Training in progress, step 430000
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 sha256:16c1077fabcb1358439d252687cf60a730df0b701cd9dba8cd4c2f8e627b961e
|
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:f73a9cf3e0ad37667ebac9ffad4a5046707edf9dc63961cc233f7e5f32a5cedd
|
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 sha256:59fa4ae65974b3438095f9910bd4e75018d4e75640ba0327b8df3608b965aa7d
|
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 sha256:8f7cfb179a47776b0e99eb314ae99a6c30f467da391e460d722638c8a52161d5
|
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:f983a8fc63d221ac8a5d25c1cbf0cb6772efa7a65e038628e08411d3aa7730c2
|
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 sha256:9c3a75e20d8714a4739623f5b1ce27c9d16638711b2b8e59d2b7374a3f862373
|
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 sha256:5e0586ba7be6f06005dd1a877b0040f675f507fbf3970cf39b275043a5803164
|
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 sha256:1b395aacc1b88911171643b9c61fb83d1c016edb52eee71692131a6541c07fa0
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5106,6 +5106,66 @@
|
|
5106 |
"learning_rate": 1.7662523268144196e-05,
|
5107 |
"loss": 0.3195,
|
5108 |
"step": 425000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5109 |
}
|
5110 |
],
|
5111 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.31914622003217,
|
5 |
+
"global_step": 430000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5106 |
"learning_rate": 1.7662523268144196e-05,
|
5107 |
"loss": 0.3195,
|
5108 |
"step": 425000
|
5109 |
+
},
|
5110 |
+
{
|
5111 |
+
"epoch": 7.24,
|
5112 |
+
"learning_rate": 1.7562790245271302e-05,
|
5113 |
+
"loss": 0.3194,
|
5114 |
+
"step": 425500
|
5115 |
+
},
|
5116 |
+
{
|
5117 |
+
"epoch": 7.25,
|
5118 |
+
"learning_rate": 1.746367345245176e-05,
|
5119 |
+
"loss": 0.3194,
|
5120 |
+
"step": 426000
|
5121 |
+
},
|
5122 |
+
{
|
5123 |
+
"epoch": 7.26,
|
5124 |
+
"learning_rate": 1.7365173867928312e-05,
|
5125 |
+
"loss": 0.3194,
|
5126 |
+
"step": 426500
|
5127 |
+
},
|
5128 |
+
{
|
5129 |
+
"epoch": 7.27,
|
5130 |
+
"learning_rate": 1.726729246385207e-05,
|
5131 |
+
"loss": 0.3194,
|
5132 |
+
"step": 427000
|
5133 |
+
},
|
5134 |
+
{
|
5135 |
+
"epoch": 7.28,
|
5136 |
+
"learning_rate": 1.7170224112240894e-05,
|
5137 |
+
"loss": 0.3192,
|
5138 |
+
"step": 427500
|
5139 |
+
},
|
5140 |
+
{
|
5141 |
+
"epoch": 7.29,
|
5142 |
+
"learning_rate": 1.707358071993139e-05,
|
5143 |
+
"loss": 0.3192,
|
5144 |
+
"step": 428000
|
5145 |
+
},
|
5146 |
+
{
|
5147 |
+
"epoch": 7.29,
|
5148 |
+
"learning_rate": 1.6977558385975733e-05,
|
5149 |
+
"loss": 0.3192,
|
5150 |
+
"step": 428500
|
5151 |
+
},
|
5152 |
+
{
|
5153 |
+
"epoch": 7.3,
|
5154 |
+
"learning_rate": 1.6882158058075643e-05,
|
5155 |
+
"loss": 0.3193,
|
5156 |
+
"step": 429000
|
5157 |
+
},
|
5158 |
+
{
|
5159 |
+
"epoch": 7.31,
|
5160 |
+
"learning_rate": 1.6787569610229864e-05,
|
5161 |
+
"loss": 0.3193,
|
5162 |
+
"step": 429500
|
5163 |
+
},
|
5164 |
+
{
|
5165 |
+
"epoch": 7.32,
|
5166 |
+
"learning_rate": 1.6693414864285253e-05,
|
5167 |
+
"loss": 0.3193,
|
5168 |
+
"step": 430000
|
5169 |
}
|
5170 |
],
|
5171 |
"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:f73a9cf3e0ad37667ebac9ffad4a5046707edf9dc63961cc233f7e5f32a5cedd
|
3 |
size 201355195
|