Training in progress, step 180000
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:e00dfb6570e6058a13ab78da8572c823f929678a4417da77916090ee4d4184d7
|
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:be86d2bff33fa6899dcbcbb8c1514ad5ebc34e19a6d45effffd88614d531f8a2
|
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 sha256:30f8855e289818b480254745c6cad28b0f999810f519eb5a6ff7a0aea3f235bd
|
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 sha256:62e2e5f68f52a3a8726fcf3e0e6d3f44eb7519f8706c2ed8be8ab76a4686fb8a
|
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 sha256:93ec12a0879b27c92b709a91bfbb990c2d77c5333a9a37e084db0388a27546be
|
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 sha256:573df7989752c7cf0f2122cd80a79b0e2f80ed5dbccbfe72aa70ea81b7853582
|
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 sha256:0b6d639fc9be21ec690ba0f6589e373d572939ddb4c01a4c98a550989e369f97
|
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 sha256:9f01adbf075cdc5fa0718f79c0326e3cd028644bccc4e6c2bb8efca7fb627ec8
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2106,6 +2106,66 @@
|
|
2106 |
"learning_rate": 0.00011180676386671593,
|
2107 |
"loss": 0.3389,
|
2108 |
"step": 175000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2109 |
}
|
2110 |
],
|
2111 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.063829244006434,
|
5 |
+
"global_step": 180000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2106 |
"learning_rate": 0.00011180676386671593,
|
2107 |
"loss": 0.3389,
|
2108 |
"step": 175000
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 2.99,
|
2112 |
+
"learning_rate": 0.00011161070859032411,
|
2113 |
+
"loss": 0.3387,
|
2114 |
+
"step": 175500
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 3.0,
|
2118 |
+
"learning_rate": 0.00011141434132900025,
|
2119 |
+
"loss": 0.3385,
|
2120 |
+
"step": 176000
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 3.0,
|
2124 |
+
"learning_rate": 0.00011121805768356343,
|
2125 |
+
"loss": 0.339,
|
2126 |
+
"step": 176500
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 3.01,
|
2130 |
+
"learning_rate": 0.00011102107288390457,
|
2131 |
+
"loss": 0.3386,
|
2132 |
+
"step": 177000
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 3.02,
|
2136 |
+
"learning_rate": 0.00011082378191878007,
|
2137 |
+
"loss": 0.3383,
|
2138 |
+
"step": 177500
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 3.03,
|
2142 |
+
"learning_rate": 0.000110626582228053,
|
2143 |
+
"loss": 0.3385,
|
2144 |
+
"step": 178000
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 3.04,
|
2148 |
+
"learning_rate": 0.00011042908147320174,
|
2149 |
+
"loss": 0.3391,
|
2150 |
+
"step": 178500
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 3.05,
|
2154 |
+
"learning_rate": 0.00011023128159568977,
|
2155 |
+
"loss": 0.339,
|
2156 |
+
"step": 179000
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 3.06,
|
2160 |
+
"learning_rate": 0.00011003278725476702,
|
2161 |
+
"loss": 0.3386,
|
2162 |
+
"step": 179500
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 3.06,
|
2166 |
+
"learning_rate": 0.00010983399650235882,
|
2167 |
+
"loss": 0.3384,
|
2168 |
+
"step": 180000
|
2169 |
}
|
2170 |
],
|
2171 |
"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:be86d2bff33fa6899dcbcbb8c1514ad5ebc34e19a6d45effffd88614d531f8a2
|
3 |
size 201355195
|