Training in progress, step 185000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- 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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60070dd891e1643521307f27b60bcad5d8609aa3b4604c193773b0b7ebaccf3f
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69efe896f1a722db56bb95e38573a2695ce6bbcf1295b2053cc3e7dbc1e9dbc6
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e662b52fb4d85a9fa2766fe418a962af198257860e9f239171a0a162abe49c4
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1abaa2d9c68626c86b9b75e243efb188cc5d09f126eb4436d455b42fc7341262
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c54d53af0cddeebd03bbcd9939967852cca2b81b7504188340e79322a08fe57b
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3f630809085edcfd6d205212d799c0f53d27219090a684935d835d62897b69
|
3 |
size 14503
|
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:b6ceb7e099c62b9903eb6c08b3d9818597b6c5df5bf025be87708229161c3c70
|
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 sha256:00ee8f83d0a3e74bcab95eab146501dc1c273f922ff52225a2175f1abf3b6e83
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2166,6 +2166,66 @@
|
|
2166 |
"learning_rate": 0.0001098324049865014,
|
2167 |
"loss": 0.3392,
|
2168 |
"step": 180000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2169 |
}
|
2170 |
],
|
2171 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.148936170212766,
|
5 |
+
"global_step": 185000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2166 |
"learning_rate": 0.0001098324049865014,
|
2167 |
"loss": 0.3392,
|
2168 |
"step": 180000
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 3.07,
|
2172 |
+
"learning_rate": 0.00010963331743691472,
|
2173 |
+
"loss": 0.3387,
|
2174 |
+
"step": 180500
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 3.08,
|
2178 |
+
"learning_rate": 0.00010943393741844842,
|
2179 |
+
"loss": 0.338,
|
2180 |
+
"step": 181000
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 3.09,
|
2184 |
+
"learning_rate": 0.00010923426689890275,
|
2185 |
+
"loss": 0.3376,
|
2186 |
+
"step": 181500
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 3.1,
|
2190 |
+
"learning_rate": 0.00010903430784894515,
|
2191 |
+
"loss": 0.3373,
|
2192 |
+
"step": 182000
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 3.11,
|
2196 |
+
"learning_rate": 0.00010883406224209071,
|
2197 |
+
"loss": 0.3371,
|
2198 |
+
"step": 182500
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 3.11,
|
2202 |
+
"learning_rate": 0.00010863353205468268,
|
2203 |
+
"loss": 0.3369,
|
2204 |
+
"step": 183000
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 3.12,
|
2208 |
+
"learning_rate": 0.00010843271926587313,
|
2209 |
+
"loss": 0.3368,
|
2210 |
+
"step": 183500
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 3.13,
|
2214 |
+
"learning_rate": 0.00010823162585760317,
|
2215 |
+
"loss": 0.3365,
|
2216 |
+
"step": 184000
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 3.14,
|
2220 |
+
"learning_rate": 0.00010803025381458359,
|
2221 |
+
"loss": 0.3364,
|
2222 |
+
"step": 184500
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 3.15,
|
2226 |
+
"learning_rate": 0.0001078286051242751,
|
2227 |
+
"loss": 0.3361,
|
2228 |
+
"step": 185000
|
2229 |
}
|
2230 |
],
|
2231 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69efe896f1a722db56bb95e38573a2695ce6bbcf1295b2053cc3e7dbc1e9dbc6
|
3 |
size 201355195
|