Training in progress, step 170000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +139 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893439185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3edb0adadd334561a36e43a4212a4e9514b0b74e249ccb77a9f1a398e42f35
|
3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
|
3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15587
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c26ad211585233ad2dccb9325976cb7e71ced6080ea69e9468119115e0c0050
|
3 |
size 15587
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ae036049be18d3db0b069d7cdee2136b0e955af29d02ba238e8d63ec3de1819
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f97d2f076eca9f1526fcbf8cced9c57bd3414f3b9c7f6f76f9126f17c819f1a
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2182,11 +2182,147 @@
|
|
2182 |
"eval_samples_per_second": 144.224,
|
2183 |
"eval_steps_per_second": 2.254,
|
2184 |
"step": 160000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2185 |
}
|
2186 |
],
|
2187 |
"max_steps": 200000,
|
2188 |
"num_train_epochs": 9223372036854775807,
|
2189 |
-
"total_flos":
|
2190 |
"trial_name": null,
|
2191 |
"trial_params": null
|
2192 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1,
|
5 |
+
"global_step": 170000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2182 |
"eval_samples_per_second": 144.224,
|
2183 |
"eval_steps_per_second": 2.254,
|
2184 |
"step": 160000
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 0.05,
|
2188 |
+
"learning_rate": 1.848573312159415e-05,
|
2189 |
+
"loss": 0.378,
|
2190 |
+
"step": 160500
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 0.06,
|
2194 |
+
"learning_rate": 1.8279734067715378e-05,
|
2195 |
+
"loss": 0.3769,
|
2196 |
+
"step": 161000
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 0.06,
|
2200 |
+
"learning_rate": 1.8075609083923823e-05,
|
2201 |
+
"loss": 0.3772,
|
2202 |
+
"step": 161500
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 0.06,
|
2206 |
+
"learning_rate": 1.7873785866083376e-05,
|
2207 |
+
"loss": 0.3761,
|
2208 |
+
"step": 162000
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 0.06,
|
2212 |
+
"learning_rate": 1.7674276863600826e-05,
|
2213 |
+
"loss": 0.3754,
|
2214 |
+
"step": 162500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.07,
|
2218 |
+
"learning_rate": 1.747709438313117e-05,
|
2219 |
+
"loss": 0.3761,
|
2220 |
+
"step": 163000
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 0.07,
|
2224 |
+
"learning_rate": 1.728225058781864e-05,
|
2225 |
+
"loss": 0.3757,
|
2226 |
+
"step": 163500
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 0.07,
|
2230 |
+
"learning_rate": 1.7089757496546325e-05,
|
2231 |
+
"loss": 0.3764,
|
2232 |
+
"step": 164000
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 0.07,
|
2236 |
+
"learning_rate": 1.6899626983194823e-05,
|
2237 |
+
"loss": 0.3746,
|
2238 |
+
"step": 164500
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 0.07,
|
2242 |
+
"learning_rate": 1.6712243911044467e-05,
|
2243 |
+
"loss": 0.375,
|
2244 |
+
"step": 165000
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.07,
|
2248 |
+
"eval_loss": 0.34934455156326294,
|
2249 |
+
"eval_runtime": 286.3366,
|
2250 |
+
"eval_samples_per_second": 150.173,
|
2251 |
+
"eval_steps_per_second": 2.347,
|
2252 |
+
"step": 165000
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 0.08,
|
2256 |
+
"learning_rate": 1.6526868808276845e-05,
|
2257 |
+
"loss": 0.3763,
|
2258 |
+
"step": 165500
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.08,
|
2262 |
+
"learning_rate": 1.6344254560630497e-05,
|
2263 |
+
"loss": 0.3733,
|
2264 |
+
"step": 166000
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.08,
|
2268 |
+
"learning_rate": 1.616368051555008e-05,
|
2269 |
+
"loss": 0.3749,
|
2270 |
+
"step": 166500
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.09,
|
2274 |
+
"learning_rate": 1.5985526173180873e-05,
|
2275 |
+
"loss": 0.3755,
|
2276 |
+
"step": 167000
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 0.09,
|
2280 |
+
"learning_rate": 1.580980252292188e-05,
|
2281 |
+
"loss": 0.3754,
|
2282 |
+
"step": 167500
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 0.09,
|
2286 |
+
"learning_rate": 1.563652040423561e-05,
|
2287 |
+
"loss": 0.3747,
|
2288 |
+
"step": 168000
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 0.09,
|
2292 |
+
"learning_rate": 1.546569050597935e-05,
|
2293 |
+
"loss": 0.3758,
|
2294 |
+
"step": 168500
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 0.1,
|
2298 |
+
"learning_rate": 1.5297657635265495e-05,
|
2299 |
+
"loss": 0.3756,
|
2300 |
+
"step": 169000
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.1,
|
2304 |
+
"learning_rate": 1.5131758682182151e-05,
|
2305 |
+
"loss": 0.375,
|
2306 |
+
"step": 169500
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.1,
|
2310 |
+
"learning_rate": 1.49683430856095e-05,
|
2311 |
+
"loss": 0.3759,
|
2312 |
+
"step": 170000
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.1,
|
2316 |
+
"eval_loss": 0.3487904369831085,
|
2317 |
+
"eval_runtime": 298.7435,
|
2318 |
+
"eval_samples_per_second": 143.936,
|
2319 |
+
"eval_steps_per_second": 2.249,
|
2320 |
+
"step": 170000
|
2321 |
}
|
2322 |
],
|
2323 |
"max_steps": 200000,
|
2324 |
"num_train_epochs": 9223372036854775807,
|
2325 |
+
"total_flos": 4.003382145200947e+21,
|
2326 |
"trial_name": null,
|
2327 |
"trial_params": null
|
2328 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
|
3 |
size 449471589
|