| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.962025316455696, | |
| "eval_steps": 500, | |
| "global_step": 78, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0379746835443038, | |
| "grad_norm": 9.957548553322647, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.9713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "grad_norm": 9.985108674661252, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.991, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11392405063291139, | |
| "grad_norm": 9.706261106399902, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.0266, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 8.001810981524628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9713, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.189873417721519, | |
| "grad_norm": 5.169780518606936, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.9267, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22784810126582278, | |
| "grad_norm": 3.998888986405131, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.8087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26582278481012656, | |
| "grad_norm": 3.3221599230206063, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 0.7365, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 2.616871192982944, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7156, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34177215189873417, | |
| "grad_norm": 2.346550661330392, | |
| "learning_rate": 9.994965332706574e-06, | |
| "loss": 0.687, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.379746835443038, | |
| "grad_norm": 2.4394026660864716, | |
| "learning_rate": 9.979871469976197e-06, | |
| "loss": 0.6445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4177215189873418, | |
| "grad_norm": 1.9546180950509056, | |
| "learning_rate": 9.954748808839675e-06, | |
| "loss": 0.634, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45569620253164556, | |
| "grad_norm": 1.6494467158995272, | |
| "learning_rate": 9.91964794299315e-06, | |
| "loss": 0.6408, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4936708860759494, | |
| "grad_norm": 1.593487584280316, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.5857, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5316455696202531, | |
| "grad_norm": 1.7418928363879251, | |
| "learning_rate": 9.819814303479268e-06, | |
| "loss": 0.6297, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.569620253164557, | |
| "grad_norm": 1.481174396209577, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 0.6558, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.3303606157200163, | |
| "learning_rate": 9.681174353198687e-06, | |
| "loss": 0.6002, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6455696202531646, | |
| "grad_norm": 1.433820593402365, | |
| "learning_rate": 9.597638862757255e-06, | |
| "loss": 0.6206, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6835443037974683, | |
| "grad_norm": 1.2744328251297492, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.6227, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7215189873417721, | |
| "grad_norm": 1.3031604814024054, | |
| "learning_rate": 9.40297765928369e-06, | |
| "loss": 0.587, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.759493670886076, | |
| "grad_norm": 1.4316949075465608, | |
| "learning_rate": 9.292243968009332e-06, | |
| "loss": 0.6471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7974683544303798, | |
| "grad_norm": 1.162051301543542, | |
| "learning_rate": 9.172866268606514e-06, | |
| "loss": 0.5536, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8354430379746836, | |
| "grad_norm": 1.157069048811417, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.578, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8734177215189873, | |
| "grad_norm": 1.3103025654917138, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.591, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.380236644707809, | |
| "learning_rate": 8.765357330018056e-06, | |
| "loss": 0.6074, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9493670886075949, | |
| "grad_norm": 1.2486616195577804, | |
| "learning_rate": 8.613974319136959e-06, | |
| "loss": 0.6023, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9873417721518988, | |
| "grad_norm": 1.2816040526324866, | |
| "learning_rate": 8.455313244934324e-06, | |
| "loss": 0.5933, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0253164556962024, | |
| "grad_norm": 2.335290159380928, | |
| "learning_rate": 8.289693629698564e-06, | |
| "loss": 0.9482, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0632911392405062, | |
| "grad_norm": 1.097409197181704, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.4475, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1012658227848102, | |
| "grad_norm": 1.0749833654838596, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 0.479, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.139240506329114, | |
| "grad_norm": 1.060278309114871, | |
| "learning_rate": 7.754484907260513e-06, | |
| "loss": 0.487, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1772151898734178, | |
| "grad_norm": 1.1027437567641056, | |
| "learning_rate": 7.564496387029532e-06, | |
| "loss": 0.4719, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.1228067655268963, | |
| "learning_rate": 7.369343312364994e-06, | |
| "loss": 0.439, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2531645569620253, | |
| "grad_norm": 1.2042550076536291, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.4851, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2911392405063291, | |
| "grad_norm": 1.071175489408689, | |
| "learning_rate": 6.965125158269619e-06, | |
| "loss": 0.4677, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3291139240506329, | |
| "grad_norm": 1.095264978758299, | |
| "learning_rate": 6.7568741204067145e-06, | |
| "loss": 0.4578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3670886075949367, | |
| "grad_norm": 1.147169839461561, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.4479, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4050632911392404, | |
| "grad_norm": 1.2799965851045123, | |
| "learning_rate": 6.330184227833376e-06, | |
| "loss": 0.4731, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4430379746835442, | |
| "grad_norm": 1.177828457101423, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.4498, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.481012658227848, | |
| "grad_norm": 1.1619484427029347, | |
| "learning_rate": 5.892784473993184e-06, | |
| "loss": 0.4736, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.0345103815690855, | |
| "learning_rate": 5.671166329088278e-06, | |
| "loss": 0.435, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5569620253164556, | |
| "grad_norm": 1.1026479888157206, | |
| "learning_rate": 5.448196544517168e-06, | |
| "loss": 0.4889, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5949367088607596, | |
| "grad_norm": 0.9919388016336564, | |
| "learning_rate": 5.224324151752575e-06, | |
| "loss": 0.4153, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6329113924050633, | |
| "grad_norm": 1.0715771514703643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4665, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6708860759493671, | |
| "grad_norm": 1.1245062678426976, | |
| "learning_rate": 4.775675848247427e-06, | |
| "loss": 0.467, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7088607594936709, | |
| "grad_norm": 0.9773184362626276, | |
| "learning_rate": 4.551803455482833e-06, | |
| "loss": 0.4624, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7468354430379747, | |
| "grad_norm": 0.9253982190523925, | |
| "learning_rate": 4.3288336709117246e-06, | |
| "loss": 0.4029, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7848101265822784, | |
| "grad_norm": 1.0275614152119965, | |
| "learning_rate": 4.107215526006818e-06, | |
| "loss": 0.4661, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.0879971013287744, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.4822, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8607594936708862, | |
| "grad_norm": 0.9725180909825993, | |
| "learning_rate": 3.669815772166625e-06, | |
| "loss": 0.437, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8987341772151898, | |
| "grad_norm": 1.0660365226149333, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.4685, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9367088607594938, | |
| "grad_norm": 0.9864954896447238, | |
| "learning_rate": 3.2431258795932863e-06, | |
| "loss": 0.4427, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.9746835443037973, | |
| "grad_norm": 1.0251705463878462, | |
| "learning_rate": 3.0348748417303826e-06, | |
| "loss": 0.4103, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0126582278481013, | |
| "grad_norm": 1.7762263480297156, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.6331, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.050632911392405, | |
| "grad_norm": 1.0454599192267253, | |
| "learning_rate": 2.6306566876350072e-06, | |
| "loss": 0.3539, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.088607594936709, | |
| "grad_norm": 0.9998841150009384, | |
| "learning_rate": 2.43550361297047e-06, | |
| "loss": 0.3578, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 0.9964166404453179, | |
| "learning_rate": 2.245515092739488e-06, | |
| "loss": 0.3562, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.1645569620253164, | |
| "grad_norm": 0.9459908925231907, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.3568, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.2025316455696204, | |
| "grad_norm": 0.8966814279446472, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.3325, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.240506329113924, | |
| "grad_norm": 0.9244456697881348, | |
| "learning_rate": 1.7103063703014372e-06, | |
| "loss": 0.3113, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.278481012658228, | |
| "grad_norm": 0.9483141643601266, | |
| "learning_rate": 1.544686755065677e-06, | |
| "loss": 0.3228, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3164556962025316, | |
| "grad_norm": 1.0064785741358837, | |
| "learning_rate": 1.3860256808630429e-06, | |
| "loss": 0.3656, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.3544303797468356, | |
| "grad_norm": 0.9913312730806086, | |
| "learning_rate": 1.234642669981946e-06, | |
| "loss": 0.3416, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.392405063291139, | |
| "grad_norm": 0.9569431038994634, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.3091, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.0791734978912138, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.3358, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.4683544303797467, | |
| "grad_norm": 1.061245141407699, | |
| "learning_rate": 8.271337313934869e-07, | |
| "loss": 0.3524, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.5063291139240507, | |
| "grad_norm": 1.0946626722996773, | |
| "learning_rate": 7.077560319906696e-07, | |
| "loss": 0.3412, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.5443037974683547, | |
| "grad_norm": 0.9843396259475062, | |
| "learning_rate": 5.9702234071631e-07, | |
| "loss": 0.3056, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.5822784810126582, | |
| "grad_norm": 0.9896788540648425, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.3231, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.620253164556962, | |
| "grad_norm": 1.018520895923904, | |
| "learning_rate": 4.0236113724274716e-07, | |
| "loss": 0.3487, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.6582278481012658, | |
| "grad_norm": 1.0112046345213885, | |
| "learning_rate": 3.18825646801314e-07, | |
| "loss": 0.3574, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.6962025316455698, | |
| "grad_norm": 0.9805922789991742, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 0.3268, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.0121311757244564, | |
| "learning_rate": 1.801856965207338e-07, | |
| "loss": 0.3047, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.7721518987341773, | |
| "grad_norm": 0.9808044853524287, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.344, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.810126582278481, | |
| "grad_norm": 0.9448770611064761, | |
| "learning_rate": 8.035205700685167e-08, | |
| "loss": 0.3286, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.848101265822785, | |
| "grad_norm": 0.938807423248215, | |
| "learning_rate": 4.52511911603265e-08, | |
| "loss": 0.3249, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.8860759493670884, | |
| "grad_norm": 0.9467118042819199, | |
| "learning_rate": 2.012853002380466e-08, | |
| "loss": 0.3396, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.9240506329113924, | |
| "grad_norm": 1.0059613466947979, | |
| "learning_rate": 5.034667293427053e-09, | |
| "loss": 0.3369, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.962025316455696, | |
| "grad_norm": 0.999912605851653, | |
| "learning_rate": 0.0, | |
| "loss": 0.348, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.962025316455696, | |
| "step": 78, | |
| "total_flos": 16384759316480.0, | |
| "train_loss": 0.5084553494667395, | |
| "train_runtime": 492.5209, | |
| "train_samples_per_second": 15.228, | |
| "train_steps_per_second": 0.158 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 78, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 16384759316480.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |