Upload folder using huggingface_hub
Browse files- hop4_ckpt16000/added_tokens.json +485 -0
- hop4_ckpt16000/config.json +25 -0
- hop4_ckpt16000/generation_config.json +6 -0
- hop4_ckpt16000/merges.txt +0 -0
- hop4_ckpt16000/model.safetensors +3 -0
- hop4_ckpt16000/optimizer.pt +3 -0
- hop4_ckpt16000/output/ind_test_metrics.json +23 -0
- hop4_ckpt16000/output/ind_test_predictions.json +0 -0
- hop4_ckpt16000/output/ood_test_metrics.json +23 -0
- hop4_ckpt16000/output/ood_test_predictions.json +0 -0
- hop4_ckpt16000/rng_state.pth +3 -0
- hop4_ckpt16000/scheduler.pt +3 -0
- hop4_ckpt16000/special_tokens_map.json +24 -0
- hop4_ckpt16000/tokenizer_config.json +0 -0
- hop4_ckpt16000/trainer_state.json +1153 -0
- hop4_ckpt16000/training_args.bin +3 -0
- hop4_ckpt16000/vocab.json +0 -0
hop4_ckpt16000/added_tokens.json
ADDED
|
@@ -0,0 +1,485 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Abby": 50258,
|
| 3 |
+
"Abel": 50257,
|
| 4 |
+
"Ace": 50259,
|
| 5 |
+
"Ada": 50260,
|
| 6 |
+
"Addie": 50261,
|
| 7 |
+
"Adele": 50262,
|
| 8 |
+
"Aiden": 50263,
|
| 9 |
+
"Aimee": 50264,
|
| 10 |
+
"Aisha": 50641,
|
| 11 |
+
"Ajay": 50265,
|
| 12 |
+
"Alba": 50266,
|
| 13 |
+
"Alec": 50267,
|
| 14 |
+
"Alfonso": 50642,
|
| 15 |
+
"Aline": 50268,
|
| 16 |
+
"Allegra": 50643,
|
| 17 |
+
"Alma": 50269,
|
| 18 |
+
"Alvin": 50270,
|
| 19 |
+
"Amber": 50271,
|
| 20 |
+
"Amie": 50272,
|
| 21 |
+
"Amir": 50273,
|
| 22 |
+
"Amos": 50644,
|
| 23 |
+
"Ana": 50274,
|
| 24 |
+
"Anika": 50275,
|
| 25 |
+
"Anita": 50276,
|
| 26 |
+
"Annie": 50277,
|
| 27 |
+
"Anson": 50645,
|
| 28 |
+
"Antwan": 50646,
|
| 29 |
+
"Anya": 50278,
|
| 30 |
+
"Araceli": 50647,
|
| 31 |
+
"Arden": 50648,
|
| 32 |
+
"Aria": 50279,
|
| 33 |
+
"Ariel": 50280,
|
| 34 |
+
"Arjun": 50649,
|
| 35 |
+
"Arlette": 50650,
|
| 36 |
+
"Arlo": 50281,
|
| 37 |
+
"Arman": 50282,
|
| 38 |
+
"Aron": 50283,
|
| 39 |
+
"Arya": 50284,
|
| 40 |
+
"Asa": 50285,
|
| 41 |
+
"Ashanti": 50651,
|
| 42 |
+
"Asher": 50286,
|
| 43 |
+
"Aston": 50287,
|
| 44 |
+
"Astrid": 50288,
|
| 45 |
+
"Aubrey": 50289,
|
| 46 |
+
"Aubri": 50652,
|
| 47 |
+
"Audra": 50290,
|
| 48 |
+
"Ava": 50291,
|
| 49 |
+
"Axel": 50292,
|
| 50 |
+
"Ayaan": 50293,
|
| 51 |
+
"Ayden": 50294,
|
| 52 |
+
"Bailey": 50295,
|
| 53 |
+
"Barb": 50296,
|
| 54 |
+
"Barry": 50297,
|
| 55 |
+
"Basil": 50653,
|
| 56 |
+
"Beatrix": 50654,
|
| 57 |
+
"Beau": 50298,
|
| 58 |
+
"Bella": 50299,
|
| 59 |
+
"Benedict": 50655,
|
| 60 |
+
"Benny": 50300,
|
| 61 |
+
"Bernadette": 50656,
|
| 62 |
+
"Bert": 50301,
|
| 63 |
+
"Beth": 50302,
|
| 64 |
+
"Beverly": 50303,
|
| 65 |
+
"Bianca": 50304,
|
| 66 |
+
"Bjorn": 50305,
|
| 67 |
+
"Blaise": 50657,
|
| 68 |
+
"Bobby": 50306,
|
| 69 |
+
"Bonita": 50658,
|
| 70 |
+
"Bonnie": 50307,
|
| 71 |
+
"Boyd": 50308,
|
| 72 |
+
"Brady": 50309,
|
| 73 |
+
"Brandy": 50310,
|
| 74 |
+
"Branson": 50659,
|
| 75 |
+
"Brenda": 50311,
|
| 76 |
+
"Brent": 50312,
|
| 77 |
+
"Brett": 50313,
|
| 78 |
+
"Brianna": 50314,
|
| 79 |
+
"Briar": 50660,
|
| 80 |
+
"Brice": 50315,
|
| 81 |
+
"Bridget": 50316,
|
| 82 |
+
"Britt": 50317,
|
| 83 |
+
"Brock": 50318,
|
| 84 |
+
"Brody": 50319,
|
| 85 |
+
"Brogan": 50661,
|
| 86 |
+
"Bruno": 50320,
|
| 87 |
+
"Bryan": 50321,
|
| 88 |
+
"Bryce": 50322,
|
| 89 |
+
"Byron": 50323,
|
| 90 |
+
"Cade": 50324,
|
| 91 |
+
"Cael": 50325,
|
| 92 |
+
"Cain": 50326,
|
| 93 |
+
"Caleb": 50327,
|
| 94 |
+
"Callan": 50662,
|
| 95 |
+
"Callie": 50328,
|
| 96 |
+
"Calvin": 50663,
|
| 97 |
+
"Cambria": 50664,
|
| 98 |
+
"Cameron": 50329,
|
| 99 |
+
"Cami": 50330,
|
| 100 |
+
"Candace": 50331,
|
| 101 |
+
"Cara": 50332,
|
| 102 |
+
"Carla": 50333,
|
| 103 |
+
"Carlton": 50334,
|
| 104 |
+
"Carmelo": 50665,
|
| 105 |
+
"Carol": 50335,
|
| 106 |
+
"Carrie": 50336,
|
| 107 |
+
"Carson": 50337,
|
| 108 |
+
"Carys": 50666,
|
| 109 |
+
"Casey": 50338,
|
| 110 |
+
"Cason": 50339,
|
| 111 |
+
"Cassius": 50667,
|
| 112 |
+
"Cathy": 50340,
|
| 113 |
+
"Cedric": 50341,
|
| 114 |
+
"Celeste": 50668,
|
| 115 |
+
"Celine": 50669,
|
| 116 |
+
"Cesar": 50342,
|
| 117 |
+
"Chad": 50343,
|
| 118 |
+
"Chandler": 50344,
|
| 119 |
+
"Charlton": 50670,
|
| 120 |
+
"Chase": 50345,
|
| 121 |
+
"Chloe": 50346,
|
| 122 |
+
"Cillian": 50671,
|
| 123 |
+
"Cindy": 50347,
|
| 124 |
+
"Claire": 50348,
|
| 125 |
+
"Claude": 50349,
|
| 126 |
+
"Clay": 50350,
|
| 127 |
+
"Cleo": 50672,
|
| 128 |
+
"Cliff": 50351,
|
| 129 |
+
"Clint": 50352,
|
| 130 |
+
"Clover": 50673,
|
| 131 |
+
"Clyde": 50353,
|
| 132 |
+
"Cody": 50354,
|
| 133 |
+
"Colby": 50355,
|
| 134 |
+
"Colin": 50356,
|
| 135 |
+
"Collette": 50674,
|
| 136 |
+
"Connie": 50357,
|
| 137 |
+
"Cooper": 50358,
|
| 138 |
+
"Cordelia": 50675,
|
| 139 |
+
"Corey": 50359,
|
| 140 |
+
"Cormac": 50676,
|
| 141 |
+
"Corwin": 50677,
|
| 142 |
+
"Cory": 50360,
|
| 143 |
+
"Curt": 50361,
|
| 144 |
+
"Curtis": 50362,
|
| 145 |
+
"Cyrus": 50363,
|
| 146 |
+
"Dahlia": 50678,
|
| 147 |
+
"Daisy": 50364,
|
| 148 |
+
"Dale": 50365,
|
| 149 |
+
"Damon": 50366,
|
| 150 |
+
"Dana": 50367,
|
| 151 |
+
"Danielle": 50368,
|
| 152 |
+
"Dante": 50369,
|
| 153 |
+
"Daphne": 50370,
|
| 154 |
+
"Darin": 50371,
|
| 155 |
+
"Darius": 50372,
|
| 156 |
+
"Darla": 50373,
|
| 157 |
+
"Darlene": 50374,
|
| 158 |
+
"Darnell": 50679,
|
| 159 |
+
"Darrel": 50375,
|
| 160 |
+
"Darren": 50376,
|
| 161 |
+
"Darryl": 50377,
|
| 162 |
+
"Dashiell": 50680,
|
| 163 |
+
"Dawn": 50378,
|
| 164 |
+
"Deacon": 50681,
|
| 165 |
+
"Debbie": 50379,
|
| 166 |
+
"Deborah": 50380,
|
| 167 |
+
"Declan": 50381,
|
| 168 |
+
"Delaney": 50682,
|
| 169 |
+
"Delia": 50382,
|
| 170 |
+
"Demetri": 50383,
|
| 171 |
+
"Demetrius": 50683,
|
| 172 |
+
"Demi": 50384,
|
| 173 |
+
"Denise": 50385,
|
| 174 |
+
"Dennis": 50386,
|
| 175 |
+
"Derek": 50387,
|
| 176 |
+
"Derrick": 50388,
|
| 177 |
+
"Deshawn": 50684,
|
| 178 |
+
"Devin": 50389,
|
| 179 |
+
"Devon": 50390,
|
| 180 |
+
"Dewey": 50685,
|
| 181 |
+
"Dexter": 50391,
|
| 182 |
+
"Diana": 50392,
|
| 183 |
+
"Diane": 50393,
|
| 184 |
+
"Diego": 50394,
|
| 185 |
+
"Dillon": 50395,
|
| 186 |
+
"Dina": 50396,
|
| 187 |
+
"Dino": 50397,
|
| 188 |
+
"Dior": 50686,
|
| 189 |
+
"Dirk": 50398,
|
| 190 |
+
"Dixie": 50399,
|
| 191 |
+
"Dolly": 50400,
|
| 192 |
+
"Dominic": 50401,
|
| 193 |
+
"Donna": 50402,
|
| 194 |
+
"Dorian": 50403,
|
| 195 |
+
"Doris": 50404,
|
| 196 |
+
"Douglas": 50405,
|
| 197 |
+
"Drake": 50406,
|
| 198 |
+
"Drew": 50407,
|
| 199 |
+
"Duke": 50408,
|
| 200 |
+
"Dulcie": 50687,
|
| 201 |
+
"Duncan": 50409,
|
| 202 |
+
"Dustin": 50410,
|
| 203 |
+
"Dusty": 50411,
|
| 204 |
+
"Dwayne": 50412,
|
| 205 |
+
"Dwight": 50413,
|
| 206 |
+
"Dylan": 50414,
|
| 207 |
+
"Eamon": 50688,
|
| 208 |
+
"Earl": 50415,
|
| 209 |
+
"Eddard": 50689,
|
| 210 |
+
"Eddie": 50416,
|
| 211 |
+
"Edgar": 50417,
|
| 212 |
+
"Edith": 50418,
|
| 213 |
+
"Edna": 50419,
|
| 214 |
+
"Edwin": 50420,
|
| 215 |
+
"Eileen": 50421,
|
| 216 |
+
"Elaine": 50422,
|
| 217 |
+
"Eldon": 50690,
|
| 218 |
+
"Eleanor": 50423,
|
| 219 |
+
"Elena": 50424,
|
| 220 |
+
"Eli": 50425,
|
| 221 |
+
"Eliana": 50426,
|
| 222 |
+
"Elijah": 50427,
|
| 223 |
+
"Elisa": 50428,
|
| 224 |
+
"Elise": 50429,
|
| 225 |
+
"Eliza": 50430,
|
| 226 |
+
"Ella": 50431,
|
| 227 |
+
"Ellen": 50432,
|
| 228 |
+
"Elliot": 50433,
|
| 229 |
+
"Eloise": 50434,
|
| 230 |
+
"Elowen": 50691,
|
| 231 |
+
"Elton": 50435,
|
| 232 |
+
"Elvira": 50692,
|
| 233 |
+
"Elvis": 50436,
|
| 234 |
+
"Ember": 50693,
|
| 235 |
+
"Emery": 50437,
|
| 236 |
+
"Emil": 50438,
|
| 237 |
+
"Emilia": 50439,
|
| 238 |
+
"Emiliano": 50694,
|
| 239 |
+
"Emma": 50440,
|
| 240 |
+
"Emmeline": 50695,
|
| 241 |
+
"Emory": 50441,
|
| 242 |
+
"Enid": 50442,
|
| 243 |
+
"Enzo": 50443,
|
| 244 |
+
"Ephraim": 50696,
|
| 245 |
+
"Erica": 50444,
|
| 246 |
+
"Erick": 50445,
|
| 247 |
+
"Erik": 50446,
|
| 248 |
+
"Erin": 50447,
|
| 249 |
+
"Ernest": 50448,
|
| 250 |
+
"Ernie": 50449,
|
| 251 |
+
"Esme": 50450,
|
| 252 |
+
"Esther": 50451,
|
| 253 |
+
"Ethan": 50452,
|
| 254 |
+
"Ethel": 50453,
|
| 255 |
+
"Eugene": 50454,
|
| 256 |
+
"Eulalia": 50697,
|
| 257 |
+
"Eunice": 50455,
|
| 258 |
+
"Evan": 50456,
|
| 259 |
+
"Evander": 50698,
|
| 260 |
+
"Eve": 50457,
|
| 261 |
+
"Evelyn": 50458,
|
| 262 |
+
"Everett": 50459,
|
| 263 |
+
"Ewan": 50460,
|
| 264 |
+
"Ezra": 50461,
|
| 265 |
+
"Fabian": 50462,
|
| 266 |
+
"Fanny": 50463,
|
| 267 |
+
"Faustino": 50699,
|
| 268 |
+
"Felicia": 50464,
|
| 269 |
+
"Felicity": 50700,
|
| 270 |
+
"Felix": 50465,
|
| 271 |
+
"Finley": 50701,
|
| 272 |
+
"Finn": 50467,
|
| 273 |
+
"Fiona": 50466,
|
| 274 |
+
"Flora": 50702,
|
| 275 |
+
"Floyd": 50468,
|
| 276 |
+
"Flynn": 50703,
|
| 277 |
+
"Forrest": 50469,
|
| 278 |
+
"Frances": 50470,
|
| 279 |
+
"Francis": 50471,
|
| 280 |
+
"Frankie": 50472,
|
| 281 |
+
"Freddie": 50473,
|
| 282 |
+
"Freddy": 50474,
|
| 283 |
+
"Frederica": 50704,
|
| 284 |
+
"Freya": 50475,
|
| 285 |
+
"Gabby": 50476,
|
| 286 |
+
"Gabe": 50477,
|
| 287 |
+
"Gabriel": 50478,
|
| 288 |
+
"Gael": 50705,
|
| 289 |
+
"Gail": 50479,
|
| 290 |
+
"Gale": 50480,
|
| 291 |
+
"Garrett": 50706,
|
| 292 |
+
"Garry": 50481,
|
| 293 |
+
"Gavin": 50482,
|
| 294 |
+
"Geoff": 50483,
|
| 295 |
+
"Gerald": 50484,
|
| 296 |
+
"Gerard": 50485,
|
| 297 |
+
"Gigi": 50486,
|
| 298 |
+
"Gilbert": 50487,
|
| 299 |
+
"Gina": 50488,
|
| 300 |
+
"Ginger": 50489,
|
| 301 |
+
"Gino": 50490,
|
| 302 |
+
"Giovanni": 50491,
|
| 303 |
+
"Gisela": 50707,
|
| 304 |
+
"Giselle": 50492,
|
| 305 |
+
"Gladys": 50493,
|
| 306 |
+
"Glen": 50494,
|
| 307 |
+
"Glenda": 50495,
|
| 308 |
+
"Glenn": 50496,
|
| 309 |
+
"Gloria": 50497,
|
| 310 |
+
"Grace": 50498,
|
| 311 |
+
"Grady": 50499,
|
| 312 |
+
"Gregg": 50500,
|
| 313 |
+
"Gregory": 50501,
|
| 314 |
+
"Greta": 50502,
|
| 315 |
+
"Gretchen": 50503,
|
| 316 |
+
"Griffin": 50504,
|
| 317 |
+
"Gus": 50505,
|
| 318 |
+
"Gustavo": 50708,
|
| 319 |
+
"Gwen": 50506,
|
| 320 |
+
"Hadley": 50709,
|
| 321 |
+
"Hailey": 50507,
|
| 322 |
+
"Hamza": 50710,
|
| 323 |
+
"Hank": 50508,
|
| 324 |
+
"Hanna": 50509,
|
| 325 |
+
"Hannah": 50510,
|
| 326 |
+
"Harland": 50711,
|
| 327 |
+
"Harley": 50511,
|
| 328 |
+
"Harold": 50512,
|
| 329 |
+
"Harvey": 50513,
|
| 330 |
+
"Hattie": 50712,
|
| 331 |
+
"Haven": 50713,
|
| 332 |
+
"Hazel": 50514,
|
| 333 |
+
"Heath": 50515,
|
| 334 |
+
"Heather": 50516,
|
| 335 |
+
"Hector": 50517,
|
| 336 |
+
"Heidi": 50518,
|
| 337 |
+
"Helen": 50519,
|
| 338 |
+
"Henri": 50520,
|
| 339 |
+
"Herb": 50521,
|
| 340 |
+
"Herman": 50522,
|
| 341 |
+
"Hilary": 50523,
|
| 342 |
+
"Holland": 50714,
|
| 343 |
+
"Holly": 50524,
|
| 344 |
+
"Horace": 50525,
|
| 345 |
+
"Hudson": 50526,
|
| 346 |
+
"Hugh": 50527,
|
| 347 |
+
"Hugo": 50528,
|
| 348 |
+
"Ida": 50529,
|
| 349 |
+
"Igor": 50530,
|
| 350 |
+
"Iker": 50715,
|
| 351 |
+
"Imogen": 50531,
|
| 352 |
+
"Indira": 50716,
|
| 353 |
+
"Ines": 50532,
|
| 354 |
+
"Inigo": 50717,
|
| 355 |
+
"Irene": 50533,
|
| 356 |
+
"Iris": 50534,
|
| 357 |
+
"Irma": 50535,
|
| 358 |
+
"Isaac": 50536,
|
| 359 |
+
"Isabel": 50537,
|
| 360 |
+
"Isabella": 50538,
|
| 361 |
+
"Isaiah": 50539,
|
| 362 |
+
"Isla": 50540,
|
| 363 |
+
"Ivan": 50541,
|
| 364 |
+
"Ivy": 50542,
|
| 365 |
+
"Jace": 50543,
|
| 366 |
+
"Jackie": 50544,
|
| 367 |
+
"Jacqueline": 50545,
|
| 368 |
+
"Jade": 50546,
|
| 369 |
+
"Jaime": 50547,
|
| 370 |
+
"Jalen": 50548,
|
| 371 |
+
"Jalil": 50718,
|
| 372 |
+
"Jana": 50549,
|
| 373 |
+
"Janet": 50550,
|
| 374 |
+
"Janice": 50551,
|
| 375 |
+
"Jared": 50552,
|
| 376 |
+
"Jareth": 50719,
|
| 377 |
+
"Jasmine": 50553,
|
| 378 |
+
"Jasper": 50554,
|
| 379 |
+
"Javier": 50555,
|
| 380 |
+
"Jayden": 50556,
|
| 381 |
+
"Jeanette": 50557,
|
| 382 |
+
"Jeanne": 50558,
|
| 383 |
+
"Jeffery": 50559,
|
| 384 |
+
"Jeffrey": 50560,
|
| 385 |
+
"Jenna": 50561,
|
| 386 |
+
"Jenny": 50562,
|
| 387 |
+
"Jensen": 50720,
|
| 388 |
+
"Jeremiah": 50563,
|
| 389 |
+
"Jermaine": 50564,
|
| 390 |
+
"Jerome": 50565,
|
| 391 |
+
"Jesse": 50566,
|
| 392 |
+
"Jessie": 50567,
|
| 393 |
+
"Jethro": 50721,
|
| 394 |
+
"Jill": 50568,
|
| 395 |
+
"Joan": 50569,
|
| 396 |
+
"Joanna": 50570,
|
| 397 |
+
"Joanne": 50571,
|
| 398 |
+
"Jocelyn": 50572,
|
| 399 |
+
"Jodi": 50573,
|
| 400 |
+
"Jodie": 50574,
|
| 401 |
+
"Joel": 50575,
|
| 402 |
+
"Joey": 50576,
|
| 403 |
+
"Jonah": 50577,
|
| 404 |
+
"Jorge": 50578,
|
| 405 |
+
"Josie": 50579,
|
| 406 |
+
"Jovan": 50722,
|
| 407 |
+
"Joyce": 50580,
|
| 408 |
+
"Juan": 50581,
|
| 409 |
+
"Juanita": 50582,
|
| 410 |
+
"Judith": 50583,
|
| 411 |
+
"Judy": 50584,
|
| 412 |
+
"Jules": 50585,
|
| 413 |
+
"Julia": 50586,
|
| 414 |
+
"Julian": 50587,
|
| 415 |
+
"Julie": 50588,
|
| 416 |
+
"Juliet": 50589,
|
| 417 |
+
"Julio": 50590,
|
| 418 |
+
"Julius": 50591,
|
| 419 |
+
"Kaden": 50592,
|
| 420 |
+
"Kael": 50723,
|
| 421 |
+
"Kai": 50593,
|
| 422 |
+
"Kaia": 50724,
|
| 423 |
+
"Kara": 50594,
|
| 424 |
+
"Karen": 50595,
|
| 425 |
+
"Kari": 50596,
|
| 426 |
+
"Karina": 50597,
|
| 427 |
+
"Katherine": 50598,
|
| 428 |
+
"Kathleen": 50599,
|
| 429 |
+
"Kathy": 50600,
|
| 430 |
+
"Katie": 50601,
|
| 431 |
+
"Kayla": 50602,
|
| 432 |
+
"Keira": 50603,
|
| 433 |
+
"Kelsey": 50604,
|
| 434 |
+
"Kendall": 50605,
|
| 435 |
+
"Kenji": 50725,
|
| 436 |
+
"Kennedy": 50606,
|
| 437 |
+
"Kenneth": 50607,
|
| 438 |
+
"Kenny": 50608,
|
| 439 |
+
"Khalid": 50609,
|
| 440 |
+
"Kian": 50726,
|
| 441 |
+
"Kimberly": 50610,
|
| 442 |
+
"Kip": 50727,
|
| 443 |
+
"Kirk": 50611,
|
| 444 |
+
"Kris": 50612,
|
| 445 |
+
"Krista": 50613,
|
| 446 |
+
"Kristen": 50614,
|
| 447 |
+
"Kristin": 50615,
|
| 448 |
+
"Kristina": 50616,
|
| 449 |
+
"Kurt": 50617,
|
| 450 |
+
"Lacey": 50618,
|
| 451 |
+
"Lachlan": 50728,
|
| 452 |
+
"Lana": 50619,
|
| 453 |
+
"Lance": 50620,
|
| 454 |
+
"Lara": 50621,
|
| 455 |
+
"Lauren": 50622,
|
| 456 |
+
"Laurie": 50623,
|
| 457 |
+
"Layla": 50624,
|
| 458 |
+
"Lazaro": 50729,
|
| 459 |
+
"Leah": 50625,
|
| 460 |
+
"Leandro": 50730,
|
| 461 |
+
"Leo": 50626,
|
| 462 |
+
"Leona": 50627,
|
| 463 |
+
"Leonard": 50628,
|
| 464 |
+
"Leroy": 50629,
|
| 465 |
+
"Leslie": 50630,
|
| 466 |
+
"Lester": 50631,
|
| 467 |
+
"Liam": 50632,
|
| 468 |
+
"Lincoln": 50633,
|
| 469 |
+
"Linda": 50634,
|
| 470 |
+
"Lindsay": 50635,
|
| 471 |
+
"Logan": 50636,
|
| 472 |
+
"Lola": 50637,
|
| 473 |
+
"Loren": 50638,
|
| 474 |
+
"Louise": 50639,
|
| 475 |
+
"Lucas": 50640,
|
| 476 |
+
"Lucien": 50731,
|
| 477 |
+
"Ludwig": 50732,
|
| 478 |
+
"Malik": 50733,
|
| 479 |
+
"Marcella": 50734,
|
| 480 |
+
"Maxton": 50735,
|
| 481 |
+
"Melina": 50736,
|
| 482 |
+
"Mireille": 50737,
|
| 483 |
+
"Mordecai": 50738,
|
| 484 |
+
"Talia": 50739
|
| 485 |
+
}
|
hop4_ckpt16000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTJForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gptj",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"resid_pdrop": 0.1,
|
| 19 |
+
"rotary_dim": 64,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.46.2",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 50740
|
| 25 |
+
}
|
hop4_ckpt16000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.2"
|
| 6 |
+
}
|
hop4_ckpt16000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hop4_ckpt16000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c4ceaf67e05632932fff1738fc8759026caa0f80f1a2c7d2daa82bfeebeb29
|
| 3 |
+
size 651965360
|
hop4_ckpt16000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee56a896e8f743111a1bb87e8646ee1705c471ba0f60916d7e1d9c7f3ffdb50
|
| 3 |
+
size 1303978682
|
hop4_ckpt16000/output/ind_test_metrics.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"exact_match": 0.504,
|
| 3 |
+
"administrator_1_administrator_1_patron_1_advisor_1_exact_match": 1.0,
|
| 4 |
+
"administrator_1_administrator_1_predecessor_1_coordinator_1_exact_match": 1.0,
|
| 5 |
+
"administrator_1_administrator_1_teacher_1_coordinator_1_exact_match": 1.0,
|
| 6 |
+
"administrator_1_administrator_1_teacher_1_supervisor_1_exact_match": 0.0,
|
| 7 |
+
"administrator_1_advisor_1_administrator_1_ruler_1_exact_match": 1.0,
|
| 8 |
+
"administrator_1_advisor_1_advisor_1_administrator_1_exact_match": 1.0,
|
| 9 |
+
"administrator_1_advisor_1_advisor_1_instructor_1_exact_match": 0.0,
|
| 10 |
+
"administrator_1_advisor_1_coordinator_1_administrator_1_exact_match": 1.0,
|
| 11 |
+
"administrator_1_advisor_1_overseer_1_overseer_1_exact_match": 1.0,
|
| 12 |
+
"administrator_1_advisor_1_patron_1_ruler_1_exact_match": 0.0,
|
| 13 |
+
"administrator_1_advisor_1_predecessor_1_overseer_1_exact_match": 1.0,
|
| 14 |
+
"administrator_1_advisor_1_predecessor_1_supervisor_1_exact_match": 0.0,
|
| 15 |
+
"administrator_1_advisor_1_sponsor_1_administrator_1_exact_match": 1.0,
|
| 16 |
+
"administrator_1_advisor_1_tutor_1_sponsor_1_exact_match": 1.0,
|
| 17 |
+
"administrator_1_backer_1_advisor_1_overseer_1_exact_match": 0.0,
|
| 18 |
+
"administrator_1_backer_1_leader_1_employer_1_exact_match": 1.0,
|
| 19 |
+
"administrator_1_backer_1_ruler_1_overseer_1_exact_match": 1.0,
|
| 20 |
+
"administrator_1_backer_1_teacher_1_advisor_1_exact_match": 1.0,
|
| 21 |
+
"administrator_1_backer_1_tutor_1_employer_1_exact_match": 0.0,
|
| 22 |
+
"administrator_1_boss_1_boss_1_ruler_1_exact_match": 1.0
|
| 23 |
+
}
|
hop4_ckpt16000/output/ind_test_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hop4_ckpt16000/output/ood_test_metrics.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"exact_match": 0.46066666666666667,
|
| 3 |
+
"administrator_1_administrator_1_advisor_1_patron_1_exact_match": 0.0,
|
| 4 |
+
"administrator_1_administrator_1_director_1_boss_1_exact_match": 0.0,
|
| 5 |
+
"administrator_1_administrator_1_director_1_coordinator_1_exact_match": 0.0,
|
| 6 |
+
"administrator_1_administrator_1_overseer_1_instructor_1_exact_match": 0.0,
|
| 7 |
+
"administrator_1_administrator_1_supervisor_1_coordinator_1_exact_match": 0.0,
|
| 8 |
+
"administrator_1_administrator_1_teacher_1_backer_1_exact_match": 0.0,
|
| 9 |
+
"administrator_1_administrator_1_tutor_1_predecessor_1_exact_match": 0.0,
|
| 10 |
+
"administrator_1_advisor_1_administrator_1_boss_1_exact_match": 1.0,
|
| 11 |
+
"administrator_1_advisor_1_director_1_boss_1_exact_match": 0.0,
|
| 12 |
+
"administrator_1_advisor_1_employer_1_director_1_exact_match": 1.0,
|
| 13 |
+
"administrator_1_advisor_1_predecessor_1_predecessor_1_exact_match": 1.0,
|
| 14 |
+
"administrator_1_advisor_1_sponsor_1_sponsor_1_exact_match": 1.0,
|
| 15 |
+
"administrator_1_advisor_1_tutor_1_supervisor_1_exact_match": 1.0,
|
| 16 |
+
"administrator_1_backer_1_boss_1_leader_1_exact_match": 0.0,
|
| 17 |
+
"administrator_1_backer_1_director_1_coordinator_1_exact_match": 1.0,
|
| 18 |
+
"administrator_1_backer_1_instructor_1_overseer_1_exact_match": 1.0,
|
| 19 |
+
"administrator_1_backer_1_leader_1_manager_1_exact_match": 0.0,
|
| 20 |
+
"administrator_1_backer_1_manager_1_leader_1_exact_match": 0.0,
|
| 21 |
+
"administrator_1_backer_1_patron_1_tutor_1_exact_match": 0.0,
|
| 22 |
+
"administrator_1_backer_1_predecessor_1_advisor_1_exact_match": 1.0
|
| 23 |
+
}
|
hop4_ckpt16000/output/ood_test_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hop4_ckpt16000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebddf114a1d2582ab54a2f5ff9eff001cd593eb1ab645c14f2ea578fb23c34af
|
| 3 |
+
size 14180
|
hop4_ckpt16000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8495ac79e8c7e3f08d77d1712b6d5798ef3e7aace6aea96e1b088f6570679768
|
| 3 |
+
size 1000
|
hop4_ckpt16000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
hop4_ckpt16000/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hop4_ckpt16000/trainer_state.json
ADDED
|
@@ -0,0 +1,1153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.37666325486182,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1023541453428864,
|
| 13 |
+
"grad_norm": 3.721527099609375,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 4.1737,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2047082906857728,
|
| 20 |
+
"grad_norm": 0.54378342628479,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 1.0918,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3070624360286592,
|
| 27 |
+
"grad_norm": 0.4711856544017792,
|
| 28 |
+
"learning_rate": 0.00015,
|
| 29 |
+
"loss": 0.9279,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4094165813715456,
|
| 34 |
+
"grad_norm": 0.47602081298828125,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.9056,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5117707267144319,
|
| 41 |
+
"grad_norm": 0.5099281072616577,
|
| 42 |
+
"learning_rate": 0.00025,
|
| 43 |
+
"loss": 0.9043,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6141248720573184,
|
| 48 |
+
"grad_norm": 0.4542568325996399,
|
| 49 |
+
"learning_rate": 0.0003,
|
| 50 |
+
"loss": 0.9037,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7164790174002047,
|
| 55 |
+
"grad_norm": 0.5254802703857422,
|
| 56 |
+
"learning_rate": 0.00035,
|
| 57 |
+
"loss": 0.903,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8188331627430911,
|
| 62 |
+
"grad_norm": 0.6677226424217224,
|
| 63 |
+
"learning_rate": 0.0004,
|
| 64 |
+
"loss": 0.9166,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9211873080859775,
|
| 69 |
+
"grad_norm": 0.4749118685722351,
|
| 70 |
+
"learning_rate": 0.00045000000000000004,
|
| 71 |
+
"loss": 0.9036,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0235414534288638,
|
| 76 |
+
"grad_norm": 0.39232656359672546,
|
| 77 |
+
"learning_rate": 0.0005,
|
| 78 |
+
"loss": 0.8953,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.1258955987717503,
|
| 83 |
+
"grad_norm": 0.3761468827724457,
|
| 84 |
+
"learning_rate": 0.0004999927000362188,
|
| 85 |
+
"loss": 0.8881,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.2282497441146367,
|
| 90 |
+
"grad_norm": 0.4788665473461151,
|
| 91 |
+
"learning_rate": 0.0004999708006185593,
|
| 92 |
+
"loss": 0.8834,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.330603889457523,
|
| 97 |
+
"grad_norm": 0.3669916093349457,
|
| 98 |
+
"learning_rate": 0.0004999343031680435,
|
| 99 |
+
"loss": 0.8822,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.4329580348004094,
|
| 104 |
+
"grad_norm": 0.31602203845977783,
|
| 105 |
+
"learning_rate": 0.0004998832100529384,
|
| 106 |
+
"loss": 0.8809,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.5353121801432958,
|
| 111 |
+
"grad_norm": 0.4091733694076538,
|
| 112 |
+
"learning_rate": 0.0004998175245886032,
|
| 113 |
+
"loss": 0.8809,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.6376663254861823,
|
| 118 |
+
"grad_norm": 0.5138052701950073,
|
| 119 |
+
"learning_rate": 0.0004997372510372735,
|
| 120 |
+
"loss": 0.88,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.7400204708290685,
|
| 125 |
+
"grad_norm": 0.41574376821517944,
|
| 126 |
+
"learning_rate": 0.0004996423946077849,
|
| 127 |
+
"loss": 0.8792,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.842374616171955,
|
| 132 |
+
"grad_norm": 0.3944094777107239,
|
| 133 |
+
"learning_rate": 0.0004995329614552355,
|
| 134 |
+
"loss": 0.8798,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.9447287615148414,
|
| 139 |
+
"grad_norm": 0.3074951767921448,
|
| 140 |
+
"learning_rate": 0.0004994089586805856,
|
| 141 |
+
"loss": 0.8785,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.0470829068577276,
|
| 146 |
+
"grad_norm": 0.44581228494644165,
|
| 147 |
+
"learning_rate": 0.0004992703943301973,
|
| 148 |
+
"loss": 0.878,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.1494370522006143,
|
| 153 |
+
"grad_norm": 0.5131877064704895,
|
| 154 |
+
"learning_rate": 0.000499117277395313,
|
| 155 |
+
"loss": 0.8776,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.2517911975435005,
|
| 160 |
+
"grad_norm": 0.3895834684371948,
|
| 161 |
+
"learning_rate": 0.000498949617811471,
|
| 162 |
+
"loss": 0.877,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.3541453428863868,
|
| 167 |
+
"grad_norm": 0.42680710554122925,
|
| 168 |
+
"learning_rate": 0.0004987674264578615,
|
| 169 |
+
"loss": 0.8771,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.4564994882292734,
|
| 174 |
+
"grad_norm": 0.31428012251853943,
|
| 175 |
+
"learning_rate": 0.0004985707151566205,
|
| 176 |
+
"loss": 0.8766,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.5588536335721597,
|
| 181 |
+
"grad_norm": 0.33548253774642944,
|
| 182 |
+
"learning_rate": 0.0004983594966720622,
|
| 183 |
+
"loss": 0.8757,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.661207778915046,
|
| 188 |
+
"grad_norm": 0.3320448100566864,
|
| 189 |
+
"learning_rate": 0.0004981337847098515,
|
| 190 |
+
"loss": 0.8752,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.7635619242579326,
|
| 195 |
+
"grad_norm": 0.2956862449645996,
|
| 196 |
+
"learning_rate": 0.0004978935939161141,
|
| 197 |
+
"loss": 0.8743,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.865916069600819,
|
| 202 |
+
"grad_norm": 0.410280704498291,
|
| 203 |
+
"learning_rate": 0.0004976389398764865,
|
| 204 |
+
"loss": 0.8743,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.968270214943705,
|
| 209 |
+
"grad_norm": 0.48070162534713745,
|
| 210 |
+
"learning_rate": 0.0004973698391151043,
|
| 211 |
+
"loss": 0.8731,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.0706243602865917,
|
| 216 |
+
"grad_norm": 0.3661304712295532,
|
| 217 |
+
"learning_rate": 0.0004970863090935304,
|
| 218 |
+
"loss": 0.8723,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.172978505629478,
|
| 223 |
+
"grad_norm": 0.33573538064956665,
|
| 224 |
+
"learning_rate": 0.0004967883682096214,
|
| 225 |
+
"loss": 0.8723,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.2753326509723646,
|
| 230 |
+
"grad_norm": 0.4095386266708374,
|
| 231 |
+
"learning_rate": 0.0004964760357963345,
|
| 232 |
+
"loss": 0.8712,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.377686796315251,
|
| 237 |
+
"grad_norm": 0.4460015594959259,
|
| 238 |
+
"learning_rate": 0.0004961493321204723,
|
| 239 |
+
"loss": 0.8708,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.480040941658137,
|
| 244 |
+
"grad_norm": 0.3180485963821411,
|
| 245 |
+
"learning_rate": 0.000495808278381368,
|
| 246 |
+
"loss": 0.8704,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.5823950870010233,
|
| 251 |
+
"grad_norm": 0.40890687704086304,
|
| 252 |
+
"learning_rate": 0.0004954528967095102,
|
| 253 |
+
"loss": 0.8701,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.68474923234391,
|
| 258 |
+
"grad_norm": 0.36936187744140625,
|
| 259 |
+
"learning_rate": 0.0004950832101651062,
|
| 260 |
+
"loss": 0.8695,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.787103377686796,
|
| 265 |
+
"grad_norm": 0.37348586320877075,
|
| 266 |
+
"learning_rate": 0.0004946992427365862,
|
| 267 |
+
"loss": 0.8785,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.889457523029683,
|
| 272 |
+
"grad_norm": 0.49073702096939087,
|
| 273 |
+
"learning_rate": 0.0004943010193390463,
|
| 274 |
+
"loss": 0.8697,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.991811668372569,
|
| 279 |
+
"grad_norm": 0.3646635413169861,
|
| 280 |
+
"learning_rate": 0.0004938885658126319,
|
| 281 |
+
"loss": 0.8693,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.094165813715455,
|
| 286 |
+
"grad_norm": 0.4270021319389343,
|
| 287 |
+
"learning_rate": 0.0004934619089208617,
|
| 288 |
+
"loss": 0.8683,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.1965199590583415,
|
| 293 |
+
"grad_norm": 0.36060985922813416,
|
| 294 |
+
"learning_rate": 0.0004930210763488896,
|
| 295 |
+
"loss": 0.868,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.298874104401229,
|
| 300 |
+
"grad_norm": 0.39852678775787354,
|
| 301 |
+
"learning_rate": 0.0004925660967017097,
|
| 302 |
+
"loss": 0.8675,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.401228249744115,
|
| 307 |
+
"grad_norm": 0.3556267023086548,
|
| 308 |
+
"learning_rate": 0.0004920969995022991,
|
| 309 |
+
"loss": 0.8678,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.503582395087001,
|
| 314 |
+
"grad_norm": 0.3079313337802887,
|
| 315 |
+
"learning_rate": 0.0004916138151897029,
|
| 316 |
+
"loss": 0.8676,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.605936540429887,
|
| 321 |
+
"grad_norm": 0.27450665831565857,
|
| 322 |
+
"learning_rate": 0.0004911165751170588,
|
| 323 |
+
"loss": 0.8672,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.7082906857727735,
|
| 328 |
+
"grad_norm": 0.3451884686946869,
|
| 329 |
+
"learning_rate": 0.0004906053115495624,
|
| 330 |
+
"loss": 0.8672,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.81064483111566,
|
| 335 |
+
"grad_norm": 0.32675692439079285,
|
| 336 |
+
"learning_rate": 0.0004900800576623741,
|
| 337 |
+
"loss": 0.8672,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.912998976458547,
|
| 342 |
+
"grad_norm": 0.3228359520435333,
|
| 343 |
+
"learning_rate": 0.0004895408475384656,
|
| 344 |
+
"loss": 0.8666,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.015353121801433,
|
| 349 |
+
"grad_norm": 0.34758397936820984,
|
| 350 |
+
"learning_rate": 0.0004889877161664096,
|
| 351 |
+
"loss": 0.8668,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 5.117707267144319,
|
| 356 |
+
"grad_norm": 0.3868649899959564,
|
| 357 |
+
"learning_rate": 0.0004884206994381077,
|
| 358 |
+
"loss": 0.8666,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.220061412487206,
|
| 363 |
+
"grad_norm": 0.2795661687850952,
|
| 364 |
+
"learning_rate": 0.00048783983414646317,
|
| 365 |
+
"loss": 0.8661,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.322415557830092,
|
| 370 |
+
"grad_norm": 0.387501060962677,
|
| 371 |
+
"learning_rate": 0.00048724515798299217,
|
| 372 |
+
"loss": 0.8666,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 5.424769703172979,
|
| 377 |
+
"grad_norm": 0.33271458745002747,
|
| 378 |
+
"learning_rate": 0.00048663670953537884,
|
| 379 |
+
"loss": 0.8659,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.527123848515865,
|
| 384 |
+
"grad_norm": 0.254276841878891,
|
| 385 |
+
"learning_rate": 0.000486014528284971,
|
| 386 |
+
"loss": 0.8661,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.629477993858751,
|
| 391 |
+
"grad_norm": 0.2719576954841614,
|
| 392 |
+
"learning_rate": 0.0004853786546042184,
|
| 393 |
+
"loss": 0.8661,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.731832139201638,
|
| 398 |
+
"grad_norm": 0.24630558490753174,
|
| 399 |
+
"learning_rate": 0.0004847291297540528,
|
| 400 |
+
"loss": 0.8659,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.834186284544524,
|
| 405 |
+
"grad_norm": 0.286715030670166,
|
| 406 |
+
"learning_rate": 0.000484065995881211,
|
| 407 |
+
"loss": 0.8657,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.93654042988741,
|
| 412 |
+
"grad_norm": 0.3164106607437134,
|
| 413 |
+
"learning_rate": 0.0004833892960154997,
|
| 414 |
+
"loss": 0.8657,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 6.038894575230297,
|
| 419 |
+
"grad_norm": 0.39808493852615356,
|
| 420 |
+
"learning_rate": 0.0004826990740670035,
|
| 421 |
+
"loss": 0.8654,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.141248720573183,
|
| 426 |
+
"grad_norm": 0.2913668751716614,
|
| 427 |
+
"learning_rate": 0.0004819953748232355,
|
| 428 |
+
"loss": 0.8653,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 6.24360286591607,
|
| 433 |
+
"grad_norm": 0.25999435782432556,
|
| 434 |
+
"learning_rate": 0.0004812782439462311,
|
| 435 |
+
"loss": 0.8653,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 6.345957011258956,
|
| 440 |
+
"grad_norm": 0.28035813570022583,
|
| 441 |
+
"learning_rate": 0.00048054772796958517,
|
| 442 |
+
"loss": 0.8654,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.448311156601842,
|
| 447 |
+
"grad_norm": 0.3780825436115265,
|
| 448 |
+
"learning_rate": 0.00047980387429543276,
|
| 449 |
+
"loss": 0.8653,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.550665301944729,
|
| 454 |
+
"grad_norm": 0.33089521527290344,
|
| 455 |
+
"learning_rate": 0.0004790467311913727,
|
| 456 |
+
"loss": 0.8652,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.653019447287615,
|
| 461 |
+
"grad_norm": 0.26362425088882446,
|
| 462 |
+
"learning_rate": 0.000478276347787336,
|
| 463 |
+
"loss": 0.8648,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.755373592630502,
|
| 468 |
+
"grad_norm": 0.31732290983200073,
|
| 469 |
+
"learning_rate": 0.0004774927740723977,
|
| 470 |
+
"loss": 0.865,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.857727737973388,
|
| 475 |
+
"grad_norm": 0.30799731612205505,
|
| 476 |
+
"learning_rate": 0.00047669606089153333,
|
| 477 |
+
"loss": 0.865,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.960081883316274,
|
| 482 |
+
"grad_norm": 0.25146472454071045,
|
| 483 |
+
"learning_rate": 0.0004758862599423194,
|
| 484 |
+
"loss": 0.8652,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.06243602865916,
|
| 489 |
+
"grad_norm": 0.3829899728298187,
|
| 490 |
+
"learning_rate": 0.0004750634237715791,
|
| 491 |
+
"loss": 0.8645,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.164790174002047,
|
| 496 |
+
"grad_norm": 0.33478277921676636,
|
| 497 |
+
"learning_rate": 0.0004742276057719722,
|
| 498 |
+
"loss": 0.8643,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.267144319344934,
|
| 503 |
+
"grad_norm": 0.32199761271476746,
|
| 504 |
+
"learning_rate": 0.00047337886017853115,
|
| 505 |
+
"loss": 0.864,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.36949846468782,
|
| 510 |
+
"grad_norm": 0.27683335542678833,
|
| 511 |
+
"learning_rate": 0.0004725172420651411,
|
| 512 |
+
"loss": 0.8642,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.471852610030706,
|
| 517 |
+
"grad_norm": 0.2956780791282654,
|
| 518 |
+
"learning_rate": 0.0004716428073409665,
|
| 519 |
+
"loss": 0.8644,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.574206755373592,
|
| 524 |
+
"grad_norm": 0.2937179207801819,
|
| 525 |
+
"learning_rate": 0.0004707556127468238,
|
| 526 |
+
"loss": 0.8645,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.6765609007164795,
|
| 531 |
+
"grad_norm": 0.302227646112442,
|
| 532 |
+
"learning_rate": 0.0004698557158514987,
|
| 533 |
+
"loss": 0.8644,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.778915046059366,
|
| 538 |
+
"grad_norm": 0.24734708666801453,
|
| 539 |
+
"learning_rate": 0.0004689431750480111,
|
| 540 |
+
"loss": 0.864,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.881269191402252,
|
| 545 |
+
"grad_norm": 0.3221675157546997,
|
| 546 |
+
"learning_rate": 0.00046801804954982594,
|
| 547 |
+
"loss": 0.8638,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.983623336745138,
|
| 552 |
+
"grad_norm": 0.2962391972541809,
|
| 553 |
+
"learning_rate": 0.0004670803993870113,
|
| 554 |
+
"loss": 0.8639,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 8.085977482088024,
|
| 559 |
+
"grad_norm": 0.3594909608364105,
|
| 560 |
+
"learning_rate": 0.00046613028540234226,
|
| 561 |
+
"loss": 0.8634,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 8.18833162743091,
|
| 566 |
+
"grad_norm": 0.2882649004459381,
|
| 567 |
+
"learning_rate": 0.0004651677692473538,
|
| 568 |
+
"loss": 0.8628,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.290685772773797,
|
| 573 |
+
"grad_norm": 0.30463457107543945,
|
| 574 |
+
"learning_rate": 0.00046419291337834,
|
| 575 |
+
"loss": 0.8634,
|
| 576 |
+
"step": 8100
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 8.393039918116683,
|
| 580 |
+
"grad_norm": 0.2734189033508301,
|
| 581 |
+
"learning_rate": 0.00046320578105230097,
|
| 582 |
+
"loss": 0.863,
|
| 583 |
+
"step": 8200
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 8.49539406345957,
|
| 587 |
+
"grad_norm": 0.29210585355758667,
|
| 588 |
+
"learning_rate": 0.00046220643632283897,
|
| 589 |
+
"loss": 0.8626,
|
| 590 |
+
"step": 8300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.597748208802457,
|
| 594 |
+
"grad_norm": 0.30293673276901245,
|
| 595 |
+
"learning_rate": 0.0004611949440360013,
|
| 596 |
+
"loss": 0.8627,
|
| 597 |
+
"step": 8400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.700102354145343,
|
| 601 |
+
"grad_norm": 0.36015939712524414,
|
| 602 |
+
"learning_rate": 0.00046017136982607265,
|
| 603 |
+
"loss": 0.8628,
|
| 604 |
+
"step": 8500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.80245649948823,
|
| 608 |
+
"grad_norm": 0.2649295926094055,
|
| 609 |
+
"learning_rate": 0.00045913578011131707,
|
| 610 |
+
"loss": 0.8626,
|
| 611 |
+
"step": 8600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.904810644831116,
|
| 615 |
+
"grad_norm": 0.28369492292404175,
|
| 616 |
+
"learning_rate": 0.00045808824208966694,
|
| 617 |
+
"loss": 0.8625,
|
| 618 |
+
"step": 8700
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 9.007164790174002,
|
| 622 |
+
"grad_norm": 0.3470466732978821,
|
| 623 |
+
"learning_rate": 0.00045702882373436317,
|
| 624 |
+
"loss": 0.8625,
|
| 625 |
+
"step": 8800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 9.109518935516888,
|
| 629 |
+
"grad_norm": 0.3262699544429779,
|
| 630 |
+
"learning_rate": 0.00045595759378954477,
|
| 631 |
+
"loss": 0.8612,
|
| 632 |
+
"step": 8900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 9.211873080859775,
|
| 636 |
+
"grad_norm": 0.3072861135005951,
|
| 637 |
+
"learning_rate": 0.0004548746217657878,
|
| 638 |
+
"loss": 0.8618,
|
| 639 |
+
"step": 9000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 9.31422722620266,
|
| 643 |
+
"grad_norm": 0.33485347032546997,
|
| 644 |
+
"learning_rate": 0.0004537799779355947,
|
| 645 |
+
"loss": 0.8614,
|
| 646 |
+
"step": 9100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 9.416581371545547,
|
| 650 |
+
"grad_norm": 0.29758310317993164,
|
| 651 |
+
"learning_rate": 0.0004526737333288351,
|
| 652 |
+
"loss": 0.8616,
|
| 653 |
+
"step": 9200
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 9.518935516888433,
|
| 657 |
+
"grad_norm": 0.3337891697883606,
|
| 658 |
+
"learning_rate": 0.0004515559597281362,
|
| 659 |
+
"loss": 0.8615,
|
| 660 |
+
"step": 9300
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.62128966223132,
|
| 664 |
+
"grad_norm": 0.3982974588871002,
|
| 665 |
+
"learning_rate": 0.00045042672966422506,
|
| 666 |
+
"loss": 0.8614,
|
| 667 |
+
"step": 9400
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 9.723643807574208,
|
| 671 |
+
"grad_norm": 0.35770276188850403,
|
| 672 |
+
"learning_rate": 0.00044928611641122226,
|
| 673 |
+
"loss": 0.8632,
|
| 674 |
+
"step": 9500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.825997952917094,
|
| 678 |
+
"grad_norm": 0.2550787627696991,
|
| 679 |
+
"learning_rate": 0.0004481341939818874,
|
| 680 |
+
"loss": 0.8618,
|
| 681 |
+
"step": 9600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.92835209825998,
|
| 685 |
+
"grad_norm": 0.2718902826309204,
|
| 686 |
+
"learning_rate": 0.00044697103712281584,
|
| 687 |
+
"loss": 0.8612,
|
| 688 |
+
"step": 9700
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 10.030706243602866,
|
| 692 |
+
"grad_norm": 0.35453763604164124,
|
| 693 |
+
"learning_rate": 0.00044579672130958957,
|
| 694 |
+
"loss": 0.8607,
|
| 695 |
+
"step": 9800
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 10.133060388945752,
|
| 699 |
+
"grad_norm": 0.3834429979324341,
|
| 700 |
+
"learning_rate": 0.00044461132274187877,
|
| 701 |
+
"loss": 0.86,
|
| 702 |
+
"step": 9900
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 10.235414534288639,
|
| 706 |
+
"grad_norm": 0.32199379801750183,
|
| 707 |
+
"learning_rate": 0.00044341491833849774,
|
| 708 |
+
"loss": 0.86,
|
| 709 |
+
"step": 10000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 10.337768679631525,
|
| 713 |
+
"grad_norm": 0.37525153160095215,
|
| 714 |
+
"learning_rate": 0.0004422075857324137,
|
| 715 |
+
"loss": 0.86,
|
| 716 |
+
"step": 10100
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 10.440122824974411,
|
| 720 |
+
"grad_norm": 0.32633689045906067,
|
| 721 |
+
"learning_rate": 0.0004409894032657094,
|
| 722 |
+
"loss": 0.8601,
|
| 723 |
+
"step": 10200
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 10.542476970317297,
|
| 727 |
+
"grad_norm": 0.3036169707775116,
|
| 728 |
+
"learning_rate": 0.000439760449984499,
|
| 729 |
+
"loss": 0.8599,
|
| 730 |
+
"step": 10300
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 10.644831115660184,
|
| 734 |
+
"grad_norm": 0.38257095217704773,
|
| 735 |
+
"learning_rate": 0.00043852080563380025,
|
| 736 |
+
"loss": 0.8601,
|
| 737 |
+
"step": 10400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 10.74718526100307,
|
| 741 |
+
"grad_norm": 0.34093451499938965,
|
| 742 |
+
"learning_rate": 0.00043727055065235826,
|
| 743 |
+
"loss": 0.8601,
|
| 744 |
+
"step": 10500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 10.849539406345958,
|
| 748 |
+
"grad_norm": 0.3586497902870178,
|
| 749 |
+
"learning_rate": 0.00043600976616742725,
|
| 750 |
+
"loss": 0.86,
|
| 751 |
+
"step": 10600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 10.951893551688844,
|
| 755 |
+
"grad_norm": 0.40940773487091064,
|
| 756 |
+
"learning_rate": 0.00043473853398950566,
|
| 757 |
+
"loss": 0.8601,
|
| 758 |
+
"step": 10700
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 11.05424769703173,
|
| 762 |
+
"grad_norm": 0.41463154554367065,
|
| 763 |
+
"learning_rate": 0.0004334569366070277,
|
| 764 |
+
"loss": 0.8593,
|
| 765 |
+
"step": 10800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 11.156601842374616,
|
| 769 |
+
"grad_norm": 0.3642037808895111,
|
| 770 |
+
"learning_rate": 0.0004321650571810109,
|
| 771 |
+
"loss": 0.8587,
|
| 772 |
+
"step": 10900
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 11.258955987717503,
|
| 776 |
+
"grad_norm": 0.3396519124507904,
|
| 777 |
+
"learning_rate": 0.0004308629795396599,
|
| 778 |
+
"loss": 0.8589,
|
| 779 |
+
"step": 11000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 11.361310133060389,
|
| 783 |
+
"grad_norm": 0.37284061312675476,
|
| 784 |
+
"learning_rate": 0.00042955078817292694,
|
| 785 |
+
"loss": 0.8586,
|
| 786 |
+
"step": 11100
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 11.463664278403275,
|
| 790 |
+
"grad_norm": 0.3378123641014099,
|
| 791 |
+
"learning_rate": 0.0004282285682270294,
|
| 792 |
+
"loss": 0.8591,
|
| 793 |
+
"step": 11200
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 11.566018423746161,
|
| 797 |
+
"grad_norm": 0.35244375467300415,
|
| 798 |
+
"learning_rate": 0.00042689640549892465,
|
| 799 |
+
"loss": 0.8588,
|
| 800 |
+
"step": 11300
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 11.668372569089048,
|
| 804 |
+
"grad_norm": 0.40692681074142456,
|
| 805 |
+
"learning_rate": 0.0004255543864307431,
|
| 806 |
+
"loss": 0.8589,
|
| 807 |
+
"step": 11400
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 11.770726714431934,
|
| 811 |
+
"grad_norm": 0.33798882365226746,
|
| 812 |
+
"learning_rate": 0.00042420259810417897,
|
| 813 |
+
"loss": 0.8588,
|
| 814 |
+
"step": 11500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 11.87308085977482,
|
| 818 |
+
"grad_norm": 0.29084691405296326,
|
| 819 |
+
"learning_rate": 0.00042284112823483944,
|
| 820 |
+
"loss": 0.8588,
|
| 821 |
+
"step": 11600
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 11.975435005117708,
|
| 825 |
+
"grad_norm": 0.41095981001853943,
|
| 826 |
+
"learning_rate": 0.0004214700651665534,
|
| 827 |
+
"loss": 0.8587,
|
| 828 |
+
"step": 11700
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 12.077789150460594,
|
| 832 |
+
"grad_norm": 0.35685116052627563,
|
| 833 |
+
"learning_rate": 0.0004200894978656384,
|
| 834 |
+
"loss": 0.8573,
|
| 835 |
+
"step": 11800
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 12.18014329580348,
|
| 839 |
+
"grad_norm": 0.3948342204093933,
|
| 840 |
+
"learning_rate": 0.0004186995159151283,
|
| 841 |
+
"loss": 0.8572,
|
| 842 |
+
"step": 11900
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 12.282497441146367,
|
| 846 |
+
"grad_norm": 0.4299517571926117,
|
| 847 |
+
"learning_rate": 0.0004173002095089599,
|
| 848 |
+
"loss": 0.8573,
|
| 849 |
+
"step": 12000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 12.384851586489253,
|
| 853 |
+
"grad_norm": 0.36627063155174255,
|
| 854 |
+
"learning_rate": 0.0004158916694461206,
|
| 855 |
+
"loss": 0.8577,
|
| 856 |
+
"step": 12100
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 12.48720573183214,
|
| 860 |
+
"grad_norm": 0.353518545627594,
|
| 861 |
+
"learning_rate": 0.0004144739871247566,
|
| 862 |
+
"loss": 0.8577,
|
| 863 |
+
"step": 12200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 12.589559877175025,
|
| 867 |
+
"grad_norm": 0.4006243646144867,
|
| 868 |
+
"learning_rate": 0.00041304725453624196,
|
| 869 |
+
"loss": 0.8576,
|
| 870 |
+
"step": 12300
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 12.691914022517912,
|
| 874 |
+
"grad_norm": 0.495148628950119,
|
| 875 |
+
"learning_rate": 0.00041161156425921004,
|
| 876 |
+
"loss": 0.8577,
|
| 877 |
+
"step": 12400
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 12.794268167860798,
|
| 881 |
+
"grad_norm": 0.38269224762916565,
|
| 882 |
+
"learning_rate": 0.0004101670094535453,
|
| 883 |
+
"loss": 0.8576,
|
| 884 |
+
"step": 12500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 12.896622313203684,
|
| 888 |
+
"grad_norm": 0.35717472434043884,
|
| 889 |
+
"learning_rate": 0.00040871368385433894,
|
| 890 |
+
"loss": 0.8576,
|
| 891 |
+
"step": 12600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 12.99897645854657,
|
| 895 |
+
"grad_norm": 0.4034062623977661,
|
| 896 |
+
"learning_rate": 0.0004072516817658065,
|
| 897 |
+
"loss": 0.8575,
|
| 898 |
+
"step": 12700
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 13.101330603889458,
|
| 902 |
+
"grad_norm": 0.37198975682258606,
|
| 903 |
+
"learning_rate": 0.0004057810980551683,
|
| 904 |
+
"loss": 0.8556,
|
| 905 |
+
"step": 12800
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 13.203684749232345,
|
| 909 |
+
"grad_norm": 0.47273877263069153,
|
| 910 |
+
"learning_rate": 0.00040430202814649386,
|
| 911 |
+
"loss": 0.8558,
|
| 912 |
+
"step": 12900
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 13.30603889457523,
|
| 916 |
+
"grad_norm": 0.46173539757728577,
|
| 917 |
+
"learning_rate": 0.00040281456801451003,
|
| 918 |
+
"loss": 0.856,
|
| 919 |
+
"step": 13000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 13.408393039918117,
|
| 923 |
+
"grad_norm": 0.39931073784828186,
|
| 924 |
+
"learning_rate": 0.0004013188141783732,
|
| 925 |
+
"loss": 0.8559,
|
| 926 |
+
"step": 13100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 13.510747185261003,
|
| 930 |
+
"grad_norm": 0.49196308851242065,
|
| 931 |
+
"learning_rate": 0.0003998148636954063,
|
| 932 |
+
"loss": 0.8562,
|
| 933 |
+
"step": 13200
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 13.61310133060389,
|
| 937 |
+
"grad_norm": 0.3254620134830475,
|
| 938 |
+
"learning_rate": 0.0003983028141548008,
|
| 939 |
+
"loss": 0.8563,
|
| 940 |
+
"step": 13300
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 13.715455475946776,
|
| 944 |
+
"grad_norm": 0.4419420659542084,
|
| 945 |
+
"learning_rate": 0.00039678276367128456,
|
| 946 |
+
"loss": 0.8563,
|
| 947 |
+
"step": 13400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 13.817809621289662,
|
| 951 |
+
"grad_norm": 0.44381722807884216,
|
| 952 |
+
"learning_rate": 0.00039525481087875525,
|
| 953 |
+
"loss": 0.8562,
|
| 954 |
+
"step": 13500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 13.920163766632548,
|
| 958 |
+
"grad_norm": 0.3799549341201782,
|
| 959 |
+
"learning_rate": 0.0003937190549238799,
|
| 960 |
+
"loss": 0.8562,
|
| 961 |
+
"step": 13600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 14.022517911975434,
|
| 965 |
+
"grad_norm": 0.45465409755706787,
|
| 966 |
+
"learning_rate": 0.00039217559545966154,
|
| 967 |
+
"loss": 0.8557,
|
| 968 |
+
"step": 13700
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 14.12487205731832,
|
| 972 |
+
"grad_norm": 0.404901385307312,
|
| 973 |
+
"learning_rate": 0.00039062453263897297,
|
| 974 |
+
"loss": 0.8536,
|
| 975 |
+
"step": 13800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 14.227226202661209,
|
| 979 |
+
"grad_norm": 0.3856695294380188,
|
| 980 |
+
"learning_rate": 0.0003890659671080579,
|
| 981 |
+
"loss": 0.8539,
|
| 982 |
+
"step": 13900
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 14.329580348004095,
|
| 986 |
+
"grad_norm": 0.5299059152603149,
|
| 987 |
+
"learning_rate": 0.00038750000000000004,
|
| 988 |
+
"loss": 0.8542,
|
| 989 |
+
"step": 14000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.431934493346981,
|
| 993 |
+
"grad_norm": 0.4421129524707794,
|
| 994 |
+
"learning_rate": 0.00038592673292816096,
|
| 995 |
+
"loss": 0.8544,
|
| 996 |
+
"step": 14100
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.534288638689867,
|
| 1000 |
+
"grad_norm": 0.35971203446388245,
|
| 1001 |
+
"learning_rate": 0.0003843462679795863,
|
| 1002 |
+
"loss": 0.8541,
|
| 1003 |
+
"step": 14200
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.636642784032754,
|
| 1007 |
+
"grad_norm": 0.44856682419776917,
|
| 1008 |
+
"learning_rate": 0.0003827587077083819,
|
| 1009 |
+
"loss": 0.8539,
|
| 1010 |
+
"step": 14300
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.73899692937564,
|
| 1014 |
+
"grad_norm": 0.3967397212982178,
|
| 1015 |
+
"learning_rate": 0.00038116415512905844,
|
| 1016 |
+
"loss": 0.8539,
|
| 1017 |
+
"step": 14400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.841351074718526,
|
| 1021 |
+
"grad_norm": 0.37601029872894287,
|
| 1022 |
+
"learning_rate": 0.0003795627137098479,
|
| 1023 |
+
"loss": 0.8538,
|
| 1024 |
+
"step": 14500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 14.943705220061412,
|
| 1028 |
+
"grad_norm": 0.5979766249656677,
|
| 1029 |
+
"learning_rate": 0.000377954487365989,
|
| 1030 |
+
"loss": 0.8535,
|
| 1031 |
+
"step": 14600
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 15.046059365404298,
|
| 1035 |
+
"grad_norm": 0.5098422169685364,
|
| 1036 |
+
"learning_rate": 0.00037633958045298435,
|
| 1037 |
+
"loss": 0.8517,
|
| 1038 |
+
"step": 14700
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 15.148413510747185,
|
| 1042 |
+
"grad_norm": 0.47610965371131897,
|
| 1043 |
+
"learning_rate": 0.0003747180977598293,
|
| 1044 |
+
"loss": 0.85,
|
| 1045 |
+
"step": 14800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 15.250767656090071,
|
| 1049 |
+
"grad_norm": 0.5189594626426697,
|
| 1050 |
+
"learning_rate": 0.0003730901445022123,
|
| 1051 |
+
"loss": 0.8501,
|
| 1052 |
+
"step": 14900
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 15.353121801432959,
|
| 1056 |
+
"grad_norm": 0.5471639037132263,
|
| 1057 |
+
"learning_rate": 0.0003714558263156872,
|
| 1058 |
+
"loss": 0.8501,
|
| 1059 |
+
"step": 15000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 15.455475946775845,
|
| 1063 |
+
"grad_norm": 0.44605281949043274,
|
| 1064 |
+
"learning_rate": 0.0003698152492488191,
|
| 1065 |
+
"loss": 0.8495,
|
| 1066 |
+
"step": 15100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 15.557830092118731,
|
| 1070 |
+
"grad_norm": 0.4775630235671997,
|
| 1071 |
+
"learning_rate": 0.0003681685197563027,
|
| 1072 |
+
"loss": 0.8488,
|
| 1073 |
+
"step": 15200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 15.660184237461618,
|
| 1077 |
+
"grad_norm": 0.44392699003219604,
|
| 1078 |
+
"learning_rate": 0.0003665157446920551,
|
| 1079 |
+
"loss": 0.848,
|
| 1080 |
+
"step": 15300
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 15.762538382804504,
|
| 1084 |
+
"grad_norm": 0.45308026671409607,
|
| 1085 |
+
"learning_rate": 0.00036485703130228147,
|
| 1086 |
+
"loss": 0.8468,
|
| 1087 |
+
"step": 15400
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 15.86489252814739,
|
| 1091 |
+
"grad_norm": 0.477937787771225,
|
| 1092 |
+
"learning_rate": 0.00036319248721851686,
|
| 1093 |
+
"loss": 0.8454,
|
| 1094 |
+
"step": 15500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 15.967246673490276,
|
| 1098 |
+
"grad_norm": 0.5226846933364868,
|
| 1099 |
+
"learning_rate": 0.0003615222204506415,
|
| 1100 |
+
"loss": 0.8426,
|
| 1101 |
+
"step": 15600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 16.069600818833162,
|
| 1105 |
+
"grad_norm": 0.4371955096721649,
|
| 1106 |
+
"learning_rate": 0.0003598463393798721,
|
| 1107 |
+
"loss": 0.8362,
|
| 1108 |
+
"step": 15700
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 16.17195496417605,
|
| 1112 |
+
"grad_norm": 0.5559117197990417,
|
| 1113 |
+
"learning_rate": 0.00035816495275173,
|
| 1114 |
+
"loss": 0.831,
|
| 1115 |
+
"step": 15800
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 16.274309109518935,
|
| 1119 |
+
"grad_norm": 0.5163963437080383,
|
| 1120 |
+
"learning_rate": 0.0003564781696689838,
|
| 1121 |
+
"loss": 0.8238,
|
| 1122 |
+
"step": 15900
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 16.37666325486182,
|
| 1126 |
+
"grad_norm": 0.5618897676467896,
|
| 1127 |
+
"learning_rate": 0.0003547860995845705,
|
| 1128 |
+
"loss": 0.8131,
|
| 1129 |
+
"step": 16000
|
| 1130 |
+
}
|
| 1131 |
+
],
|
| 1132 |
+
"logging_steps": 100,
|
| 1133 |
+
"max_steps": 40000,
|
| 1134 |
+
"num_input_tokens_seen": 0,
|
| 1135 |
+
"num_train_epochs": 41,
|
| 1136 |
+
"save_steps": 1000,
|
| 1137 |
+
"stateful_callbacks": {
|
| 1138 |
+
"TrainerControl": {
|
| 1139 |
+
"args": {
|
| 1140 |
+
"should_epoch_stop": false,
|
| 1141 |
+
"should_evaluate": false,
|
| 1142 |
+
"should_log": false,
|
| 1143 |
+
"should_save": true,
|
| 1144 |
+
"should_training_stop": false
|
| 1145 |
+
},
|
| 1146 |
+
"attributes": {}
|
| 1147 |
+
}
|
| 1148 |
+
},
|
| 1149 |
+
"total_flos": 5.6090149292867584e+17,
|
| 1150 |
+
"train_batch_size": 512,
|
| 1151 |
+
"trial_name": null,
|
| 1152 |
+
"trial_params": null
|
| 1153 |
+
}
|
hop4_ckpt16000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b5815a817710b6be6fd8559850ed3037fd3433526ae6385d6e9df768dae586
|
| 3 |
+
size 5240
|
hop4_ckpt16000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|