| { | |
| "best_metric": 0.8685290217399597, | |
| "best_model_checkpoint": "data/Gemma-2-2B_task-2_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": 0.4663330316543579, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.3148, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.49109163880348206, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.3549, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5797170400619507, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.3614, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.5457412600517273, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 1.3863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.48563823103904724, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 1.3353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.41699832677841187, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.2963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.4280100464820862, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 1.2778, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.4805794060230255, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 1.3136, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.4118902385234833, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 1.2797, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.269832730293274, | |
| "eval_runtime": 13.934, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 2.584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.3912472426891327, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.3179, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.34678152203559875, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.2681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.3228563964366913, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.2207, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.297993928194046, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.1748, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.25391504168510437, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.1349, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2437594085931778, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.1553, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.2889123857021332, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.1451, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.2736818790435791, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.0915, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2786788046360016, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1117, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.088223934173584, | |
| "eval_runtime": 13.9255, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.28480198979377747, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.064, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.24093686044216156, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.0225, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.23838327825069427, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.0147, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.26892682909965515, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.0347, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.3480377495288849, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 0.9732, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.35282817482948303, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 0.9884, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.22866079211235046, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 0.9572, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.2268373817205429, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.9258, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.9471964240074158, | |
| "eval_runtime": 13.9276, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.18994289636611938, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.8951, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.18752464652061462, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.8713, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.18600308895111084, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.9155, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.22079868614673615, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 0.9368, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.23555976152420044, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.8272, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.1756589412689209, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.9183, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.5781435370445251, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.8667, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.18368655443191528, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.8306, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.22530372440814972, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8212, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.901809811592102, | |
| "eval_runtime": 13.9235, | |
| "eval_samples_per_second": 2.586, | |
| "eval_steps_per_second": 2.586, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.2051382064819336, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.93, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.180986225605011, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.787, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.17009112238883972, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.8612, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.1875051110982895, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.8008, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.18995052576065063, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8217, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.18762436509132385, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.839, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.21154262125492096, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.8045, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.20175059139728546, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.7979, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8801479339599609, | |
| "eval_runtime": 13.9356, | |
| "eval_samples_per_second": 2.583, | |
| "eval_steps_per_second": 2.583, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.20424281060695648, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.7645, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.21113455295562744, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.78, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.20115172863006592, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.8151, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.2209591418504715, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.8173, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.21552880108356476, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.7695, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.2150675356388092, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.778, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.21824193000793457, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.7985, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.26986488699913025, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.8247, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.22610753774642944, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7616, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.8685290217399597, | |
| "eval_runtime": 13.9296, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 2.584, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.22851842641830444, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.7273, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.25495514273643494, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.7517, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.2536880671977997, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.6985, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 0.27880415320396423, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.761, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 0.27292999625205994, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.7325, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 0.3406491279602051, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.8005, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 0.30790194869041443, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.7768, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 0.3078755736351013, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.7431, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8697893619537354, | |
| "eval_runtime": 13.9305, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 2.584, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.3024759292602539, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.7606, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 0.28439903259277344, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.7103, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 0.3533192574977875, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.6982, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 0.3567720055580139, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.6725, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 0.34326615929603577, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.6864, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.36330753564834595, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.7019, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 0.38707226514816284, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.6471, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 0.3947407305240631, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.7523, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.41330084204673767, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.6675, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.8850482702255249, | |
| "eval_runtime": 13.9274, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 0.42337167263031006, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.6519, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 0.5889256596565247, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.6166, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 0.4771933853626251, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.664, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 0.4492894411087036, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.6641, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 0.5383152365684509, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.6787, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 0.4846758246421814, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.6574, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.47182518243789673, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.6161, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 0.504204511642456, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.5991, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.912237286567688, | |
| "eval_runtime": 13.9274, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 0.5389410257339478, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.6284, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 0.5193843245506287, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.5861, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 0.729849636554718, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.5946, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 0.58505779504776, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.5976, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 0.5613174438476562, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.5691, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 0.6326307654380798, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.5962, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 0.590175986289978, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.6193, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 0.6606982350349426, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.5262, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.68808513879776, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.5797, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.9582248330116272, | |
| "eval_runtime": 13.9362, | |
| "eval_samples_per_second": 2.583, | |
| "eval_steps_per_second": 2.583, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 0.6920706629753113, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.4959, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.2780792713165283, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.5312, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 0.7444865107536316, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.5488, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 0.7448853850364685, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.4854, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 0.9281625151634216, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.5463, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 0.7427995204925537, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.5007, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 0.759475588798523, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.5333, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 0.8229702115058899, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.559, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.0085738897323608, | |
| "eval_runtime": 13.9279, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 0.6575381755828857, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.544, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 0.742940366268158, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.4674, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.261710524559021, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.5313, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 0.8558570146560669, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.3409, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 0.8562042117118835, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.5117, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 0.8646235466003418, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.4758, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 0.8664374351501465, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.4725, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 0.8843783736228943, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.4565, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.8938696384429932, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4197, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.1556185483932495, | |
| "eval_runtime": 13.9319, | |
| "eval_samples_per_second": 2.584, | |
| "eval_steps_per_second": 2.584, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.8586167097091675, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.4199, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 0.9320749640464783, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.3656, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 1.0425074100494385, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.4047, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 0.9784245491027832, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.3648, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.032303810119629, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.4507, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 0.950233519077301, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.3723, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.0120763778686523, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.4029, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 0.9681946635246277, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.4433, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.1318533420562744, | |
| "eval_runtime": 13.9264, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 2.585, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 5.79219938649047e+16, | |
| "train_loss": 0.77317684969751, | |
| "train_runtime": 2461.5487, | |
| "train_samples_per_second": 2.762, | |
| "train_steps_per_second": 0.345 | |
| } | |
| ], | |
| "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": 5.79219938649047e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |