Commit
•
3348a74
1
Parent(s):
81ffe17
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +433 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 3.3398852348327637,
|
| 14 |
+
"learning_rate": 4.999950652140343e-05,
|
| 15 |
+
"loss": 0.288,
|
| 16 |
+
"num_input_tokens_seen": 1192,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04,
|
| 21 |
+
"grad_norm": 3.534205436706543,
|
| 22 |
+
"learning_rate": 4.9998026105095405e-05,
|
| 23 |
+
"loss": 0.1627,
|
| 24 |
+
"num_input_tokens_seen": 2208,
|
| 25 |
+
"step": 2
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.06,
|
| 29 |
+
"grad_norm": 3.9795141220092773,
|
| 30 |
+
"learning_rate": 4.999555880952023e-05,
|
| 31 |
+
"loss": 0.2259,
|
| 32 |
+
"num_input_tokens_seen": 3320,
|
| 33 |
+
"step": 3
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"grad_norm": 2.712265729904175,
|
| 38 |
+
"learning_rate": 4.99921047320825e-05,
|
| 39 |
+
"loss": 0.3248,
|
| 40 |
+
"num_input_tokens_seen": 4536,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1,
|
| 45 |
+
"grad_norm": 2.0970170497894287,
|
| 46 |
+
"learning_rate": 4.998766400914329e-05,
|
| 47 |
+
"loss": 0.1867,
|
| 48 |
+
"num_input_tokens_seen": 5960,
|
| 49 |
+
"step": 5
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.12,
|
| 53 |
+
"grad_norm": 2.16365909576416,
|
| 54 |
+
"learning_rate": 4.998223681601473e-05,
|
| 55 |
+
"loss": 0.1558,
|
| 56 |
+
"num_input_tokens_seen": 7304,
|
| 57 |
+
"step": 6
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.14,
|
| 61 |
+
"grad_norm": 1.9363147020339966,
|
| 62 |
+
"learning_rate": 4.9975823366953124e-05,
|
| 63 |
+
"loss": 0.1863,
|
| 64 |
+
"num_input_tokens_seen": 8744,
|
| 65 |
+
"step": 7
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16,
|
| 69 |
+
"grad_norm": 1.874936819076538,
|
| 70 |
+
"learning_rate": 4.996842391515044e-05,
|
| 71 |
+
"loss": 0.1679,
|
| 72 |
+
"num_input_tokens_seen": 10120,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.18,
|
| 77 |
+
"grad_norm": 7.298994541168213,
|
| 78 |
+
"learning_rate": 4.996003875272438e-05,
|
| 79 |
+
"loss": 0.3627,
|
| 80 |
+
"num_input_tokens_seen": 10816,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2,
|
| 85 |
+
"grad_norm": 1.7786474227905273,
|
| 86 |
+
"learning_rate": 4.995066821070679e-05,
|
| 87 |
+
"loss": 0.1466,
|
| 88 |
+
"num_input_tokens_seen": 11920,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.22,
|
| 93 |
+
"grad_norm": 1.9229803085327148,
|
| 94 |
+
"learning_rate": 4.994031265903063e-05,
|
| 95 |
+
"loss": 0.2029,
|
| 96 |
+
"num_input_tokens_seen": 13216,
|
| 97 |
+
"step": 11
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.24,
|
| 101 |
+
"grad_norm": 1.230123519897461,
|
| 102 |
+
"learning_rate": 4.992897250651535e-05,
|
| 103 |
+
"loss": 0.1142,
|
| 104 |
+
"num_input_tokens_seen": 14552,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.26,
|
| 109 |
+
"grad_norm": 2.0229177474975586,
|
| 110 |
+
"learning_rate": 4.991664820085074e-05,
|
| 111 |
+
"loss": 0.2142,
|
| 112 |
+
"num_input_tokens_seen": 15600,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.28,
|
| 117 |
+
"grad_norm": 1.4955450296401978,
|
| 118 |
+
"learning_rate": 4.990334022857932e-05,
|
| 119 |
+
"loss": 0.149,
|
| 120 |
+
"num_input_tokens_seen": 16744,
|
| 121 |
+
"step": 14
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3,
|
| 125 |
+
"grad_norm": 3.070120334625244,
|
| 126 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 127 |
+
"loss": 0.2267,
|
| 128 |
+
"num_input_tokens_seen": 17424,
|
| 129 |
+
"step": 15
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.32,
|
| 133 |
+
"grad_norm": 2.16508150100708,
|
| 134 |
+
"learning_rate": 4.987377542453251e-05,
|
| 135 |
+
"loss": 0.1499,
|
| 136 |
+
"num_input_tokens_seen": 18408,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.34,
|
| 141 |
+
"grad_norm": 3.1738064289093018,
|
| 142 |
+
"learning_rate": 4.9857519759924974e-05,
|
| 143 |
+
"loss": 0.4279,
|
| 144 |
+
"num_input_tokens_seen": 19288,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.36,
|
| 149 |
+
"grad_norm": 2.7662558555603027,
|
| 150 |
+
"learning_rate": 4.984028276300021e-05,
|
| 151 |
+
"loss": 0.2957,
|
| 152 |
+
"num_input_tokens_seen": 20336,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.38,
|
| 157 |
+
"grad_norm": 1.4056564569473267,
|
| 158 |
+
"learning_rate": 4.982206511424534e-05,
|
| 159 |
+
"loss": 0.1899,
|
| 160 |
+
"num_input_tokens_seen": 21528,
|
| 161 |
+
"step": 19
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.4,
|
| 165 |
+
"grad_norm": 1.4555004835128784,
|
| 166 |
+
"learning_rate": 4.980286753286195e-05,
|
| 167 |
+
"loss": 0.1429,
|
| 168 |
+
"num_input_tokens_seen": 22680,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.42,
|
| 173 |
+
"grad_norm": 1.6009600162506104,
|
| 174 |
+
"learning_rate": 4.978269077673767e-05,
|
| 175 |
+
"loss": 0.2084,
|
| 176 |
+
"num_input_tokens_seen": 23800,
|
| 177 |
+
"step": 21
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.44,
|
| 181 |
+
"grad_norm": 1.1936904191970825,
|
| 182 |
+
"learning_rate": 4.976153564241628e-05,
|
| 183 |
+
"loss": 0.0474,
|
| 184 |
+
"num_input_tokens_seen": 24784,
|
| 185 |
+
"step": 22
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.46,
|
| 189 |
+
"grad_norm": 2.241938829421997,
|
| 190 |
+
"learning_rate": 4.9739402965066276e-05,
|
| 191 |
+
"loss": 0.1757,
|
| 192 |
+
"num_input_tokens_seen": 25688,
|
| 193 |
+
"step": 23
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.48,
|
| 197 |
+
"grad_norm": 1.735016942024231,
|
| 198 |
+
"learning_rate": 4.971629361844785e-05,
|
| 199 |
+
"loss": 0.2083,
|
| 200 |
+
"num_input_tokens_seen": 27016,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.5,
|
| 205 |
+
"grad_norm": 1.648120403289795,
|
| 206 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 207 |
+
"loss": 0.1653,
|
| 208 |
+
"num_input_tokens_seen": 28200,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.52,
|
| 213 |
+
"grad_norm": 2.088919162750244,
|
| 214 |
+
"learning_rate": 4.96671486051967e-05,
|
| 215 |
+
"loss": 0.2277,
|
| 216 |
+
"num_input_tokens_seen": 29240,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.54,
|
| 221 |
+
"grad_norm": 1.9720033407211304,
|
| 222 |
+
"learning_rate": 4.9641114878724956e-05,
|
| 223 |
+
"loss": 0.2262,
|
| 224 |
+
"num_input_tokens_seen": 30264,
|
| 225 |
+
"step": 27
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.56,
|
| 229 |
+
"grad_norm": 2.137261390686035,
|
| 230 |
+
"learning_rate": 4.9614108363230135e-05,
|
| 231 |
+
"loss": 0.2119,
|
| 232 |
+
"num_input_tokens_seen": 31376,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.58,
|
| 237 |
+
"grad_norm": 1.7072184085845947,
|
| 238 |
+
"learning_rate": 4.958613012488324e-05,
|
| 239 |
+
"loss": 0.186,
|
| 240 |
+
"num_input_tokens_seen": 32288,
|
| 241 |
+
"step": 29
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6,
|
| 245 |
+
"grad_norm": 1.6640106439590454,
|
| 246 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 247 |
+
"loss": 0.1381,
|
| 248 |
+
"num_input_tokens_seen": 33336,
|
| 249 |
+
"step": 30
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.62,
|
| 253 |
+
"grad_norm": 0.743667721748352,
|
| 254 |
+
"learning_rate": 4.952726293608335e-05,
|
| 255 |
+
"loss": 0.1521,
|
| 256 |
+
"num_input_tokens_seen": 35264,
|
| 257 |
+
"step": 31
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.64,
|
| 261 |
+
"grad_norm": 1.3096036911010742,
|
| 262 |
+
"learning_rate": 4.949637630960617e-05,
|
| 263 |
+
"loss": 0.2232,
|
| 264 |
+
"num_input_tokens_seen": 36496,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.66,
|
| 269 |
+
"grad_norm": 1.943765640258789,
|
| 270 |
+
"learning_rate": 4.9464522608136805e-05,
|
| 271 |
+
"loss": 0.0252,
|
| 272 |
+
"num_input_tokens_seen": 37312,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.68,
|
| 277 |
+
"grad_norm": 1.8293421268463135,
|
| 278 |
+
"learning_rate": 4.943170308920484e-05,
|
| 279 |
+
"loss": 0.264,
|
| 280 |
+
"num_input_tokens_seen": 38376,
|
| 281 |
+
"step": 34
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.7,
|
| 285 |
+
"grad_norm": 2.6471211910247803,
|
| 286 |
+
"learning_rate": 4.939791904846869e-05,
|
| 287 |
+
"loss": 0.1645,
|
| 288 |
+
"num_input_tokens_seen": 39168,
|
| 289 |
+
"step": 35
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.72,
|
| 293 |
+
"grad_norm": 1.6533693075180054,
|
| 294 |
+
"learning_rate": 4.9363171819664434e-05,
|
| 295 |
+
"loss": 0.1802,
|
| 296 |
+
"num_input_tokens_seen": 40440,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.74,
|
| 301 |
+
"grad_norm": 1.3770309686660767,
|
| 302 |
+
"learning_rate": 4.9327462774553166e-05,
|
| 303 |
+
"loss": 0.2206,
|
| 304 |
+
"num_input_tokens_seen": 41760,
|
| 305 |
+
"step": 37
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.76,
|
| 309 |
+
"grad_norm": 1.6882014274597168,
|
| 310 |
+
"learning_rate": 4.929079332286685e-05,
|
| 311 |
+
"loss": 0.2886,
|
| 312 |
+
"num_input_tokens_seen": 42944,
|
| 313 |
+
"step": 38
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.78,
|
| 317 |
+
"grad_norm": 1.9799898862838745,
|
| 318 |
+
"learning_rate": 4.925316491225265e-05,
|
| 319 |
+
"loss": 0.1897,
|
| 320 |
+
"num_input_tokens_seen": 44008,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8,
|
| 325 |
+
"grad_norm": 1.551802158355713,
|
| 326 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 327 |
+
"loss": 0.1935,
|
| 328 |
+
"num_input_tokens_seen": 45168,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.82,
|
| 333 |
+
"grad_norm": 1.0445095300674438,
|
| 334 |
+
"learning_rate": 4.917503719406088e-05,
|
| 335 |
+
"loss": 0.1071,
|
| 336 |
+
"num_input_tokens_seen": 46432,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.84,
|
| 341 |
+
"grad_norm": 3.2616090774536133,
|
| 342 |
+
"learning_rate": 4.913454097083185e-05,
|
| 343 |
+
"loss": 0.5737,
|
| 344 |
+
"num_input_tokens_seen": 47360,
|
| 345 |
+
"step": 42
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.86,
|
| 349 |
+
"grad_norm": 0.9618259072303772,
|
| 350 |
+
"learning_rate": 4.909309195725025e-05,
|
| 351 |
+
"loss": 0.114,
|
| 352 |
+
"num_input_tokens_seen": 49008,
|
| 353 |
+
"step": 43
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.88,
|
| 357 |
+
"grad_norm": 1.5821013450622559,
|
| 358 |
+
"learning_rate": 4.905069178965215e-05,
|
| 359 |
+
"loss": 0.2676,
|
| 360 |
+
"num_input_tokens_seen": 50264,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9,
|
| 365 |
+
"grad_norm": 1.1913903951644897,
|
| 366 |
+
"learning_rate": 4.900734214192358e-05,
|
| 367 |
+
"loss": 0.1061,
|
| 368 |
+
"num_input_tokens_seen": 51368,
|
| 369 |
+
"step": 45
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.92,
|
| 373 |
+
"grad_norm": 1.8395439386367798,
|
| 374 |
+
"learning_rate": 4.89630447254344e-05,
|
| 375 |
+
"loss": 0.2161,
|
| 376 |
+
"num_input_tokens_seen": 52304,
|
| 377 |
+
"step": 46
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.94,
|
| 381 |
+
"grad_norm": 0.736319363117218,
|
| 382 |
+
"learning_rate": 4.891780128897077e-05,
|
| 383 |
+
"loss": 0.1163,
|
| 384 |
+
"num_input_tokens_seen": 53712,
|
| 385 |
+
"step": 47
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.96,
|
| 389 |
+
"grad_norm": 1.5373475551605225,
|
| 390 |
+
"learning_rate": 4.887161361866608e-05,
|
| 391 |
+
"loss": 0.1609,
|
| 392 |
+
"num_input_tokens_seen": 54704,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.98,
|
| 397 |
+
"grad_norm": 1.3580759763717651,
|
| 398 |
+
"learning_rate": 4.882448353793048e-05,
|
| 399 |
+
"loss": 0.1673,
|
| 400 |
+
"num_input_tokens_seen": 55880,
|
| 401 |
+
"step": 49
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.0,
|
| 405 |
+
"grad_norm": 2.0536258220672607,
|
| 406 |
+
"learning_rate": 4.877641290737884e-05,
|
| 407 |
+
"loss": 0.1955,
|
| 408 |
+
"num_input_tokens_seen": 56784,
|
| 409 |
+
"step": 50
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"logging_steps": 1,
|
| 413 |
+
"max_steps": 500,
|
| 414 |
+
"num_input_tokens_seen": 56784,
|
| 415 |
+
"num_train_epochs": 10,
|
| 416 |
+
"save_steps": 50,
|
| 417 |
+
"stateful_callbacks": {
|
| 418 |
+
"TrainerControl": {
|
| 419 |
+
"args": {
|
| 420 |
+
"should_epoch_stop": false,
|
| 421 |
+
"should_evaluate": false,
|
| 422 |
+
"should_log": false,
|
| 423 |
+
"should_save": true,
|
| 424 |
+
"should_training_stop": false
|
| 425 |
+
},
|
| 426 |
+
"attributes": {}
|
| 427 |
+
}
|
| 428 |
+
},
|
| 429 |
+
"total_flos": 2564102936199168.0,
|
| 430 |
+
"train_batch_size": 1,
|
| 431 |
+
"trial_name": null,
|
| 432 |
+
"trial_params": null
|
| 433 |
+
}
|