Instructions to use kurtpayne/skillscan-deberta-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use kurtpayne/skillscan-deberta-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("answerdotai/ModernBERT-base") model = PeftModel.from_pretrained(base_model, "kurtpayne/skillscan-deberta-adapter") - Transformers
How to use kurtpayne/skillscan-deberta-adapter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="kurtpayne/skillscan-deberta-adapter")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kurtpayne/skillscan-deberta-adapter") model = AutoModelForSequenceClassification.from_pretrained("kurtpayne/skillscan-deberta-adapter") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 5, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41326816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d1433d4e4339e2841a40e263c888bec9f25cfe7bdb630a06cfa160acd0e881e
|
| 3 |
size 41326816
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 82710219
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ab4431a5db8d23049c17ead1ee12d4b9b0e467426a295bdebdf54b00096c9fe
|
| 3 |
size 82710219
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b5b218011616df264922fa5ac76d9d4bfced159ec4ab13de08b3483606f3f2
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f18de9d18d2a2e6be549612c0bb1e2a24d9b75770502f7a5c001184a16c40414
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c82f734f517a2798e2d64427ec70011ea213131c5b83d8ea95de6baca42b2fd6
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 7578,
|
| 3 |
"best_metric": 0.014301872812211514,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpe4p6q40s/adapter-multilabel/checkpoint-7578",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -7110,6 +7110,1785 @@
|
|
| 7110 |
"eval_samples_per_second": 186.334,
|
| 7111 |
"eval_steps_per_second": 23.312,
|
| 7112 |
"step": 10104
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7113 |
}
|
| 7114 |
],
|
| 7115 |
"logging_steps": 10,
|
|
@@ -7124,7 +8903,7 @@
|
|
| 7124 |
"early_stopping_threshold": 0.0
|
| 7125 |
},
|
| 7126 |
"attributes": {
|
| 7127 |
-
"early_stopping_patience_counter":
|
| 7128 |
}
|
| 7129 |
},
|
| 7130 |
"TrainerControl": {
|
|
@@ -7133,12 +8912,12 @@
|
|
| 7133 |
"should_evaluate": false,
|
| 7134 |
"should_log": false,
|
| 7135 |
"should_save": true,
|
| 7136 |
-
"should_training_stop":
|
| 7137 |
},
|
| 7138 |
"attributes": {}
|
| 7139 |
}
|
| 7140 |
},
|
| 7141 |
-
"total_flos": 2.
|
| 7142 |
"train_batch_size": 8,
|
| 7143 |
"trial_name": null,
|
| 7144 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 7578,
|
| 3 |
"best_metric": 0.014301872812211514,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpe4p6q40s/adapter-multilabel/checkpoint-7578",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7110 |
"eval_samples_per_second": 186.334,
|
| 7111 |
"eval_steps_per_second": 23.312,
|
| 7112 |
"step": 10104
|
| 7113 |
+
},
|
| 7114 |
+
{
|
| 7115 |
+
"epoch": 4.002375296912114,
|
| 7116 |
+
"grad_norm": 0.025458339601755142,
|
| 7117 |
+
"learning_rate": 3.3267352863552386e-06,
|
| 7118 |
+
"loss": 0.0176,
|
| 7119 |
+
"step": 10110
|
| 7120 |
+
},
|
| 7121 |
+
{
|
| 7122 |
+
"epoch": 4.006334125098971,
|
| 7123 |
+
"grad_norm": 0.693576455116272,
|
| 7124 |
+
"learning_rate": 3.31353919239905e-06,
|
| 7125 |
+
"loss": 0.0358,
|
| 7126 |
+
"step": 10120
|
| 7127 |
+
},
|
| 7128 |
+
{
|
| 7129 |
+
"epoch": 4.010292953285828,
|
| 7130 |
+
"grad_norm": 0.3112759590148926,
|
| 7131 |
+
"learning_rate": 3.3003430984428613e-06,
|
| 7132 |
+
"loss": 0.0137,
|
| 7133 |
+
"step": 10130
|
| 7134 |
+
},
|
| 7135 |
+
{
|
| 7136 |
+
"epoch": 4.014251781472684,
|
| 7137 |
+
"grad_norm": 0.21676863729953766,
|
| 7138 |
+
"learning_rate": 3.287147004486672e-06,
|
| 7139 |
+
"loss": 0.009,
|
| 7140 |
+
"step": 10140
|
| 7141 |
+
},
|
| 7142 |
+
{
|
| 7143 |
+
"epoch": 4.0182106096595405,
|
| 7144 |
+
"grad_norm": 0.02533499151468277,
|
| 7145 |
+
"learning_rate": 3.273950910530483e-06,
|
| 7146 |
+
"loss": 0.0018,
|
| 7147 |
+
"step": 10150
|
| 7148 |
+
},
|
| 7149 |
+
{
|
| 7150 |
+
"epoch": 4.022169437846397,
|
| 7151 |
+
"grad_norm": 0.038250651210546494,
|
| 7152 |
+
"learning_rate": 3.2607548165742945e-06,
|
| 7153 |
+
"loss": 0.0105,
|
| 7154 |
+
"step": 10160
|
| 7155 |
+
},
|
| 7156 |
+
{
|
| 7157 |
+
"epoch": 4.026128266033254,
|
| 7158 |
+
"grad_norm": 2.936196804046631,
|
| 7159 |
+
"learning_rate": 3.2475587226181054e-06,
|
| 7160 |
+
"loss": 0.019,
|
| 7161 |
+
"step": 10170
|
| 7162 |
+
},
|
| 7163 |
+
{
|
| 7164 |
+
"epoch": 4.030087094220111,
|
| 7165 |
+
"grad_norm": 0.04230177402496338,
|
| 7166 |
+
"learning_rate": 3.2343626286619163e-06,
|
| 7167 |
+
"loss": 0.0018,
|
| 7168 |
+
"step": 10180
|
| 7169 |
+
},
|
| 7170 |
+
{
|
| 7171 |
+
"epoch": 4.034045922406968,
|
| 7172 |
+
"grad_norm": 0.9019578099250793,
|
| 7173 |
+
"learning_rate": 3.2211665347057272e-06,
|
| 7174 |
+
"loss": 0.0034,
|
| 7175 |
+
"step": 10190
|
| 7176 |
+
},
|
| 7177 |
+
{
|
| 7178 |
+
"epoch": 4.038004750593824,
|
| 7179 |
+
"grad_norm": 0.015337091870605946,
|
| 7180 |
+
"learning_rate": 3.207970440749538e-06,
|
| 7181 |
+
"loss": 0.0017,
|
| 7182 |
+
"step": 10200
|
| 7183 |
+
},
|
| 7184 |
+
{
|
| 7185 |
+
"epoch": 4.041963578780681,
|
| 7186 |
+
"grad_norm": 0.007164216134697199,
|
| 7187 |
+
"learning_rate": 3.1947743467933495e-06,
|
| 7188 |
+
"loss": 0.0104,
|
| 7189 |
+
"step": 10210
|
| 7190 |
+
},
|
| 7191 |
+
{
|
| 7192 |
+
"epoch": 4.045922406967538,
|
| 7193 |
+
"grad_norm": 0.003774322336539626,
|
| 7194 |
+
"learning_rate": 3.1815782528371604e-06,
|
| 7195 |
+
"loss": 0.0021,
|
| 7196 |
+
"step": 10220
|
| 7197 |
+
},
|
| 7198 |
+
{
|
| 7199 |
+
"epoch": 4.049881235154395,
|
| 7200 |
+
"grad_norm": 0.008863361552357674,
|
| 7201 |
+
"learning_rate": 3.1683821588809713e-06,
|
| 7202 |
+
"loss": 0.001,
|
| 7203 |
+
"step": 10230
|
| 7204 |
+
},
|
| 7205 |
+
{
|
| 7206 |
+
"epoch": 4.053840063341251,
|
| 7207 |
+
"grad_norm": 0.09657549113035202,
|
| 7208 |
+
"learning_rate": 3.1551860649247822e-06,
|
| 7209 |
+
"loss": 0.0099,
|
| 7210 |
+
"step": 10240
|
| 7211 |
+
},
|
| 7212 |
+
{
|
| 7213 |
+
"epoch": 4.057798891528107,
|
| 7214 |
+
"grad_norm": 0.08302096277475357,
|
| 7215 |
+
"learning_rate": 3.1419899709685936e-06,
|
| 7216 |
+
"loss": 0.0302,
|
| 7217 |
+
"step": 10250
|
| 7218 |
+
},
|
| 7219 |
+
{
|
| 7220 |
+
"epoch": 4.061757719714964,
|
| 7221 |
+
"grad_norm": 0.09942620992660522,
|
| 7222 |
+
"learning_rate": 3.1287938770124045e-06,
|
| 7223 |
+
"loss": 0.0152,
|
| 7224 |
+
"step": 10260
|
| 7225 |
+
},
|
| 7226 |
+
{
|
| 7227 |
+
"epoch": 4.065716547901821,
|
| 7228 |
+
"grad_norm": 0.13514858484268188,
|
| 7229 |
+
"learning_rate": 3.1155977830562154e-06,
|
| 7230 |
+
"loss": 0.0125,
|
| 7231 |
+
"step": 10270
|
| 7232 |
+
},
|
| 7233 |
+
{
|
| 7234 |
+
"epoch": 4.069675376088678,
|
| 7235 |
+
"grad_norm": 0.020670639351010323,
|
| 7236 |
+
"learning_rate": 3.1024016891000264e-06,
|
| 7237 |
+
"loss": 0.0086,
|
| 7238 |
+
"step": 10280
|
| 7239 |
+
},
|
| 7240 |
+
{
|
| 7241 |
+
"epoch": 4.0736342042755345,
|
| 7242 |
+
"grad_norm": 0.07322364300489426,
|
| 7243 |
+
"learning_rate": 3.0892055951438373e-06,
|
| 7244 |
+
"loss": 0.02,
|
| 7245 |
+
"step": 10290
|
| 7246 |
+
},
|
| 7247 |
+
{
|
| 7248 |
+
"epoch": 4.077593032462391,
|
| 7249 |
+
"grad_norm": 0.340831995010376,
|
| 7250 |
+
"learning_rate": 3.0760095011876486e-06,
|
| 7251 |
+
"loss": 0.013,
|
| 7252 |
+
"step": 10300
|
| 7253 |
+
},
|
| 7254 |
+
{
|
| 7255 |
+
"epoch": 4.081551860649248,
|
| 7256 |
+
"grad_norm": 0.01248082984238863,
|
| 7257 |
+
"learning_rate": 3.0628134072314595e-06,
|
| 7258 |
+
"loss": 0.0089,
|
| 7259 |
+
"step": 10310
|
| 7260 |
+
},
|
| 7261 |
+
{
|
| 7262 |
+
"epoch": 4.085510688836105,
|
| 7263 |
+
"grad_norm": 0.024720976129174232,
|
| 7264 |
+
"learning_rate": 3.0496173132752705e-06,
|
| 7265 |
+
"loss": 0.02,
|
| 7266 |
+
"step": 10320
|
| 7267 |
+
},
|
| 7268 |
+
{
|
| 7269 |
+
"epoch": 4.089469517022962,
|
| 7270 |
+
"grad_norm": 0.019353309646248817,
|
| 7271 |
+
"learning_rate": 3.0364212193190814e-06,
|
| 7272 |
+
"loss": 0.0019,
|
| 7273 |
+
"step": 10330
|
| 7274 |
+
},
|
| 7275 |
+
{
|
| 7276 |
+
"epoch": 4.0934283452098175,
|
| 7277 |
+
"grad_norm": 0.08675594627857208,
|
| 7278 |
+
"learning_rate": 3.0232251253628927e-06,
|
| 7279 |
+
"loss": 0.0202,
|
| 7280 |
+
"step": 10340
|
| 7281 |
+
},
|
| 7282 |
+
{
|
| 7283 |
+
"epoch": 4.097387173396674,
|
| 7284 |
+
"grad_norm": 0.2732747495174408,
|
| 7285 |
+
"learning_rate": 3.0100290314067037e-06,
|
| 7286 |
+
"loss": 0.0072,
|
| 7287 |
+
"step": 10350
|
| 7288 |
+
},
|
| 7289 |
+
{
|
| 7290 |
+
"epoch": 4.101346001583531,
|
| 7291 |
+
"grad_norm": 0.006827787961810827,
|
| 7292 |
+
"learning_rate": 2.9968329374505146e-06,
|
| 7293 |
+
"loss": 0.0016,
|
| 7294 |
+
"step": 10360
|
| 7295 |
+
},
|
| 7296 |
+
{
|
| 7297 |
+
"epoch": 4.105304829770388,
|
| 7298 |
+
"grad_norm": 0.03036872111260891,
|
| 7299 |
+
"learning_rate": 2.9836368434943255e-06,
|
| 7300 |
+
"loss": 0.0052,
|
| 7301 |
+
"step": 10370
|
| 7302 |
+
},
|
| 7303 |
+
{
|
| 7304 |
+
"epoch": 4.109263657957245,
|
| 7305 |
+
"grad_norm": 0.02737751416862011,
|
| 7306 |
+
"learning_rate": 2.970440749538137e-06,
|
| 7307 |
+
"loss": 0.0088,
|
| 7308 |
+
"step": 10380
|
| 7309 |
+
},
|
| 7310 |
+
{
|
| 7311 |
+
"epoch": 4.113222486144101,
|
| 7312 |
+
"grad_norm": 0.26449987292289734,
|
| 7313 |
+
"learning_rate": 2.9572446555819478e-06,
|
| 7314 |
+
"loss": 0.025,
|
| 7315 |
+
"step": 10390
|
| 7316 |
+
},
|
| 7317 |
+
{
|
| 7318 |
+
"epoch": 4.117181314330958,
|
| 7319 |
+
"grad_norm": 0.015447895973920822,
|
| 7320 |
+
"learning_rate": 2.9440485616257587e-06,
|
| 7321 |
+
"loss": 0.0064,
|
| 7322 |
+
"step": 10400
|
| 7323 |
+
},
|
| 7324 |
+
{
|
| 7325 |
+
"epoch": 4.121140142517815,
|
| 7326 |
+
"grad_norm": 0.48912787437438965,
|
| 7327 |
+
"learning_rate": 2.9308524676695696e-06,
|
| 7328 |
+
"loss": 0.0051,
|
| 7329 |
+
"step": 10410
|
| 7330 |
+
},
|
| 7331 |
+
{
|
| 7332 |
+
"epoch": 4.125098970704672,
|
| 7333 |
+
"grad_norm": 0.009630228392779827,
|
| 7334 |
+
"learning_rate": 2.9176563737133805e-06,
|
| 7335 |
+
"loss": 0.0006,
|
| 7336 |
+
"step": 10420
|
| 7337 |
+
},
|
| 7338 |
+
{
|
| 7339 |
+
"epoch": 4.1290577988915285,
|
| 7340 |
+
"grad_norm": 0.016364438459277153,
|
| 7341 |
+
"learning_rate": 2.904460279757192e-06,
|
| 7342 |
+
"loss": 0.0111,
|
| 7343 |
+
"step": 10430
|
| 7344 |
+
},
|
| 7345 |
+
{
|
| 7346 |
+
"epoch": 4.133016627078385,
|
| 7347 |
+
"grad_norm": 0.146970734000206,
|
| 7348 |
+
"learning_rate": 2.891264185801003e-06,
|
| 7349 |
+
"loss": 0.0158,
|
| 7350 |
+
"step": 10440
|
| 7351 |
+
},
|
| 7352 |
+
{
|
| 7353 |
+
"epoch": 4.136975455265241,
|
| 7354 |
+
"grad_norm": 0.01109443698078394,
|
| 7355 |
+
"learning_rate": 2.878068091844814e-06,
|
| 7356 |
+
"loss": 0.0111,
|
| 7357 |
+
"step": 10450
|
| 7358 |
+
},
|
| 7359 |
+
{
|
| 7360 |
+
"epoch": 4.140934283452098,
|
| 7361 |
+
"grad_norm": 1.858878254890442,
|
| 7362 |
+
"learning_rate": 2.864871997888625e-06,
|
| 7363 |
+
"loss": 0.0055,
|
| 7364 |
+
"step": 10460
|
| 7365 |
+
},
|
| 7366 |
+
{
|
| 7367 |
+
"epoch": 4.144893111638955,
|
| 7368 |
+
"grad_norm": 0.07197848707437515,
|
| 7369 |
+
"learning_rate": 2.8516759039324364e-06,
|
| 7370 |
+
"loss": 0.0012,
|
| 7371 |
+
"step": 10470
|
| 7372 |
+
},
|
| 7373 |
+
{
|
| 7374 |
+
"epoch": 4.1488519398258115,
|
| 7375 |
+
"grad_norm": 0.0016396682476624846,
|
| 7376 |
+
"learning_rate": 2.8384798099762473e-06,
|
| 7377 |
+
"loss": 0.0415,
|
| 7378 |
+
"step": 10480
|
| 7379 |
+
},
|
| 7380 |
+
{
|
| 7381 |
+
"epoch": 4.152810768012668,
|
| 7382 |
+
"grad_norm": 0.006434198934584856,
|
| 7383 |
+
"learning_rate": 2.8252837160200583e-06,
|
| 7384 |
+
"loss": 0.0083,
|
| 7385 |
+
"step": 10490
|
| 7386 |
+
},
|
| 7387 |
+
{
|
| 7388 |
+
"epoch": 4.156769596199525,
|
| 7389 |
+
"grad_norm": 0.010171783156692982,
|
| 7390 |
+
"learning_rate": 2.812087622063869e-06,
|
| 7391 |
+
"loss": 0.0088,
|
| 7392 |
+
"step": 10500
|
| 7393 |
+
},
|
| 7394 |
+
{
|
| 7395 |
+
"epoch": 4.160728424386382,
|
| 7396 |
+
"grad_norm": 0.00399325555190444,
|
| 7397 |
+
"learning_rate": 2.7988915281076805e-06,
|
| 7398 |
+
"loss": 0.0255,
|
| 7399 |
+
"step": 10510
|
| 7400 |
+
},
|
| 7401 |
+
{
|
| 7402 |
+
"epoch": 4.164687252573239,
|
| 7403 |
+
"grad_norm": 1.4930006265640259,
|
| 7404 |
+
"learning_rate": 2.7856954341514914e-06,
|
| 7405 |
+
"loss": 0.0247,
|
| 7406 |
+
"step": 10520
|
| 7407 |
+
},
|
| 7408 |
+
{
|
| 7409 |
+
"epoch": 4.168646080760095,
|
| 7410 |
+
"grad_norm": 1.2947190999984741,
|
| 7411 |
+
"learning_rate": 2.7724993401953024e-06,
|
| 7412 |
+
"loss": 0.0049,
|
| 7413 |
+
"step": 10530
|
| 7414 |
+
},
|
| 7415 |
+
{
|
| 7416 |
+
"epoch": 4.172604908946952,
|
| 7417 |
+
"grad_norm": 0.3954826593399048,
|
| 7418 |
+
"learning_rate": 2.7593032462391133e-06,
|
| 7419 |
+
"loss": 0.02,
|
| 7420 |
+
"step": 10540
|
| 7421 |
+
},
|
| 7422 |
+
{
|
| 7423 |
+
"epoch": 4.176563737133808,
|
| 7424 |
+
"grad_norm": 2.7527806758880615,
|
| 7425 |
+
"learning_rate": 2.746107152282924e-06,
|
| 7426 |
+
"loss": 0.0187,
|
| 7427 |
+
"step": 10550
|
| 7428 |
+
},
|
| 7429 |
+
{
|
| 7430 |
+
"epoch": 4.180522565320665,
|
| 7431 |
+
"grad_norm": 0.0014982519205659628,
|
| 7432 |
+
"learning_rate": 2.7329110583267356e-06,
|
| 7433 |
+
"loss": 0.0152,
|
| 7434 |
+
"step": 10560
|
| 7435 |
+
},
|
| 7436 |
+
{
|
| 7437 |
+
"epoch": 4.184481393507522,
|
| 7438 |
+
"grad_norm": 0.1216762438416481,
|
| 7439 |
+
"learning_rate": 2.7197149643705465e-06,
|
| 7440 |
+
"loss": 0.0034,
|
| 7441 |
+
"step": 10570
|
| 7442 |
+
},
|
| 7443 |
+
{
|
| 7444 |
+
"epoch": 4.188440221694378,
|
| 7445 |
+
"grad_norm": 2.067582845687866,
|
| 7446 |
+
"learning_rate": 2.7065188704143574e-06,
|
| 7447 |
+
"loss": 0.0063,
|
| 7448 |
+
"step": 10580
|
| 7449 |
+
},
|
| 7450 |
+
{
|
| 7451 |
+
"epoch": 4.192399049881235,
|
| 7452 |
+
"grad_norm": 0.06368841975927353,
|
| 7453 |
+
"learning_rate": 2.6933227764581683e-06,
|
| 7454 |
+
"loss": 0.0042,
|
| 7455 |
+
"step": 10590
|
| 7456 |
+
},
|
| 7457 |
+
{
|
| 7458 |
+
"epoch": 4.196357878068092,
|
| 7459 |
+
"grad_norm": 0.017680363729596138,
|
| 7460 |
+
"learning_rate": 2.6801266825019797e-06,
|
| 7461 |
+
"loss": 0.0122,
|
| 7462 |
+
"step": 10600
|
| 7463 |
+
},
|
| 7464 |
+
{
|
| 7465 |
+
"epoch": 4.200316706254949,
|
| 7466 |
+
"grad_norm": 0.013119541108608246,
|
| 7467 |
+
"learning_rate": 2.6669305885457906e-06,
|
| 7468 |
+
"loss": 0.0071,
|
| 7469 |
+
"step": 10610
|
| 7470 |
+
},
|
| 7471 |
+
{
|
| 7472 |
+
"epoch": 4.2042755344418055,
|
| 7473 |
+
"grad_norm": 0.017275096848607063,
|
| 7474 |
+
"learning_rate": 2.6537344945896015e-06,
|
| 7475 |
+
"loss": 0.0162,
|
| 7476 |
+
"step": 10620
|
| 7477 |
+
},
|
| 7478 |
+
{
|
| 7479 |
+
"epoch": 4.208234362628662,
|
| 7480 |
+
"grad_norm": 0.13690078258514404,
|
| 7481 |
+
"learning_rate": 2.6405384006334124e-06,
|
| 7482 |
+
"loss": 0.0165,
|
| 7483 |
+
"step": 10630
|
| 7484 |
+
},
|
| 7485 |
+
{
|
| 7486 |
+
"epoch": 4.212193190815519,
|
| 7487 |
+
"grad_norm": 0.022821534425020218,
|
| 7488 |
+
"learning_rate": 2.6273423066772233e-06,
|
| 7489 |
+
"loss": 0.0013,
|
| 7490 |
+
"step": 10640
|
| 7491 |
+
},
|
| 7492 |
+
{
|
| 7493 |
+
"epoch": 4.216152019002375,
|
| 7494 |
+
"grad_norm": 0.0382111519575119,
|
| 7495 |
+
"learning_rate": 2.6141462127210347e-06,
|
| 7496 |
+
"loss": 0.021,
|
| 7497 |
+
"step": 10650
|
| 7498 |
+
},
|
| 7499 |
+
{
|
| 7500 |
+
"epoch": 4.220110847189232,
|
| 7501 |
+
"grad_norm": 0.39983102679252625,
|
| 7502 |
+
"learning_rate": 2.6009501187648456e-06,
|
| 7503 |
+
"loss": 0.0107,
|
| 7504 |
+
"step": 10660
|
| 7505 |
+
},
|
| 7506 |
+
{
|
| 7507 |
+
"epoch": 4.2240696753760885,
|
| 7508 |
+
"grad_norm": 0.09305311739444733,
|
| 7509 |
+
"learning_rate": 2.5877540248086565e-06,
|
| 7510 |
+
"loss": 0.0022,
|
| 7511 |
+
"step": 10670
|
| 7512 |
+
},
|
| 7513 |
+
{
|
| 7514 |
+
"epoch": 4.228028503562945,
|
| 7515 |
+
"grad_norm": 0.002689237706363201,
|
| 7516 |
+
"learning_rate": 2.5745579308524675e-06,
|
| 7517 |
+
"loss": 0.0141,
|
| 7518 |
+
"step": 10680
|
| 7519 |
+
},
|
| 7520 |
+
{
|
| 7521 |
+
"epoch": 4.231987331749802,
|
| 7522 |
+
"grad_norm": 2.4468233585357666,
|
| 7523 |
+
"learning_rate": 2.561361836896279e-06,
|
| 7524 |
+
"loss": 0.0325,
|
| 7525 |
+
"step": 10690
|
| 7526 |
+
},
|
| 7527 |
+
{
|
| 7528 |
+
"epoch": 4.235946159936659,
|
| 7529 |
+
"grad_norm": 0.25319406390190125,
|
| 7530 |
+
"learning_rate": 2.5481657429400897e-06,
|
| 7531 |
+
"loss": 0.0018,
|
| 7532 |
+
"step": 10700
|
| 7533 |
+
},
|
| 7534 |
+
{
|
| 7535 |
+
"epoch": 4.239904988123516,
|
| 7536 |
+
"grad_norm": 0.08327177911996841,
|
| 7537 |
+
"learning_rate": 2.5349696489839006e-06,
|
| 7538 |
+
"loss": 0.0007,
|
| 7539 |
+
"step": 10710
|
| 7540 |
+
},
|
| 7541 |
+
{
|
| 7542 |
+
"epoch": 4.243863816310372,
|
| 7543 |
+
"grad_norm": 0.0035083668772131205,
|
| 7544 |
+
"learning_rate": 2.5217735550277116e-06,
|
| 7545 |
+
"loss": 0.0131,
|
| 7546 |
+
"step": 10720
|
| 7547 |
+
},
|
| 7548 |
+
{
|
| 7549 |
+
"epoch": 4.247822644497229,
|
| 7550 |
+
"grad_norm": 0.040262769907712936,
|
| 7551 |
+
"learning_rate": 2.508577461071523e-06,
|
| 7552 |
+
"loss": 0.0098,
|
| 7553 |
+
"step": 10730
|
| 7554 |
+
},
|
| 7555 |
+
{
|
| 7556 |
+
"epoch": 4.251781472684086,
|
| 7557 |
+
"grad_norm": 0.03535272926092148,
|
| 7558 |
+
"learning_rate": 2.495381367115334e-06,
|
| 7559 |
+
"loss": 0.002,
|
| 7560 |
+
"step": 10740
|
| 7561 |
+
},
|
| 7562 |
+
{
|
| 7563 |
+
"epoch": 4.255740300870942,
|
| 7564 |
+
"grad_norm": 0.008145648054778576,
|
| 7565 |
+
"learning_rate": 2.4821852731591448e-06,
|
| 7566 |
+
"loss": 0.0518,
|
| 7567 |
+
"step": 10750
|
| 7568 |
+
},
|
| 7569 |
+
{
|
| 7570 |
+
"epoch": 4.259699129057799,
|
| 7571 |
+
"grad_norm": 0.0012378422543406487,
|
| 7572 |
+
"learning_rate": 2.468989179202956e-06,
|
| 7573 |
+
"loss": 0.0068,
|
| 7574 |
+
"step": 10760
|
| 7575 |
+
},
|
| 7576 |
+
{
|
| 7577 |
+
"epoch": 4.263657957244655,
|
| 7578 |
+
"grad_norm": 0.011911870911717415,
|
| 7579 |
+
"learning_rate": 2.455793085246767e-06,
|
| 7580 |
+
"loss": 0.0022,
|
| 7581 |
+
"step": 10770
|
| 7582 |
+
},
|
| 7583 |
+
{
|
| 7584 |
+
"epoch": 4.267616785431512,
|
| 7585 |
+
"grad_norm": 0.020499201491475105,
|
| 7586 |
+
"learning_rate": 2.4425969912905784e-06,
|
| 7587 |
+
"loss": 0.0455,
|
| 7588 |
+
"step": 10780
|
| 7589 |
+
},
|
| 7590 |
+
{
|
| 7591 |
+
"epoch": 4.271575613618369,
|
| 7592 |
+
"grad_norm": 0.2833760380744934,
|
| 7593 |
+
"learning_rate": 2.4294008973343893e-06,
|
| 7594 |
+
"loss": 0.0028,
|
| 7595 |
+
"step": 10790
|
| 7596 |
+
},
|
| 7597 |
+
{
|
| 7598 |
+
"epoch": 4.275534441805226,
|
| 7599 |
+
"grad_norm": 2.9257848262786865,
|
| 7600 |
+
"learning_rate": 2.4162048033782002e-06,
|
| 7601 |
+
"loss": 0.0275,
|
| 7602 |
+
"step": 10800
|
| 7603 |
+
},
|
| 7604 |
+
{
|
| 7605 |
+
"epoch": 4.2794932699920825,
|
| 7606 |
+
"grad_norm": 0.004658582620322704,
|
| 7607 |
+
"learning_rate": 2.403008709422011e-06,
|
| 7608 |
+
"loss": 0.0103,
|
| 7609 |
+
"step": 10810
|
| 7610 |
+
},
|
| 7611 |
+
{
|
| 7612 |
+
"epoch": 4.283452098178939,
|
| 7613 |
+
"grad_norm": 0.045958828181028366,
|
| 7614 |
+
"learning_rate": 2.3898126154658225e-06,
|
| 7615 |
+
"loss": 0.0021,
|
| 7616 |
+
"step": 10820
|
| 7617 |
+
},
|
| 7618 |
+
{
|
| 7619 |
+
"epoch": 4.287410926365796,
|
| 7620 |
+
"grad_norm": 0.03812342882156372,
|
| 7621 |
+
"learning_rate": 2.3766165215096334e-06,
|
| 7622 |
+
"loss": 0.0112,
|
| 7623 |
+
"step": 10830
|
| 7624 |
+
},
|
| 7625 |
+
{
|
| 7626 |
+
"epoch": 4.291369754552653,
|
| 7627 |
+
"grad_norm": 0.42923569679260254,
|
| 7628 |
+
"learning_rate": 2.3634204275534443e-06,
|
| 7629 |
+
"loss": 0.0178,
|
| 7630 |
+
"step": 10840
|
| 7631 |
+
},
|
| 7632 |
+
{
|
| 7633 |
+
"epoch": 4.29532858273951,
|
| 7634 |
+
"grad_norm": 2.794842481613159,
|
| 7635 |
+
"learning_rate": 2.3502243335972552e-06,
|
| 7636 |
+
"loss": 0.0167,
|
| 7637 |
+
"step": 10850
|
| 7638 |
+
},
|
| 7639 |
+
{
|
| 7640 |
+
"epoch": 4.2992874109263655,
|
| 7641 |
+
"grad_norm": 2.6024465560913086,
|
| 7642 |
+
"learning_rate": 2.337028239641066e-06,
|
| 7643 |
+
"loss": 0.0098,
|
| 7644 |
+
"step": 10860
|
| 7645 |
+
},
|
| 7646 |
+
{
|
| 7647 |
+
"epoch": 4.303246239113222,
|
| 7648 |
+
"grad_norm": 0.3943503499031067,
|
| 7649 |
+
"learning_rate": 2.3238321456848775e-06,
|
| 7650 |
+
"loss": 0.0241,
|
| 7651 |
+
"step": 10870
|
| 7652 |
+
},
|
| 7653 |
+
{
|
| 7654 |
+
"epoch": 4.307205067300079,
|
| 7655 |
+
"grad_norm": 0.3368546664714813,
|
| 7656 |
+
"learning_rate": 2.3106360517286884e-06,
|
| 7657 |
+
"loss": 0.0102,
|
| 7658 |
+
"step": 10880
|
| 7659 |
+
},
|
| 7660 |
+
{
|
| 7661 |
+
"epoch": 4.311163895486936,
|
| 7662 |
+
"grad_norm": 2.6512246131896973,
|
| 7663 |
+
"learning_rate": 2.2974399577724994e-06,
|
| 7664 |
+
"loss": 0.038,
|
| 7665 |
+
"step": 10890
|
| 7666 |
+
},
|
| 7667 |
+
{
|
| 7668 |
+
"epoch": 4.315122723673793,
|
| 7669 |
+
"grad_norm": 0.010673053562641144,
|
| 7670 |
+
"learning_rate": 2.2842438638163103e-06,
|
| 7671 |
+
"loss": 0.0028,
|
| 7672 |
+
"step": 10900
|
| 7673 |
+
},
|
| 7674 |
+
{
|
| 7675 |
+
"epoch": 4.319081551860649,
|
| 7676 |
+
"grad_norm": 0.024181121960282326,
|
| 7677 |
+
"learning_rate": 2.2710477698601216e-06,
|
| 7678 |
+
"loss": 0.0222,
|
| 7679 |
+
"step": 10910
|
| 7680 |
+
},
|
| 7681 |
+
{
|
| 7682 |
+
"epoch": 4.323040380047506,
|
| 7683 |
+
"grad_norm": 0.23308300971984863,
|
| 7684 |
+
"learning_rate": 2.2578516759039325e-06,
|
| 7685 |
+
"loss": 0.0016,
|
| 7686 |
+
"step": 10920
|
| 7687 |
+
},
|
| 7688 |
+
{
|
| 7689 |
+
"epoch": 4.326999208234363,
|
| 7690 |
+
"grad_norm": 0.20534226298332214,
|
| 7691 |
+
"learning_rate": 2.2446555819477435e-06,
|
| 7692 |
+
"loss": 0.0129,
|
| 7693 |
+
"step": 10930
|
| 7694 |
+
},
|
| 7695 |
+
{
|
| 7696 |
+
"epoch": 4.33095803642122,
|
| 7697 |
+
"grad_norm": 4.1924614906311035,
|
| 7698 |
+
"learning_rate": 2.2314594879915544e-06,
|
| 7699 |
+
"loss": 0.0191,
|
| 7700 |
+
"step": 10940
|
| 7701 |
+
},
|
| 7702 |
+
{
|
| 7703 |
+
"epoch": 4.334916864608076,
|
| 7704 |
+
"grad_norm": 0.005158805754035711,
|
| 7705 |
+
"learning_rate": 2.2182633940353657e-06,
|
| 7706 |
+
"loss": 0.0136,
|
| 7707 |
+
"step": 10950
|
| 7708 |
+
},
|
| 7709 |
+
{
|
| 7710 |
+
"epoch": 4.338875692794932,
|
| 7711 |
+
"grad_norm": 0.001412239857017994,
|
| 7712 |
+
"learning_rate": 2.2050673000791767e-06,
|
| 7713 |
+
"loss": 0.006,
|
| 7714 |
+
"step": 10960
|
| 7715 |
+
},
|
| 7716 |
+
{
|
| 7717 |
+
"epoch": 4.342834520981789,
|
| 7718 |
+
"grad_norm": 0.16200730204582214,
|
| 7719 |
+
"learning_rate": 2.1918712061229876e-06,
|
| 7720 |
+
"loss": 0.0218,
|
| 7721 |
+
"step": 10970
|
| 7722 |
+
},
|
| 7723 |
+
{
|
| 7724 |
+
"epoch": 4.346793349168646,
|
| 7725 |
+
"grad_norm": 0.012622310779988766,
|
| 7726 |
+
"learning_rate": 2.1786751121667985e-06,
|
| 7727 |
+
"loss": 0.0034,
|
| 7728 |
+
"step": 10980
|
| 7729 |
+
},
|
| 7730 |
+
{
|
| 7731 |
+
"epoch": 4.350752177355503,
|
| 7732 |
+
"grad_norm": 0.002170913852751255,
|
| 7733 |
+
"learning_rate": 2.1654790182106094e-06,
|
| 7734 |
+
"loss": 0.0036,
|
| 7735 |
+
"step": 10990
|
| 7736 |
+
},
|
| 7737 |
+
{
|
| 7738 |
+
"epoch": 4.3547110055423595,
|
| 7739 |
+
"grad_norm": 0.025332679972052574,
|
| 7740 |
+
"learning_rate": 2.1522829242544208e-06,
|
| 7741 |
+
"loss": 0.019,
|
| 7742 |
+
"step": 11000
|
| 7743 |
+
},
|
| 7744 |
+
{
|
| 7745 |
+
"epoch": 4.358669833729216,
|
| 7746 |
+
"grad_norm": 2.4141597747802734,
|
| 7747 |
+
"learning_rate": 2.1390868302982317e-06,
|
| 7748 |
+
"loss": 0.0197,
|
| 7749 |
+
"step": 11010
|
| 7750 |
+
},
|
| 7751 |
+
{
|
| 7752 |
+
"epoch": 4.362628661916073,
|
| 7753 |
+
"grad_norm": 0.021384382620453835,
|
| 7754 |
+
"learning_rate": 2.1258907363420426e-06,
|
| 7755 |
+
"loss": 0.0109,
|
| 7756 |
+
"step": 11020
|
| 7757 |
+
},
|
| 7758 |
+
{
|
| 7759 |
+
"epoch": 4.36658749010293,
|
| 7760 |
+
"grad_norm": 0.23710516095161438,
|
| 7761 |
+
"learning_rate": 2.1126946423858535e-06,
|
| 7762 |
+
"loss": 0.0157,
|
| 7763 |
+
"step": 11030
|
| 7764 |
+
},
|
| 7765 |
+
{
|
| 7766 |
+
"epoch": 4.370546318289787,
|
| 7767 |
+
"grad_norm": 0.2813720405101776,
|
| 7768 |
+
"learning_rate": 2.099498548429665e-06,
|
| 7769 |
+
"loss": 0.0188,
|
| 7770 |
+
"step": 11040
|
| 7771 |
+
},
|
| 7772 |
+
{
|
| 7773 |
+
"epoch": 4.374505146476643,
|
| 7774 |
+
"grad_norm": 0.033856701105833054,
|
| 7775 |
+
"learning_rate": 2.086302454473476e-06,
|
| 7776 |
+
"loss": 0.0089,
|
| 7777 |
+
"step": 11050
|
| 7778 |
+
},
|
| 7779 |
+
{
|
| 7780 |
+
"epoch": 4.378463974663499,
|
| 7781 |
+
"grad_norm": 0.03744563087821007,
|
| 7782 |
+
"learning_rate": 2.0731063605172867e-06,
|
| 7783 |
+
"loss": 0.0141,
|
| 7784 |
+
"step": 11060
|
| 7785 |
+
},
|
| 7786 |
+
{
|
| 7787 |
+
"epoch": 4.382422802850356,
|
| 7788 |
+
"grad_norm": 0.11789966374635696,
|
| 7789 |
+
"learning_rate": 2.0599102665610976e-06,
|
| 7790 |
+
"loss": 0.0294,
|
| 7791 |
+
"step": 11070
|
| 7792 |
+
},
|
| 7793 |
+
{
|
| 7794 |
+
"epoch": 4.386381631037213,
|
| 7795 |
+
"grad_norm": 0.6800145506858826,
|
| 7796 |
+
"learning_rate": 2.0467141726049094e-06,
|
| 7797 |
+
"loss": 0.0152,
|
| 7798 |
+
"step": 11080
|
| 7799 |
+
},
|
| 7800 |
+
{
|
| 7801 |
+
"epoch": 4.39034045922407,
|
| 7802 |
+
"grad_norm": 4.2035932540893555,
|
| 7803 |
+
"learning_rate": 2.0335180786487203e-06,
|
| 7804 |
+
"loss": 0.0393,
|
| 7805 |
+
"step": 11090
|
| 7806 |
+
},
|
| 7807 |
+
{
|
| 7808 |
+
"epoch": 4.394299287410926,
|
| 7809 |
+
"grad_norm": 0.4387066960334778,
|
| 7810 |
+
"learning_rate": 2.0203219846925313e-06,
|
| 7811 |
+
"loss": 0.0109,
|
| 7812 |
+
"step": 11100
|
| 7813 |
+
},
|
| 7814 |
+
{
|
| 7815 |
+
"epoch": 4.398258115597783,
|
| 7816 |
+
"grad_norm": 0.0016134337056428194,
|
| 7817 |
+
"learning_rate": 2.007125890736342e-06,
|
| 7818 |
+
"loss": 0.0018,
|
| 7819 |
+
"step": 11110
|
| 7820 |
+
},
|
| 7821 |
+
{
|
| 7822 |
+
"epoch": 4.40221694378464,
|
| 7823 |
+
"grad_norm": 0.03524504229426384,
|
| 7824 |
+
"learning_rate": 1.993929796780153e-06,
|
| 7825 |
+
"loss": 0.0196,
|
| 7826 |
+
"step": 11120
|
| 7827 |
+
},
|
| 7828 |
+
{
|
| 7829 |
+
"epoch": 4.406175771971497,
|
| 7830 |
+
"grad_norm": 0.008228733204305172,
|
| 7831 |
+
"learning_rate": 1.9807337028239644e-06,
|
| 7832 |
+
"loss": 0.0021,
|
| 7833 |
+
"step": 11130
|
| 7834 |
+
},
|
| 7835 |
+
{
|
| 7836 |
+
"epoch": 4.4101346001583535,
|
| 7837 |
+
"grad_norm": 0.2361990064382553,
|
| 7838 |
+
"learning_rate": 1.9675376088677754e-06,
|
| 7839 |
+
"loss": 0.0097,
|
| 7840 |
+
"step": 11140
|
| 7841 |
+
},
|
| 7842 |
+
{
|
| 7843 |
+
"epoch": 4.414093428345209,
|
| 7844 |
+
"grad_norm": 0.17866535484790802,
|
| 7845 |
+
"learning_rate": 1.9543415149115863e-06,
|
| 7846 |
+
"loss": 0.0015,
|
| 7847 |
+
"step": 11150
|
| 7848 |
+
},
|
| 7849 |
+
{
|
| 7850 |
+
"epoch": 4.418052256532066,
|
| 7851 |
+
"grad_norm": 0.9840713143348694,
|
| 7852 |
+
"learning_rate": 1.941145420955397e-06,
|
| 7853 |
+
"loss": 0.0056,
|
| 7854 |
+
"step": 11160
|
| 7855 |
+
},
|
| 7856 |
+
{
|
| 7857 |
+
"epoch": 4.422011084718923,
|
| 7858 |
+
"grad_norm": 0.034094199538230896,
|
| 7859 |
+
"learning_rate": 1.9279493269992085e-06,
|
| 7860 |
+
"loss": 0.0126,
|
| 7861 |
+
"step": 11170
|
| 7862 |
+
},
|
| 7863 |
+
{
|
| 7864 |
+
"epoch": 4.42596991290578,
|
| 7865 |
+
"grad_norm": 0.01327612716704607,
|
| 7866 |
+
"learning_rate": 1.9147532330430195e-06,
|
| 7867 |
+
"loss": 0.032,
|
| 7868 |
+
"step": 11180
|
| 7869 |
+
},
|
| 7870 |
+
{
|
| 7871 |
+
"epoch": 4.4299287410926365,
|
| 7872 |
+
"grad_norm": 0.03214488551020622,
|
| 7873 |
+
"learning_rate": 1.9015571390868304e-06,
|
| 7874 |
+
"loss": 0.0007,
|
| 7875 |
+
"step": 11190
|
| 7876 |
+
},
|
| 7877 |
+
{
|
| 7878 |
+
"epoch": 4.433887569279493,
|
| 7879 |
+
"grad_norm": 0.1643148809671402,
|
| 7880 |
+
"learning_rate": 1.8883610451306415e-06,
|
| 7881 |
+
"loss": 0.001,
|
| 7882 |
+
"step": 11200
|
| 7883 |
+
},
|
| 7884 |
+
{
|
| 7885 |
+
"epoch": 4.43784639746635,
|
| 7886 |
+
"grad_norm": 1.2142212390899658,
|
| 7887 |
+
"learning_rate": 1.8751649511744524e-06,
|
| 7888 |
+
"loss": 0.0029,
|
| 7889 |
+
"step": 11210
|
| 7890 |
+
},
|
| 7891 |
+
{
|
| 7892 |
+
"epoch": 4.441805225653207,
|
| 7893 |
+
"grad_norm": 0.050521478056907654,
|
| 7894 |
+
"learning_rate": 1.8619688572182634e-06,
|
| 7895 |
+
"loss": 0.0015,
|
| 7896 |
+
"step": 11220
|
| 7897 |
+
},
|
| 7898 |
+
{
|
| 7899 |
+
"epoch": 4.445764053840064,
|
| 7900 |
+
"grad_norm": 2.6327645778656006,
|
| 7901 |
+
"learning_rate": 1.8487727632620745e-06,
|
| 7902 |
+
"loss": 0.0141,
|
| 7903 |
+
"step": 11230
|
| 7904 |
+
},
|
| 7905 |
+
{
|
| 7906 |
+
"epoch": 4.44972288202692,
|
| 7907 |
+
"grad_norm": 0.10866005718708038,
|
| 7908 |
+
"learning_rate": 1.8355766693058854e-06,
|
| 7909 |
+
"loss": 0.0331,
|
| 7910 |
+
"step": 11240
|
| 7911 |
+
},
|
| 7912 |
+
{
|
| 7913 |
+
"epoch": 4.453681710213777,
|
| 7914 |
+
"grad_norm": 2.2170937061309814,
|
| 7915 |
+
"learning_rate": 1.8223805753496966e-06,
|
| 7916 |
+
"loss": 0.0085,
|
| 7917 |
+
"step": 11250
|
| 7918 |
+
},
|
| 7919 |
+
{
|
| 7920 |
+
"epoch": 4.457640538400633,
|
| 7921 |
+
"grad_norm": 0.15154610574245453,
|
| 7922 |
+
"learning_rate": 1.8091844813935075e-06,
|
| 7923 |
+
"loss": 0.0237,
|
| 7924 |
+
"step": 11260
|
| 7925 |
+
},
|
| 7926 |
+
{
|
| 7927 |
+
"epoch": 4.46159936658749,
|
| 7928 |
+
"grad_norm": 0.005728883668780327,
|
| 7929 |
+
"learning_rate": 1.7959883874373186e-06,
|
| 7930 |
+
"loss": 0.0185,
|
| 7931 |
+
"step": 11270
|
| 7932 |
+
},
|
| 7933 |
+
{
|
| 7934 |
+
"epoch": 4.465558194774347,
|
| 7935 |
+
"grad_norm": 0.08254682272672653,
|
| 7936 |
+
"learning_rate": 1.7827922934811295e-06,
|
| 7937 |
+
"loss": 0.0084,
|
| 7938 |
+
"step": 11280
|
| 7939 |
+
},
|
| 7940 |
+
{
|
| 7941 |
+
"epoch": 4.469517022961203,
|
| 7942 |
+
"grad_norm": 0.36999353766441345,
|
| 7943 |
+
"learning_rate": 1.7695961995249407e-06,
|
| 7944 |
+
"loss": 0.012,
|
| 7945 |
+
"step": 11290
|
| 7946 |
+
},
|
| 7947 |
+
{
|
| 7948 |
+
"epoch": 4.47347585114806,
|
| 7949 |
+
"grad_norm": 0.023466236889362335,
|
| 7950 |
+
"learning_rate": 1.7564001055687516e-06,
|
| 7951 |
+
"loss": 0.001,
|
| 7952 |
+
"step": 11300
|
| 7953 |
+
},
|
| 7954 |
+
{
|
| 7955 |
+
"epoch": 4.477434679334917,
|
| 7956 |
+
"grad_norm": 0.10780829936265945,
|
| 7957 |
+
"learning_rate": 1.7432040116125627e-06,
|
| 7958 |
+
"loss": 0.0131,
|
| 7959 |
+
"step": 11310
|
| 7960 |
+
},
|
| 7961 |
+
{
|
| 7962 |
+
"epoch": 4.481393507521774,
|
| 7963 |
+
"grad_norm": 0.01709785871207714,
|
| 7964 |
+
"learning_rate": 1.7300079176563739e-06,
|
| 7965 |
+
"loss": 0.0095,
|
| 7966 |
+
"step": 11320
|
| 7967 |
+
},
|
| 7968 |
+
{
|
| 7969 |
+
"epoch": 4.4853523357086305,
|
| 7970 |
+
"grad_norm": 0.01511989627033472,
|
| 7971 |
+
"learning_rate": 1.7168118237001848e-06,
|
| 7972 |
+
"loss": 0.0042,
|
| 7973 |
+
"step": 11330
|
| 7974 |
+
},
|
| 7975 |
+
{
|
| 7976 |
+
"epoch": 4.489311163895487,
|
| 7977 |
+
"grad_norm": 0.13262680172920227,
|
| 7978 |
+
"learning_rate": 1.703615729743996e-06,
|
| 7979 |
+
"loss": 0.0272,
|
| 7980 |
+
"step": 11340
|
| 7981 |
+
},
|
| 7982 |
+
{
|
| 7983 |
+
"epoch": 4.493269992082344,
|
| 7984 |
+
"grad_norm": 0.01472618617117405,
|
| 7985 |
+
"learning_rate": 1.6904196357878068e-06,
|
| 7986 |
+
"loss": 0.001,
|
| 7987 |
+
"step": 11350
|
| 7988 |
+
},
|
| 7989 |
+
{
|
| 7990 |
+
"epoch": 4.4972288202692,
|
| 7991 |
+
"grad_norm": 0.0017839232459664345,
|
| 7992 |
+
"learning_rate": 1.677223541831618e-06,
|
| 7993 |
+
"loss": 0.0125,
|
| 7994 |
+
"step": 11360
|
| 7995 |
+
},
|
| 7996 |
+
{
|
| 7997 |
+
"epoch": 4.501187648456057,
|
| 7998 |
+
"grad_norm": 0.15884031355381012,
|
| 7999 |
+
"learning_rate": 1.6640274478754289e-06,
|
| 8000 |
+
"loss": 0.0019,
|
| 8001 |
+
"step": 11370
|
| 8002 |
+
},
|
| 8003 |
+
{
|
| 8004 |
+
"epoch": 4.5051464766429135,
|
| 8005 |
+
"grad_norm": 0.07231657952070236,
|
| 8006 |
+
"learning_rate": 1.65083135391924e-06,
|
| 8007 |
+
"loss": 0.0021,
|
| 8008 |
+
"step": 11380
|
| 8009 |
+
},
|
| 8010 |
+
{
|
| 8011 |
+
"epoch": 4.50910530482977,
|
| 8012 |
+
"grad_norm": 0.15871493518352509,
|
| 8013 |
+
"learning_rate": 1.637635259963051e-06,
|
| 8014 |
+
"loss": 0.0008,
|
| 8015 |
+
"step": 11390
|
| 8016 |
+
},
|
| 8017 |
+
{
|
| 8018 |
+
"epoch": 4.513064133016627,
|
| 8019 |
+
"grad_norm": 0.011580166406929493,
|
| 8020 |
+
"learning_rate": 1.624439166006862e-06,
|
| 8021 |
+
"loss": 0.0049,
|
| 8022 |
+
"step": 11400
|
| 8023 |
+
},
|
| 8024 |
+
{
|
| 8025 |
+
"epoch": 4.517022961203484,
|
| 8026 |
+
"grad_norm": 0.014912627637386322,
|
| 8027 |
+
"learning_rate": 1.611243072050673e-06,
|
| 8028 |
+
"loss": 0.0158,
|
| 8029 |
+
"step": 11410
|
| 8030 |
+
},
|
| 8031 |
+
{
|
| 8032 |
+
"epoch": 4.520981789390341,
|
| 8033 |
+
"grad_norm": 0.0724916085600853,
|
| 8034 |
+
"learning_rate": 1.5980469780944841e-06,
|
| 8035 |
+
"loss": 0.0466,
|
| 8036 |
+
"step": 11420
|
| 8037 |
+
},
|
| 8038 |
+
{
|
| 8039 |
+
"epoch": 4.524940617577197,
|
| 8040 |
+
"grad_norm": 0.21377435326576233,
|
| 8041 |
+
"learning_rate": 1.584850884138295e-06,
|
| 8042 |
+
"loss": 0.0009,
|
| 8043 |
+
"step": 11430
|
| 8044 |
+
},
|
| 8045 |
+
{
|
| 8046 |
+
"epoch": 4.528899445764054,
|
| 8047 |
+
"grad_norm": 0.005721719935536385,
|
| 8048 |
+
"learning_rate": 1.571654790182106e-06,
|
| 8049 |
+
"loss": 0.0165,
|
| 8050 |
+
"step": 11440
|
| 8051 |
+
},
|
| 8052 |
+
{
|
| 8053 |
+
"epoch": 4.532858273950911,
|
| 8054 |
+
"grad_norm": 0.009795432910323143,
|
| 8055 |
+
"learning_rate": 1.5584586962259171e-06,
|
| 8056 |
+
"loss": 0.0016,
|
| 8057 |
+
"step": 11450
|
| 8058 |
+
},
|
| 8059 |
+
{
|
| 8060 |
+
"epoch": 4.536817102137768,
|
| 8061 |
+
"grad_norm": 0.026736890897154808,
|
| 8062 |
+
"learning_rate": 1.545262602269728e-06,
|
| 8063 |
+
"loss": 0.0014,
|
| 8064 |
+
"step": 11460
|
| 8065 |
+
},
|
| 8066 |
+
{
|
| 8067 |
+
"epoch": 4.540775930324624,
|
| 8068 |
+
"grad_norm": 0.014911648817360401,
|
| 8069 |
+
"learning_rate": 1.5320665083135392e-06,
|
| 8070 |
+
"loss": 0.0218,
|
| 8071 |
+
"step": 11470
|
| 8072 |
+
},
|
| 8073 |
+
{
|
| 8074 |
+
"epoch": 4.54473475851148,
|
| 8075 |
+
"grad_norm": 0.0018749868031591177,
|
| 8076 |
+
"learning_rate": 1.5188704143573503e-06,
|
| 8077 |
+
"loss": 0.0015,
|
| 8078 |
+
"step": 11480
|
| 8079 |
+
},
|
| 8080 |
+
{
|
| 8081 |
+
"epoch": 4.548693586698337,
|
| 8082 |
+
"grad_norm": 2.4239377975463867,
|
| 8083 |
+
"learning_rate": 1.5056743204011614e-06,
|
| 8084 |
+
"loss": 0.0177,
|
| 8085 |
+
"step": 11490
|
| 8086 |
+
},
|
| 8087 |
+
{
|
| 8088 |
+
"epoch": 4.552652414885194,
|
| 8089 |
+
"grad_norm": 0.2642796039581299,
|
| 8090 |
+
"learning_rate": 1.4924782264449724e-06,
|
| 8091 |
+
"loss": 0.0085,
|
| 8092 |
+
"step": 11500
|
| 8093 |
+
},
|
| 8094 |
+
{
|
| 8095 |
+
"epoch": 4.556611243072051,
|
| 8096 |
+
"grad_norm": 0.6623967289924622,
|
| 8097 |
+
"learning_rate": 1.4792821324887835e-06,
|
| 8098 |
+
"loss": 0.0031,
|
| 8099 |
+
"step": 11510
|
| 8100 |
+
},
|
| 8101 |
+
{
|
| 8102 |
+
"epoch": 4.5605700712589075,
|
| 8103 |
+
"grad_norm": 2.6269302368164062,
|
| 8104 |
+
"learning_rate": 1.4660860385325944e-06,
|
| 8105 |
+
"loss": 0.0092,
|
| 8106 |
+
"step": 11520
|
| 8107 |
+
},
|
| 8108 |
+
{
|
| 8109 |
+
"epoch": 4.564528899445764,
|
| 8110 |
+
"grad_norm": 0.20825159549713135,
|
| 8111 |
+
"learning_rate": 1.4528899445764055e-06,
|
| 8112 |
+
"loss": 0.0013,
|
| 8113 |
+
"step": 11530
|
| 8114 |
+
},
|
| 8115 |
+
{
|
| 8116 |
+
"epoch": 4.568487727632621,
|
| 8117 |
+
"grad_norm": 0.44120895862579346,
|
| 8118 |
+
"learning_rate": 1.4396938506202165e-06,
|
| 8119 |
+
"loss": 0.0022,
|
| 8120 |
+
"step": 11540
|
| 8121 |
+
},
|
| 8122 |
+
{
|
| 8123 |
+
"epoch": 4.572446555819478,
|
| 8124 |
+
"grad_norm": 0.4229113459587097,
|
| 8125 |
+
"learning_rate": 1.4264977566640274e-06,
|
| 8126 |
+
"loss": 0.0137,
|
| 8127 |
+
"step": 11550
|
| 8128 |
+
},
|
| 8129 |
+
{
|
| 8130 |
+
"epoch": 4.576405384006334,
|
| 8131 |
+
"grad_norm": 0.12956929206848145,
|
| 8132 |
+
"learning_rate": 1.4133016627078385e-06,
|
| 8133 |
+
"loss": 0.0026,
|
| 8134 |
+
"step": 11560
|
| 8135 |
+
},
|
| 8136 |
+
{
|
| 8137 |
+
"epoch": 4.5803642121931905,
|
| 8138 |
+
"grad_norm": 0.013492707163095474,
|
| 8139 |
+
"learning_rate": 1.4001055687516494e-06,
|
| 8140 |
+
"loss": 0.0013,
|
| 8141 |
+
"step": 11570
|
| 8142 |
+
},
|
| 8143 |
+
{
|
| 8144 |
+
"epoch": 4.584323040380047,
|
| 8145 |
+
"grad_norm": 0.030138276517391205,
|
| 8146 |
+
"learning_rate": 1.3869094747954606e-06,
|
| 8147 |
+
"loss": 0.001,
|
| 8148 |
+
"step": 11580
|
| 8149 |
+
},
|
| 8150 |
+
{
|
| 8151 |
+
"epoch": 4.588281868566904,
|
| 8152 |
+
"grad_norm": 0.05256173387169838,
|
| 8153 |
+
"learning_rate": 1.3737133808392715e-06,
|
| 8154 |
+
"loss": 0.0006,
|
| 8155 |
+
"step": 11590
|
| 8156 |
+
},
|
| 8157 |
+
{
|
| 8158 |
+
"epoch": 4.592240696753761,
|
| 8159 |
+
"grad_norm": 0.0029339452739804983,
|
| 8160 |
+
"learning_rate": 1.3605172868830826e-06,
|
| 8161 |
+
"loss": 0.0249,
|
| 8162 |
+
"step": 11600
|
| 8163 |
+
},
|
| 8164 |
+
{
|
| 8165 |
+
"epoch": 4.596199524940618,
|
| 8166 |
+
"grad_norm": 2.4009523391723633,
|
| 8167 |
+
"learning_rate": 1.3473211929268935e-06,
|
| 8168 |
+
"loss": 0.0255,
|
| 8169 |
+
"step": 11610
|
| 8170 |
+
},
|
| 8171 |
+
{
|
| 8172 |
+
"epoch": 4.600158353127474,
|
| 8173 |
+
"grad_norm": 2.775813341140747,
|
| 8174 |
+
"learning_rate": 1.3341250989707047e-06,
|
| 8175 |
+
"loss": 0.0276,
|
| 8176 |
+
"step": 11620
|
| 8177 |
+
},
|
| 8178 |
+
{
|
| 8179 |
+
"epoch": 4.604117181314331,
|
| 8180 |
+
"grad_norm": 0.020541055127978325,
|
| 8181 |
+
"learning_rate": 1.3209290050145156e-06,
|
| 8182 |
+
"loss": 0.0008,
|
| 8183 |
+
"step": 11630
|
| 8184 |
+
},
|
| 8185 |
+
{
|
| 8186 |
+
"epoch": 4.608076009501188,
|
| 8187 |
+
"grad_norm": 0.12365325540304184,
|
| 8188 |
+
"learning_rate": 1.307732911058327e-06,
|
| 8189 |
+
"loss": 0.0215,
|
| 8190 |
+
"step": 11640
|
| 8191 |
+
},
|
| 8192 |
+
{
|
| 8193 |
+
"epoch": 4.612034837688045,
|
| 8194 |
+
"grad_norm": 0.10344530642032623,
|
| 8195 |
+
"learning_rate": 1.2945368171021379e-06,
|
| 8196 |
+
"loss": 0.0009,
|
| 8197 |
+
"step": 11650
|
| 8198 |
+
},
|
| 8199 |
+
{
|
| 8200 |
+
"epoch": 4.6159936658749015,
|
| 8201 |
+
"grad_norm": 0.021320436149835587,
|
| 8202 |
+
"learning_rate": 1.2813407231459488e-06,
|
| 8203 |
+
"loss": 0.0018,
|
| 8204 |
+
"step": 11660
|
| 8205 |
+
},
|
| 8206 |
+
{
|
| 8207 |
+
"epoch": 4.619952494061757,
|
| 8208 |
+
"grad_norm": 0.1441866159439087,
|
| 8209 |
+
"learning_rate": 1.26814462918976e-06,
|
| 8210 |
+
"loss": 0.031,
|
| 8211 |
+
"step": 11670
|
| 8212 |
+
},
|
| 8213 |
+
{
|
| 8214 |
+
"epoch": 4.623911322248614,
|
| 8215 |
+
"grad_norm": 0.010510790161788464,
|
| 8216 |
+
"learning_rate": 1.2549485352335708e-06,
|
| 8217 |
+
"loss": 0.0174,
|
| 8218 |
+
"step": 11680
|
| 8219 |
+
},
|
| 8220 |
+
{
|
| 8221 |
+
"epoch": 4.627870150435471,
|
| 8222 |
+
"grad_norm": 0.5400771498680115,
|
| 8223 |
+
"learning_rate": 1.241752441277382e-06,
|
| 8224 |
+
"loss": 0.0156,
|
| 8225 |
+
"step": 11690
|
| 8226 |
+
},
|
| 8227 |
+
{
|
| 8228 |
+
"epoch": 4.631828978622328,
|
| 8229 |
+
"grad_norm": 0.2115350365638733,
|
| 8230 |
+
"learning_rate": 1.228556347321193e-06,
|
| 8231 |
+
"loss": 0.0037,
|
| 8232 |
+
"step": 11700
|
| 8233 |
+
},
|
| 8234 |
+
{
|
| 8235 |
+
"epoch": 4.6357878068091845,
|
| 8236 |
+
"grad_norm": 0.13378827273845673,
|
| 8237 |
+
"learning_rate": 1.215360253365004e-06,
|
| 8238 |
+
"loss": 0.0027,
|
| 8239 |
+
"step": 11710
|
| 8240 |
+
},
|
| 8241 |
+
{
|
| 8242 |
+
"epoch": 4.639746634996041,
|
| 8243 |
+
"grad_norm": 0.03523465245962143,
|
| 8244 |
+
"learning_rate": 1.202164159408815e-06,
|
| 8245 |
+
"loss": 0.0181,
|
| 8246 |
+
"step": 11720
|
| 8247 |
+
},
|
| 8248 |
+
{
|
| 8249 |
+
"epoch": 4.643705463182898,
|
| 8250 |
+
"grad_norm": 0.0026600570417940617,
|
| 8251 |
+
"learning_rate": 1.188968065452626e-06,
|
| 8252 |
+
"loss": 0.0023,
|
| 8253 |
+
"step": 11730
|
| 8254 |
+
},
|
| 8255 |
+
{
|
| 8256 |
+
"epoch": 4.647664291369755,
|
| 8257 |
+
"grad_norm": 0.0101556908339262,
|
| 8258 |
+
"learning_rate": 1.175771971496437e-06,
|
| 8259 |
+
"loss": 0.0007,
|
| 8260 |
+
"step": 11740
|
| 8261 |
+
},
|
| 8262 |
+
{
|
| 8263 |
+
"epoch": 4.651623119556612,
|
| 8264 |
+
"grad_norm": 0.13945993781089783,
|
| 8265 |
+
"learning_rate": 1.1625758775402481e-06,
|
| 8266 |
+
"loss": 0.0066,
|
| 8267 |
+
"step": 11750
|
| 8268 |
+
},
|
| 8269 |
+
{
|
| 8270 |
+
"epoch": 4.6555819477434675,
|
| 8271 |
+
"grad_norm": 0.3167749047279358,
|
| 8272 |
+
"learning_rate": 1.149379783584059e-06,
|
| 8273 |
+
"loss": 0.0022,
|
| 8274 |
+
"step": 11760
|
| 8275 |
+
},
|
| 8276 |
+
{
|
| 8277 |
+
"epoch": 4.659540775930324,
|
| 8278 |
+
"grad_norm": 0.004489412531256676,
|
| 8279 |
+
"learning_rate": 1.1361836896278702e-06,
|
| 8280 |
+
"loss": 0.0105,
|
| 8281 |
+
"step": 11770
|
| 8282 |
+
},
|
| 8283 |
+
{
|
| 8284 |
+
"epoch": 4.663499604117181,
|
| 8285 |
+
"grad_norm": 0.27212023735046387,
|
| 8286 |
+
"learning_rate": 1.1229875956716811e-06,
|
| 8287 |
+
"loss": 0.0086,
|
| 8288 |
+
"step": 11780
|
| 8289 |
+
},
|
| 8290 |
+
{
|
| 8291 |
+
"epoch": 4.667458432304038,
|
| 8292 |
+
"grad_norm": 0.03749987855553627,
|
| 8293 |
+
"learning_rate": 1.1097915017154923e-06,
|
| 8294 |
+
"loss": 0.0095,
|
| 8295 |
+
"step": 11790
|
| 8296 |
+
},
|
| 8297 |
+
{
|
| 8298 |
+
"epoch": 4.671417260490895,
|
| 8299 |
+
"grad_norm": 0.15570545196533203,
|
| 8300 |
+
"learning_rate": 1.0965954077593034e-06,
|
| 8301 |
+
"loss": 0.0015,
|
| 8302 |
+
"step": 11800
|
| 8303 |
+
},
|
| 8304 |
+
{
|
| 8305 |
+
"epoch": 4.675376088677751,
|
| 8306 |
+
"grad_norm": 0.052114758640527725,
|
| 8307 |
+
"learning_rate": 1.0833993138031143e-06,
|
| 8308 |
+
"loss": 0.0133,
|
| 8309 |
+
"step": 11810
|
| 8310 |
+
},
|
| 8311 |
+
{
|
| 8312 |
+
"epoch": 4.679334916864608,
|
| 8313 |
+
"grad_norm": 0.2027260959148407,
|
| 8314 |
+
"learning_rate": 1.0702032198469254e-06,
|
| 8315 |
+
"loss": 0.0159,
|
| 8316 |
+
"step": 11820
|
| 8317 |
+
},
|
| 8318 |
+
{
|
| 8319 |
+
"epoch": 4.683293745051465,
|
| 8320 |
+
"grad_norm": 0.057699043303728104,
|
| 8321 |
+
"learning_rate": 1.0570071258907364e-06,
|
| 8322 |
+
"loss": 0.0081,
|
| 8323 |
+
"step": 11830
|
| 8324 |
+
},
|
| 8325 |
+
{
|
| 8326 |
+
"epoch": 4.687252573238322,
|
| 8327 |
+
"grad_norm": 0.07636474817991257,
|
| 8328 |
+
"learning_rate": 1.0438110319345475e-06,
|
| 8329 |
+
"loss": 0.0242,
|
| 8330 |
+
"step": 11840
|
| 8331 |
+
},
|
| 8332 |
+
{
|
| 8333 |
+
"epoch": 4.6912114014251785,
|
| 8334 |
+
"grad_norm": 0.23860959708690643,
|
| 8335 |
+
"learning_rate": 1.0306149379783584e-06,
|
| 8336 |
+
"loss": 0.0146,
|
| 8337 |
+
"step": 11850
|
| 8338 |
+
},
|
| 8339 |
+
{
|
| 8340 |
+
"epoch": 4.695170229612035,
|
| 8341 |
+
"grad_norm": 0.11115310341119766,
|
| 8342 |
+
"learning_rate": 1.0174188440221696e-06,
|
| 8343 |
+
"loss": 0.0059,
|
| 8344 |
+
"step": 11860
|
| 8345 |
+
},
|
| 8346 |
+
{
|
| 8347 |
+
"epoch": 4.699129057798892,
|
| 8348 |
+
"grad_norm": 0.2461850345134735,
|
| 8349 |
+
"learning_rate": 1.0042227500659805e-06,
|
| 8350 |
+
"loss": 0.0018,
|
| 8351 |
+
"step": 11870
|
| 8352 |
+
},
|
| 8353 |
+
{
|
| 8354 |
+
"epoch": 4.703087885985748,
|
| 8355 |
+
"grad_norm": 0.007762064225971699,
|
| 8356 |
+
"learning_rate": 9.910266561097916e-07,
|
| 8357 |
+
"loss": 0.0113,
|
| 8358 |
+
"step": 11880
|
| 8359 |
+
},
|
| 8360 |
+
{
|
| 8361 |
+
"epoch": 4.707046714172605,
|
| 8362 |
+
"grad_norm": 0.21308307349681854,
|
| 8363 |
+
"learning_rate": 9.778305621536025e-07,
|
| 8364 |
+
"loss": 0.0016,
|
| 8365 |
+
"step": 11890
|
| 8366 |
+
},
|
| 8367 |
+
{
|
| 8368 |
+
"epoch": 4.7110055423594615,
|
| 8369 |
+
"grad_norm": 0.38225802779197693,
|
| 8370 |
+
"learning_rate": 9.646344681974135e-07,
|
| 8371 |
+
"loss": 0.002,
|
| 8372 |
+
"step": 11900
|
| 8373 |
+
},
|
| 8374 |
+
{
|
| 8375 |
+
"epoch": 4.714964370546318,
|
| 8376 |
+
"grad_norm": 0.47582879662513733,
|
| 8377 |
+
"learning_rate": 9.514383742412246e-07,
|
| 8378 |
+
"loss": 0.0019,
|
| 8379 |
+
"step": 11910
|
| 8380 |
+
},
|
| 8381 |
+
{
|
| 8382 |
+
"epoch": 4.718923198733175,
|
| 8383 |
+
"grad_norm": 0.13118302822113037,
|
| 8384 |
+
"learning_rate": 9.382422802850356e-07,
|
| 8385 |
+
"loss": 0.0009,
|
| 8386 |
+
"step": 11920
|
| 8387 |
+
},
|
| 8388 |
+
{
|
| 8389 |
+
"epoch": 4.722882026920032,
|
| 8390 |
+
"grad_norm": 0.11689452081918716,
|
| 8391 |
+
"learning_rate": 9.250461863288467e-07,
|
| 8392 |
+
"loss": 0.0036,
|
| 8393 |
+
"step": 11930
|
| 8394 |
+
},
|
| 8395 |
+
{
|
| 8396 |
+
"epoch": 4.726840855106889,
|
| 8397 |
+
"grad_norm": 0.011046094819903374,
|
| 8398 |
+
"learning_rate": 9.118500923726578e-07,
|
| 8399 |
+
"loss": 0.0011,
|
| 8400 |
+
"step": 11940
|
| 8401 |
+
},
|
| 8402 |
+
{
|
| 8403 |
+
"epoch": 4.730799683293745,
|
| 8404 |
+
"grad_norm": 0.00931351538747549,
|
| 8405 |
+
"learning_rate": 8.986539984164687e-07,
|
| 8406 |
+
"loss": 0.0284,
|
| 8407 |
+
"step": 11950
|
| 8408 |
+
},
|
| 8409 |
+
{
|
| 8410 |
+
"epoch": 4.734758511480602,
|
| 8411 |
+
"grad_norm": 0.058653805404901505,
|
| 8412 |
+
"learning_rate": 8.854579044602797e-07,
|
| 8413 |
+
"loss": 0.0027,
|
| 8414 |
+
"step": 11960
|
| 8415 |
+
},
|
| 8416 |
+
{
|
| 8417 |
+
"epoch": 4.738717339667458,
|
| 8418 |
+
"grad_norm": 0.0022915638983249664,
|
| 8419 |
+
"learning_rate": 8.722618105040908e-07,
|
| 8420 |
+
"loss": 0.0013,
|
| 8421 |
+
"step": 11970
|
| 8422 |
+
},
|
| 8423 |
+
{
|
| 8424 |
+
"epoch": 4.742676167854315,
|
| 8425 |
+
"grad_norm": 0.007116817403584719,
|
| 8426 |
+
"learning_rate": 8.590657165479018e-07,
|
| 8427 |
+
"loss": 0.0141,
|
| 8428 |
+
"step": 11980
|
| 8429 |
+
},
|
| 8430 |
+
{
|
| 8431 |
+
"epoch": 4.746634996041172,
|
| 8432 |
+
"grad_norm": 0.13853254914283752,
|
| 8433 |
+
"learning_rate": 8.458696225917129e-07,
|
| 8434 |
+
"loss": 0.0104,
|
| 8435 |
+
"step": 11990
|
| 8436 |
+
},
|
| 8437 |
+
{
|
| 8438 |
+
"epoch": 4.750593824228028,
|
| 8439 |
+
"grad_norm": 0.011576661840081215,
|
| 8440 |
+
"learning_rate": 8.326735286355239e-07,
|
| 8441 |
+
"loss": 0.0014,
|
| 8442 |
+
"step": 12000
|
| 8443 |
+
},
|
| 8444 |
+
{
|
| 8445 |
+
"epoch": 4.754552652414885,
|
| 8446 |
+
"grad_norm": 2.4724280834198,
|
| 8447 |
+
"learning_rate": 8.19477434679335e-07,
|
| 8448 |
+
"loss": 0.0327,
|
| 8449 |
+
"step": 12010
|
| 8450 |
+
},
|
| 8451 |
+
{
|
| 8452 |
+
"epoch": 4.758511480601742,
|
| 8453 |
+
"grad_norm": 0.08917970210313797,
|
| 8454 |
+
"learning_rate": 8.06281340723146e-07,
|
| 8455 |
+
"loss": 0.0167,
|
| 8456 |
+
"step": 12020
|
| 8457 |
+
},
|
| 8458 |
+
{
|
| 8459 |
+
"epoch": 4.762470308788599,
|
| 8460 |
+
"grad_norm": 0.13262496888637543,
|
| 8461 |
+
"learning_rate": 7.93085246766957e-07,
|
| 8462 |
+
"loss": 0.005,
|
| 8463 |
+
"step": 12030
|
| 8464 |
+
},
|
| 8465 |
+
{
|
| 8466 |
+
"epoch": 4.7664291369754554,
|
| 8467 |
+
"grad_norm": 0.005669764243066311,
|
| 8468 |
+
"learning_rate": 7.79889152810768e-07,
|
| 8469 |
+
"loss": 0.0183,
|
| 8470 |
+
"step": 12040
|
| 8471 |
+
},
|
| 8472 |
+
{
|
| 8473 |
+
"epoch": 4.770387965162312,
|
| 8474 |
+
"grad_norm": 0.13403597474098206,
|
| 8475 |
+
"learning_rate": 7.666930588545791e-07,
|
| 8476 |
+
"loss": 0.0165,
|
| 8477 |
+
"step": 12050
|
| 8478 |
+
},
|
| 8479 |
+
{
|
| 8480 |
+
"epoch": 4.774346793349169,
|
| 8481 |
+
"grad_norm": 0.017786597833037376,
|
| 8482 |
+
"learning_rate": 7.534969648983901e-07,
|
| 8483 |
+
"loss": 0.0207,
|
| 8484 |
+
"step": 12060
|
| 8485 |
+
},
|
| 8486 |
+
{
|
| 8487 |
+
"epoch": 4.778305621536026,
|
| 8488 |
+
"grad_norm": 0.2829414904117584,
|
| 8489 |
+
"learning_rate": 7.403008709422011e-07,
|
| 8490 |
+
"loss": 0.0373,
|
| 8491 |
+
"step": 12070
|
| 8492 |
+
},
|
| 8493 |
+
{
|
| 8494 |
+
"epoch": 4.782264449722882,
|
| 8495 |
+
"grad_norm": 0.0074774897657334805,
|
| 8496 |
+
"learning_rate": 7.271047769860122e-07,
|
| 8497 |
+
"loss": 0.0014,
|
| 8498 |
+
"step": 12080
|
| 8499 |
+
},
|
| 8500 |
+
{
|
| 8501 |
+
"epoch": 4.7862232779097384,
|
| 8502 |
+
"grad_norm": 0.20584142208099365,
|
| 8503 |
+
"learning_rate": 7.139086830298232e-07,
|
| 8504 |
+
"loss": 0.0027,
|
| 8505 |
+
"step": 12090
|
| 8506 |
+
},
|
| 8507 |
+
{
|
| 8508 |
+
"epoch": 4.790182106096595,
|
| 8509 |
+
"grad_norm": 0.05486268550157547,
|
| 8510 |
+
"learning_rate": 7.007125890736342e-07,
|
| 8511 |
+
"loss": 0.0111,
|
| 8512 |
+
"step": 12100
|
| 8513 |
+
},
|
| 8514 |
+
{
|
| 8515 |
+
"epoch": 4.794140934283452,
|
| 8516 |
+
"grad_norm": 0.003304367419332266,
|
| 8517 |
+
"learning_rate": 6.875164951174452e-07,
|
| 8518 |
+
"loss": 0.0096,
|
| 8519 |
+
"step": 12110
|
| 8520 |
+
},
|
| 8521 |
+
{
|
| 8522 |
+
"epoch": 4.798099762470309,
|
| 8523 |
+
"grad_norm": 2.7915356159210205,
|
| 8524 |
+
"learning_rate": 6.743204011612563e-07,
|
| 8525 |
+
"loss": 0.0238,
|
| 8526 |
+
"step": 12120
|
| 8527 |
+
},
|
| 8528 |
+
{
|
| 8529 |
+
"epoch": 4.802058590657166,
|
| 8530 |
+
"grad_norm": 0.1825484335422516,
|
| 8531 |
+
"learning_rate": 6.611243072050673e-07,
|
| 8532 |
+
"loss": 0.0128,
|
| 8533 |
+
"step": 12130
|
| 8534 |
+
},
|
| 8535 |
+
{
|
| 8536 |
+
"epoch": 4.806017418844022,
|
| 8537 |
+
"grad_norm": 0.2295331060886383,
|
| 8538 |
+
"learning_rate": 6.479282132488783e-07,
|
| 8539 |
+
"loss": 0.0016,
|
| 8540 |
+
"step": 12140
|
| 8541 |
+
},
|
| 8542 |
+
{
|
| 8543 |
+
"epoch": 4.809976247030879,
|
| 8544 |
+
"grad_norm": 0.004416352603584528,
|
| 8545 |
+
"learning_rate": 6.347321192926895e-07,
|
| 8546 |
+
"loss": 0.0015,
|
| 8547 |
+
"step": 12150
|
| 8548 |
+
},
|
| 8549 |
+
{
|
| 8550 |
+
"epoch": 4.813935075217736,
|
| 8551 |
+
"grad_norm": 0.004335583653301001,
|
| 8552 |
+
"learning_rate": 6.215360253365005e-07,
|
| 8553 |
+
"loss": 0.0096,
|
| 8554 |
+
"step": 12160
|
| 8555 |
+
},
|
| 8556 |
+
{
|
| 8557 |
+
"epoch": 4.817893903404592,
|
| 8558 |
+
"grad_norm": 0.01758703403174877,
|
| 8559 |
+
"learning_rate": 6.083399313803115e-07,
|
| 8560 |
+
"loss": 0.0047,
|
| 8561 |
+
"step": 12170
|
| 8562 |
+
},
|
| 8563 |
+
{
|
| 8564 |
+
"epoch": 4.821852731591449,
|
| 8565 |
+
"grad_norm": 0.001830776920542121,
|
| 8566 |
+
"learning_rate": 5.951438374241224e-07,
|
| 8567 |
+
"loss": 0.0085,
|
| 8568 |
+
"step": 12180
|
| 8569 |
+
},
|
| 8570 |
+
{
|
| 8571 |
+
"epoch": 4.825811559778305,
|
| 8572 |
+
"grad_norm": 0.03966958075761795,
|
| 8573 |
+
"learning_rate": 5.819477434679335e-07,
|
| 8574 |
+
"loss": 0.023,
|
| 8575 |
+
"step": 12190
|
| 8576 |
+
},
|
| 8577 |
+
{
|
| 8578 |
+
"epoch": 4.829770387965162,
|
| 8579 |
+
"grad_norm": 0.16295941174030304,
|
| 8580 |
+
"learning_rate": 5.687516495117445e-07,
|
| 8581 |
+
"loss": 0.001,
|
| 8582 |
+
"step": 12200
|
| 8583 |
+
},
|
| 8584 |
+
{
|
| 8585 |
+
"epoch": 4.833729216152019,
|
| 8586 |
+
"grad_norm": 0.029076730832457542,
|
| 8587 |
+
"learning_rate": 5.555555555555555e-07,
|
| 8588 |
+
"loss": 0.0152,
|
| 8589 |
+
"step": 12210
|
| 8590 |
+
},
|
| 8591 |
+
{
|
| 8592 |
+
"epoch": 4.837688044338876,
|
| 8593 |
+
"grad_norm": 0.012178479693830013,
|
| 8594 |
+
"learning_rate": 5.423594615993665e-07,
|
| 8595 |
+
"loss": 0.0426,
|
| 8596 |
+
"step": 12220
|
| 8597 |
+
},
|
| 8598 |
+
{
|
| 8599 |
+
"epoch": 4.8416468725257324,
|
| 8600 |
+
"grad_norm": 0.04596005380153656,
|
| 8601 |
+
"learning_rate": 5.291633676431777e-07,
|
| 8602 |
+
"loss": 0.0164,
|
| 8603 |
+
"step": 12230
|
| 8604 |
+
},
|
| 8605 |
+
{
|
| 8606 |
+
"epoch": 4.845605700712589,
|
| 8607 |
+
"grad_norm": 0.24843168258666992,
|
| 8608 |
+
"learning_rate": 5.159672736869887e-07,
|
| 8609 |
+
"loss": 0.0017,
|
| 8610 |
+
"step": 12240
|
| 8611 |
+
},
|
| 8612 |
+
{
|
| 8613 |
+
"epoch": 4.849564528899446,
|
| 8614 |
+
"grad_norm": 0.006510727573186159,
|
| 8615 |
+
"learning_rate": 5.027711797307997e-07,
|
| 8616 |
+
"loss": 0.0162,
|
| 8617 |
+
"step": 12250
|
| 8618 |
+
},
|
| 8619 |
+
{
|
| 8620 |
+
"epoch": 4.853523357086303,
|
| 8621 |
+
"grad_norm": 0.0016284239245578647,
|
| 8622 |
+
"learning_rate": 4.895750857746108e-07,
|
| 8623 |
+
"loss": 0.016,
|
| 8624 |
+
"step": 12260
|
| 8625 |
+
},
|
| 8626 |
+
{
|
| 8627 |
+
"epoch": 4.85748218527316,
|
| 8628 |
+
"grad_norm": 0.011615815572440624,
|
| 8629 |
+
"learning_rate": 4.7637899181842174e-07,
|
| 8630 |
+
"loss": 0.0121,
|
| 8631 |
+
"step": 12270
|
| 8632 |
+
},
|
| 8633 |
+
{
|
| 8634 |
+
"epoch": 4.8614410134600154,
|
| 8635 |
+
"grad_norm": 3.054940700531006,
|
| 8636 |
+
"learning_rate": 4.6318289786223276e-07,
|
| 8637 |
+
"loss": 0.0164,
|
| 8638 |
+
"step": 12280
|
| 8639 |
+
},
|
| 8640 |
+
{
|
| 8641 |
+
"epoch": 4.865399841646872,
|
| 8642 |
+
"grad_norm": 0.3476531505584717,
|
| 8643 |
+
"learning_rate": 4.4998680390604384e-07,
|
| 8644 |
+
"loss": 0.0087,
|
| 8645 |
+
"step": 12290
|
| 8646 |
+
},
|
| 8647 |
+
{
|
| 8648 |
+
"epoch": 4.869358669833729,
|
| 8649 |
+
"grad_norm": 0.4537252187728882,
|
| 8650 |
+
"learning_rate": 4.3679070994985487e-07,
|
| 8651 |
+
"loss": 0.0143,
|
| 8652 |
+
"step": 12300
|
| 8653 |
+
},
|
| 8654 |
+
{
|
| 8655 |
+
"epoch": 4.873317498020586,
|
| 8656 |
+
"grad_norm": 0.007204136345535517,
|
| 8657 |
+
"learning_rate": 4.235946159936659e-07,
|
| 8658 |
+
"loss": 0.0198,
|
| 8659 |
+
"step": 12310
|
| 8660 |
+
},
|
| 8661 |
+
{
|
| 8662 |
+
"epoch": 4.877276326207443,
|
| 8663 |
+
"grad_norm": 2.6663107872009277,
|
| 8664 |
+
"learning_rate": 4.103985220374769e-07,
|
| 8665 |
+
"loss": 0.0413,
|
| 8666 |
+
"step": 12320
|
| 8667 |
+
},
|
| 8668 |
+
{
|
| 8669 |
+
"epoch": 4.881235154394299,
|
| 8670 |
+
"grad_norm": 0.12623126804828644,
|
| 8671 |
+
"learning_rate": 3.9720242808128795e-07,
|
| 8672 |
+
"loss": 0.0027,
|
| 8673 |
+
"step": 12330
|
| 8674 |
+
},
|
| 8675 |
+
{
|
| 8676 |
+
"epoch": 4.885193982581156,
|
| 8677 |
+
"grad_norm": 0.0011634131660684943,
|
| 8678 |
+
"learning_rate": 3.84006334125099e-07,
|
| 8679 |
+
"loss": 0.014,
|
| 8680 |
+
"step": 12340
|
| 8681 |
+
},
|
| 8682 |
+
{
|
| 8683 |
+
"epoch": 4.889152810768013,
|
| 8684 |
+
"grad_norm": 0.33776265382766724,
|
| 8685 |
+
"learning_rate": 3.7081024016891e-07,
|
| 8686 |
+
"loss": 0.0171,
|
| 8687 |
+
"step": 12350
|
| 8688 |
+
},
|
| 8689 |
+
{
|
| 8690 |
+
"epoch": 4.89311163895487,
|
| 8691 |
+
"grad_norm": 0.005637482274323702,
|
| 8692 |
+
"learning_rate": 3.5761414621272104e-07,
|
| 8693 |
+
"loss": 0.0018,
|
| 8694 |
+
"step": 12360
|
| 8695 |
+
},
|
| 8696 |
+
{
|
| 8697 |
+
"epoch": 4.897070467141726,
|
| 8698 |
+
"grad_norm": 0.16389860212802887,
|
| 8699 |
+
"learning_rate": 3.444180522565321e-07,
|
| 8700 |
+
"loss": 0.0115,
|
| 8701 |
+
"step": 12370
|
| 8702 |
+
},
|
| 8703 |
+
{
|
| 8704 |
+
"epoch": 4.901029295328582,
|
| 8705 |
+
"grad_norm": 0.0014358052285388112,
|
| 8706 |
+
"learning_rate": 3.312219583003431e-07,
|
| 8707 |
+
"loss": 0.0093,
|
| 8708 |
+
"step": 12380
|
| 8709 |
+
},
|
| 8710 |
+
{
|
| 8711 |
+
"epoch": 4.904988123515439,
|
| 8712 |
+
"grad_norm": 0.16846758127212524,
|
| 8713 |
+
"learning_rate": 3.180258643441541e-07,
|
| 8714 |
+
"loss": 0.0195,
|
| 8715 |
+
"step": 12390
|
| 8716 |
+
},
|
| 8717 |
+
{
|
| 8718 |
+
"epoch": 4.908946951702296,
|
| 8719 |
+
"grad_norm": 0.034828487783670425,
|
| 8720 |
+
"learning_rate": 3.0482977038796515e-07,
|
| 8721 |
+
"loss": 0.0072,
|
| 8722 |
+
"step": 12400
|
| 8723 |
+
},
|
| 8724 |
+
{
|
| 8725 |
+
"epoch": 4.912905779889153,
|
| 8726 |
+
"grad_norm": 0.008080679923295975,
|
| 8727 |
+
"learning_rate": 2.9163367643177623e-07,
|
| 8728 |
+
"loss": 0.0092,
|
| 8729 |
+
"step": 12410
|
| 8730 |
+
},
|
| 8731 |
+
{
|
| 8732 |
+
"epoch": 4.9168646080760094,
|
| 8733 |
+
"grad_norm": 0.2054898589849472,
|
| 8734 |
+
"learning_rate": 2.7843758247558726e-07,
|
| 8735 |
+
"loss": 0.0084,
|
| 8736 |
+
"step": 12420
|
| 8737 |
+
},
|
| 8738 |
+
{
|
| 8739 |
+
"epoch": 4.920823436262866,
|
| 8740 |
+
"grad_norm": 0.0295702014118433,
|
| 8741 |
+
"learning_rate": 2.652414885193983e-07,
|
| 8742 |
+
"loss": 0.0187,
|
| 8743 |
+
"step": 12430
|
| 8744 |
+
},
|
| 8745 |
+
{
|
| 8746 |
+
"epoch": 4.924782264449723,
|
| 8747 |
+
"grad_norm": 5.268764019012451,
|
| 8748 |
+
"learning_rate": 2.5204539456320926e-07,
|
| 8749 |
+
"loss": 0.0342,
|
| 8750 |
+
"step": 12440
|
| 8751 |
+
},
|
| 8752 |
+
{
|
| 8753 |
+
"epoch": 4.92874109263658,
|
| 8754 |
+
"grad_norm": 0.18980184197425842,
|
| 8755 |
+
"learning_rate": 2.3884930060702034e-07,
|
| 8756 |
+
"loss": 0.004,
|
| 8757 |
+
"step": 12450
|
| 8758 |
+
},
|
| 8759 |
+
{
|
| 8760 |
+
"epoch": 4.932699920823437,
|
| 8761 |
+
"grad_norm": 0.06021437793970108,
|
| 8762 |
+
"learning_rate": 2.2565320665083137e-07,
|
| 8763 |
+
"loss": 0.0017,
|
| 8764 |
+
"step": 12460
|
| 8765 |
+
},
|
| 8766 |
+
{
|
| 8767 |
+
"epoch": 4.936658749010293,
|
| 8768 |
+
"grad_norm": 0.2200620025396347,
|
| 8769 |
+
"learning_rate": 2.124571126946424e-07,
|
| 8770 |
+
"loss": 0.0014,
|
| 8771 |
+
"step": 12470
|
| 8772 |
+
},
|
| 8773 |
+
{
|
| 8774 |
+
"epoch": 4.94061757719715,
|
| 8775 |
+
"grad_norm": 2.6067283153533936,
|
| 8776 |
+
"learning_rate": 1.9926101873845342e-07,
|
| 8777 |
+
"loss": 0.0182,
|
| 8778 |
+
"step": 12480
|
| 8779 |
+
},
|
| 8780 |
+
{
|
| 8781 |
+
"epoch": 4.944576405384006,
|
| 8782 |
+
"grad_norm": 0.4836919903755188,
|
| 8783 |
+
"learning_rate": 1.8606492478226445e-07,
|
| 8784 |
+
"loss": 0.0118,
|
| 8785 |
+
"step": 12490
|
| 8786 |
+
},
|
| 8787 |
+
{
|
| 8788 |
+
"epoch": 4.948535233570863,
|
| 8789 |
+
"grad_norm": 3.4199352264404297,
|
| 8790 |
+
"learning_rate": 1.728688308260755e-07,
|
| 8791 |
+
"loss": 0.0168,
|
| 8792 |
+
"step": 12500
|
| 8793 |
+
},
|
| 8794 |
+
{
|
| 8795 |
+
"epoch": 4.95249406175772,
|
| 8796 |
+
"grad_norm": 0.0025512713473290205,
|
| 8797 |
+
"learning_rate": 1.596727368698865e-07,
|
| 8798 |
+
"loss": 0.0008,
|
| 8799 |
+
"step": 12510
|
| 8800 |
+
},
|
| 8801 |
+
{
|
| 8802 |
+
"epoch": 4.956452889944576,
|
| 8803 |
+
"grad_norm": 0.13040626049041748,
|
| 8804 |
+
"learning_rate": 1.4647664291369756e-07,
|
| 8805 |
+
"loss": 0.0043,
|
| 8806 |
+
"step": 12520
|
| 8807 |
+
},
|
| 8808 |
+
{
|
| 8809 |
+
"epoch": 4.960411718131433,
|
| 8810 |
+
"grad_norm": 0.007748185191303492,
|
| 8811 |
+
"learning_rate": 1.3328054895750858e-07,
|
| 8812 |
+
"loss": 0.002,
|
| 8813 |
+
"step": 12530
|
| 8814 |
+
},
|
| 8815 |
+
{
|
| 8816 |
+
"epoch": 4.96437054631829,
|
| 8817 |
+
"grad_norm": 0.09668821841478348,
|
| 8818 |
+
"learning_rate": 1.200844550013196e-07,
|
| 8819 |
+
"loss": 0.0024,
|
| 8820 |
+
"step": 12540
|
| 8821 |
+
},
|
| 8822 |
+
{
|
| 8823 |
+
"epoch": 4.968329374505147,
|
| 8824 |
+
"grad_norm": 0.002127299318090081,
|
| 8825 |
+
"learning_rate": 1.0688836104513065e-07,
|
| 8826 |
+
"loss": 0.0013,
|
| 8827 |
+
"step": 12550
|
| 8828 |
+
},
|
| 8829 |
+
{
|
| 8830 |
+
"epoch": 4.9722882026920034,
|
| 8831 |
+
"grad_norm": 0.3176936209201813,
|
| 8832 |
+
"learning_rate": 9.369226708894168e-08,
|
| 8833 |
+
"loss": 0.0182,
|
| 8834 |
+
"step": 12560
|
| 8835 |
+
},
|
| 8836 |
+
{
|
| 8837 |
+
"epoch": 4.97624703087886,
|
| 8838 |
+
"grad_norm": 0.07354911416769028,
|
| 8839 |
+
"learning_rate": 8.049617313275271e-08,
|
| 8840 |
+
"loss": 0.0016,
|
| 8841 |
+
"step": 12570
|
| 8842 |
+
},
|
| 8843 |
+
{
|
| 8844 |
+
"epoch": 4.980205859065716,
|
| 8845 |
+
"grad_norm": 0.12911178171634674,
|
| 8846 |
+
"learning_rate": 6.730007917656375e-08,
|
| 8847 |
+
"loss": 0.0018,
|
| 8848 |
+
"step": 12580
|
| 8849 |
+
},
|
| 8850 |
+
{
|
| 8851 |
+
"epoch": 4.984164687252573,
|
| 8852 |
+
"grad_norm": 3.4642975330352783,
|
| 8853 |
+
"learning_rate": 5.410398522037477e-08,
|
| 8854 |
+
"loss": 0.0101,
|
| 8855 |
+
"step": 12590
|
| 8856 |
+
},
|
| 8857 |
+
{
|
| 8858 |
+
"epoch": 4.98812351543943,
|
| 8859 |
+
"grad_norm": 0.0033425739966332912,
|
| 8860 |
+
"learning_rate": 4.09078912641858e-08,
|
| 8861 |
+
"loss": 0.0012,
|
| 8862 |
+
"step": 12600
|
| 8863 |
+
},
|
| 8864 |
+
{
|
| 8865 |
+
"epoch": 4.9920823436262864,
|
| 8866 |
+
"grad_norm": 0.10665281862020493,
|
| 8867 |
+
"learning_rate": 2.7711797307996835e-08,
|
| 8868 |
+
"loss": 0.012,
|
| 8869 |
+
"step": 12610
|
| 8870 |
+
},
|
| 8871 |
+
{
|
| 8872 |
+
"epoch": 4.996041171813143,
|
| 8873 |
+
"grad_norm": 0.4431086480617523,
|
| 8874 |
+
"learning_rate": 1.4515703351807866e-08,
|
| 8875 |
+
"loss": 0.0014,
|
| 8876 |
+
"step": 12620
|
| 8877 |
+
},
|
| 8878 |
+
{
|
| 8879 |
+
"epoch": 5.0,
|
| 8880 |
+
"grad_norm": 0.005758483428508043,
|
| 8881 |
+
"learning_rate": 1.3196093956188968e-09,
|
| 8882 |
+
"loss": 0.0034,
|
| 8883 |
+
"step": 12630
|
| 8884 |
+
},
|
| 8885 |
+
{
|
| 8886 |
+
"epoch": 5.0,
|
| 8887 |
+
"eval_loss": 0.016071012243628502,
|
| 8888 |
+
"eval_runtime": 12.0492,
|
| 8889 |
+
"eval_samples_per_second": 186.403,
|
| 8890 |
+
"eval_steps_per_second": 23.321,
|
| 8891 |
+
"step": 12630
|
| 8892 |
}
|
| 8893 |
],
|
| 8894 |
"logging_steps": 10,
|
|
|
|
| 8903 |
"early_stopping_threshold": 0.0
|
| 8904 |
},
|
| 8905 |
"attributes": {
|
| 8906 |
+
"early_stopping_patience_counter": 2
|
| 8907 |
}
|
| 8908 |
},
|
| 8909 |
"TrainerControl": {
|
|
|
|
| 8912 |
"should_evaluate": false,
|
| 8913 |
"should_log": false,
|
| 8914 |
"should_save": true,
|
| 8915 |
+
"should_training_stop": true
|
| 8916 |
},
|
| 8917 |
"attributes": {}
|
| 8918 |
}
|
| 8919 |
},
|
| 8920 |
+
"total_flos": 2.822821798182912e+16,
|
| 8921 |
"train_batch_size": 8,
|
| 8922 |
"trial_name": null,
|
| 8923 |
"trial_params": null
|