Training in progress, step 425000
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 sha256:262573dfa3c175a31e437def578e03a030f619bcf84aaf06469d537db822cd63
|
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 sha256:7c881a193063a30f277d137f6b68ee79d52d044eb176c66d9293045b5bce7ab6
|
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 sha256:1c90b6d5d37ff4ed282ab8d055be49375c8c871031ef729a79ac7adbd6d8e237
|
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 sha256:3d715c8111fb1a4c0d1e8edb0ea76065b3204ac7fcf062a175701ea68c51e8b0
|
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 sha256:4c0950431a22fce488bde575f64fb0ca22c7320874079e268752634e13169182
|
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 sha256:2b76f9112400485d1ac8f7410e8fa67bdb51c000af0db960442d060aa1de612b
|
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 sha256:5f3df2c4b3f15c92d09a390527c6a25fa4a7e1a15ed79c4f76e81993d5b3f633
|
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 sha256:2adb2fa2efa0efdcce92f4f10b244a995a1277b5cb566d8f71d99cf024669e57
|
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,
|
@@ -5046,6 +5046,66 @@
|
|
5046 |
"learning_rate": 1.8692889753936567e-05,
|
5047 |
"loss": 0.3195,
|
5048 |
"step": 420000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5049 |
}
|
5050 |
],
|
5051 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.234040561356925,
|
5 |
+
"global_step": 425000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5046 |
"learning_rate": 1.8692889753936567e-05,
|
5047 |
"loss": 0.3195,
|
5048 |
"step": 420000
|
5049 |
+
},
|
5050 |
+
{
|
5051 |
+
"epoch": 7.16,
|
5052 |
+
"learning_rate": 1.858705320063063e-05,
|
5053 |
+
"loss": 0.3193,
|
5054 |
+
"step": 420500
|
5055 |
+
},
|
5056 |
+
{
|
5057 |
+
"epoch": 7.17,
|
5058 |
+
"learning_rate": 1.84818227683162e-05,
|
5059 |
+
"loss": 0.3197,
|
5060 |
+
"step": 421000
|
5061 |
+
},
|
5062 |
+
{
|
5063 |
+
"epoch": 7.17,
|
5064 |
+
"learning_rate": 1.837719949557515e-05,
|
5065 |
+
"loss": 0.3195,
|
5066 |
+
"step": 421500
|
5067 |
+
},
|
5068 |
+
{
|
5069 |
+
"epoch": 7.18,
|
5070 |
+
"learning_rate": 1.8273391837498994e-05,
|
5071 |
+
"loss": 0.3193,
|
5072 |
+
"step": 422000
|
5073 |
+
},
|
5074 |
+
{
|
5075 |
+
"epoch": 7.19,
|
5076 |
+
"learning_rate": 1.816998475621245e-05,
|
5077 |
+
"loss": 0.3193,
|
5078 |
+
"step": 422500
|
5079 |
+
},
|
5080 |
+
{
|
5081 |
+
"epoch": 7.2,
|
5082 |
+
"learning_rate": 1.806718791221458e-05,
|
5083 |
+
"loss": 0.3195,
|
5084 |
+
"step": 423000
|
5085 |
+
},
|
5086 |
+
{
|
5087 |
+
"epoch": 7.21,
|
5088 |
+
"learning_rate": 1.796500232006872e-05,
|
5089 |
+
"loss": 0.3195,
|
5090 |
+
"step": 423500
|
5091 |
+
},
|
5092 |
+
{
|
5093 |
+
"epoch": 7.22,
|
5094 |
+
"learning_rate": 1.786342898830544e-05,
|
5095 |
+
"loss": 0.3195,
|
5096 |
+
"step": 424000
|
5097 |
+
},
|
5098 |
+
{
|
5099 |
+
"epoch": 7.23,
|
5100 |
+
"learning_rate": 1.776246891941248e-05,
|
5101 |
+
"loss": 0.3192,
|
5102 |
+
"step": 424500
|
5103 |
+
},
|
5104 |
+
{
|
5105 |
+
"epoch": 7.23,
|
5106 |
+
"learning_rate": 1.7662523268144196e-05,
|
5107 |
+
"loss": 0.3195,
|
5108 |
+
"step": 425000
|
5109 |
}
|
5110 |
],
|
5111 |
"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 sha256:7c881a193063a30f277d137f6b68ee79d52d044eb176c66d9293045b5bce7ab6
|
3 |
size 201355195
|