| { | |
| "best_metric": 0.9278689622879028, | |
| "best_model_checkpoint": "data/Gemma-2-2B_task-1_180-samples_config-1_full_auto/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": 1.211376428604126, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 2.2666, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 1.2106879949569702, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 2.3462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.2014598846435547, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 2.2134, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.1927666664123535, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 2.2377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.3306472301483154, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 2.249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.2041209936141968, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.2388, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 1.2755601406097412, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 2.2887, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 1.32211172580719, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 2.2792, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.220287561416626, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 2.1329, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.07915997505188, | |
| "eval_runtime": 3.2915, | |
| "eval_samples_per_second": 10.937, | |
| "eval_steps_per_second": 10.937, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 1.1516729593276978, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 2.0807, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 1.1192710399627686, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 1.9824, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 1.0268539190292358, | |
| "learning_rate": 2.5882352941176475e-05, | |
| "loss": 1.9392, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.977662980556488, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.8069, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.9665217995643616, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 1.7689, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.9652373790740967, | |
| "learning_rate": 3.294117647058824e-05, | |
| "loss": 1.6125, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.8798425197601318, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.5888, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.903175950050354, | |
| "learning_rate": 3.7647058823529415e-05, | |
| "loss": 1.4489, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8608154058456421, | |
| "learning_rate": 4e-05, | |
| "loss": 1.45, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3698946237564087, | |
| "eval_runtime": 3.2792, | |
| "eval_samples_per_second": 10.978, | |
| "eval_steps_per_second": 10.978, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.8925697207450867, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 1.3552, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.8442366123199463, | |
| "learning_rate": 4.470588235294118e-05, | |
| "loss": 1.2553, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.8634824752807617, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 1.1473, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.7777335047721863, | |
| "learning_rate": 4.9411764705882355e-05, | |
| "loss": 1.1648, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.6794209480285645, | |
| "learning_rate": 5.176470588235295e-05, | |
| "loss": 1.092, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.6069318056106567, | |
| "learning_rate": 5.411764705882353e-05, | |
| "loss": 1.1496, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.5978594422340393, | |
| "learning_rate": 5.647058823529412e-05, | |
| "loss": 1.0745, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.6143906116485596, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.025, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0321526527404785, | |
| "eval_runtime": 3.2435, | |
| "eval_samples_per_second": 11.099, | |
| "eval_steps_per_second": 11.099, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.5873621702194214, | |
| "learning_rate": 6.11764705882353e-05, | |
| "loss": 0.943, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.5609561800956726, | |
| "learning_rate": 6.352941176470588e-05, | |
| "loss": 0.9986, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.5394548177719116, | |
| "learning_rate": 6.588235294117648e-05, | |
| "loss": 0.9848, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.5527498722076416, | |
| "learning_rate": 6.823529411764707e-05, | |
| "loss": 1.0181, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.5643818974494934, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.9044, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.5956369042396545, | |
| "learning_rate": 7.294117647058823e-05, | |
| "loss": 0.9518, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.566049337387085, | |
| "learning_rate": 7.529411764705883e-05, | |
| "loss": 0.9283, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.5462525486946106, | |
| "learning_rate": 7.764705882352942e-05, | |
| "loss": 0.9133, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.6023619174957275, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8935, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.961121141910553, | |
| "eval_runtime": 3.2502, | |
| "eval_samples_per_second": 11.076, | |
| "eval_steps_per_second": 11.076, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.558571457862854, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.8811, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.6055217981338501, | |
| "learning_rate": 8.470588235294118e-05, | |
| "loss": 0.8486, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.5949888229370117, | |
| "learning_rate": 8.705882352941177e-05, | |
| "loss": 0.8664, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.6656898260116577, | |
| "learning_rate": 8.941176470588236e-05, | |
| "loss": 0.8458, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.6678957939147949, | |
| "learning_rate": 9.176470588235295e-05, | |
| "loss": 0.8839, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.6404339671134949, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.8121, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.642274796962738, | |
| "learning_rate": 9.647058823529412e-05, | |
| "loss": 0.8434, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.7844101786613464, | |
| "learning_rate": 9.882352941176471e-05, | |
| "loss": 0.827, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.933869481086731, | |
| "eval_runtime": 3.1753, | |
| "eval_samples_per_second": 11.337, | |
| "eval_steps_per_second": 11.337, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.0588235294117645, | |
| "grad_norm": 0.6803512573242188, | |
| "learning_rate": 9.99995783847866e-05, | |
| "loss": 0.7698, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 0.6696349382400513, | |
| "learning_rate": 9.999620550574153e-05, | |
| "loss": 0.787, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 0.6686673164367676, | |
| "learning_rate": 9.998945997517956e-05, | |
| "loss": 0.7287, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.411764705882353, | |
| "grad_norm": 0.8087121844291687, | |
| "learning_rate": 9.997934224814173e-05, | |
| "loss": 0.7254, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.529411764705882, | |
| "grad_norm": 0.9504140019416809, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.7064, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 0.8831130266189575, | |
| "learning_rate": 9.994899316216708e-05, | |
| "loss": 0.6844, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 5.764705882352941, | |
| "grad_norm": 0.8389394283294678, | |
| "learning_rate": 9.992876385052345e-05, | |
| "loss": 0.7467, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 0.861285924911499, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.773, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.8316490650177002, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7407, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9278689622879028, | |
| "eval_runtime": 3.2054, | |
| "eval_samples_per_second": 11.231, | |
| "eval_steps_per_second": 11.231, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 0.8588041067123413, | |
| "learning_rate": 9.984787389787688e-05, | |
| "loss": 0.5792, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.235294117647059, | |
| "grad_norm": 0.874444305896759, | |
| "learning_rate": 9.981418263742148e-05, | |
| "loss": 0.6258, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.352941176470588, | |
| "grad_norm": 0.8826048374176025, | |
| "learning_rate": 9.977713100437509e-05, | |
| "loss": 0.5959, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 1.0741201639175415, | |
| "learning_rate": 9.973672149817232e-05, | |
| "loss": 0.599, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 2.03265643119812, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 0.5829, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 6.705882352941177, | |
| "grad_norm": 1.414567470550537, | |
| "learning_rate": 9.964583999643174e-05, | |
| "loss": 0.6267, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.823529411764706, | |
| "grad_norm": 1.147159218788147, | |
| "learning_rate": 9.95953741315919e-05, | |
| "loss": 0.5487, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 6.9411764705882355, | |
| "grad_norm": 1.2041115760803223, | |
| "learning_rate": 9.954156265457801e-05, | |
| "loss": 0.5958, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.979455292224884, | |
| "eval_runtime": 3.241, | |
| "eval_samples_per_second": 11.108, | |
| "eval_steps_per_second": 11.108, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 1.0014081001281738, | |
| "learning_rate": 9.948440919541278e-05, | |
| "loss": 0.5794, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.176470588235294, | |
| "grad_norm": 1.009001612663269, | |
| "learning_rate": 9.942391760956277e-05, | |
| "loss": 0.4625, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.294117647058823, | |
| "grad_norm": 1.1101174354553223, | |
| "learning_rate": 9.936009197767845e-05, | |
| "loss": 0.4484, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.411764705882353, | |
| "grad_norm": 1.410061240196228, | |
| "learning_rate": 9.929293660531888e-05, | |
| "loss": 0.4385, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 1.6077678203582764, | |
| "learning_rate": 9.922245602266118e-05, | |
| "loss": 0.4205, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 1.6185195446014404, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.4509, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.764705882352941, | |
| "grad_norm": 1.506198763847351, | |
| "learning_rate": 9.90715384684021e-05, | |
| "loss": 0.434, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 7.882352941176471, | |
| "grad_norm": 1.2955230474472046, | |
| "learning_rate": 9.899111167741966e-05, | |
| "loss": 0.4812, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.3530545234680176, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.4738, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0904909372329712, | |
| "eval_runtime": 3.2248, | |
| "eval_samples_per_second": 11.163, | |
| "eval_steps_per_second": 11.163, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.117647058823529, | |
| "grad_norm": 1.145385980606079, | |
| "learning_rate": 9.882034919459555e-05, | |
| "loss": 0.3233, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 1.1618925333023071, | |
| "learning_rate": 9.873002502207503e-05, | |
| "loss": 0.3232, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.352941176470589, | |
| "grad_norm": 1.4919087886810303, | |
| "learning_rate": 9.863641361223024e-05, | |
| "loss": 0.2922, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 1.4797271490097046, | |
| "learning_rate": 9.853952127991372e-05, | |
| "loss": 0.3519, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 8.588235294117647, | |
| "grad_norm": 2.053419351577759, | |
| "learning_rate": 9.843935456130295e-05, | |
| "loss": 0.3247, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.705882352941176, | |
| "grad_norm": 1.6330363750457764, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 0.2855, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 1.7503317594528198, | |
| "learning_rate": 9.822922521387276e-05, | |
| "loss": 0.353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 1.9878220558166504, | |
| "learning_rate": 9.811927675999036e-05, | |
| "loss": 0.3328, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.3366488218307495, | |
| "eval_runtime": 3.1728, | |
| "eval_samples_per_second": 11.346, | |
| "eval_steps_per_second": 11.346, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.058823529411764, | |
| "grad_norm": 1.2611256837844849, | |
| "learning_rate": 9.800608226873142e-05, | |
| "loss": 0.2561, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.176470588235293, | |
| "grad_norm": 1.37074875831604, | |
| "learning_rate": 9.788964937598689e-05, | |
| "loss": 0.2339, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.294117647058824, | |
| "grad_norm": 1.5084260702133179, | |
| "learning_rate": 9.776998593610428e-05, | |
| "loss": 0.2086, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.6777526140213013, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.231, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.529411764705882, | |
| "grad_norm": 1.6174005270004272, | |
| "learning_rate": 9.752099992140399e-05, | |
| "loss": 0.1978, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 9.647058823529411, | |
| "grad_norm": 1.7943024635314941, | |
| "learning_rate": 9.739169414272217e-05, | |
| "loss": 0.2341, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.764705882352942, | |
| "grad_norm": 1.7131166458129883, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 0.2301, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 9.882352941176471, | |
| "grad_norm": 1.6622118949890137, | |
| "learning_rate": 9.71235006557497e-05, | |
| "loss": 0.2313, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.804017186164856, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2352, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.5624709129333496, | |
| "eval_runtime": 3.2479, | |
| "eval_samples_per_second": 11.084, | |
| "eval_steps_per_second": 11.084, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.117647058823529, | |
| "grad_norm": 1.4273288249969482, | |
| "learning_rate": 9.684259192656553e-05, | |
| "loss": 0.1517, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.235294117647058, | |
| "grad_norm": 1.3310012817382812, | |
| "learning_rate": 9.669739289925577e-05, | |
| "loss": 0.1501, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.352941176470589, | |
| "grad_norm": 1.6097581386566162, | |
| "learning_rate": 9.654904375222385e-05, | |
| "loss": 0.1573, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 10.470588235294118, | |
| "grad_norm": 1.6645879745483398, | |
| "learning_rate": 9.639755449282875e-05, | |
| "loss": 0.1506, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 10.588235294117647, | |
| "grad_norm": 1.8366305828094482, | |
| "learning_rate": 9.62429353402556e-05, | |
| "loss": 0.1654, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.705882352941176, | |
| "grad_norm": 1.6256617307662964, | |
| "learning_rate": 9.608519672482636e-05, | |
| "loss": 0.1921, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.823529411764707, | |
| "grad_norm": 1.610995888710022, | |
| "learning_rate": 9.592434928729616e-05, | |
| "loss": 0.167, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 10.941176470588236, | |
| "grad_norm": 1.6675574779510498, | |
| "learning_rate": 9.576040387813552e-05, | |
| "loss": 0.1754, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.6811158657073975, | |
| "eval_runtime": 3.1996, | |
| "eval_samples_per_second": 11.252, | |
| "eval_steps_per_second": 11.252, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.058823529411764, | |
| "grad_norm": 1.390575885772705, | |
| "learning_rate": 9.559337155679842e-05, | |
| "loss": 0.1403, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.176470588235293, | |
| "grad_norm": 1.263203740119934, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.1194, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.294117647058824, | |
| "grad_norm": 1.2151466608047485, | |
| "learning_rate": 9.525009145583745e-05, | |
| "loss": 0.1169, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 11.411764705882353, | |
| "grad_norm": 1.5443471670150757, | |
| "learning_rate": 9.507386683325404e-05, | |
| "loss": 0.1249, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 11.529411764705882, | |
| "grad_norm": 1.971842885017395, | |
| "learning_rate": 9.489460161101291e-05, | |
| "loss": 0.1374, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 11.647058823529411, | |
| "grad_norm": 1.6832834482192993, | |
| "learning_rate": 9.471230788201429e-05, | |
| "loss": 0.1198, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 1.4485572576522827, | |
| "learning_rate": 9.452699794345581e-05, | |
| "loss": 0.12, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.882352941176471, | |
| "grad_norm": 1.4913806915283203, | |
| "learning_rate": 9.43386842960031e-05, | |
| "loss": 0.1121, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.5377891063690186, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1229, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.821463942527771, | |
| "eval_runtime": 3.2352, | |
| "eval_samples_per_second": 11.127, | |
| "eval_steps_per_second": 11.127, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.117647058823529, | |
| "grad_norm": 0.9307077527046204, | |
| "learning_rate": 9.395309688934351e-05, | |
| "loss": 0.0877, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.235294117647058, | |
| "grad_norm": 1.4314453601837158, | |
| "learning_rate": 9.375584914114963e-05, | |
| "loss": 0.0962, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 12.352941176470589, | |
| "grad_norm": 1.3369566202163696, | |
| "learning_rate": 9.355564970433288e-05, | |
| "loss": 0.1064, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.470588235294118, | |
| "grad_norm": 1.500665545463562, | |
| "learning_rate": 9.335251208397684e-05, | |
| "loss": 0.0932, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 12.588235294117647, | |
| "grad_norm": 1.5071280002593994, | |
| "learning_rate": 9.314644998336949e-05, | |
| "loss": 0.0974, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 12.705882352941176, | |
| "grad_norm": 1.623448133468628, | |
| "learning_rate": 9.293747730307889e-05, | |
| "loss": 0.1044, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 12.823529411764707, | |
| "grad_norm": 1.0675303936004639, | |
| "learning_rate": 9.272560814001539e-05, | |
| "loss": 0.0995, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 12.941176470588236, | |
| "grad_norm": 2.572380304336548, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.1126, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.8674242496490479, | |
| "eval_runtime": 3.2508, | |
| "eval_samples_per_second": 11.074, | |
| "eval_steps_per_second": 11.074, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 221, | |
| "total_flos": 7837976520294400.0, | |
| "train_loss": 0.7398496248940537, | |
| "train_runtime": 766.0105, | |
| "train_samples_per_second": 8.877, | |
| "train_steps_per_second": 1.11 | |
| } | |
| ], | |
| "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": 7837976520294400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |