Add 1epoch model
Browse files- adapter_config.json +18 -0
- adapter_model.bin +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +250 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-65b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"lora_alpha": 8,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"merge_weights": false,
|
| 10 |
+
"modules_to_save": null,
|
| 11 |
+
"peft_type": "LORA",
|
| 12 |
+
"r": 8,
|
| 13 |
+
"target_modules": [
|
| 14 |
+
"q_proj",
|
| 15 |
+
"v_proj"
|
| 16 |
+
],
|
| 17 |
+
"task_type": "CAUSAL_LM"
|
| 18 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ca454d8ba439b4cef7beede18ffae063dd2beec9865effd22c0da7f6d8401f
|
| 3 |
+
size 84001933
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea735ae0c189065358f008d523f4f1807a7fa29c59cc7362a0139b7f2f3b08c7
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d18ab954df86b57e3eba640e829940adb19509a7bba9768a5cd80012e190d0f
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,250 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.998109640831758,
|
| 5 |
+
"global_step": 396,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 1.6488,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 1e-05,
|
| 19 |
+
"loss": 1.6585,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 1.5e-05,
|
| 25 |
+
"loss": 1.6373,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 1.5933,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 2.5e-05,
|
| 37 |
+
"loss": 1.4982,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 1.3297,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18,
|
| 48 |
+
"learning_rate": 3.5e-05,
|
| 49 |
+
"loss": 1.1515,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 4e-05,
|
| 55 |
+
"loss": 0.9944,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 4.5e-05,
|
| 61 |
+
"loss": 0.8887,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 0.8275,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.28,
|
| 72 |
+
"learning_rate": 4.954044117647059e-05,
|
| 73 |
+
"loss": 0.8152,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3,
|
| 78 |
+
"learning_rate": 4.908088235294118e-05,
|
| 79 |
+
"loss": 0.7991,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33,
|
| 84 |
+
"learning_rate": 4.8621323529411765e-05,
|
| 85 |
+
"loss": 0.7932,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35,
|
| 90 |
+
"learning_rate": 4.816176470588236e-05,
|
| 91 |
+
"loss": 0.7928,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 4.7702205882352946e-05,
|
| 97 |
+
"loss": 0.7968,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"learning_rate": 4.7242647058823534e-05,
|
| 103 |
+
"loss": 0.7744,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.43,
|
| 108 |
+
"learning_rate": 4.678308823529412e-05,
|
| 109 |
+
"loss": 0.7791,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.45,
|
| 114 |
+
"learning_rate": 4.632352941176471e-05,
|
| 115 |
+
"loss": 0.7736,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.48,
|
| 120 |
+
"learning_rate": 4.5863970588235296e-05,
|
| 121 |
+
"loss": 0.766,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5,
|
| 126 |
+
"learning_rate": 4.5404411764705883e-05,
|
| 127 |
+
"loss": 0.7717,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.53,
|
| 132 |
+
"learning_rate": 4.494485294117647e-05,
|
| 133 |
+
"loss": 0.7638,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 4.448529411764706e-05,
|
| 139 |
+
"loss": 0.768,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.58,
|
| 144 |
+
"learning_rate": 4.4025735294117646e-05,
|
| 145 |
+
"loss": 0.7573,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6,
|
| 150 |
+
"learning_rate": 4.356617647058824e-05,
|
| 151 |
+
"loss": 0.7633,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.63,
|
| 156 |
+
"learning_rate": 4.310661764705883e-05,
|
| 157 |
+
"loss": 0.7562,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.66,
|
| 162 |
+
"learning_rate": 4.2647058823529415e-05,
|
| 163 |
+
"loss": 0.7576,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.68,
|
| 168 |
+
"learning_rate": 4.21875e-05,
|
| 169 |
+
"loss": 0.7516,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.71,
|
| 174 |
+
"learning_rate": 4.172794117647059e-05,
|
| 175 |
+
"loss": 0.7501,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.73,
|
| 180 |
+
"learning_rate": 4.126838235294118e-05,
|
| 181 |
+
"loss": 0.7601,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.76,
|
| 186 |
+
"learning_rate": 4.0808823529411765e-05,
|
| 187 |
+
"loss": 0.7502,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.78,
|
| 192 |
+
"learning_rate": 4.034926470588236e-05,
|
| 193 |
+
"loss": 0.7583,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.81,
|
| 198 |
+
"learning_rate": 3.9889705882352946e-05,
|
| 199 |
+
"loss": 0.756,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.83,
|
| 204 |
+
"learning_rate": 3.943014705882353e-05,
|
| 205 |
+
"loss": 0.7511,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.86,
|
| 210 |
+
"learning_rate": 3.897058823529412e-05,
|
| 211 |
+
"loss": 0.7434,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.88,
|
| 216 |
+
"learning_rate": 3.851102941176471e-05,
|
| 217 |
+
"loss": 0.7586,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.91,
|
| 222 |
+
"learning_rate": 3.8051470588235296e-05,
|
| 223 |
+
"loss": 0.7486,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.93,
|
| 228 |
+
"learning_rate": 3.759191176470588e-05,
|
| 229 |
+
"loss": 0.7499,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.96,
|
| 234 |
+
"learning_rate": 3.713235294117647e-05,
|
| 235 |
+
"loss": 0.7516,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.98,
|
| 240 |
+
"learning_rate": 3.667279411764706e-05,
|
| 241 |
+
"loss": 0.7451,
|
| 242 |
+
"step": 390
|
| 243 |
+
}
|
| 244 |
+
],
|
| 245 |
+
"max_steps": 1188,
|
| 246 |
+
"num_train_epochs": 3,
|
| 247 |
+
"total_flos": 2.029497948313328e+19,
|
| 248 |
+
"trial_name": null,
|
| 249 |
+
"trial_params": null
|
| 250 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baaefb296ca3f2ea5ac43d1c93e94737ceedd062a7f88ff43312037af8e3dd24
|
| 3 |
+
size 3579
|