Upload 6 files
Browse files- chatglm-lora.pt +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +240 -0
chatglm-lora.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f412adacf5a4507ed8024072697d523100b4451717144ccb5343bde1b4ea5da0
|
| 3 |
+
size 14700127
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6adc59fdd9ccb9075a598da7135ad61502dd7f79fb2a0736bda8361b413ed2e5
|
| 3 |
+
size 29393541
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0407b29532a356faab2f98d91dc78105842211ab2c6bec1c2c03ad8e8c4ae58
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f382b9b3dd938f2cd8808d166786de50eef1d19e33eaa997aac976ed214737c0
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3365e38a8d8611c30cc6bdee6d1f36171d8dd376c0adfe6243f8ef24d68e8b08
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9141551206970433,
|
| 5 |
+
"global_step": 800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 13 |
+
"loss": 5.1881,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"eval_loss": 5.518892288208008,
|
| 19 |
+
"eval_runtime": 281.7614,
|
| 20 |
+
"eval_samples_per_second": 16.539,
|
| 21 |
+
"eval_steps_per_second": 16.539,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.11,
|
| 26 |
+
"learning_rate": 4.75e-05,
|
| 27 |
+
"loss": 3.8191,
|
| 28 |
+
"step": 100
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.11,
|
| 32 |
+
"eval_loss": 2.910094738006592,
|
| 33 |
+
"eval_runtime": 282.3915,
|
| 34 |
+
"eval_samples_per_second": 16.502,
|
| 35 |
+
"eval_steps_per_second": 16.502,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.17,
|
| 40 |
+
"learning_rate": 7.25e-05,
|
| 41 |
+
"loss": 2.5718,
|
| 42 |
+
"step": 150
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.17,
|
| 46 |
+
"eval_loss": 2.240684986114502,
|
| 47 |
+
"eval_runtime": 283.3137,
|
| 48 |
+
"eval_samples_per_second": 16.448,
|
| 49 |
+
"eval_steps_per_second": 16.448,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.23,
|
| 54 |
+
"learning_rate": 9.750000000000001e-05,
|
| 55 |
+
"loss": 2.3477,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"eval_loss": 2.1633121967315674,
|
| 61 |
+
"eval_runtime": 282.161,
|
| 62 |
+
"eval_samples_per_second": 16.515,
|
| 63 |
+
"eval_steps_per_second": 16.515,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.29,
|
| 68 |
+
"learning_rate": 0.0001225,
|
| 69 |
+
"loss": 2.3472,
|
| 70 |
+
"step": 250
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.29,
|
| 74 |
+
"eval_loss": 2.118901252746582,
|
| 75 |
+
"eval_runtime": 281.7032,
|
| 76 |
+
"eval_samples_per_second": 16.542,
|
| 77 |
+
"eval_steps_per_second": 16.542,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.34,
|
| 82 |
+
"learning_rate": 0.0001475,
|
| 83 |
+
"loss": 2.2188,
|
| 84 |
+
"step": 300
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.34,
|
| 88 |
+
"eval_loss": 2.1062021255493164,
|
| 89 |
+
"eval_runtime": 282.3706,
|
| 90 |
+
"eval_samples_per_second": 16.503,
|
| 91 |
+
"eval_steps_per_second": 16.503,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.4,
|
| 96 |
+
"learning_rate": 0.0001725,
|
| 97 |
+
"loss": 2.2085,
|
| 98 |
+
"step": 350
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"eval_loss": 2.0873425006866455,
|
| 103 |
+
"eval_runtime": 282.0216,
|
| 104 |
+
"eval_samples_per_second": 16.524,
|
| 105 |
+
"eval_steps_per_second": 16.524,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.46,
|
| 110 |
+
"learning_rate": 0.0001975,
|
| 111 |
+
"loss": 2.1271,
|
| 112 |
+
"step": 400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.46,
|
| 116 |
+
"eval_loss": 2.0874459743499756,
|
| 117 |
+
"eval_runtime": 283.0992,
|
| 118 |
+
"eval_samples_per_second": 16.461,
|
| 119 |
+
"eval_steps_per_second": 16.461,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.51,
|
| 124 |
+
"learning_rate": 0.00022250000000000001,
|
| 125 |
+
"loss": 2.1834,
|
| 126 |
+
"step": 450
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.51,
|
| 130 |
+
"eval_loss": 2.0584352016448975,
|
| 131 |
+
"eval_runtime": 281.7518,
|
| 132 |
+
"eval_samples_per_second": 16.539,
|
| 133 |
+
"eval_steps_per_second": 16.539,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.57,
|
| 138 |
+
"learning_rate": 0.0002475,
|
| 139 |
+
"loss": 2.1927,
|
| 140 |
+
"step": 500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.57,
|
| 144 |
+
"eval_loss": 2.050870656967163,
|
| 145 |
+
"eval_runtime": 281.7194,
|
| 146 |
+
"eval_samples_per_second": 16.541,
|
| 147 |
+
"eval_steps_per_second": 16.541,
|
| 148 |
+
"step": 500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.63,
|
| 152 |
+
"learning_rate": 0.0002725,
|
| 153 |
+
"loss": 2.1816,
|
| 154 |
+
"step": 550
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.63,
|
| 158 |
+
"eval_loss": 2.039118766784668,
|
| 159 |
+
"eval_runtime": 282.0613,
|
| 160 |
+
"eval_samples_per_second": 16.521,
|
| 161 |
+
"eval_steps_per_second": 16.521,
|
| 162 |
+
"step": 550
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.69,
|
| 166 |
+
"learning_rate": 0.00029749999999999997,
|
| 167 |
+
"loss": 2.2131,
|
| 168 |
+
"step": 600
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.69,
|
| 172 |
+
"eval_loss": 2.0333147048950195,
|
| 173 |
+
"eval_runtime": 282.4675,
|
| 174 |
+
"eval_samples_per_second": 16.497,
|
| 175 |
+
"eval_steps_per_second": 16.497,
|
| 176 |
+
"step": 600
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.74,
|
| 180 |
+
"learning_rate": 0.00032250000000000003,
|
| 181 |
+
"loss": 2.2322,
|
| 182 |
+
"step": 650
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.74,
|
| 186 |
+
"eval_loss": 2.0386910438537598,
|
| 187 |
+
"eval_runtime": 282.3106,
|
| 188 |
+
"eval_samples_per_second": 16.507,
|
| 189 |
+
"eval_steps_per_second": 16.507,
|
| 190 |
+
"step": 650
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.8,
|
| 194 |
+
"learning_rate": 0.0003475,
|
| 195 |
+
"loss": 2.2614,
|
| 196 |
+
"step": 700
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8,
|
| 200 |
+
"eval_loss": 2.025144577026367,
|
| 201 |
+
"eval_runtime": 285.8974,
|
| 202 |
+
"eval_samples_per_second": 16.3,
|
| 203 |
+
"eval_steps_per_second": 16.3,
|
| 204 |
+
"step": 700
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.86,
|
| 208 |
+
"learning_rate": 0.0003725,
|
| 209 |
+
"loss": 2.186,
|
| 210 |
+
"step": 750
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.86,
|
| 214 |
+
"eval_loss": 2.0244803428649902,
|
| 215 |
+
"eval_runtime": 284.3127,
|
| 216 |
+
"eval_samples_per_second": 16.39,
|
| 217 |
+
"eval_steps_per_second": 16.39,
|
| 218 |
+
"step": 750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.91,
|
| 222 |
+
"learning_rate": 0.0003975,
|
| 223 |
+
"loss": 2.1677,
|
| 224 |
+
"step": 800
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.91,
|
| 228 |
+
"eval_loss": 2.0197227001190186,
|
| 229 |
+
"eval_runtime": 284.0212,
|
| 230 |
+
"eval_samples_per_second": 16.407,
|
| 231 |
+
"eval_steps_per_second": 16.407,
|
| 232 |
+
"step": 800
|
| 233 |
+
}
|
| 234 |
+
],
|
| 235 |
+
"max_steps": 875,
|
| 236 |
+
"num_train_epochs": 1,
|
| 237 |
+
"total_flos": 4.324339205829427e+16,
|
| 238 |
+
"trial_name": null,
|
| 239 |
+
"trial_params": null
|
| 240 |
+
}
|