Upload folder using huggingface_hub
Browse files- pytorch_model-00001-of-00003.bin +1 -1
- pytorch_model-00002-of-00003.bin +1 -1
- pytorch_model-00003-of-00003.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +671 -3
- training_args.bin +2 -2
pytorch_model-00001-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9949048046
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2a8a9cde4c46113cbbf48ae220d46fa6219fad20c081a6bf0aedee0e9719f7e
|
| 3 |
size 9949048046
|
pytorch_model-00002-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9904474400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c4e0301bb2e41ff4ff0efb7bdc0cfe5cab5e5713aa08138b7624806cfa7450f
|
| 3 |
size 9904474400
|
pytorch_model-00003-of-00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6179210249
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c085de478c04c9209f03c904d8d33b01895c7622458b9895f775f397e6a75cf4
|
| 3 |
size 6179210249
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14511
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51edccd6f9855740cdfe1d96d81afba5cfd7b32b28cf15897f8fbadf588f1179
|
| 3 |
size 14511
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec0a535d2c9c4c62a74336a7f93b6d947a1152f53a6066eccd4123d6b477c15c
|
| 3 |
size 627
|
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,
|
|
@@ -2114,11 +2114,679 @@
|
|
| 2114 |
"eval_samples_per_second": 4.049,
|
| 2115 |
"eval_steps_per_second": 2.024,
|
| 2116 |
"step": 3100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2117 |
}
|
| 2118 |
],
|
| 2119 |
"max_steps": 10000,
|
| 2120 |
"num_train_epochs": 1,
|
| 2121 |
-
"total_flos":
|
| 2122 |
"trial_name": null,
|
| 2123 |
"trial_params": null
|
| 2124 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.005037789125310321,
|
| 5 |
+
"global_step": 8000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2114 |
"eval_samples_per_second": 4.049,
|
| 2115 |
"eval_steps_per_second": 2.024,
|
| 2116 |
"step": 3100
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.0,
|
| 2120 |
+
"learning_rate": 0.0002,
|
| 2121 |
+
"loss": 2.1955,
|
| 2122 |
+
"step": 3150
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 0.0,
|
| 2126 |
+
"learning_rate": 0.0002,
|
| 2127 |
+
"loss": 2.1781,
|
| 2128 |
+
"step": 3200
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.0,
|
| 2132 |
+
"learning_rate": 0.0002,
|
| 2133 |
+
"loss": 2.1431,
|
| 2134 |
+
"step": 3250
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.0,
|
| 2138 |
+
"learning_rate": 0.0002,
|
| 2139 |
+
"loss": 2.1395,
|
| 2140 |
+
"step": 3300
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 0.0,
|
| 2144 |
+
"learning_rate": 0.0002,
|
| 2145 |
+
"loss": 2.1339,
|
| 2146 |
+
"step": 3350
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.0,
|
| 2150 |
+
"learning_rate": 0.0002,
|
| 2151 |
+
"loss": 2.1488,
|
| 2152 |
+
"step": 3400
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.0,
|
| 2156 |
+
"learning_rate": 0.0002,
|
| 2157 |
+
"loss": 2.1246,
|
| 2158 |
+
"step": 3450
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.0,
|
| 2162 |
+
"learning_rate": 0.0002,
|
| 2163 |
+
"loss": 2.1307,
|
| 2164 |
+
"step": 3500
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 0.0,
|
| 2168 |
+
"eval_loss": 2.2042970657348633,
|
| 2169 |
+
"eval_runtime": 34108.0847,
|
| 2170 |
+
"eval_samples_per_second": 2.969,
|
| 2171 |
+
"eval_steps_per_second": 0.742,
|
| 2172 |
+
"step": 3500
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.0,
|
| 2176 |
+
"learning_rate": 0.0002,
|
| 2177 |
+
"loss": 2.1207,
|
| 2178 |
+
"step": 3550
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 0.0,
|
| 2182 |
+
"learning_rate": 0.0002,
|
| 2183 |
+
"loss": 2.1247,
|
| 2184 |
+
"step": 3600
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.0,
|
| 2188 |
+
"learning_rate": 0.0002,
|
| 2189 |
+
"loss": 2.1225,
|
| 2190 |
+
"step": 3650
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 0.0,
|
| 2194 |
+
"learning_rate": 0.0002,
|
| 2195 |
+
"loss": 2.0978,
|
| 2196 |
+
"step": 3700
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 0.0,
|
| 2200 |
+
"learning_rate": 0.0002,
|
| 2201 |
+
"loss": 2.1168,
|
| 2202 |
+
"step": 3750
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.0,
|
| 2206 |
+
"learning_rate": 0.0002,
|
| 2207 |
+
"loss": 2.1122,
|
| 2208 |
+
"step": 3800
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.0,
|
| 2212 |
+
"learning_rate": 0.0002,
|
| 2213 |
+
"loss": 2.1046,
|
| 2214 |
+
"step": 3850
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.0,
|
| 2218 |
+
"learning_rate": 0.0002,
|
| 2219 |
+
"loss": 2.1208,
|
| 2220 |
+
"step": 3900
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 0.0,
|
| 2224 |
+
"learning_rate": 0.0002,
|
| 2225 |
+
"loss": 2.1206,
|
| 2226 |
+
"step": 3950
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 0.0,
|
| 2230 |
+
"learning_rate": 0.0002,
|
| 2231 |
+
"loss": 2.1128,
|
| 2232 |
+
"step": 4000
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 0.0,
|
| 2236 |
+
"eval_loss": 2.1652708053588867,
|
| 2237 |
+
"eval_runtime": 34110.436,
|
| 2238 |
+
"eval_samples_per_second": 2.969,
|
| 2239 |
+
"eval_steps_per_second": 0.742,
|
| 2240 |
+
"step": 4000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.0,
|
| 2244 |
+
"learning_rate": 0.0002,
|
| 2245 |
+
"loss": 2.0952,
|
| 2246 |
+
"step": 4050
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.0,
|
| 2250 |
+
"learning_rate": 0.0002,
|
| 2251 |
+
"loss": 2.0932,
|
| 2252 |
+
"step": 4100
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.0,
|
| 2256 |
+
"learning_rate": 0.0002,
|
| 2257 |
+
"loss": 2.0884,
|
| 2258 |
+
"step": 4150
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.0,
|
| 2262 |
+
"learning_rate": 0.0002,
|
| 2263 |
+
"loss": 2.0733,
|
| 2264 |
+
"step": 4200
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.0,
|
| 2268 |
+
"learning_rate": 0.0002,
|
| 2269 |
+
"loss": 2.0889,
|
| 2270 |
+
"step": 4250
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.0,
|
| 2274 |
+
"learning_rate": 0.0002,
|
| 2275 |
+
"loss": 2.0845,
|
| 2276 |
+
"step": 4300
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.0,
|
| 2280 |
+
"learning_rate": 0.0002,
|
| 2281 |
+
"loss": 2.0734,
|
| 2282 |
+
"step": 4350
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.0,
|
| 2286 |
+
"learning_rate": 0.0002,
|
| 2287 |
+
"loss": 2.0829,
|
| 2288 |
+
"step": 4400
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.0,
|
| 2292 |
+
"learning_rate": 0.0002,
|
| 2293 |
+
"loss": 2.0784,
|
| 2294 |
+
"step": 4450
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.0,
|
| 2298 |
+
"learning_rate": 0.0002,
|
| 2299 |
+
"loss": 2.0669,
|
| 2300 |
+
"step": 4500
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.0,
|
| 2304 |
+
"eval_loss": 2.144939661026001,
|
| 2305 |
+
"eval_runtime": 34106.0495,
|
| 2306 |
+
"eval_samples_per_second": 2.969,
|
| 2307 |
+
"eval_steps_per_second": 0.742,
|
| 2308 |
+
"step": 4500
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 0.0,
|
| 2312 |
+
"learning_rate": 0.0002,
|
| 2313 |
+
"loss": 2.0678,
|
| 2314 |
+
"step": 4550
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.0,
|
| 2318 |
+
"learning_rate": 0.0002,
|
| 2319 |
+
"loss": 2.0704,
|
| 2320 |
+
"step": 4600
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.0,
|
| 2324 |
+
"learning_rate": 0.0002,
|
| 2325 |
+
"loss": 2.0714,
|
| 2326 |
+
"step": 4650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.0,
|
| 2330 |
+
"learning_rate": 0.0002,
|
| 2331 |
+
"loss": 2.0661,
|
| 2332 |
+
"step": 4700
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.0,
|
| 2336 |
+
"learning_rate": 0.0002,
|
| 2337 |
+
"loss": 2.0707,
|
| 2338 |
+
"step": 4750
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 0.0,
|
| 2342 |
+
"learning_rate": 0.0002,
|
| 2343 |
+
"loss": 2.0685,
|
| 2344 |
+
"step": 4800
|
| 2345 |
+
},
|
| 2346 |
+
{
|
| 2347 |
+
"epoch": 0.0,
|
| 2348 |
+
"learning_rate": 0.0002,
|
| 2349 |
+
"loss": 2.0706,
|
| 2350 |
+
"step": 4850
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.0,
|
| 2354 |
+
"learning_rate": 0.0002,
|
| 2355 |
+
"loss": 2.0753,
|
| 2356 |
+
"step": 4900
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.0,
|
| 2360 |
+
"learning_rate": 0.0002,
|
| 2361 |
+
"loss": 2.056,
|
| 2362 |
+
"step": 4950
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.0,
|
| 2366 |
+
"learning_rate": 0.0002,
|
| 2367 |
+
"loss": 2.0646,
|
| 2368 |
+
"step": 5000
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.0,
|
| 2372 |
+
"eval_loss": 2.1237690448760986,
|
| 2373 |
+
"eval_runtime": 34108.4877,
|
| 2374 |
+
"eval_samples_per_second": 2.969,
|
| 2375 |
+
"eval_steps_per_second": 0.742,
|
| 2376 |
+
"step": 5000
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.0,
|
| 2380 |
+
"learning_rate": 0.0002,
|
| 2381 |
+
"loss": 2.053,
|
| 2382 |
+
"step": 5050
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.0,
|
| 2386 |
+
"learning_rate": 0.0002,
|
| 2387 |
+
"loss": 2.0622,
|
| 2388 |
+
"step": 5100
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.0,
|
| 2392 |
+
"learning_rate": 0.0002,
|
| 2393 |
+
"loss": 2.0415,
|
| 2394 |
+
"step": 5150
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 0.0,
|
| 2398 |
+
"learning_rate": 0.0002,
|
| 2399 |
+
"loss": 2.0561,
|
| 2400 |
+
"step": 5200
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 0.0,
|
| 2404 |
+
"learning_rate": 0.0002,
|
| 2405 |
+
"loss": 2.0517,
|
| 2406 |
+
"step": 5250
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.0,
|
| 2410 |
+
"learning_rate": 0.0002,
|
| 2411 |
+
"loss": 2.0559,
|
| 2412 |
+
"step": 5300
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 0.0,
|
| 2416 |
+
"learning_rate": 0.0002,
|
| 2417 |
+
"loss": 2.0417,
|
| 2418 |
+
"step": 5350
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.0,
|
| 2422 |
+
"learning_rate": 0.0002,
|
| 2423 |
+
"loss": 2.0435,
|
| 2424 |
+
"step": 5400
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.0,
|
| 2428 |
+
"learning_rate": 0.0002,
|
| 2429 |
+
"loss": 2.0533,
|
| 2430 |
+
"step": 5450
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 0.0,
|
| 2434 |
+
"learning_rate": 0.0002,
|
| 2435 |
+
"loss": 2.0388,
|
| 2436 |
+
"step": 5500
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 0.0,
|
| 2440 |
+
"eval_loss": 2.109766960144043,
|
| 2441 |
+
"eval_runtime": 34100.9613,
|
| 2442 |
+
"eval_samples_per_second": 2.97,
|
| 2443 |
+
"eval_steps_per_second": 0.742,
|
| 2444 |
+
"step": 5500
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.0,
|
| 2448 |
+
"learning_rate": 0.0002,
|
| 2449 |
+
"loss": 2.0524,
|
| 2450 |
+
"step": 5550
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 0.0,
|
| 2454 |
+
"learning_rate": 0.0002,
|
| 2455 |
+
"loss": 2.0521,
|
| 2456 |
+
"step": 5600
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.0,
|
| 2460 |
+
"learning_rate": 0.0002,
|
| 2461 |
+
"loss": 2.0356,
|
| 2462 |
+
"step": 5650
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.0,
|
| 2466 |
+
"learning_rate": 0.0002,
|
| 2467 |
+
"loss": 2.0565,
|
| 2468 |
+
"step": 5700
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 0.0,
|
| 2472 |
+
"learning_rate": 0.0002,
|
| 2473 |
+
"loss": 2.0341,
|
| 2474 |
+
"step": 5750
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.0,
|
| 2478 |
+
"learning_rate": 0.0002,
|
| 2479 |
+
"loss": 2.041,
|
| 2480 |
+
"step": 5800
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.0,
|
| 2484 |
+
"learning_rate": 0.0002,
|
| 2485 |
+
"loss": 2.0378,
|
| 2486 |
+
"step": 5850
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.0,
|
| 2490 |
+
"learning_rate": 0.0002,
|
| 2491 |
+
"loss": 2.0388,
|
| 2492 |
+
"step": 5900
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 0.0,
|
| 2496 |
+
"learning_rate": 0.0002,
|
| 2497 |
+
"loss": 2.0456,
|
| 2498 |
+
"step": 5950
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.0,
|
| 2502 |
+
"learning_rate": 0.0002,
|
| 2503 |
+
"loss": 2.0391,
|
| 2504 |
+
"step": 6000
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 0.0,
|
| 2508 |
+
"eval_loss": 2.0924971103668213,
|
| 2509 |
+
"eval_runtime": 34094.327,
|
| 2510 |
+
"eval_samples_per_second": 2.97,
|
| 2511 |
+
"eval_steps_per_second": 0.743,
|
| 2512 |
+
"step": 6000
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 0.0,
|
| 2516 |
+
"learning_rate": 0.0002,
|
| 2517 |
+
"loss": 2.0364,
|
| 2518 |
+
"step": 6050
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 0.0,
|
| 2522 |
+
"learning_rate": 0.0002,
|
| 2523 |
+
"loss": 2.028,
|
| 2524 |
+
"step": 6100
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 0.0,
|
| 2528 |
+
"learning_rate": 0.0002,
|
| 2529 |
+
"loss": 2.0255,
|
| 2530 |
+
"step": 6150
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.0,
|
| 2534 |
+
"learning_rate": 0.0002,
|
| 2535 |
+
"loss": 2.0049,
|
| 2536 |
+
"step": 6200
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.0,
|
| 2540 |
+
"learning_rate": 0.0002,
|
| 2541 |
+
"loss": 2.0214,
|
| 2542 |
+
"step": 6250
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 0.0,
|
| 2546 |
+
"learning_rate": 0.0002,
|
| 2547 |
+
"loss": 2.0303,
|
| 2548 |
+
"step": 6300
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 0.0,
|
| 2552 |
+
"learning_rate": 0.0002,
|
| 2553 |
+
"loss": 2.0216,
|
| 2554 |
+
"step": 6350
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 0.0,
|
| 2558 |
+
"learning_rate": 0.0002,
|
| 2559 |
+
"loss": 2.0278,
|
| 2560 |
+
"step": 6400
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 0.0,
|
| 2564 |
+
"learning_rate": 0.0002,
|
| 2565 |
+
"loss": 2.04,
|
| 2566 |
+
"step": 6450
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 0.0,
|
| 2570 |
+
"learning_rate": 0.0002,
|
| 2571 |
+
"loss": 2.0146,
|
| 2572 |
+
"step": 6500
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.0,
|
| 2576 |
+
"eval_loss": 2.082850217819214,
|
| 2577 |
+
"eval_runtime": 34130.627,
|
| 2578 |
+
"eval_samples_per_second": 2.967,
|
| 2579 |
+
"eval_steps_per_second": 0.742,
|
| 2580 |
+
"step": 6500
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 0.0,
|
| 2584 |
+
"learning_rate": 0.0002,
|
| 2585 |
+
"loss": 2.0299,
|
| 2586 |
+
"step": 6550
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.0,
|
| 2590 |
+
"learning_rate": 0.0002,
|
| 2591 |
+
"loss": 2.0249,
|
| 2592 |
+
"step": 6600
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.0,
|
| 2596 |
+
"learning_rate": 0.0002,
|
| 2597 |
+
"loss": 2.0169,
|
| 2598 |
+
"step": 6650
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 0.0,
|
| 2602 |
+
"learning_rate": 0.0002,
|
| 2603 |
+
"loss": 2.0043,
|
| 2604 |
+
"step": 6700
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 0.0,
|
| 2608 |
+
"learning_rate": 0.0002,
|
| 2609 |
+
"loss": 2.0169,
|
| 2610 |
+
"step": 6750
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 0.0,
|
| 2614 |
+
"learning_rate": 0.0002,
|
| 2615 |
+
"loss": 2.0146,
|
| 2616 |
+
"step": 6800
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 0.0,
|
| 2620 |
+
"learning_rate": 0.0002,
|
| 2621 |
+
"loss": 2.0178,
|
| 2622 |
+
"step": 6850
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 0.0,
|
| 2626 |
+
"learning_rate": 0.0002,
|
| 2627 |
+
"loss": 2.017,
|
| 2628 |
+
"step": 6900
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.0,
|
| 2632 |
+
"learning_rate": 0.0002,
|
| 2633 |
+
"loss": 2.0011,
|
| 2634 |
+
"step": 6950
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.0,
|
| 2638 |
+
"learning_rate": 0.0002,
|
| 2639 |
+
"loss": 1.9961,
|
| 2640 |
+
"step": 7000
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 0.0,
|
| 2644 |
+
"eval_loss": 2.0665175914764404,
|
| 2645 |
+
"eval_runtime": 34103.0381,
|
| 2646 |
+
"eval_samples_per_second": 2.97,
|
| 2647 |
+
"eval_steps_per_second": 0.742,
|
| 2648 |
+
"step": 7000
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.0,
|
| 2652 |
+
"learning_rate": 0.0002,
|
| 2653 |
+
"loss": 2.0201,
|
| 2654 |
+
"step": 7050
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.0,
|
| 2658 |
+
"learning_rate": 0.0002,
|
| 2659 |
+
"loss": 2.0165,
|
| 2660 |
+
"step": 7100
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.0,
|
| 2664 |
+
"learning_rate": 0.0002,
|
| 2665 |
+
"loss": 2.0071,
|
| 2666 |
+
"step": 7150
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 0.0,
|
| 2670 |
+
"learning_rate": 0.0002,
|
| 2671 |
+
"loss": 2.0038,
|
| 2672 |
+
"step": 7200
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.0,
|
| 2676 |
+
"learning_rate": 0.0002,
|
| 2677 |
+
"loss": 2.0074,
|
| 2678 |
+
"step": 7250
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.0,
|
| 2682 |
+
"learning_rate": 0.0002,
|
| 2683 |
+
"loss": 2.0009,
|
| 2684 |
+
"step": 7300
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.0,
|
| 2688 |
+
"learning_rate": 0.0002,
|
| 2689 |
+
"loss": 1.9877,
|
| 2690 |
+
"step": 7350
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.0,
|
| 2694 |
+
"learning_rate": 0.0002,
|
| 2695 |
+
"loss": 2.006,
|
| 2696 |
+
"step": 7400
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.0,
|
| 2700 |
+
"learning_rate": 0.0002,
|
| 2701 |
+
"loss": 1.9915,
|
| 2702 |
+
"step": 7450
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 0.0,
|
| 2706 |
+
"learning_rate": 0.0002,
|
| 2707 |
+
"loss": 1.993,
|
| 2708 |
+
"step": 7500
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 0.0,
|
| 2712 |
+
"eval_loss": 2.0603718757629395,
|
| 2713 |
+
"eval_runtime": 34086.5352,
|
| 2714 |
+
"eval_samples_per_second": 2.971,
|
| 2715 |
+
"eval_steps_per_second": 0.743,
|
| 2716 |
+
"step": 7500
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 0.0,
|
| 2720 |
+
"learning_rate": 0.0002,
|
| 2721 |
+
"loss": 1.9975,
|
| 2722 |
+
"step": 7550
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 0.0,
|
| 2726 |
+
"learning_rate": 0.0002,
|
| 2727 |
+
"loss": 1.994,
|
| 2728 |
+
"step": 7600
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 0.0,
|
| 2732 |
+
"learning_rate": 0.0002,
|
| 2733 |
+
"loss": 2.007,
|
| 2734 |
+
"step": 7650
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 0.0,
|
| 2738 |
+
"learning_rate": 0.0002,
|
| 2739 |
+
"loss": 2.0034,
|
| 2740 |
+
"step": 7700
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.0,
|
| 2744 |
+
"learning_rate": 0.0002,
|
| 2745 |
+
"loss": 2.0081,
|
| 2746 |
+
"step": 7750
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.0,
|
| 2750 |
+
"learning_rate": 0.0002,
|
| 2751 |
+
"loss": 1.9855,
|
| 2752 |
+
"step": 7800
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 0.0,
|
| 2756 |
+
"learning_rate": 0.0002,
|
| 2757 |
+
"loss": 2.0026,
|
| 2758 |
+
"step": 7850
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 0.0,
|
| 2762 |
+
"learning_rate": 0.0002,
|
| 2763 |
+
"loss": 2.0022,
|
| 2764 |
+
"step": 7900
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 0.01,
|
| 2768 |
+
"learning_rate": 0.0002,
|
| 2769 |
+
"loss": 2.0013,
|
| 2770 |
+
"step": 7950
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 0.01,
|
| 2774 |
+
"learning_rate": 0.0002,
|
| 2775 |
+
"loss": 2.0073,
|
| 2776 |
+
"step": 8000
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.01,
|
| 2780 |
+
"eval_loss": 2.050844669342041,
|
| 2781 |
+
"eval_runtime": 34104.8601,
|
| 2782 |
+
"eval_samples_per_second": 2.969,
|
| 2783 |
+
"eval_steps_per_second": 0.742,
|
| 2784 |
+
"step": 8000
|
| 2785 |
}
|
| 2786 |
],
|
| 2787 |
"max_steps": 10000,
|
| 2788 |
"num_train_epochs": 1,
|
| 2789 |
+
"total_flos": 2.484742130335789e+19,
|
| 2790 |
"trial_name": null,
|
| 2791 |
"trial_params": null
|
| 2792 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:151c1e0a38693ccd36dfbee906fcda3901de363201e50826113290f62066924b
|
| 3 |
+
size 5819
|