Training in progress, step 150, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 847599616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a5404464e9bb484d34cf47867fbfeae189029cf7ff2bee8c63256927076502f
|
| 3 |
size 847599616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1386414411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c832c15b463bb0902009acdb43bc55402abacb2120ea591b3d08765c6df315f
|
| 3 |
size 1386414411
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b61860000f270ef24d0bb03522991107ebd533901ca499cabb492a726a088a
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04fab8fc2dd4bbc722b26708598a504e6b169355d93ff7b889697b9ea28dd82b
|
| 3 |
size 14917
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cccf9bf3b3a85fdcc4a8781fe5c4acc7a0e94c949399f0bb52fbdd509f3aa7c
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,292 +2,49 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate": 3.
|
| 16 |
-
"loss":
|
| 17 |
"step": 50
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate": 6.6e-
|
| 23 |
-
"loss":
|
| 24 |
"step": 100
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate": 9.
|
| 30 |
-
"loss":
|
| 31 |
"step": 150
|
| 32 |
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.06666666666666667,
|
| 35 |
-
"grad_norm": 6535.71044921875,
|
| 36 |
-
"learning_rate": 9.99270816881235e-05,
|
| 37 |
-
"loss": 71.871,
|
| 38 |
-
"step": 200
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.06666666666666667,
|
| 42 |
-
"eval_accuracy": 0.2704493860434324,
|
| 43 |
-
"eval_loss": 4.5415215492248535,
|
| 44 |
-
"eval_runtime": 7.9125,
|
| 45 |
-
"eval_samples_per_second": 63.191,
|
| 46 |
-
"eval_steps_per_second": 2.022,
|
| 47 |
-
"step": 200
|
| 48 |
-
},
|
| 49 |
-
{
|
| 50 |
-
"epoch": 0.08333333333333333,
|
| 51 |
-
"grad_norm": 2549.314208984375,
|
| 52 |
-
"learning_rate": 9.970256684745258e-05,
|
| 53 |
-
"loss": 73.4509,
|
| 54 |
-
"step": 250
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 0.1,
|
| 58 |
-
"grad_norm": 30061.046875,
|
| 59 |
-
"learning_rate": 9.932710694482191e-05,
|
| 60 |
-
"loss": 75.4218,
|
| 61 |
-
"step": 300
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.11666666666666667,
|
| 65 |
-
"grad_norm": 48175.3359375,
|
| 66 |
-
"learning_rate": 9.880184223961573e-05,
|
| 67 |
-
"loss": 76.206,
|
| 68 |
-
"step": 350
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.13333333333333333,
|
| 72 |
-
"grad_norm": 32999.78515625,
|
| 73 |
-
"learning_rate": 9.812836794348004e-05,
|
| 74 |
-
"loss": 76.8908,
|
| 75 |
-
"step": 400
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.13333333333333333,
|
| 79 |
-
"eval_accuracy": 0.23184523867818646,
|
| 80 |
-
"eval_loss": 4.965036869049072,
|
| 81 |
-
"eval_runtime": 7.7766,
|
| 82 |
-
"eval_samples_per_second": 64.296,
|
| 83 |
-
"eval_steps_per_second": 2.057,
|
| 84 |
-
"step": 400
|
| 85 |
-
},
|
| 86 |
{
|
| 87 |
"epoch": 0.15,
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
"epoch": 0.16666666666666666,
|
| 95 |
-
"grad_norm": 112764.3515625,
|
| 96 |
-
"learning_rate": 9.634541575171929e-05,
|
| 97 |
-
"loss": 77.5796,
|
| 98 |
-
"step": 500
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.18333333333333332,
|
| 102 |
-
"grad_norm": 30660.970703125,
|
| 103 |
-
"learning_rate": 9.524135262330098e-05,
|
| 104 |
-
"loss": 77.067,
|
| 105 |
-
"step": 550
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.2,
|
| 109 |
-
"grad_norm": 55290.8203125,
|
| 110 |
-
"learning_rate": 9.399989299389661e-05,
|
| 111 |
-
"loss": 75.4663,
|
| 112 |
-
"step": 600
|
| 113 |
-
},
|
| 114 |
-
{
|
| 115 |
-
"epoch": 0.2,
|
| 116 |
-
"eval_accuracy": 0.24998188196442597,
|
| 117 |
-
"eval_loss": 4.73757791519165,
|
| 118 |
-
"eval_runtime": 8.0417,
|
| 119 |
-
"eval_samples_per_second": 62.176,
|
| 120 |
-
"eval_steps_per_second": 1.99,
|
| 121 |
-
"step": 600
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.21666666666666667,
|
| 125 |
-
"grad_norm": 28325.5859375,
|
| 126 |
-
"learning_rate": 9.262480713559808e-05,
|
| 127 |
-
"loss": 76.2754,
|
| 128 |
-
"step": 650
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.23333333333333334,
|
| 132 |
-
"grad_norm": 354199.03125,
|
| 133 |
-
"learning_rate": 9.112027113896262e-05,
|
| 134 |
-
"loss": 76.0095,
|
| 135 |
-
"step": 700
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.25,
|
| 139 |
-
"grad_norm": 1301901.625,
|
| 140 |
-
"learning_rate": 8.949085423036296e-05,
|
| 141 |
-
"loss": 76.6464,
|
| 142 |
-
"step": 750
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.26666666666666666,
|
| 146 |
-
"grad_norm": 118610.0,
|
| 147 |
-
"learning_rate": 8.774150489539707e-05,
|
| 148 |
-
"loss": 78.2808,
|
| 149 |
-
"step": 800
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.26666666666666666,
|
| 153 |
-
"eval_accuracy": 0.22522578989738337,
|
| 154 |
-
"eval_loss": 5.033573150634766,
|
| 155 |
-
"eval_runtime": 7.5988,
|
| 156 |
-
"eval_samples_per_second": 65.8,
|
| 157 |
-
"eval_steps_per_second": 2.106,
|
| 158 |
-
"step": 800
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.2833333333333333,
|
| 162 |
-
"grad_norm": 22132.029296875,
|
| 163 |
-
"learning_rate": 8.587753585050004e-05,
|
| 164 |
-
"loss": 79.5805,
|
| 165 |
-
"step": 850
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.3,
|
| 169 |
-
"grad_norm": 10536.388671875,
|
| 170 |
-
"learning_rate": 8.390460790839882e-05,
|
| 171 |
-
"loss": 77.5871,
|
| 172 |
-
"step": 900
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.31666666666666665,
|
| 176 |
-
"grad_norm": 15219.642578125,
|
| 177 |
-
"learning_rate": 8.182871278641009e-05,
|
| 178 |
-
"loss": 77.6208,
|
| 179 |
-
"step": 950
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 0.3333333333333333,
|
| 183 |
-
"grad_norm": 92554.859375,
|
| 184 |
-
"learning_rate": 7.965615490979163e-05,
|
| 185 |
-
"loss": 78.9266,
|
| 186 |
-
"step": 1000
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 0.3333333333333333,
|
| 190 |
-
"eval_accuracy": 0.2367096863914945,
|
| 191 |
-
"eval_loss": 4.885761737823486,
|
| 192 |
-
"eval_runtime": 7.9133,
|
| 193 |
-
"eval_samples_per_second": 63.185,
|
| 194 |
-
"eval_steps_per_second": 2.022,
|
| 195 |
-
"step": 1000
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.35,
|
| 199 |
-
"grad_norm": 869790.875,
|
| 200 |
-
"learning_rate": 7.739353226541009e-05,
|
| 201 |
-
"loss": 78.3315,
|
| 202 |
-
"step": 1050
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"epoch": 0.36666666666666664,
|
| 206 |
-
"grad_norm": 131137.71875,
|
| 207 |
-
"learning_rate": 7.504771636387163e-05,
|
| 208 |
-
"loss": 79.5684,
|
| 209 |
-
"step": 1100
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 0.38333333333333336,
|
| 213 |
-
"grad_norm": 188537.671875,
|
| 214 |
-
"learning_rate": 7.262583137097018e-05,
|
| 215 |
-
"loss": 79.0903,
|
| 216 |
-
"step": 1150
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 0.4,
|
| 220 |
-
"grad_norm": 38120.7890625,
|
| 221 |
-
"learning_rate": 7.013523247183e-05,
|
| 222 |
-
"loss": 79.5616,
|
| 223 |
-
"step": 1200
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 0.4,
|
| 227 |
-
"eval_accuracy": 0.2313888600523758,
|
| 228 |
-
"eval_loss": 4.960353374481201,
|
| 229 |
-
"eval_runtime": 7.869,
|
| 230 |
-
"eval_samples_per_second": 63.54,
|
| 231 |
-
"eval_steps_per_second": 2.033,
|
| 232 |
-
"step": 1200
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 0.4166666666666667,
|
| 236 |
-
"grad_norm": 178847.84375,
|
| 237 |
-
"learning_rate": 6.758348353345014e-05,
|
| 238 |
-
"loss": 78.9412,
|
| 239 |
-
"step": 1250
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 0.43333333333333335,
|
| 243 |
-
"grad_norm": 72944.7734375,
|
| 244 |
-
"learning_rate": 6.497833413348909e-05,
|
| 245 |
-
"loss": 78.9907,
|
| 246 |
-
"step": 1300
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 0.45,
|
| 250 |
-
"grad_norm": 82608.953125,
|
| 251 |
-
"learning_rate": 6.232769602505203e-05,
|
| 252 |
-
"loss": 78.8287,
|
| 253 |
-
"step": 1350
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 0.4666666666666667,
|
| 257 |
-
"grad_norm": 321814.40625,
|
| 258 |
-
"learning_rate": 5.963961910895676e-05,
|
| 259 |
-
"loss": 79.5967,
|
| 260 |
-
"step": 1400
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 0.4666666666666667,
|
| 264 |
-
"eval_accuracy": 0.22584767922654594,
|
| 265 |
-
"eval_loss": 5.036545753479004,
|
| 266 |
-
"eval_runtime": 8.0524,
|
| 267 |
-
"eval_samples_per_second": 62.094,
|
| 268 |
-
"eval_steps_per_second": 1.987,
|
| 269 |
-
"step": 1400
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.48333333333333334,
|
| 273 |
-
"grad_norm": 27832.90625,
|
| 274 |
-
"learning_rate": 5.692226698644938e-05,
|
| 275 |
-
"loss": 80.2996,
|
| 276 |
-
"step": 1450
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.5,
|
| 280 |
-
"grad_norm": 165018.953125,
|
| 281 |
-
"learning_rate": 5.418389216661579e-05,
|
| 282 |
-
"loss": 82.4446,
|
| 283 |
-
"step": 1500
|
| 284 |
}
|
| 285 |
],
|
| 286 |
"logging_steps": 50,
|
| 287 |
-
"max_steps":
|
| 288 |
"num_input_tokens_seen": 0,
|
| 289 |
"num_train_epochs": 9223372036854775807,
|
| 290 |
-
"save_steps":
|
| 291 |
"stateful_callbacks": {
|
| 292 |
"TrainerControl": {
|
| 293 |
"args": {
|
|
@@ -301,7 +58,7 @@
|
|
| 301 |
}
|
| 302 |
},
|
| 303 |
"total_flos": 0.0,
|
| 304 |
-
"train_batch_size":
|
| 305 |
"trial_name": null,
|
| 306 |
"trial_params": null
|
| 307 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.15,
|
| 6 |
+
"eval_steps": 150,
|
| 7 |
+
"global_step": 150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.05,
|
| 14 |
+
"grad_norm": 4757.10498046875,
|
| 15 |
+
"learning_rate": 3.2666666666666663e-07,
|
| 16 |
+
"loss": 74.4742,
|
| 17 |
"step": 50
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.1,
|
| 21 |
+
"grad_norm": 15446.2177734375,
|
| 22 |
+
"learning_rate": 6.6e-07,
|
| 23 |
+
"loss": 74.3892,
|
| 24 |
"step": 100
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.15,
|
| 28 |
+
"grad_norm": 6237.49609375,
|
| 29 |
+
"learning_rate": 9.933333333333333e-07,
|
| 30 |
+
"loss": 74.3298,
|
| 31 |
"step": 150
|
| 32 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{
|
| 34 |
"epoch": 0.15,
|
| 35 |
+
"eval_accuracy": 0.25207497151999875,
|
| 36 |
+
"eval_loss": 4.663373947143555,
|
| 37 |
+
"eval_runtime": 6.2495,
|
| 38 |
+
"eval_samples_per_second": 80.007,
|
| 39 |
+
"eval_steps_per_second": 1.28,
|
| 40 |
+
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"logging_steps": 50,
|
| 44 |
+
"max_steps": 1000,
|
| 45 |
"num_input_tokens_seen": 0,
|
| 46 |
"num_train_epochs": 9223372036854775807,
|
| 47 |
+
"save_steps": 150,
|
| 48 |
"stateful_callbacks": {
|
| 49 |
"TrainerControl": {
|
| 50 |
"args": {
|
|
|
|
| 58 |
}
|
| 59 |
},
|
| 60 |
"total_flos": 0.0,
|
| 61 |
+
"train_batch_size": 32,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
| 64 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d40d24b46d3cd4d473941fc8d4a15b5795409810b25bec36748fef2488d6892
|
| 3 |
size 5841
|