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 8000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +2 -2
- last-checkpoint/rng_state_4.pth +2 -2
- last-checkpoint/rng_state_5.pth +2 -2
- last-checkpoint/rng_state_6.pth +2 -2
- last-checkpoint/rng_state_7.pth +2 -2
- 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 sha256:866e75c99e401c6fc4314023695489d65fcd5b9eaca8dde7642e6125835d6762
|
| 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:ff5bd566a6290228d61c2b0a64576637d68ab6f88e45b96b393bed3fe1419863
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc43fb30d4954a7fe8242ecf9efc90cf1895ba433c6b84aed827fd7e8890fc47
|
| 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 sha256:070e6d875daa93eee00ceb16c7956211f031e29ae89c0bf2b8c1638bfc724904
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afcb6da67f70f314a010a9987a5b352b967a4f9fa86b16cc95539556cc4d4b57
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50d6b0a99b3ef96868343a1a08693fcc566709fe5025abcde86626cac6379389
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e08e9ba40189eac7d5cd9c7fdb48812d033226be82605e39640894f69559aa36
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e39da057b37f74f810adcb1a33229a68d68a756d6cc2abf032078fbe45fc3a55
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b8b6d464ceead03c3bbad95ead841465f74b330a13ee3ce979e17fb8e372b42
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35f8ceff7347b2e4d980c59159b27487947fb8e524c24e87a3115123f2bc8a95
|
| 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:a3cb85ac9abf82ce747c60e9879ff175c317b429dff1e2463093126cce085180
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -4907,6 +4907,706 @@
|
|
| 4907 |
"learning_rate": 4.9900555892560594e-05,
|
| 4908 |
"loss": 0.6768,
|
| 4909 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4910 |
}
|
| 4911 |
],
|
| 4912 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.071281961526834,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 4907 |
"learning_rate": 4.9900555892560594e-05,
|
| 4908 |
"loss": 0.6768,
|
| 4909 |
"step": 7000
|
| 4910 |
+
},
|
| 4911 |
+
{
|
| 4912 |
+
"epoch": 3.567709907874429,
|
| 4913 |
+
"grad_norm": 0.16426721215248108,
|
| 4914 |
+
"learning_rate": 4.990041382954997e-05,
|
| 4915 |
+
"loss": 0.683,
|
| 4916 |
+
"step": 7010
|
| 4917 |
+
},
|
| 4918 |
+
{
|
| 4919 |
+
"epoch": 3.5728014765549174,
|
| 4920 |
+
"grad_norm": 0.12947894632816315,
|
| 4921 |
+
"learning_rate": 4.990027176653933e-05,
|
| 4922 |
+
"loss": 0.6729,
|
| 4923 |
+
"step": 7020
|
| 4924 |
+
},
|
| 4925 |
+
{
|
| 4926 |
+
"epoch": 3.5778930452354056,
|
| 4927 |
+
"grad_norm": 0.15960286557674408,
|
| 4928 |
+
"learning_rate": 4.9900129703528706e-05,
|
| 4929 |
+
"loss": 0.679,
|
| 4930 |
+
"step": 7030
|
| 4931 |
+
},
|
| 4932 |
+
{
|
| 4933 |
+
"epoch": 3.582984613915894,
|
| 4934 |
+
"grad_norm": 0.12176317721605301,
|
| 4935 |
+
"learning_rate": 4.989998764051807e-05,
|
| 4936 |
+
"loss": 0.6832,
|
| 4937 |
+
"step": 7040
|
| 4938 |
+
},
|
| 4939 |
+
{
|
| 4940 |
+
"epoch": 3.5880761825963816,
|
| 4941 |
+
"grad_norm": 0.12822549045085907,
|
| 4942 |
+
"learning_rate": 4.9899845577507446e-05,
|
| 4943 |
+
"loss": 0.6807,
|
| 4944 |
+
"step": 7050
|
| 4945 |
+
},
|
| 4946 |
+
{
|
| 4947 |
+
"epoch": 3.59316775127687,
|
| 4948 |
+
"grad_norm": 0.09114730358123779,
|
| 4949 |
+
"learning_rate": 4.989970351449682e-05,
|
| 4950 |
+
"loss": 0.6837,
|
| 4951 |
+
"step": 7060
|
| 4952 |
+
},
|
| 4953 |
+
{
|
| 4954 |
+
"epoch": 3.598259319957358,
|
| 4955 |
+
"grad_norm": 0.11248596012592316,
|
| 4956 |
+
"learning_rate": 4.989956145148619e-05,
|
| 4957 |
+
"loss": 0.6773,
|
| 4958 |
+
"step": 7070
|
| 4959 |
+
},
|
| 4960 |
+
{
|
| 4961 |
+
"epoch": 3.6033508886378462,
|
| 4962 |
+
"grad_norm": 0.14381690323352814,
|
| 4963 |
+
"learning_rate": 4.9899419388475565e-05,
|
| 4964 |
+
"loss": 0.6763,
|
| 4965 |
+
"step": 7080
|
| 4966 |
+
},
|
| 4967 |
+
{
|
| 4968 |
+
"epoch": 3.6084424573183345,
|
| 4969 |
+
"grad_norm": 0.1576450616121292,
|
| 4970 |
+
"learning_rate": 4.989927732546494e-05,
|
| 4971 |
+
"loss": 0.6796,
|
| 4972 |
+
"step": 7090
|
| 4973 |
+
},
|
| 4974 |
+
{
|
| 4975 |
+
"epoch": 3.6135340259988227,
|
| 4976 |
+
"grad_norm": 0.12672173976898193,
|
| 4977 |
+
"learning_rate": 4.989913526245431e-05,
|
| 4978 |
+
"loss": 0.6773,
|
| 4979 |
+
"step": 7100
|
| 4980 |
+
},
|
| 4981 |
+
{
|
| 4982 |
+
"epoch": 3.618625594679311,
|
| 4983 |
+
"grad_norm": 0.10089720040559769,
|
| 4984 |
+
"learning_rate": 4.9898993199443684e-05,
|
| 4985 |
+
"loss": 0.6835,
|
| 4986 |
+
"step": 7110
|
| 4987 |
+
},
|
| 4988 |
+
{
|
| 4989 |
+
"epoch": 3.6237171633597987,
|
| 4990 |
+
"grad_norm": 0.10352669656276703,
|
| 4991 |
+
"learning_rate": 4.989885113643306e-05,
|
| 4992 |
+
"loss": 0.6804,
|
| 4993 |
+
"step": 7120
|
| 4994 |
+
},
|
| 4995 |
+
{
|
| 4996 |
+
"epoch": 3.6288087320402873,
|
| 4997 |
+
"grad_norm": 0.12168221920728683,
|
| 4998 |
+
"learning_rate": 4.989870907342243e-05,
|
| 4999 |
+
"loss": 0.6775,
|
| 5000 |
+
"step": 7130
|
| 5001 |
+
},
|
| 5002 |
+
{
|
| 5003 |
+
"epoch": 3.633900300720775,
|
| 5004 |
+
"grad_norm": 0.152724489569664,
|
| 5005 |
+
"learning_rate": 4.9898567010411804e-05,
|
| 5006 |
+
"loss": 0.6832,
|
| 5007 |
+
"step": 7140
|
| 5008 |
+
},
|
| 5009 |
+
{
|
| 5010 |
+
"epoch": 3.6389918694012633,
|
| 5011 |
+
"grad_norm": 0.10124222189188004,
|
| 5012 |
+
"learning_rate": 4.989842494740118e-05,
|
| 5013 |
+
"loss": 0.6824,
|
| 5014 |
+
"step": 7150
|
| 5015 |
+
},
|
| 5016 |
+
{
|
| 5017 |
+
"epoch": 3.6440834380817515,
|
| 5018 |
+
"grad_norm": 0.10840737819671631,
|
| 5019 |
+
"learning_rate": 4.989828288439054e-05,
|
| 5020 |
+
"loss": 0.6781,
|
| 5021 |
+
"step": 7160
|
| 5022 |
+
},
|
| 5023 |
+
{
|
| 5024 |
+
"epoch": 3.6491750067622397,
|
| 5025 |
+
"grad_norm": 0.10668514668941498,
|
| 5026 |
+
"learning_rate": 4.9898140821379916e-05,
|
| 5027 |
+
"loss": 0.6857,
|
| 5028 |
+
"step": 7170
|
| 5029 |
+
},
|
| 5030 |
+
{
|
| 5031 |
+
"epoch": 3.654266575442728,
|
| 5032 |
+
"grad_norm": 0.11429141461849213,
|
| 5033 |
+
"learning_rate": 4.989799875836929e-05,
|
| 5034 |
+
"loss": 0.6823,
|
| 5035 |
+
"step": 7180
|
| 5036 |
+
},
|
| 5037 |
+
{
|
| 5038 |
+
"epoch": 3.6593581441232157,
|
| 5039 |
+
"grad_norm": 0.1012284979224205,
|
| 5040 |
+
"learning_rate": 4.989785669535866e-05,
|
| 5041 |
+
"loss": 0.678,
|
| 5042 |
+
"step": 7190
|
| 5043 |
+
},
|
| 5044 |
+
{
|
| 5045 |
+
"epoch": 3.6644497128037044,
|
| 5046 |
+
"grad_norm": 0.15000002086162567,
|
| 5047 |
+
"learning_rate": 4.9897714632348035e-05,
|
| 5048 |
+
"loss": 0.6763,
|
| 5049 |
+
"step": 7200
|
| 5050 |
+
},
|
| 5051 |
+
{
|
| 5052 |
+
"epoch": 3.669541281484192,
|
| 5053 |
+
"grad_norm": 0.15613609552383423,
|
| 5054 |
+
"learning_rate": 4.989757256933741e-05,
|
| 5055 |
+
"loss": 0.6837,
|
| 5056 |
+
"step": 7210
|
| 5057 |
+
},
|
| 5058 |
+
{
|
| 5059 |
+
"epoch": 3.6746328501646803,
|
| 5060 |
+
"grad_norm": 0.13344906270503998,
|
| 5061 |
+
"learning_rate": 4.989743050632678e-05,
|
| 5062 |
+
"loss": 0.6841,
|
| 5063 |
+
"step": 7220
|
| 5064 |
+
},
|
| 5065 |
+
{
|
| 5066 |
+
"epoch": 3.6797244188451685,
|
| 5067 |
+
"grad_norm": 0.12140567600727081,
|
| 5068 |
+
"learning_rate": 4.9897288443316155e-05,
|
| 5069 |
+
"loss": 0.6792,
|
| 5070 |
+
"step": 7230
|
| 5071 |
+
},
|
| 5072 |
+
{
|
| 5073 |
+
"epoch": 3.6848159875256568,
|
| 5074 |
+
"grad_norm": 0.11317454278469086,
|
| 5075 |
+
"learning_rate": 4.989714638030552e-05,
|
| 5076 |
+
"loss": 0.6821,
|
| 5077 |
+
"step": 7240
|
| 5078 |
+
},
|
| 5079 |
+
{
|
| 5080 |
+
"epoch": 3.689907556206145,
|
| 5081 |
+
"grad_norm": 0.1328129768371582,
|
| 5082 |
+
"learning_rate": 4.9897004317294894e-05,
|
| 5083 |
+
"loss": 0.6842,
|
| 5084 |
+
"step": 7250
|
| 5085 |
+
},
|
| 5086 |
+
{
|
| 5087 |
+
"epoch": 3.694999124886633,
|
| 5088 |
+
"grad_norm": 0.1081654503941536,
|
| 5089 |
+
"learning_rate": 4.989686225428427e-05,
|
| 5090 |
+
"loss": 0.6796,
|
| 5091 |
+
"step": 7260
|
| 5092 |
+
},
|
| 5093 |
+
{
|
| 5094 |
+
"epoch": 3.7000906935671214,
|
| 5095 |
+
"grad_norm": 0.09531684964895248,
|
| 5096 |
+
"learning_rate": 4.989672019127364e-05,
|
| 5097 |
+
"loss": 0.6833,
|
| 5098 |
+
"step": 7270
|
| 5099 |
+
},
|
| 5100 |
+
{
|
| 5101 |
+
"epoch": 3.705182262247609,
|
| 5102 |
+
"grad_norm": 0.10997920483350754,
|
| 5103 |
+
"learning_rate": 4.9896578128263013e-05,
|
| 5104 |
+
"loss": 0.6795,
|
| 5105 |
+
"step": 7280
|
| 5106 |
+
},
|
| 5107 |
+
{
|
| 5108 |
+
"epoch": 3.7102738309280974,
|
| 5109 |
+
"grad_norm": 0.15568581223487854,
|
| 5110 |
+
"learning_rate": 4.9896436065252387e-05,
|
| 5111 |
+
"loss": 0.6804,
|
| 5112 |
+
"step": 7290
|
| 5113 |
+
},
|
| 5114 |
+
{
|
| 5115 |
+
"epoch": 3.7153653996085856,
|
| 5116 |
+
"grad_norm": 0.130909726023674,
|
| 5117 |
+
"learning_rate": 4.989629400224175e-05,
|
| 5118 |
+
"loss": 0.6814,
|
| 5119 |
+
"step": 7300
|
| 5120 |
+
},
|
| 5121 |
+
{
|
| 5122 |
+
"epoch": 3.720456968289074,
|
| 5123 |
+
"grad_norm": 0.13917888700962067,
|
| 5124 |
+
"learning_rate": 4.9896151939231126e-05,
|
| 5125 |
+
"loss": 0.6793,
|
| 5126 |
+
"step": 7310
|
| 5127 |
+
},
|
| 5128 |
+
{
|
| 5129 |
+
"epoch": 3.725548536969562,
|
| 5130 |
+
"grad_norm": 0.12968967854976654,
|
| 5131 |
+
"learning_rate": 4.98960098762205e-05,
|
| 5132 |
+
"loss": 0.6819,
|
| 5133 |
+
"step": 7320
|
| 5134 |
+
},
|
| 5135 |
+
{
|
| 5136 |
+
"epoch": 3.73064010565005,
|
| 5137 |
+
"grad_norm": 0.12175523489713669,
|
| 5138 |
+
"learning_rate": 4.989586781320987e-05,
|
| 5139 |
+
"loss": 0.6785,
|
| 5140 |
+
"step": 7330
|
| 5141 |
+
},
|
| 5142 |
+
{
|
| 5143 |
+
"epoch": 3.7357316743305384,
|
| 5144 |
+
"grad_norm": 0.12431439012289047,
|
| 5145 |
+
"learning_rate": 4.9895725750199245e-05,
|
| 5146 |
+
"loss": 0.6785,
|
| 5147 |
+
"step": 7340
|
| 5148 |
+
},
|
| 5149 |
+
{
|
| 5150 |
+
"epoch": 3.740823243011026,
|
| 5151 |
+
"grad_norm": 0.1398157924413681,
|
| 5152 |
+
"learning_rate": 4.989558368718862e-05,
|
| 5153 |
+
"loss": 0.6779,
|
| 5154 |
+
"step": 7350
|
| 5155 |
+
},
|
| 5156 |
+
{
|
| 5157 |
+
"epoch": 3.745914811691515,
|
| 5158 |
+
"grad_norm": 0.11357001215219498,
|
| 5159 |
+
"learning_rate": 4.989544162417799e-05,
|
| 5160 |
+
"loss": 0.685,
|
| 5161 |
+
"step": 7360
|
| 5162 |
+
},
|
| 5163 |
+
{
|
| 5164 |
+
"epoch": 3.7510063803720026,
|
| 5165 |
+
"grad_norm": 0.16288457810878754,
|
| 5166 |
+
"learning_rate": 4.9895299561167365e-05,
|
| 5167 |
+
"loss": 0.6811,
|
| 5168 |
+
"step": 7370
|
| 5169 |
+
},
|
| 5170 |
+
{
|
| 5171 |
+
"epoch": 3.756097949052491,
|
| 5172 |
+
"grad_norm": 0.11568481475114822,
|
| 5173 |
+
"learning_rate": 4.989515749815674e-05,
|
| 5174 |
+
"loss": 0.6796,
|
| 5175 |
+
"step": 7380
|
| 5176 |
+
},
|
| 5177 |
+
{
|
| 5178 |
+
"epoch": 3.761189517732979,
|
| 5179 |
+
"grad_norm": 0.15195196866989136,
|
| 5180 |
+
"learning_rate": 4.989501543514611e-05,
|
| 5181 |
+
"loss": 0.6777,
|
| 5182 |
+
"step": 7390
|
| 5183 |
+
},
|
| 5184 |
+
{
|
| 5185 |
+
"epoch": 3.7662810864134673,
|
| 5186 |
+
"grad_norm": 0.12881244719028473,
|
| 5187 |
+
"learning_rate": 4.9894873372135484e-05,
|
| 5188 |
+
"loss": 0.6775,
|
| 5189 |
+
"step": 7400
|
| 5190 |
+
},
|
| 5191 |
+
{
|
| 5192 |
+
"epoch": 3.7713726550939555,
|
| 5193 |
+
"grad_norm": 0.1401291787624359,
|
| 5194 |
+
"learning_rate": 4.989473130912485e-05,
|
| 5195 |
+
"loss": 0.6834,
|
| 5196 |
+
"step": 7410
|
| 5197 |
+
},
|
| 5198 |
+
{
|
| 5199 |
+
"epoch": 3.7764642237744432,
|
| 5200 |
+
"grad_norm": 0.12248072773218155,
|
| 5201 |
+
"learning_rate": 4.9894589246114223e-05,
|
| 5202 |
+
"loss": 0.6792,
|
| 5203 |
+
"step": 7420
|
| 5204 |
+
},
|
| 5205 |
+
{
|
| 5206 |
+
"epoch": 3.781555792454932,
|
| 5207 |
+
"grad_norm": 0.11089824140071869,
|
| 5208 |
+
"learning_rate": 4.9894447183103596e-05,
|
| 5209 |
+
"loss": 0.6819,
|
| 5210 |
+
"step": 7430
|
| 5211 |
+
},
|
| 5212 |
+
{
|
| 5213 |
+
"epoch": 3.7866473611354197,
|
| 5214 |
+
"grad_norm": 0.09657898545265198,
|
| 5215 |
+
"learning_rate": 4.989430512009297e-05,
|
| 5216 |
+
"loss": 0.6841,
|
| 5217 |
+
"step": 7440
|
| 5218 |
+
},
|
| 5219 |
+
{
|
| 5220 |
+
"epoch": 3.791738929815908,
|
| 5221 |
+
"grad_norm": 0.12385948747396469,
|
| 5222 |
+
"learning_rate": 4.9894163057082336e-05,
|
| 5223 |
+
"loss": 0.6795,
|
| 5224 |
+
"step": 7450
|
| 5225 |
+
},
|
| 5226 |
+
{
|
| 5227 |
+
"epoch": 3.796830498496396,
|
| 5228 |
+
"grad_norm": 0.10562111437320709,
|
| 5229 |
+
"learning_rate": 4.989402099407171e-05,
|
| 5230 |
+
"loss": 0.6783,
|
| 5231 |
+
"step": 7460
|
| 5232 |
+
},
|
| 5233 |
+
{
|
| 5234 |
+
"epoch": 3.8019220671768843,
|
| 5235 |
+
"grad_norm": 0.11349403858184814,
|
| 5236 |
+
"learning_rate": 4.989387893106108e-05,
|
| 5237 |
+
"loss": 0.6807,
|
| 5238 |
+
"step": 7470
|
| 5239 |
+
},
|
| 5240 |
+
{
|
| 5241 |
+
"epoch": 3.8070136358573725,
|
| 5242 |
+
"grad_norm": 0.11444567143917084,
|
| 5243 |
+
"learning_rate": 4.9893736868050455e-05,
|
| 5244 |
+
"loss": 0.6791,
|
| 5245 |
+
"step": 7480
|
| 5246 |
+
},
|
| 5247 |
+
{
|
| 5248 |
+
"epoch": 3.8121052045378607,
|
| 5249 |
+
"grad_norm": 0.1610439121723175,
|
| 5250 |
+
"learning_rate": 4.989359480503983e-05,
|
| 5251 |
+
"loss": 0.6812,
|
| 5252 |
+
"step": 7490
|
| 5253 |
+
},
|
| 5254 |
+
{
|
| 5255 |
+
"epoch": 3.817196773218349,
|
| 5256 |
+
"grad_norm": 0.1214766800403595,
|
| 5257 |
+
"learning_rate": 4.98934527420292e-05,
|
| 5258 |
+
"loss": 0.6817,
|
| 5259 |
+
"step": 7500
|
| 5260 |
+
},
|
| 5261 |
+
{
|
| 5262 |
+
"epoch": 3.8222883418988367,
|
| 5263 |
+
"grad_norm": 0.12765400111675262,
|
| 5264 |
+
"learning_rate": 4.9893310679018575e-05,
|
| 5265 |
+
"loss": 0.6787,
|
| 5266 |
+
"step": 7510
|
| 5267 |
+
},
|
| 5268 |
+
{
|
| 5269 |
+
"epoch": 3.827379910579325,
|
| 5270 |
+
"grad_norm": 0.10731592029333115,
|
| 5271 |
+
"learning_rate": 4.989316861600795e-05,
|
| 5272 |
+
"loss": 0.683,
|
| 5273 |
+
"step": 7520
|
| 5274 |
+
},
|
| 5275 |
+
{
|
| 5276 |
+
"epoch": 3.832471479259813,
|
| 5277 |
+
"grad_norm": 0.12986642122268677,
|
| 5278 |
+
"learning_rate": 4.989302655299732e-05,
|
| 5279 |
+
"loss": 0.6766,
|
| 5280 |
+
"step": 7530
|
| 5281 |
+
},
|
| 5282 |
+
{
|
| 5283 |
+
"epoch": 3.8375630479403013,
|
| 5284 |
+
"grad_norm": 0.12156540900468826,
|
| 5285 |
+
"learning_rate": 4.9892884489986694e-05,
|
| 5286 |
+
"loss": 0.6834,
|
| 5287 |
+
"step": 7540
|
| 5288 |
+
},
|
| 5289 |
+
{
|
| 5290 |
+
"epoch": 3.8426546166207896,
|
| 5291 |
+
"grad_norm": 0.10650958865880966,
|
| 5292 |
+
"learning_rate": 4.989274242697606e-05,
|
| 5293 |
+
"loss": 0.6821,
|
| 5294 |
+
"step": 7550
|
| 5295 |
+
},
|
| 5296 |
+
{
|
| 5297 |
+
"epoch": 3.8477461853012778,
|
| 5298 |
+
"grad_norm": 0.09265447407960892,
|
| 5299 |
+
"learning_rate": 4.989260036396543e-05,
|
| 5300 |
+
"loss": 0.6807,
|
| 5301 |
+
"step": 7560
|
| 5302 |
+
},
|
| 5303 |
+
{
|
| 5304 |
+
"epoch": 3.852837753981766,
|
| 5305 |
+
"grad_norm": 0.13007622957229614,
|
| 5306 |
+
"learning_rate": 4.9892458300954806e-05,
|
| 5307 |
+
"loss": 0.681,
|
| 5308 |
+
"step": 7570
|
| 5309 |
+
},
|
| 5310 |
+
{
|
| 5311 |
+
"epoch": 3.8579293226622537,
|
| 5312 |
+
"grad_norm": 0.1033967137336731,
|
| 5313 |
+
"learning_rate": 4.989231623794418e-05,
|
| 5314 |
+
"loss": 0.686,
|
| 5315 |
+
"step": 7580
|
| 5316 |
+
},
|
| 5317 |
+
{
|
| 5318 |
+
"epoch": 3.8630208913427424,
|
| 5319 |
+
"grad_norm": 0.10867638140916824,
|
| 5320 |
+
"learning_rate": 4.989217417493355e-05,
|
| 5321 |
+
"loss": 0.6796,
|
| 5322 |
+
"step": 7590
|
| 5323 |
+
},
|
| 5324 |
+
{
|
| 5325 |
+
"epoch": 3.86811246002323,
|
| 5326 |
+
"grad_norm": 0.105263352394104,
|
| 5327 |
+
"learning_rate": 4.9892032111922926e-05,
|
| 5328 |
+
"loss": 0.6824,
|
| 5329 |
+
"step": 7600
|
| 5330 |
+
},
|
| 5331 |
+
{
|
| 5332 |
+
"epoch": 3.8732040287037184,
|
| 5333 |
+
"grad_norm": 0.12403067946434021,
|
| 5334 |
+
"learning_rate": 4.98918900489123e-05,
|
| 5335 |
+
"loss": 0.6793,
|
| 5336 |
+
"step": 7610
|
| 5337 |
+
},
|
| 5338 |
+
{
|
| 5339 |
+
"epoch": 3.8782955973842066,
|
| 5340 |
+
"grad_norm": 0.09988098591566086,
|
| 5341 |
+
"learning_rate": 4.989174798590167e-05,
|
| 5342 |
+
"loss": 0.6842,
|
| 5343 |
+
"step": 7620
|
| 5344 |
+
},
|
| 5345 |
+
{
|
| 5346 |
+
"epoch": 3.883387166064695,
|
| 5347 |
+
"grad_norm": 0.13452745974063873,
|
| 5348 |
+
"learning_rate": 4.9891605922891045e-05,
|
| 5349 |
+
"loss": 0.6811,
|
| 5350 |
+
"step": 7630
|
| 5351 |
+
},
|
| 5352 |
+
{
|
| 5353 |
+
"epoch": 3.888478734745183,
|
| 5354 |
+
"grad_norm": 0.10854171961545944,
|
| 5355 |
+
"learning_rate": 4.989146385988042e-05,
|
| 5356 |
+
"loss": 0.6827,
|
| 5357 |
+
"step": 7640
|
| 5358 |
+
},
|
| 5359 |
+
{
|
| 5360 |
+
"epoch": 3.893570303425671,
|
| 5361 |
+
"grad_norm": 0.10819829255342484,
|
| 5362 |
+
"learning_rate": 4.9891321796869784e-05,
|
| 5363 |
+
"loss": 0.6796,
|
| 5364 |
+
"step": 7650
|
| 5365 |
+
},
|
| 5366 |
+
{
|
| 5367 |
+
"epoch": 3.8986618721061594,
|
| 5368 |
+
"grad_norm": 0.17421726882457733,
|
| 5369 |
+
"learning_rate": 4.989117973385916e-05,
|
| 5370 |
+
"loss": 0.6808,
|
| 5371 |
+
"step": 7660
|
| 5372 |
+
},
|
| 5373 |
+
{
|
| 5374 |
+
"epoch": 3.903753440786647,
|
| 5375 |
+
"grad_norm": 0.13020376861095428,
|
| 5376 |
+
"learning_rate": 4.989103767084853e-05,
|
| 5377 |
+
"loss": 0.6796,
|
| 5378 |
+
"step": 7670
|
| 5379 |
+
},
|
| 5380 |
+
{
|
| 5381 |
+
"epoch": 3.9088450094671354,
|
| 5382 |
+
"grad_norm": 0.10870732367038727,
|
| 5383 |
+
"learning_rate": 4.9890895607837904e-05,
|
| 5384 |
+
"loss": 0.6867,
|
| 5385 |
+
"step": 7680
|
| 5386 |
+
},
|
| 5387 |
+
{
|
| 5388 |
+
"epoch": 3.9139365781476236,
|
| 5389 |
+
"grad_norm": 0.10249564051628113,
|
| 5390 |
+
"learning_rate": 4.989075354482727e-05,
|
| 5391 |
+
"loss": 0.6847,
|
| 5392 |
+
"step": 7690
|
| 5393 |
+
},
|
| 5394 |
+
{
|
| 5395 |
+
"epoch": 3.919028146828112,
|
| 5396 |
+
"grad_norm": 0.09583424031734467,
|
| 5397 |
+
"learning_rate": 4.989061148181664e-05,
|
| 5398 |
+
"loss": 0.6837,
|
| 5399 |
+
"step": 7700
|
| 5400 |
+
},
|
| 5401 |
+
{
|
| 5402 |
+
"epoch": 3.9241197155086,
|
| 5403 |
+
"grad_norm": 0.10090246796607971,
|
| 5404 |
+
"learning_rate": 4.9890469418806016e-05,
|
| 5405 |
+
"loss": 0.6814,
|
| 5406 |
+
"step": 7710
|
| 5407 |
+
},
|
| 5408 |
+
{
|
| 5409 |
+
"epoch": 3.9292112841890883,
|
| 5410 |
+
"grad_norm": 0.1201721727848053,
|
| 5411 |
+
"learning_rate": 4.989032735579539e-05,
|
| 5412 |
+
"loss": 0.6843,
|
| 5413 |
+
"step": 7720
|
| 5414 |
+
},
|
| 5415 |
+
{
|
| 5416 |
+
"epoch": 3.9343028528695765,
|
| 5417 |
+
"grad_norm": 0.11703382432460785,
|
| 5418 |
+
"learning_rate": 4.989018529278476e-05,
|
| 5419 |
+
"loss": 0.6784,
|
| 5420 |
+
"step": 7730
|
| 5421 |
+
},
|
| 5422 |
+
{
|
| 5423 |
+
"epoch": 3.9393944215500643,
|
| 5424 |
+
"grad_norm": 0.1226707398891449,
|
| 5425 |
+
"learning_rate": 4.9890043229774136e-05,
|
| 5426 |
+
"loss": 0.6847,
|
| 5427 |
+
"step": 7740
|
| 5428 |
+
},
|
| 5429 |
+
{
|
| 5430 |
+
"epoch": 3.9444859902305525,
|
| 5431 |
+
"grad_norm": 0.09304598718881607,
|
| 5432 |
+
"learning_rate": 4.988990116676351e-05,
|
| 5433 |
+
"loss": 0.6812,
|
| 5434 |
+
"step": 7750
|
| 5435 |
+
},
|
| 5436 |
+
{
|
| 5437 |
+
"epoch": 3.9495775589110407,
|
| 5438 |
+
"grad_norm": 0.10586468130350113,
|
| 5439 |
+
"learning_rate": 4.988975910375288e-05,
|
| 5440 |
+
"loss": 0.679,
|
| 5441 |
+
"step": 7760
|
| 5442 |
+
},
|
| 5443 |
+
{
|
| 5444 |
+
"epoch": 3.954669127591529,
|
| 5445 |
+
"grad_norm": 0.10969860106706619,
|
| 5446 |
+
"learning_rate": 4.9889617040742255e-05,
|
| 5447 |
+
"loss": 0.6826,
|
| 5448 |
+
"step": 7770
|
| 5449 |
+
},
|
| 5450 |
+
{
|
| 5451 |
+
"epoch": 3.959760696272017,
|
| 5452 |
+
"grad_norm": 0.1249874085187912,
|
| 5453 |
+
"learning_rate": 4.988947497773163e-05,
|
| 5454 |
+
"loss": 0.6767,
|
| 5455 |
+
"step": 7780
|
| 5456 |
+
},
|
| 5457 |
+
{
|
| 5458 |
+
"epoch": 3.9648522649525053,
|
| 5459 |
+
"grad_norm": 0.16480816900730133,
|
| 5460 |
+
"learning_rate": 4.9889332914721e-05,
|
| 5461 |
+
"loss": 0.6796,
|
| 5462 |
+
"step": 7790
|
| 5463 |
+
},
|
| 5464 |
+
{
|
| 5465 |
+
"epoch": 3.9699438336329935,
|
| 5466 |
+
"grad_norm": 0.2025347650051117,
|
| 5467 |
+
"learning_rate": 4.9889190851710374e-05,
|
| 5468 |
+
"loss": 0.678,
|
| 5469 |
+
"step": 7800
|
| 5470 |
+
},
|
| 5471 |
+
{
|
| 5472 |
+
"epoch": 3.9750354023134813,
|
| 5473 |
+
"grad_norm": 0.1153530701994896,
|
| 5474 |
+
"learning_rate": 4.988904878869974e-05,
|
| 5475 |
+
"loss": 0.6812,
|
| 5476 |
+
"step": 7810
|
| 5477 |
+
},
|
| 5478 |
+
{
|
| 5479 |
+
"epoch": 3.98012697099397,
|
| 5480 |
+
"grad_norm": 0.12336631864309311,
|
| 5481 |
+
"learning_rate": 4.9888906725689114e-05,
|
| 5482 |
+
"loss": 0.6781,
|
| 5483 |
+
"step": 7820
|
| 5484 |
+
},
|
| 5485 |
+
{
|
| 5486 |
+
"epoch": 3.9852185396744577,
|
| 5487 |
+
"grad_norm": 0.1417071670293808,
|
| 5488 |
+
"learning_rate": 4.988876466267849e-05,
|
| 5489 |
+
"loss": 0.6796,
|
| 5490 |
+
"step": 7830
|
| 5491 |
+
},
|
| 5492 |
+
{
|
| 5493 |
+
"epoch": 3.990310108354946,
|
| 5494 |
+
"grad_norm": 0.12677961587905884,
|
| 5495 |
+
"learning_rate": 4.988862259966786e-05,
|
| 5496 |
+
"loss": 0.6819,
|
| 5497 |
+
"step": 7840
|
| 5498 |
+
},
|
| 5499 |
+
{
|
| 5500 |
+
"epoch": 3.995401677035434,
|
| 5501 |
+
"grad_norm": 0.1134430319070816,
|
| 5502 |
+
"learning_rate": 4.988848053665723e-05,
|
| 5503 |
+
"loss": 0.6802,
|
| 5504 |
+
"step": 7850
|
| 5505 |
+
},
|
| 5506 |
+
{
|
| 5507 |
+
"epoch": 4.0,
|
| 5508 |
+
"grad_norm": 0.021812934428453445,
|
| 5509 |
+
"learning_rate": 4.98883384736466e-05,
|
| 5510 |
+
"loss": 0.6148,
|
| 5511 |
+
"step": 7860
|
| 5512 |
+
},
|
| 5513 |
+
{
|
| 5514 |
+
"epoch": 4.005091568680488,
|
| 5515 |
+
"grad_norm": 0.11325574666261673,
|
| 5516 |
+
"learning_rate": 4.988819641063597e-05,
|
| 5517 |
+
"loss": 0.6823,
|
| 5518 |
+
"step": 7870
|
| 5519 |
+
},
|
| 5520 |
+
{
|
| 5521 |
+
"epoch": 4.010183137360976,
|
| 5522 |
+
"grad_norm": 0.12439537793397903,
|
| 5523 |
+
"learning_rate": 4.9888054347625346e-05,
|
| 5524 |
+
"loss": 0.6808,
|
| 5525 |
+
"step": 7880
|
| 5526 |
+
},
|
| 5527 |
+
{
|
| 5528 |
+
"epoch": 4.015274706041464,
|
| 5529 |
+
"grad_norm": 0.11274933069944382,
|
| 5530 |
+
"learning_rate": 4.988791228461472e-05,
|
| 5531 |
+
"loss": 0.6828,
|
| 5532 |
+
"step": 7890
|
| 5533 |
+
},
|
| 5534 |
+
{
|
| 5535 |
+
"epoch": 4.020366274721953,
|
| 5536 |
+
"grad_norm": 0.10643935203552246,
|
| 5537 |
+
"learning_rate": 4.988777022160409e-05,
|
| 5538 |
+
"loss": 0.6833,
|
| 5539 |
+
"step": 7900
|
| 5540 |
+
},
|
| 5541 |
+
{
|
| 5542 |
+
"epoch": 4.025457843402441,
|
| 5543 |
+
"grad_norm": 0.0944155901670456,
|
| 5544 |
+
"learning_rate": 4.9887628158593465e-05,
|
| 5545 |
+
"loss": 0.6842,
|
| 5546 |
+
"step": 7910
|
| 5547 |
+
},
|
| 5548 |
+
{
|
| 5549 |
+
"epoch": 4.030549412082929,
|
| 5550 |
+
"grad_norm": 0.12772725522518158,
|
| 5551 |
+
"learning_rate": 4.988748609558284e-05,
|
| 5552 |
+
"loss": 0.6764,
|
| 5553 |
+
"step": 7920
|
| 5554 |
+
},
|
| 5555 |
+
{
|
| 5556 |
+
"epoch": 4.035640980763417,
|
| 5557 |
+
"grad_norm": 0.19370485842227936,
|
| 5558 |
+
"learning_rate": 4.988734403257221e-05,
|
| 5559 |
+
"loss": 0.6845,
|
| 5560 |
+
"step": 7930
|
| 5561 |
+
},
|
| 5562 |
+
{
|
| 5563 |
+
"epoch": 4.040732549443905,
|
| 5564 |
+
"grad_norm": 0.13512100279331207,
|
| 5565 |
+
"learning_rate": 4.9887201969561584e-05,
|
| 5566 |
+
"loss": 0.6745,
|
| 5567 |
+
"step": 7940
|
| 5568 |
+
},
|
| 5569 |
+
{
|
| 5570 |
+
"epoch": 4.0458241181243935,
|
| 5571 |
+
"grad_norm": 0.13933135569095612,
|
| 5572 |
+
"learning_rate": 4.988705990655095e-05,
|
| 5573 |
+
"loss": 0.6842,
|
| 5574 |
+
"step": 7950
|
| 5575 |
+
},
|
| 5576 |
+
{
|
| 5577 |
+
"epoch": 4.050915686804881,
|
| 5578 |
+
"grad_norm": 0.13375182449817657,
|
| 5579 |
+
"learning_rate": 4.9886917843540324e-05,
|
| 5580 |
+
"loss": 0.6815,
|
| 5581 |
+
"step": 7960
|
| 5582 |
+
},
|
| 5583 |
+
{
|
| 5584 |
+
"epoch": 4.05600725548537,
|
| 5585 |
+
"grad_norm": 0.11060313135385513,
|
| 5586 |
+
"learning_rate": 4.98867757805297e-05,
|
| 5587 |
+
"loss": 0.6798,
|
| 5588 |
+
"step": 7970
|
| 5589 |
+
},
|
| 5590 |
+
{
|
| 5591 |
+
"epoch": 4.061098824165858,
|
| 5592 |
+
"grad_norm": 0.14003530144691467,
|
| 5593 |
+
"learning_rate": 4.988663371751907e-05,
|
| 5594 |
+
"loss": 0.6787,
|
| 5595 |
+
"step": 7980
|
| 5596 |
+
},
|
| 5597 |
+
{
|
| 5598 |
+
"epoch": 4.066190392846346,
|
| 5599 |
+
"grad_norm": 0.10484720021486282,
|
| 5600 |
+
"learning_rate": 4.988649165450844e-05,
|
| 5601 |
+
"loss": 0.6818,
|
| 5602 |
+
"step": 7990
|
| 5603 |
+
},
|
| 5604 |
+
{
|
| 5605 |
+
"epoch": 4.071281961526834,
|
| 5606 |
+
"grad_norm": 0.11415210366249084,
|
| 5607 |
+
"learning_rate": 4.9886349591497816e-05,
|
| 5608 |
+
"loss": 0.6804,
|
| 5609 |
+
"step": 8000
|
| 5610 |
}
|
| 5611 |
],
|
| 5612 |
"logging_steps": 10,
|