DuongTrongChi
commited on
Commit
•
54798b2
1
Parent(s):
a197ac0
Training in progress, step 361, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8095535d287a5363ea56d6e1a990b793651e0842f91f0e62b2cde7ad796e3c97
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:165bc7411b625ca298d13e3c88f8745dc09872293291b602919d21265ad0ba3b
|
3 |
size 50675604
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84cd725a97db95f8de6db3eaffde1002a056efc831c1635a52e2a74854a937e4
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2037,6 +2037,503 @@
|
|
2037 |
"learning_rate": 1.3493150684931508e-05,
|
2038 |
"loss": 1.1981,
|
2039 |
"step": 290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2040 |
}
|
2041 |
],
|
2042 |
"logging_steps": 1,
|
@@ -2056,7 +2553,7 @@
|
|
2056 |
"attributes": {}
|
2057 |
}
|
2058 |
},
|
2059 |
-
"total_flos":
|
2060 |
"train_batch_size": 4,
|
2061 |
"trial_name": null,
|
2062 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5274404164003287,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 361,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2037 |
"learning_rate": 1.3493150684931508e-05,
|
2038 |
"loss": 1.1981,
|
2039 |
"step": 290
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.4251666514473564,
|
2043 |
+
"grad_norm": 0.09126268327236176,
|
2044 |
+
"learning_rate": 1.3458904109589042e-05,
|
2045 |
+
"loss": 1.2296,
|
2046 |
+
"step": 291
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.42662770523239885,
|
2050 |
+
"grad_norm": 0.09404008835554123,
|
2051 |
+
"learning_rate": 1.3424657534246576e-05,
|
2052 |
+
"loss": 1.3013,
|
2053 |
+
"step": 292
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.4280887590174413,
|
2057 |
+
"grad_norm": 0.09837393462657928,
|
2058 |
+
"learning_rate": 1.339041095890411e-05,
|
2059 |
+
"loss": 1.2102,
|
2060 |
+
"step": 293
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.4295498128024838,
|
2064 |
+
"grad_norm": 0.0978068932890892,
|
2065 |
+
"learning_rate": 1.3356164383561646e-05,
|
2066 |
+
"loss": 1.1995,
|
2067 |
+
"step": 294
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.43101086658752624,
|
2071 |
+
"grad_norm": 0.09333440661430359,
|
2072 |
+
"learning_rate": 1.332191780821918e-05,
|
2073 |
+
"loss": 1.2284,
|
2074 |
+
"step": 295
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.4324719203725687,
|
2078 |
+
"grad_norm": 0.10575850307941437,
|
2079 |
+
"learning_rate": 1.3287671232876714e-05,
|
2080 |
+
"loss": 1.1442,
|
2081 |
+
"step": 296
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.4339329741576112,
|
2085 |
+
"grad_norm": 0.10079637169837952,
|
2086 |
+
"learning_rate": 1.3253424657534248e-05,
|
2087 |
+
"loss": 1.2114,
|
2088 |
+
"step": 297
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.43539402794265364,
|
2092 |
+
"grad_norm": 0.10534002631902695,
|
2093 |
+
"learning_rate": 1.3219178082191781e-05,
|
2094 |
+
"loss": 1.1894,
|
2095 |
+
"step": 298
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.4368550817276961,
|
2099 |
+
"grad_norm": 0.09364209324121475,
|
2100 |
+
"learning_rate": 1.3184931506849316e-05,
|
2101 |
+
"loss": 1.1565,
|
2102 |
+
"step": 299
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.43831613551273857,
|
2106 |
+
"grad_norm": 0.09970992058515549,
|
2107 |
+
"learning_rate": 1.3150684931506849e-05,
|
2108 |
+
"loss": 1.234,
|
2109 |
+
"step": 300
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.43977718929778103,
|
2113 |
+
"grad_norm": 0.10115770250558853,
|
2114 |
+
"learning_rate": 1.3116438356164385e-05,
|
2115 |
+
"loss": 1.2113,
|
2116 |
+
"step": 301
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.4412382430828235,
|
2120 |
+
"grad_norm": 0.10583057254552841,
|
2121 |
+
"learning_rate": 1.3082191780821919e-05,
|
2122 |
+
"loss": 1.1469,
|
2123 |
+
"step": 302
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.44269929686786597,
|
2127 |
+
"grad_norm": 0.10508885979652405,
|
2128 |
+
"learning_rate": 1.3047945205479453e-05,
|
2129 |
+
"loss": 1.1648,
|
2130 |
+
"step": 303
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.44416035065290843,
|
2134 |
+
"grad_norm": 0.09814278036355972,
|
2135 |
+
"learning_rate": 1.3013698630136988e-05,
|
2136 |
+
"loss": 1.1365,
|
2137 |
+
"step": 304
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.4456214044379509,
|
2141 |
+
"grad_norm": 0.0985088050365448,
|
2142 |
+
"learning_rate": 1.2979452054794521e-05,
|
2143 |
+
"loss": 1.2589,
|
2144 |
+
"step": 305
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.4470824582229933,
|
2148 |
+
"grad_norm": 0.10917991399765015,
|
2149 |
+
"learning_rate": 1.2945205479452056e-05,
|
2150 |
+
"loss": 1.2256,
|
2151 |
+
"step": 306
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.44854351200803577,
|
2155 |
+
"grad_norm": 0.10406248271465302,
|
2156 |
+
"learning_rate": 1.2910958904109589e-05,
|
2157 |
+
"loss": 1.2597,
|
2158 |
+
"step": 307
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.45000456579307824,
|
2162 |
+
"grad_norm": 0.09909600764513016,
|
2163 |
+
"learning_rate": 1.2876712328767125e-05,
|
2164 |
+
"loss": 1.2125,
|
2165 |
+
"step": 308
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.4514656195781207,
|
2169 |
+
"grad_norm": 0.10518831014633179,
|
2170 |
+
"learning_rate": 1.2842465753424658e-05,
|
2171 |
+
"loss": 1.1912,
|
2172 |
+
"step": 309
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.45292667336316317,
|
2176 |
+
"grad_norm": 0.09970947355031967,
|
2177 |
+
"learning_rate": 1.2808219178082193e-05,
|
2178 |
+
"loss": 1.207,
|
2179 |
+
"step": 310
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.45438772714820563,
|
2183 |
+
"grad_norm": 0.10252334922552109,
|
2184 |
+
"learning_rate": 1.2773972602739728e-05,
|
2185 |
+
"loss": 1.2133,
|
2186 |
+
"step": 311
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.4558487809332481,
|
2190 |
+
"grad_norm": 0.10719390958547592,
|
2191 |
+
"learning_rate": 1.273972602739726e-05,
|
2192 |
+
"loss": 1.146,
|
2193 |
+
"step": 312
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.45730983471829056,
|
2197 |
+
"grad_norm": 0.11196637153625488,
|
2198 |
+
"learning_rate": 1.2705479452054796e-05,
|
2199 |
+
"loss": 1.2922,
|
2200 |
+
"step": 313
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.45877088850333303,
|
2204 |
+
"grad_norm": 0.11517077684402466,
|
2205 |
+
"learning_rate": 1.2671232876712329e-05,
|
2206 |
+
"loss": 1.2577,
|
2207 |
+
"step": 314
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.4602319422883755,
|
2211 |
+
"grad_norm": 0.09453711658716202,
|
2212 |
+
"learning_rate": 1.2636986301369865e-05,
|
2213 |
+
"loss": 1.3212,
|
2214 |
+
"step": 315
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.46169299607341796,
|
2218 |
+
"grad_norm": 0.1068459153175354,
|
2219 |
+
"learning_rate": 1.2602739726027398e-05,
|
2220 |
+
"loss": 1.1981,
|
2221 |
+
"step": 316
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.4631540498584604,
|
2225 |
+
"grad_norm": 0.0985800251364708,
|
2226 |
+
"learning_rate": 1.2568493150684933e-05,
|
2227 |
+
"loss": 1.189,
|
2228 |
+
"step": 317
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.4646151036435029,
|
2232 |
+
"grad_norm": 0.10522795468568802,
|
2233 |
+
"learning_rate": 1.2534246575342466e-05,
|
2234 |
+
"loss": 1.2341,
|
2235 |
+
"step": 318
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.46607615742854536,
|
2239 |
+
"grad_norm": 0.10663071274757385,
|
2240 |
+
"learning_rate": 1.25e-05,
|
2241 |
+
"loss": 1.1654,
|
2242 |
+
"step": 319
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.4675372112135878,
|
2246 |
+
"grad_norm": 0.10541412234306335,
|
2247 |
+
"learning_rate": 1.2465753424657537e-05,
|
2248 |
+
"loss": 1.3409,
|
2249 |
+
"step": 320
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.4689982649986303,
|
2253 |
+
"grad_norm": 0.10836822539567947,
|
2254 |
+
"learning_rate": 1.243150684931507e-05,
|
2255 |
+
"loss": 1.2551,
|
2256 |
+
"step": 321
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.4704593187836727,
|
2260 |
+
"grad_norm": 0.09797906875610352,
|
2261 |
+
"learning_rate": 1.2397260273972605e-05,
|
2262 |
+
"loss": 1.1954,
|
2263 |
+
"step": 322
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.47192037256871516,
|
2267 |
+
"grad_norm": 0.10791884362697601,
|
2268 |
+
"learning_rate": 1.2363013698630138e-05,
|
2269 |
+
"loss": 1.2677,
|
2270 |
+
"step": 323
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.47338142635375763,
|
2274 |
+
"grad_norm": 0.10603371262550354,
|
2275 |
+
"learning_rate": 1.2328767123287673e-05,
|
2276 |
+
"loss": 1.1747,
|
2277 |
+
"step": 324
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.4748424801388001,
|
2281 |
+
"grad_norm": 0.09947334975004196,
|
2282 |
+
"learning_rate": 1.2294520547945206e-05,
|
2283 |
+
"loss": 1.24,
|
2284 |
+
"step": 325
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.47630353392384256,
|
2288 |
+
"grad_norm": 0.0948692336678505,
|
2289 |
+
"learning_rate": 1.226027397260274e-05,
|
2290 |
+
"loss": 1.3252,
|
2291 |
+
"step": 326
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.477764587708885,
|
2295 |
+
"grad_norm": 0.11293943971395493,
|
2296 |
+
"learning_rate": 1.2226027397260273e-05,
|
2297 |
+
"loss": 1.2193,
|
2298 |
+
"step": 327
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.4792256414939275,
|
2302 |
+
"grad_norm": 0.10320023447275162,
|
2303 |
+
"learning_rate": 1.219178082191781e-05,
|
2304 |
+
"loss": 1.2418,
|
2305 |
+
"step": 328
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.48068669527896996,
|
2309 |
+
"grad_norm": 0.1106739267706871,
|
2310 |
+
"learning_rate": 1.2157534246575345e-05,
|
2311 |
+
"loss": 1.1499,
|
2312 |
+
"step": 329
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.4821477490640124,
|
2316 |
+
"grad_norm": 0.1147918552160263,
|
2317 |
+
"learning_rate": 1.2123287671232878e-05,
|
2318 |
+
"loss": 1.1246,
|
2319 |
+
"step": 330
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.4836088028490549,
|
2323 |
+
"grad_norm": 0.10941941291093826,
|
2324 |
+
"learning_rate": 1.2089041095890412e-05,
|
2325 |
+
"loss": 1.185,
|
2326 |
+
"step": 331
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 0.48506985663409735,
|
2330 |
+
"grad_norm": 0.10806426405906677,
|
2331 |
+
"learning_rate": 1.2054794520547945e-05,
|
2332 |
+
"loss": 1.2699,
|
2333 |
+
"step": 332
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.4865309104191398,
|
2337 |
+
"grad_norm": 0.09904070943593979,
|
2338 |
+
"learning_rate": 1.202054794520548e-05,
|
2339 |
+
"loss": 1.1772,
|
2340 |
+
"step": 333
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 0.4879919642041823,
|
2344 |
+
"grad_norm": 0.097396120429039,
|
2345 |
+
"learning_rate": 1.1986301369863013e-05,
|
2346 |
+
"loss": 1.1753,
|
2347 |
+
"step": 334
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.48945301798922475,
|
2351 |
+
"grad_norm": 0.10030350089073181,
|
2352 |
+
"learning_rate": 1.195205479452055e-05,
|
2353 |
+
"loss": 1.22,
|
2354 |
+
"step": 335
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.4909140717742672,
|
2358 |
+
"grad_norm": 0.1039762943983078,
|
2359 |
+
"learning_rate": 1.1917808219178084e-05,
|
2360 |
+
"loss": 1.2396,
|
2361 |
+
"step": 336
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.4923751255593097,
|
2365 |
+
"grad_norm": 0.10109396278858185,
|
2366 |
+
"learning_rate": 1.1883561643835617e-05,
|
2367 |
+
"loss": 1.185,
|
2368 |
+
"step": 337
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.4938361793443521,
|
2372 |
+
"grad_norm": 0.1067412868142128,
|
2373 |
+
"learning_rate": 1.1849315068493152e-05,
|
2374 |
+
"loss": 1.1804,
|
2375 |
+
"step": 338
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.49529723312939455,
|
2379 |
+
"grad_norm": 0.1046527549624443,
|
2380 |
+
"learning_rate": 1.1815068493150685e-05,
|
2381 |
+
"loss": 1.1996,
|
2382 |
+
"step": 339
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 0.496758286914437,
|
2386 |
+
"grad_norm": 0.10973203927278519,
|
2387 |
+
"learning_rate": 1.178082191780822e-05,
|
2388 |
+
"loss": 1.1812,
|
2389 |
+
"step": 340
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.4982193406994795,
|
2393 |
+
"grad_norm": 0.11020953208208084,
|
2394 |
+
"learning_rate": 1.1746575342465753e-05,
|
2395 |
+
"loss": 1.2603,
|
2396 |
+
"step": 341
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.49968039448452195,
|
2400 |
+
"grad_norm": 0.10667795687913895,
|
2401 |
+
"learning_rate": 1.171232876712329e-05,
|
2402 |
+
"loss": 1.2421,
|
2403 |
+
"step": 342
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.5011414482695644,
|
2407 |
+
"grad_norm": 0.0992070883512497,
|
2408 |
+
"learning_rate": 1.1678082191780822e-05,
|
2409 |
+
"loss": 1.1995,
|
2410 |
+
"step": 343
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.5026025020546069,
|
2414 |
+
"grad_norm": 0.11278413236141205,
|
2415 |
+
"learning_rate": 1.1643835616438357e-05,
|
2416 |
+
"loss": 1.2166,
|
2417 |
+
"step": 344
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.5040635558396493,
|
2421 |
+
"grad_norm": 0.11119436472654343,
|
2422 |
+
"learning_rate": 1.1609589041095892e-05,
|
2423 |
+
"loss": 1.2551,
|
2424 |
+
"step": 345
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.5055246096246918,
|
2428 |
+
"grad_norm": 0.11275441944599152,
|
2429 |
+
"learning_rate": 1.1575342465753425e-05,
|
2430 |
+
"loss": 1.2082,
|
2431 |
+
"step": 346
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.5069856634097343,
|
2435 |
+
"grad_norm": 0.10059484094381332,
|
2436 |
+
"learning_rate": 1.154109589041096e-05,
|
2437 |
+
"loss": 1.172,
|
2438 |
+
"step": 347
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.5084467171947767,
|
2442 |
+
"grad_norm": 0.11156380921602249,
|
2443 |
+
"learning_rate": 1.1506849315068493e-05,
|
2444 |
+
"loss": 1.1818,
|
2445 |
+
"step": 348
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.5099077709798192,
|
2449 |
+
"grad_norm": 0.09762994199991226,
|
2450 |
+
"learning_rate": 1.147260273972603e-05,
|
2451 |
+
"loss": 1.1674,
|
2452 |
+
"step": 349
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 0.5113688247648617,
|
2456 |
+
"grad_norm": 0.10659226775169373,
|
2457 |
+
"learning_rate": 1.1438356164383562e-05,
|
2458 |
+
"loss": 1.1513,
|
2459 |
+
"step": 350
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.5128298785499041,
|
2463 |
+
"grad_norm": 0.11233004927635193,
|
2464 |
+
"learning_rate": 1.1404109589041097e-05,
|
2465 |
+
"loss": 1.1637,
|
2466 |
+
"step": 351
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 0.5142909323349466,
|
2470 |
+
"grad_norm": 0.10431814193725586,
|
2471 |
+
"learning_rate": 1.1369863013698632e-05,
|
2472 |
+
"loss": 1.2148,
|
2473 |
+
"step": 352
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.5157519861199891,
|
2477 |
+
"grad_norm": 0.09940113872289658,
|
2478 |
+
"learning_rate": 1.1335616438356165e-05,
|
2479 |
+
"loss": 1.1836,
|
2480 |
+
"step": 353
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.5172130399050315,
|
2484 |
+
"grad_norm": 0.09862768650054932,
|
2485 |
+
"learning_rate": 1.1301369863013701e-05,
|
2486 |
+
"loss": 1.2356,
|
2487 |
+
"step": 354
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.518674093690074,
|
2491 |
+
"grad_norm": 0.10437644273042679,
|
2492 |
+
"learning_rate": 1.1267123287671232e-05,
|
2493 |
+
"loss": 1.1193,
|
2494 |
+
"step": 355
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.5201351474751165,
|
2498 |
+
"grad_norm": 0.09749601781368256,
|
2499 |
+
"learning_rate": 1.1232876712328769e-05,
|
2500 |
+
"loss": 1.2704,
|
2501 |
+
"step": 356
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.5215962012601589,
|
2505 |
+
"grad_norm": 0.1042131707072258,
|
2506 |
+
"learning_rate": 1.1198630136986302e-05,
|
2507 |
+
"loss": 1.156,
|
2508 |
+
"step": 357
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 0.5230572550452014,
|
2512 |
+
"grad_norm": 0.10424741357564926,
|
2513 |
+
"learning_rate": 1.1164383561643837e-05,
|
2514 |
+
"loss": 1.2334,
|
2515 |
+
"step": 358
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.5245183088302439,
|
2519 |
+
"grad_norm": 0.09913278371095657,
|
2520 |
+
"learning_rate": 1.113013698630137e-05,
|
2521 |
+
"loss": 1.1721,
|
2522 |
+
"step": 359
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.5259793626152863,
|
2526 |
+
"grad_norm": 0.11436072736978531,
|
2527 |
+
"learning_rate": 1.1095890410958904e-05,
|
2528 |
+
"loss": 1.1675,
|
2529 |
+
"step": 360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.5274404164003287,
|
2533 |
+
"grad_norm": 0.1049785315990448,
|
2534 |
+
"learning_rate": 1.1061643835616441e-05,
|
2535 |
+
"loss": 1.1788,
|
2536 |
+
"step": 361
|
2537 |
}
|
2538 |
],
|
2539 |
"logging_steps": 1,
|
|
|
2553 |
"attributes": {}
|
2554 |
}
|
2555 |
},
|
2556 |
+
"total_flos": 4.0655166024812544e+17,
|
2557 |
"train_batch_size": 4,
|
2558 |
"trial_name": null,
|
2559 |
"trial_params": null
|