Upload folder using huggingface_hub
Browse files- analysis/final/critical_pattern.png +0 -0
- analysis/final/head_ablation.png +0 -0
- analysis/final/lookup_current.png +0 -0
- analysis/final/lookup_next.png +0 -0
- analysis/final/lookup_next_pattern.png +0 -0
- analysis/final/results.json +219 -0
- analysis/final/source-snapshot.tar.gz +3 -0
- metrics.json +228 -0
- model.safetensors +3 -0
- model_config.json +81 -0
- source-snapshot.tar.gz +3 -0
- training.png +0 -0
analysis/final/critical_pattern.png
ADDED
|
analysis/final/head_ablation.png
ADDED
|
analysis/final/lookup_current.png
ADDED
|
analysis/final/lookup_next.png
ADDED
|
analysis/final/lookup_next_pattern.png
ADDED
|
analysis/final/results.json
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run": "runs/default-seed0",
|
| 3 |
+
"code": {
|
| 4 |
+
"commit": "19276f75392bee9d5f6f61820395002a0746e349",
|
| 5 |
+
"dirty": true,
|
| 6 |
+
"snapshot": "source-snapshot.tar.gz"
|
| 7 |
+
},
|
| 8 |
+
"environment": {
|
| 9 |
+
"python": "3.12.3",
|
| 10 |
+
"torch": "2.15.0+cu132",
|
| 11 |
+
"device": "cuda",
|
| 12 |
+
"precision": "torch.float32",
|
| 13 |
+
"uv_lock_sha256": "60eba889e8dcd90d00fdcc282a51fc42df3869f3ef3807b1946aaa3cfd5f62e2",
|
| 14 |
+
"gpu": "NVIDIA GeForce RTX 3060",
|
| 15 |
+
"cuda": "13.2"
|
| 16 |
+
},
|
| 17 |
+
"test_size": 2048,
|
| 18 |
+
"chance_token_accuracy": 0.015625,
|
| 19 |
+
"trained": {
|
| 20 |
+
"loss": 4.249109224474523e-06,
|
| 21 |
+
"token_accuracy": 1.0,
|
| 22 |
+
"exact_match": 1.0
|
| 23 |
+
},
|
| 24 |
+
"untrained": {
|
| 25 |
+
"loss": 4.214900970458984,
|
| 26 |
+
"token_accuracy": 0.01812744140625,
|
| 27 |
+
"exact_match": 0.0
|
| 28 |
+
},
|
| 29 |
+
"head_ablation": {
|
| 30 |
+
"clean_loss": 4.249109224474523e-06,
|
| 31 |
+
"identity_patch_max_logit_change": 0.0,
|
| 32 |
+
"loss_rise": [
|
| 33 |
+
[
|
| 34 |
+
0.09456062089066108,
|
| 35 |
+
0.006693977446957433,
|
| 36 |
+
2.235693497167631,
|
| 37 |
+
0.15027083228687843,
|
| 38 |
+
0.07599250744442543,
|
| 39 |
+
0.00419125804091891,
|
| 40 |
+
0.10219017933468422,
|
| 41 |
+
5.169036907659574
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
0.00025813918091444066,
|
| 45 |
+
2.973878781631356e-05,
|
| 46 |
+
0.00024059577026491752,
|
| 47 |
+
0.0009068534045582055,
|
| 48 |
+
0.003771953800423944,
|
| 49 |
+
0.0006174362997626304,
|
| 50 |
+
0.000752416023715341,
|
| 51 |
+
0.004184644253655279
|
| 52 |
+
],
|
| 53 |
+
[
|
| 54 |
+
0.00014806245508225402,
|
| 55 |
+
4.894880476058461e-06,
|
| 56 |
+
2.7085926376457792e-05,
|
| 57 |
+
0.00017150774419860682,
|
| 58 |
+
0.00021039024341007462,
|
| 59 |
+
0.0007992379169081687,
|
| 60 |
+
0.0008647132117403089,
|
| 61 |
+
1.1404487850086298e-05
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
1.613488984730793e-05,
|
| 65 |
+
8.192873792722821e-07,
|
| 66 |
+
1.7713737179292366e-06,
|
| 67 |
+
2.291507462359732e-05,
|
| 68 |
+
0.0001252591091542854,
|
| 69 |
+
5.263272214506287e-06,
|
| 70 |
+
4.800411898031598e-05,
|
| 71 |
+
7.388479389192071e-06
|
| 72 |
+
]
|
| 73 |
+
],
|
| 74 |
+
"token_accuracy_drop": [
|
| 75 |
+
[
|
| 76 |
+
0.021453857421875,
|
| 77 |
+
0.001556396484375,
|
| 78 |
+
0.322906494140625,
|
| 79 |
+
0.017242431640625,
|
| 80 |
+
0.010345458984375,
|
| 81 |
+
0.00079345703125,
|
| 82 |
+
0.010589599609375,
|
| 83 |
+
0.764434814453125
|
| 84 |
+
],
|
| 85 |
+
[
|
| 86 |
+
6.103515625e-05,
|
| 87 |
+
3.0517578125e-05,
|
| 88 |
+
9.1552734375e-05,
|
| 89 |
+
0.0003662109375,
|
| 90 |
+
0.001220703125,
|
| 91 |
+
0.00018310546875,
|
| 92 |
+
0.000274658203125,
|
| 93 |
+
0.00128173828125
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
3.0517578125e-05,
|
| 97 |
+
0.0,
|
| 98 |
+
0.0,
|
| 99 |
+
6.103515625e-05,
|
| 100 |
+
0.0001220703125,
|
| 101 |
+
0.000152587890625,
|
| 102 |
+
0.00030517578125,
|
| 103 |
+
0.0
|
| 104 |
+
],
|
| 105 |
+
[
|
| 106 |
+
0.0,
|
| 107 |
+
0.0,
|
| 108 |
+
0.0,
|
| 109 |
+
0.0,
|
| 110 |
+
0.0,
|
| 111 |
+
0.0,
|
| 112 |
+
0.0,
|
| 113 |
+
0.0
|
| 114 |
+
]
|
| 115 |
+
],
|
| 116 |
+
"layer_loss_rise": [
|
| 117 |
+
13.57202391098599,
|
| 118 |
+
0.19787378381352028,
|
| 119 |
+
0.04730297024707397,
|
| 120 |
+
0.0025761095375855803
|
| 121 |
+
],
|
| 122 |
+
"layer_token_accuracy_drop": [
|
| 123 |
+
0.88677978515625,
|
| 124 |
+
0.04681396484375,
|
| 125 |
+
0.016082763671875,
|
| 126 |
+
0.000274658203125
|
| 127 |
+
]
|
| 128 |
+
},
|
| 129 |
+
"lookup_next": {
|
| 130 |
+
"score": [
|
| 131 |
+
[
|
| 132 |
+
0.196746826171875,
|
| 133 |
+
0.322418212890625,
|
| 134 |
+
0.204315185546875,
|
| 135 |
+
0.372955322265625,
|
| 136 |
+
0.4195556640625,
|
| 137 |
+
0.290557861328125,
|
| 138 |
+
0.11737060546875,
|
| 139 |
+
0.136383056640625
|
| 140 |
+
],
|
| 141 |
+
[
|
| 142 |
+
0.53216552734375,
|
| 143 |
+
0.451263427734375,
|
| 144 |
+
0.471405029296875,
|
| 145 |
+
0.4954833984375,
|
| 146 |
+
0.45703125,
|
| 147 |
+
0.5029296875,
|
| 148 |
+
0.46435546875,
|
| 149 |
+
0.466583251953125
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
0.43756103515625,
|
| 153 |
+
0.59722900390625,
|
| 154 |
+
0.504119873046875,
|
| 155 |
+
0.58270263671875,
|
| 156 |
+
0.451690673828125,
|
| 157 |
+
0.468170166015625,
|
| 158 |
+
0.674285888671875,
|
| 159 |
+
0.673553466796875
|
| 160 |
+
],
|
| 161 |
+
[
|
| 162 |
+
0.269866943359375,
|
| 163 |
+
0.328369140625,
|
| 164 |
+
0.2083740234375,
|
| 165 |
+
0.380889892578125,
|
| 166 |
+
0.379302978515625,
|
| 167 |
+
0.265625,
|
| 168 |
+
0.322174072265625,
|
| 169 |
+
0.201141357421875
|
| 170 |
+
]
|
| 171 |
+
],
|
| 172 |
+
"chance": 0.07715225219726562
|
| 173 |
+
},
|
| 174 |
+
"lookup_current": {
|
| 175 |
+
"score": [
|
| 176 |
+
[
|
| 177 |
+
0.58856201171875,
|
| 178 |
+
0.199432373046875,
|
| 179 |
+
0.859954833984375,
|
| 180 |
+
0.282135009765625,
|
| 181 |
+
0.2462158203125,
|
| 182 |
+
0.19976806640625,
|
| 183 |
+
0.03662109375,
|
| 184 |
+
0.988250732421875
|
| 185 |
+
],
|
| 186 |
+
[
|
| 187 |
+
0.286376953125,
|
| 188 |
+
0.254669189453125,
|
| 189 |
+
0.499359130859375,
|
| 190 |
+
0.36083984375,
|
| 191 |
+
0.21551513671875,
|
| 192 |
+
0.195831298828125,
|
| 193 |
+
0.14984130859375,
|
| 194 |
+
0.171142578125
|
| 195 |
+
],
|
| 196 |
+
[
|
| 197 |
+
0.3846435546875,
|
| 198 |
+
0.24420166015625,
|
| 199 |
+
0.2579345703125,
|
| 200 |
+
0.267059326171875,
|
| 201 |
+
0.279937744140625,
|
| 202 |
+
0.378326416015625,
|
| 203 |
+
0.229736328125,
|
| 204 |
+
0.234710693359375
|
| 205 |
+
],
|
| 206 |
+
[
|
| 207 |
+
0.243560791015625,
|
| 208 |
+
0.227264404296875,
|
| 209 |
+
0.204864501953125,
|
| 210 |
+
0.244720458984375,
|
| 211 |
+
0.27691650390625,
|
| 212 |
+
0.246490478515625,
|
| 213 |
+
0.29443359375,
|
| 214 |
+
0.200347900390625
|
| 215 |
+
]
|
| 216 |
+
],
|
| 217 |
+
"chance": 0.07715225219726562
|
| 218 |
+
}
|
| 219 |
+
}
|
analysis/final/source-snapshot.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:495dc85a840188753c5988108593ae96365fd22456f9f8e412970d33522e4f36
|
| 3 |
+
size 189601
|
metrics.json
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"run_name": "default-seed0",
|
| 4 |
+
"seed": 0,
|
| 5 |
+
"quick": false,
|
| 6 |
+
"device": "auto",
|
| 7 |
+
"eval_every": 250,
|
| 8 |
+
"task": {
|
| 9 |
+
"n_values": 64,
|
| 10 |
+
"length": 16
|
| 11 |
+
},
|
| 12 |
+
"splits": {
|
| 13 |
+
"val_seed": 1000003,
|
| 14 |
+
"val_size": 1024,
|
| 15 |
+
"test_seed": 2000003,
|
| 16 |
+
"test_size": 2048
|
| 17 |
+
},
|
| 18 |
+
"model": {
|
| 19 |
+
"n_layers": 4,
|
| 20 |
+
"d_model": 256,
|
| 21 |
+
"n_heads": 8,
|
| 22 |
+
"d_mlp": 1024,
|
| 23 |
+
"mlp": "gelu",
|
| 24 |
+
"norm": "layernorm",
|
| 25 |
+
"dropout": 0.0
|
| 26 |
+
},
|
| 27 |
+
"optim": {
|
| 28 |
+
"steps": 4000,
|
| 29 |
+
"batch_size": 256,
|
| 30 |
+
"lr": 0.001,
|
| 31 |
+
"warmup_steps": 100,
|
| 32 |
+
"min_lr_ratio": 0.1,
|
| 33 |
+
"weight_decay": 0.1,
|
| 34 |
+
"grad_clip": 1.0
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"model_config": {
|
| 38 |
+
"vocab_size": 65,
|
| 39 |
+
"n_layers": 4,
|
| 40 |
+
"d_model": 256,
|
| 41 |
+
"n_heads": 8,
|
| 42 |
+
"d_mlp": 1024,
|
| 43 |
+
"max_seq_len": 33,
|
| 44 |
+
"mlp": "gelu",
|
| 45 |
+
"norm": "layernorm",
|
| 46 |
+
"dropout": 0.0
|
| 47 |
+
},
|
| 48 |
+
"parameters": 3201280,
|
| 49 |
+
"data": {
|
| 50 |
+
"task": "sorting",
|
| 51 |
+
"version": 1,
|
| 52 |
+
"n_values": 64,
|
| 53 |
+
"length": 16,
|
| 54 |
+
"val_seed": 1000003,
|
| 55 |
+
"val_size": 1024,
|
| 56 |
+
"test_seed": 2000003,
|
| 57 |
+
"test_size": 2048,
|
| 58 |
+
"train_seed": 0
|
| 59 |
+
},
|
| 60 |
+
"code": {
|
| 61 |
+
"commit": "19276f75392bee9d5f6f61820395002a0746e349",
|
| 62 |
+
"dirty": true,
|
| 63 |
+
"snapshot": "source-snapshot.tar.gz"
|
| 64 |
+
},
|
| 65 |
+
"environment": {
|
| 66 |
+
"python": "3.12.3",
|
| 67 |
+
"torch": "2.15.0+cu132",
|
| 68 |
+
"device": "cuda",
|
| 69 |
+
"precision": "torch.float32",
|
| 70 |
+
"uv_lock_sha256": "60eba889e8dcd90d00fdcc282a51fc42df3869f3ef3807b1946aaa3cfd5f62e2",
|
| 71 |
+
"gpu": "NVIDIA GeForce RTX 3060",
|
| 72 |
+
"cuda": "13.2"
|
| 73 |
+
},
|
| 74 |
+
"resumable": false,
|
| 75 |
+
"status": "finished",
|
| 76 |
+
"seconds": 646.7,
|
| 77 |
+
"history": [
|
| 78 |
+
{
|
| 79 |
+
"step": 250,
|
| 80 |
+
"train_loss": 0.07291533797979355,
|
| 81 |
+
"val_loss": 0.0985519140958786,
|
| 82 |
+
"val_token_accuracy": 0.9683837890625,
|
| 83 |
+
"val_exact_match": 0.595703125,
|
| 84 |
+
"grad_norm": 2.3497650623321533,
|
| 85 |
+
"lr": 0.0009967189933441244
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"step": 500,
|
| 89 |
+
"train_loss": 0.014207392930984497,
|
| 90 |
+
"val_loss": 0.031683966517448425,
|
| 91 |
+
"val_token_accuracy": 0.99053955078125,
|
| 92 |
+
"val_exact_match": 0.8720703125,
|
| 93 |
+
"grad_norm": 0.7331729531288147,
|
| 94 |
+
"lr": 0.0009768413988762155
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"step": 750,
|
| 98 |
+
"train_loss": 0.02052781730890274,
|
| 99 |
+
"val_loss": 0.023844445124268532,
|
| 100 |
+
"val_token_accuracy": 0.99273681640625,
|
| 101 |
+
"val_exact_match": 0.890625,
|
| 102 |
+
"grad_norm": 1.3566714525222778,
|
| 103 |
+
"lr": 0.0009397114317029974
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"step": 1000,
|
| 107 |
+
"train_loss": 0.009082821197807789,
|
| 108 |
+
"val_loss": 0.01231020875275135,
|
| 109 |
+
"val_token_accuracy": 0.996826171875,
|
| 110 |
+
"val_exact_match": 0.951171875,
|
| 111 |
+
"grad_norm": 0.7233428359031677,
|
| 112 |
+
"lr": 0.0008868298366769955
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"step": 1250,
|
| 116 |
+
"train_loss": 0.00922011211514473,
|
| 117 |
+
"val_loss": 0.019146941602230072,
|
| 118 |
+
"val_token_accuracy": 0.994873046875,
|
| 119 |
+
"val_exact_match": 0.9208984375,
|
| 120 |
+
"grad_norm": 0.5756050944328308,
|
| 121 |
+
"lr": 0.0008203340189070906
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"step": 1500,
|
| 125 |
+
"train_loss": 0.01364622451364994,
|
| 126 |
+
"val_loss": 0.005576150491833687,
|
| 127 |
+
"val_token_accuracy": 0.998779296875,
|
| 128 |
+
"val_exact_match": 0.9814453125,
|
| 129 |
+
"grad_norm": 1.3124696016311646,
|
| 130 |
+
"lr": 0.0007429116526313744
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"step": 1750,
|
| 134 |
+
"train_loss": 0.003266311716288328,
|
| 135 |
+
"val_loss": 0.001853839261457324,
|
| 136 |
+
"val_token_accuracy": 0.9996337890625,
|
| 137 |
+
"val_exact_match": 0.994140625,
|
| 138 |
+
"grad_norm": 0.28147438168525696,
|
| 139 |
+
"lr": 0.0006576920489294011
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"step": 2000,
|
| 143 |
+
"train_loss": 0.005052485503256321,
|
| 144 |
+
"val_loss": 0.0006970376125536859,
|
| 145 |
+
"val_token_accuracy": 0.9998779296875,
|
| 146 |
+
"val_exact_match": 0.998046875,
|
| 147 |
+
"grad_norm": 1.1249206066131592,
|
| 148 |
+
"lr": 0.0005681196730492369
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"step": 2250,
|
| 152 |
+
"train_loss": 0.00020874346955679357,
|
| 153 |
+
"val_loss": 0.0009217980550602078,
|
| 154 |
+
"val_token_accuracy": 0.99981689453125,
|
| 155 |
+
"val_exact_match": 0.9970703125,
|
| 156 |
+
"grad_norm": 0.03951434791088104,
|
| 157 |
+
"lr": 0.00047781492361400794
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"step": 2500,
|
| 161 |
+
"train_loss": 0.001243826001882553,
|
| 162 |
+
"val_loss": 0.0005396516062319279,
|
| 163 |
+
"val_token_accuracy": 0.99981689453125,
|
| 164 |
+
"val_exact_match": 0.9970703125,
|
| 165 |
+
"grad_norm": 0.23733462393283844,
|
| 166 |
+
"lr": 0.0003904278008308589
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"step": 2750,
|
| 170 |
+
"train_loss": 0.00022199669911060482,
|
| 171 |
+
"val_loss": 0.00017582655709702522,
|
| 172 |
+
"val_token_accuracy": 0.99993896484375,
|
| 173 |
+
"val_exact_match": 0.9990234375,
|
| 174 |
+
"grad_norm": 0.11565989255905151,
|
| 175 |
+
"lr": 0.0003094903782424895
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"step": 3000,
|
| 179 |
+
"train_loss": 0.00021956569980829954,
|
| 180 |
+
"val_loss": 8.435545896645635e-05,
|
| 181 |
+
"val_token_accuracy": 1.0,
|
| 182 |
+
"val_exact_match": 1.0,
|
| 183 |
+
"grad_norm": 0.061819761991500854,
|
| 184 |
+
"lr": 0.0002382740409206803
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"step": 3250,
|
| 188 |
+
"train_loss": 3.6058951081940904e-05,
|
| 189 |
+
"val_loss": 8.97766076377593e-05,
|
| 190 |
+
"val_token_accuracy": 0.99993896484375,
|
| 191 |
+
"val_exact_match": 0.9990234375,
|
| 192 |
+
"grad_norm": 0.004151737317442894,
|
| 193 |
+
"lr": 0.00017965726034785466
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"step": 3500,
|
| 197 |
+
"train_loss": 4.75610613648314e-06,
|
| 198 |
+
"val_loss": 9.887960004562046e-06,
|
| 199 |
+
"val_token_accuracy": 1.0,
|
| 200 |
+
"val_exact_match": 1.0,
|
| 201 |
+
"grad_norm": 0.0010888022370636463,
|
| 202 |
+
"lr": 0.00013600925035352912
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"step": 3750,
|
| 206 |
+
"train_loss": 0.00010177387594012544,
|
| 207 |
+
"val_loss": 0.00023778356262482703,
|
| 208 |
+
"val_token_accuracy": 0.99993896484375,
|
| 209 |
+
"val_exact_match": 0.9990234375,
|
| 210 |
+
"grad_norm": 0.09358467906713486,
|
| 211 |
+
"lr": 0.00010909420658097956
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"step": 4000,
|
| 215 |
+
"train_loss": 1.727779454085976e-05,
|
| 216 |
+
"val_loss": 1.847820749389939e-05,
|
| 217 |
+
"val_token_accuracy": 1.0,
|
| 218 |
+
"val_exact_match": 1.0,
|
| 219 |
+
"grad_norm": 0.014979858882725239,
|
| 220 |
+
"lr": 0.0001
|
| 221 |
+
}
|
| 222 |
+
],
|
| 223 |
+
"final": {
|
| 224 |
+
"val_loss": 1.847820749389939e-05,
|
| 225 |
+
"val_token_accuracy": 1.0,
|
| 226 |
+
"val_exact_match": 1.0
|
| 227 |
+
}
|
| 228 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c56f9f38dbed7db80d810f7cbec73980f4303018991b46a0edb1bdf9f962fb68
|
| 3 |
+
size 12811264
|
model_config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format_version": 1,
|
| 3 |
+
"transformer": {
|
| 4 |
+
"vocab_size": 65,
|
| 5 |
+
"n_layers": 4,
|
| 6 |
+
"d_model": 256,
|
| 7 |
+
"n_heads": 8,
|
| 8 |
+
"d_mlp": 1024,
|
| 9 |
+
"max_seq_len": 33,
|
| 10 |
+
"mlp": "gelu",
|
| 11 |
+
"norm": "layernorm",
|
| 12 |
+
"dropout": 0.0
|
| 13 |
+
},
|
| 14 |
+
"vocab": [
|
| 15 |
+
"0",
|
| 16 |
+
"1",
|
| 17 |
+
"2",
|
| 18 |
+
"3",
|
| 19 |
+
"4",
|
| 20 |
+
"5",
|
| 21 |
+
"6",
|
| 22 |
+
"7",
|
| 23 |
+
"8",
|
| 24 |
+
"9",
|
| 25 |
+
"10",
|
| 26 |
+
"11",
|
| 27 |
+
"12",
|
| 28 |
+
"13",
|
| 29 |
+
"14",
|
| 30 |
+
"15",
|
| 31 |
+
"16",
|
| 32 |
+
"17",
|
| 33 |
+
"18",
|
| 34 |
+
"19",
|
| 35 |
+
"20",
|
| 36 |
+
"21",
|
| 37 |
+
"22",
|
| 38 |
+
"23",
|
| 39 |
+
"24",
|
| 40 |
+
"25",
|
| 41 |
+
"26",
|
| 42 |
+
"27",
|
| 43 |
+
"28",
|
| 44 |
+
"29",
|
| 45 |
+
"30",
|
| 46 |
+
"31",
|
| 47 |
+
"32",
|
| 48 |
+
"33",
|
| 49 |
+
"34",
|
| 50 |
+
"35",
|
| 51 |
+
"36",
|
| 52 |
+
"37",
|
| 53 |
+
"38",
|
| 54 |
+
"39",
|
| 55 |
+
"40",
|
| 56 |
+
"41",
|
| 57 |
+
"42",
|
| 58 |
+
"43",
|
| 59 |
+
"44",
|
| 60 |
+
"45",
|
| 61 |
+
"46",
|
| 62 |
+
"47",
|
| 63 |
+
"48",
|
| 64 |
+
"49",
|
| 65 |
+
"50",
|
| 66 |
+
"51",
|
| 67 |
+
"52",
|
| 68 |
+
"53",
|
| 69 |
+
"54",
|
| 70 |
+
"55",
|
| 71 |
+
"56",
|
| 72 |
+
"57",
|
| 73 |
+
"58",
|
| 74 |
+
"59",
|
| 75 |
+
"60",
|
| 76 |
+
"61",
|
| 77 |
+
"62",
|
| 78 |
+
"63",
|
| 79 |
+
"SEP"
|
| 80 |
+
]
|
| 81 |
+
}
|
source-snapshot.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e963742ccde0aca2462ea11e294c6b2504355b7b78eda8738885e210454496e
|
| 3 |
+
size 187056
|
training.png
ADDED
|