Upload 8 files
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +442 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca2f652b50161f1f365baf8d7263a0de21b273291ddee69e160ae8137f775f4
|
| 3 |
+
size 160172869
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2216405c6e3b4b6c318003c5e38e29c1a7a0ce2eb21abf474114378e8c274c9f
|
| 3 |
+
size 80114765
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9defd0d2ac7cea09127fefb20385f7a54eb2860c6bd9a32502c3c5a52f9ad55c
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e8bfa24714ec568e1cb11f40b8e7b5945102f5516627c6bc17c400ab29513c9
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9074f5d5b0ae79eb8de0c0b12be33d42a5246074a74de638af3c1b2e70535446
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.110647439956665,
|
| 3 |
+
"best_model_checkpoint": "outs/instuct_chat_50k/checkpoint-2000",
|
| 4 |
+
"epoch": 0.23353573096683794,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1.5568240788790864e-07,
|
| 13 |
+
"loss": 1.1388,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 1.5412558380902958e-05,
|
| 19 |
+
"loss": 1.5551,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"eval_loss": 1.2936956882476807,
|
| 25 |
+
"eval_runtime": 31.4406,
|
| 26 |
+
"eval_samples_per_second": 6.361,
|
| 27 |
+
"eval_steps_per_second": 0.795,
|
| 28 |
+
"step": 100
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.02,
|
| 32 |
+
"learning_rate": 3.098079916969382e-05,
|
| 33 |
+
"loss": 1.4423,
|
| 34 |
+
"step": 200
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.02,
|
| 38 |
+
"eval_loss": 1.227220892906189,
|
| 39 |
+
"eval_runtime": 31.4526,
|
| 40 |
+
"eval_samples_per_second": 6.359,
|
| 41 |
+
"eval_steps_per_second": 0.795,
|
| 42 |
+
"step": 200
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.02,
|
| 46 |
+
"learning_rate": 4.6393357550596784e-05,
|
| 47 |
+
"loss": 1.3335,
|
| 48 |
+
"step": 300
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.02,
|
| 52 |
+
"eval_loss": 1.2049953937530518,
|
| 53 |
+
"eval_runtime": 31.9522,
|
| 54 |
+
"eval_samples_per_second": 6.259,
|
| 55 |
+
"eval_steps_per_second": 0.782,
|
| 56 |
+
"step": 300
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.03,
|
| 60 |
+
"learning_rate": 6.165023352361183e-05,
|
| 61 |
+
"loss": 1.4225,
|
| 62 |
+
"step": 400
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.03,
|
| 66 |
+
"eval_loss": 1.1863670349121094,
|
| 67 |
+
"eval_runtime": 31.5148,
|
| 68 |
+
"eval_samples_per_second": 6.346,
|
| 69 |
+
"eval_steps_per_second": 0.793,
|
| 70 |
+
"step": 400
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.04,
|
| 74 |
+
"learning_rate": 7.721847431240269e-05,
|
| 75 |
+
"loss": 1.3618,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.04,
|
| 80 |
+
"eval_loss": 1.1773875951766968,
|
| 81 |
+
"eval_runtime": 31.4521,
|
| 82 |
+
"eval_samples_per_second": 6.359,
|
| 83 |
+
"eval_steps_per_second": 0.795,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.05,
|
| 88 |
+
"learning_rate": 9.278671510119357e-05,
|
| 89 |
+
"loss": 1.3262,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05,
|
| 94 |
+
"eval_loss": 1.168226718902588,
|
| 95 |
+
"eval_runtime": 31.5121,
|
| 96 |
+
"eval_samples_per_second": 6.347,
|
| 97 |
+
"eval_steps_per_second": 0.793,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.05,
|
| 102 |
+
"learning_rate": 0.00010835495588998442,
|
| 103 |
+
"loss": 1.2133,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.05,
|
| 108 |
+
"eval_loss": 1.1481703519821167,
|
| 109 |
+
"eval_runtime": 31.504,
|
| 110 |
+
"eval_samples_per_second": 6.348,
|
| 111 |
+
"eval_steps_per_second": 0.794,
|
| 112 |
+
"step": 700
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.06,
|
| 116 |
+
"learning_rate": 0.00012392319667877528,
|
| 117 |
+
"loss": 1.2034,
|
| 118 |
+
"step": 800
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.06,
|
| 122 |
+
"eval_loss": 1.13801908493042,
|
| 123 |
+
"eval_runtime": 31.5183,
|
| 124 |
+
"eval_samples_per_second": 6.346,
|
| 125 |
+
"eval_steps_per_second": 0.793,
|
| 126 |
+
"step": 800
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.07,
|
| 130 |
+
"learning_rate": 0.00013949143746756616,
|
| 131 |
+
"loss": 1.2159,
|
| 132 |
+
"step": 900
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.07,
|
| 136 |
+
"eval_loss": 1.1303695440292358,
|
| 137 |
+
"eval_runtime": 31.4531,
|
| 138 |
+
"eval_samples_per_second": 6.359,
|
| 139 |
+
"eval_steps_per_second": 0.795,
|
| 140 |
+
"step": 900
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.08,
|
| 144 |
+
"learning_rate": 0.00015505967825635704,
|
| 145 |
+
"loss": 1.1612,
|
| 146 |
+
"step": 1000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.08,
|
| 150 |
+
"eval_loss": 1.1280632019042969,
|
| 151 |
+
"eval_runtime": 31.434,
|
| 152 |
+
"eval_samples_per_second": 6.363,
|
| 153 |
+
"eval_steps_per_second": 0.795,
|
| 154 |
+
"step": 1000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.09,
|
| 158 |
+
"learning_rate": 0.00017062791904514786,
|
| 159 |
+
"loss": 1.1549,
|
| 160 |
+
"step": 1100
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.09,
|
| 164 |
+
"eval_loss": 1.1211422681808472,
|
| 165 |
+
"eval_runtime": 31.5065,
|
| 166 |
+
"eval_samples_per_second": 6.348,
|
| 167 |
+
"eval_steps_per_second": 0.793,
|
| 168 |
+
"step": 1100
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.09,
|
| 172 |
+
"learning_rate": 0.00018619615983393875,
|
| 173 |
+
"loss": 1.2038,
|
| 174 |
+
"step": 1200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.09,
|
| 178 |
+
"eval_loss": 1.126134991645813,
|
| 179 |
+
"eval_runtime": 31.4919,
|
| 180 |
+
"eval_samples_per_second": 6.351,
|
| 181 |
+
"eval_steps_per_second": 0.794,
|
| 182 |
+
"step": 1200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.1,
|
| 186 |
+
"learning_rate": 0.00020176440062272963,
|
| 187 |
+
"loss": 1.1784,
|
| 188 |
+
"step": 1300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.1,
|
| 192 |
+
"eval_loss": 1.1223646402359009,
|
| 193 |
+
"eval_runtime": 31.4108,
|
| 194 |
+
"eval_samples_per_second": 6.367,
|
| 195 |
+
"eval_steps_per_second": 0.796,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.11,
|
| 200 |
+
"learning_rate": 0.00021733264141152048,
|
| 201 |
+
"loss": 1.1834,
|
| 202 |
+
"step": 1400
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.11,
|
| 206 |
+
"eval_loss": 1.113663911819458,
|
| 207 |
+
"eval_runtime": 31.463,
|
| 208 |
+
"eval_samples_per_second": 6.357,
|
| 209 |
+
"eval_steps_per_second": 0.795,
|
| 210 |
+
"step": 1400
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.12,
|
| 214 |
+
"learning_rate": 0.00023290088220031133,
|
| 215 |
+
"loss": 1.1974,
|
| 216 |
+
"step": 1500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.12,
|
| 220 |
+
"eval_loss": 1.1265443563461304,
|
| 221 |
+
"eval_runtime": 31.4893,
|
| 222 |
+
"eval_samples_per_second": 6.351,
|
| 223 |
+
"eval_steps_per_second": 0.794,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.12,
|
| 228 |
+
"learning_rate": 0.0002484691229891022,
|
| 229 |
+
"loss": 1.2174,
|
| 230 |
+
"step": 1600
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.12,
|
| 234 |
+
"eval_loss": 1.1237465143203735,
|
| 235 |
+
"eval_runtime": 31.5226,
|
| 236 |
+
"eval_samples_per_second": 6.345,
|
| 237 |
+
"eval_steps_per_second": 0.793,
|
| 238 |
+
"step": 1600
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.13,
|
| 242 |
+
"learning_rate": 0.00026403736377789307,
|
| 243 |
+
"loss": 1.2019,
|
| 244 |
+
"step": 1700
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.13,
|
| 248 |
+
"eval_loss": 1.1198475360870361,
|
| 249 |
+
"eval_runtime": 31.4658,
|
| 250 |
+
"eval_samples_per_second": 6.356,
|
| 251 |
+
"eval_steps_per_second": 0.795,
|
| 252 |
+
"step": 1700
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.14,
|
| 256 |
+
"learning_rate": 0.0002796056045666839,
|
| 257 |
+
"loss": 1.2114,
|
| 258 |
+
"step": 1800
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.14,
|
| 262 |
+
"eval_loss": 1.1201978921890259,
|
| 263 |
+
"eval_runtime": 31.5138,
|
| 264 |
+
"eval_samples_per_second": 6.346,
|
| 265 |
+
"eval_steps_per_second": 0.793,
|
| 266 |
+
"step": 1800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.15,
|
| 270 |
+
"learning_rate": 0.00029517384535547483,
|
| 271 |
+
"loss": 1.1848,
|
| 272 |
+
"step": 1900
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.15,
|
| 276 |
+
"eval_loss": 1.1198968887329102,
|
| 277 |
+
"eval_runtime": 31.1932,
|
| 278 |
+
"eval_samples_per_second": 6.412,
|
| 279 |
+
"eval_steps_per_second": 0.801,
|
| 280 |
+
"step": 1900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.16,
|
| 284 |
+
"learning_rate": 0.0002994345961596241,
|
| 285 |
+
"loss": 1.129,
|
| 286 |
+
"step": 2000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.16,
|
| 290 |
+
"eval_loss": 1.110647439956665,
|
| 291 |
+
"eval_runtime": 31.1909,
|
| 292 |
+
"eval_samples_per_second": 6.412,
|
| 293 |
+
"eval_steps_per_second": 0.802,
|
| 294 |
+
"step": 2000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.16,
|
| 298 |
+
"learning_rate": 0.00029861517030400697,
|
| 299 |
+
"loss": 1.1864,
|
| 300 |
+
"step": 2100
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.16,
|
| 304 |
+
"eval_loss": 1.1134731769561768,
|
| 305 |
+
"eval_runtime": 31.169,
|
| 306 |
+
"eval_samples_per_second": 6.417,
|
| 307 |
+
"eval_steps_per_second": 0.802,
|
| 308 |
+
"step": 2100
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.17,
|
| 312 |
+
"learning_rate": 0.0002977957444483898,
|
| 313 |
+
"loss": 1.1725,
|
| 314 |
+
"step": 2200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.17,
|
| 318 |
+
"eval_loss": 1.1226890087127686,
|
| 319 |
+
"eval_runtime": 31.1975,
|
| 320 |
+
"eval_samples_per_second": 6.411,
|
| 321 |
+
"eval_steps_per_second": 0.801,
|
| 322 |
+
"step": 2200
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.18,
|
| 326 |
+
"learning_rate": 0.0002969763185927726,
|
| 327 |
+
"loss": 1.1363,
|
| 328 |
+
"step": 2300
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.18,
|
| 332 |
+
"eval_loss": 1.1255100965499878,
|
| 333 |
+
"eval_runtime": 31.237,
|
| 334 |
+
"eval_samples_per_second": 6.403,
|
| 335 |
+
"eval_steps_per_second": 0.8,
|
| 336 |
+
"step": 2300
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.19,
|
| 340 |
+
"learning_rate": 0.00029615689273715547,
|
| 341 |
+
"loss": 1.204,
|
| 342 |
+
"step": 2400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.19,
|
| 346 |
+
"eval_loss": 1.1148998737335205,
|
| 347 |
+
"eval_runtime": 31.2369,
|
| 348 |
+
"eval_samples_per_second": 6.403,
|
| 349 |
+
"eval_steps_per_second": 0.8,
|
| 350 |
+
"step": 2400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.19,
|
| 354 |
+
"learning_rate": 0.0002953374668815383,
|
| 355 |
+
"loss": 1.1465,
|
| 356 |
+
"step": 2500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.19,
|
| 360 |
+
"eval_loss": 1.1103030443191528,
|
| 361 |
+
"eval_runtime": 31.2141,
|
| 362 |
+
"eval_samples_per_second": 6.407,
|
| 363 |
+
"eval_steps_per_second": 0.801,
|
| 364 |
+
"step": 2500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.2,
|
| 368 |
+
"learning_rate": 0.0002945180410259212,
|
| 369 |
+
"loss": 1.2058,
|
| 370 |
+
"step": 2600
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.2,
|
| 374 |
+
"eval_loss": 1.1112116575241089,
|
| 375 |
+
"eval_runtime": 31.6225,
|
| 376 |
+
"eval_samples_per_second": 6.325,
|
| 377 |
+
"eval_steps_per_second": 0.791,
|
| 378 |
+
"step": 2600
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.21,
|
| 382 |
+
"learning_rate": 0.00029369861517030397,
|
| 383 |
+
"loss": 1.1662,
|
| 384 |
+
"step": 2700
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.21,
|
| 388 |
+
"eval_loss": 1.1122115850448608,
|
| 389 |
+
"eval_runtime": 31.1829,
|
| 390 |
+
"eval_samples_per_second": 6.414,
|
| 391 |
+
"eval_steps_per_second": 0.802,
|
| 392 |
+
"step": 2700
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.22,
|
| 396 |
+
"learning_rate": 0.0002928791893146868,
|
| 397 |
+
"loss": 1.1372,
|
| 398 |
+
"step": 2800
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.22,
|
| 402 |
+
"eval_loss": 1.1113629341125488,
|
| 403 |
+
"eval_runtime": 31.6588,
|
| 404 |
+
"eval_samples_per_second": 6.317,
|
| 405 |
+
"eval_steps_per_second": 0.79,
|
| 406 |
+
"step": 2800
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.23,
|
| 410 |
+
"learning_rate": 0.0002920597634590696,
|
| 411 |
+
"loss": 1.1693,
|
| 412 |
+
"step": 2900
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.23,
|
| 416 |
+
"eval_loss": 1.1073808670043945,
|
| 417 |
+
"eval_runtime": 31.5886,
|
| 418 |
+
"eval_samples_per_second": 6.331,
|
| 419 |
+
"eval_steps_per_second": 0.791,
|
| 420 |
+
"step": 2900
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.23,
|
| 424 |
+
"learning_rate": 0.0002912403376034525,
|
| 425 |
+
"loss": 1.1776,
|
| 426 |
+
"step": 3000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.23,
|
| 430 |
+
"eval_loss": 1.1112266778945923,
|
| 431 |
+
"eval_runtime": 31.3957,
|
| 432 |
+
"eval_samples_per_second": 6.37,
|
| 433 |
+
"eval_steps_per_second": 0.796,
|
| 434 |
+
"step": 3000
|
| 435 |
+
}
|
| 436 |
+
],
|
| 437 |
+
"max_steps": 38538,
|
| 438 |
+
"num_train_epochs": 3,
|
| 439 |
+
"total_flos": 4.679774978918646e+17,
|
| 440 |
+
"trial_name": null,
|
| 441 |
+
"trial_params": null
|
| 442 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bb6ba6f5e12c684d8d83e0b5f07bf755523076c01cd9fe3b53e7d228104ff0
|
| 3 |
+
size 3579
|