Training in progress, step 3500, 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 4523108832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718339d978d719631718cf1e1021d975eff890a6f6395001809d622ae5248e83
|
| 3 |
size 4523108832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2912179275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a30b0ce74d4d05f4828b62e82be9db01d80a45a8e3f52c8d9a7dc5ec1dd312
|
| 3 |
size 2912179275
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e48253f89442a3ab8e914e97842a4d8d8c7232b507f4c3119b0e561bd4162e58
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2108,6 +2108,356 @@
|
|
| 2108 |
"learning_rate": 0.00014002,
|
| 2109 |
"loss": 0.08511788249015809,
|
| 2110 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2111 |
}
|
| 2112 |
],
|
| 2113 |
"logging_steps": 10,
|
|
@@ -2127,7 +2477,7 @@
|
|
| 2127 |
"attributes": {}
|
| 2128 |
}
|
| 2129 |
},
|
| 2130 |
-
"total_flos": 2.
|
| 2131 |
"train_batch_size": 1,
|
| 2132 |
"trial_name": null,
|
| 2133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0252,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2108 |
"learning_rate": 0.00014002,
|
| 2109 |
"loss": 0.08511788249015809,
|
| 2110 |
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 4.0074,
|
| 2114 |
+
"grad_norm": 0.37289556860923767,
|
| 2115 |
+
"learning_rate": 0.00013982000000000003,
|
| 2116 |
+
"loss": 0.10226565599441528,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 4.0084,
|
| 2121 |
+
"grad_norm": 0.36419790983200073,
|
| 2122 |
+
"learning_rate": 0.00013962000000000002,
|
| 2123 |
+
"loss": 0.0977319598197937,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 4.0094,
|
| 2128 |
+
"grad_norm": 0.347756952047348,
|
| 2129 |
+
"learning_rate": 0.00013942000000000002,
|
| 2130 |
+
"loss": 0.10832228660583496,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 4.0104,
|
| 2135 |
+
"grad_norm": 0.40426164865493774,
|
| 2136 |
+
"learning_rate": 0.00013922,
|
| 2137 |
+
"loss": 0.11001000404357911,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 4.0114,
|
| 2142 |
+
"grad_norm": 0.3765728771686554,
|
| 2143 |
+
"learning_rate": 0.00013902,
|
| 2144 |
+
"loss": 0.10214830636978149,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 4.0124,
|
| 2149 |
+
"grad_norm": 0.37442028522491455,
|
| 2150 |
+
"learning_rate": 0.00013882000000000003,
|
| 2151 |
+
"loss": 0.10177899599075317,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 4.0134,
|
| 2156 |
+
"grad_norm": 0.3760021924972534,
|
| 2157 |
+
"learning_rate": 0.00013862000000000002,
|
| 2158 |
+
"loss": 0.10235388278961181,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 4.0144,
|
| 2163 |
+
"grad_norm": 0.40187352895736694,
|
| 2164 |
+
"learning_rate": 0.00013842000000000002,
|
| 2165 |
+
"loss": 0.10720946788787841,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 4.0154,
|
| 2170 |
+
"grad_norm": 0.33189886808395386,
|
| 2171 |
+
"learning_rate": 0.00013822000000000001,
|
| 2172 |
+
"loss": 0.12659095525741576,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 4.0164,
|
| 2177 |
+
"grad_norm": 0.35277223587036133,
|
| 2178 |
+
"learning_rate": 0.00013802,
|
| 2179 |
+
"loss": 0.10271661281585694,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 4.0174,
|
| 2184 |
+
"grad_norm": 0.37806376814842224,
|
| 2185 |
+
"learning_rate": 0.00013782,
|
| 2186 |
+
"loss": 0.10171124935150147,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 4.0184,
|
| 2191 |
+
"grad_norm": 0.38206177949905396,
|
| 2192 |
+
"learning_rate": 0.00013762000000000003,
|
| 2193 |
+
"loss": 0.10048867464065551,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 4.0194,
|
| 2198 |
+
"grad_norm": 0.36296215653419495,
|
| 2199 |
+
"learning_rate": 0.00013742000000000002,
|
| 2200 |
+
"loss": 0.09387139678001404,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 4.0204,
|
| 2205 |
+
"grad_norm": 0.3241318166255951,
|
| 2206 |
+
"learning_rate": 0.00013722000000000002,
|
| 2207 |
+
"loss": 0.09321512579917908,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 4.0214,
|
| 2212 |
+
"grad_norm": 0.3707175552845001,
|
| 2213 |
+
"learning_rate": 0.00013702,
|
| 2214 |
+
"loss": 0.10409607887268066,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 4.0224,
|
| 2219 |
+
"grad_norm": 0.35573673248291016,
|
| 2220 |
+
"learning_rate": 0.00013682,
|
| 2221 |
+
"loss": 0.09896103143692017,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 4.0234,
|
| 2226 |
+
"grad_norm": 0.4057498276233673,
|
| 2227 |
+
"learning_rate": 0.00013662,
|
| 2228 |
+
"loss": 0.11238985061645508,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 4.0244,
|
| 2233 |
+
"grad_norm": 0.34688249230384827,
|
| 2234 |
+
"learning_rate": 0.00013642000000000003,
|
| 2235 |
+
"loss": 0.09726371765136718,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 4.0254,
|
| 2240 |
+
"grad_norm": 0.36548253893852234,
|
| 2241 |
+
"learning_rate": 0.00013622000000000002,
|
| 2242 |
+
"loss": 0.09118783473968506,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 4.0264,
|
| 2247 |
+
"grad_norm": 0.3322118818759918,
|
| 2248 |
+
"learning_rate": 0.00013602000000000002,
|
| 2249 |
+
"loss": 0.08653171062469482,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 4.0274,
|
| 2254 |
+
"grad_norm": 0.35557135939598083,
|
| 2255 |
+
"learning_rate": 0.00013582,
|
| 2256 |
+
"loss": 0.08778741359710693,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 4.0284,
|
| 2261 |
+
"grad_norm": 0.3009137511253357,
|
| 2262 |
+
"learning_rate": 0.00013562,
|
| 2263 |
+
"loss": 0.09119086265563965,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 4.0294,
|
| 2268 |
+
"grad_norm": 0.3856281340122223,
|
| 2269 |
+
"learning_rate": 0.00013542,
|
| 2270 |
+
"loss": 0.09039224982261658,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 4.0304,
|
| 2275 |
+
"grad_norm": 0.33204856514930725,
|
| 2276 |
+
"learning_rate": 0.00013522000000000002,
|
| 2277 |
+
"loss": 0.08515154123306275,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 5.0002,
|
| 2282 |
+
"grad_norm": 0.31765300035476685,
|
| 2283 |
+
"learning_rate": 0.00013502000000000002,
|
| 2284 |
+
"loss": 0.10655074119567871,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 5.0012,
|
| 2289 |
+
"grad_norm": 0.26351630687713623,
|
| 2290 |
+
"learning_rate": 0.00013482000000000001,
|
| 2291 |
+
"loss": 0.06924263834953308,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 5.0022,
|
| 2296 |
+
"grad_norm": 0.2613130211830139,
|
| 2297 |
+
"learning_rate": 0.00013462,
|
| 2298 |
+
"loss": 0.07073780298233032,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 5.0032,
|
| 2303 |
+
"grad_norm": 0.2842184603214264,
|
| 2304 |
+
"learning_rate": 0.00013442,
|
| 2305 |
+
"loss": 0.06662424206733704,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 5.0042,
|
| 2310 |
+
"grad_norm": 0.2726162075996399,
|
| 2311 |
+
"learning_rate": 0.00013422,
|
| 2312 |
+
"loss": 0.07099056243896484,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 5.0052,
|
| 2317 |
+
"grad_norm": 0.302075058221817,
|
| 2318 |
+
"learning_rate": 0.00013402000000000002,
|
| 2319 |
+
"loss": 0.06526976823806763,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 5.0062,
|
| 2324 |
+
"grad_norm": 0.310641884803772,
|
| 2325 |
+
"learning_rate": 0.00013382000000000002,
|
| 2326 |
+
"loss": 0.06162307262420654,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 5.0072,
|
| 2331 |
+
"grad_norm": 0.32952383160591125,
|
| 2332 |
+
"learning_rate": 0.00013362,
|
| 2333 |
+
"loss": 0.07002668380737305,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 5.0082,
|
| 2338 |
+
"grad_norm": 0.30953407287597656,
|
| 2339 |
+
"learning_rate": 0.00013342,
|
| 2340 |
+
"loss": 0.0669539988040924,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 5.0092,
|
| 2345 |
+
"grad_norm": 0.3306865692138672,
|
| 2346 |
+
"learning_rate": 0.00013322,
|
| 2347 |
+
"loss": 0.07151323556900024,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 5.0102,
|
| 2352 |
+
"grad_norm": 0.28720608353614807,
|
| 2353 |
+
"learning_rate": 0.00013302000000000002,
|
| 2354 |
+
"loss": 0.07206830978393555,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 5.0112,
|
| 2359 |
+
"grad_norm": 0.29193148016929626,
|
| 2360 |
+
"learning_rate": 0.00013282000000000002,
|
| 2361 |
+
"loss": 0.0766656219959259,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 5.0122,
|
| 2366 |
+
"grad_norm": 0.2924456298351288,
|
| 2367 |
+
"learning_rate": 0.00013262000000000001,
|
| 2368 |
+
"loss": 0.06823275685310363,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 5.0132,
|
| 2373 |
+
"grad_norm": 0.2984090745449066,
|
| 2374 |
+
"learning_rate": 0.00013242,
|
| 2375 |
+
"loss": 0.06823591589927673,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 5.0142,
|
| 2380 |
+
"grad_norm": 0.30468592047691345,
|
| 2381 |
+
"learning_rate": 0.00013222,
|
| 2382 |
+
"loss": 0.07523037791252137,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 5.0152,
|
| 2387 |
+
"grad_norm": 0.32693299651145935,
|
| 2388 |
+
"learning_rate": 0.00013202,
|
| 2389 |
+
"loss": 0.09835698008537293,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 5.0162,
|
| 2394 |
+
"grad_norm": 0.34058642387390137,
|
| 2395 |
+
"learning_rate": 0.00013182000000000002,
|
| 2396 |
+
"loss": 0.07129377722740174,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 5.0172,
|
| 2401 |
+
"grad_norm": 0.31692641973495483,
|
| 2402 |
+
"learning_rate": 0.00013162000000000002,
|
| 2403 |
+
"loss": 0.06967606544494628,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 5.0182,
|
| 2408 |
+
"grad_norm": 0.27472278475761414,
|
| 2409 |
+
"learning_rate": 0.00013142,
|
| 2410 |
+
"loss": 0.06811057925224304,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 5.0192,
|
| 2415 |
+
"grad_norm": 0.3070657253265381,
|
| 2416 |
+
"learning_rate": 0.00013122,
|
| 2417 |
+
"loss": 0.06674447655677795,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 5.0202,
|
| 2422 |
+
"grad_norm": 0.31556063890457153,
|
| 2423 |
+
"learning_rate": 0.00013102,
|
| 2424 |
+
"loss": 0.0634992241859436,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 5.0212,
|
| 2429 |
+
"grad_norm": 0.32814645767211914,
|
| 2430 |
+
"learning_rate": 0.00013082,
|
| 2431 |
+
"loss": 0.07011401653289795,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 5.0222,
|
| 2436 |
+
"grad_norm": 0.32829102873802185,
|
| 2437 |
+
"learning_rate": 0.00013062000000000002,
|
| 2438 |
+
"loss": 0.06834354400634765,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 5.0232,
|
| 2443 |
+
"grad_norm": 0.27184948325157166,
|
| 2444 |
+
"learning_rate": 0.00013042000000000002,
|
| 2445 |
+
"loss": 0.07986602783203126,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 5.0242,
|
| 2450 |
+
"grad_norm": 0.2695474624633789,
|
| 2451 |
+
"learning_rate": 0.00013022,
|
| 2452 |
+
"loss": 0.06707475185394288,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 5.0252,
|
| 2457 |
+
"grad_norm": 0.3358134627342224,
|
| 2458 |
+
"learning_rate": 0.00013002,
|
| 2459 |
+
"loss": 0.06365590691566467,
|
| 2460 |
+
"step": 3500
|
| 2461 |
}
|
| 2462 |
],
|
| 2463 |
"logging_steps": 10,
|
|
|
|
| 2477 |
"attributes": {}
|
| 2478 |
}
|
| 2479 |
},
|
| 2480 |
+
"total_flos": 2.962923297730806e+17,
|
| 2481 |
"train_batch_size": 1,
|
| 2482 |
"trial_name": null,
|
| 2483 |
"trial_params": null
|