| { | |
| "best_metric": 0.9429291486740112, | |
| "best_model_checkpoint": "data/Gemma-2-2B_task-3_180-samples_config-1_full/checkpoint-102", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 221, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.44520437717437744, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.3799, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.45859649777412415, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.4186, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5357824563980103, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.4172, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.5245683789253235, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.4514, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.45616987347602844, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.3955, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.7059785723686218, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.3596, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.41806259751319885, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.3467, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.46011263132095337, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.3993, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.39417997002601624, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.3583, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3383493423461914, | |
| "eval_runtime": 11.3081, | |
| "eval_samples_per_second": 3.184, | |
| "eval_steps_per_second": 3.184, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.377594918012619, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.3709, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.3283311724662781, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.3543, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.30775314569473267, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.2849, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.29247111082077026, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.2454, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.25112494826316833, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.2185, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.25338229537010193, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.2225, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.294301301240921, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.2331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.27364638447761536, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.1786, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2826504111289978, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1931, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.161141276359558, | |
| "eval_runtime": 11.2966, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.28443294763565063, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.1352, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.271122008562088, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.1016, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.25979140400886536, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.0829, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.29166024923324585, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.0891, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.41109684109687805, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.0292, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.3248695731163025, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.0533, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.2497558742761612, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.024, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.24576611816883087, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9969, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.014572262763977, | |
| "eval_runtime": 11.2943, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.21467238664627075, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.9683, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.19869673252105713, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.9336, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.19860883057117462, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.9892, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.2291756272315979, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.9661, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.2128845751285553, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.8865, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.1970745325088501, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.988, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.2762312889099121, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.9445, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.212728813290596, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.897, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.22113971412181854, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8959, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.9699280261993408, | |
| "eval_runtime": 11.2935, | |
| "eval_samples_per_second": 3.188, | |
| "eval_steps_per_second": 3.188, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.19231808185577393, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.965, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.22489900887012482, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.8563, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.1847766786813736, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.9331, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.22063417732715607, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.8604, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.21326088905334473, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8892, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.20971600711345673, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.9113, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.2362341433763504, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.8667, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.21359607577323914, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.8646, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.9505686163902283, | |
| "eval_runtime": 11.2911, | |
| "eval_samples_per_second": 3.188, | |
| "eval_steps_per_second": 3.188, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.2615335285663605, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.8254, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.24993883073329926, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.8357, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.2440963238477707, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.8649, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.2394658476114273, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.875, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.2597372531890869, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.8387, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.2577613592147827, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.8409, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.257099986076355, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.8609, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.30528348684310913, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.8887, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.26377636194229126, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8205, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9429291486740112, | |
| "eval_runtime": 11.3073, | |
| "eval_samples_per_second": 3.184, | |
| "eval_steps_per_second": 3.184, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.33210882544517517, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.7834, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.29507479071617126, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.7995, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.2986210584640503, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.7575, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.3783329129219055, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.8225, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.3038838803768158, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.7791, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.36617377400398254, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.8604, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.3460572361946106, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.8339, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.3697707951068878, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.7947, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.9491720199584961, | |
| "eval_runtime": 11.2912, | |
| "eval_samples_per_second": 3.188, | |
| "eval_steps_per_second": 3.188, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.3217655420303345, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.8017, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.34303125739097595, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.7615, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.4326487183570862, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.742, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.4410136938095093, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.7159, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.44748595356941223, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.7386, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.4633381962776184, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.7461, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.47947824001312256, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.6938, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.4737105667591095, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.7975, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.5155892372131348, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7099, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.9748880863189697, | |
| "eval_runtime": 11.2958, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.5446560978889465, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.6843, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.7322703003883362, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.6481, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.6326209902763367, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.7069, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.612084686756134, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.6996, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.6935217380523682, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.7148, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.6035698056221008, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.6926, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.6253191828727722, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.6508, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.6796343922615051, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.6368, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0093340873718262, | |
| "eval_runtime": 11.2948, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.5984119176864624, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.6623, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.6029745936393738, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.6102, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 1.0763262510299683, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.6304, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.7631277441978455, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.622, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.6751508712768555, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.5996, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.7833979725837708, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.6203, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.7388814091682434, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.6484, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.7772870063781738, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.5447, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.8894267082214355, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6039, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0973275899887085, | |
| "eval_runtime": 11.2949, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.8078559637069702, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.5073, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.4214626550674438, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5418, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.8617724776268005, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.5641, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.9274459481239319, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.4927, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 1.1095643043518066, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.5607, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.9272680282592773, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.518, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.8688672780990601, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.5376, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.9498487710952759, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.5767, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.124273657798767, | |
| "eval_runtime": 11.2996, | |
| "eval_samples_per_second": 3.186, | |
| "eval_steps_per_second": 3.186, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.798162043094635, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.5494, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.9384578466415405, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.4692, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.6115288734436035, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5352, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 1.0060256719589233, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3399, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.9934931993484497, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5134, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.1829591989517212, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.4742, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.9848449230194092, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.476, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 1.0878208875656128, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.4566, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.144034504890442, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4197, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.3016955852508545, | |
| "eval_runtime": 11.2876, | |
| "eval_samples_per_second": 3.189, | |
| "eval_steps_per_second": 3.189, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 1.0310981273651123, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4131, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.1738086938858032, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.364, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 1.147154688835144, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4009, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.1842771768569946, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.3603, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.426638126373291, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.4468, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.136128544807434, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.3603, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.1854625940322876, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.4013, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 1.248672604560852, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.4419, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.2848278284072876, | |
| "eval_runtime": 11.2944, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 3.187, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 4.767811216238182e+16, | |
| "train_loss": 0.8169799776098847, | |
| "train_runtime": 2005.7122, | |
| "train_samples_per_second": 3.39, | |
| "train_steps_per_second": 0.424 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 850, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 7, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.767811216238182e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |