Training in progress, step 9000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +766 -2
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738367848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6621097a97062a5102e67fc29c2bb01fb6549601c085f8f26cce5a1634634ee
|
| 3 |
size 738367848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1476823354
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e77fb5c2bafed3ee939a6057af4a25e874ed04b715f60fc720a59e7b1d77f2d
|
| 3 |
size 1476823354
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98b04d6c2e8863bbad65481224e2bdca0706f808989765d4a58e7054f3e5dac5
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ae3ef9777e30c36dff6498b006da1eb150bccee38de6cf7669f386fc977289b
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:680cdbb58729160d28a1f3cc615b2c063f7c72522976ed4abf05aaf19f07acb8
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c050129d4c78b5963b9d24ede87255fc330819afb083e880a4ab6391077de6
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95927238adba95b6358a20dd1852c4905066c03f5b6f24857e2f6c82bb9f0977
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7431d23b9b61660f73b469a3e73ae62f971d8bd2ced76f239fd78258fe40a803
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bdcc55ac2d89ab7fac22a6eb989c2be897f201356182513ed90bc09a5326786
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aae3da8149789ffc686c284e85fc275d996d793ce0edd8fa2949c1a21a4de8c9
|
| 3 |
size 15984
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:708acca42b057f68ded76410daaf0ceaf94be65729403bb2d72b15a907559585
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -6119,6 +6119,770 @@
|
|
| 6119 |
"eval_spearman_manhattan": 0.7409361299302836,
|
| 6120 |
"eval_steps_per_second": 8.407,
|
| 6121 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6122 |
}
|
| 6123 |
],
|
| 6124 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.434864104967197,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 6119 |
"eval_spearman_manhattan": 0.7409361299302836,
|
| 6120 |
"eval_steps_per_second": 8.407,
|
| 6121 |
"step": 8000
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 7.507029053420806,
|
| 6125 |
+
"grad_norm": 0.443439781665802,
|
| 6126 |
+
"learning_rate": 9.941352194350481e-06,
|
| 6127 |
+
"loss": 0.0301,
|
| 6128 |
+
"step": 8010
|
| 6129 |
+
},
|
| 6130 |
+
{
|
| 6131 |
+
"epoch": 7.516401124648548,
|
| 6132 |
+
"grad_norm": 0.5801528692245483,
|
| 6133 |
+
"learning_rate": 9.941278976116214e-06,
|
| 6134 |
+
"loss": 0.0379,
|
| 6135 |
+
"step": 8020
|
| 6136 |
+
},
|
| 6137 |
+
{
|
| 6138 |
+
"epoch": 7.525773195876289,
|
| 6139 |
+
"grad_norm": 0.9093418717384338,
|
| 6140 |
+
"learning_rate": 9.941205757881943e-06,
|
| 6141 |
+
"loss": 0.0376,
|
| 6142 |
+
"step": 8030
|
| 6143 |
+
},
|
| 6144 |
+
{
|
| 6145 |
+
"epoch": 7.5351452671040295,
|
| 6146 |
+
"grad_norm": 0.7593823671340942,
|
| 6147 |
+
"learning_rate": 9.941132539647674e-06,
|
| 6148 |
+
"loss": 0.0444,
|
| 6149 |
+
"step": 8040
|
| 6150 |
+
},
|
| 6151 |
+
{
|
| 6152 |
+
"epoch": 7.544517338331771,
|
| 6153 |
+
"grad_norm": 0.706062376499176,
|
| 6154 |
+
"learning_rate": 9.941059321413406e-06,
|
| 6155 |
+
"loss": 0.0365,
|
| 6156 |
+
"step": 8050
|
| 6157 |
+
},
|
| 6158 |
+
{
|
| 6159 |
+
"epoch": 7.553889409559512,
|
| 6160 |
+
"grad_norm": 0.9754658937454224,
|
| 6161 |
+
"learning_rate": 9.940986103179137e-06,
|
| 6162 |
+
"loss": 0.0333,
|
| 6163 |
+
"step": 8060
|
| 6164 |
+
},
|
| 6165 |
+
{
|
| 6166 |
+
"epoch": 7.563261480787254,
|
| 6167 |
+
"grad_norm": 0.8546915054321289,
|
| 6168 |
+
"learning_rate": 9.940912884944867e-06,
|
| 6169 |
+
"loss": 0.0365,
|
| 6170 |
+
"step": 8070
|
| 6171 |
+
},
|
| 6172 |
+
{
|
| 6173 |
+
"epoch": 7.572633552014995,
|
| 6174 |
+
"grad_norm": 1.0958435535430908,
|
| 6175 |
+
"learning_rate": 9.940839666710598e-06,
|
| 6176 |
+
"loss": 0.0371,
|
| 6177 |
+
"step": 8080
|
| 6178 |
+
},
|
| 6179 |
+
{
|
| 6180 |
+
"epoch": 7.582005623242736,
|
| 6181 |
+
"grad_norm": 0.9083812832832336,
|
| 6182 |
+
"learning_rate": 9.940766448476329e-06,
|
| 6183 |
+
"loss": 0.0355,
|
| 6184 |
+
"step": 8090
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 7.591377694470478,
|
| 6188 |
+
"grad_norm": 0.8183301091194153,
|
| 6189 |
+
"learning_rate": 9.94069323024206e-06,
|
| 6190 |
+
"loss": 0.0366,
|
| 6191 |
+
"step": 8100
|
| 6192 |
+
},
|
| 6193 |
+
{
|
| 6194 |
+
"epoch": 7.600749765698219,
|
| 6195 |
+
"grad_norm": 1.1571640968322754,
|
| 6196 |
+
"learning_rate": 9.94062001200779e-06,
|
| 6197 |
+
"loss": 0.0357,
|
| 6198 |
+
"step": 8110
|
| 6199 |
+
},
|
| 6200 |
+
{
|
| 6201 |
+
"epoch": 7.610121836925961,
|
| 6202 |
+
"grad_norm": 0.47001174092292786,
|
| 6203 |
+
"learning_rate": 9.940546793773523e-06,
|
| 6204 |
+
"loss": 0.0366,
|
| 6205 |
+
"step": 8120
|
| 6206 |
+
},
|
| 6207 |
+
{
|
| 6208 |
+
"epoch": 7.619493908153702,
|
| 6209 |
+
"grad_norm": 0.7864421010017395,
|
| 6210 |
+
"learning_rate": 9.940473575539254e-06,
|
| 6211 |
+
"loss": 0.0354,
|
| 6212 |
+
"step": 8130
|
| 6213 |
+
},
|
| 6214 |
+
{
|
| 6215 |
+
"epoch": 7.628865979381443,
|
| 6216 |
+
"grad_norm": 1.7657727003097534,
|
| 6217 |
+
"learning_rate": 9.940400357304984e-06,
|
| 6218 |
+
"loss": 0.0353,
|
| 6219 |
+
"step": 8140
|
| 6220 |
+
},
|
| 6221 |
+
{
|
| 6222 |
+
"epoch": 7.638238050609185,
|
| 6223 |
+
"grad_norm": 0.9494844079017639,
|
| 6224 |
+
"learning_rate": 9.940327139070715e-06,
|
| 6225 |
+
"loss": 0.0358,
|
| 6226 |
+
"step": 8150
|
| 6227 |
+
},
|
| 6228 |
+
{
|
| 6229 |
+
"epoch": 7.647610121836926,
|
| 6230 |
+
"grad_norm": 1.1095364093780518,
|
| 6231 |
+
"learning_rate": 9.940253920836446e-06,
|
| 6232 |
+
"loss": 0.0338,
|
| 6233 |
+
"step": 8160
|
| 6234 |
+
},
|
| 6235 |
+
{
|
| 6236 |
+
"epoch": 7.6569821930646675,
|
| 6237 |
+
"grad_norm": 0.5973043441772461,
|
| 6238 |
+
"learning_rate": 9.940180702602177e-06,
|
| 6239 |
+
"loss": 0.0332,
|
| 6240 |
+
"step": 8170
|
| 6241 |
+
},
|
| 6242 |
+
{
|
| 6243 |
+
"epoch": 7.6663542642924085,
|
| 6244 |
+
"grad_norm": 0.5820950865745544,
|
| 6245 |
+
"learning_rate": 9.940107484367907e-06,
|
| 6246 |
+
"loss": 0.0398,
|
| 6247 |
+
"step": 8180
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 7.6757263355201495,
|
| 6251 |
+
"grad_norm": 0.8826543688774109,
|
| 6252 |
+
"learning_rate": 9.94003426613364e-06,
|
| 6253 |
+
"loss": 0.0363,
|
| 6254 |
+
"step": 8190
|
| 6255 |
+
},
|
| 6256 |
+
{
|
| 6257 |
+
"epoch": 7.685098406747891,
|
| 6258 |
+
"grad_norm": 1.2651371955871582,
|
| 6259 |
+
"learning_rate": 9.93996104789937e-06,
|
| 6260 |
+
"loss": 0.041,
|
| 6261 |
+
"step": 8200
|
| 6262 |
+
},
|
| 6263 |
+
{
|
| 6264 |
+
"epoch": 7.694470477975632,
|
| 6265 |
+
"grad_norm": 0.4515238106250763,
|
| 6266 |
+
"learning_rate": 9.9398878296651e-06,
|
| 6267 |
+
"loss": 0.0375,
|
| 6268 |
+
"step": 8210
|
| 6269 |
+
},
|
| 6270 |
+
{
|
| 6271 |
+
"epoch": 7.703842549203374,
|
| 6272 |
+
"grad_norm": 1.2343902587890625,
|
| 6273 |
+
"learning_rate": 9.939814611430832e-06,
|
| 6274 |
+
"loss": 0.0362,
|
| 6275 |
+
"step": 8220
|
| 6276 |
+
},
|
| 6277 |
+
{
|
| 6278 |
+
"epoch": 7.713214620431115,
|
| 6279 |
+
"grad_norm": 0.9942644238471985,
|
| 6280 |
+
"learning_rate": 9.939741393196563e-06,
|
| 6281 |
+
"loss": 0.029,
|
| 6282 |
+
"step": 8230
|
| 6283 |
+
},
|
| 6284 |
+
{
|
| 6285 |
+
"epoch": 7.722586691658856,
|
| 6286 |
+
"grad_norm": 1.327783226966858,
|
| 6287 |
+
"learning_rate": 9.939668174962294e-06,
|
| 6288 |
+
"loss": 0.0392,
|
| 6289 |
+
"step": 8240
|
| 6290 |
+
},
|
| 6291 |
+
{
|
| 6292 |
+
"epoch": 7.731958762886598,
|
| 6293 |
+
"grad_norm": 1.4785791635513306,
|
| 6294 |
+
"learning_rate": 9.939594956728024e-06,
|
| 6295 |
+
"loss": 0.035,
|
| 6296 |
+
"step": 8250
|
| 6297 |
+
},
|
| 6298 |
+
{
|
| 6299 |
+
"epoch": 7.731958762886598,
|
| 6300 |
+
"eval_loss": 0.037988826632499695,
|
| 6301 |
+
"eval_pearson_cosine": 0.7700406312942505,
|
| 6302 |
+
"eval_pearson_dot": 0.7271457314491272,
|
| 6303 |
+
"eval_pearson_euclidean": 0.7288488745689392,
|
| 6304 |
+
"eval_pearson_manhattan": 0.7308281660079956,
|
| 6305 |
+
"eval_runtime": 23.4237,
|
| 6306 |
+
"eval_samples_per_second": 64.038,
|
| 6307 |
+
"eval_spearman_cosine": 0.7690641250527666,
|
| 6308 |
+
"eval_spearman_dot": 0.72759972168602,
|
| 6309 |
+
"eval_spearman_euclidean": 0.7335219335323239,
|
| 6310 |
+
"eval_spearman_manhattan": 0.7351665552942261,
|
| 6311 |
+
"eval_steps_per_second": 8.026,
|
| 6312 |
+
"step": 8250
|
| 6313 |
+
},
|
| 6314 |
+
{
|
| 6315 |
+
"epoch": 7.741330834114339,
|
| 6316 |
+
"grad_norm": 0.9368901252746582,
|
| 6317 |
+
"learning_rate": 9.939521738493755e-06,
|
| 6318 |
+
"loss": 0.0354,
|
| 6319 |
+
"step": 8260
|
| 6320 |
+
},
|
| 6321 |
+
{
|
| 6322 |
+
"epoch": 7.750702905342081,
|
| 6323 |
+
"grad_norm": 0.924701452255249,
|
| 6324 |
+
"learning_rate": 9.939448520259486e-06,
|
| 6325 |
+
"loss": 0.0308,
|
| 6326 |
+
"step": 8270
|
| 6327 |
+
},
|
| 6328 |
+
{
|
| 6329 |
+
"epoch": 7.760074976569822,
|
| 6330 |
+
"grad_norm": 0.6925562620162964,
|
| 6331 |
+
"learning_rate": 9.939375302025217e-06,
|
| 6332 |
+
"loss": 0.0379,
|
| 6333 |
+
"step": 8280
|
| 6334 |
+
},
|
| 6335 |
+
{
|
| 6336 |
+
"epoch": 7.769447047797563,
|
| 6337 |
+
"grad_norm": 1.1450366973876953,
|
| 6338 |
+
"learning_rate": 9.939302083790947e-06,
|
| 6339 |
+
"loss": 0.035,
|
| 6340 |
+
"step": 8290
|
| 6341 |
+
},
|
| 6342 |
+
{
|
| 6343 |
+
"epoch": 7.778819119025305,
|
| 6344 |
+
"grad_norm": 1.4248292446136475,
|
| 6345 |
+
"learning_rate": 9.93922886555668e-06,
|
| 6346 |
+
"loss": 0.0425,
|
| 6347 |
+
"step": 8300
|
| 6348 |
+
},
|
| 6349 |
+
{
|
| 6350 |
+
"epoch": 7.788191190253046,
|
| 6351 |
+
"grad_norm": 1.1555083990097046,
|
| 6352 |
+
"learning_rate": 9.93915564732241e-06,
|
| 6353 |
+
"loss": 0.035,
|
| 6354 |
+
"step": 8310
|
| 6355 |
+
},
|
| 6356 |
+
{
|
| 6357 |
+
"epoch": 7.7975632614807875,
|
| 6358 |
+
"grad_norm": 0.8950551152229309,
|
| 6359 |
+
"learning_rate": 9.93908242908814e-06,
|
| 6360 |
+
"loss": 0.0371,
|
| 6361 |
+
"step": 8320
|
| 6362 |
+
},
|
| 6363 |
+
{
|
| 6364 |
+
"epoch": 7.8069353327085285,
|
| 6365 |
+
"grad_norm": 0.9402216076850891,
|
| 6366 |
+
"learning_rate": 9.939009210853872e-06,
|
| 6367 |
+
"loss": 0.0325,
|
| 6368 |
+
"step": 8330
|
| 6369 |
+
},
|
| 6370 |
+
{
|
| 6371 |
+
"epoch": 7.816307403936269,
|
| 6372 |
+
"grad_norm": 0.7723280191421509,
|
| 6373 |
+
"learning_rate": 9.938935992619603e-06,
|
| 6374 |
+
"loss": 0.0335,
|
| 6375 |
+
"step": 8340
|
| 6376 |
+
},
|
| 6377 |
+
{
|
| 6378 |
+
"epoch": 7.825679475164011,
|
| 6379 |
+
"grad_norm": 1.1138160228729248,
|
| 6380 |
+
"learning_rate": 9.938862774385334e-06,
|
| 6381 |
+
"loss": 0.0392,
|
| 6382 |
+
"step": 8350
|
| 6383 |
+
},
|
| 6384 |
+
{
|
| 6385 |
+
"epoch": 7.835051546391752,
|
| 6386 |
+
"grad_norm": 1.1937012672424316,
|
| 6387 |
+
"learning_rate": 9.938789556151064e-06,
|
| 6388 |
+
"loss": 0.0349,
|
| 6389 |
+
"step": 8360
|
| 6390 |
+
},
|
| 6391 |
+
{
|
| 6392 |
+
"epoch": 7.844423617619494,
|
| 6393 |
+
"grad_norm": 0.8927692174911499,
|
| 6394 |
+
"learning_rate": 9.938716337916797e-06,
|
| 6395 |
+
"loss": 0.0339,
|
| 6396 |
+
"step": 8370
|
| 6397 |
+
},
|
| 6398 |
+
{
|
| 6399 |
+
"epoch": 7.853795688847235,
|
| 6400 |
+
"grad_norm": 1.1513832807540894,
|
| 6401 |
+
"learning_rate": 9.938643119682526e-06,
|
| 6402 |
+
"loss": 0.039,
|
| 6403 |
+
"step": 8380
|
| 6404 |
+
},
|
| 6405 |
+
{
|
| 6406 |
+
"epoch": 7.863167760074976,
|
| 6407 |
+
"grad_norm": 0.6757535338401794,
|
| 6408 |
+
"learning_rate": 9.938569901448257e-06,
|
| 6409 |
+
"loss": 0.0331,
|
| 6410 |
+
"step": 8390
|
| 6411 |
+
},
|
| 6412 |
+
{
|
| 6413 |
+
"epoch": 7.872539831302718,
|
| 6414 |
+
"grad_norm": 0.64778071641922,
|
| 6415 |
+
"learning_rate": 9.938496683213989e-06,
|
| 6416 |
+
"loss": 0.0357,
|
| 6417 |
+
"step": 8400
|
| 6418 |
+
},
|
| 6419 |
+
{
|
| 6420 |
+
"epoch": 7.881911902530459,
|
| 6421 |
+
"grad_norm": 0.8938049674034119,
|
| 6422 |
+
"learning_rate": 9.93842346497972e-06,
|
| 6423 |
+
"loss": 0.0342,
|
| 6424 |
+
"step": 8410
|
| 6425 |
+
},
|
| 6426 |
+
{
|
| 6427 |
+
"epoch": 7.891283973758201,
|
| 6428 |
+
"grad_norm": 1.0501271486282349,
|
| 6429 |
+
"learning_rate": 9.93835024674545e-06,
|
| 6430 |
+
"loss": 0.0335,
|
| 6431 |
+
"step": 8420
|
| 6432 |
+
},
|
| 6433 |
+
{
|
| 6434 |
+
"epoch": 7.900656044985942,
|
| 6435 |
+
"grad_norm": 0.8977199792861938,
|
| 6436 |
+
"learning_rate": 9.938277028511181e-06,
|
| 6437 |
+
"loss": 0.0352,
|
| 6438 |
+
"step": 8430
|
| 6439 |
+
},
|
| 6440 |
+
{
|
| 6441 |
+
"epoch": 7.910028116213683,
|
| 6442 |
+
"grad_norm": 1.1958116292953491,
|
| 6443 |
+
"learning_rate": 9.938203810276912e-06,
|
| 6444 |
+
"loss": 0.0349,
|
| 6445 |
+
"step": 8440
|
| 6446 |
+
},
|
| 6447 |
+
{
|
| 6448 |
+
"epoch": 7.919400187441425,
|
| 6449 |
+
"grad_norm": 0.9677138328552246,
|
| 6450 |
+
"learning_rate": 9.938130592042643e-06,
|
| 6451 |
+
"loss": 0.0368,
|
| 6452 |
+
"step": 8450
|
| 6453 |
+
},
|
| 6454 |
+
{
|
| 6455 |
+
"epoch": 7.928772258669166,
|
| 6456 |
+
"grad_norm": 0.6786054372787476,
|
| 6457 |
+
"learning_rate": 9.938057373808374e-06,
|
| 6458 |
+
"loss": 0.0312,
|
| 6459 |
+
"step": 8460
|
| 6460 |
+
},
|
| 6461 |
+
{
|
| 6462 |
+
"epoch": 7.938144329896907,
|
| 6463 |
+
"grad_norm": 0.8180833458900452,
|
| 6464 |
+
"learning_rate": 9.937984155574106e-06,
|
| 6465 |
+
"loss": 0.0351,
|
| 6466 |
+
"step": 8470
|
| 6467 |
+
},
|
| 6468 |
+
{
|
| 6469 |
+
"epoch": 7.947516401124648,
|
| 6470 |
+
"grad_norm": 0.9622411727905273,
|
| 6471 |
+
"learning_rate": 9.937910937339837e-06,
|
| 6472 |
+
"loss": 0.0312,
|
| 6473 |
+
"step": 8480
|
| 6474 |
+
},
|
| 6475 |
+
{
|
| 6476 |
+
"epoch": 7.956888472352389,
|
| 6477 |
+
"grad_norm": 0.7947582006454468,
|
| 6478 |
+
"learning_rate": 9.937837719105566e-06,
|
| 6479 |
+
"loss": 0.0309,
|
| 6480 |
+
"step": 8490
|
| 6481 |
+
},
|
| 6482 |
+
{
|
| 6483 |
+
"epoch": 7.966260543580131,
|
| 6484 |
+
"grad_norm": 0.663296103477478,
|
| 6485 |
+
"learning_rate": 9.937764500871298e-06,
|
| 6486 |
+
"loss": 0.0361,
|
| 6487 |
+
"step": 8500
|
| 6488 |
+
},
|
| 6489 |
+
{
|
| 6490 |
+
"epoch": 7.966260543580131,
|
| 6491 |
+
"eval_loss": 0.03769104555249214,
|
| 6492 |
+
"eval_pearson_cosine": 0.7716894745826721,
|
| 6493 |
+
"eval_pearson_dot": 0.7308681011199951,
|
| 6494 |
+
"eval_pearson_euclidean": 0.7253518104553223,
|
| 6495 |
+
"eval_pearson_manhattan": 0.727583646774292,
|
| 6496 |
+
"eval_runtime": 21.789,
|
| 6497 |
+
"eval_samples_per_second": 68.842,
|
| 6498 |
+
"eval_spearman_cosine": 0.7708559308843369,
|
| 6499 |
+
"eval_spearman_dot": 0.7317227014854395,
|
| 6500 |
+
"eval_spearman_euclidean": 0.729650509473576,
|
| 6501 |
+
"eval_spearman_manhattan": 0.7317616874018321,
|
| 6502 |
+
"eval_steps_per_second": 8.628,
|
| 6503 |
+
"step": 8500
|
| 6504 |
+
},
|
| 6505 |
+
{
|
| 6506 |
+
"epoch": 7.975632614807872,
|
| 6507 |
+
"grad_norm": 0.4781196415424347,
|
| 6508 |
+
"learning_rate": 9.937691282637029e-06,
|
| 6509 |
+
"loss": 0.0322,
|
| 6510 |
+
"step": 8510
|
| 6511 |
+
},
|
| 6512 |
+
{
|
| 6513 |
+
"epoch": 7.985004686035614,
|
| 6514 |
+
"grad_norm": 1.5688908100128174,
|
| 6515 |
+
"learning_rate": 9.93761806440276e-06,
|
| 6516 |
+
"loss": 0.0385,
|
| 6517 |
+
"step": 8520
|
| 6518 |
+
},
|
| 6519 |
+
{
|
| 6520 |
+
"epoch": 7.994376757263355,
|
| 6521 |
+
"grad_norm": 0.9491916298866272,
|
| 6522 |
+
"learning_rate": 9.93754484616849e-06,
|
| 6523 |
+
"loss": 0.0349,
|
| 6524 |
+
"step": 8530
|
| 6525 |
+
},
|
| 6526 |
+
{
|
| 6527 |
+
"epoch": 8.003748828491096,
|
| 6528 |
+
"grad_norm": 0.5889357924461365,
|
| 6529 |
+
"learning_rate": 9.937471627934221e-06,
|
| 6530 |
+
"loss": 0.0282,
|
| 6531 |
+
"step": 8540
|
| 6532 |
+
},
|
| 6533 |
+
{
|
| 6534 |
+
"epoch": 8.013120899718837,
|
| 6535 |
+
"grad_norm": 0.7906449437141418,
|
| 6536 |
+
"learning_rate": 9.937398409699952e-06,
|
| 6537 |
+
"loss": 0.0236,
|
| 6538 |
+
"step": 8550
|
| 6539 |
+
},
|
| 6540 |
+
{
|
| 6541 |
+
"epoch": 8.02249297094658,
|
| 6542 |
+
"grad_norm": 1.4013662338256836,
|
| 6543 |
+
"learning_rate": 9.937325191465683e-06,
|
| 6544 |
+
"loss": 0.0303,
|
| 6545 |
+
"step": 8560
|
| 6546 |
+
},
|
| 6547 |
+
{
|
| 6548 |
+
"epoch": 8.03186504217432,
|
| 6549 |
+
"grad_norm": 1.186049461364746,
|
| 6550 |
+
"learning_rate": 9.937251973231414e-06,
|
| 6551 |
+
"loss": 0.0283,
|
| 6552 |
+
"step": 8570
|
| 6553 |
+
},
|
| 6554 |
+
{
|
| 6555 |
+
"epoch": 8.041237113402062,
|
| 6556 |
+
"grad_norm": 0.9762454628944397,
|
| 6557 |
+
"learning_rate": 9.937178754997146e-06,
|
| 6558 |
+
"loss": 0.0235,
|
| 6559 |
+
"step": 8580
|
| 6560 |
+
},
|
| 6561 |
+
{
|
| 6562 |
+
"epoch": 8.050609184629803,
|
| 6563 |
+
"grad_norm": 0.8854254484176636,
|
| 6564 |
+
"learning_rate": 9.937105536762877e-06,
|
| 6565 |
+
"loss": 0.0269,
|
| 6566 |
+
"step": 8590
|
| 6567 |
+
},
|
| 6568 |
+
{
|
| 6569 |
+
"epoch": 8.059981255857544,
|
| 6570 |
+
"grad_norm": 1.2090007066726685,
|
| 6571 |
+
"learning_rate": 9.937032318528607e-06,
|
| 6572 |
+
"loss": 0.0254,
|
| 6573 |
+
"step": 8600
|
| 6574 |
+
},
|
| 6575 |
+
{
|
| 6576 |
+
"epoch": 8.069353327085286,
|
| 6577 |
+
"grad_norm": 0.5176217555999756,
|
| 6578 |
+
"learning_rate": 9.936959100294338e-06,
|
| 6579 |
+
"loss": 0.0317,
|
| 6580 |
+
"step": 8610
|
| 6581 |
+
},
|
| 6582 |
+
{
|
| 6583 |
+
"epoch": 8.078725398313027,
|
| 6584 |
+
"grad_norm": 0.4938619136810303,
|
| 6585 |
+
"learning_rate": 9.936885882060069e-06,
|
| 6586 |
+
"loss": 0.0245,
|
| 6587 |
+
"step": 8620
|
| 6588 |
+
},
|
| 6589 |
+
{
|
| 6590 |
+
"epoch": 8.088097469540768,
|
| 6591 |
+
"grad_norm": 1.6035066843032837,
|
| 6592 |
+
"learning_rate": 9.9368126638258e-06,
|
| 6593 |
+
"loss": 0.0296,
|
| 6594 |
+
"step": 8630
|
| 6595 |
+
},
|
| 6596 |
+
{
|
| 6597 |
+
"epoch": 8.09746954076851,
|
| 6598 |
+
"grad_norm": 0.6895983815193176,
|
| 6599 |
+
"learning_rate": 9.93673944559153e-06,
|
| 6600 |
+
"loss": 0.0292,
|
| 6601 |
+
"step": 8640
|
| 6602 |
+
},
|
| 6603 |
+
{
|
| 6604 |
+
"epoch": 8.10684161199625,
|
| 6605 |
+
"grad_norm": 0.6980400085449219,
|
| 6606 |
+
"learning_rate": 9.936666227357263e-06,
|
| 6607 |
+
"loss": 0.0299,
|
| 6608 |
+
"step": 8650
|
| 6609 |
+
},
|
| 6610 |
+
{
|
| 6611 |
+
"epoch": 8.116213683223993,
|
| 6612 |
+
"grad_norm": 1.0714101791381836,
|
| 6613 |
+
"learning_rate": 9.936593009122992e-06,
|
| 6614 |
+
"loss": 0.0258,
|
| 6615 |
+
"step": 8660
|
| 6616 |
+
},
|
| 6617 |
+
{
|
| 6618 |
+
"epoch": 8.125585754451734,
|
| 6619 |
+
"grad_norm": 0.6729503273963928,
|
| 6620 |
+
"learning_rate": 9.936519790888723e-06,
|
| 6621 |
+
"loss": 0.0279,
|
| 6622 |
+
"step": 8670
|
| 6623 |
+
},
|
| 6624 |
+
{
|
| 6625 |
+
"epoch": 8.134957825679475,
|
| 6626 |
+
"grad_norm": 0.8938456177711487,
|
| 6627 |
+
"learning_rate": 9.936446572654455e-06,
|
| 6628 |
+
"loss": 0.0245,
|
| 6629 |
+
"step": 8680
|
| 6630 |
+
},
|
| 6631 |
+
{
|
| 6632 |
+
"epoch": 8.144329896907216,
|
| 6633 |
+
"grad_norm": 1.2066154479980469,
|
| 6634 |
+
"learning_rate": 9.936373354420186e-06,
|
| 6635 |
+
"loss": 0.0334,
|
| 6636 |
+
"step": 8690
|
| 6637 |
+
},
|
| 6638 |
+
{
|
| 6639 |
+
"epoch": 8.153701968134957,
|
| 6640 |
+
"grad_norm": 0.7639226913452148,
|
| 6641 |
+
"learning_rate": 9.936300136185917e-06,
|
| 6642 |
+
"loss": 0.0245,
|
| 6643 |
+
"step": 8700
|
| 6644 |
+
},
|
| 6645 |
+
{
|
| 6646 |
+
"epoch": 8.1630740393627,
|
| 6647 |
+
"grad_norm": 1.4429128170013428,
|
| 6648 |
+
"learning_rate": 9.936226917951647e-06,
|
| 6649 |
+
"loss": 0.0278,
|
| 6650 |
+
"step": 8710
|
| 6651 |
+
},
|
| 6652 |
+
{
|
| 6653 |
+
"epoch": 8.17244611059044,
|
| 6654 |
+
"grad_norm": 0.8992042541503906,
|
| 6655 |
+
"learning_rate": 9.936153699717378e-06,
|
| 6656 |
+
"loss": 0.0267,
|
| 6657 |
+
"step": 8720
|
| 6658 |
+
},
|
| 6659 |
+
{
|
| 6660 |
+
"epoch": 8.181818181818182,
|
| 6661 |
+
"grad_norm": 0.598173975944519,
|
| 6662 |
+
"learning_rate": 9.936080481483109e-06,
|
| 6663 |
+
"loss": 0.0258,
|
| 6664 |
+
"step": 8730
|
| 6665 |
+
},
|
| 6666 |
+
{
|
| 6667 |
+
"epoch": 8.191190253045923,
|
| 6668 |
+
"grad_norm": 0.42205601930618286,
|
| 6669 |
+
"learning_rate": 9.93600726324884e-06,
|
| 6670 |
+
"loss": 0.0323,
|
| 6671 |
+
"step": 8740
|
| 6672 |
+
},
|
| 6673 |
+
{
|
| 6674 |
+
"epoch": 8.200562324273664,
|
| 6675 |
+
"grad_norm": 0.584039568901062,
|
| 6676 |
+
"learning_rate": 9.935934045014572e-06,
|
| 6677 |
+
"loss": 0.0224,
|
| 6678 |
+
"step": 8750
|
| 6679 |
+
},
|
| 6680 |
+
{
|
| 6681 |
+
"epoch": 8.200562324273664,
|
| 6682 |
+
"eval_loss": 0.037737876176834106,
|
| 6683 |
+
"eval_pearson_cosine": 0.7710561156272888,
|
| 6684 |
+
"eval_pearson_dot": 0.7243790626525879,
|
| 6685 |
+
"eval_pearson_euclidean": 0.7310018539428711,
|
| 6686 |
+
"eval_pearson_manhattan": 0.7328372001647949,
|
| 6687 |
+
"eval_runtime": 24.3532,
|
| 6688 |
+
"eval_samples_per_second": 61.593,
|
| 6689 |
+
"eval_spearman_cosine": 0.7703050511110383,
|
| 6690 |
+
"eval_spearman_dot": 0.725368343860831,
|
| 6691 |
+
"eval_spearman_euclidean": 0.7355669919591825,
|
| 6692 |
+
"eval_spearman_manhattan": 0.7369211933770833,
|
| 6693 |
+
"eval_steps_per_second": 7.72,
|
| 6694 |
+
"step": 8750
|
| 6695 |
+
},
|
| 6696 |
+
{
|
| 6697 |
+
"epoch": 8.209934395501406,
|
| 6698 |
+
"grad_norm": 0.8525517582893372,
|
| 6699 |
+
"learning_rate": 9.935860826780303e-06,
|
| 6700 |
+
"loss": 0.0268,
|
| 6701 |
+
"step": 8760
|
| 6702 |
+
},
|
| 6703 |
+
{
|
| 6704 |
+
"epoch": 8.219306466729147,
|
| 6705 |
+
"grad_norm": 0.7080439329147339,
|
| 6706 |
+
"learning_rate": 9.935787608546034e-06,
|
| 6707 |
+
"loss": 0.0237,
|
| 6708 |
+
"step": 8770
|
| 6709 |
+
},
|
| 6710 |
+
{
|
| 6711 |
+
"epoch": 8.228678537956888,
|
| 6712 |
+
"grad_norm": 0.7084332704544067,
|
| 6713 |
+
"learning_rate": 9.935714390311764e-06,
|
| 6714 |
+
"loss": 0.0232,
|
| 6715 |
+
"step": 8780
|
| 6716 |
+
},
|
| 6717 |
+
{
|
| 6718 |
+
"epoch": 8.23805060918463,
|
| 6719 |
+
"grad_norm": 1.2140733003616333,
|
| 6720 |
+
"learning_rate": 9.935641172077495e-06,
|
| 6721 |
+
"loss": 0.028,
|
| 6722 |
+
"step": 8790
|
| 6723 |
+
},
|
| 6724 |
+
{
|
| 6725 |
+
"epoch": 8.24742268041237,
|
| 6726 |
+
"grad_norm": 0.6614952087402344,
|
| 6727 |
+
"learning_rate": 9.935567953843226e-06,
|
| 6728 |
+
"loss": 0.025,
|
| 6729 |
+
"step": 8800
|
| 6730 |
+
},
|
| 6731 |
+
{
|
| 6732 |
+
"epoch": 8.256794751640113,
|
| 6733 |
+
"grad_norm": 0.642755925655365,
|
| 6734 |
+
"learning_rate": 9.935494735608957e-06,
|
| 6735 |
+
"loss": 0.0259,
|
| 6736 |
+
"step": 8810
|
| 6737 |
+
},
|
| 6738 |
+
{
|
| 6739 |
+
"epoch": 8.266166822867854,
|
| 6740 |
+
"grad_norm": 1.1676636934280396,
|
| 6741 |
+
"learning_rate": 9.935421517374687e-06,
|
| 6742 |
+
"loss": 0.0292,
|
| 6743 |
+
"step": 8820
|
| 6744 |
+
},
|
| 6745 |
+
{
|
| 6746 |
+
"epoch": 8.275538894095595,
|
| 6747 |
+
"grad_norm": 0.4561503529548645,
|
| 6748 |
+
"learning_rate": 9.935348299140418e-06,
|
| 6749 |
+
"loss": 0.026,
|
| 6750 |
+
"step": 8830
|
| 6751 |
+
},
|
| 6752 |
+
{
|
| 6753 |
+
"epoch": 8.284910965323336,
|
| 6754 |
+
"grad_norm": 0.5693290829658508,
|
| 6755 |
+
"learning_rate": 9.935275080906149e-06,
|
| 6756 |
+
"loss": 0.0283,
|
| 6757 |
+
"step": 8840
|
| 6758 |
+
},
|
| 6759 |
+
{
|
| 6760 |
+
"epoch": 8.294283036551079,
|
| 6761 |
+
"grad_norm": 1.2574779987335205,
|
| 6762 |
+
"learning_rate": 9.935201862671881e-06,
|
| 6763 |
+
"loss": 0.0275,
|
| 6764 |
+
"step": 8850
|
| 6765 |
+
},
|
| 6766 |
+
{
|
| 6767 |
+
"epoch": 8.30365510777882,
|
| 6768 |
+
"grad_norm": 0.9662300944328308,
|
| 6769 |
+
"learning_rate": 9.935128644437612e-06,
|
| 6770 |
+
"loss": 0.0257,
|
| 6771 |
+
"step": 8860
|
| 6772 |
+
},
|
| 6773 |
+
{
|
| 6774 |
+
"epoch": 8.31302717900656,
|
| 6775 |
+
"grad_norm": 0.5467878580093384,
|
| 6776 |
+
"learning_rate": 9.935055426203343e-06,
|
| 6777 |
+
"loss": 0.0264,
|
| 6778 |
+
"step": 8870
|
| 6779 |
+
},
|
| 6780 |
+
{
|
| 6781 |
+
"epoch": 8.322399250234302,
|
| 6782 |
+
"grad_norm": 1.0672435760498047,
|
| 6783 |
+
"learning_rate": 9.934982207969074e-06,
|
| 6784 |
+
"loss": 0.0334,
|
| 6785 |
+
"step": 8880
|
| 6786 |
+
},
|
| 6787 |
+
{
|
| 6788 |
+
"epoch": 8.331771321462043,
|
| 6789 |
+
"grad_norm": 1.155970573425293,
|
| 6790 |
+
"learning_rate": 9.934908989734804e-06,
|
| 6791 |
+
"loss": 0.029,
|
| 6792 |
+
"step": 8890
|
| 6793 |
+
},
|
| 6794 |
+
{
|
| 6795 |
+
"epoch": 8.341143392689784,
|
| 6796 |
+
"grad_norm": 0.9163686037063599,
|
| 6797 |
+
"learning_rate": 9.934835771500535e-06,
|
| 6798 |
+
"loss": 0.0295,
|
| 6799 |
+
"step": 8900
|
| 6800 |
+
},
|
| 6801 |
+
{
|
| 6802 |
+
"epoch": 8.350515463917526,
|
| 6803 |
+
"grad_norm": 0.6844992637634277,
|
| 6804 |
+
"learning_rate": 9.934762553266266e-06,
|
| 6805 |
+
"loss": 0.0228,
|
| 6806 |
+
"step": 8910
|
| 6807 |
+
},
|
| 6808 |
+
{
|
| 6809 |
+
"epoch": 8.359887535145267,
|
| 6810 |
+
"grad_norm": 0.6449628472328186,
|
| 6811 |
+
"learning_rate": 9.934689335031997e-06,
|
| 6812 |
+
"loss": 0.0272,
|
| 6813 |
+
"step": 8920
|
| 6814 |
+
},
|
| 6815 |
+
{
|
| 6816 |
+
"epoch": 8.369259606373008,
|
| 6817 |
+
"grad_norm": 1.0157432556152344,
|
| 6818 |
+
"learning_rate": 9.934616116797729e-06,
|
| 6819 |
+
"loss": 0.0251,
|
| 6820 |
+
"step": 8930
|
| 6821 |
+
},
|
| 6822 |
+
{
|
| 6823 |
+
"epoch": 8.37863167760075,
|
| 6824 |
+
"grad_norm": 0.9558159112930298,
|
| 6825 |
+
"learning_rate": 9.93454289856346e-06,
|
| 6826 |
+
"loss": 0.0262,
|
| 6827 |
+
"step": 8940
|
| 6828 |
+
},
|
| 6829 |
+
{
|
| 6830 |
+
"epoch": 8.388003748828492,
|
| 6831 |
+
"grad_norm": 1.2592884302139282,
|
| 6832 |
+
"learning_rate": 9.934469680329189e-06,
|
| 6833 |
+
"loss": 0.0317,
|
| 6834 |
+
"step": 8950
|
| 6835 |
+
},
|
| 6836 |
+
{
|
| 6837 |
+
"epoch": 8.397375820056233,
|
| 6838 |
+
"grad_norm": 0.8466887474060059,
|
| 6839 |
+
"learning_rate": 9.934396462094921e-06,
|
| 6840 |
+
"loss": 0.0333,
|
| 6841 |
+
"step": 8960
|
| 6842 |
+
},
|
| 6843 |
+
{
|
| 6844 |
+
"epoch": 8.406747891283974,
|
| 6845 |
+
"grad_norm": 0.8453270792961121,
|
| 6846 |
+
"learning_rate": 9.934323243860652e-06,
|
| 6847 |
+
"loss": 0.0276,
|
| 6848 |
+
"step": 8970
|
| 6849 |
+
},
|
| 6850 |
+
{
|
| 6851 |
+
"epoch": 8.416119962511715,
|
| 6852 |
+
"grad_norm": 0.6024593710899353,
|
| 6853 |
+
"learning_rate": 9.934250025626383e-06,
|
| 6854 |
+
"loss": 0.0269,
|
| 6855 |
+
"step": 8980
|
| 6856 |
+
},
|
| 6857 |
+
{
|
| 6858 |
+
"epoch": 8.425492033739456,
|
| 6859 |
+
"grad_norm": 0.8663728833198547,
|
| 6860 |
+
"learning_rate": 9.934176807392114e-06,
|
| 6861 |
+
"loss": 0.0289,
|
| 6862 |
+
"step": 8990
|
| 6863 |
+
},
|
| 6864 |
+
{
|
| 6865 |
+
"epoch": 8.434864104967197,
|
| 6866 |
+
"grad_norm": 0.8765361905097961,
|
| 6867 |
+
"learning_rate": 9.934103589157846e-06,
|
| 6868 |
+
"loss": 0.0256,
|
| 6869 |
+
"step": 9000
|
| 6870 |
+
},
|
| 6871 |
+
{
|
| 6872 |
+
"epoch": 8.434864104967197,
|
| 6873 |
+
"eval_loss": 0.038624610751867294,
|
| 6874 |
+
"eval_pearson_cosine": 0.7652055025100708,
|
| 6875 |
+
"eval_pearson_dot": 0.7185550928115845,
|
| 6876 |
+
"eval_pearson_euclidean": 0.7254422903060913,
|
| 6877 |
+
"eval_pearson_manhattan": 0.7273893356323242,
|
| 6878 |
+
"eval_runtime": 25.8439,
|
| 6879 |
+
"eval_samples_per_second": 58.041,
|
| 6880 |
+
"eval_spearman_cosine": 0.7646832614130892,
|
| 6881 |
+
"eval_spearman_dot": 0.7190565869110545,
|
| 6882 |
+
"eval_spearman_euclidean": 0.7303235144121284,
|
| 6883 |
+
"eval_spearman_manhattan": 0.7319318616566108,
|
| 6884 |
+
"eval_steps_per_second": 7.274,
|
| 6885 |
+
"step": 9000
|
| 6886 |
}
|
| 6887 |
],
|
| 6888 |
"logging_steps": 10,
|