Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Instructions to use CocoRoF/KoModernBERT-rerank_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CocoRoF/KoModernBERT-rerank_test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="CocoRoF/KoModernBERT-rerank_test")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("CocoRoF/KoModernBERT-rerank_test") model = AutoModelForSequenceClassification.from_pretrained("CocoRoF/KoModernBERT-rerank_test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
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 +702 -2
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737582948
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8d206265a0b197c430d5db1dceb9e0719e92da9b59d0c3da6842f0e99e941d8
|
| 3 |
size 737582948
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475256250
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1696326f679683a9f34c793252e2017911d534537abfc1dc9d0a3fe8f45106b6
|
| 3 |
size 1475256250
|
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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f335a0d32127eae0fdcf59f45dca546cc29b400ceb49efdaf226d770bb1f9985
|
| 3 |
size 15920
|
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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf72c9ac54b677d04298e8196362c894fb1bbab0b170c6b126a20403defdbe5e
|
| 3 |
size 15920
|
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:b838592ef20a1667b8825d9074c8bbc834f905d4bafc3831091c8d2ef1222e8e
|
| 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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5614c95101f8338093d02ef29f758ebbc594454a0c062b29967faccef1f5681e
|
| 3 |
size 15920
|
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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8574fbcf678031bfce3030b6ab38ab711fea77e25850d96e78211b3ee5d3b3c7
|
| 3 |
size 15920
|
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 sha256:553aaee47dca935766711df0292d8f3994cc3563450e4309eec18f2ce8bbccbd
|
| 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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:451b633025bf7f06c687f3adc2e2f5d7e58a1f353e44407c357c3324212aac8c
|
| 3 |
size 15920
|
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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ab5745b6d1b865720b4ea79e3beb1dd68a908a1259f3f247f874c6e1cde631b
|
| 3 |
size 15920
|
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 sha256:1489ea3c74c8e04296c65d61ebf0a8744873b77492a299b4f5f0b241898def6f
|
| 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": 4.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -5607,6 +5607,706 @@
|
|
| 5607 |
"learning_rate": 4.9886349591497816e-05,
|
| 5608 |
"loss": 0.6804,
|
| 5609 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5610 |
}
|
| 5611 |
],
|
| 5612 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.58043882957565,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 5607 |
"learning_rate": 4.9886349591497816e-05,
|
| 5608 |
"loss": 0.6804,
|
| 5609 |
"step": 8000
|
| 5610 |
+
},
|
| 5611 |
+
{
|
| 5612 |
+
"epoch": 4.076373530207323,
|
| 5613 |
+
"grad_norm": 0.1279604583978653,
|
| 5614 |
+
"learning_rate": 4.988620752848719e-05,
|
| 5615 |
+
"loss": 0.6793,
|
| 5616 |
+
"step": 8010
|
| 5617 |
+
},
|
| 5618 |
+
{
|
| 5619 |
+
"epoch": 4.0814650988878105,
|
| 5620 |
+
"grad_norm": 0.12138471007347107,
|
| 5621 |
+
"learning_rate": 4.988606546547656e-05,
|
| 5622 |
+
"loss": 0.6814,
|
| 5623 |
+
"step": 8020
|
| 5624 |
+
},
|
| 5625 |
+
{
|
| 5626 |
+
"epoch": 4.086556667568298,
|
| 5627 |
+
"grad_norm": 0.13427557051181793,
|
| 5628 |
+
"learning_rate": 4.9885923402465935e-05,
|
| 5629 |
+
"loss": 0.6752,
|
| 5630 |
+
"step": 8030
|
| 5631 |
+
},
|
| 5632 |
+
{
|
| 5633 |
+
"epoch": 4.091648236248787,
|
| 5634 |
+
"grad_norm": 0.14821045100688934,
|
| 5635 |
+
"learning_rate": 4.988578133945531e-05,
|
| 5636 |
+
"loss": 0.6775,
|
| 5637 |
+
"step": 8040
|
| 5638 |
+
},
|
| 5639 |
+
{
|
| 5640 |
+
"epoch": 4.096739804929275,
|
| 5641 |
+
"grad_norm": 0.13484236598014832,
|
| 5642 |
+
"learning_rate": 4.988563927644468e-05,
|
| 5643 |
+
"loss": 0.6846,
|
| 5644 |
+
"step": 8050
|
| 5645 |
+
},
|
| 5646 |
+
{
|
| 5647 |
+
"epoch": 4.101831373609763,
|
| 5648 |
+
"grad_norm": 0.07954470813274384,
|
| 5649 |
+
"learning_rate": 4.9885497213434055e-05,
|
| 5650 |
+
"loss": 0.684,
|
| 5651 |
+
"step": 8060
|
| 5652 |
+
},
|
| 5653 |
+
{
|
| 5654 |
+
"epoch": 4.106922942290251,
|
| 5655 |
+
"grad_norm": 0.10616060346364975,
|
| 5656 |
+
"learning_rate": 4.988535515042342e-05,
|
| 5657 |
+
"loss": 0.6822,
|
| 5658 |
+
"step": 8070
|
| 5659 |
+
},
|
| 5660 |
+
{
|
| 5661 |
+
"epoch": 4.11201451097074,
|
| 5662 |
+
"grad_norm": 0.10499216616153717,
|
| 5663 |
+
"learning_rate": 4.9885213087412794e-05,
|
| 5664 |
+
"loss": 0.6798,
|
| 5665 |
+
"step": 8080
|
| 5666 |
+
},
|
| 5667 |
+
{
|
| 5668 |
+
"epoch": 4.1171060796512275,
|
| 5669 |
+
"grad_norm": 0.12274570018053055,
|
| 5670 |
+
"learning_rate": 4.988507102440216e-05,
|
| 5671 |
+
"loss": 0.6799,
|
| 5672 |
+
"step": 8090
|
| 5673 |
+
},
|
| 5674 |
+
{
|
| 5675 |
+
"epoch": 4.122197648331715,
|
| 5676 |
+
"grad_norm": 0.11465749889612198,
|
| 5677 |
+
"learning_rate": 4.9884928961391534e-05,
|
| 5678 |
+
"loss": 0.6817,
|
| 5679 |
+
"step": 8100
|
| 5680 |
+
},
|
| 5681 |
+
{
|
| 5682 |
+
"epoch": 4.127289217012204,
|
| 5683 |
+
"grad_norm": 0.09962257742881775,
|
| 5684 |
+
"learning_rate": 4.988478689838091e-05,
|
| 5685 |
+
"loss": 0.6844,
|
| 5686 |
+
"step": 8110
|
| 5687 |
+
},
|
| 5688 |
+
{
|
| 5689 |
+
"epoch": 4.132380785692692,
|
| 5690 |
+
"grad_norm": 0.1151047945022583,
|
| 5691 |
+
"learning_rate": 4.988464483537028e-05,
|
| 5692 |
+
"loss": 0.6787,
|
| 5693 |
+
"step": 8120
|
| 5694 |
+
},
|
| 5695 |
+
{
|
| 5696 |
+
"epoch": 4.13747235437318,
|
| 5697 |
+
"grad_norm": 0.1360507756471634,
|
| 5698 |
+
"learning_rate": 4.988450277235965e-05,
|
| 5699 |
+
"loss": 0.6791,
|
| 5700 |
+
"step": 8130
|
| 5701 |
+
},
|
| 5702 |
+
{
|
| 5703 |
+
"epoch": 4.142563923053668,
|
| 5704 |
+
"grad_norm": 0.16751664876937866,
|
| 5705 |
+
"learning_rate": 4.9884360709349026e-05,
|
| 5706 |
+
"loss": 0.6738,
|
| 5707 |
+
"step": 8140
|
| 5708 |
+
},
|
| 5709 |
+
{
|
| 5710 |
+
"epoch": 4.147655491734157,
|
| 5711 |
+
"grad_norm": 0.18576379120349884,
|
| 5712 |
+
"learning_rate": 4.98842186463384e-05,
|
| 5713 |
+
"loss": 0.678,
|
| 5714 |
+
"step": 8150
|
| 5715 |
+
},
|
| 5716 |
+
{
|
| 5717 |
+
"epoch": 4.152747060414645,
|
| 5718 |
+
"grad_norm": 0.12279310077428818,
|
| 5719 |
+
"learning_rate": 4.988407658332777e-05,
|
| 5720 |
+
"loss": 0.6786,
|
| 5721 |
+
"step": 8160
|
| 5722 |
+
},
|
| 5723 |
+
{
|
| 5724 |
+
"epoch": 4.157838629095132,
|
| 5725 |
+
"grad_norm": 0.14428728818893433,
|
| 5726 |
+
"learning_rate": 4.9883934520317145e-05,
|
| 5727 |
+
"loss": 0.6756,
|
| 5728 |
+
"step": 8170
|
| 5729 |
+
},
|
| 5730 |
+
{
|
| 5731 |
+
"epoch": 4.162930197775621,
|
| 5732 |
+
"grad_norm": 0.1211373507976532,
|
| 5733 |
+
"learning_rate": 4.988379245730652e-05,
|
| 5734 |
+
"loss": 0.6775,
|
| 5735 |
+
"step": 8180
|
| 5736 |
+
},
|
| 5737 |
+
{
|
| 5738 |
+
"epoch": 4.168021766456109,
|
| 5739 |
+
"grad_norm": 0.13393299281597137,
|
| 5740 |
+
"learning_rate": 4.988365039429589e-05,
|
| 5741 |
+
"loss": 0.6769,
|
| 5742 |
+
"step": 8190
|
| 5743 |
+
},
|
| 5744 |
+
{
|
| 5745 |
+
"epoch": 4.173113335136597,
|
| 5746 |
+
"grad_norm": 0.12077504396438599,
|
| 5747 |
+
"learning_rate": 4.9883508331285265e-05,
|
| 5748 |
+
"loss": 0.6829,
|
| 5749 |
+
"step": 8200
|
| 5750 |
+
},
|
| 5751 |
+
{
|
| 5752 |
+
"epoch": 4.178204903817085,
|
| 5753 |
+
"grad_norm": 0.10940321534872055,
|
| 5754 |
+
"learning_rate": 4.988336626827463e-05,
|
| 5755 |
+
"loss": 0.6809,
|
| 5756 |
+
"step": 8210
|
| 5757 |
+
},
|
| 5758 |
+
{
|
| 5759 |
+
"epoch": 4.183296472497574,
|
| 5760 |
+
"grad_norm": 0.09884709119796753,
|
| 5761 |
+
"learning_rate": 4.9883224205264004e-05,
|
| 5762 |
+
"loss": 0.6813,
|
| 5763 |
+
"step": 8220
|
| 5764 |
+
},
|
| 5765 |
+
{
|
| 5766 |
+
"epoch": 4.188388041178062,
|
| 5767 |
+
"grad_norm": 0.10086120665073395,
|
| 5768 |
+
"learning_rate": 4.988308214225338e-05,
|
| 5769 |
+
"loss": 0.6809,
|
| 5770 |
+
"step": 8230
|
| 5771 |
+
},
|
| 5772 |
+
{
|
| 5773 |
+
"epoch": 4.19347960985855,
|
| 5774 |
+
"grad_norm": 0.11668648570775986,
|
| 5775 |
+
"learning_rate": 4.988294007924275e-05,
|
| 5776 |
+
"loss": 0.6798,
|
| 5777 |
+
"step": 8240
|
| 5778 |
+
},
|
| 5779 |
+
{
|
| 5780 |
+
"epoch": 4.198571178539038,
|
| 5781 |
+
"grad_norm": 0.12528111040592194,
|
| 5782 |
+
"learning_rate": 4.9882798016232123e-05,
|
| 5783 |
+
"loss": 0.6765,
|
| 5784 |
+
"step": 8250
|
| 5785 |
+
},
|
| 5786 |
+
{
|
| 5787 |
+
"epoch": 4.203662747219526,
|
| 5788 |
+
"grad_norm": 0.11714299023151398,
|
| 5789 |
+
"learning_rate": 4.9882655953221497e-05,
|
| 5790 |
+
"loss": 0.6744,
|
| 5791 |
+
"step": 8260
|
| 5792 |
+
},
|
| 5793 |
+
{
|
| 5794 |
+
"epoch": 4.2087543159000145,
|
| 5795 |
+
"grad_norm": 0.11050295829772949,
|
| 5796 |
+
"learning_rate": 4.988251389021087e-05,
|
| 5797 |
+
"loss": 0.6874,
|
| 5798 |
+
"step": 8270
|
| 5799 |
+
},
|
| 5800 |
+
{
|
| 5801 |
+
"epoch": 4.213845884580502,
|
| 5802 |
+
"grad_norm": 0.09499291330575943,
|
| 5803 |
+
"learning_rate": 4.9882371827200236e-05,
|
| 5804 |
+
"loss": 0.6817,
|
| 5805 |
+
"step": 8280
|
| 5806 |
+
},
|
| 5807 |
+
{
|
| 5808 |
+
"epoch": 4.218937453260991,
|
| 5809 |
+
"grad_norm": 0.09335146099328995,
|
| 5810 |
+
"learning_rate": 4.988222976418961e-05,
|
| 5811 |
+
"loss": 0.6818,
|
| 5812 |
+
"step": 8290
|
| 5813 |
+
},
|
| 5814 |
+
{
|
| 5815 |
+
"epoch": 4.224029021941479,
|
| 5816 |
+
"grad_norm": 0.1219559907913208,
|
| 5817 |
+
"learning_rate": 4.988208770117898e-05,
|
| 5818 |
+
"loss": 0.681,
|
| 5819 |
+
"step": 8300
|
| 5820 |
+
},
|
| 5821 |
+
{
|
| 5822 |
+
"epoch": 4.229120590621967,
|
| 5823 |
+
"grad_norm": 0.14629492163658142,
|
| 5824 |
+
"learning_rate": 4.9881945638168355e-05,
|
| 5825 |
+
"loss": 0.6822,
|
| 5826 |
+
"step": 8310
|
| 5827 |
+
},
|
| 5828 |
+
{
|
| 5829 |
+
"epoch": 4.234212159302455,
|
| 5830 |
+
"grad_norm": 0.13365550339221954,
|
| 5831 |
+
"learning_rate": 4.988180357515773e-05,
|
| 5832 |
+
"loss": 0.6805,
|
| 5833 |
+
"step": 8320
|
| 5834 |
+
},
|
| 5835 |
+
{
|
| 5836 |
+
"epoch": 4.239303727982943,
|
| 5837 |
+
"grad_norm": 0.141509547829628,
|
| 5838 |
+
"learning_rate": 4.98816615121471e-05,
|
| 5839 |
+
"loss": 0.6783,
|
| 5840 |
+
"step": 8330
|
| 5841 |
+
},
|
| 5842 |
+
{
|
| 5843 |
+
"epoch": 4.2443952966634315,
|
| 5844 |
+
"grad_norm": 0.13036063313484192,
|
| 5845 |
+
"learning_rate": 4.9881519449136475e-05,
|
| 5846 |
+
"loss": 0.6756,
|
| 5847 |
+
"step": 8340
|
| 5848 |
+
},
|
| 5849 |
+
{
|
| 5850 |
+
"epoch": 4.249486865343919,
|
| 5851 |
+
"grad_norm": 0.11939451843500137,
|
| 5852 |
+
"learning_rate": 4.988137738612584e-05,
|
| 5853 |
+
"loss": 0.6826,
|
| 5854 |
+
"step": 8350
|
| 5855 |
+
},
|
| 5856 |
+
{
|
| 5857 |
+
"epoch": 4.254578434024408,
|
| 5858 |
+
"grad_norm": 0.12008455395698547,
|
| 5859 |
+
"learning_rate": 4.9881235323115214e-05,
|
| 5860 |
+
"loss": 0.681,
|
| 5861 |
+
"step": 8360
|
| 5862 |
+
},
|
| 5863 |
+
{
|
| 5864 |
+
"epoch": 4.259670002704896,
|
| 5865 |
+
"grad_norm": 0.11019112914800644,
|
| 5866 |
+
"learning_rate": 4.988109326010459e-05,
|
| 5867 |
+
"loss": 0.6856,
|
| 5868 |
+
"step": 8370
|
| 5869 |
+
},
|
| 5870 |
+
{
|
| 5871 |
+
"epoch": 4.264761571385384,
|
| 5872 |
+
"grad_norm": 0.10078281164169312,
|
| 5873 |
+
"learning_rate": 4.988095119709396e-05,
|
| 5874 |
+
"loss": 0.6792,
|
| 5875 |
+
"step": 8380
|
| 5876 |
+
},
|
| 5877 |
+
{
|
| 5878 |
+
"epoch": 4.269853140065872,
|
| 5879 |
+
"grad_norm": 0.1294504553079605,
|
| 5880 |
+
"learning_rate": 4.988080913408333e-05,
|
| 5881 |
+
"loss": 0.6825,
|
| 5882 |
+
"step": 8390
|
| 5883 |
+
},
|
| 5884 |
+
{
|
| 5885 |
+
"epoch": 4.274944708746361,
|
| 5886 |
+
"grad_norm": 0.1074661836028099,
|
| 5887 |
+
"learning_rate": 4.9880667071072706e-05,
|
| 5888 |
+
"loss": 0.6799,
|
| 5889 |
+
"step": 8400
|
| 5890 |
+
},
|
| 5891 |
+
{
|
| 5892 |
+
"epoch": 4.280036277426849,
|
| 5893 |
+
"grad_norm": 0.11285123229026794,
|
| 5894 |
+
"learning_rate": 4.988052500806208e-05,
|
| 5895 |
+
"loss": 0.6831,
|
| 5896 |
+
"step": 8410
|
| 5897 |
+
},
|
| 5898 |
+
{
|
| 5899 |
+
"epoch": 4.285127846107336,
|
| 5900 |
+
"grad_norm": 0.12429996579885483,
|
| 5901 |
+
"learning_rate": 4.988038294505145e-05,
|
| 5902 |
+
"loss": 0.6793,
|
| 5903 |
+
"step": 8420
|
| 5904 |
+
},
|
| 5905 |
+
{
|
| 5906 |
+
"epoch": 4.290219414787825,
|
| 5907 |
+
"grad_norm": 0.10803820192813873,
|
| 5908 |
+
"learning_rate": 4.9880240882040826e-05,
|
| 5909 |
+
"loss": 0.6787,
|
| 5910 |
+
"step": 8430
|
| 5911 |
+
},
|
| 5912 |
+
{
|
| 5913 |
+
"epoch": 4.295310983468313,
|
| 5914 |
+
"grad_norm": 0.12693211436271667,
|
| 5915 |
+
"learning_rate": 4.98800988190302e-05,
|
| 5916 |
+
"loss": 0.6729,
|
| 5917 |
+
"step": 8440
|
| 5918 |
+
},
|
| 5919 |
+
{
|
| 5920 |
+
"epoch": 4.300402552148801,
|
| 5921 |
+
"grad_norm": 0.11828629672527313,
|
| 5922 |
+
"learning_rate": 4.987995675601957e-05,
|
| 5923 |
+
"loss": 0.6829,
|
| 5924 |
+
"step": 8450
|
| 5925 |
+
},
|
| 5926 |
+
{
|
| 5927 |
+
"epoch": 4.305494120829289,
|
| 5928 |
+
"grad_norm": 0.11893879622220993,
|
| 5929 |
+
"learning_rate": 4.987981469300894e-05,
|
| 5930 |
+
"loss": 0.681,
|
| 5931 |
+
"step": 8460
|
| 5932 |
+
},
|
| 5933 |
+
{
|
| 5934 |
+
"epoch": 4.310585689509777,
|
| 5935 |
+
"grad_norm": 0.12228237092494965,
|
| 5936 |
+
"learning_rate": 4.987967262999831e-05,
|
| 5937 |
+
"loss": 0.6793,
|
| 5938 |
+
"step": 8470
|
| 5939 |
+
},
|
| 5940 |
+
{
|
| 5941 |
+
"epoch": 4.315677258190266,
|
| 5942 |
+
"grad_norm": 0.11881165206432343,
|
| 5943 |
+
"learning_rate": 4.9879530566987684e-05,
|
| 5944 |
+
"loss": 0.681,
|
| 5945 |
+
"step": 8480
|
| 5946 |
+
},
|
| 5947 |
+
{
|
| 5948 |
+
"epoch": 4.320768826870753,
|
| 5949 |
+
"grad_norm": 0.09753947705030441,
|
| 5950 |
+
"learning_rate": 4.987938850397705e-05,
|
| 5951 |
+
"loss": 0.6812,
|
| 5952 |
+
"step": 8490
|
| 5953 |
+
},
|
| 5954 |
+
{
|
| 5955 |
+
"epoch": 4.325860395551242,
|
| 5956 |
+
"grad_norm": 0.10875561088323593,
|
| 5957 |
+
"learning_rate": 4.9879246440966424e-05,
|
| 5958 |
+
"loss": 0.6764,
|
| 5959 |
+
"step": 8500
|
| 5960 |
+
},
|
| 5961 |
+
{
|
| 5962 |
+
"epoch": 4.33095196423173,
|
| 5963 |
+
"grad_norm": 0.1029878631234169,
|
| 5964 |
+
"learning_rate": 4.98791043779558e-05,
|
| 5965 |
+
"loss": 0.6793,
|
| 5966 |
+
"step": 8510
|
| 5967 |
+
},
|
| 5968 |
+
{
|
| 5969 |
+
"epoch": 4.3360435329122184,
|
| 5970 |
+
"grad_norm": 0.11321298032999039,
|
| 5971 |
+
"learning_rate": 4.987896231494517e-05,
|
| 5972 |
+
"loss": 0.6805,
|
| 5973 |
+
"step": 8520
|
| 5974 |
+
},
|
| 5975 |
+
{
|
| 5976 |
+
"epoch": 4.341135101592706,
|
| 5977 |
+
"grad_norm": 0.12302636355161667,
|
| 5978 |
+
"learning_rate": 4.987882025193454e-05,
|
| 5979 |
+
"loss": 0.6841,
|
| 5980 |
+
"step": 8530
|
| 5981 |
+
},
|
| 5982 |
+
{
|
| 5983 |
+
"epoch": 4.346226670273195,
|
| 5984 |
+
"grad_norm": 0.0927717313170433,
|
| 5985 |
+
"learning_rate": 4.9878678188923916e-05,
|
| 5986 |
+
"loss": 0.6848,
|
| 5987 |
+
"step": 8540
|
| 5988 |
+
},
|
| 5989 |
+
{
|
| 5990 |
+
"epoch": 4.351318238953683,
|
| 5991 |
+
"grad_norm": 0.1418168693780899,
|
| 5992 |
+
"learning_rate": 4.987853612591329e-05,
|
| 5993 |
+
"loss": 0.6764,
|
| 5994 |
+
"step": 8550
|
| 5995 |
+
},
|
| 5996 |
+
{
|
| 5997 |
+
"epoch": 4.35640980763417,
|
| 5998 |
+
"grad_norm": 0.12036493420600891,
|
| 5999 |
+
"learning_rate": 4.987839406290266e-05,
|
| 6000 |
+
"loss": 0.6783,
|
| 6001 |
+
"step": 8560
|
| 6002 |
+
},
|
| 6003 |
+
{
|
| 6004 |
+
"epoch": 4.361501376314659,
|
| 6005 |
+
"grad_norm": 0.14609991014003754,
|
| 6006 |
+
"learning_rate": 4.9878251999892036e-05,
|
| 6007 |
+
"loss": 0.676,
|
| 6008 |
+
"step": 8570
|
| 6009 |
+
},
|
| 6010 |
+
{
|
| 6011 |
+
"epoch": 4.366592944995147,
|
| 6012 |
+
"grad_norm": 0.1448822170495987,
|
| 6013 |
+
"learning_rate": 4.987810993688141e-05,
|
| 6014 |
+
"loss": 0.6803,
|
| 6015 |
+
"step": 8580
|
| 6016 |
+
},
|
| 6017 |
+
{
|
| 6018 |
+
"epoch": 4.3716845136756355,
|
| 6019 |
+
"grad_norm": 0.14650079607963562,
|
| 6020 |
+
"learning_rate": 4.987796787387078e-05,
|
| 6021 |
+
"loss": 0.6795,
|
| 6022 |
+
"step": 8590
|
| 6023 |
+
},
|
| 6024 |
+
{
|
| 6025 |
+
"epoch": 4.376776082356123,
|
| 6026 |
+
"grad_norm": 0.10146970301866531,
|
| 6027 |
+
"learning_rate": 4.987782581086015e-05,
|
| 6028 |
+
"loss": 0.6826,
|
| 6029 |
+
"step": 8600
|
| 6030 |
+
},
|
| 6031 |
+
{
|
| 6032 |
+
"epoch": 4.381867651036612,
|
| 6033 |
+
"grad_norm": 0.10098574310541153,
|
| 6034 |
+
"learning_rate": 4.987768374784952e-05,
|
| 6035 |
+
"loss": 0.6814,
|
| 6036 |
+
"step": 8610
|
| 6037 |
+
},
|
| 6038 |
+
{
|
| 6039 |
+
"epoch": 4.3869592197171,
|
| 6040 |
+
"grad_norm": 0.12981392443180084,
|
| 6041 |
+
"learning_rate": 4.9877541684838894e-05,
|
| 6042 |
+
"loss": 0.6774,
|
| 6043 |
+
"step": 8620
|
| 6044 |
+
},
|
| 6045 |
+
{
|
| 6046 |
+
"epoch": 4.392050788397588,
|
| 6047 |
+
"grad_norm": 0.1231103241443634,
|
| 6048 |
+
"learning_rate": 4.987739962182827e-05,
|
| 6049 |
+
"loss": 0.6751,
|
| 6050 |
+
"step": 8630
|
| 6051 |
+
},
|
| 6052 |
+
{
|
| 6053 |
+
"epoch": 4.397142357078076,
|
| 6054 |
+
"grad_norm": 0.17549310624599457,
|
| 6055 |
+
"learning_rate": 4.987725755881764e-05,
|
| 6056 |
+
"loss": 0.6773,
|
| 6057 |
+
"step": 8640
|
| 6058 |
+
},
|
| 6059 |
+
{
|
| 6060 |
+
"epoch": 4.402233925758564,
|
| 6061 |
+
"grad_norm": 0.1261102259159088,
|
| 6062 |
+
"learning_rate": 4.9877115495807014e-05,
|
| 6063 |
+
"loss": 0.6778,
|
| 6064 |
+
"step": 8650
|
| 6065 |
+
},
|
| 6066 |
+
{
|
| 6067 |
+
"epoch": 4.4073254944390525,
|
| 6068 |
+
"grad_norm": 0.12228421121835709,
|
| 6069 |
+
"learning_rate": 4.987697343279639e-05,
|
| 6070 |
+
"loss": 0.6815,
|
| 6071 |
+
"step": 8660
|
| 6072 |
+
},
|
| 6073 |
+
{
|
| 6074 |
+
"epoch": 4.41241706311954,
|
| 6075 |
+
"grad_norm": 0.08992882072925568,
|
| 6076 |
+
"learning_rate": 4.987683136978576e-05,
|
| 6077 |
+
"loss": 0.6829,
|
| 6078 |
+
"step": 8670
|
| 6079 |
+
},
|
| 6080 |
+
{
|
| 6081 |
+
"epoch": 4.417508631800029,
|
| 6082 |
+
"grad_norm": 0.10478372871875763,
|
| 6083 |
+
"learning_rate": 4.987668930677513e-05,
|
| 6084 |
+
"loss": 0.6758,
|
| 6085 |
+
"step": 8680
|
| 6086 |
+
},
|
| 6087 |
+
{
|
| 6088 |
+
"epoch": 4.422600200480517,
|
| 6089 |
+
"grad_norm": 0.1255083978176117,
|
| 6090 |
+
"learning_rate": 4.9876547243764506e-05,
|
| 6091 |
+
"loss": 0.6741,
|
| 6092 |
+
"step": 8690
|
| 6093 |
+
},
|
| 6094 |
+
{
|
| 6095 |
+
"epoch": 4.4276917691610045,
|
| 6096 |
+
"grad_norm": 0.13139568269252777,
|
| 6097 |
+
"learning_rate": 4.987640518075387e-05,
|
| 6098 |
+
"loss": 0.6803,
|
| 6099 |
+
"step": 8700
|
| 6100 |
+
},
|
| 6101 |
+
{
|
| 6102 |
+
"epoch": 4.432783337841493,
|
| 6103 |
+
"grad_norm": 0.1472860723733902,
|
| 6104 |
+
"learning_rate": 4.9876263117743246e-05,
|
| 6105 |
+
"loss": 0.6759,
|
| 6106 |
+
"step": 8710
|
| 6107 |
+
},
|
| 6108 |
+
{
|
| 6109 |
+
"epoch": 4.437874906521981,
|
| 6110 |
+
"grad_norm": 0.16318807005882263,
|
| 6111 |
+
"learning_rate": 4.987612105473262e-05,
|
| 6112 |
+
"loss": 0.6868,
|
| 6113 |
+
"step": 8720
|
| 6114 |
+
},
|
| 6115 |
+
{
|
| 6116 |
+
"epoch": 4.44296647520247,
|
| 6117 |
+
"grad_norm": 0.1145109310746193,
|
| 6118 |
+
"learning_rate": 4.987597899172199e-05,
|
| 6119 |
+
"loss": 0.6788,
|
| 6120 |
+
"step": 8730
|
| 6121 |
+
},
|
| 6122 |
+
{
|
| 6123 |
+
"epoch": 4.448058043882957,
|
| 6124 |
+
"grad_norm": 0.09544923901557922,
|
| 6125 |
+
"learning_rate": 4.987583692871136e-05,
|
| 6126 |
+
"loss": 0.682,
|
| 6127 |
+
"step": 8740
|
| 6128 |
+
},
|
| 6129 |
+
{
|
| 6130 |
+
"epoch": 4.453149612563446,
|
| 6131 |
+
"grad_norm": 0.10780615359544754,
|
| 6132 |
+
"learning_rate": 4.987569486570073e-05,
|
| 6133 |
+
"loss": 0.6781,
|
| 6134 |
+
"step": 8750
|
| 6135 |
+
},
|
| 6136 |
+
{
|
| 6137 |
+
"epoch": 4.458241181243934,
|
| 6138 |
+
"grad_norm": 0.14260242879390717,
|
| 6139 |
+
"learning_rate": 4.9875552802690104e-05,
|
| 6140 |
+
"loss": 0.6782,
|
| 6141 |
+
"step": 8760
|
| 6142 |
+
},
|
| 6143 |
+
{
|
| 6144 |
+
"epoch": 4.463332749924422,
|
| 6145 |
+
"grad_norm": 0.13693778216838837,
|
| 6146 |
+
"learning_rate": 4.987541073967948e-05,
|
| 6147 |
+
"loss": 0.6771,
|
| 6148 |
+
"step": 8770
|
| 6149 |
+
},
|
| 6150 |
+
{
|
| 6151 |
+
"epoch": 4.46842431860491,
|
| 6152 |
+
"grad_norm": 0.10794325917959213,
|
| 6153 |
+
"learning_rate": 4.987526867666885e-05,
|
| 6154 |
+
"loss": 0.6789,
|
| 6155 |
+
"step": 8780
|
| 6156 |
+
},
|
| 6157 |
+
{
|
| 6158 |
+
"epoch": 4.473515887285398,
|
| 6159 |
+
"grad_norm": 0.11324315518140793,
|
| 6160 |
+
"learning_rate": 4.9875126613658224e-05,
|
| 6161 |
+
"loss": 0.684,
|
| 6162 |
+
"step": 8790
|
| 6163 |
+
},
|
| 6164 |
+
{
|
| 6165 |
+
"epoch": 4.478607455965887,
|
| 6166 |
+
"grad_norm": 0.10087355971336365,
|
| 6167 |
+
"learning_rate": 4.98749845506476e-05,
|
| 6168 |
+
"loss": 0.6819,
|
| 6169 |
+
"step": 8800
|
| 6170 |
+
},
|
| 6171 |
+
{
|
| 6172 |
+
"epoch": 4.483699024646374,
|
| 6173 |
+
"grad_norm": 0.09752973914146423,
|
| 6174 |
+
"learning_rate": 4.987484248763697e-05,
|
| 6175 |
+
"loss": 0.6819,
|
| 6176 |
+
"step": 8810
|
| 6177 |
+
},
|
| 6178 |
+
{
|
| 6179 |
+
"epoch": 4.488790593326863,
|
| 6180 |
+
"grad_norm": 0.12462896853685379,
|
| 6181 |
+
"learning_rate": 4.987470042462634e-05,
|
| 6182 |
+
"loss": 0.6844,
|
| 6183 |
+
"step": 8820
|
| 6184 |
+
},
|
| 6185 |
+
{
|
| 6186 |
+
"epoch": 4.493882162007351,
|
| 6187 |
+
"grad_norm": 0.12875770032405853,
|
| 6188 |
+
"learning_rate": 4.9874558361615716e-05,
|
| 6189 |
+
"loss": 0.6784,
|
| 6190 |
+
"step": 8830
|
| 6191 |
+
},
|
| 6192 |
+
{
|
| 6193 |
+
"epoch": 4.4989737306878395,
|
| 6194 |
+
"grad_norm": 0.11722705513238907,
|
| 6195 |
+
"learning_rate": 4.987441629860509e-05,
|
| 6196 |
+
"loss": 0.6797,
|
| 6197 |
+
"step": 8840
|
| 6198 |
+
},
|
| 6199 |
+
{
|
| 6200 |
+
"epoch": 4.504065299368327,
|
| 6201 |
+
"grad_norm": 0.16931360960006714,
|
| 6202 |
+
"learning_rate": 4.987427423559446e-05,
|
| 6203 |
+
"loss": 0.6766,
|
| 6204 |
+
"step": 8850
|
| 6205 |
+
},
|
| 6206 |
+
{
|
| 6207 |
+
"epoch": 4.509156868048816,
|
| 6208 |
+
"grad_norm": 0.13619418442249298,
|
| 6209 |
+
"learning_rate": 4.987413217258383e-05,
|
| 6210 |
+
"loss": 0.6774,
|
| 6211 |
+
"step": 8860
|
| 6212 |
+
},
|
| 6213 |
+
{
|
| 6214 |
+
"epoch": 4.514248436729304,
|
| 6215 |
+
"grad_norm": 0.19465768337249756,
|
| 6216 |
+
"learning_rate": 4.98739901095732e-05,
|
| 6217 |
+
"loss": 0.6832,
|
| 6218 |
+
"step": 8870
|
| 6219 |
+
},
|
| 6220 |
+
{
|
| 6221 |
+
"epoch": 4.519340005409791,
|
| 6222 |
+
"grad_norm": 0.11889132857322693,
|
| 6223 |
+
"learning_rate": 4.9873848046562575e-05,
|
| 6224 |
+
"loss": 0.6848,
|
| 6225 |
+
"step": 8880
|
| 6226 |
+
},
|
| 6227 |
+
{
|
| 6228 |
+
"epoch": 4.52443157409028,
|
| 6229 |
+
"grad_norm": 0.10783824324607849,
|
| 6230 |
+
"learning_rate": 4.987370598355195e-05,
|
| 6231 |
+
"loss": 0.6793,
|
| 6232 |
+
"step": 8890
|
| 6233 |
+
},
|
| 6234 |
+
{
|
| 6235 |
+
"epoch": 4.529523142770768,
|
| 6236 |
+
"grad_norm": 0.11385292559862137,
|
| 6237 |
+
"learning_rate": 4.987356392054132e-05,
|
| 6238 |
+
"loss": 0.6754,
|
| 6239 |
+
"step": 8900
|
| 6240 |
+
},
|
| 6241 |
+
{
|
| 6242 |
+
"epoch": 4.5346147114512565,
|
| 6243 |
+
"grad_norm": 0.13017722964286804,
|
| 6244 |
+
"learning_rate": 4.987342185753069e-05,
|
| 6245 |
+
"loss": 0.6778,
|
| 6246 |
+
"step": 8910
|
| 6247 |
+
},
|
| 6248 |
+
{
|
| 6249 |
+
"epoch": 4.539706280131744,
|
| 6250 |
+
"grad_norm": 0.13603904843330383,
|
| 6251 |
+
"learning_rate": 4.987327979452006e-05,
|
| 6252 |
+
"loss": 0.6758,
|
| 6253 |
+
"step": 8920
|
| 6254 |
+
},
|
| 6255 |
+
{
|
| 6256 |
+
"epoch": 4.544797848812232,
|
| 6257 |
+
"grad_norm": 0.15172545611858368,
|
| 6258 |
+
"learning_rate": 4.9873137731509434e-05,
|
| 6259 |
+
"loss": 0.677,
|
| 6260 |
+
"step": 8930
|
| 6261 |
+
},
|
| 6262 |
+
{
|
| 6263 |
+
"epoch": 4.549889417492721,
|
| 6264 |
+
"grad_norm": 0.13269858062267303,
|
| 6265 |
+
"learning_rate": 4.987299566849881e-05,
|
| 6266 |
+
"loss": 0.6823,
|
| 6267 |
+
"step": 8940
|
| 6268 |
+
},
|
| 6269 |
+
{
|
| 6270 |
+
"epoch": 4.5549809861732085,
|
| 6271 |
+
"grad_norm": 0.14247867465019226,
|
| 6272 |
+
"learning_rate": 4.987285360548818e-05,
|
| 6273 |
+
"loss": 0.6803,
|
| 6274 |
+
"step": 8950
|
| 6275 |
+
},
|
| 6276 |
+
{
|
| 6277 |
+
"epoch": 4.560072554853697,
|
| 6278 |
+
"grad_norm": 0.1458357870578766,
|
| 6279 |
+
"learning_rate": 4.987271154247755e-05,
|
| 6280 |
+
"loss": 0.6755,
|
| 6281 |
+
"step": 8960
|
| 6282 |
+
},
|
| 6283 |
+
{
|
| 6284 |
+
"epoch": 4.565164123534185,
|
| 6285 |
+
"grad_norm": 0.1240466758608818,
|
| 6286 |
+
"learning_rate": 4.9872569479466926e-05,
|
| 6287 |
+
"loss": 0.6793,
|
| 6288 |
+
"step": 8970
|
| 6289 |
+
},
|
| 6290 |
+
{
|
| 6291 |
+
"epoch": 4.5702556922146735,
|
| 6292 |
+
"grad_norm": 0.14014077186584473,
|
| 6293 |
+
"learning_rate": 4.98724274164563e-05,
|
| 6294 |
+
"loss": 0.6812,
|
| 6295 |
+
"step": 8980
|
| 6296 |
+
},
|
| 6297 |
+
{
|
| 6298 |
+
"epoch": 4.575347260895161,
|
| 6299 |
+
"grad_norm": 0.1574947088956833,
|
| 6300 |
+
"learning_rate": 4.987228535344567e-05,
|
| 6301 |
+
"loss": 0.6752,
|
| 6302 |
+
"step": 8990
|
| 6303 |
+
},
|
| 6304 |
+
{
|
| 6305 |
+
"epoch": 4.58043882957565,
|
| 6306 |
+
"grad_norm": 0.12997229397296906,
|
| 6307 |
+
"learning_rate": 4.987214329043504e-05,
|
| 6308 |
+
"loss": 0.6853,
|
| 6309 |
+
"step": 9000
|
| 6310 |
}
|
| 6311 |
],
|
| 6312 |
"logging_steps": 10,
|