "eval_runtime": 279.6067, | |
| "eval_samples_per_second": 120.766, | |
| "eval_steps_per_second": 3.355, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.012478204010462075, | |
| "grad_norm": 1.2606781721115112, | |
| "learning_rate": 9.998844812554492e-06, | |
| "loss": 9.7891, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.012478204010462075, | |
| "eval_accuracy": 0.08197398762915582, | |
| "eval_loss": 9.7734375, | |
| "eval_runtime": 279.4306, | |
| "eval_samples_per_second": 120.842, | |
| "eval_steps_per_second": 3.357, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.012532693984306887, | |
| "grad_norm": 1.248340368270874, | |
| "learning_rate": 9.998839363557107e-06, | |
| "loss": 9.7969, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.012532693984306887, | |
| "eval_accuracy": 0.08206019741810078, | |
| "eval_loss": 9.7734375, | |
| "eval_runtime": 278.547, | |
| "eval_samples_per_second": 121.226, | |
| "eval_steps_per_second": 3.367, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0125871839581517, | |
| "grad_norm": 1.3996437788009644, | |
| "learning_rate": 9.998833914559722e-06, | |
| "loss": 9.7578, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.0125871839581517, | |
| "eval_accuracy": 0.08214620456482859, | |
| "eval_loss": 9.765625, | |
| "eval_runtime": 279.48, | |
| "eval_samples_per_second": 120.821, | |
| "eval_steps_per_second": 3.356, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.012641673931996512, | |
| "grad_norm": 1.2275718450546265, | |
| "learning_rate": 9.998828465562337e-06, | |
| "loss": 9.8125, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.012641673931996512, | |
| "eval_accuracy": 0.08221081848320505, | |
| "eval_loss": 9.765625, | |
| "eval_runtime": 280.1352, | |
| "eval_samples_per_second": 120.538, | |
| "eval_steps_per_second": 3.348, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.012696163905841325, | |
| "grad_norm": 1.294257640838623, | |
| "learning_rate": 9.998823016564952e-06, | |
| "loss": 9.7734, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.012696163905841325, | |
| "eval_accuracy": 0.0822595105130927, | |
| "eval_loss": 9.765625, | |
| "eval_runtime": 278.3308, | |
| "eval_samples_per_second": 121.32, | |
| "eval_steps_per_second": 3.37, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.012750653879686137, | |
| "grad_norm": 1.302538275718689, | |
| "learning_rate": 9.998817567567569e-06, | |
| "loss": 9.7656, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.012750653879686137, | |
| "eval_accuracy": 0.0823088394185199, | |
| "eval_loss": 9.7578125, | |
| "eval_runtime": 279.0657, | |
| "eval_samples_per_second": 121.0, | |
| "eval_steps_per_second": 3.361, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.01280514385353095, | |
| "grad_norm": 1.2675853967666626, | |
| "learning_rate": 9.998812118570184e-06, | |
| "loss": 9.7578, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.01280514385353095, | |
| "eval_accuracy": 0.0823553023840191, | |
| "eval_loss": 9.7578125, | |
| "eval_runtime": 279.2742, | |
| "eval_samples_per_second": 120.91, | |
| "eval_steps_per_second": 3.359, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.012859633827375762, | |
| "grad_norm": 1.2685391902923584, | |
| "learning_rate": 9.998806669572799e-06, | |
| "loss": 9.7891, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.012859633827375762, | |
| "eval_accuracy": 0.08240431285167651, | |
| "eval_loss": 9.7578125, | |
| "eval_runtime": 279.3255, | |
| "eval_samples_per_second": 120.888, | |
| "eval_steps_per_second": 3.358, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.012914123801220576, | |
| "grad_norm": 1.279767632484436, | |
| "learning_rate": 9.998801220575415e-06, | |
| "loss": 9.7812, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.012914123801220576, | |
| "eval_accuracy": 0.08243551975311462, | |
| "eval_loss": 9.75, | |
| "eval_runtime": 278.6385, | |
| "eval_samples_per_second": 121.186, | |
| "eval_steps_per_second": 3.366, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.012968613775065387, | |
| "grad_norm": 1.2205240726470947, | |
| "learning_rate": 9.99879577157803e-06, | |
| "loss": 9.7656, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.012968613775065387, | |
| "eval_accuracy": 0.08245219431269564, | |
| "eval_loss": 9.75, | |
| "eval_runtime": 278.8375, | |
| "eval_samples_per_second": 121.099, | |
| "eval_steps_per_second": 3.364, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.0130231037489102, | |
| "grad_norm": 1.1911712884902954, | |
| "learning_rate": 9.998790322580645e-06, | |
| "loss": 9.7969, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.0130231037489102, | |
| "eval_accuracy": 0.08246684245010535, | |
| "eval_loss": 9.75, | |
| "eval_runtime": 279.7565, | |
| "eval_samples_per_second": 120.701, | |
| "eval_steps_per_second": 3.353, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.013077593722755012, | |
| "grad_norm": 1.250552773475647, | |
| "learning_rate": 9.998784873583262e-06, | |
| "loss": 9.75, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.013077593722755012, | |
| "eval_accuracy": 0.0824862092562854, | |
| "eval_loss": 9.7421875, | |
| "eval_runtime": 279.3878, | |
| "eval_samples_per_second": 120.861, | |
| "eval_steps_per_second": 3.357, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.013132083696599826, | |
| "grad_norm": 1.1946778297424316, | |
| "learning_rate": 9.998779424585877e-06, | |
| "loss": 9.7734, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.013132083696599826, | |
| "eval_accuracy": 0.08250629978466949, | |
| "eval_loss": 9.7421875, | |
| "eval_runtime": 278.1923, | |
| "eval_samples_per_second": 121.38, | |
| "eval_steps_per_second": 3.372, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.013186573670444637, | |
| "grad_norm": 1.2602076530456543, | |
| "learning_rate": 9.998773975588492e-06, | |
| "loss": 9.7578, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.013186573670444637, | |
| "eval_accuracy": 0.08251411598447309, | |
| "eval_loss": 9.734375, | |
| "eval_runtime": 278.443, | |
| "eval_samples_per_second": 121.271, | |
| "eval_steps_per_second": 3.369, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.01324106364428945, | |
| "grad_norm": 1.2365894317626953, | |
| "learning_rate": 9.998768526591109e-06, | |
| "loss": 9.7656, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.01324106364428945, | |
| "eval_accuracy": 0.08253744878833126, | |
| "eval_loss": 9.734375, | |
| "eval_runtime": 278.0592, | |
| "eval_samples_per_second": 121.438, | |
| "eval_steps_per_second": 3.373, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.013295553618134264, | |
| "grad_norm": 1.2928210496902466, | |
| "learning_rate": 9.998763077593724e-06, | |
| "loss": 9.7266, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.013295553618134264, | |
| "eval_accuracy": 0.0825691478208681, | |
| "eval_loss": 9.734375, | |
| "eval_runtime": 277.8043, | |
| "eval_samples_per_second": 121.55, | |
| "eval_steps_per_second": 3.376, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.013350043591979076, | |
| "grad_norm": 1.2674510478973389, | |
| "learning_rate": 9.998757628596339e-06, | |
| "loss": 9.75, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.013350043591979076, | |
| "eval_accuracy": 0.08259832830013489, | |
| "eval_loss": 9.7265625, | |
| "eval_runtime": 278.1561, | |
| "eval_samples_per_second": 121.396, | |
| "eval_steps_per_second": 3.372, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.01340453356582389, | |
| "grad_norm": 1.2813974618911743, | |
| "learning_rate": 9.998752179598956e-06, | |
| "loss": 9.7422, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.01340453356582389, | |
| "eval_accuracy": 0.08266126318299799, | |
| "eval_loss": 9.7265625, | |
| "eval_runtime": 280.0345, | |
| "eval_samples_per_second": 120.582, | |
| "eval_steps_per_second": 3.35, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.0134590235396687, | |
| "grad_norm": 1.2468206882476807, | |
| "learning_rate": 9.99874673060157e-06, | |
| "loss": 9.75, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.0134590235396687, | |
| "eval_accuracy": 0.08272399542364396, | |
| "eval_loss": 9.7265625, | |
| "eval_runtime": 277.7706, | |
| "eval_samples_per_second": 121.564, | |
| "eval_steps_per_second": 3.377, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 1.1757469177246094, | |
| "learning_rate": 9.998741281604186e-06, | |
| "loss": 9.7656, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "eval_accuracy": 0.08277827458894678, | |
| "eval_loss": 9.71875, | |
| "eval_runtime": 278.8949, | |
| "eval_samples_per_second": 121.074, | |
| "eval_steps_per_second": 3.363, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.013568003487358326, | |
| "grad_norm": 1.2581287622451782, | |
| "learning_rate": 9.998735832606801e-06, | |
| "loss": 9.7266, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.013568003487358326, | |
| "eval_accuracy": 0.08281637132576732, | |
| "eval_loss": 9.71875, | |
| "eval_runtime": 277.5935, | |
| "eval_samples_per_second": 121.642, | |
| "eval_steps_per_second": 3.379, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.01362249346120314, | |
| "grad_norm": 1.2253607511520386, | |
| "learning_rate": 9.998730383609416e-06, | |
| "loss": 9.75, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01362249346120314, | |
| "eval_accuracy": 0.08284589919169204, | |
| "eval_loss": 9.7109375, | |
| "eval_runtime": 277.5385, | |
| "eval_samples_per_second": 121.666, | |
| "eval_steps_per_second": 3.38, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.013676983435047951, | |
| "grad_norm": 1.2590970993041992, | |
| "learning_rate": 9.998724934612033e-06, | |
| "loss": 9.7266, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.013676983435047951, | |
| "eval_accuracy": 0.08286613446451693, | |
| "eval_loss": 9.7109375, | |
| "eval_runtime": 278.6492, | |
| "eval_samples_per_second": 121.181, | |
| "eval_steps_per_second": 3.366, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.013731473408892764, | |
| "grad_norm": 1.2588908672332764, | |
| "learning_rate": 9.998719485614648e-06, | |
| "loss": 9.7266, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.013731473408892764, | |
| "eval_accuracy": 0.08288451700849948, | |
| "eval_loss": 9.7109375, | |
| "eval_runtime": 278.1724, | |
| "eval_samples_per_second": 121.389, | |
| "eval_steps_per_second": 3.372, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.013785963382737576, | |
| "grad_norm": 1.2583962678909302, | |
| "learning_rate": 9.998714036617263e-06, | |
| "loss": 9.7266, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.013785963382737576, | |
| "eval_accuracy": 0.0829049549235415, | |
| "eval_loss": 9.703125, | |
| "eval_runtime": 277.9162, | |
| "eval_samples_per_second": 121.501, | |
| "eval_steps_per_second": 3.375, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.01384045335658239, | |
| "grad_norm": 1.2444450855255127, | |
| "learning_rate": 9.998708587619878e-06, | |
| "loss": 9.7266, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.01384045335658239, | |
| "eval_accuracy": 0.08292394539417544, | |
| "eval_loss": 9.703125, | |
| "eval_runtime": 279.5035, | |
| "eval_samples_per_second": 120.811, | |
| "eval_steps_per_second": 3.356, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.013894943330427201, | |
| "grad_norm": 1.201521396636963, | |
| "learning_rate": 9.998703138622494e-06, | |
| "loss": 9.7344, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.013894943330427201, | |
| "eval_accuracy": 0.08293364327170955, | |
| "eval_loss": 9.703125, | |
| "eval_runtime": 278.5449, | |
| "eval_samples_per_second": 121.226, | |
| "eval_steps_per_second": 3.368, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.013949433304272014, | |
| "grad_norm": 1.2879900932312012, | |
| "learning_rate": 9.99869768962511e-06, | |
| "loss": 9.7109, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.013949433304272014, | |
| "eval_accuracy": 0.08292825877851151, | |
| "eval_loss": 9.6953125, | |
| "eval_runtime": 278.9219, | |
| "eval_samples_per_second": 121.063, | |
| "eval_steps_per_second": 3.363, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.014003923278116826, | |
| "grad_norm": 1.2371270656585693, | |
| "learning_rate": 9.998692240627725e-06, | |
| "loss": 9.7109, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.014003923278116826, | |
| "eval_accuracy": 0.08293071943400523, | |
| "eval_loss": 9.6953125, | |
| "eval_runtime": 280.4149, | |
| "eval_samples_per_second": 120.418, | |
| "eval_steps_per_second": 3.345, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.01405841325196164, | |
| "grad_norm": 1.2438043355941772, | |
| "learning_rate": 9.998686791630341e-06, | |
| "loss": 9.7109, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.01405841325196164, | |
| "eval_accuracy": 0.08297243478184596, | |
| "eval_loss": 9.6953125, | |
| "eval_runtime": 279.9479, | |
| "eval_samples_per_second": 120.619, | |
| "eval_steps_per_second": 3.351, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.014112903225806451, | |
| "grad_norm": 1.2312678098678589, | |
| "learning_rate": 9.998681342632956e-06, | |
| "loss": 9.7031, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.014112903225806451, | |
| "eval_accuracy": 0.08300974989868613, | |
| "eval_loss": 9.6875, | |
| "eval_runtime": 278.9806, | |
| "eval_samples_per_second": 121.037, | |
| "eval_steps_per_second": 3.362, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.014167393199651265, | |
| "grad_norm": 1.289109706878662, | |
| "learning_rate": 9.998675893635571e-06, | |
| "loss": 9.7109, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.014167393199651265, | |
| "eval_accuracy": 0.0830896198811237, | |
| "eval_loss": 9.6875, | |
| "eval_runtime": 280.8942, | |
| "eval_samples_per_second": 120.213, | |
| "eval_steps_per_second": 3.339, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.014221883173496076, | |
| "grad_norm": 1.2733935117721558, | |
| "learning_rate": 9.998670444638188e-06, | |
| "loss": 9.6953, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.014221883173496076, | |
| "eval_accuracy": 0.08316147102154055, | |
| "eval_loss": 9.6796875, | |
| "eval_runtime": 279.4498, | |
| "eval_samples_per_second": 120.834, | |
| "eval_steps_per_second": 3.357, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.01427637314734089, | |
| "grad_norm": 1.2618088722229004, | |
| "learning_rate": 9.998664995640803e-06, | |
| "loss": 9.7031, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.01427637314734089, | |
| "eval_accuracy": 0.08321233421804031, | |
| "eval_loss": 9.6796875, | |
| "eval_runtime": 278.1291, | |
| "eval_samples_per_second": 121.408, | |
| "eval_steps_per_second": 3.373, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.014330863121185701, | |
| "grad_norm": 1.2773399353027344, | |
| "learning_rate": 9.998659546643418e-06, | |
| "loss": 9.6953, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.014330863121185701, | |
| "eval_accuracy": 0.08324872297045931, | |
| "eval_loss": 9.6796875, | |
| "eval_runtime": 278.6034, | |
| "eval_samples_per_second": 121.201, | |
| "eval_steps_per_second": 3.367, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.014385353095030515, | |
| "grad_norm": 1.246199131011963, | |
| "learning_rate": 9.998654097646035e-06, | |
| "loss": 9.6875, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.014385353095030515, | |
| "eval_accuracy": 0.08326855295884994, | |
| "eval_loss": 9.671875, | |
| "eval_runtime": 278.4105, | |
| "eval_samples_per_second": 121.285, | |
| "eval_steps_per_second": 3.369, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.014439843068875326, | |
| "grad_norm": 1.2552728652954102, | |
| "learning_rate": 9.998648648648648e-06, | |
| "loss": 9.6719, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.014439843068875326, | |
| "eval_accuracy": 0.08325928931463826, | |
| "eval_loss": 9.671875, | |
| "eval_runtime": 279.4834, | |
| "eval_samples_per_second": 120.819, | |
| "eval_steps_per_second": 3.356, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.01449433304272014, | |
| "grad_norm": 1.2612943649291992, | |
| "learning_rate": 9.998643199651265e-06, | |
| "loss": 9.6797, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.01449433304272014, | |
| "eval_accuracy": 0.08324947564155151, | |
| "eval_loss": 9.671875, | |
| "eval_runtime": 277.8081, | |
| "eval_samples_per_second": 121.548, | |
| "eval_steps_per_second": 3.376, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.014548823016564951, | |
| "grad_norm": 1.1741077899932861, | |
| "learning_rate": 9.99863775065388e-06, | |
| "loss": 9.7188, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.014548823016564951, | |
| "eval_accuracy": 0.08325022831264371, | |
| "eval_loss": 9.6640625, | |
| "eval_runtime": 278.7089, | |
| "eval_samples_per_second": 121.155, | |
| "eval_steps_per_second": 3.366, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.014603312990409765, | |
| "grad_norm": 1.2685978412628174, | |
| "learning_rate": 9.998632301656495e-06, | |
| "loss": 9.6953, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.014603312990409765, | |
| "eval_accuracy": 0.08326976881215271, | |
| "eval_loss": 9.6640625, | |
| "eval_runtime": 278.6178, | |
| "eval_samples_per_second": 121.195, | |
| "eval_steps_per_second": 3.367, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.014657802964254577, | |
| "grad_norm": 1.329729437828064, | |
| "learning_rate": 9.998626852659112e-06, | |
| "loss": 9.6797, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.014657802964254577, | |
| "eval_accuracy": 0.08330664969567048, | |
| "eval_loss": 9.6640625, | |
| "eval_runtime": 276.7799, | |
| "eval_samples_per_second": 121.999, | |
| "eval_steps_per_second": 3.389, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.01471229293809939, | |
| "grad_norm": 1.2404329776763916, | |
| "learning_rate": 9.998621403661727e-06, | |
| "loss": 9.6719, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01471229293809939, | |
| "eval_accuracy": 0.08336324477202621, | |
| "eval_loss": 9.65625, | |
| "eval_runtime": 277.6213, | |
| "eval_samples_per_second": 121.63, | |
| "eval_steps_per_second": 3.379, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.014766782911944202, | |
| "grad_norm": 1.2414337396621704, | |
| "learning_rate": 9.998615954664342e-06, | |
| "loss": 9.6875, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.014766782911944202, | |
| "eval_accuracy": 0.0834355011968773, | |
| "eval_loss": 9.65625, | |
| "eval_runtime": 278.0197, | |
| "eval_samples_per_second": 121.455, | |
| "eval_steps_per_second": 3.374, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.014821272885789015, | |
| "grad_norm": 1.241061806678772, | |
| "learning_rate": 9.998610505666959e-06, | |
| "loss": 9.6641, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.014821272885789015, | |
| "eval_accuracy": 0.083517542345927, | |
| "eval_loss": 9.6484375, | |
| "eval_runtime": 278.7783, | |
| "eval_samples_per_second": 121.125, | |
| "eval_steps_per_second": 3.365, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.014875762859633827, | |
| "grad_norm": 1.2449415922164917, | |
| "learning_rate": 9.998605056669574e-06, | |
| "loss": 9.6719, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.014875762859633827, | |
| "eval_accuracy": 0.08358869871302796, | |
| "eval_loss": 9.6484375, | |
| "eval_runtime": 278.069, | |
| "eval_samples_per_second": 121.434, | |
| "eval_steps_per_second": 3.373, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.01493025283347864, | |
| "grad_norm": 1.2785589694976807, | |
| "learning_rate": 9.998599607672189e-06, | |
| "loss": 9.6719, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.01493025283347864, | |
| "eval_accuracy": 0.08364344106054136, | |
| "eval_loss": 9.6484375, | |
| "eval_runtime": 278.0063, | |
| "eval_samples_per_second": 121.461, | |
| "eval_steps_per_second": 3.374, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.014984742807323452, | |
| "grad_norm": 1.2922983169555664, | |
| "learning_rate": 9.998594158674805e-06, | |
| "loss": 9.6406, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.014984742807323452, | |
| "eval_accuracy": 0.08369166990821841, | |
| "eval_loss": 9.640625, | |
| "eval_runtime": 278.9804, | |
| "eval_samples_per_second": 121.037, | |
| "eval_steps_per_second": 3.362, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.015039232781168265, | |
| "grad_norm": 1.2422248125076294, | |
| "learning_rate": 9.99858870967742e-06, | |
| "loss": 9.6641, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.015039232781168265, | |
| "eval_accuracy": 0.08373764074261889, | |
| "eval_loss": 9.640625, | |
| "eval_runtime": 279.0599, | |
| "eval_samples_per_second": 121.003, | |
| "eval_steps_per_second": 3.361, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.015093722755013077, | |
| "grad_norm": 1.3546416759490967, | |
| "learning_rate": 9.998583260680035e-06, | |
| "loss": 9.6328, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.015093722755013077, | |
| "eval_accuracy": 0.08375952610206898, | |
| "eval_loss": 9.640625, | |
| "eval_runtime": 279.3312, | |
| "eval_samples_per_second": 120.885, | |
| "eval_steps_per_second": 3.358, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.01514821272885789, | |
| "grad_norm": 1.3069231510162354, | |
| "learning_rate": 9.998577811682652e-06, | |
| "loss": 9.6328, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.01514821272885789, | |
| "eval_accuracy": 0.08376647383522773, | |
| "eval_loss": 9.6328125, | |
| "eval_runtime": 277.9079, | |
| "eval_samples_per_second": 121.504, | |
| "eval_steps_per_second": 3.375, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.015202702702702704, | |
| "grad_norm": 1.2460886240005493, | |
| "learning_rate": 9.998572362685267e-06, | |
| "loss": 9.6484, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.015202702702702704, | |
| "eval_accuracy": 0.08376496849304334, | |
| "eval_loss": 9.6328125, | |
| "eval_runtime": 277.6965, | |
| "eval_samples_per_second": 121.597, | |
| "eval_steps_per_second": 3.378, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.015257192676547515, | |
| "grad_norm": 1.2432016134262085, | |
| "learning_rate": 9.998566913687882e-06, | |
| "loss": 9.6484, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.015257192676547515, | |
| "eval_accuracy": 0.08377012139513608, | |
| "eval_loss": 9.6328125, | |
| "eval_runtime": 278.8575, | |
| "eval_samples_per_second": 121.091, | |
| "eval_steps_per_second": 3.364, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.015311682650392329, | |
| "grad_norm": 1.1862634420394897, | |
| "learning_rate": 9.998561464690499e-06, | |
| "loss": 9.6875, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.015311682650392329, | |
| "eval_accuracy": 0.08376899238849779, | |
| "eval_loss": 9.625, | |
| "eval_runtime": 277.3994, | |
| "eval_samples_per_second": 121.727, | |
| "eval_steps_per_second": 3.381, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.01536617262423714, | |
| "grad_norm": 1.2821177244186401, | |
| "learning_rate": 9.998556015693112e-06, | |
| "loss": 9.6328, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.01536617262423714, | |
| "eval_accuracy": 0.08377649015053161, | |
| "eval_loss": 9.625, | |
| "eval_runtime": 277.0927, | |
| "eval_samples_per_second": 121.862, | |
| "eval_steps_per_second": 3.385, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.015420662598081954, | |
| "grad_norm": 1.2484102249145508, | |
| "learning_rate": 9.998550566695729e-06, | |
| "loss": 9.6562, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.015420662598081954, | |
| "eval_accuracy": 0.08380494690759437, | |
| "eval_loss": 9.6171875, | |
| "eval_runtime": 277.7775, | |
| "eval_samples_per_second": 121.561, | |
| "eval_steps_per_second": 3.377, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.015475152571926765, | |
| "grad_norm": 1.188653588294983, | |
| "learning_rate": 9.998545117698344e-06, | |
| "loss": 9.6719, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.015475152571926765, | |
| "eval_accuracy": 0.08383511164905864, | |
| "eval_loss": 9.6171875, | |
| "eval_runtime": 278.6388, | |
| "eval_samples_per_second": 121.186, | |
| "eval_steps_per_second": 3.366, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.015529642545771579, | |
| "grad_norm": 1.2269041538238525, | |
| "learning_rate": 9.998539668700959e-06, | |
| "loss": 9.6641, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.015529642545771579, | |
| "eval_accuracy": 0.08384709648875752, | |
| "eval_loss": 9.6171875, | |
| "eval_runtime": 278.3677, | |
| "eval_samples_per_second": 121.304, | |
| "eval_steps_per_second": 3.37, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.01558413251961639, | |
| "grad_norm": 1.266385555267334, | |
| "learning_rate": 9.998534219703576e-06, | |
| "loss": 9.6328, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.01558413251961639, | |
| "eval_accuracy": 0.08384223307554638, | |
| "eval_loss": 9.609375, | |
| "eval_runtime": 278.3739, | |
| "eval_samples_per_second": 121.301, | |
| "eval_steps_per_second": 3.37, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.015638622493461204, | |
| "grad_norm": 1.28980553150177, | |
| "learning_rate": 9.998528770706191e-06, | |
| "loss": 9.6328, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.015638622493461204, | |
| "eval_accuracy": 0.08388331154784755, | |
| "eval_loss": 9.609375, | |
| "eval_runtime": 279.4156, | |
| "eval_samples_per_second": 120.849, | |
| "eval_steps_per_second": 3.357, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.015693112467306015, | |
| "grad_norm": 1.2614293098449707, | |
| "learning_rate": 9.998523321708806e-06, | |
| "loss": 9.625, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.015693112467306015, | |
| "eval_accuracy": 0.08391469214261461, | |
| "eval_loss": 9.609375, | |
| "eval_runtime": 278.4116, | |
| "eval_samples_per_second": 121.284, | |
| "eval_steps_per_second": 3.369, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.015747602441150827, | |
| "grad_norm": 1.226367473602295, | |
| "learning_rate": 9.998517872711423e-06, | |
| "loss": 9.6328, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.015747602441150827, | |
| "eval_accuracy": 0.08397444264777995, | |
| "eval_loss": 9.6015625, | |
| "eval_runtime": 277.9542, | |
| "eval_samples_per_second": 121.484, | |
| "eval_steps_per_second": 3.375, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.015802092414995642, | |
| "grad_norm": 1.2424851655960083, | |
| "learning_rate": 9.998512423714038e-06, | |
| "loss": 9.6172, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.015802092414995642, | |
| "eval_accuracy": 0.08402672433979962, | |
| "eval_loss": 9.6015625, | |
| "eval_runtime": 277.2733, | |
| "eval_samples_per_second": 121.782, | |
| "eval_steps_per_second": 3.383, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.015856582388840454, | |
| "grad_norm": 1.2392754554748535, | |
| "learning_rate": 9.998506974716653e-06, | |
| "loss": 9.6172, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.015856582388840454, | |
| "eval_accuracy": 0.08409255411147887, | |
| "eval_loss": 9.6015625, | |
| "eval_runtime": 276.0303, | |
| "eval_samples_per_second": 122.331, | |
| "eval_steps_per_second": 3.398, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.015911072362685266, | |
| "grad_norm": 1.2615457773208618, | |
| "learning_rate": 9.998501525719268e-06, | |
| "loss": 9.6094, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.015911072362685266, | |
| "eval_accuracy": 0.08412827703947016, | |
| "eval_loss": 9.59375, | |
| "eval_runtime": 278.5317, | |
| "eval_samples_per_second": 121.232, | |
| "eval_steps_per_second": 3.368, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.015965562336530077, | |
| "grad_norm": 1.2395169734954834, | |
| "learning_rate": 9.998496076721884e-06, | |
| "loss": 9.6172, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.015965562336530077, | |
| "eval_accuracy": 0.0841603524075531, | |
| "eval_loss": 9.59375, | |
| "eval_runtime": 278.5884, | |
| "eval_samples_per_second": 121.207, | |
| "eval_steps_per_second": 3.367, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.016020052310374892, | |
| "grad_norm": 1.2416415214538574, | |
| "learning_rate": 9.9984906277245e-06, | |
| "loss": 9.6094, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.016020052310374892, | |
| "eval_accuracy": 0.08417905338930542, | |
| "eval_loss": 9.59375, | |
| "eval_runtime": 279.278, | |
| "eval_samples_per_second": 120.908, | |
| "eval_steps_per_second": 3.359, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.016074542284219704, | |
| "grad_norm": 1.2306995391845703, | |
| "learning_rate": 9.998485178727115e-06, | |
| "loss": 9.6328, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.016074542284219704, | |
| "eval_accuracy": 0.08419016976235945, | |
| "eval_loss": 9.5859375, | |
| "eval_runtime": 279.0203, | |
| "eval_samples_per_second": 121.02, | |
| "eval_steps_per_second": 3.362, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.016129032258064516, | |
| "grad_norm": 1.2327263355255127, | |
| "learning_rate": 9.998479729729731e-06, | |
| "loss": 9.5938, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.016129032258064516, | |
| "eval_accuracy": 0.08418545109358912, | |
| "eval_loss": 9.5859375, | |
| "eval_runtime": 279.0896, | |
| "eval_samples_per_second": 120.99, | |
| "eval_steps_per_second": 3.361, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.016183522231909327, | |
| "grad_norm": 1.322943091392517, | |
| "learning_rate": 9.998474280732346e-06, | |
| "loss": 9.5938, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.016183522231909327, | |
| "eval_accuracy": 0.08417552162494972, | |
| "eval_loss": 9.578125, | |
| "eval_runtime": 278.5612, | |
| "eval_samples_per_second": 121.219, | |
| "eval_steps_per_second": 3.367, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.016238012205754142, | |
| "grad_norm": 1.264687180519104, | |
| "learning_rate": 9.998468831734961e-06, | |
| "loss": 9.6016, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.016238012205754142, | |
| "eval_accuracy": 0.08418681169133271, | |
| "eval_loss": 9.578125, | |
| "eval_runtime": 276.7181, | |
| "eval_samples_per_second": 122.027, | |
| "eval_steps_per_second": 3.39, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.016292502179598954, | |
| "grad_norm": 1.2931830883026123, | |
| "learning_rate": 9.998463382737576e-06, | |
| "loss": 9.5781, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.016292502179598954, | |
| "eval_accuracy": 0.08422736908364697, | |
| "eval_loss": 9.578125, | |
| "eval_runtime": 278.6618, | |
| "eval_samples_per_second": 121.176, | |
| "eval_steps_per_second": 3.366, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.016346992153443766, | |
| "grad_norm": 1.247689962387085, | |
| "learning_rate": 9.998457933740191e-06, | |
| "loss": 9.5938, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.016346992153443766, | |
| "eval_accuracy": 0.08427264514473155, | |
| "eval_loss": 9.5703125, | |
| "eval_runtime": 278.3198, | |
| "eval_samples_per_second": 121.324, | |
| "eval_steps_per_second": 3.37, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.016401482127288577, | |
| "grad_norm": 1.269108772277832, | |
| "learning_rate": 9.998452484742808e-06, | |
| "loss": 9.5938, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.016401482127288577, | |
| "eval_accuracy": 0.08434733327618822, | |
| "eval_loss": 9.5703125, | |
| "eval_runtime": 277.9862, | |
| "eval_samples_per_second": 121.47, | |
| "eval_steps_per_second": 3.374, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.016455972101133393, | |
| "grad_norm": 1.2147337198257446, | |
| "learning_rate": 9.998447035745423e-06, | |
| "loss": 9.6016, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.016455972101133393, | |
| "eval_accuracy": 0.08440334937478074, | |
| "eval_loss": 9.5703125, | |
| "eval_runtime": 278.4928, | |
| "eval_samples_per_second": 121.249, | |
| "eval_steps_per_second": 3.368, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.016510462074978204, | |
| "grad_norm": 1.2472692728042603, | |
| "learning_rate": 9.998441586748038e-06, | |
| "loss": 9.5781, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.016510462074978204, | |
| "eval_accuracy": 0.08445693376676766, | |
| "eval_loss": 9.5625, | |
| "eval_runtime": 277.2562, | |
| "eval_samples_per_second": 121.79, | |
| "eval_steps_per_second": 3.383, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.016564952048823016, | |
| "grad_norm": 1.2579458951950073, | |
| "learning_rate": 9.998436137750655e-06, | |
| "loss": 9.6016, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.016564952048823016, | |
| "eval_accuracy": 0.08448973285705465, | |
| "eval_loss": 9.5625, | |
| "eval_runtime": 277.2268, | |
| "eval_samples_per_second": 121.803, | |
| "eval_steps_per_second": 3.384, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.016619442022667828, | |
| "grad_norm": 1.2708834409713745, | |
| "learning_rate": 9.99843068875327e-06, | |
| "loss": 9.5703, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.016619442022667828, | |
| "eval_accuracy": 0.084512920916472, | |
| "eval_loss": 9.5625, | |
| "eval_runtime": 277.9135, | |
| "eval_samples_per_second": 121.502, | |
| "eval_steps_per_second": 3.375, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.016673931996512643, | |
| "grad_norm": 1.2249526977539062, | |
| "learning_rate": 9.998425239755885e-06, | |
| "loss": 9.5781, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.016673931996512643, | |
| "eval_accuracy": 0.08454019076912014, | |
| "eval_loss": 9.5546875, | |
| "eval_runtime": 277.7743, | |
| "eval_samples_per_second": 121.563, | |
| "eval_steps_per_second": 3.377, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.016728421970357454, | |
| "grad_norm": 1.214102029800415, | |
| "learning_rate": 9.998419790758502e-06, | |
| "loss": 9.5938, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.016728421970357454, | |
| "eval_accuracy": 0.08456963178838038, | |
| "eval_loss": 9.5546875, | |
| "eval_runtime": 277.7599, | |
| "eval_samples_per_second": 121.569, | |
| "eval_steps_per_second": 3.377, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.016782911944202266, | |
| "grad_norm": 1.2691110372543335, | |
| "learning_rate": 9.998414341761117e-06, | |
| "loss": 9.5391, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.016782911944202266, | |
| "eval_accuracy": 0.08458882490123146, | |
| "eval_loss": 9.5546875, | |
| "eval_runtime": 278.1571, | |
| "eval_samples_per_second": 121.395, | |
| "eval_steps_per_second": 3.372, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.016837401918047078, | |
| "grad_norm": 1.2669826745986938, | |
| "learning_rate": 9.998408892763732e-06, | |
| "loss": 9.5625, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.016837401918047078, | |
| "eval_accuracy": 0.08460961020293142, | |
| "eval_loss": 9.546875, | |
| "eval_runtime": 277.952, | |
| "eval_samples_per_second": 121.485, | |
| "eval_steps_per_second": 3.375, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.016891891891891893, | |
| "grad_norm": 1.2808586359024048, | |
| "learning_rate": 9.998403443766349e-06, | |
| "loss": 9.5547, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.016891891891891893, | |
| "eval_accuracy": 0.08461615265165591, | |
| "eval_loss": 9.546875, | |
| "eval_runtime": 277.1252, | |
| "eval_samples_per_second": 121.847, | |
| "eval_steps_per_second": 3.385, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.016946381865736704, | |
| "grad_norm": 1.252959132194519, | |
| "learning_rate": 9.998397994768964e-06, | |
| "loss": 9.5703, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.016946381865736704, | |
| "eval_accuracy": 0.08458865120790249, | |
| "eval_loss": 9.546875, | |
| "eval_runtime": 278.3797, | |
| "eval_samples_per_second": 121.298, | |
| "eval_steps_per_second": 3.369, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.017000871839581516, | |
| "grad_norm": 1.2392700910568237, | |
| "learning_rate": 9.998392545771579e-06, | |
| "loss": 9.5625, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.017000871839581516, | |
| "eval_accuracy": 0.08457846119926964, | |
| "eval_loss": 9.5390625, | |
| "eval_runtime": 278.5979, | |
| "eval_samples_per_second": 121.203, | |
| "eval_steps_per_second": 3.367, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.01705536181342633, | |
| "grad_norm": 1.363663673400879, | |
| "learning_rate": 9.998387096774195e-06, | |
| "loss": 9.5469, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.01705536181342633, | |
| "eval_accuracy": 0.0846050362786019, | |
| "eval_loss": 9.5390625, | |
| "eval_runtime": 279.48, | |
| "eval_samples_per_second": 120.821, | |
| "eval_steps_per_second": 3.356, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.017109851787271143, | |
| "grad_norm": 1.258362889289856, | |
| "learning_rate": 9.99838164777681e-06, | |
| "loss": 9.5469, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.017109851787271143, | |
| "eval_accuracy": 0.08462159504263028, | |
| "eval_loss": 9.5390625, | |
| "eval_runtime": 280.9528, | |
| "eval_samples_per_second": 120.187, | |
| "eval_steps_per_second": 3.339, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.017164341761115955, | |
| "grad_norm": 1.2624891996383667, | |
| "learning_rate": 9.998376198779425e-06, | |
| "loss": 9.5391, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.017164341761115955, | |
| "eval_accuracy": 0.08465442308180542, | |
| "eval_loss": 9.53125, | |
| "eval_runtime": 280.6538, | |
| "eval_samples_per_second": 120.316, | |
| "eval_steps_per_second": 3.342, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.017218831734960766, | |
| "grad_norm": 1.2132024765014648, | |
| "learning_rate": 9.998370749782042e-06, | |
| "loss": 9.5781, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.017218831734960766, | |
| "eval_accuracy": 0.08470062550731117, | |
| "eval_loss": 9.53125, | |
| "eval_runtime": 279.7295, | |
| "eval_samples_per_second": 120.713, | |
| "eval_steps_per_second": 3.353, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.01727332170880558, | |
| "grad_norm": 1.2480347156524658, | |
| "learning_rate": 9.998365300784656e-06, | |
| "loss": 9.5469, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.01727332170880558, | |
| "eval_accuracy": 0.08472815589995276, | |
| "eval_loss": 9.53125, | |
| "eval_runtime": 278.8002, | |
| "eval_samples_per_second": 121.115, | |
| "eval_steps_per_second": 3.364, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.017327811682650393, | |
| "grad_norm": 1.304702639579773, | |
| "learning_rate": 9.998359851787272e-06, | |
| "loss": 9.5312, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.017327811682650393, | |
| "eval_accuracy": 0.0847501570549555, | |
| "eval_loss": 9.5234375, | |
| "eval_runtime": 279.8383, | |
| "eval_samples_per_second": 120.666, | |
| "eval_steps_per_second": 3.352, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.017382301656495205, | |
| "grad_norm": 1.221549153327942, | |
| "learning_rate": 9.998354402789887e-06, | |
| "loss": 9.5703, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.017382301656495205, | |
| "eval_accuracy": 0.08476648422787858, | |
| "eval_loss": 9.5234375, | |
| "eval_runtime": 278.8177, | |
| "eval_samples_per_second": 121.108, | |
| "eval_steps_per_second": 3.364, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.017436791630340016, | |
| "grad_norm": 1.262052297592163, | |
| "learning_rate": 9.998348953792502e-06, | |
| "loss": 9.5312, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.017436791630340016, | |
| "eval_accuracy": 0.08480269928696862, | |
| "eval_loss": 9.5234375, | |
| "eval_runtime": 278.2907, | |
| "eval_samples_per_second": 121.337, | |
| "eval_steps_per_second": 3.371, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.01749128160418483, | |
| "grad_norm": 1.20883047580719, | |
| "learning_rate": 9.998343504795119e-06, | |
| "loss": 9.5703, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.01749128160418483, | |
| "eval_accuracy": 0.08483929068160476, | |
| "eval_loss": 9.515625, | |
| "eval_runtime": 278.7692, | |
| "eval_samples_per_second": 121.129, | |
| "eval_steps_per_second": 3.365, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.017545771578029643, | |
| "grad_norm": 1.2607730627059937, | |
| "learning_rate": 9.998338055797734e-06, | |
| "loss": 9.5312, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.017545771578029643, | |
| "eval_accuracy": 0.08487046863415469, | |
| "eval_loss": 9.515625, | |
| "eval_runtime": 278.4626, | |
| "eval_samples_per_second": 121.262, | |
| "eval_steps_per_second": 3.368, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.017600261551874455, | |
| "grad_norm": 1.2543152570724487, | |
| "learning_rate": 9.998332606800349e-06, | |
| "loss": 9.5391, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.017600261551874455, | |
| "eval_accuracy": 0.08489484359798667, | |
| "eval_loss": 9.5078125, | |
| "eval_runtime": 278.034, | |
| "eval_samples_per_second": 121.449, | |
| "eval_steps_per_second": 3.374, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.017654751525719267, | |
| "grad_norm": 1.261744737625122, | |
| "learning_rate": 9.998327157802966e-06, | |
| "loss": 9.5156, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.017654751525719267, | |
| "eval_accuracy": 0.08491759742408161, | |
| "eval_loss": 9.5078125, | |
| "eval_runtime": 278.3626, | |
| "eval_samples_per_second": 121.306, | |
| "eval_steps_per_second": 3.37, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.01770924149956408, | |
| "grad_norm": 1.261576771736145, | |
| "learning_rate": 9.998321708805581e-06, | |
| "loss": 9.5234, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.01770924149956408, | |
| "eval_accuracy": 0.08492923487712253, | |
| "eval_loss": 9.5078125, | |
| "eval_runtime": 278.7706, | |
| "eval_samples_per_second": 121.128, | |
| "eval_steps_per_second": 3.365, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.017763731473408893, | |
| "grad_norm": 1.2752763032913208, | |
| "learning_rate": 9.998316259808196e-06, | |
| "loss": 9.5391, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.017763731473408893, | |
| "eval_accuracy": 0.08490972332650168, | |
| "eval_loss": 9.5, | |
| "eval_runtime": 277.4247, | |
| "eval_samples_per_second": 121.716, | |
| "eval_steps_per_second": 3.381, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.017818221447253705, | |
| "grad_norm": 1.2762752771377563, | |
| "learning_rate": 9.998310810810811e-06, | |
| "loss": 9.5078, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.017818221447253705, | |
| "eval_accuracy": 0.08489041441809797, | |
| "eval_loss": 9.5, | |
| "eval_runtime": 278.791, | |
| "eval_samples_per_second": 121.119, | |
| "eval_steps_per_second": 3.365, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.017872711421098517, | |
| "grad_norm": 1.2357895374298096, | |
| "learning_rate": 9.998305361813428e-06, | |
| "loss": 9.5312, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.017872711421098517, | |
| "eval_accuracy": 0.08484099866600628, | |
| "eval_loss": 9.5, | |
| "eval_runtime": 278.1228, | |
| "eval_samples_per_second": 121.41, | |
| "eval_steps_per_second": 3.373, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.017927201394943332, | |
| "grad_norm": 1.2696473598480225, | |
| "learning_rate": 9.998299912816043e-06, | |
| "loss": 9.5078, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.017927201394943332, | |
| "eval_accuracy": 0.08476593419900351, | |
| "eval_loss": 9.4921875, | |
| "eval_runtime": 279.1969, | |
| "eval_samples_per_second": 120.943, | |
| "eval_steps_per_second": 3.36, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.017981691368788143, | |
| "grad_norm": 1.2310556173324585, | |
| "learning_rate": 9.998294463818658e-06, | |
| "loss": 9.5234, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.017981691368788143, | |
| "eval_accuracy": 0.08473466939978909, | |
| "eval_loss": 9.4921875, | |
| "eval_runtime": 278.5891, | |
| "eval_samples_per_second": 121.207, | |
| "eval_steps_per_second": 3.367, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.018036181342632955, | |
| "grad_norm": 1.2741543054580688, | |
| "learning_rate": 9.998289014821274e-06, | |
| "loss": 9.5078, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.018036181342632955, | |
| "eval_accuracy": 0.08475229927267945, | |
| "eval_loss": 9.4921875, | |
| "eval_runtime": 278.1693, | |
| "eval_samples_per_second": 121.39, | |
| "eval_steps_per_second": 3.372, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.018090671316477767, | |
| "grad_norm": 1.2879000902175903, | |
| "learning_rate": 9.99828356582389e-06, | |
| "loss": 9.4922, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.018090671316477767, | |
| "eval_accuracy": 0.08481100761787097, | |
| "eval_loss": 9.484375, | |
| "eval_runtime": 279.2612, | |
| "eval_samples_per_second": 120.915, | |
| "eval_steps_per_second": 3.359, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.018145161290322582, | |
| "grad_norm": 1.2958968877792358, | |
| "learning_rate": 9.998278116826505e-06, | |
| "loss": 9.5, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.018145161290322582, | |
| "eval_accuracy": 0.08491096812869263, | |
| "eval_loss": 9.484375, | |
| "eval_runtime": 278.8921, | |
| "eval_samples_per_second": 121.076, | |
| "eval_steps_per_second": 3.363, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.018199651264167394, | |
| "grad_norm": 1.2337111234664917, | |
| "learning_rate": 9.99827266782912e-06, | |
| "loss": 9.5078, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.018199651264167394, | |
| "eval_accuracy": 0.08498186395580014, | |
| "eval_loss": 9.484375, | |
| "eval_runtime": 279.3346, | |
| "eval_samples_per_second": 120.884, | |
| "eval_steps_per_second": 3.358, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.018254141238012205, | |
| "grad_norm": 1.3057183027267456, | |
| "learning_rate": 9.998267218831735e-06, | |
| "loss": 9.4766, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.018254141238012205, | |
| "eval_accuracy": 0.0850502412296376, | |
| "eval_loss": 9.4765625, | |
| "eval_runtime": 278.5471, | |
| "eval_samples_per_second": 121.225, | |
| "eval_steps_per_second": 3.367, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.018308631211857017, | |
| "grad_norm": 1.2413270473480225, | |
| "learning_rate": 9.998261769834351e-06, | |
| "loss": 9.5, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.018308631211857017, | |
| "eval_accuracy": 0.08509852797509099, | |
| "eval_loss": 9.4765625, | |
| "eval_runtime": 277.2384, | |
| "eval_samples_per_second": 121.798, | |
| "eval_steps_per_second": 3.383, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.018308631211857017, | |
| "step": 336, | |
| "total_flos": 352197518819328.0, | |
| "train_loss": 10.035667782738095, | |
| "train_runtime": 94125.7847, | |
| "train_samples_per_second": 701.873, | |
| "train_steps_per_second": 19.497 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1835200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 1000000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 352197518819328.0, | |
| "train_batch_size": 36, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |