Upload 10 files
Browse files- config.json +258 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- spiece.model +3 -0
- tokenizer_config.json +58 -0
- trainer_state.json +2174 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/albert-base-spanish",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "control de bienes",
|
| 18 |
+
"1": "capacitaciones",
|
| 19 |
+
"2": "aval",
|
| 20 |
+
"3": "adquisiciones informe rt",
|
| 21 |
+
"4": "adquisiciones",
|
| 22 |
+
"5": "erp crm",
|
| 23 |
+
"6": "control de bienes prestamos",
|
| 24 |
+
"7": "control de cambios",
|
| 25 |
+
"8": "erp bienestar",
|
| 26 |
+
"9": "erp centros de produccion",
|
| 27 |
+
"10": "erp gestion academica evaluacion docente",
|
| 28 |
+
"11": "erp conceder acceso",
|
| 29 |
+
"12": "erp eliminar accesos",
|
| 30 |
+
"13": "erp financiero",
|
| 31 |
+
"14": "erp gestion academica",
|
| 32 |
+
"15": "erp no reportes",
|
| 33 |
+
"16": "erp gestion de biblioteca",
|
| 34 |
+
"17": "erp gestion logistica",
|
| 35 |
+
"18": "erp internacionalizacion",
|
| 36 |
+
"19": "erp investigacion cientifica",
|
| 37 |
+
"20": "erp talento humano",
|
| 38 |
+
"21": "erp salud ocupacional",
|
| 39 |
+
"22": "erp planificacion",
|
| 40 |
+
"23": "erp otros",
|
| 41 |
+
"24": "erp odoo monica otros",
|
| 42 |
+
"25": "evea conceder acceso",
|
| 43 |
+
"26": "erp vinculacion",
|
| 44 |
+
"27": "erp votaciones",
|
| 45 |
+
"28": "evea acceso al servicio evea",
|
| 46 |
+
"29": "evea cursos",
|
| 47 |
+
"30": "evea modificacion de la informacion",
|
| 48 |
+
"31": "evea eliminar accesos",
|
| 49 |
+
"32": "evea encuesta cuestionario tareas examenes",
|
| 50 |
+
"33": "evea interrupcion del servicio",
|
| 51 |
+
"34": "evea matriculacion en cursos",
|
| 52 |
+
"35": "evea reportes",
|
| 53 |
+
"36": "evea nuevo",
|
| 54 |
+
"37": "evea otro",
|
| 55 |
+
"38": "evea plataforma",
|
| 56 |
+
"39": "evea problema con la configuracion",
|
| 57 |
+
"40": "firma electronica quipux",
|
| 58 |
+
"41": "encuesta",
|
| 59 |
+
"42": "evea sincronizacion",
|
| 60 |
+
"43": "evea sincronizacion proveedor",
|
| 61 |
+
"44": "evea respaldos",
|
| 62 |
+
"45": "infraestructura respaldo y recuperacion",
|
| 63 |
+
"46": "gestion",
|
| 64 |
+
"47": "infraestructura conectividad",
|
| 65 |
+
"48": "infraestructura mantenimiento preventivo",
|
| 66 |
+
"49": "infraestructura uso de infraestructura fisica",
|
| 67 |
+
"50": "office 365 conceder acceso",
|
| 68 |
+
"51": "informe",
|
| 69 |
+
"52": "office 365",
|
| 70 |
+
"53": "office 365 acceso al servicio",
|
| 71 |
+
"54": "office 365 bloqueo de servicio",
|
| 72 |
+
"55": "office 365 problema con el servicio",
|
| 73 |
+
"56": "office 365 creacion de cuenta",
|
| 74 |
+
"57": "office 365 eliminar accesos",
|
| 75 |
+
"58": "office 365 interrupcion del servicio",
|
| 76 |
+
"59": "office 365 otro",
|
| 77 |
+
"60": "poa",
|
| 78 |
+
"61": "pagina web",
|
| 79 |
+
"62": "otros",
|
| 80 |
+
"63": "oficio",
|
| 81 |
+
"64": "office 365 roles y permisos",
|
| 82 |
+
"65": "reportes",
|
| 83 |
+
"66": "proveedor",
|
| 84 |
+
"67": "redes sociales",
|
| 85 |
+
"68": "proyectos",
|
| 86 |
+
"69": "repositorio base digital",
|
| 87 |
+
"70": "soporte equipos mantenimiento de hardware",
|
| 88 |
+
"71": "revistas",
|
| 89 |
+
"72": "servicios conceder accesos",
|
| 90 |
+
"73": "servicios elimnar accesos",
|
| 91 |
+
"74": "soporte equipos garantia",
|
| 92 |
+
"75": "soporte erp gestion logistica",
|
| 93 |
+
"76": "soporte equipos mantenimiento de software",
|
| 94 |
+
"77": "soporte erp bienestar",
|
| 95 |
+
"78": "soporte erp financiero",
|
| 96 |
+
"79": "soporte erp gestion academica",
|
| 97 |
+
"80": "soporte infraestructura",
|
| 98 |
+
"81": "soporte evea sincronizacion",
|
| 99 |
+
"82": "soporte erp talento humano",
|
| 100 |
+
"83": "soporte evea plataforma",
|
| 101 |
+
"84": "soporte erp otros",
|
| 102 |
+
"85": "soporte seguridad",
|
| 103 |
+
"86": "soporte otros",
|
| 104 |
+
"87": "soporte pagina web",
|
| 105 |
+
"88": "soporte repositorio base digital",
|
| 106 |
+
"89": "soporte revistas",
|
| 107 |
+
"90": "soporte odoo monica otros",
|
| 108 |
+
"91": "soporte infraestructura conectividad",
|
| 109 |
+
"92": "soporte infraestructura respaldo y recuperacion",
|
| 110 |
+
"93": "soporte mantenimiento correctivo",
|
| 111 |
+
"94": "soporte office 365",
|
| 112 |
+
"95": "streaming eventos",
|
| 113 |
+
"96": "soporte streaming eventos",
|
| 114 |
+
"97": "soporte turniting",
|
| 115 |
+
"98": "soporte zoom",
|
| 116 |
+
"99": "sin datos",
|
| 117 |
+
"100": "turnitin",
|
| 118 |
+
"101": "zoom credenciales zoom",
|
| 119 |
+
"102": "zoom interrupcion del servicio",
|
| 120 |
+
"103": "zoom licenciamiento",
|
| 121 |
+
"104": "zoom otros",
|
| 122 |
+
"105": "zoom webinar",
|
| 123 |
+
"106": "zoom conceder accesos",
|
| 124 |
+
"107": "zoom eliminar accesos",
|
| 125 |
+
"108": "zoom videoconferencia",
|
| 126 |
+
"109": "reporte informe"
|
| 127 |
+
},
|
| 128 |
+
"initializer_range": 0.02,
|
| 129 |
+
"inner_group_num": 1,
|
| 130 |
+
"intermediate_size": 3072,
|
| 131 |
+
"label2id": {
|
| 132 |
+
"adquisiciones": 4,
|
| 133 |
+
"adquisiciones informe rt": 3,
|
| 134 |
+
"aval": 2,
|
| 135 |
+
"capacitaciones": 1,
|
| 136 |
+
"control de bienes": 0,
|
| 137 |
+
"control de bienes prestamos": 6,
|
| 138 |
+
"control de cambios": 7,
|
| 139 |
+
"encuesta": 41,
|
| 140 |
+
"erp bienestar": 8,
|
| 141 |
+
"erp centros de produccion": 9,
|
| 142 |
+
"erp conceder acceso": 11,
|
| 143 |
+
"erp crm": 5,
|
| 144 |
+
"erp eliminar accesos": 12,
|
| 145 |
+
"erp financiero": 13,
|
| 146 |
+
"erp gestion academica": 14,
|
| 147 |
+
"erp gestion academica evaluacion docente": 10,
|
| 148 |
+
"erp gestion de biblioteca": 16,
|
| 149 |
+
"erp gestion logistica": 17,
|
| 150 |
+
"erp internacionalizacion": 18,
|
| 151 |
+
"erp investigacion cientifica": 19,
|
| 152 |
+
"erp no reportes": 15,
|
| 153 |
+
"erp odoo monica otros": 24,
|
| 154 |
+
"erp otros": 23,
|
| 155 |
+
"erp planificacion": 22,
|
| 156 |
+
"erp salud ocupacional": 21,
|
| 157 |
+
"erp talento humano": 20,
|
| 158 |
+
"erp vinculacion": 26,
|
| 159 |
+
"erp votaciones": 27,
|
| 160 |
+
"evea acceso al servicio evea": 28,
|
| 161 |
+
"evea conceder acceso": 25,
|
| 162 |
+
"evea cursos": 29,
|
| 163 |
+
"evea eliminar accesos": 31,
|
| 164 |
+
"evea encuesta cuestionario tareas examenes": 32,
|
| 165 |
+
"evea interrupcion del servicio": 33,
|
| 166 |
+
"evea matriculacion en cursos": 34,
|
| 167 |
+
"evea modificacion de la informacion": 30,
|
| 168 |
+
"evea nuevo": 36,
|
| 169 |
+
"evea otro": 37,
|
| 170 |
+
"evea plataforma": 38,
|
| 171 |
+
"evea problema con la configuracion": 39,
|
| 172 |
+
"evea reportes": 35,
|
| 173 |
+
"evea respaldos": 44,
|
| 174 |
+
"evea sincronizacion": 42,
|
| 175 |
+
"evea sincronizacion proveedor": 43,
|
| 176 |
+
"firma electronica quipux": 40,
|
| 177 |
+
"gestion": 46,
|
| 178 |
+
"informe": 51,
|
| 179 |
+
"infraestructura conectividad": 47,
|
| 180 |
+
"infraestructura mantenimiento preventivo": 48,
|
| 181 |
+
"infraestructura respaldo y recuperacion": 45,
|
| 182 |
+
"infraestructura uso de infraestructura fisica": 49,
|
| 183 |
+
"office 365": 52,
|
| 184 |
+
"office 365 acceso al servicio": 53,
|
| 185 |
+
"office 365 bloqueo de servicio": 54,
|
| 186 |
+
"office 365 conceder acceso": 50,
|
| 187 |
+
"office 365 creacion de cuenta": 56,
|
| 188 |
+
"office 365 eliminar accesos": 57,
|
| 189 |
+
"office 365 interrupcion del servicio": 58,
|
| 190 |
+
"office 365 otro": 59,
|
| 191 |
+
"office 365 problema con el servicio": 55,
|
| 192 |
+
"office 365 roles y permisos": 64,
|
| 193 |
+
"oficio": 63,
|
| 194 |
+
"otros": 62,
|
| 195 |
+
"pagina web": 61,
|
| 196 |
+
"poa": 60,
|
| 197 |
+
"proveedor": 66,
|
| 198 |
+
"proyectos": 68,
|
| 199 |
+
"redes sociales": 67,
|
| 200 |
+
"reporte informe": 109,
|
| 201 |
+
"reportes": 65,
|
| 202 |
+
"repositorio base digital": 69,
|
| 203 |
+
"revistas": 71,
|
| 204 |
+
"servicios conceder accesos": 72,
|
| 205 |
+
"servicios elimnar accesos": 73,
|
| 206 |
+
"sin datos": 99,
|
| 207 |
+
"soporte equipos garantia": 74,
|
| 208 |
+
"soporte equipos mantenimiento de hardware": 70,
|
| 209 |
+
"soporte equipos mantenimiento de software": 76,
|
| 210 |
+
"soporte erp bienestar": 77,
|
| 211 |
+
"soporte erp financiero": 78,
|
| 212 |
+
"soporte erp gestion academica": 79,
|
| 213 |
+
"soporte erp gestion logistica": 75,
|
| 214 |
+
"soporte erp otros": 84,
|
| 215 |
+
"soporte erp talento humano": 82,
|
| 216 |
+
"soporte evea plataforma": 83,
|
| 217 |
+
"soporte evea sincronizacion": 81,
|
| 218 |
+
"soporte infraestructura": 80,
|
| 219 |
+
"soporte infraestructura conectividad": 91,
|
| 220 |
+
"soporte infraestructura respaldo y recuperacion": 92,
|
| 221 |
+
"soporte mantenimiento correctivo": 93,
|
| 222 |
+
"soporte odoo monica otros": 90,
|
| 223 |
+
"soporte office 365": 94,
|
| 224 |
+
"soporte otros": 86,
|
| 225 |
+
"soporte pagina web": 87,
|
| 226 |
+
"soporte repositorio base digital": 88,
|
| 227 |
+
"soporte revistas": 89,
|
| 228 |
+
"soporte seguridad": 85,
|
| 229 |
+
"soporte streaming eventos": 96,
|
| 230 |
+
"soporte turniting": 97,
|
| 231 |
+
"soporte zoom": 98,
|
| 232 |
+
"streaming eventos": 95,
|
| 233 |
+
"turnitin": 100,
|
| 234 |
+
"zoom conceder accesos": 106,
|
| 235 |
+
"zoom credenciales zoom": 101,
|
| 236 |
+
"zoom eliminar accesos": 107,
|
| 237 |
+
"zoom interrupcion del servicio": 102,
|
| 238 |
+
"zoom licenciamiento": 103,
|
| 239 |
+
"zoom otros": 104,
|
| 240 |
+
"zoom videoconferencia": 108,
|
| 241 |
+
"zoom webinar": 105
|
| 242 |
+
},
|
| 243 |
+
"layer_norm_eps": 1e-12,
|
| 244 |
+
"max_position_embeddings": 512,
|
| 245 |
+
"model_type": "albert",
|
| 246 |
+
"net_structure_type": 0,
|
| 247 |
+
"num_attention_heads": 12,
|
| 248 |
+
"num_hidden_groups": 1,
|
| 249 |
+
"num_hidden_layers": 12,
|
| 250 |
+
"num_memory_blocks": 0,
|
| 251 |
+
"pad_token_id": 0,
|
| 252 |
+
"position_embedding_type": "absolute",
|
| 253 |
+
"problem_type": "single_label_classification",
|
| 254 |
+
"torch_dtype": "float32",
|
| 255 |
+
"transformers_version": "4.39.3",
|
| 256 |
+
"type_vocab_size": 2,
|
| 257 |
+
"vocab_size": 31000
|
| 258 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:909e97aade0be53fc202864814e872ee3509c2b036257c62995f0c7f7a9e2543
|
| 3 |
+
size 47588120
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c41fba1428b748c8b47cca1be887635074f6905ff26550bbad0bb1cf40ba8728
|
| 3 |
+
size 95192333
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be4aae32274ac6eb63aa22c35c92225e8f4e902c4a18206cedebd97731c0d092
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d95796ee97736aa2d0fb68a4f67e3fddbc81fbce9ec77a81f9e8eb8c1259245
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c98d44f2c8ba92d861c8705ca4386454387ac7070fb00e9cd934f401387656
|
| 3 |
+
size 797897
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"keep_accents": true,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"remove_space": true,
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9182948490230906,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-29910",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 29910,
|
| 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": 4.954967021942139,
|
| 14 |
+
"learning_rate": 4.9832831828819794e-05,
|
| 15 |
+
"loss": 4.7403,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 9.918214797973633,
|
| 21 |
+
"learning_rate": 4.9665663657639585e-05,
|
| 22 |
+
"loss": 4.7281,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 6.391179084777832,
|
| 28 |
+
"learning_rate": 4.949849548645938e-05,
|
| 29 |
+
"loss": 4.6786,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07,
|
| 34 |
+
"grad_norm": 6.756315231323242,
|
| 35 |
+
"learning_rate": 4.9331327315279175e-05,
|
| 36 |
+
"loss": 4.6128,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 8.407713890075684,
|
| 42 |
+
"learning_rate": 4.916415914409897e-05,
|
| 43 |
+
"loss": 4.4836,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"grad_norm": 8.354033470153809,
|
| 49 |
+
"learning_rate": 4.899699097291876e-05,
|
| 50 |
+
"loss": 4.3776,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"grad_norm": 7.996518611907959,
|
| 56 |
+
"learning_rate": 4.882982280173855e-05,
|
| 57 |
+
"loss": 4.2701,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13,
|
| 62 |
+
"grad_norm": 14.100532531738281,
|
| 63 |
+
"learning_rate": 4.866265463055835e-05,
|
| 64 |
+
"loss": 4.1032,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15,
|
| 69 |
+
"grad_norm": 10.907315254211426,
|
| 70 |
+
"learning_rate": 4.849548645937814e-05,
|
| 71 |
+
"loss": 3.952,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17,
|
| 76 |
+
"grad_norm": 9.731605529785156,
|
| 77 |
+
"learning_rate": 4.8328318288197924e-05,
|
| 78 |
+
"loss": 3.732,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18,
|
| 83 |
+
"grad_norm": 9.989665985107422,
|
| 84 |
+
"learning_rate": 4.816115011701772e-05,
|
| 85 |
+
"loss": 3.5489,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"grad_norm": 9.542133331298828,
|
| 91 |
+
"learning_rate": 4.7993981945837514e-05,
|
| 92 |
+
"loss": 3.3949,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22,
|
| 97 |
+
"grad_norm": 11.988595008850098,
|
| 98 |
+
"learning_rate": 4.7826813774657305e-05,
|
| 99 |
+
"loss": 3.216,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"grad_norm": 13.553967475891113,
|
| 105 |
+
"learning_rate": 4.76596456034771e-05,
|
| 106 |
+
"loss": 2.9855,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25,
|
| 111 |
+
"grad_norm": 42.20621109008789,
|
| 112 |
+
"learning_rate": 4.7492477432296895e-05,
|
| 113 |
+
"loss": 2.7659,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.27,
|
| 118 |
+
"grad_norm": 18.790130615234375,
|
| 119 |
+
"learning_rate": 4.732530926111669e-05,
|
| 120 |
+
"loss": 2.5604,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.28,
|
| 125 |
+
"grad_norm": 20.554113388061523,
|
| 126 |
+
"learning_rate": 4.715814108993648e-05,
|
| 127 |
+
"loss": 2.4376,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3,
|
| 132 |
+
"grad_norm": 18.882707595825195,
|
| 133 |
+
"learning_rate": 4.699097291875627e-05,
|
| 134 |
+
"loss": 2.3501,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32,
|
| 139 |
+
"grad_norm": 14.733109474182129,
|
| 140 |
+
"learning_rate": 4.682380474757606e-05,
|
| 141 |
+
"loss": 2.168,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33,
|
| 146 |
+
"grad_norm": 17.430740356445312,
|
| 147 |
+
"learning_rate": 4.665663657639586e-05,
|
| 148 |
+
"loss": 2.0081,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35,
|
| 153 |
+
"grad_norm": 21.797836303710938,
|
| 154 |
+
"learning_rate": 4.6489468405215644e-05,
|
| 155 |
+
"loss": 1.9554,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.37,
|
| 160 |
+
"grad_norm": 13.148958206176758,
|
| 161 |
+
"learning_rate": 4.632230023403544e-05,
|
| 162 |
+
"loss": 1.8524,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.38,
|
| 167 |
+
"grad_norm": 14.161394119262695,
|
| 168 |
+
"learning_rate": 4.6155132062855234e-05,
|
| 169 |
+
"loss": 1.793,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4,
|
| 174 |
+
"grad_norm": 20.908519744873047,
|
| 175 |
+
"learning_rate": 4.5987963891675026e-05,
|
| 176 |
+
"loss": 1.6493,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"grad_norm": 15.107952117919922,
|
| 182 |
+
"learning_rate": 4.582079572049482e-05,
|
| 183 |
+
"loss": 1.5724,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.43,
|
| 188 |
+
"grad_norm": 18.561201095581055,
|
| 189 |
+
"learning_rate": 4.5653627549314615e-05,
|
| 190 |
+
"loss": 1.4915,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.45,
|
| 195 |
+
"grad_norm": 15.365275382995605,
|
| 196 |
+
"learning_rate": 4.548645937813441e-05,
|
| 197 |
+
"loss": 1.488,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.47,
|
| 202 |
+
"grad_norm": 16.04875946044922,
|
| 203 |
+
"learning_rate": 4.53192912069542e-05,
|
| 204 |
+
"loss": 1.4316,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.48,
|
| 209 |
+
"grad_norm": 13.593673706054688,
|
| 210 |
+
"learning_rate": 4.515212303577399e-05,
|
| 211 |
+
"loss": 1.456,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5,
|
| 216 |
+
"grad_norm": 16.379798889160156,
|
| 217 |
+
"learning_rate": 4.498495486459378e-05,
|
| 218 |
+
"loss": 1.3006,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.52,
|
| 223 |
+
"grad_norm": 13.564205169677734,
|
| 224 |
+
"learning_rate": 4.481778669341358e-05,
|
| 225 |
+
"loss": 1.2661,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.53,
|
| 230 |
+
"grad_norm": 15.44586181640625,
|
| 231 |
+
"learning_rate": 4.4650618522233364e-05,
|
| 232 |
+
"loss": 1.2917,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.55,
|
| 237 |
+
"grad_norm": 12.80644416809082,
|
| 238 |
+
"learning_rate": 4.448345035105316e-05,
|
| 239 |
+
"loss": 1.1765,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.57,
|
| 244 |
+
"grad_norm": 19.545106887817383,
|
| 245 |
+
"learning_rate": 4.4316282179872954e-05,
|
| 246 |
+
"loss": 1.1622,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.59,
|
| 251 |
+
"grad_norm": 14.377379417419434,
|
| 252 |
+
"learning_rate": 4.414911400869275e-05,
|
| 253 |
+
"loss": 1.1047,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6,
|
| 258 |
+
"grad_norm": 21.595245361328125,
|
| 259 |
+
"learning_rate": 4.398194583751254e-05,
|
| 260 |
+
"loss": 1.1384,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.62,
|
| 265 |
+
"grad_norm": 14.641448020935059,
|
| 266 |
+
"learning_rate": 4.3814777666332335e-05,
|
| 267 |
+
"loss": 1.0872,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.64,
|
| 272 |
+
"grad_norm": 13.082781791687012,
|
| 273 |
+
"learning_rate": 4.364760949515213e-05,
|
| 274 |
+
"loss": 1.0366,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.65,
|
| 279 |
+
"grad_norm": 18.576641082763672,
|
| 280 |
+
"learning_rate": 4.348044132397192e-05,
|
| 281 |
+
"loss": 1.0953,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.67,
|
| 286 |
+
"grad_norm": 9.915220260620117,
|
| 287 |
+
"learning_rate": 4.331327315279171e-05,
|
| 288 |
+
"loss": 1.001,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.69,
|
| 293 |
+
"grad_norm": 12.059024810791016,
|
| 294 |
+
"learning_rate": 4.31461049816115e-05,
|
| 295 |
+
"loss": 1.0585,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7,
|
| 300 |
+
"grad_norm": 17.607337951660156,
|
| 301 |
+
"learning_rate": 4.29789368104313e-05,
|
| 302 |
+
"loss": 1.0179,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.72,
|
| 307 |
+
"grad_norm": 16.324430465698242,
|
| 308 |
+
"learning_rate": 4.2811768639251084e-05,
|
| 309 |
+
"loss": 0.9491,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.74,
|
| 314 |
+
"grad_norm": 19.5161075592041,
|
| 315 |
+
"learning_rate": 4.264460046807088e-05,
|
| 316 |
+
"loss": 0.9374,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.75,
|
| 321 |
+
"grad_norm": 20.448488235473633,
|
| 322 |
+
"learning_rate": 4.2477432296890674e-05,
|
| 323 |
+
"loss": 0.9146,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.77,
|
| 328 |
+
"grad_norm": 10.544804573059082,
|
| 329 |
+
"learning_rate": 4.231026412571047e-05,
|
| 330 |
+
"loss": 0.9187,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.79,
|
| 335 |
+
"grad_norm": 17.095731735229492,
|
| 336 |
+
"learning_rate": 4.214309595453026e-05,
|
| 337 |
+
"loss": 0.8732,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8,
|
| 342 |
+
"grad_norm": 18.1314754486084,
|
| 343 |
+
"learning_rate": 4.197592778335005e-05,
|
| 344 |
+
"loss": 0.9072,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.82,
|
| 349 |
+
"grad_norm": 8.516233444213867,
|
| 350 |
+
"learning_rate": 4.180875961216985e-05,
|
| 351 |
+
"loss": 0.8264,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.84,
|
| 356 |
+
"grad_norm": 12.620676040649414,
|
| 357 |
+
"learning_rate": 4.164159144098964e-05,
|
| 358 |
+
"loss": 0.8425,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.85,
|
| 363 |
+
"grad_norm": 23.544219970703125,
|
| 364 |
+
"learning_rate": 4.147442326980943e-05,
|
| 365 |
+
"loss": 0.8371,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.87,
|
| 370 |
+
"grad_norm": 15.980536460876465,
|
| 371 |
+
"learning_rate": 4.130725509862922e-05,
|
| 372 |
+
"loss": 0.8257,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.89,
|
| 377 |
+
"grad_norm": 16.621524810791016,
|
| 378 |
+
"learning_rate": 4.114008692744902e-05,
|
| 379 |
+
"loss": 0.7705,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9,
|
| 384 |
+
"grad_norm": 25.2496280670166,
|
| 385 |
+
"learning_rate": 4.0972918756268804e-05,
|
| 386 |
+
"loss": 0.7741,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.92,
|
| 391 |
+
"grad_norm": 12.541385650634766,
|
| 392 |
+
"learning_rate": 4.08057505850886e-05,
|
| 393 |
+
"loss": 0.7408,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.94,
|
| 398 |
+
"grad_norm": 30.975236892700195,
|
| 399 |
+
"learning_rate": 4.0638582413908394e-05,
|
| 400 |
+
"loss": 0.7417,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.95,
|
| 405 |
+
"grad_norm": 16.33625030517578,
|
| 406 |
+
"learning_rate": 4.0471414242728186e-05,
|
| 407 |
+
"loss": 0.766,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.97,
|
| 412 |
+
"grad_norm": 17.48399543762207,
|
| 413 |
+
"learning_rate": 4.030424607154798e-05,
|
| 414 |
+
"loss": 0.8336,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.99,
|
| 419 |
+
"grad_norm": 19.421096801757812,
|
| 420 |
+
"learning_rate": 4.013707790036777e-05,
|
| 421 |
+
"loss": 0.7135,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.0,
|
| 426 |
+
"eval_accuracy": 0.7995263469508584,
|
| 427 |
+
"eval_f1": 0.7955612032049123,
|
| 428 |
+
"eval_loss": 0.7165877223014832,
|
| 429 |
+
"eval_precision": 0.805591523931921,
|
| 430 |
+
"eval_recall": 0.7995263469508584,
|
| 431 |
+
"eval_runtime": 64.1068,
|
| 432 |
+
"eval_samples_per_second": 131.733,
|
| 433 |
+
"eval_steps_per_second": 8.236,
|
| 434 |
+
"step": 5982
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0,
|
| 438 |
+
"grad_norm": 10.486939430236816,
|
| 439 |
+
"learning_rate": 3.996990972918757e-05,
|
| 440 |
+
"loss": 0.685,
|
| 441 |
+
"step": 6000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.02,
|
| 445 |
+
"grad_norm": 19.489837646484375,
|
| 446 |
+
"learning_rate": 3.980274155800736e-05,
|
| 447 |
+
"loss": 0.6431,
|
| 448 |
+
"step": 6100
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.04,
|
| 452 |
+
"grad_norm": 8.935369491577148,
|
| 453 |
+
"learning_rate": 3.963557338682715e-05,
|
| 454 |
+
"loss": 0.6402,
|
| 455 |
+
"step": 6200
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.05,
|
| 459 |
+
"grad_norm": 10.298083305358887,
|
| 460 |
+
"learning_rate": 3.946840521564694e-05,
|
| 461 |
+
"loss": 0.6261,
|
| 462 |
+
"step": 6300
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.07,
|
| 466 |
+
"grad_norm": 18.606569290161133,
|
| 467 |
+
"learning_rate": 3.930123704446674e-05,
|
| 468 |
+
"loss": 0.5874,
|
| 469 |
+
"step": 6400
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.09,
|
| 473 |
+
"grad_norm": 12.412484169006348,
|
| 474 |
+
"learning_rate": 3.913406887328653e-05,
|
| 475 |
+
"loss": 0.5923,
|
| 476 |
+
"step": 6500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.1,
|
| 480 |
+
"grad_norm": 9.3939847946167,
|
| 481 |
+
"learning_rate": 3.8966900702106316e-05,
|
| 482 |
+
"loss": 0.6091,
|
| 483 |
+
"step": 6600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.12,
|
| 487 |
+
"grad_norm": 14.168825149536133,
|
| 488 |
+
"learning_rate": 3.8799732530926114e-05,
|
| 489 |
+
"loss": 0.6259,
|
| 490 |
+
"step": 6700
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.14,
|
| 494 |
+
"grad_norm": 18.846487045288086,
|
| 495 |
+
"learning_rate": 3.8632564359745906e-05,
|
| 496 |
+
"loss": 0.5543,
|
| 497 |
+
"step": 6800
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.15,
|
| 501 |
+
"grad_norm": 7.268430709838867,
|
| 502 |
+
"learning_rate": 3.84653961885657e-05,
|
| 503 |
+
"loss": 0.5615,
|
| 504 |
+
"step": 6900
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.17,
|
| 508 |
+
"grad_norm": 6.565930366516113,
|
| 509 |
+
"learning_rate": 3.829822801738549e-05,
|
| 510 |
+
"loss": 0.5725,
|
| 511 |
+
"step": 7000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.19,
|
| 515 |
+
"grad_norm": 11.122172355651855,
|
| 516 |
+
"learning_rate": 3.813105984620529e-05,
|
| 517 |
+
"loss": 0.543,
|
| 518 |
+
"step": 7100
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.2,
|
| 522 |
+
"grad_norm": 15.909794807434082,
|
| 523 |
+
"learning_rate": 3.796389167502508e-05,
|
| 524 |
+
"loss": 0.5053,
|
| 525 |
+
"step": 7200
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.22,
|
| 529 |
+
"grad_norm": 17.935998916625977,
|
| 530 |
+
"learning_rate": 3.779672350384487e-05,
|
| 531 |
+
"loss": 0.5866,
|
| 532 |
+
"step": 7300
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.24,
|
| 536 |
+
"grad_norm": 7.46903657913208,
|
| 537 |
+
"learning_rate": 3.762955533266466e-05,
|
| 538 |
+
"loss": 0.5573,
|
| 539 |
+
"step": 7400
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.25,
|
| 543 |
+
"grad_norm": 10.208723068237305,
|
| 544 |
+
"learning_rate": 3.746238716148446e-05,
|
| 545 |
+
"loss": 0.511,
|
| 546 |
+
"step": 7500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.27,
|
| 550 |
+
"grad_norm": 15.062224388122559,
|
| 551 |
+
"learning_rate": 3.729521899030425e-05,
|
| 552 |
+
"loss": 0.5211,
|
| 553 |
+
"step": 7600
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.29,
|
| 557 |
+
"grad_norm": 11.787239074707031,
|
| 558 |
+
"learning_rate": 3.7128050819124036e-05,
|
| 559 |
+
"loss": 0.5687,
|
| 560 |
+
"step": 7700
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.3,
|
| 564 |
+
"grad_norm": 20.22210693359375,
|
| 565 |
+
"learning_rate": 3.6960882647943834e-05,
|
| 566 |
+
"loss": 0.544,
|
| 567 |
+
"step": 7800
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.32,
|
| 571 |
+
"grad_norm": 22.17251205444336,
|
| 572 |
+
"learning_rate": 3.6793714476763626e-05,
|
| 573 |
+
"loss": 0.5223,
|
| 574 |
+
"step": 7900
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.34,
|
| 578 |
+
"grad_norm": 16.83318519592285,
|
| 579 |
+
"learning_rate": 3.662654630558342e-05,
|
| 580 |
+
"loss": 0.5043,
|
| 581 |
+
"step": 8000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.35,
|
| 585 |
+
"grad_norm": 10.143548965454102,
|
| 586 |
+
"learning_rate": 3.645937813440321e-05,
|
| 587 |
+
"loss": 0.5181,
|
| 588 |
+
"step": 8100
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.37,
|
| 592 |
+
"grad_norm": 20.629831314086914,
|
| 593 |
+
"learning_rate": 3.629220996322301e-05,
|
| 594 |
+
"loss": 0.4886,
|
| 595 |
+
"step": 8200
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.39,
|
| 599 |
+
"grad_norm": 12.14686107635498,
|
| 600 |
+
"learning_rate": 3.61250417920428e-05,
|
| 601 |
+
"loss": 0.5667,
|
| 602 |
+
"step": 8300
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.4,
|
| 606 |
+
"grad_norm": 17.1881160736084,
|
| 607 |
+
"learning_rate": 3.595787362086259e-05,
|
| 608 |
+
"loss": 0.5211,
|
| 609 |
+
"step": 8400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.42,
|
| 613 |
+
"grad_norm": 7.506267070770264,
|
| 614 |
+
"learning_rate": 3.579070544968238e-05,
|
| 615 |
+
"loss": 0.5356,
|
| 616 |
+
"step": 8500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.44,
|
| 620 |
+
"grad_norm": 23.122560501098633,
|
| 621 |
+
"learning_rate": 3.562353727850217e-05,
|
| 622 |
+
"loss": 0.5044,
|
| 623 |
+
"step": 8600
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.45,
|
| 627 |
+
"grad_norm": 21.808191299438477,
|
| 628 |
+
"learning_rate": 3.545636910732197e-05,
|
| 629 |
+
"loss": 0.5059,
|
| 630 |
+
"step": 8700
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.47,
|
| 634 |
+
"grad_norm": 12.899435997009277,
|
| 635 |
+
"learning_rate": 3.5289200936141756e-05,
|
| 636 |
+
"loss": 0.5082,
|
| 637 |
+
"step": 8800
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.49,
|
| 641 |
+
"grad_norm": 11.228046417236328,
|
| 642 |
+
"learning_rate": 3.5122032764961554e-05,
|
| 643 |
+
"loss": 0.4466,
|
| 644 |
+
"step": 8900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.5,
|
| 648 |
+
"grad_norm": 15.656624794006348,
|
| 649 |
+
"learning_rate": 3.4954864593781346e-05,
|
| 650 |
+
"loss": 0.4877,
|
| 651 |
+
"step": 9000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.52,
|
| 655 |
+
"grad_norm": 14.958187103271484,
|
| 656 |
+
"learning_rate": 3.478769642260114e-05,
|
| 657 |
+
"loss": 0.4283,
|
| 658 |
+
"step": 9100
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.54,
|
| 662 |
+
"grad_norm": 27.727924346923828,
|
| 663 |
+
"learning_rate": 3.462052825142093e-05,
|
| 664 |
+
"loss": 0.504,
|
| 665 |
+
"step": 9200
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.55,
|
| 669 |
+
"grad_norm": 21.103147506713867,
|
| 670 |
+
"learning_rate": 3.445336008024073e-05,
|
| 671 |
+
"loss": 0.5081,
|
| 672 |
+
"step": 9300
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.57,
|
| 676 |
+
"grad_norm": 14.884688377380371,
|
| 677 |
+
"learning_rate": 3.428619190906052e-05,
|
| 678 |
+
"loss": 0.47,
|
| 679 |
+
"step": 9400
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.59,
|
| 683 |
+
"grad_norm": 26.825908660888672,
|
| 684 |
+
"learning_rate": 3.411902373788031e-05,
|
| 685 |
+
"loss": 0.4587,
|
| 686 |
+
"step": 9500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.6,
|
| 690 |
+
"grad_norm": 23.39227867126465,
|
| 691 |
+
"learning_rate": 3.39518555667001e-05,
|
| 692 |
+
"loss": 0.4621,
|
| 693 |
+
"step": 9600
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.62,
|
| 697 |
+
"grad_norm": 15.503640174865723,
|
| 698 |
+
"learning_rate": 3.378468739551989e-05,
|
| 699 |
+
"loss": 0.5122,
|
| 700 |
+
"step": 9700
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.64,
|
| 704 |
+
"grad_norm": 13.298539161682129,
|
| 705 |
+
"learning_rate": 3.361751922433969e-05,
|
| 706 |
+
"loss": 0.4846,
|
| 707 |
+
"step": 9800
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.65,
|
| 711 |
+
"grad_norm": 17.961261749267578,
|
| 712 |
+
"learning_rate": 3.3450351053159476e-05,
|
| 713 |
+
"loss": 0.4576,
|
| 714 |
+
"step": 9900
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.67,
|
| 718 |
+
"grad_norm": 15.622933387756348,
|
| 719 |
+
"learning_rate": 3.3283182881979274e-05,
|
| 720 |
+
"loss": 0.4239,
|
| 721 |
+
"step": 10000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.69,
|
| 725 |
+
"grad_norm": 15.286486625671387,
|
| 726 |
+
"learning_rate": 3.3116014710799066e-05,
|
| 727 |
+
"loss": 0.4478,
|
| 728 |
+
"step": 10100
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.71,
|
| 732 |
+
"grad_norm": 28.045799255371094,
|
| 733 |
+
"learning_rate": 3.294884653961886e-05,
|
| 734 |
+
"loss": 0.4457,
|
| 735 |
+
"step": 10200
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.72,
|
| 739 |
+
"grad_norm": 23.578136444091797,
|
| 740 |
+
"learning_rate": 3.278167836843865e-05,
|
| 741 |
+
"loss": 0.464,
|
| 742 |
+
"step": 10300
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.74,
|
| 746 |
+
"grad_norm": 12.858305931091309,
|
| 747 |
+
"learning_rate": 3.261451019725844e-05,
|
| 748 |
+
"loss": 0.4507,
|
| 749 |
+
"step": 10400
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.76,
|
| 753 |
+
"grad_norm": 18.197952270507812,
|
| 754 |
+
"learning_rate": 3.244734202607824e-05,
|
| 755 |
+
"loss": 0.4158,
|
| 756 |
+
"step": 10500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.77,
|
| 760 |
+
"grad_norm": 5.134513854980469,
|
| 761 |
+
"learning_rate": 3.228017385489803e-05,
|
| 762 |
+
"loss": 0.4088,
|
| 763 |
+
"step": 10600
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.79,
|
| 767 |
+
"grad_norm": 2.1014363765716553,
|
| 768 |
+
"learning_rate": 3.211300568371782e-05,
|
| 769 |
+
"loss": 0.4524,
|
| 770 |
+
"step": 10700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.81,
|
| 774 |
+
"grad_norm": 14.459040641784668,
|
| 775 |
+
"learning_rate": 3.194583751253761e-05,
|
| 776 |
+
"loss": 0.4637,
|
| 777 |
+
"step": 10800
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.82,
|
| 781 |
+
"grad_norm": 29.922468185424805,
|
| 782 |
+
"learning_rate": 3.177866934135741e-05,
|
| 783 |
+
"loss": 0.4302,
|
| 784 |
+
"step": 10900
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.84,
|
| 788 |
+
"grad_norm": 23.523460388183594,
|
| 789 |
+
"learning_rate": 3.1611501170177196e-05,
|
| 790 |
+
"loss": 0.4155,
|
| 791 |
+
"step": 11000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.86,
|
| 795 |
+
"grad_norm": 11.668371200561523,
|
| 796 |
+
"learning_rate": 3.1444332998996994e-05,
|
| 797 |
+
"loss": 0.4238,
|
| 798 |
+
"step": 11100
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.87,
|
| 802 |
+
"grad_norm": 15.930005073547363,
|
| 803 |
+
"learning_rate": 3.1277164827816786e-05,
|
| 804 |
+
"loss": 0.4072,
|
| 805 |
+
"step": 11200
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.89,
|
| 809 |
+
"grad_norm": 18.61160659790039,
|
| 810 |
+
"learning_rate": 3.110999665663658e-05,
|
| 811 |
+
"loss": 0.4348,
|
| 812 |
+
"step": 11300
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.91,
|
| 816 |
+
"grad_norm": 27.475053787231445,
|
| 817 |
+
"learning_rate": 3.094282848545637e-05,
|
| 818 |
+
"loss": 0.4648,
|
| 819 |
+
"step": 11400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.92,
|
| 823 |
+
"grad_norm": 6.477468013763428,
|
| 824 |
+
"learning_rate": 3.077566031427616e-05,
|
| 825 |
+
"loss": 0.4241,
|
| 826 |
+
"step": 11500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.94,
|
| 830 |
+
"grad_norm": 26.99014663696289,
|
| 831 |
+
"learning_rate": 3.060849214309596e-05,
|
| 832 |
+
"loss": 0.4243,
|
| 833 |
+
"step": 11600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.96,
|
| 837 |
+
"grad_norm": 16.152755737304688,
|
| 838 |
+
"learning_rate": 3.0441323971915747e-05,
|
| 839 |
+
"loss": 0.4186,
|
| 840 |
+
"step": 11700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.97,
|
| 844 |
+
"grad_norm": 15.536150932312012,
|
| 845 |
+
"learning_rate": 3.0274155800735542e-05,
|
| 846 |
+
"loss": 0.3808,
|
| 847 |
+
"step": 11800
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.99,
|
| 851 |
+
"grad_norm": 23.708145141601562,
|
| 852 |
+
"learning_rate": 3.0106987629555333e-05,
|
| 853 |
+
"loss": 0.4365,
|
| 854 |
+
"step": 11900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.0,
|
| 858 |
+
"eval_accuracy": 0.8680876258140912,
|
| 859 |
+
"eval_f1": 0.8628914936078326,
|
| 860 |
+
"eval_loss": 0.4633374810218811,
|
| 861 |
+
"eval_precision": 0.8684864554322808,
|
| 862 |
+
"eval_recall": 0.8680876258140912,
|
| 863 |
+
"eval_runtime": 64.0052,
|
| 864 |
+
"eval_samples_per_second": 131.942,
|
| 865 |
+
"eval_steps_per_second": 8.249,
|
| 866 |
+
"step": 11964
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.01,
|
| 870 |
+
"grad_norm": 10.474257469177246,
|
| 871 |
+
"learning_rate": 2.9939819458375128e-05,
|
| 872 |
+
"loss": 0.3853,
|
| 873 |
+
"step": 12000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.02,
|
| 877 |
+
"grad_norm": 15.668170928955078,
|
| 878 |
+
"learning_rate": 2.977265128719492e-05,
|
| 879 |
+
"loss": 0.2858,
|
| 880 |
+
"step": 12100
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.04,
|
| 884 |
+
"grad_norm": 10.29902172088623,
|
| 885 |
+
"learning_rate": 2.960548311601471e-05,
|
| 886 |
+
"loss": 0.2803,
|
| 887 |
+
"step": 12200
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.06,
|
| 891 |
+
"grad_norm": 33.27579116821289,
|
| 892 |
+
"learning_rate": 2.9438314944834506e-05,
|
| 893 |
+
"loss": 0.2858,
|
| 894 |
+
"step": 12300
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.07,
|
| 898 |
+
"grad_norm": 13.799466133117676,
|
| 899 |
+
"learning_rate": 2.9271146773654294e-05,
|
| 900 |
+
"loss": 0.2793,
|
| 901 |
+
"step": 12400
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.09,
|
| 905 |
+
"grad_norm": 4.722692489624023,
|
| 906 |
+
"learning_rate": 2.9103978602474092e-05,
|
| 907 |
+
"loss": 0.2935,
|
| 908 |
+
"step": 12500
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.11,
|
| 912 |
+
"grad_norm": 8.643231391906738,
|
| 913 |
+
"learning_rate": 2.893681043129388e-05,
|
| 914 |
+
"loss": 0.2825,
|
| 915 |
+
"step": 12600
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.12,
|
| 919 |
+
"grad_norm": 10.378469467163086,
|
| 920 |
+
"learning_rate": 2.876964226011368e-05,
|
| 921 |
+
"loss": 0.2845,
|
| 922 |
+
"step": 12700
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.14,
|
| 926 |
+
"grad_norm": 9.1376953125,
|
| 927 |
+
"learning_rate": 2.8602474088933467e-05,
|
| 928 |
+
"loss": 0.2725,
|
| 929 |
+
"step": 12800
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.16,
|
| 933 |
+
"grad_norm": 10.372312545776367,
|
| 934 |
+
"learning_rate": 2.8435305917753262e-05,
|
| 935 |
+
"loss": 0.3067,
|
| 936 |
+
"step": 12900
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.17,
|
| 940 |
+
"grad_norm": 23.952699661254883,
|
| 941 |
+
"learning_rate": 2.8268137746573053e-05,
|
| 942 |
+
"loss": 0.2934,
|
| 943 |
+
"step": 13000
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.19,
|
| 947 |
+
"grad_norm": 2.125562906265259,
|
| 948 |
+
"learning_rate": 2.8100969575392848e-05,
|
| 949 |
+
"loss": 0.2535,
|
| 950 |
+
"step": 13100
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.21,
|
| 954 |
+
"grad_norm": 8.090828895568848,
|
| 955 |
+
"learning_rate": 2.793380140421264e-05,
|
| 956 |
+
"loss": 0.295,
|
| 957 |
+
"step": 13200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.22,
|
| 961 |
+
"grad_norm": 13.274210929870605,
|
| 962 |
+
"learning_rate": 2.776663323303243e-05,
|
| 963 |
+
"loss": 0.2851,
|
| 964 |
+
"step": 13300
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.24,
|
| 968 |
+
"grad_norm": 5.6807732582092285,
|
| 969 |
+
"learning_rate": 2.7599465061852226e-05,
|
| 970 |
+
"loss": 0.2662,
|
| 971 |
+
"step": 13400
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.26,
|
| 975 |
+
"grad_norm": 11.885269165039062,
|
| 976 |
+
"learning_rate": 2.7432296890672014e-05,
|
| 977 |
+
"loss": 0.2969,
|
| 978 |
+
"step": 13500
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.27,
|
| 982 |
+
"grad_norm": 21.52318000793457,
|
| 983 |
+
"learning_rate": 2.7265128719491812e-05,
|
| 984 |
+
"loss": 0.2706,
|
| 985 |
+
"step": 13600
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.29,
|
| 989 |
+
"grad_norm": 21.661279678344727,
|
| 990 |
+
"learning_rate": 2.70979605483116e-05,
|
| 991 |
+
"loss": 0.2715,
|
| 992 |
+
"step": 13700
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.31,
|
| 996 |
+
"grad_norm": 27.985078811645508,
|
| 997 |
+
"learning_rate": 2.69307923771314e-05,
|
| 998 |
+
"loss": 0.3016,
|
| 999 |
+
"step": 13800
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.32,
|
| 1003 |
+
"grad_norm": 11.431729316711426,
|
| 1004 |
+
"learning_rate": 2.6763624205951187e-05,
|
| 1005 |
+
"loss": 0.2501,
|
| 1006 |
+
"step": 13900
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.34,
|
| 1010 |
+
"grad_norm": 5.3406901359558105,
|
| 1011 |
+
"learning_rate": 2.6596456034770982e-05,
|
| 1012 |
+
"loss": 0.2762,
|
| 1013 |
+
"step": 14000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.36,
|
| 1017 |
+
"grad_norm": 11.077746391296387,
|
| 1018 |
+
"learning_rate": 2.6429287863590773e-05,
|
| 1019 |
+
"loss": 0.2819,
|
| 1020 |
+
"step": 14100
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.37,
|
| 1024 |
+
"grad_norm": 17.451330184936523,
|
| 1025 |
+
"learning_rate": 2.6262119692410565e-05,
|
| 1026 |
+
"loss": 0.3074,
|
| 1027 |
+
"step": 14200
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.39,
|
| 1031 |
+
"grad_norm": 7.353370189666748,
|
| 1032 |
+
"learning_rate": 2.609495152123036e-05,
|
| 1033 |
+
"loss": 0.3068,
|
| 1034 |
+
"step": 14300
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.41,
|
| 1038 |
+
"grad_norm": 12.055102348327637,
|
| 1039 |
+
"learning_rate": 2.592778335005015e-05,
|
| 1040 |
+
"loss": 0.2779,
|
| 1041 |
+
"step": 14400
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.42,
|
| 1045 |
+
"grad_norm": 17.555917739868164,
|
| 1046 |
+
"learning_rate": 2.5760615178869946e-05,
|
| 1047 |
+
"loss": 0.2421,
|
| 1048 |
+
"step": 14500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.44,
|
| 1052 |
+
"grad_norm": 22.887771606445312,
|
| 1053 |
+
"learning_rate": 2.5593447007689734e-05,
|
| 1054 |
+
"loss": 0.3016,
|
| 1055 |
+
"step": 14600
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.46,
|
| 1059 |
+
"grad_norm": 1.915899395942688,
|
| 1060 |
+
"learning_rate": 2.5426278836509533e-05,
|
| 1061 |
+
"loss": 0.2638,
|
| 1062 |
+
"step": 14700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.47,
|
| 1066 |
+
"grad_norm": 13.446496963500977,
|
| 1067 |
+
"learning_rate": 2.525911066532932e-05,
|
| 1068 |
+
"loss": 0.293,
|
| 1069 |
+
"step": 14800
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.49,
|
| 1073 |
+
"grad_norm": 12.734638214111328,
|
| 1074 |
+
"learning_rate": 2.509194249414912e-05,
|
| 1075 |
+
"loss": 0.2668,
|
| 1076 |
+
"step": 14900
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.51,
|
| 1080 |
+
"grad_norm": 15.557112693786621,
|
| 1081 |
+
"learning_rate": 2.4924774322968907e-05,
|
| 1082 |
+
"loss": 0.2691,
|
| 1083 |
+
"step": 15000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.52,
|
| 1087 |
+
"grad_norm": 10.383445739746094,
|
| 1088 |
+
"learning_rate": 2.4757606151788702e-05,
|
| 1089 |
+
"loss": 0.2204,
|
| 1090 |
+
"step": 15100
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.54,
|
| 1094 |
+
"grad_norm": 7.19666862487793,
|
| 1095 |
+
"learning_rate": 2.4590437980608493e-05,
|
| 1096 |
+
"loss": 0.2447,
|
| 1097 |
+
"step": 15200
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.56,
|
| 1101 |
+
"grad_norm": 17.903339385986328,
|
| 1102 |
+
"learning_rate": 2.442326980942829e-05,
|
| 1103 |
+
"loss": 0.2504,
|
| 1104 |
+
"step": 15300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.57,
|
| 1108 |
+
"grad_norm": 10.492616653442383,
|
| 1109 |
+
"learning_rate": 2.425610163824808e-05,
|
| 1110 |
+
"loss": 0.2256,
|
| 1111 |
+
"step": 15400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.59,
|
| 1115 |
+
"grad_norm": 11.051074028015137,
|
| 1116 |
+
"learning_rate": 2.408893346706787e-05,
|
| 1117 |
+
"loss": 0.259,
|
| 1118 |
+
"step": 15500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.61,
|
| 1122 |
+
"grad_norm": 23.400402069091797,
|
| 1123 |
+
"learning_rate": 2.3921765295887663e-05,
|
| 1124 |
+
"loss": 0.2487,
|
| 1125 |
+
"step": 15600
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.62,
|
| 1129 |
+
"grad_norm": 20.601686477661133,
|
| 1130 |
+
"learning_rate": 2.3754597124707458e-05,
|
| 1131 |
+
"loss": 0.2338,
|
| 1132 |
+
"step": 15700
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.64,
|
| 1136 |
+
"grad_norm": 12.519159317016602,
|
| 1137 |
+
"learning_rate": 2.358742895352725e-05,
|
| 1138 |
+
"loss": 0.2652,
|
| 1139 |
+
"step": 15800
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.66,
|
| 1143 |
+
"grad_norm": 21.95683479309082,
|
| 1144 |
+
"learning_rate": 2.342026078234704e-05,
|
| 1145 |
+
"loss": 0.2306,
|
| 1146 |
+
"step": 15900
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.67,
|
| 1150 |
+
"grad_norm": 24.98236656188965,
|
| 1151 |
+
"learning_rate": 2.3253092611166836e-05,
|
| 1152 |
+
"loss": 0.2475,
|
| 1153 |
+
"step": 16000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.69,
|
| 1157 |
+
"grad_norm": 6.362200736999512,
|
| 1158 |
+
"learning_rate": 2.3085924439986627e-05,
|
| 1159 |
+
"loss": 0.2646,
|
| 1160 |
+
"step": 16100
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.71,
|
| 1164 |
+
"grad_norm": 14.293391227722168,
|
| 1165 |
+
"learning_rate": 2.2918756268806422e-05,
|
| 1166 |
+
"loss": 0.2404,
|
| 1167 |
+
"step": 16200
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.72,
|
| 1171 |
+
"grad_norm": 11.405878067016602,
|
| 1172 |
+
"learning_rate": 2.2751588097626213e-05,
|
| 1173 |
+
"loss": 0.2651,
|
| 1174 |
+
"step": 16300
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.74,
|
| 1178 |
+
"grad_norm": 15.082180976867676,
|
| 1179 |
+
"learning_rate": 2.258441992644601e-05,
|
| 1180 |
+
"loss": 0.281,
|
| 1181 |
+
"step": 16400
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.76,
|
| 1185 |
+
"grad_norm": 27.33397674560547,
|
| 1186 |
+
"learning_rate": 2.2417251755265796e-05,
|
| 1187 |
+
"loss": 0.2492,
|
| 1188 |
+
"step": 16500
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.77,
|
| 1192 |
+
"grad_norm": 10.052102088928223,
|
| 1193 |
+
"learning_rate": 2.225008358408559e-05,
|
| 1194 |
+
"loss": 0.2382,
|
| 1195 |
+
"step": 16600
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.79,
|
| 1199 |
+
"grad_norm": 15.405964851379395,
|
| 1200 |
+
"learning_rate": 2.2082915412905383e-05,
|
| 1201 |
+
"loss": 0.2496,
|
| 1202 |
+
"step": 16700
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.81,
|
| 1206 |
+
"grad_norm": 7.162382125854492,
|
| 1207 |
+
"learning_rate": 2.1915747241725178e-05,
|
| 1208 |
+
"loss": 0.2343,
|
| 1209 |
+
"step": 16800
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.83,
|
| 1213 |
+
"grad_norm": 11.130888938903809,
|
| 1214 |
+
"learning_rate": 2.174857907054497e-05,
|
| 1215 |
+
"loss": 0.2474,
|
| 1216 |
+
"step": 16900
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.84,
|
| 1220 |
+
"grad_norm": 8.277360916137695,
|
| 1221 |
+
"learning_rate": 2.158141089936476e-05,
|
| 1222 |
+
"loss": 0.2687,
|
| 1223 |
+
"step": 17000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.86,
|
| 1227 |
+
"grad_norm": 31.100744247436523,
|
| 1228 |
+
"learning_rate": 2.1414242728184556e-05,
|
| 1229 |
+
"loss": 0.2422,
|
| 1230 |
+
"step": 17100
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.88,
|
| 1234 |
+
"grad_norm": 12.757442474365234,
|
| 1235 |
+
"learning_rate": 2.1247074557004347e-05,
|
| 1236 |
+
"loss": 0.2275,
|
| 1237 |
+
"step": 17200
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 2.89,
|
| 1241 |
+
"grad_norm": 4.860738277435303,
|
| 1242 |
+
"learning_rate": 2.1079906385824142e-05,
|
| 1243 |
+
"loss": 0.2252,
|
| 1244 |
+
"step": 17300
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.91,
|
| 1248 |
+
"grad_norm": 10.574835777282715,
|
| 1249 |
+
"learning_rate": 2.091273821464393e-05,
|
| 1250 |
+
"loss": 0.2114,
|
| 1251 |
+
"step": 17400
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.93,
|
| 1255 |
+
"grad_norm": 13.01117992401123,
|
| 1256 |
+
"learning_rate": 2.0745570043463725e-05,
|
| 1257 |
+
"loss": 0.2407,
|
| 1258 |
+
"step": 17500
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.94,
|
| 1262 |
+
"grad_norm": 4.970390319824219,
|
| 1263 |
+
"learning_rate": 2.0578401872283517e-05,
|
| 1264 |
+
"loss": 0.2509,
|
| 1265 |
+
"step": 17600
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.96,
|
| 1269 |
+
"grad_norm": 18.95350456237793,
|
| 1270 |
+
"learning_rate": 2.041123370110331e-05,
|
| 1271 |
+
"loss": 0.2814,
|
| 1272 |
+
"step": 17700
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.98,
|
| 1276 |
+
"grad_norm": 1.5296308994293213,
|
| 1277 |
+
"learning_rate": 2.0244065529923103e-05,
|
| 1278 |
+
"loss": 0.235,
|
| 1279 |
+
"step": 17800
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.99,
|
| 1283 |
+
"grad_norm": 12.501904487609863,
|
| 1284 |
+
"learning_rate": 2.0076897358742898e-05,
|
| 1285 |
+
"loss": 0.2479,
|
| 1286 |
+
"step": 17900
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.0,
|
| 1290 |
+
"eval_accuracy": 0.8965068087625814,
|
| 1291 |
+
"eval_f1": 0.8930257247589533,
|
| 1292 |
+
"eval_loss": 0.36622655391693115,
|
| 1293 |
+
"eval_precision": 0.8950199629292306,
|
| 1294 |
+
"eval_recall": 0.8965068087625814,
|
| 1295 |
+
"eval_runtime": 64.0862,
|
| 1296 |
+
"eval_samples_per_second": 131.776,
|
| 1297 |
+
"eval_steps_per_second": 8.239,
|
| 1298 |
+
"step": 17946
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.01,
|
| 1302 |
+
"grad_norm": 19.13836097717285,
|
| 1303 |
+
"learning_rate": 1.990972918756269e-05,
|
| 1304 |
+
"loss": 0.2272,
|
| 1305 |
+
"step": 18000
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.03,
|
| 1309 |
+
"grad_norm": 8.622084617614746,
|
| 1310 |
+
"learning_rate": 1.9742561016382484e-05,
|
| 1311 |
+
"loss": 0.131,
|
| 1312 |
+
"step": 18100
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 3.04,
|
| 1316 |
+
"grad_norm": 32.99411392211914,
|
| 1317 |
+
"learning_rate": 1.9575392845202276e-05,
|
| 1318 |
+
"loss": 0.1477,
|
| 1319 |
+
"step": 18200
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.06,
|
| 1323 |
+
"grad_norm": 5.467390060424805,
|
| 1324 |
+
"learning_rate": 1.9408224674022067e-05,
|
| 1325 |
+
"loss": 0.1439,
|
| 1326 |
+
"step": 18300
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.08,
|
| 1330 |
+
"grad_norm": 2.5153982639312744,
|
| 1331 |
+
"learning_rate": 1.924105650284186e-05,
|
| 1332 |
+
"loss": 0.1405,
|
| 1333 |
+
"step": 18400
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.09,
|
| 1337 |
+
"grad_norm": 20.424579620361328,
|
| 1338 |
+
"learning_rate": 1.907388833166165e-05,
|
| 1339 |
+
"loss": 0.1594,
|
| 1340 |
+
"step": 18500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.11,
|
| 1344 |
+
"grad_norm": 5.207544803619385,
|
| 1345 |
+
"learning_rate": 1.8906720160481445e-05,
|
| 1346 |
+
"loss": 0.1323,
|
| 1347 |
+
"step": 18600
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.13,
|
| 1351 |
+
"grad_norm": 8.750362396240234,
|
| 1352 |
+
"learning_rate": 1.8739551989301237e-05,
|
| 1353 |
+
"loss": 0.1683,
|
| 1354 |
+
"step": 18700
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.14,
|
| 1358 |
+
"grad_norm": 2.464329481124878,
|
| 1359 |
+
"learning_rate": 1.857238381812103e-05,
|
| 1360 |
+
"loss": 0.1388,
|
| 1361 |
+
"step": 18800
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.16,
|
| 1365 |
+
"grad_norm": 3.784031867980957,
|
| 1366 |
+
"learning_rate": 1.8405215646940823e-05,
|
| 1367 |
+
"loss": 0.149,
|
| 1368 |
+
"step": 18900
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.18,
|
| 1372 |
+
"grad_norm": 2.632542610168457,
|
| 1373 |
+
"learning_rate": 1.8238047475760618e-05,
|
| 1374 |
+
"loss": 0.1284,
|
| 1375 |
+
"step": 19000
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.19,
|
| 1379 |
+
"grad_norm": 11.050533294677734,
|
| 1380 |
+
"learning_rate": 1.807087930458041e-05,
|
| 1381 |
+
"loss": 0.1525,
|
| 1382 |
+
"step": 19100
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.21,
|
| 1386 |
+
"grad_norm": 7.363661766052246,
|
| 1387 |
+
"learning_rate": 1.7903711133400204e-05,
|
| 1388 |
+
"loss": 0.1481,
|
| 1389 |
+
"step": 19200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.23,
|
| 1393 |
+
"grad_norm": 9.882287979125977,
|
| 1394 |
+
"learning_rate": 1.7736542962219992e-05,
|
| 1395 |
+
"loss": 0.1231,
|
| 1396 |
+
"step": 19300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.24,
|
| 1400 |
+
"grad_norm": 24.93657684326172,
|
| 1401 |
+
"learning_rate": 1.7569374791039787e-05,
|
| 1402 |
+
"loss": 0.1332,
|
| 1403 |
+
"step": 19400
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.26,
|
| 1407 |
+
"grad_norm": 2.2802133560180664,
|
| 1408 |
+
"learning_rate": 1.740220661985958e-05,
|
| 1409 |
+
"loss": 0.1425,
|
| 1410 |
+
"step": 19500
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.28,
|
| 1414 |
+
"grad_norm": 1.5991661548614502,
|
| 1415 |
+
"learning_rate": 1.7235038448679374e-05,
|
| 1416 |
+
"loss": 0.1283,
|
| 1417 |
+
"step": 19600
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.29,
|
| 1421 |
+
"grad_norm": 8.344457626342773,
|
| 1422 |
+
"learning_rate": 1.7067870277499165e-05,
|
| 1423 |
+
"loss": 0.1502,
|
| 1424 |
+
"step": 19700
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.31,
|
| 1428 |
+
"grad_norm": 12.95904541015625,
|
| 1429 |
+
"learning_rate": 1.6900702106318957e-05,
|
| 1430 |
+
"loss": 0.1287,
|
| 1431 |
+
"step": 19800
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.33,
|
| 1435 |
+
"grad_norm": 20.562625885009766,
|
| 1436 |
+
"learning_rate": 1.673353393513875e-05,
|
| 1437 |
+
"loss": 0.1422,
|
| 1438 |
+
"step": 19900
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.34,
|
| 1442 |
+
"grad_norm": 4.20346736907959,
|
| 1443 |
+
"learning_rate": 1.6566365763958543e-05,
|
| 1444 |
+
"loss": 0.1082,
|
| 1445 |
+
"step": 20000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.36,
|
| 1449 |
+
"grad_norm": 25.636775970458984,
|
| 1450 |
+
"learning_rate": 1.6399197592778338e-05,
|
| 1451 |
+
"loss": 0.1416,
|
| 1452 |
+
"step": 20100
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.38,
|
| 1456 |
+
"grad_norm": 23.23301887512207,
|
| 1457 |
+
"learning_rate": 1.6232029421598126e-05,
|
| 1458 |
+
"loss": 0.1497,
|
| 1459 |
+
"step": 20200
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.39,
|
| 1463 |
+
"grad_norm": 22.21303939819336,
|
| 1464 |
+
"learning_rate": 1.606486125041792e-05,
|
| 1465 |
+
"loss": 0.1568,
|
| 1466 |
+
"step": 20300
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.41,
|
| 1470 |
+
"grad_norm": 21.14128303527832,
|
| 1471 |
+
"learning_rate": 1.5897693079237712e-05,
|
| 1472 |
+
"loss": 0.139,
|
| 1473 |
+
"step": 20400
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.43,
|
| 1477 |
+
"grad_norm": 22.63404083251953,
|
| 1478 |
+
"learning_rate": 1.5730524908057507e-05,
|
| 1479 |
+
"loss": 0.1518,
|
| 1480 |
+
"step": 20500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.44,
|
| 1484 |
+
"grad_norm": 13.030010223388672,
|
| 1485 |
+
"learning_rate": 1.55633567368773e-05,
|
| 1486 |
+
"loss": 0.1319,
|
| 1487 |
+
"step": 20600
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.46,
|
| 1491 |
+
"grad_norm": 18.308670043945312,
|
| 1492 |
+
"learning_rate": 1.5396188565697094e-05,
|
| 1493 |
+
"loss": 0.1494,
|
| 1494 |
+
"step": 20700
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.48,
|
| 1498 |
+
"grad_norm": 24.907419204711914,
|
| 1499 |
+
"learning_rate": 1.5229020394516885e-05,
|
| 1500 |
+
"loss": 0.1425,
|
| 1501 |
+
"step": 20800
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.49,
|
| 1505 |
+
"grad_norm": 19.32282066345215,
|
| 1506 |
+
"learning_rate": 1.5061852223336678e-05,
|
| 1507 |
+
"loss": 0.1264,
|
| 1508 |
+
"step": 20900
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 3.51,
|
| 1512 |
+
"grad_norm": 17.444271087646484,
|
| 1513 |
+
"learning_rate": 1.4894684052156472e-05,
|
| 1514 |
+
"loss": 0.14,
|
| 1515 |
+
"step": 21000
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.53,
|
| 1519 |
+
"grad_norm": 1.832461953163147,
|
| 1520 |
+
"learning_rate": 1.4727515880976261e-05,
|
| 1521 |
+
"loss": 0.1438,
|
| 1522 |
+
"step": 21100
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 3.54,
|
| 1526 |
+
"grad_norm": 10.410861015319824,
|
| 1527 |
+
"learning_rate": 1.4560347709796055e-05,
|
| 1528 |
+
"loss": 0.1393,
|
| 1529 |
+
"step": 21200
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.56,
|
| 1533 |
+
"grad_norm": 3.6459202766418457,
|
| 1534 |
+
"learning_rate": 1.4393179538615848e-05,
|
| 1535 |
+
"loss": 0.1077,
|
| 1536 |
+
"step": 21300
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 3.58,
|
| 1540 |
+
"grad_norm": 3.216399669647217,
|
| 1541 |
+
"learning_rate": 1.4226011367435641e-05,
|
| 1542 |
+
"loss": 0.1154,
|
| 1543 |
+
"step": 21400
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 3.59,
|
| 1547 |
+
"grad_norm": 5.621729373931885,
|
| 1548 |
+
"learning_rate": 1.4058843196255434e-05,
|
| 1549 |
+
"loss": 0.1208,
|
| 1550 |
+
"step": 21500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.61,
|
| 1554 |
+
"grad_norm": 5.559453010559082,
|
| 1555 |
+
"learning_rate": 1.3891675025075226e-05,
|
| 1556 |
+
"loss": 0.1441,
|
| 1557 |
+
"step": 21600
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.63,
|
| 1561 |
+
"grad_norm": 22.32745933532715,
|
| 1562 |
+
"learning_rate": 1.3724506853895019e-05,
|
| 1563 |
+
"loss": 0.1176,
|
| 1564 |
+
"step": 21700
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 3.64,
|
| 1568 |
+
"grad_norm": 4.509443759918213,
|
| 1569 |
+
"learning_rate": 1.3557338682714812e-05,
|
| 1570 |
+
"loss": 0.1382,
|
| 1571 |
+
"step": 21800
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.66,
|
| 1575 |
+
"grad_norm": 15.154895782470703,
|
| 1576 |
+
"learning_rate": 1.3390170511534605e-05,
|
| 1577 |
+
"loss": 0.1475,
|
| 1578 |
+
"step": 21900
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.68,
|
| 1582 |
+
"grad_norm": 0.8804099559783936,
|
| 1583 |
+
"learning_rate": 1.3223002340354398e-05,
|
| 1584 |
+
"loss": 0.1325,
|
| 1585 |
+
"step": 22000
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.69,
|
| 1589 |
+
"grad_norm": 1.9917913675308228,
|
| 1590 |
+
"learning_rate": 1.3055834169174188e-05,
|
| 1591 |
+
"loss": 0.1255,
|
| 1592 |
+
"step": 22100
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 3.71,
|
| 1596 |
+
"grad_norm": 16.314374923706055,
|
| 1597 |
+
"learning_rate": 1.2888665997993981e-05,
|
| 1598 |
+
"loss": 0.1275,
|
| 1599 |
+
"step": 22200
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.73,
|
| 1603 |
+
"grad_norm": 5.355242729187012,
|
| 1604 |
+
"learning_rate": 1.2721497826813775e-05,
|
| 1605 |
+
"loss": 0.1185,
|
| 1606 |
+
"step": 22300
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 3.74,
|
| 1610 |
+
"grad_norm": 20.218473434448242,
|
| 1611 |
+
"learning_rate": 1.2554329655633568e-05,
|
| 1612 |
+
"loss": 0.1203,
|
| 1613 |
+
"step": 22400
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.76,
|
| 1617 |
+
"grad_norm": 1.39955735206604,
|
| 1618 |
+
"learning_rate": 1.2387161484453361e-05,
|
| 1619 |
+
"loss": 0.1636,
|
| 1620 |
+
"step": 22500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.78,
|
| 1624 |
+
"grad_norm": 17.855899810791016,
|
| 1625 |
+
"learning_rate": 1.2219993313273154e-05,
|
| 1626 |
+
"loss": 0.1369,
|
| 1627 |
+
"step": 22600
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.79,
|
| 1631 |
+
"grad_norm": 14.41054630279541,
|
| 1632 |
+
"learning_rate": 1.2052825142092947e-05,
|
| 1633 |
+
"loss": 0.1245,
|
| 1634 |
+
"step": 22700
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 3.81,
|
| 1638 |
+
"grad_norm": 11.451350212097168,
|
| 1639 |
+
"learning_rate": 1.1885656970912739e-05,
|
| 1640 |
+
"loss": 0.1508,
|
| 1641 |
+
"step": 22800
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.83,
|
| 1645 |
+
"grad_norm": 9.41112995147705,
|
| 1646 |
+
"learning_rate": 1.171848879973253e-05,
|
| 1647 |
+
"loss": 0.125,
|
| 1648 |
+
"step": 22900
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.84,
|
| 1652 |
+
"grad_norm": 29.826963424682617,
|
| 1653 |
+
"learning_rate": 1.1551320628552324e-05,
|
| 1654 |
+
"loss": 0.1545,
|
| 1655 |
+
"step": 23000
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.86,
|
| 1659 |
+
"grad_norm": 11.454690933227539,
|
| 1660 |
+
"learning_rate": 1.1384152457372117e-05,
|
| 1661 |
+
"loss": 0.1353,
|
| 1662 |
+
"step": 23100
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 3.88,
|
| 1666 |
+
"grad_norm": 12.364923477172852,
|
| 1667 |
+
"learning_rate": 1.121698428619191e-05,
|
| 1668 |
+
"loss": 0.1346,
|
| 1669 |
+
"step": 23200
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 3.9,
|
| 1673 |
+
"grad_norm": 1.8181456327438354,
|
| 1674 |
+
"learning_rate": 1.1049816115011702e-05,
|
| 1675 |
+
"loss": 0.1092,
|
| 1676 |
+
"step": 23300
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.91,
|
| 1680 |
+
"grad_norm": 30.87436866760254,
|
| 1681 |
+
"learning_rate": 1.0882647943831495e-05,
|
| 1682 |
+
"loss": 0.1059,
|
| 1683 |
+
"step": 23400
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.93,
|
| 1687 |
+
"grad_norm": 16.423452377319336,
|
| 1688 |
+
"learning_rate": 1.0715479772651288e-05,
|
| 1689 |
+
"loss": 0.1157,
|
| 1690 |
+
"step": 23500
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.95,
|
| 1694 |
+
"grad_norm": 27.86665153503418,
|
| 1695 |
+
"learning_rate": 1.0548311601471081e-05,
|
| 1696 |
+
"loss": 0.1317,
|
| 1697 |
+
"step": 23600
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.96,
|
| 1701 |
+
"grad_norm": 24.479764938354492,
|
| 1702 |
+
"learning_rate": 1.0381143430290873e-05,
|
| 1703 |
+
"loss": 0.1184,
|
| 1704 |
+
"step": 23700
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.98,
|
| 1708 |
+
"grad_norm": 1.4079170227050781,
|
| 1709 |
+
"learning_rate": 1.0213975259110666e-05,
|
| 1710 |
+
"loss": 0.1303,
|
| 1711 |
+
"step": 23800
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 4.0,
|
| 1715 |
+
"grad_norm": 4.259897232055664,
|
| 1716 |
+
"learning_rate": 1.0046807087930459e-05,
|
| 1717 |
+
"loss": 0.1322,
|
| 1718 |
+
"step": 23900
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 4.0,
|
| 1722 |
+
"eval_accuracy": 0.9113084665482534,
|
| 1723 |
+
"eval_f1": 0.9092055511030135,
|
| 1724 |
+
"eval_loss": 0.3260073661804199,
|
| 1725 |
+
"eval_precision": 0.9099757491171729,
|
| 1726 |
+
"eval_recall": 0.9113084665482534,
|
| 1727 |
+
"eval_runtime": 64.1166,
|
| 1728 |
+
"eval_samples_per_second": 131.713,
|
| 1729 |
+
"eval_steps_per_second": 8.235,
|
| 1730 |
+
"step": 23928
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 4.01,
|
| 1734 |
+
"grad_norm": 13.925552368164062,
|
| 1735 |
+
"learning_rate": 9.879638916750252e-06,
|
| 1736 |
+
"loss": 0.0687,
|
| 1737 |
+
"step": 24000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 4.03,
|
| 1741 |
+
"grad_norm": 0.18495211005210876,
|
| 1742 |
+
"learning_rate": 9.712470745570044e-06,
|
| 1743 |
+
"loss": 0.066,
|
| 1744 |
+
"step": 24100
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 4.05,
|
| 1748 |
+
"grad_norm": 1.0808857679367065,
|
| 1749 |
+
"learning_rate": 9.545302574389837e-06,
|
| 1750 |
+
"loss": 0.0648,
|
| 1751 |
+
"step": 24200
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 4.06,
|
| 1755 |
+
"grad_norm": 1.0073552131652832,
|
| 1756 |
+
"learning_rate": 9.378134403209628e-06,
|
| 1757 |
+
"loss": 0.071,
|
| 1758 |
+
"step": 24300
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 4.08,
|
| 1762 |
+
"grad_norm": 15.166232109069824,
|
| 1763 |
+
"learning_rate": 9.210966232029422e-06,
|
| 1764 |
+
"loss": 0.0666,
|
| 1765 |
+
"step": 24400
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 4.1,
|
| 1769 |
+
"grad_norm": 18.000640869140625,
|
| 1770 |
+
"learning_rate": 9.043798060849215e-06,
|
| 1771 |
+
"loss": 0.0778,
|
| 1772 |
+
"step": 24500
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 4.11,
|
| 1776 |
+
"grad_norm": 1.214728593826294,
|
| 1777 |
+
"learning_rate": 8.876629889669008e-06,
|
| 1778 |
+
"loss": 0.07,
|
| 1779 |
+
"step": 24600
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 4.13,
|
| 1783 |
+
"grad_norm": 1.982407808303833,
|
| 1784 |
+
"learning_rate": 8.7094617184888e-06,
|
| 1785 |
+
"loss": 0.0752,
|
| 1786 |
+
"step": 24700
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 4.15,
|
| 1790 |
+
"grad_norm": 20.929153442382812,
|
| 1791 |
+
"learning_rate": 8.542293547308593e-06,
|
| 1792 |
+
"loss": 0.0785,
|
| 1793 |
+
"step": 24800
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 4.16,
|
| 1797 |
+
"grad_norm": 0.8963820934295654,
|
| 1798 |
+
"learning_rate": 8.375125376128386e-06,
|
| 1799 |
+
"loss": 0.0524,
|
| 1800 |
+
"step": 24900
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 4.18,
|
| 1804 |
+
"grad_norm": 3.5774483680725098,
|
| 1805 |
+
"learning_rate": 8.207957204948179e-06,
|
| 1806 |
+
"loss": 0.0692,
|
| 1807 |
+
"step": 25000
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 4.2,
|
| 1811 |
+
"grad_norm": 3.7253074645996094,
|
| 1812 |
+
"learning_rate": 8.04078903376797e-06,
|
| 1813 |
+
"loss": 0.0641,
|
| 1814 |
+
"step": 25100
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 4.21,
|
| 1818 |
+
"grad_norm": 1.2855291366577148,
|
| 1819 |
+
"learning_rate": 7.873620862587764e-06,
|
| 1820 |
+
"loss": 0.0699,
|
| 1821 |
+
"step": 25200
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 4.23,
|
| 1825 |
+
"grad_norm": 1.9972455501556396,
|
| 1826 |
+
"learning_rate": 7.706452691407557e-06,
|
| 1827 |
+
"loss": 0.062,
|
| 1828 |
+
"step": 25300
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 4.25,
|
| 1832 |
+
"grad_norm": 1.0809322595596313,
|
| 1833 |
+
"learning_rate": 7.539284520227349e-06,
|
| 1834 |
+
"loss": 0.058,
|
| 1835 |
+
"step": 25400
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 4.26,
|
| 1839 |
+
"grad_norm": 3.876232862472534,
|
| 1840 |
+
"learning_rate": 7.3721163490471425e-06,
|
| 1841 |
+
"loss": 0.0693,
|
| 1842 |
+
"step": 25500
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 4.28,
|
| 1846 |
+
"grad_norm": 6.069151878356934,
|
| 1847 |
+
"learning_rate": 7.204948177866934e-06,
|
| 1848 |
+
"loss": 0.0617,
|
| 1849 |
+
"step": 25600
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 4.3,
|
| 1853 |
+
"grad_norm": 0.895815372467041,
|
| 1854 |
+
"learning_rate": 7.037780006686727e-06,
|
| 1855 |
+
"loss": 0.0623,
|
| 1856 |
+
"step": 25700
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 4.31,
|
| 1860 |
+
"grad_norm": 0.4176822602748871,
|
| 1861 |
+
"learning_rate": 6.8706118355065195e-06,
|
| 1862 |
+
"loss": 0.0833,
|
| 1863 |
+
"step": 25800
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 4.33,
|
| 1867 |
+
"grad_norm": 0.6760619878768921,
|
| 1868 |
+
"learning_rate": 6.703443664326313e-06,
|
| 1869 |
+
"loss": 0.0567,
|
| 1870 |
+
"step": 25900
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 4.35,
|
| 1874 |
+
"grad_norm": 14.889734268188477,
|
| 1875 |
+
"learning_rate": 6.536275493146106e-06,
|
| 1876 |
+
"loss": 0.053,
|
| 1877 |
+
"step": 26000
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 4.36,
|
| 1881 |
+
"grad_norm": 0.5385121703147888,
|
| 1882 |
+
"learning_rate": 6.369107321965897e-06,
|
| 1883 |
+
"loss": 0.0703,
|
| 1884 |
+
"step": 26100
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 4.38,
|
| 1888 |
+
"grad_norm": 6.336006164550781,
|
| 1889 |
+
"learning_rate": 6.201939150785691e-06,
|
| 1890 |
+
"loss": 0.063,
|
| 1891 |
+
"step": 26200
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 4.4,
|
| 1895 |
+
"grad_norm": 0.20758749544620514,
|
| 1896 |
+
"learning_rate": 6.034770979605484e-06,
|
| 1897 |
+
"loss": 0.0753,
|
| 1898 |
+
"step": 26300
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 4.41,
|
| 1902 |
+
"grad_norm": 11.717066764831543,
|
| 1903 |
+
"learning_rate": 5.867602808425276e-06,
|
| 1904 |
+
"loss": 0.0598,
|
| 1905 |
+
"step": 26400
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 4.43,
|
| 1909 |
+
"grad_norm": 26.475128173828125,
|
| 1910 |
+
"learning_rate": 5.7004346372450685e-06,
|
| 1911 |
+
"loss": 0.064,
|
| 1912 |
+
"step": 26500
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 4.45,
|
| 1916 |
+
"grad_norm": 20.872194290161133,
|
| 1917 |
+
"learning_rate": 5.533266466064862e-06,
|
| 1918 |
+
"loss": 0.0708,
|
| 1919 |
+
"step": 26600
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 4.46,
|
| 1923 |
+
"grad_norm": 1.2749828100204468,
|
| 1924 |
+
"learning_rate": 5.366098294884654e-06,
|
| 1925 |
+
"loss": 0.0705,
|
| 1926 |
+
"step": 26700
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 4.48,
|
| 1930 |
+
"grad_norm": 6.7912702560424805,
|
| 1931 |
+
"learning_rate": 5.198930123704447e-06,
|
| 1932 |
+
"loss": 0.0742,
|
| 1933 |
+
"step": 26800
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 4.5,
|
| 1937 |
+
"grad_norm": 10.904654502868652,
|
| 1938 |
+
"learning_rate": 5.03176195252424e-06,
|
| 1939 |
+
"loss": 0.0665,
|
| 1940 |
+
"step": 26900
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 4.51,
|
| 1944 |
+
"grad_norm": 6.191511154174805,
|
| 1945 |
+
"learning_rate": 4.864593781344033e-06,
|
| 1946 |
+
"loss": 0.0549,
|
| 1947 |
+
"step": 27000
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 4.53,
|
| 1951 |
+
"grad_norm": 2.479524850845337,
|
| 1952 |
+
"learning_rate": 4.697425610163825e-06,
|
| 1953 |
+
"loss": 0.0539,
|
| 1954 |
+
"step": 27100
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 4.55,
|
| 1958 |
+
"grad_norm": 0.7285805940628052,
|
| 1959 |
+
"learning_rate": 4.5302574389836175e-06,
|
| 1960 |
+
"loss": 0.0662,
|
| 1961 |
+
"step": 27200
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 4.56,
|
| 1965 |
+
"grad_norm": 4.313304901123047,
|
| 1966 |
+
"learning_rate": 4.363089267803411e-06,
|
| 1967 |
+
"loss": 0.0571,
|
| 1968 |
+
"step": 27300
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 4.58,
|
| 1972 |
+
"grad_norm": 17.61699867248535,
|
| 1973 |
+
"learning_rate": 4.195921096623203e-06,
|
| 1974 |
+
"loss": 0.0634,
|
| 1975 |
+
"step": 27400
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 4.6,
|
| 1979 |
+
"grad_norm": 1.3776081800460815,
|
| 1980 |
+
"learning_rate": 4.028752925442996e-06,
|
| 1981 |
+
"loss": 0.0526,
|
| 1982 |
+
"step": 27500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 4.61,
|
| 1986 |
+
"grad_norm": 0.36369597911834717,
|
| 1987 |
+
"learning_rate": 3.8615847542627886e-06,
|
| 1988 |
+
"loss": 0.0669,
|
| 1989 |
+
"step": 27600
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 4.63,
|
| 1993 |
+
"grad_norm": 4.591643333435059,
|
| 1994 |
+
"learning_rate": 3.6944165830825813e-06,
|
| 1995 |
+
"loss": 0.0578,
|
| 1996 |
+
"step": 27700
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 4.65,
|
| 2000 |
+
"grad_norm": 0.930225670337677,
|
| 2001 |
+
"learning_rate": 3.5272484119023737e-06,
|
| 2002 |
+
"loss": 0.0456,
|
| 2003 |
+
"step": 27800
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 4.66,
|
| 2007 |
+
"grad_norm": 1.136043906211853,
|
| 2008 |
+
"learning_rate": 3.360080240722167e-06,
|
| 2009 |
+
"loss": 0.0617,
|
| 2010 |
+
"step": 27900
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 4.68,
|
| 2014 |
+
"grad_norm": 0.6426201462745667,
|
| 2015 |
+
"learning_rate": 3.1929120695419596e-06,
|
| 2016 |
+
"loss": 0.0568,
|
| 2017 |
+
"step": 28000
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 4.7,
|
| 2021 |
+
"grad_norm": 2.6884241104125977,
|
| 2022 |
+
"learning_rate": 3.025743898361752e-06,
|
| 2023 |
+
"loss": 0.0606,
|
| 2024 |
+
"step": 28100
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 4.71,
|
| 2028 |
+
"grad_norm": 0.4525424838066101,
|
| 2029 |
+
"learning_rate": 2.8585757271815448e-06,
|
| 2030 |
+
"loss": 0.066,
|
| 2031 |
+
"step": 28200
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 4.73,
|
| 2035 |
+
"grad_norm": 1.0276681184768677,
|
| 2036 |
+
"learning_rate": 2.6914075560013375e-06,
|
| 2037 |
+
"loss": 0.0444,
|
| 2038 |
+
"step": 28300
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 4.75,
|
| 2042 |
+
"grad_norm": 7.886939525604248,
|
| 2043 |
+
"learning_rate": 2.5242393848211303e-06,
|
| 2044 |
+
"loss": 0.065,
|
| 2045 |
+
"step": 28400
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 4.76,
|
| 2049 |
+
"grad_norm": 0.37203583121299744,
|
| 2050 |
+
"learning_rate": 2.357071213640923e-06,
|
| 2051 |
+
"loss": 0.0559,
|
| 2052 |
+
"step": 28500
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 4.78,
|
| 2056 |
+
"grad_norm": 6.219501495361328,
|
| 2057 |
+
"learning_rate": 2.1899030424607154e-06,
|
| 2058 |
+
"loss": 0.07,
|
| 2059 |
+
"step": 28600
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 4.8,
|
| 2063 |
+
"grad_norm": 8.10631275177002,
|
| 2064 |
+
"learning_rate": 2.022734871280508e-06,
|
| 2065 |
+
"loss": 0.0623,
|
| 2066 |
+
"step": 28700
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 4.81,
|
| 2070 |
+
"grad_norm": 24.999059677124023,
|
| 2071 |
+
"learning_rate": 1.855566700100301e-06,
|
| 2072 |
+
"loss": 0.0701,
|
| 2073 |
+
"step": 28800
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 4.83,
|
| 2077 |
+
"grad_norm": 3.5445597171783447,
|
| 2078 |
+
"learning_rate": 1.6883985289200935e-06,
|
| 2079 |
+
"loss": 0.0561,
|
| 2080 |
+
"step": 28900
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 4.85,
|
| 2084 |
+
"grad_norm": 11.693018913269043,
|
| 2085 |
+
"learning_rate": 1.5212303577398863e-06,
|
| 2086 |
+
"loss": 0.062,
|
| 2087 |
+
"step": 29000
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 4.86,
|
| 2091 |
+
"grad_norm": 17.059640884399414,
|
| 2092 |
+
"learning_rate": 1.354062186559679e-06,
|
| 2093 |
+
"loss": 0.0663,
|
| 2094 |
+
"step": 29100
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 4.88,
|
| 2098 |
+
"grad_norm": 3.2128794193267822,
|
| 2099 |
+
"learning_rate": 1.1868940153794718e-06,
|
| 2100 |
+
"loss": 0.0541,
|
| 2101 |
+
"step": 29200
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 4.9,
|
| 2105 |
+
"grad_norm": 1.6803439855575562,
|
| 2106 |
+
"learning_rate": 1.0197258441992646e-06,
|
| 2107 |
+
"loss": 0.0619,
|
| 2108 |
+
"step": 29300
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 4.91,
|
| 2112 |
+
"grad_norm": 7.980160236358643,
|
| 2113 |
+
"learning_rate": 8.525576730190572e-07,
|
| 2114 |
+
"loss": 0.0649,
|
| 2115 |
+
"step": 29400
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 4.93,
|
| 2119 |
+
"grad_norm": 0.3919593393802643,
|
| 2120 |
+
"learning_rate": 6.853895018388499e-07,
|
| 2121 |
+
"loss": 0.0753,
|
| 2122 |
+
"step": 29500
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 4.95,
|
| 2126 |
+
"grad_norm": 2.870180368423462,
|
| 2127 |
+
"learning_rate": 5.182213306586426e-07,
|
| 2128 |
+
"loss": 0.0461,
|
| 2129 |
+
"step": 29600
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 4.96,
|
| 2133 |
+
"grad_norm": 0.5204899907112122,
|
| 2134 |
+
"learning_rate": 3.510531594784353e-07,
|
| 2135 |
+
"loss": 0.0446,
|
| 2136 |
+
"step": 29700
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 4.98,
|
| 2140 |
+
"grad_norm": 2.318403482437134,
|
| 2141 |
+
"learning_rate": 1.8388498829822804e-07,
|
| 2142 |
+
"loss": 0.0588,
|
| 2143 |
+
"step": 29800
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 5.0,
|
| 2147 |
+
"grad_norm": 1.1591626405715942,
|
| 2148 |
+
"learning_rate": 1.6716817118020728e-08,
|
| 2149 |
+
"loss": 0.0589,
|
| 2150 |
+
"step": 29900
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 5.0,
|
| 2154 |
+
"eval_accuracy": 0.9182948490230906,
|
| 2155 |
+
"eval_f1": 0.9165254517429693,
|
| 2156 |
+
"eval_loss": 0.3342040479183197,
|
| 2157 |
+
"eval_precision": 0.9170562701684628,
|
| 2158 |
+
"eval_recall": 0.9182948490230906,
|
| 2159 |
+
"eval_runtime": 63.9141,
|
| 2160 |
+
"eval_samples_per_second": 132.131,
|
| 2161 |
+
"eval_steps_per_second": 8.261,
|
| 2162 |
+
"step": 29910
|
| 2163 |
+
}
|
| 2164 |
+
],
|
| 2165 |
+
"logging_steps": 100,
|
| 2166 |
+
"max_steps": 29910,
|
| 2167 |
+
"num_input_tokens_seen": 0,
|
| 2168 |
+
"num_train_epochs": 5,
|
| 2169 |
+
"save_steps": 500,
|
| 2170 |
+
"total_flos": 1.15579279766016e+16,
|
| 2171 |
+
"train_batch_size": 16,
|
| 2172 |
+
"trial_name": null,
|
| 2173 |
+
"trial_params": null
|
| 2174 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bdc897def407dfe2e4318176425168f13f8e1110eb62832d0ba83b7723ba91d
|
| 3 |
+
size 4856
|