Training in progress, step 8000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:838a4ab73674e543294413e3097b3eabbd630f5c20a124585de69ad0e0e815d8
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235130
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a621c8febc9a6c490ca85de5343a09d239443b3e81df1d9eac8308b435de3e
|
| 3 |
size 440235130
|
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 sha256:02f168edafa2801f823807e6afc046dca92cd4ad947f02d4df54bbd69faf05d4
|
| 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:b666ed9a86454cc0d63d2bc4e76ac33fe2a0be0b9e396efaa3946446f4e018d4
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": Infinity,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2030,6 +2030,295 @@
|
|
| 2030 |
"eval_steps_per_second": 1.222,
|
| 2031 |
"eval_wer": Infinity,
|
| 2032 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2033 |
}
|
| 2034 |
],
|
| 2035 |
"logging_steps": 25,
|
|
@@ -2049,7 +2338,7 @@
|
|
| 2049 |
"attributes": {}
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
-
"total_flos": 1.
|
| 2053 |
"train_batch_size": 12,
|
| 2054 |
"trial_name": null,
|
| 2055 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": Infinity,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.20148637489678,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2030 |
"eval_steps_per_second": 1.222,
|
| 2031 |
"eval_wer": Infinity,
|
| 2032 |
"step": 7000
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 11.59289843104872,
|
| 2036 |
+
"grad_norm": 6.9122748374938965,
|
| 2037 |
+
"learning_rate": 6.267368421052632e-06,
|
| 2038 |
+
"loss": 0.2701,
|
| 2039 |
+
"step": 7025
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 11.63418662262593,
|
| 2043 |
+
"grad_norm": 4.586194038391113,
|
| 2044 |
+
"learning_rate": 6.214736842105264e-06,
|
| 2045 |
+
"loss": 0.2496,
|
| 2046 |
+
"step": 7050
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 11.675474814203138,
|
| 2050 |
+
"grad_norm": 5.90902853012085,
|
| 2051 |
+
"learning_rate": 6.1621052631578945e-06,
|
| 2052 |
+
"loss": 0.2384,
|
| 2053 |
+
"step": 7075
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 11.716763005780347,
|
| 2057 |
+
"grad_norm": 5.328728199005127,
|
| 2058 |
+
"learning_rate": 6.109473684210527e-06,
|
| 2059 |
+
"loss": 0.253,
|
| 2060 |
+
"step": 7100
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 11.758051197357556,
|
| 2064 |
+
"grad_norm": 6.127770900726318,
|
| 2065 |
+
"learning_rate": 6.056842105263159e-06,
|
| 2066 |
+
"loss": 0.2359,
|
| 2067 |
+
"step": 7125
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 11.799339388934765,
|
| 2071 |
+
"grad_norm": 5.675428867340088,
|
| 2072 |
+
"learning_rate": 6.00421052631579e-06,
|
| 2073 |
+
"loss": 0.2383,
|
| 2074 |
+
"step": 7150
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 11.840627580511974,
|
| 2078 |
+
"grad_norm": 4.921765327453613,
|
| 2079 |
+
"learning_rate": 5.951578947368422e-06,
|
| 2080 |
+
"loss": 0.2648,
|
| 2081 |
+
"step": 7175
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 11.881915772089183,
|
| 2085 |
+
"grad_norm": 4.198760986328125,
|
| 2086 |
+
"learning_rate": 5.898947368421053e-06,
|
| 2087 |
+
"loss": 0.2351,
|
| 2088 |
+
"step": 7200
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 11.923203963666392,
|
| 2092 |
+
"grad_norm": 4.786856174468994,
|
| 2093 |
+
"learning_rate": 5.846315789473684e-06,
|
| 2094 |
+
"loss": 0.2468,
|
| 2095 |
+
"step": 7225
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 11.964492155243601,
|
| 2099 |
+
"grad_norm": 4.955503463745117,
|
| 2100 |
+
"learning_rate": 5.793684210526316e-06,
|
| 2101 |
+
"loss": 0.2471,
|
| 2102 |
+
"step": 7250
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 12.004954582989265,
|
| 2106 |
+
"grad_norm": 4.753754138946533,
|
| 2107 |
+
"learning_rate": 5.7410526315789485e-06,
|
| 2108 |
+
"loss": 0.2625,
|
| 2109 |
+
"step": 7275
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 12.046242774566474,
|
| 2113 |
+
"grad_norm": 3.7155563831329346,
|
| 2114 |
+
"learning_rate": 5.68842105263158e-06,
|
| 2115 |
+
"loss": 0.2123,
|
| 2116 |
+
"step": 7300
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 12.087530966143683,
|
| 2120 |
+
"grad_norm": 4.637264251708984,
|
| 2121 |
+
"learning_rate": 5.635789473684211e-06,
|
| 2122 |
+
"loss": 0.209,
|
| 2123 |
+
"step": 7325
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 12.128819157720892,
|
| 2127 |
+
"grad_norm": 5.065235614776611,
|
| 2128 |
+
"learning_rate": 5.5831578947368425e-06,
|
| 2129 |
+
"loss": 0.2016,
|
| 2130 |
+
"step": 7350
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 12.170107349298101,
|
| 2134 |
+
"grad_norm": 4.761934280395508,
|
| 2135 |
+
"learning_rate": 5.530526315789474e-06,
|
| 2136 |
+
"loss": 0.2081,
|
| 2137 |
+
"step": 7375
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 12.21139554087531,
|
| 2141 |
+
"grad_norm": 5.17978048324585,
|
| 2142 |
+
"learning_rate": 5.477894736842105e-06,
|
| 2143 |
+
"loss": 0.2288,
|
| 2144 |
+
"step": 7400
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 12.25268373245252,
|
| 2148 |
+
"grad_norm": 3.554265260696411,
|
| 2149 |
+
"learning_rate": 5.425263157894737e-06,
|
| 2150 |
+
"loss": 0.2143,
|
| 2151 |
+
"step": 7425
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 12.293971924029728,
|
| 2155 |
+
"grad_norm": 5.236491680145264,
|
| 2156 |
+
"learning_rate": 5.372631578947369e-06,
|
| 2157 |
+
"loss": 0.2025,
|
| 2158 |
+
"step": 7450
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 12.335260115606937,
|
| 2162 |
+
"grad_norm": 5.198639392852783,
|
| 2163 |
+
"learning_rate": 5.320000000000001e-06,
|
| 2164 |
+
"loss": 0.2199,
|
| 2165 |
+
"step": 7475
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 12.376548307184144,
|
| 2169 |
+
"grad_norm": 5.509646892547607,
|
| 2170 |
+
"learning_rate": 5.267368421052632e-06,
|
| 2171 |
+
"loss": 0.1932,
|
| 2172 |
+
"step": 7500
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 12.417836498761353,
|
| 2176 |
+
"grad_norm": 4.569394588470459,
|
| 2177 |
+
"learning_rate": 5.214736842105263e-06,
|
| 2178 |
+
"loss": 0.2018,
|
| 2179 |
+
"step": 7525
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 12.459124690338562,
|
| 2183 |
+
"grad_norm": 4.686092376708984,
|
| 2184 |
+
"learning_rate": 5.162105263157895e-06,
|
| 2185 |
+
"loss": 0.2148,
|
| 2186 |
+
"step": 7550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 12.500412881915771,
|
| 2190 |
+
"grad_norm": 5.779174327850342,
|
| 2191 |
+
"learning_rate": 5.1094736842105264e-06,
|
| 2192 |
+
"loss": 0.2362,
|
| 2193 |
+
"step": 7575
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 12.54170107349298,
|
| 2197 |
+
"grad_norm": 7.2701873779296875,
|
| 2198 |
+
"learning_rate": 5.056842105263158e-06,
|
| 2199 |
+
"loss": 0.2421,
|
| 2200 |
+
"step": 7600
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 12.58298926507019,
|
| 2204 |
+
"grad_norm": 4.832854270935059,
|
| 2205 |
+
"learning_rate": 5.0042105263157906e-06,
|
| 2206 |
+
"loss": 0.219,
|
| 2207 |
+
"step": 7625
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 12.624277456647398,
|
| 2211 |
+
"grad_norm": 5.803878307342529,
|
| 2212 |
+
"learning_rate": 4.951578947368421e-06,
|
| 2213 |
+
"loss": 0.2172,
|
| 2214 |
+
"step": 7650
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 12.665565648224607,
|
| 2218 |
+
"grad_norm": 4.021119594573975,
|
| 2219 |
+
"learning_rate": 4.898947368421053e-06,
|
| 2220 |
+
"loss": 0.227,
|
| 2221 |
+
"step": 7675
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 12.706853839801816,
|
| 2225 |
+
"grad_norm": 5.169255256652832,
|
| 2226 |
+
"learning_rate": 4.846315789473685e-06,
|
| 2227 |
+
"loss": 0.21,
|
| 2228 |
+
"step": 7700
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 12.748142031379025,
|
| 2232 |
+
"grad_norm": 4.798264503479004,
|
| 2233 |
+
"learning_rate": 4.793684210526316e-06,
|
| 2234 |
+
"loss": 0.1984,
|
| 2235 |
+
"step": 7725
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 12.789430222956234,
|
| 2239 |
+
"grad_norm": 5.631106853485107,
|
| 2240 |
+
"learning_rate": 4.741052631578948e-06,
|
| 2241 |
+
"loss": 0.225,
|
| 2242 |
+
"step": 7750
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 12.830718414533443,
|
| 2246 |
+
"grad_norm": 4.223946571350098,
|
| 2247 |
+
"learning_rate": 4.6884210526315795e-06,
|
| 2248 |
+
"loss": 0.2163,
|
| 2249 |
+
"step": 7775
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 12.872006606110652,
|
| 2253 |
+
"grad_norm": 4.958042621612549,
|
| 2254 |
+
"learning_rate": 4.63578947368421e-06,
|
| 2255 |
+
"loss": 0.2131,
|
| 2256 |
+
"step": 7800
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 12.913294797687861,
|
| 2260 |
+
"grad_norm": 6.063140392303467,
|
| 2261 |
+
"learning_rate": 4.583157894736843e-06,
|
| 2262 |
+
"loss": 0.2443,
|
| 2263 |
+
"step": 7825
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 12.95458298926507,
|
| 2267 |
+
"grad_norm": 4.037540435791016,
|
| 2268 |
+
"learning_rate": 4.5305263157894744e-06,
|
| 2269 |
+
"loss": 0.2033,
|
| 2270 |
+
"step": 7850
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 12.995871180842279,
|
| 2274 |
+
"grad_norm": 4.495209217071533,
|
| 2275 |
+
"learning_rate": 4.477894736842105e-06,
|
| 2276 |
+
"loss": 0.2307,
|
| 2277 |
+
"step": 7875
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 13.036333608587944,
|
| 2281 |
+
"grad_norm": 4.494256496429443,
|
| 2282 |
+
"learning_rate": 4.425263157894737e-06,
|
| 2283 |
+
"loss": 0.1894,
|
| 2284 |
+
"step": 7900
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 13.077621800165153,
|
| 2288 |
+
"grad_norm": 3.877058744430542,
|
| 2289 |
+
"learning_rate": 4.3726315789473685e-06,
|
| 2290 |
+
"loss": 0.195,
|
| 2291 |
+
"step": 7925
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 13.118909991742361,
|
| 2295 |
+
"grad_norm": 4.717246055603027,
|
| 2296 |
+
"learning_rate": 4.32e-06,
|
| 2297 |
+
"loss": 0.1745,
|
| 2298 |
+
"step": 7950
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 13.16019818331957,
|
| 2302 |
+
"grad_norm": 4.590612411499023,
|
| 2303 |
+
"learning_rate": 4.267368421052632e-06,
|
| 2304 |
+
"loss": 0.195,
|
| 2305 |
+
"step": 7975
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 13.20148637489678,
|
| 2309 |
+
"grad_norm": 6.558470249176025,
|
| 2310 |
+
"learning_rate": 4.214736842105263e-06,
|
| 2311 |
+
"loss": 0.1913,
|
| 2312 |
+
"step": 8000
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 13.20148637489678,
|
| 2316 |
+
"eval_loss": 1.1226582527160645,
|
| 2317 |
+
"eval_runtime": 703.5225,
|
| 2318 |
+
"eval_samples_per_second": 15.04,
|
| 2319 |
+
"eval_steps_per_second": 1.254,
|
| 2320 |
+
"eval_wer": Infinity,
|
| 2321 |
+
"step": 8000
|
| 2322 |
}
|
| 2323 |
],
|
| 2324 |
"logging_steps": 25,
|
|
|
|
| 2338 |
"attributes": {}
|
| 2339 |
}
|
| 2340 |
},
|
| 2341 |
+
"total_flos": 1.559294663196672e+19,
|
| 2342 |
"train_batch_size": 12,
|
| 2343 |
"trial_name": null,
|
| 2344 |
"trial_params": null
|