File size: 8,513 Bytes
19675be | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | {
"run_id": "20260512_190433",
"model_id": "google/gemma-4-E4B-it",
"adapter_repo": "josephmayo/gemma-4-E4B-it-coding-lora",
"merged_repo": "josephmayo/gemma-4-E4B-it-coding-merged",
"stage": "after_eval",
"errors": [
],
"cuda_available": true,
"cuda_device_count": 2,
"devices": [
"Tesla T4",
"Tesla T4"
],
"torch_version_initial": "2.10.0+cu128",
"hf_token_present": false,
"max_train_samples": 1024,
"max_steps": 200,
"max_seq_length": 512,
"eval_count": 8,
"lora_r": 16,
"lora_alpha": 32,
"lr": 0.0001,
"grad_accum": 8,
"push_to_hf": true,
"merge_and_push": false,
"load_in_4bit": true,
"memory_after_load": [
0,
9302143488
],
"eval_source": "openai/openai_humaneval:8",
"baseline_avg_score": 0.76875,
"safe_train_rows": 1024,
"trainable_parameters": {
"trainable": 50499584,
"total": 7991600416
},
"log_history_tail": [
{
"loss": 1.0154043197631837,
"grad_norm": 0.37521687150001526,
"learning_rate": 4.51495073572676E-05,
"epoch": 1.71875
},
{
"loss": 0.9917967796325684,
"grad_norm": 0.42887604236602783,
"learning_rate": 4.1140450421038868E-05,
"epoch": 1.796875
},
{
"loss": 1.1146905899047852,
"grad_norm": 0.4208148717880249,
"learning_rate": 3.718944461187138E-05,
"epoch": 1.875
},
{
"loss": 0.9283761978149414,
"grad_norm": 0.3849687874317169,
"learning_rate": 3.332237841745898E-05,
"epoch": 1.953125
},
{
"loss": 1.113053035736084,
"grad_norm": 0.4142734110355377,
"learning_rate": 2.9564590321322207E-05,
"epoch": 2.03125
},
{
"loss": 0.9842248916625976,
"grad_norm": 0.44529953598976135,
"learning_rate": 2.5940702775459747E-05,
"epoch": 2.109375
},
{
"loss": 0.9449721336364746,
"grad_norm": 0.3756776750087738,
"learning_rate": 2.2474460864709824E-05,
"epoch": 2.1875
},
{
"loss": 1.0590093612670899,
"grad_norm": 0.4192875325679779,
"learning_rate": 1.9188576719953633E-05,
"epoch": 2.265625
},
{
"loss": 0.9768091201782226,
"grad_norm": 0.5095818638801575,
"learning_rate": 1.6104580699624837E-05,
"epoch": 2.34375
},
{
"loss": 1.038302516937256,
"grad_norm": 0.41709497570991516,
"learning_rate": 1.3242680314639993E-05,
"epoch": 2.421875
},
{
"loss": 0.9975608825683594,
"grad_norm": 0.5563586354255676,
"learning_rate": 1.0621627821127289E-05,
"epoch": 2.5
},
{
"loss": 0.9714397430419922,
"grad_norm": 0.8915637135505676,
"learning_rate": 8.25859734853645E-06,
"epoch": 2.578125
},
{
"loss": 0.9948483467102051,
"grad_norm": 0.4391196370124817,
"learning_rate": 6.16907236823262E-06,
"epoch": 2.65625
},
{
"loss": 0.9389057159423828,
"grad_norm": 0.4650712311267853,
"learning_rate": 4.3667442399229984E-06,
"epoch": 2.734375
},
{
"loss": 1.06390380859375,
"grad_norm": 0.4836062788963318,
"learning_rate": 2.8634225006782865E-06,
"epoch": 2.8125
},
{
"loss": 1.008359718322754,
"grad_norm": 0.45215511322021484,
"learning_rate": 1.6689574843694433E-06,
"epoch": 2.890625
},
{
"loss": 1.0110493659973145,
"grad_norm": 0.5408219695091248,
"learning_rate": 7.9117577854628813E-07,
"epoch": 2.96875
},
{
"loss": 0.911649227142334,
"grad_norm": 0.4599083364009857,
"learning_rate": 2.3582894166930268E-07,
"epoch": 3.046875
},
{
"loss": 0.9673548698425293,
"grad_norm": 0.43304941058158875,
"learning_rate": 6.5558167183898955E-09,
"epoch": 3.125
},
{
"train_runtime": 4256.6409,
"train_samples_per_second": 0.752,
"train_steps_per_second": 0.047,
"total_flos": 42593137620095232,
"train_loss": 1.142699921131134,
"epoch": 3.125
}
],
"train_metrics": {
"train_runtime": 4256.6409,
"train_samples_per_second": 0.752,
"train_steps_per_second": 0.047,
"total_flos": 42593137620095232,
"train_loss": 1.142699921131134,
"epoch": 3.125
},
"after_avg_score": 0.76875,
"score_delta": 0.0,
"adapter_dir": "/kaggle/working/gemma4_e4b_coding_lora",
"release_gate_pass": true,
"data_description": "filtered benign coding instruction data"
}
|