Training in progress, epoch 0
Browse files- adapter_config.json +6 -3
- adapter_model.safetensors +2 -2
- trainer_state.json +380 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,10 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
-
"q_proj",
|
| 25 |
"o_proj",
|
| 26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca8063b1bccb8b154202f4a9d4101c79bd50a1226d01702c835f0370cb387250
|
| 3 |
+
size 39256704
|
trainer_state.json
ADDED
|
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.950248756218905,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19900497512437812,
|
| 13 |
+
"grad_norm": 0.258056640625,
|
| 14 |
+
"learning_rate": 0.00019980267284282717,
|
| 15 |
+
"loss": 0.7217,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.39800995024875624,
|
| 20 |
+
"grad_norm": 0.217041015625,
|
| 21 |
+
"learning_rate": 0.0001992114701314478,
|
| 22 |
+
"loss": 0.665,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5970149253731343,
|
| 27 |
+
"grad_norm": 0.4091796875,
|
| 28 |
+
"learning_rate": 0.0001982287250728689,
|
| 29 |
+
"loss": 0.685,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7960199004975125,
|
| 34 |
+
"grad_norm": 0.393798828125,
|
| 35 |
+
"learning_rate": 0.0001968583161128631,
|
| 36 |
+
"loss": 0.7191,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9950248756218906,
|
| 41 |
+
"grad_norm": 0.33740234375,
|
| 42 |
+
"learning_rate": 0.00019510565162951537,
|
| 43 |
+
"loss": 0.7127,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.1940298507462686,
|
| 48 |
+
"grad_norm": 1.5546875,
|
| 49 |
+
"learning_rate": 0.00019297764858882514,
|
| 50 |
+
"loss": 0.7251,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.3930348258706466,
|
| 55 |
+
"grad_norm": 0.347412109375,
|
| 56 |
+
"learning_rate": 0.00019048270524660196,
|
| 57 |
+
"loss": 0.6989,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.5920398009950247,
|
| 62 |
+
"grad_norm": 0.362060546875,
|
| 63 |
+
"learning_rate": 0.00018763066800438636,
|
| 64 |
+
"loss": 0.6677,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.7910447761194028,
|
| 69 |
+
"grad_norm": 0.39794921875,
|
| 70 |
+
"learning_rate": 0.00018443279255020152,
|
| 71 |
+
"loss": 0.6782,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.9900497512437811,
|
| 76 |
+
"grad_norm": 0.428955078125,
|
| 77 |
+
"learning_rate": 0.00018090169943749476,
|
| 78 |
+
"loss": 0.6859,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.189054726368159,
|
| 83 |
+
"grad_norm": 0.41259765625,
|
| 84 |
+
"learning_rate": 0.00017705132427757895,
|
| 85 |
+
"loss": 0.6552,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.388059701492537,
|
| 90 |
+
"grad_norm": 0.359130859375,
|
| 91 |
+
"learning_rate": 0.00017289686274214118,
|
| 92 |
+
"loss": 0.6583,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.587064676616915,
|
| 97 |
+
"grad_norm": 0.425537109375,
|
| 98 |
+
"learning_rate": 0.00016845471059286887,
|
| 99 |
+
"loss": 0.647,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.7860696517412933,
|
| 104 |
+
"grad_norm": 0.403564453125,
|
| 105 |
+
"learning_rate": 0.000163742398974869,
|
| 106 |
+
"loss": 0.6839,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.9850746268656714,
|
| 111 |
+
"grad_norm": 0.406982421875,
|
| 112 |
+
"learning_rate": 0.00015877852522924732,
|
| 113 |
+
"loss": 0.6724,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.18407960199005,
|
| 118 |
+
"grad_norm": 0.3798828125,
|
| 119 |
+
"learning_rate": 0.00015358267949789966,
|
| 120 |
+
"loss": 0.6476,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.383084577114428,
|
| 125 |
+
"grad_norm": 0.41455078125,
|
| 126 |
+
"learning_rate": 0.00014817536741017152,
|
| 127 |
+
"loss": 0.6179,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.582089552238806,
|
| 132 |
+
"grad_norm": 0.494140625,
|
| 133 |
+
"learning_rate": 0.00014257792915650728,
|
| 134 |
+
"loss": 0.6344,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.781094527363184,
|
| 139 |
+
"grad_norm": 0.54443359375,
|
| 140 |
+
"learning_rate": 0.00013681245526846783,
|
| 141 |
+
"loss": 0.6503,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.9800995024875623,
|
| 146 |
+
"grad_norm": 0.46484375,
|
| 147 |
+
"learning_rate": 0.00013090169943749476,
|
| 148 |
+
"loss": 0.6389,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.17910447761194,
|
| 153 |
+
"grad_norm": 0.40673828125,
|
| 154 |
+
"learning_rate": 0.0001248689887164855,
|
| 155 |
+
"loss": 0.6063,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.378109452736318,
|
| 160 |
+
"grad_norm": 0.494140625,
|
| 161 |
+
"learning_rate": 0.00011873813145857249,
|
| 162 |
+
"loss": 0.6267,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.577114427860696,
|
| 167 |
+
"grad_norm": 0.443603515625,
|
| 168 |
+
"learning_rate": 0.00011253332335643043,
|
| 169 |
+
"loss": 0.6111,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.776119402985074,
|
| 174 |
+
"grad_norm": 0.525390625,
|
| 175 |
+
"learning_rate": 0.00010627905195293135,
|
| 176 |
+
"loss": 0.6374,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.975124378109452,
|
| 181 |
+
"grad_norm": 0.5419921875,
|
| 182 |
+
"learning_rate": 0.0001,
|
| 183 |
+
"loss": 0.6143,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.174129353233831,
|
| 188 |
+
"grad_norm": 0.451416015625,
|
| 189 |
+
"learning_rate": 9.372094804706867e-05,
|
| 190 |
+
"loss": 0.5851,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.373134328358209,
|
| 195 |
+
"grad_norm": 0.459716796875,
|
| 196 |
+
"learning_rate": 8.746667664356956e-05,
|
| 197 |
+
"loss": 0.6088,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.572139303482587,
|
| 202 |
+
"grad_norm": 0.4765625,
|
| 203 |
+
"learning_rate": 8.126186854142752e-05,
|
| 204 |
+
"loss": 0.5803,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.7711442786069655,
|
| 209 |
+
"grad_norm": 0.5380859375,
|
| 210 |
+
"learning_rate": 7.513101128351454e-05,
|
| 211 |
+
"loss": 0.6084,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 5.970149253731344,
|
| 216 |
+
"grad_norm": 0.5205078125,
|
| 217 |
+
"learning_rate": 6.909830056250527e-05,
|
| 218 |
+
"loss": 0.599,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.169154228855722,
|
| 223 |
+
"grad_norm": 0.52294921875,
|
| 224 |
+
"learning_rate": 6.318754473153221e-05,
|
| 225 |
+
"loss": 0.5874,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 6.3681592039801,
|
| 230 |
+
"grad_norm": 0.5244140625,
|
| 231 |
+
"learning_rate": 5.7422070843492734e-05,
|
| 232 |
+
"loss": 0.5631,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.567164179104478,
|
| 237 |
+
"grad_norm": 0.5087890625,
|
| 238 |
+
"learning_rate": 5.182463258982846e-05,
|
| 239 |
+
"loss": 0.5574,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.766169154228856,
|
| 244 |
+
"grad_norm": 0.5107421875,
|
| 245 |
+
"learning_rate": 4.6417320502100316e-05,
|
| 246 |
+
"loss": 0.5902,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 6.965174129353234,
|
| 251 |
+
"grad_norm": 0.53369140625,
|
| 252 |
+
"learning_rate": 4.12214747707527e-05,
|
| 253 |
+
"loss": 0.5869,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.164179104477612,
|
| 258 |
+
"grad_norm": 0.54638671875,
|
| 259 |
+
"learning_rate": 3.6257601025131026e-05,
|
| 260 |
+
"loss": 0.5644,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.36318407960199,
|
| 265 |
+
"grad_norm": 0.533203125,
|
| 266 |
+
"learning_rate": 3.154528940713113e-05,
|
| 267 |
+
"loss": 0.5528,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.562189054726368,
|
| 272 |
+
"grad_norm": 0.5322265625,
|
| 273 |
+
"learning_rate": 2.7103137257858868e-05,
|
| 274 |
+
"loss": 0.5852,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.7611940298507465,
|
| 279 |
+
"grad_norm": 0.5146484375,
|
| 280 |
+
"learning_rate": 2.2948675722421086e-05,
|
| 281 |
+
"loss": 0.5543,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.960199004975125,
|
| 286 |
+
"grad_norm": 0.53955078125,
|
| 287 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 288 |
+
"loss": 0.5786,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.159203980099502,
|
| 293 |
+
"grad_norm": 0.48974609375,
|
| 294 |
+
"learning_rate": 1.5567207449798515e-05,
|
| 295 |
+
"loss": 0.5669,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.35820895522388,
|
| 300 |
+
"grad_norm": 0.513671875,
|
| 301 |
+
"learning_rate": 1.2369331995613665e-05,
|
| 302 |
+
"loss": 0.5683,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.557213930348258,
|
| 307 |
+
"grad_norm": 0.53076171875,
|
| 308 |
+
"learning_rate": 9.517294753398064e-06,
|
| 309 |
+
"loss": 0.5493,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.756218905472636,
|
| 314 |
+
"grad_norm": 0.5400390625,
|
| 315 |
+
"learning_rate": 7.022351411174866e-06,
|
| 316 |
+
"loss": 0.5335,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 8.955223880597014,
|
| 321 |
+
"grad_norm": 0.54833984375,
|
| 322 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 323 |
+
"loss": 0.5649,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.154228855721392,
|
| 328 |
+
"grad_norm": 0.5166015625,
|
| 329 |
+
"learning_rate": 3.1416838871368924e-06,
|
| 330 |
+
"loss": 0.5557,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.35323383084577,
|
| 335 |
+
"grad_norm": 0.5068359375,
|
| 336 |
+
"learning_rate": 1.771274927131139e-06,
|
| 337 |
+
"loss": 0.5551,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.552238805970148,
|
| 342 |
+
"grad_norm": 0.51708984375,
|
| 343 |
+
"learning_rate": 7.885298685522235e-07,
|
| 344 |
+
"loss": 0.5442,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 9.751243781094526,
|
| 349 |
+
"grad_norm": 0.53564453125,
|
| 350 |
+
"learning_rate": 1.973271571728441e-07,
|
| 351 |
+
"loss": 0.5546,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 9.950248756218905,
|
| 356 |
+
"grad_norm": 0.52880859375,
|
| 357 |
+
"learning_rate": 0.0,
|
| 358 |
+
"loss": 0.569,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.950248756218905,
|
| 363 |
+
"step": 500,
|
| 364 |
+
"total_flos": 2.4398694187008e+16,
|
| 365 |
+
"train_loss": 0.6164851455688477,
|
| 366 |
+
"train_runtime": 442.613,
|
| 367 |
+
"train_samples_per_second": 4.541,
|
| 368 |
+
"train_steps_per_second": 1.13
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"logging_steps": 10,
|
| 372 |
+
"max_steps": 500,
|
| 373 |
+
"num_input_tokens_seen": 0,
|
| 374 |
+
"num_train_epochs": 10,
|
| 375 |
+
"save_steps": 500,
|
| 376 |
+
"total_flos": 2.4398694187008e+16,
|
| 377 |
+
"train_batch_size": 1,
|
| 378 |
+
"trial_name": null,
|
| 379 |
+
"trial_params": null
|
| 380 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8270d85e949a246b5106bf1c99227c3f73e3627068e69a72a8c2a4b3d98b9c0
|
| 3 |
size 4984
|