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 7000, 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 +2 -2
- last-checkpoint/rng_state_2.pth +2 -2
- 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 +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 sha256:505255bb8be77cb973b3c0c099b60ddbe10985257e13456b8ff86dd8b9cb8873
|
| 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 sha256:60d776be50d108dd81ee9b0387b3f914be892678c43979999b5d33654ba56980
|
| 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:e5a3a11b6b4e10025dadb9bffaf07ec4008881d55150f5d84a95c713a6115c05
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7274f23fed9b58a8af256d8a5074ebda8ae9f9a6fbae5266d18c1fea989b6dd3
|
| 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 sha256:8804ae92e3b2392e22e65d2ab0526c5903b460e6548b94439fb0020ed4f6c971
|
| 3 |
+
size 15920
|
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:f3e11e0f06e93328a4d905cdad25e3815ebf5e2497f1f505db912eeda651cf3a
|
| 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 sha256:13c61159190ff4452eae1732b23b98693c3d2402a9a22d6001e28feb991ad5c6
|
| 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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac997a5aab71c40ab8ef2ff5de70ff9f85b773b03f24a2a2d95bd0f7f9a02a36
|
| 3 |
size 15920
|
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 sha256:11fb3f2fa89709aa4394eeaab2935e72048d88e01b5565c44fab8e49d94e5818
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de5c48e090ff05ec024f0ed6d872fa6b88401224fc22247b9444b0418bc262b8
|
| 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:dc4672502535f71e3bfd116fab55200a1b20d47f6448284dad0f792fcd7901da
|
| 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": 3.
|
| 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,
|
|
@@ -4207,6 +4207,706 @@
|
|
| 4207 |
"learning_rate": 4.991476219362336e-05,
|
| 4208 |
"loss": 0.6877,
|
| 4209 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4210 |
}
|
| 4211 |
],
|
| 4212 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.562618339193941,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 4207 |
"learning_rate": 4.991476219362336e-05,
|
| 4208 |
"loss": 0.6877,
|
| 4209 |
"step": 6000
|
| 4210 |
+
},
|
| 4211 |
+
{
|
| 4212 |
+
"epoch": 3.0585530398256138,
|
| 4213 |
+
"grad_norm": 0.11032961308956146,
|
| 4214 |
+
"learning_rate": 4.991462013061273e-05,
|
| 4215 |
+
"loss": 0.6812,
|
| 4216 |
+
"step": 6010
|
| 4217 |
+
},
|
| 4218 |
+
{
|
| 4219 |
+
"epoch": 3.063644608506102,
|
| 4220 |
+
"grad_norm": 0.0968027114868164,
|
| 4221 |
+
"learning_rate": 4.9914478067602104e-05,
|
| 4222 |
+
"loss": 0.6818,
|
| 4223 |
+
"step": 6020
|
| 4224 |
+
},
|
| 4225 |
+
{
|
| 4226 |
+
"epoch": 3.06873617718659,
|
| 4227 |
+
"grad_norm": 0.11660617589950562,
|
| 4228 |
+
"learning_rate": 4.991433600459148e-05,
|
| 4229 |
+
"loss": 0.6806,
|
| 4230 |
+
"step": 6030
|
| 4231 |
+
},
|
| 4232 |
+
{
|
| 4233 |
+
"epoch": 3.0738277458670784,
|
| 4234 |
+
"grad_norm": 0.1213793009519577,
|
| 4235 |
+
"learning_rate": 4.991419394158085e-05,
|
| 4236 |
+
"loss": 0.6818,
|
| 4237 |
+
"step": 6040
|
| 4238 |
+
},
|
| 4239 |
+
{
|
| 4240 |
+
"epoch": 3.078919314547566,
|
| 4241 |
+
"grad_norm": 0.1275392472743988,
|
| 4242 |
+
"learning_rate": 4.991405187857022e-05,
|
| 4243 |
+
"loss": 0.6802,
|
| 4244 |
+
"step": 6050
|
| 4245 |
+
},
|
| 4246 |
+
{
|
| 4247 |
+
"epoch": 3.0840108832280544,
|
| 4248 |
+
"grad_norm": 0.1026177927851677,
|
| 4249 |
+
"learning_rate": 4.9913909815559596e-05,
|
| 4250 |
+
"loss": 0.6835,
|
| 4251 |
+
"step": 6060
|
| 4252 |
+
},
|
| 4253 |
+
{
|
| 4254 |
+
"epoch": 3.0891024519085426,
|
| 4255 |
+
"grad_norm": 0.10983236879110336,
|
| 4256 |
+
"learning_rate": 4.991376775254897e-05,
|
| 4257 |
+
"loss": 0.6838,
|
| 4258 |
+
"step": 6070
|
| 4259 |
+
},
|
| 4260 |
+
{
|
| 4261 |
+
"epoch": 3.094194020589031,
|
| 4262 |
+
"grad_norm": 0.11360979080200195,
|
| 4263 |
+
"learning_rate": 4.991362568953834e-05,
|
| 4264 |
+
"loss": 0.6806,
|
| 4265 |
+
"step": 6080
|
| 4266 |
+
},
|
| 4267 |
+
{
|
| 4268 |
+
"epoch": 3.099285589269519,
|
| 4269 |
+
"grad_norm": 0.1488681137561798,
|
| 4270 |
+
"learning_rate": 4.9913483626527716e-05,
|
| 4271 |
+
"loss": 0.6797,
|
| 4272 |
+
"step": 6090
|
| 4273 |
+
},
|
| 4274 |
+
{
|
| 4275 |
+
"epoch": 3.1043771579500072,
|
| 4276 |
+
"grad_norm": 0.13620369136333466,
|
| 4277 |
+
"learning_rate": 4.991334156351709e-05,
|
| 4278 |
+
"loss": 0.6871,
|
| 4279 |
+
"step": 6100
|
| 4280 |
+
},
|
| 4281 |
+
{
|
| 4282 |
+
"epoch": 3.1094687266304954,
|
| 4283 |
+
"grad_norm": 0.12065689265727997,
|
| 4284 |
+
"learning_rate": 4.9913199500506455e-05,
|
| 4285 |
+
"loss": 0.6792,
|
| 4286 |
+
"step": 6110
|
| 4287 |
+
},
|
| 4288 |
+
{
|
| 4289 |
+
"epoch": 3.1145602953109837,
|
| 4290 |
+
"grad_norm": 0.13917431235313416,
|
| 4291 |
+
"learning_rate": 4.991305743749583e-05,
|
| 4292 |
+
"loss": 0.676,
|
| 4293 |
+
"step": 6120
|
| 4294 |
+
},
|
| 4295 |
+
{
|
| 4296 |
+
"epoch": 3.1196518639914714,
|
| 4297 |
+
"grad_norm": 0.1255902796983719,
|
| 4298 |
+
"learning_rate": 4.99129153744852e-05,
|
| 4299 |
+
"loss": 0.6842,
|
| 4300 |
+
"step": 6130
|
| 4301 |
+
},
|
| 4302 |
+
{
|
| 4303 |
+
"epoch": 3.1247434326719596,
|
| 4304 |
+
"grad_norm": 0.11472214758396149,
|
| 4305 |
+
"learning_rate": 4.9912773311474574e-05,
|
| 4306 |
+
"loss": 0.6788,
|
| 4307 |
+
"step": 6140
|
| 4308 |
+
},
|
| 4309 |
+
{
|
| 4310 |
+
"epoch": 3.129835001352448,
|
| 4311 |
+
"grad_norm": 0.12614910304546356,
|
| 4312 |
+
"learning_rate": 4.991263124846395e-05,
|
| 4313 |
+
"loss": 0.6802,
|
| 4314 |
+
"step": 6150
|
| 4315 |
+
},
|
| 4316 |
+
{
|
| 4317 |
+
"epoch": 3.134926570032936,
|
| 4318 |
+
"grad_norm": 0.13529641926288605,
|
| 4319 |
+
"learning_rate": 4.991248918545332e-05,
|
| 4320 |
+
"loss": 0.6805,
|
| 4321 |
+
"step": 6160
|
| 4322 |
+
},
|
| 4323 |
+
{
|
| 4324 |
+
"epoch": 3.1400181387134243,
|
| 4325 |
+
"grad_norm": 0.11604179441928864,
|
| 4326 |
+
"learning_rate": 4.9912347122442694e-05,
|
| 4327 |
+
"loss": 0.6813,
|
| 4328 |
+
"step": 6170
|
| 4329 |
+
},
|
| 4330 |
+
{
|
| 4331 |
+
"epoch": 3.1451097073939125,
|
| 4332 |
+
"grad_norm": 0.12789122760295868,
|
| 4333 |
+
"learning_rate": 4.991220505943207e-05,
|
| 4334 |
+
"loss": 0.6845,
|
| 4335 |
+
"step": 6180
|
| 4336 |
+
},
|
| 4337 |
+
{
|
| 4338 |
+
"epoch": 3.1502012760744007,
|
| 4339 |
+
"grad_norm": 0.12958049774169922,
|
| 4340 |
+
"learning_rate": 4.991206299642143e-05,
|
| 4341 |
+
"loss": 0.6804,
|
| 4342 |
+
"step": 6190
|
| 4343 |
+
},
|
| 4344 |
+
{
|
| 4345 |
+
"epoch": 3.1552928447548885,
|
| 4346 |
+
"grad_norm": 0.10314188152551651,
|
| 4347 |
+
"learning_rate": 4.9911920933410806e-05,
|
| 4348 |
+
"loss": 0.6847,
|
| 4349 |
+
"step": 6200
|
| 4350 |
+
},
|
| 4351 |
+
{
|
| 4352 |
+
"epoch": 3.1603844134353767,
|
| 4353 |
+
"grad_norm": 0.10737662017345428,
|
| 4354 |
+
"learning_rate": 4.991177887040018e-05,
|
| 4355 |
+
"loss": 0.6808,
|
| 4356 |
+
"step": 6210
|
| 4357 |
+
},
|
| 4358 |
+
{
|
| 4359 |
+
"epoch": 3.165475982115865,
|
| 4360 |
+
"grad_norm": 0.15128542482852936,
|
| 4361 |
+
"learning_rate": 4.991163680738955e-05,
|
| 4362 |
+
"loss": 0.6789,
|
| 4363 |
+
"step": 6220
|
| 4364 |
+
},
|
| 4365 |
+
{
|
| 4366 |
+
"epoch": 3.170567550796353,
|
| 4367 |
+
"grad_norm": 0.11941689997911453,
|
| 4368 |
+
"learning_rate": 4.9911494744378925e-05,
|
| 4369 |
+
"loss": 0.6778,
|
| 4370 |
+
"step": 6230
|
| 4371 |
+
},
|
| 4372 |
+
{
|
| 4373 |
+
"epoch": 3.1756591194768413,
|
| 4374 |
+
"grad_norm": 0.15348762273788452,
|
| 4375 |
+
"learning_rate": 4.99113526813683e-05,
|
| 4376 |
+
"loss": 0.6799,
|
| 4377 |
+
"step": 6240
|
| 4378 |
+
},
|
| 4379 |
+
{
|
| 4380 |
+
"epoch": 3.1807506881573295,
|
| 4381 |
+
"grad_norm": 0.11959049850702286,
|
| 4382 |
+
"learning_rate": 4.9911210618357665e-05,
|
| 4383 |
+
"loss": 0.6776,
|
| 4384 |
+
"step": 6250
|
| 4385 |
+
},
|
| 4386 |
+
{
|
| 4387 |
+
"epoch": 3.1858422568378177,
|
| 4388 |
+
"grad_norm": 0.11588987708091736,
|
| 4389 |
+
"learning_rate": 4.991106855534704e-05,
|
| 4390 |
+
"loss": 0.688,
|
| 4391 |
+
"step": 6260
|
| 4392 |
+
},
|
| 4393 |
+
{
|
| 4394 |
+
"epoch": 3.190933825518306,
|
| 4395 |
+
"grad_norm": 0.09905340522527695,
|
| 4396 |
+
"learning_rate": 4.991092649233641e-05,
|
| 4397 |
+
"loss": 0.6845,
|
| 4398 |
+
"step": 6270
|
| 4399 |
+
},
|
| 4400 |
+
{
|
| 4401 |
+
"epoch": 3.196025394198794,
|
| 4402 |
+
"grad_norm": 0.11044521629810333,
|
| 4403 |
+
"learning_rate": 4.9910784429325784e-05,
|
| 4404 |
+
"loss": 0.6823,
|
| 4405 |
+
"step": 6280
|
| 4406 |
+
},
|
| 4407 |
+
{
|
| 4408 |
+
"epoch": 3.201116962879282,
|
| 4409 |
+
"grad_norm": 0.10236191004514694,
|
| 4410 |
+
"learning_rate": 4.991064236631516e-05,
|
| 4411 |
+
"loss": 0.6824,
|
| 4412 |
+
"step": 6290
|
| 4413 |
+
},
|
| 4414 |
+
{
|
| 4415 |
+
"epoch": 3.20620853155977,
|
| 4416 |
+
"grad_norm": 0.12017529457807541,
|
| 4417 |
+
"learning_rate": 4.991050030330453e-05,
|
| 4418 |
+
"loss": 0.682,
|
| 4419 |
+
"step": 6300
|
| 4420 |
+
},
|
| 4421 |
+
{
|
| 4422 |
+
"epoch": 3.2113001002402584,
|
| 4423 |
+
"grad_norm": 0.14782628417015076,
|
| 4424 |
+
"learning_rate": 4.9910358240293904e-05,
|
| 4425 |
+
"loss": 0.6781,
|
| 4426 |
+
"step": 6310
|
| 4427 |
+
},
|
| 4428 |
+
{
|
| 4429 |
+
"epoch": 3.2163916689207466,
|
| 4430 |
+
"grad_norm": 0.14653240144252777,
|
| 4431 |
+
"learning_rate": 4.991021617728328e-05,
|
| 4432 |
+
"loss": 0.6809,
|
| 4433 |
+
"step": 6320
|
| 4434 |
+
},
|
| 4435 |
+
{
|
| 4436 |
+
"epoch": 3.221483237601235,
|
| 4437 |
+
"grad_norm": 0.12069736421108246,
|
| 4438 |
+
"learning_rate": 4.991007411427265e-05,
|
| 4439 |
+
"loss": 0.6811,
|
| 4440 |
+
"step": 6330
|
| 4441 |
+
},
|
| 4442 |
+
{
|
| 4443 |
+
"epoch": 3.226574806281723,
|
| 4444 |
+
"grad_norm": 0.13772337138652802,
|
| 4445 |
+
"learning_rate": 4.990993205126202e-05,
|
| 4446 |
+
"loss": 0.6838,
|
| 4447 |
+
"step": 6340
|
| 4448 |
+
},
|
| 4449 |
+
{
|
| 4450 |
+
"epoch": 3.231666374962211,
|
| 4451 |
+
"grad_norm": 0.10374171286821365,
|
| 4452 |
+
"learning_rate": 4.9909789988251396e-05,
|
| 4453 |
+
"loss": 0.6836,
|
| 4454 |
+
"step": 6350
|
| 4455 |
+
},
|
| 4456 |
+
{
|
| 4457 |
+
"epoch": 3.236757943642699,
|
| 4458 |
+
"grad_norm": 0.11860493570566177,
|
| 4459 |
+
"learning_rate": 4.990964792524076e-05,
|
| 4460 |
+
"loss": 0.6778,
|
| 4461 |
+
"step": 6360
|
| 4462 |
+
},
|
| 4463 |
+
{
|
| 4464 |
+
"epoch": 3.241849512323187,
|
| 4465 |
+
"grad_norm": 0.1429886519908905,
|
| 4466 |
+
"learning_rate": 4.9909505862230135e-05,
|
| 4467 |
+
"loss": 0.6775,
|
| 4468 |
+
"step": 6370
|
| 4469 |
+
},
|
| 4470 |
+
{
|
| 4471 |
+
"epoch": 3.2469410810036754,
|
| 4472 |
+
"grad_norm": 0.1501941680908203,
|
| 4473 |
+
"learning_rate": 4.990936379921951e-05,
|
| 4474 |
+
"loss": 0.6804,
|
| 4475 |
+
"step": 6380
|
| 4476 |
+
},
|
| 4477 |
+
{
|
| 4478 |
+
"epoch": 3.2520326496841636,
|
| 4479 |
+
"grad_norm": 0.12676025927066803,
|
| 4480 |
+
"learning_rate": 4.990922173620888e-05,
|
| 4481 |
+
"loss": 0.6802,
|
| 4482 |
+
"step": 6390
|
| 4483 |
+
},
|
| 4484 |
+
{
|
| 4485 |
+
"epoch": 3.257124218364652,
|
| 4486 |
+
"grad_norm": 0.14346669614315033,
|
| 4487 |
+
"learning_rate": 4.990907967319825e-05,
|
| 4488 |
+
"loss": 0.6815,
|
| 4489 |
+
"step": 6400
|
| 4490 |
+
},
|
| 4491 |
+
{
|
| 4492 |
+
"epoch": 3.26221578704514,
|
| 4493 |
+
"grad_norm": 0.11594365537166595,
|
| 4494 |
+
"learning_rate": 4.990893761018762e-05,
|
| 4495 |
+
"loss": 0.6783,
|
| 4496 |
+
"step": 6410
|
| 4497 |
+
},
|
| 4498 |
+
{
|
| 4499 |
+
"epoch": 3.2673073557256282,
|
| 4500 |
+
"grad_norm": 0.12863503396511078,
|
| 4501 |
+
"learning_rate": 4.9908795547176994e-05,
|
| 4502 |
+
"loss": 0.68,
|
| 4503 |
+
"step": 6420
|
| 4504 |
+
},
|
| 4505 |
+
{
|
| 4506 |
+
"epoch": 3.272398924406116,
|
| 4507 |
+
"grad_norm": 0.13634729385375977,
|
| 4508 |
+
"learning_rate": 4.990865348416637e-05,
|
| 4509 |
+
"loss": 0.6795,
|
| 4510 |
+
"step": 6430
|
| 4511 |
+
},
|
| 4512 |
+
{
|
| 4513 |
+
"epoch": 3.2774904930866042,
|
| 4514 |
+
"grad_norm": 0.10696328431367874,
|
| 4515 |
+
"learning_rate": 4.990851142115574e-05,
|
| 4516 |
+
"loss": 0.6827,
|
| 4517 |
+
"step": 6440
|
| 4518 |
+
},
|
| 4519 |
+
{
|
| 4520 |
+
"epoch": 3.2825820617670924,
|
| 4521 |
+
"grad_norm": 0.1048332154750824,
|
| 4522 |
+
"learning_rate": 4.9908369358145113e-05,
|
| 4523 |
+
"loss": 0.6812,
|
| 4524 |
+
"step": 6450
|
| 4525 |
+
},
|
| 4526 |
+
{
|
| 4527 |
+
"epoch": 3.2876736304475807,
|
| 4528 |
+
"grad_norm": 0.09791410714387894,
|
| 4529 |
+
"learning_rate": 4.9908227295134487e-05,
|
| 4530 |
+
"loss": 0.6848,
|
| 4531 |
+
"step": 6460
|
| 4532 |
+
},
|
| 4533 |
+
{
|
| 4534 |
+
"epoch": 3.292765199128069,
|
| 4535 |
+
"grad_norm": 0.13385730981826782,
|
| 4536 |
+
"learning_rate": 4.990808523212386e-05,
|
| 4537 |
+
"loss": 0.6826,
|
| 4538 |
+
"step": 6470
|
| 4539 |
+
},
|
| 4540 |
+
{
|
| 4541 |
+
"epoch": 3.297856767808557,
|
| 4542 |
+
"grad_norm": 0.13646642863750458,
|
| 4543 |
+
"learning_rate": 4.990794316911323e-05,
|
| 4544 |
+
"loss": 0.6767,
|
| 4545 |
+
"step": 6480
|
| 4546 |
+
},
|
| 4547 |
+
{
|
| 4548 |
+
"epoch": 3.3029483364890453,
|
| 4549 |
+
"grad_norm": 0.14173270761966705,
|
| 4550 |
+
"learning_rate": 4.9907801106102606e-05,
|
| 4551 |
+
"loss": 0.6838,
|
| 4552 |
+
"step": 6490
|
| 4553 |
+
},
|
| 4554 |
+
{
|
| 4555 |
+
"epoch": 3.3080399051695335,
|
| 4556 |
+
"grad_norm": 0.14603695273399353,
|
| 4557 |
+
"learning_rate": 4.990765904309197e-05,
|
| 4558 |
+
"loss": 0.6766,
|
| 4559 |
+
"step": 6500
|
| 4560 |
+
},
|
| 4561 |
+
{
|
| 4562 |
+
"epoch": 3.3131314738500217,
|
| 4563 |
+
"grad_norm": 0.138224795460701,
|
| 4564 |
+
"learning_rate": 4.9907516980081345e-05,
|
| 4565 |
+
"loss": 0.6797,
|
| 4566 |
+
"step": 6510
|
| 4567 |
+
},
|
| 4568 |
+
{
|
| 4569 |
+
"epoch": 3.3182230425305095,
|
| 4570 |
+
"grad_norm": 0.11541623622179031,
|
| 4571 |
+
"learning_rate": 4.990737491707072e-05,
|
| 4572 |
+
"loss": 0.6814,
|
| 4573 |
+
"step": 6520
|
| 4574 |
+
},
|
| 4575 |
+
{
|
| 4576 |
+
"epoch": 3.3233146112109977,
|
| 4577 |
+
"grad_norm": 0.1160949096083641,
|
| 4578 |
+
"learning_rate": 4.990723285406009e-05,
|
| 4579 |
+
"loss": 0.6842,
|
| 4580 |
+
"step": 6530
|
| 4581 |
+
},
|
| 4582 |
+
{
|
| 4583 |
+
"epoch": 3.328406179891486,
|
| 4584 |
+
"grad_norm": 0.1572464108467102,
|
| 4585 |
+
"learning_rate": 4.9907090791049465e-05,
|
| 4586 |
+
"loss": 0.6783,
|
| 4587 |
+
"step": 6540
|
| 4588 |
+
},
|
| 4589 |
+
{
|
| 4590 |
+
"epoch": 3.333497748571974,
|
| 4591 |
+
"grad_norm": 0.13026835024356842,
|
| 4592 |
+
"learning_rate": 4.990694872803884e-05,
|
| 4593 |
+
"loss": 0.681,
|
| 4594 |
+
"step": 6550
|
| 4595 |
+
},
|
| 4596 |
+
{
|
| 4597 |
+
"epoch": 3.3385893172524623,
|
| 4598 |
+
"grad_norm": 0.11961708962917328,
|
| 4599 |
+
"learning_rate": 4.990680666502821e-05,
|
| 4600 |
+
"loss": 0.6807,
|
| 4601 |
+
"step": 6560
|
| 4602 |
+
},
|
| 4603 |
+
{
|
| 4604 |
+
"epoch": 3.3436808859329505,
|
| 4605 |
+
"grad_norm": 0.11406982690095901,
|
| 4606 |
+
"learning_rate": 4.9906664602017584e-05,
|
| 4607 |
+
"loss": 0.6795,
|
| 4608 |
+
"step": 6570
|
| 4609 |
+
},
|
| 4610 |
+
{
|
| 4611 |
+
"epoch": 3.3487724546134388,
|
| 4612 |
+
"grad_norm": 0.20744380354881287,
|
| 4613 |
+
"learning_rate": 4.990652253900696e-05,
|
| 4614 |
+
"loss": 0.6771,
|
| 4615 |
+
"step": 6580
|
| 4616 |
+
},
|
| 4617 |
+
{
|
| 4618 |
+
"epoch": 3.3538640232939265,
|
| 4619 |
+
"grad_norm": 0.11253584921360016,
|
| 4620 |
+
"learning_rate": 4.990638047599633e-05,
|
| 4621 |
+
"loss": 0.6802,
|
| 4622 |
+
"step": 6590
|
| 4623 |
+
},
|
| 4624 |
+
{
|
| 4625 |
+
"epoch": 3.3589555919744147,
|
| 4626 |
+
"grad_norm": 0.08123784512281418,
|
| 4627 |
+
"learning_rate": 4.99062384129857e-05,
|
| 4628 |
+
"loss": 0.6871,
|
| 4629 |
+
"step": 6600
|
| 4630 |
+
},
|
| 4631 |
+
{
|
| 4632 |
+
"epoch": 3.364047160654903,
|
| 4633 |
+
"grad_norm": 0.10802698135375977,
|
| 4634 |
+
"learning_rate": 4.990609634997507e-05,
|
| 4635 |
+
"loss": 0.683,
|
| 4636 |
+
"step": 6610
|
| 4637 |
+
},
|
| 4638 |
+
{
|
| 4639 |
+
"epoch": 3.369138729335391,
|
| 4640 |
+
"grad_norm": 0.11430787295103073,
|
| 4641 |
+
"learning_rate": 4.990595428696444e-05,
|
| 4642 |
+
"loss": 0.6821,
|
| 4643 |
+
"step": 6620
|
| 4644 |
+
},
|
| 4645 |
+
{
|
| 4646 |
+
"epoch": 3.3742302980158794,
|
| 4647 |
+
"grad_norm": 0.09323684871196747,
|
| 4648 |
+
"learning_rate": 4.9905812223953816e-05,
|
| 4649 |
+
"loss": 0.6836,
|
| 4650 |
+
"step": 6630
|
| 4651 |
+
},
|
| 4652 |
+
{
|
| 4653 |
+
"epoch": 3.3793218666963676,
|
| 4654 |
+
"grad_norm": 0.10404845327138901,
|
| 4655 |
+
"learning_rate": 4.990567016094318e-05,
|
| 4656 |
+
"loss": 0.6849,
|
| 4657 |
+
"step": 6640
|
| 4658 |
+
},
|
| 4659 |
+
{
|
| 4660 |
+
"epoch": 3.384413435376856,
|
| 4661 |
+
"grad_norm": 0.1404566615819931,
|
| 4662 |
+
"learning_rate": 4.9905528097932555e-05,
|
| 4663 |
+
"loss": 0.6769,
|
| 4664 |
+
"step": 6650
|
| 4665 |
+
},
|
| 4666 |
+
{
|
| 4667 |
+
"epoch": 3.3895050040573436,
|
| 4668 |
+
"grad_norm": 0.17702195048332214,
|
| 4669 |
+
"learning_rate": 4.990538603492193e-05,
|
| 4670 |
+
"loss": 0.6808,
|
| 4671 |
+
"step": 6660
|
| 4672 |
+
},
|
| 4673 |
+
{
|
| 4674 |
+
"epoch": 3.3945965727378318,
|
| 4675 |
+
"grad_norm": 0.1227133646607399,
|
| 4676 |
+
"learning_rate": 4.99052439719113e-05,
|
| 4677 |
+
"loss": 0.6855,
|
| 4678 |
+
"step": 6670
|
| 4679 |
+
},
|
| 4680 |
+
{
|
| 4681 |
+
"epoch": 3.39968814141832,
|
| 4682 |
+
"grad_norm": 0.0946226418018341,
|
| 4683 |
+
"learning_rate": 4.9905101908900675e-05,
|
| 4684 |
+
"loss": 0.6804,
|
| 4685 |
+
"step": 6680
|
| 4686 |
+
},
|
| 4687 |
+
{
|
| 4688 |
+
"epoch": 3.404779710098808,
|
| 4689 |
+
"grad_norm": 0.11467920988798141,
|
| 4690 |
+
"learning_rate": 4.990495984589005e-05,
|
| 4691 |
+
"loss": 0.677,
|
| 4692 |
+
"step": 6690
|
| 4693 |
+
},
|
| 4694 |
+
{
|
| 4695 |
+
"epoch": 3.4098712787792964,
|
| 4696 |
+
"grad_norm": 0.1885383576154709,
|
| 4697 |
+
"learning_rate": 4.990481778287942e-05,
|
| 4698 |
+
"loss": 0.6786,
|
| 4699 |
+
"step": 6700
|
| 4700 |
+
},
|
| 4701 |
+
{
|
| 4702 |
+
"epoch": 3.4149628474597846,
|
| 4703 |
+
"grad_norm": 0.0994097888469696,
|
| 4704 |
+
"learning_rate": 4.9904675719868794e-05,
|
| 4705 |
+
"loss": 0.6908,
|
| 4706 |
+
"step": 6710
|
| 4707 |
+
},
|
| 4708 |
+
{
|
| 4709 |
+
"epoch": 3.420054416140273,
|
| 4710 |
+
"grad_norm": 0.09989442676305771,
|
| 4711 |
+
"learning_rate": 4.990453365685817e-05,
|
| 4712 |
+
"loss": 0.6804,
|
| 4713 |
+
"step": 6720
|
| 4714 |
+
},
|
| 4715 |
+
{
|
| 4716 |
+
"epoch": 3.425145984820761,
|
| 4717 |
+
"grad_norm": 0.12362310290336609,
|
| 4718 |
+
"learning_rate": 4.990439159384754e-05,
|
| 4719 |
+
"loss": 0.6817,
|
| 4720 |
+
"step": 6730
|
| 4721 |
+
},
|
| 4722 |
+
{
|
| 4723 |
+
"epoch": 3.4302375535012493,
|
| 4724 |
+
"grad_norm": 0.13228794932365417,
|
| 4725 |
+
"learning_rate": 4.990424953083691e-05,
|
| 4726 |
+
"loss": 0.681,
|
| 4727 |
+
"step": 6740
|
| 4728 |
+
},
|
| 4729 |
+
{
|
| 4730 |
+
"epoch": 3.435329122181737,
|
| 4731 |
+
"grad_norm": 0.11642909795045853,
|
| 4732 |
+
"learning_rate": 4.9904107467826286e-05,
|
| 4733 |
+
"loss": 0.6825,
|
| 4734 |
+
"step": 6750
|
| 4735 |
+
},
|
| 4736 |
+
{
|
| 4737 |
+
"epoch": 3.4404206908622252,
|
| 4738 |
+
"grad_norm": 0.12548530101776123,
|
| 4739 |
+
"learning_rate": 4.990396540481565e-05,
|
| 4740 |
+
"loss": 0.6814,
|
| 4741 |
+
"step": 6760
|
| 4742 |
+
},
|
| 4743 |
+
{
|
| 4744 |
+
"epoch": 3.4455122595427135,
|
| 4745 |
+
"grad_norm": 0.11513999849557877,
|
| 4746 |
+
"learning_rate": 4.9903823341805026e-05,
|
| 4747 |
+
"loss": 0.6792,
|
| 4748 |
+
"step": 6770
|
| 4749 |
+
},
|
| 4750 |
+
{
|
| 4751 |
+
"epoch": 3.4506038282232017,
|
| 4752 |
+
"grad_norm": 0.12245498597621918,
|
| 4753 |
+
"learning_rate": 4.99036812787944e-05,
|
| 4754 |
+
"loss": 0.6771,
|
| 4755 |
+
"step": 6780
|
| 4756 |
+
},
|
| 4757 |
+
{
|
| 4758 |
+
"epoch": 3.45569539690369,
|
| 4759 |
+
"grad_norm": 0.12722285091876984,
|
| 4760 |
+
"learning_rate": 4.990353921578377e-05,
|
| 4761 |
+
"loss": 0.679,
|
| 4762 |
+
"step": 6790
|
| 4763 |
+
},
|
| 4764 |
+
{
|
| 4765 |
+
"epoch": 3.460786965584178,
|
| 4766 |
+
"grad_norm": 0.13212384283542633,
|
| 4767 |
+
"learning_rate": 4.9903397152773145e-05,
|
| 4768 |
+
"loss": 0.6818,
|
| 4769 |
+
"step": 6800
|
| 4770 |
+
},
|
| 4771 |
+
{
|
| 4772 |
+
"epoch": 3.4658785342646663,
|
| 4773 |
+
"grad_norm": 0.11193917691707611,
|
| 4774 |
+
"learning_rate": 4.990325508976252e-05,
|
| 4775 |
+
"loss": 0.6822,
|
| 4776 |
+
"step": 6810
|
| 4777 |
+
},
|
| 4778 |
+
{
|
| 4779 |
+
"epoch": 3.470970102945154,
|
| 4780 |
+
"grad_norm": 0.14051009714603424,
|
| 4781 |
+
"learning_rate": 4.9903113026751884e-05,
|
| 4782 |
+
"loss": 0.673,
|
| 4783 |
+
"step": 6820
|
| 4784 |
+
},
|
| 4785 |
+
{
|
| 4786 |
+
"epoch": 3.4760616716256423,
|
| 4787 |
+
"grad_norm": 0.16787344217300415,
|
| 4788 |
+
"learning_rate": 4.990297096374126e-05,
|
| 4789 |
+
"loss": 0.6834,
|
| 4790 |
+
"step": 6830
|
| 4791 |
+
},
|
| 4792 |
+
{
|
| 4793 |
+
"epoch": 3.4811532403061305,
|
| 4794 |
+
"grad_norm": 0.1313748061656952,
|
| 4795 |
+
"learning_rate": 4.990282890073063e-05,
|
| 4796 |
+
"loss": 0.6785,
|
| 4797 |
+
"step": 6840
|
| 4798 |
+
},
|
| 4799 |
+
{
|
| 4800 |
+
"epoch": 3.4862448089866187,
|
| 4801 |
+
"grad_norm": 0.13282889127731323,
|
| 4802 |
+
"learning_rate": 4.9902686837720004e-05,
|
| 4803 |
+
"loss": 0.6791,
|
| 4804 |
+
"step": 6850
|
| 4805 |
+
},
|
| 4806 |
+
{
|
| 4807 |
+
"epoch": 3.491336377667107,
|
| 4808 |
+
"grad_norm": 0.15743672847747803,
|
| 4809 |
+
"learning_rate": 4.990254477470938e-05,
|
| 4810 |
+
"loss": 0.685,
|
| 4811 |
+
"step": 6860
|
| 4812 |
+
},
|
| 4813 |
+
{
|
| 4814 |
+
"epoch": 3.496427946347595,
|
| 4815 |
+
"grad_norm": 0.09886245429515839,
|
| 4816 |
+
"learning_rate": 4.990240271169875e-05,
|
| 4817 |
+
"loss": 0.6831,
|
| 4818 |
+
"step": 6870
|
| 4819 |
+
},
|
| 4820 |
+
{
|
| 4821 |
+
"epoch": 3.5015195150280833,
|
| 4822 |
+
"grad_norm": 0.14891770482063293,
|
| 4823 |
+
"learning_rate": 4.990226064868812e-05,
|
| 4824 |
+
"loss": 0.681,
|
| 4825 |
+
"step": 6880
|
| 4826 |
+
},
|
| 4827 |
+
{
|
| 4828 |
+
"epoch": 3.506611083708571,
|
| 4829 |
+
"grad_norm": 0.13956576585769653,
|
| 4830 |
+
"learning_rate": 4.9902118585677496e-05,
|
| 4831 |
+
"loss": 0.6806,
|
| 4832 |
+
"step": 6890
|
| 4833 |
+
},
|
| 4834 |
+
{
|
| 4835 |
+
"epoch": 3.5117026523890598,
|
| 4836 |
+
"grad_norm": 0.1325678676366806,
|
| 4837 |
+
"learning_rate": 4.990197652266686e-05,
|
| 4838 |
+
"loss": 0.6809,
|
| 4839 |
+
"step": 6900
|
| 4840 |
+
},
|
| 4841 |
+
{
|
| 4842 |
+
"epoch": 3.5167942210695475,
|
| 4843 |
+
"grad_norm": 0.13164210319519043,
|
| 4844 |
+
"learning_rate": 4.9901834459656236e-05,
|
| 4845 |
+
"loss": 0.6822,
|
| 4846 |
+
"step": 6910
|
| 4847 |
+
},
|
| 4848 |
+
{
|
| 4849 |
+
"epoch": 3.5218857897500357,
|
| 4850 |
+
"grad_norm": 0.13481168448925018,
|
| 4851 |
+
"learning_rate": 4.990169239664561e-05,
|
| 4852 |
+
"loss": 0.673,
|
| 4853 |
+
"step": 6920
|
| 4854 |
+
},
|
| 4855 |
+
{
|
| 4856 |
+
"epoch": 3.526977358430524,
|
| 4857 |
+
"grad_norm": 0.16314196586608887,
|
| 4858 |
+
"learning_rate": 4.990155033363498e-05,
|
| 4859 |
+
"loss": 0.6768,
|
| 4860 |
+
"step": 6930
|
| 4861 |
+
},
|
| 4862 |
+
{
|
| 4863 |
+
"epoch": 3.532068927111012,
|
| 4864 |
+
"grad_norm": 0.1418369710445404,
|
| 4865 |
+
"learning_rate": 4.9901408270624355e-05,
|
| 4866 |
+
"loss": 0.6777,
|
| 4867 |
+
"step": 6940
|
| 4868 |
+
},
|
| 4869 |
+
{
|
| 4870 |
+
"epoch": 3.5371604957915004,
|
| 4871 |
+
"grad_norm": 0.12762701511383057,
|
| 4872 |
+
"learning_rate": 4.990126620761373e-05,
|
| 4873 |
+
"loss": 0.6788,
|
| 4874 |
+
"step": 6950
|
| 4875 |
+
},
|
| 4876 |
+
{
|
| 4877 |
+
"epoch": 3.542252064471988,
|
| 4878 |
+
"grad_norm": 0.10353351384401321,
|
| 4879 |
+
"learning_rate": 4.99011241446031e-05,
|
| 4880 |
+
"loss": 0.6858,
|
| 4881 |
+
"step": 6960
|
| 4882 |
+
},
|
| 4883 |
+
{
|
| 4884 |
+
"epoch": 3.547343633152477,
|
| 4885 |
+
"grad_norm": 0.0953698605298996,
|
| 4886 |
+
"learning_rate": 4.9900982081592474e-05,
|
| 4887 |
+
"loss": 0.6783,
|
| 4888 |
+
"step": 6970
|
| 4889 |
+
},
|
| 4890 |
+
{
|
| 4891 |
+
"epoch": 3.5524352018329646,
|
| 4892 |
+
"grad_norm": 0.10428538918495178,
|
| 4893 |
+
"learning_rate": 4.990084001858185e-05,
|
| 4894 |
+
"loss": 0.6844,
|
| 4895 |
+
"step": 6980
|
| 4896 |
+
},
|
| 4897 |
+
{
|
| 4898 |
+
"epoch": 3.557526770513453,
|
| 4899 |
+
"grad_norm": 0.11740399152040482,
|
| 4900 |
+
"learning_rate": 4.990069795557122e-05,
|
| 4901 |
+
"loss": 0.6838,
|
| 4902 |
+
"step": 6990
|
| 4903 |
+
},
|
| 4904 |
+
{
|
| 4905 |
+
"epoch": 3.562618339193941,
|
| 4906 |
+
"grad_norm": 0.12733303010463715,
|
| 4907 |
+
"learning_rate": 4.9900555892560594e-05,
|
| 4908 |
+
"loss": 0.6768,
|
| 4909 |
+
"step": 7000
|
| 4910 |
}
|
| 4911 |
],
|
| 4912 |
"logging_steps": 10,
|