Training in progress, step 3500, 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 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb65aad7f5881ab6c4f55f41fa5aa18d8451e3142560b840323390718fbf1c0
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed6c83118141e829ba55ae59bd3661bdfd7b741a28a938857f067ee13bda6e1f
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cd6b45f83835221dcdf23f243180950e962516b14dd7ff28fbb69bb83387d6c
|
| 3 |
size 14244
|
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 sha256:15c59c2a801a017f8138f2d9ac3b94589723ddfbbf1ae570418aa9bfac089535
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4271390736103058,
|
| 3 |
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-3000",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2047,13 +2047,353 @@
|
|
| 2047 |
"eval_samples_per_second": 91.022,
|
| 2048 |
"eval_steps_per_second": 11.426,
|
| 2049 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2050 |
}
|
| 2051 |
],
|
| 2052 |
"logging_steps": 10,
|
| 2053 |
"max_steps": 6130,
|
| 2054 |
"num_train_epochs": 10,
|
| 2055 |
"save_steps": 500,
|
| 2056 |
-
"total_flos":
|
| 2057 |
"trial_name": null,
|
| 2058 |
"trial_params": null
|
| 2059 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4271390736103058,
|
| 3 |
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-3000",
|
| 4 |
+
"epoch": 5.709624796084829,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 3500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2047 |
"eval_samples_per_second": 91.022,
|
| 2048 |
"eval_steps_per_second": 11.426,
|
| 2049 |
"step": 3000
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 4.91,
|
| 2053 |
+
"learning_rate": 0.0005541740674955595,
|
| 2054 |
+
"loss": 0.4681,
|
| 2055 |
+
"step": 3010
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 4.93,
|
| 2059 |
+
"learning_rate": 0.0005523978685612788,
|
| 2060 |
+
"loss": 0.4466,
|
| 2061 |
+
"step": 3020
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 4.94,
|
| 2065 |
+
"learning_rate": 0.0005506216696269982,
|
| 2066 |
+
"loss": 0.4146,
|
| 2067 |
+
"step": 3030
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.96,
|
| 2071 |
+
"learning_rate": 0.0005488454706927176,
|
| 2072 |
+
"loss": 0.4909,
|
| 2073 |
+
"step": 3040
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 4.98,
|
| 2077 |
+
"learning_rate": 0.0005470692717584369,
|
| 2078 |
+
"loss": 0.4382,
|
| 2079 |
+
"step": 3050
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 4.99,
|
| 2083 |
+
"learning_rate": 0.0005452930728241563,
|
| 2084 |
+
"loss": 0.4615,
|
| 2085 |
+
"step": 3060
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 5.01,
|
| 2089 |
+
"learning_rate": 0.0005435168738898757,
|
| 2090 |
+
"loss": 0.4114,
|
| 2091 |
+
"step": 3070
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 5.02,
|
| 2095 |
+
"learning_rate": 0.0005417406749555951,
|
| 2096 |
+
"loss": 0.4365,
|
| 2097 |
+
"step": 3080
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 5.04,
|
| 2101 |
+
"learning_rate": 0.0005399644760213144,
|
| 2102 |
+
"loss": 0.4459,
|
| 2103 |
+
"step": 3090
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 5.06,
|
| 2107 |
+
"learning_rate": 0.0005381882770870338,
|
| 2108 |
+
"loss": 0.4326,
|
| 2109 |
+
"step": 3100
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 5.06,
|
| 2113 |
+
"eval_loss": 0.42266643047332764,
|
| 2114 |
+
"eval_runtime": 12.9188,
|
| 2115 |
+
"eval_samples_per_second": 90.643,
|
| 2116 |
+
"eval_steps_per_second": 11.379,
|
| 2117 |
+
"step": 3100
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 5.07,
|
| 2121 |
+
"learning_rate": 0.0005364120781527531,
|
| 2122 |
+
"loss": 0.4261,
|
| 2123 |
+
"step": 3110
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 5.09,
|
| 2127 |
+
"learning_rate": 0.0005346358792184724,
|
| 2128 |
+
"loss": 0.4112,
|
| 2129 |
+
"step": 3120
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 5.11,
|
| 2133 |
+
"learning_rate": 0.0005328596802841918,
|
| 2134 |
+
"loss": 0.4144,
|
| 2135 |
+
"step": 3130
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 5.12,
|
| 2139 |
+
"learning_rate": 0.0005310834813499112,
|
| 2140 |
+
"loss": 0.4119,
|
| 2141 |
+
"step": 3140
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 5.14,
|
| 2145 |
+
"learning_rate": 0.0005293072824156305,
|
| 2146 |
+
"loss": 0.3985,
|
| 2147 |
+
"step": 3150
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 5.15,
|
| 2151 |
+
"learning_rate": 0.0005275310834813499,
|
| 2152 |
+
"loss": 0.4249,
|
| 2153 |
+
"step": 3160
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 5.17,
|
| 2157 |
+
"learning_rate": 0.0005257548845470693,
|
| 2158 |
+
"loss": 0.4289,
|
| 2159 |
+
"step": 3170
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 5.19,
|
| 2163 |
+
"learning_rate": 0.0005239786856127886,
|
| 2164 |
+
"loss": 0.446,
|
| 2165 |
+
"step": 3180
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 5.2,
|
| 2169 |
+
"learning_rate": 0.000522202486678508,
|
| 2170 |
+
"loss": 0.4505,
|
| 2171 |
+
"step": 3190
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 5.22,
|
| 2175 |
+
"learning_rate": 0.0005204262877442274,
|
| 2176 |
+
"loss": 0.4613,
|
| 2177 |
+
"step": 3200
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 5.22,
|
| 2181 |
+
"eval_loss": 0.4256543815135956,
|
| 2182 |
+
"eval_runtime": 12.7792,
|
| 2183 |
+
"eval_samples_per_second": 91.634,
|
| 2184 |
+
"eval_steps_per_second": 11.503,
|
| 2185 |
+
"step": 3200
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 5.24,
|
| 2189 |
+
"learning_rate": 0.0005186500888099467,
|
| 2190 |
+
"loss": 0.4168,
|
| 2191 |
+
"step": 3210
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 5.25,
|
| 2195 |
+
"learning_rate": 0.000516873889875666,
|
| 2196 |
+
"loss": 0.4754,
|
| 2197 |
+
"step": 3220
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 5.27,
|
| 2201 |
+
"learning_rate": 0.0005150976909413854,
|
| 2202 |
+
"loss": 0.4053,
|
| 2203 |
+
"step": 3230
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 5.29,
|
| 2207 |
+
"learning_rate": 0.0005133214920071047,
|
| 2208 |
+
"loss": 0.4463,
|
| 2209 |
+
"step": 3240
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 5.3,
|
| 2213 |
+
"learning_rate": 0.0005115452930728241,
|
| 2214 |
+
"loss": 0.4651,
|
| 2215 |
+
"step": 3250
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 5.32,
|
| 2219 |
+
"learning_rate": 0.0005097690941385435,
|
| 2220 |
+
"loss": 0.4347,
|
| 2221 |
+
"step": 3260
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 5.33,
|
| 2225 |
+
"learning_rate": 0.0005079928952042628,
|
| 2226 |
+
"loss": 0.4227,
|
| 2227 |
+
"step": 3270
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 5.35,
|
| 2231 |
+
"learning_rate": 0.0005062166962699822,
|
| 2232 |
+
"loss": 0.4292,
|
| 2233 |
+
"step": 3280
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 5.37,
|
| 2237 |
+
"learning_rate": 0.0005044404973357016,
|
| 2238 |
+
"loss": 0.4408,
|
| 2239 |
+
"step": 3290
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 5.38,
|
| 2243 |
+
"learning_rate": 0.0005026642984014209,
|
| 2244 |
+
"loss": 0.446,
|
| 2245 |
+
"step": 3300
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 5.38,
|
| 2249 |
+
"eval_loss": 0.4269155263900757,
|
| 2250 |
+
"eval_runtime": 12.9043,
|
| 2251 |
+
"eval_samples_per_second": 90.745,
|
| 2252 |
+
"eval_steps_per_second": 11.392,
|
| 2253 |
+
"step": 3300
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 5.4,
|
| 2257 |
+
"learning_rate": 0.0005008880994671403,
|
| 2258 |
+
"loss": 0.4059,
|
| 2259 |
+
"step": 3310
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 5.42,
|
| 2263 |
+
"learning_rate": 0.0004991119005328598,
|
| 2264 |
+
"loss": 0.4111,
|
| 2265 |
+
"step": 3320
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 5.43,
|
| 2269 |
+
"learning_rate": 0.000497335701598579,
|
| 2270 |
+
"loss": 0.3952,
|
| 2271 |
+
"step": 3330
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 5.45,
|
| 2275 |
+
"learning_rate": 0.0004955595026642984,
|
| 2276 |
+
"loss": 0.4449,
|
| 2277 |
+
"step": 3340
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 5.46,
|
| 2281 |
+
"learning_rate": 0.0004937833037300178,
|
| 2282 |
+
"loss": 0.4312,
|
| 2283 |
+
"step": 3350
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 5.48,
|
| 2287 |
+
"learning_rate": 0.0004920071047957371,
|
| 2288 |
+
"loss": 0.428,
|
| 2289 |
+
"step": 3360
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 5.5,
|
| 2293 |
+
"learning_rate": 0.0004902309058614565,
|
| 2294 |
+
"loss": 0.4202,
|
| 2295 |
+
"step": 3370
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 5.51,
|
| 2299 |
+
"learning_rate": 0.0004884547069271759,
|
| 2300 |
+
"loss": 0.4164,
|
| 2301 |
+
"step": 3380
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 5.53,
|
| 2305 |
+
"learning_rate": 0.0004866785079928952,
|
| 2306 |
+
"loss": 0.407,
|
| 2307 |
+
"step": 3390
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 5.55,
|
| 2311 |
+
"learning_rate": 0.0004849023090586146,
|
| 2312 |
+
"loss": 0.4,
|
| 2313 |
+
"step": 3400
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 5.55,
|
| 2317 |
+
"eval_loss": 0.4314885437488556,
|
| 2318 |
+
"eval_runtime": 13.0675,
|
| 2319 |
+
"eval_samples_per_second": 89.612,
|
| 2320 |
+
"eval_steps_per_second": 11.249,
|
| 2321 |
+
"step": 3400
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 5.56,
|
| 2325 |
+
"learning_rate": 0.0004831261101243339,
|
| 2326 |
+
"loss": 0.4138,
|
| 2327 |
+
"step": 3410
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 5.58,
|
| 2331 |
+
"learning_rate": 0.00048134991119005326,
|
| 2332 |
+
"loss": 0.4223,
|
| 2333 |
+
"step": 3420
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 5.6,
|
| 2337 |
+
"learning_rate": 0.00047957371225577266,
|
| 2338 |
+
"loss": 0.4108,
|
| 2339 |
+
"step": 3430
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 5.61,
|
| 2343 |
+
"learning_rate": 0.000477797513321492,
|
| 2344 |
+
"loss": 0.4065,
|
| 2345 |
+
"step": 3440
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 5.63,
|
| 2349 |
+
"learning_rate": 0.00047602131438721133,
|
| 2350 |
+
"loss": 0.4481,
|
| 2351 |
+
"step": 3450
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 5.64,
|
| 2355 |
+
"learning_rate": 0.00047424511545293073,
|
| 2356 |
+
"loss": 0.4273,
|
| 2357 |
+
"step": 3460
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 5.66,
|
| 2361 |
+
"learning_rate": 0.00047246891651865007,
|
| 2362 |
+
"loss": 0.4267,
|
| 2363 |
+
"step": 3470
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 5.68,
|
| 2367 |
+
"learning_rate": 0.00047069271758436946,
|
| 2368 |
+
"loss": 0.4626,
|
| 2369 |
+
"step": 3480
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 5.69,
|
| 2373 |
+
"learning_rate": 0.00046891651865008885,
|
| 2374 |
+
"loss": 0.4441,
|
| 2375 |
+
"step": 3490
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 5.71,
|
| 2379 |
+
"learning_rate": 0.0004671403197158082,
|
| 2380 |
+
"loss": 0.4086,
|
| 2381 |
+
"step": 3500
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 5.71,
|
| 2385 |
+
"eval_loss": 0.4278687536716461,
|
| 2386 |
+
"eval_runtime": 12.9778,
|
| 2387 |
+
"eval_samples_per_second": 90.231,
|
| 2388 |
+
"eval_steps_per_second": 11.327,
|
| 2389 |
+
"step": 3500
|
| 2390 |
}
|
| 2391 |
],
|
| 2392 |
"logging_steps": 10,
|
| 2393 |
"max_steps": 6130,
|
| 2394 |
"num_train_epochs": 10,
|
| 2395 |
"save_steps": 500,
|
| 2396 |
+
"total_flos": 6614658553872384.0,
|
| 2397 |
"trial_name": null,
|
| 2398 |
"trial_params": null
|
| 2399 |
}
|