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")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kurtpayne/skillscan-deberta-adapter") model = AutoModelForSequenceClassification.from_pretrained("kurtpayne/skillscan-deberta-adapter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 6, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737737736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a28e98ee3861a076d3a768c8c18a4543287175543fde942c18bb644868920c6d
|
| 3 |
size 737737736
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475598539
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577a7de00a56f9fbc64798cb0ee6e2385e46810f0e61599e47a62f41b9e1e338
|
| 3 |
size 1475598539
|
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 sha256:6b36346f8aa7a17f49d2529f5ace1a38a5544521c94aca6c7d6719e4e7ad62b2
|
| 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:f2a6b510ad2979f937933b282818cdd08f2f928c8bfb0f5b3eb59c8bd28887c8
|
| 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:f808ab18fbea1efaadb0591ca3af0f57d02f583625ad1e79532c8a63d019d2ef
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 10188,
|
| 3 |
"best_metric": 0.13098350167274475,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpuqxd53f1/deberta-multilabel/checkpoint-10188",
|
| 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,
|
|
@@ -8959,6 +8959,1799 @@
|
|
| 8959 |
"eval_samples_per_second": 109.693,
|
| 8960 |
"eval_steps_per_second": 13.712,
|
| 8961 |
"step": 12735
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8962 |
}
|
| 8963 |
],
|
| 8964 |
"logging_steps": 10,
|
|
@@ -8973,7 +10766,7 @@
|
|
| 8973 |
"early_stopping_threshold": 0.0
|
| 8974 |
},
|
| 8975 |
"attributes": {
|
| 8976 |
-
"early_stopping_patience_counter":
|
| 8977 |
}
|
| 8978 |
},
|
| 8979 |
"TrainerControl": {
|
|
@@ -8982,12 +10775,12 @@
|
|
| 8982 |
"should_evaluate": false,
|
| 8983 |
"should_log": false,
|
| 8984 |
"should_save": true,
|
| 8985 |
-
"should_training_stop":
|
| 8986 |
},
|
| 8987 |
"attributes": {}
|
| 8988 |
}
|
| 8989 |
},
|
| 8990 |
-
"total_flos":
|
| 8991 |
"train_batch_size": 8,
|
| 8992 |
"trial_name": null,
|
| 8993 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 10188,
|
| 3 |
"best_metric": 0.13098350167274475,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpuqxd53f1/deberta-multilabel/checkpoint-10188",
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 15282,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8959 |
"eval_samples_per_second": 109.693,
|
| 8960 |
"eval_steps_per_second": 13.712,
|
| 8961 |
"step": 12735
|
| 8962 |
+
},
|
| 8963 |
+
{
|
| 8964 |
+
"epoch": 5.001963093835886,
|
| 8965 |
+
"grad_norm": 0.12626679241657257,
|
| 8966 |
+
"learning_rate": 3.6981022322402387e-06,
|
| 8967 |
+
"loss": 0.0298,
|
| 8968 |
+
"step": 12740
|
| 8969 |
+
},
|
| 8970 |
+
{
|
| 8971 |
+
"epoch": 5.005889281507656,
|
| 8972 |
+
"grad_norm": 0.28340965509414673,
|
| 8973 |
+
"learning_rate": 3.6835599505562427e-06,
|
| 8974 |
+
"loss": 0.0335,
|
| 8975 |
+
"step": 12750
|
| 8976 |
+
},
|
| 8977 |
+
{
|
| 8978 |
+
"epoch": 5.0098154691794266,
|
| 8979 |
+
"grad_norm": 0.013585710898041725,
|
| 8980 |
+
"learning_rate": 3.6690176688722462e-06,
|
| 8981 |
+
"loss": 0.0128,
|
| 8982 |
+
"step": 12760
|
| 8983 |
+
},
|
| 8984 |
+
{
|
| 8985 |
+
"epoch": 5.013741656851198,
|
| 8986 |
+
"grad_norm": 15.476011276245117,
|
| 8987 |
+
"learning_rate": 3.6544753871882498e-06,
|
| 8988 |
+
"loss": 0.0526,
|
| 8989 |
+
"step": 12770
|
| 8990 |
+
},
|
| 8991 |
+
{
|
| 8992 |
+
"epoch": 5.017667844522968,
|
| 8993 |
+
"grad_norm": 0.03241879492998123,
|
| 8994 |
+
"learning_rate": 3.639933105504254e-06,
|
| 8995 |
+
"loss": 0.0229,
|
| 8996 |
+
"step": 12780
|
| 8997 |
+
},
|
| 8998 |
+
{
|
| 8999 |
+
"epoch": 5.021594032194739,
|
| 9000 |
+
"grad_norm": 0.1293519139289856,
|
| 9001 |
+
"learning_rate": 3.6253908238202577e-06,
|
| 9002 |
+
"loss": 0.0284,
|
| 9003 |
+
"step": 12790
|
| 9004 |
+
},
|
| 9005 |
+
{
|
| 9006 |
+
"epoch": 5.025520219866509,
|
| 9007 |
+
"grad_norm": 97.42695617675781,
|
| 9008 |
+
"learning_rate": 3.6108485421362617e-06,
|
| 9009 |
+
"loss": 0.0495,
|
| 9010 |
+
"step": 12800
|
| 9011 |
+
},
|
| 9012 |
+
{
|
| 9013 |
+
"epoch": 5.0294464075382805,
|
| 9014 |
+
"grad_norm": 0.40893232822418213,
|
| 9015 |
+
"learning_rate": 3.5963062604522652e-06,
|
| 9016 |
+
"loss": 0.0193,
|
| 9017 |
+
"step": 12810
|
| 9018 |
+
},
|
| 9019 |
+
{
|
| 9020 |
+
"epoch": 5.033372595210051,
|
| 9021 |
+
"grad_norm": 0.6639312505722046,
|
| 9022 |
+
"learning_rate": 3.5817639787682688e-06,
|
| 9023 |
+
"loss": 0.0178,
|
| 9024 |
+
"step": 12820
|
| 9025 |
+
},
|
| 9026 |
+
{
|
| 9027 |
+
"epoch": 5.037298782881821,
|
| 9028 |
+
"grad_norm": 0.014410450123250484,
|
| 9029 |
+
"learning_rate": 3.5672216970842727e-06,
|
| 9030 |
+
"loss": 0.0033,
|
| 9031 |
+
"step": 12830
|
| 9032 |
+
},
|
| 9033 |
+
{
|
| 9034 |
+
"epoch": 5.041224970553593,
|
| 9035 |
+
"grad_norm": 0.4094603657722473,
|
| 9036 |
+
"learning_rate": 3.5526794154002763e-06,
|
| 9037 |
+
"loss": 0.0051,
|
| 9038 |
+
"step": 12840
|
| 9039 |
+
},
|
| 9040 |
+
{
|
| 9041 |
+
"epoch": 5.045151158225363,
|
| 9042 |
+
"grad_norm": 0.09336494654417038,
|
| 9043 |
+
"learning_rate": 3.5381371337162807e-06,
|
| 9044 |
+
"loss": 0.1481,
|
| 9045 |
+
"step": 12850
|
| 9046 |
+
},
|
| 9047 |
+
{
|
| 9048 |
+
"epoch": 5.049077345897134,
|
| 9049 |
+
"grad_norm": 25.632780075073242,
|
| 9050 |
+
"learning_rate": 3.5235948520322842e-06,
|
| 9051 |
+
"loss": 0.0396,
|
| 9052 |
+
"step": 12860
|
| 9053 |
+
},
|
| 9054 |
+
{
|
| 9055 |
+
"epoch": 5.053003533568905,
|
| 9056 |
+
"grad_norm": 0.060434430837631226,
|
| 9057 |
+
"learning_rate": 3.509052570348288e-06,
|
| 9058 |
+
"loss": 0.0207,
|
| 9059 |
+
"step": 12870
|
| 9060 |
+
},
|
| 9061 |
+
{
|
| 9062 |
+
"epoch": 5.056929721240675,
|
| 9063 |
+
"grad_norm": 7.9765167236328125,
|
| 9064 |
+
"learning_rate": 3.4945102886642917e-06,
|
| 9065 |
+
"loss": 0.0204,
|
| 9066 |
+
"step": 12880
|
| 9067 |
+
},
|
| 9068 |
+
{
|
| 9069 |
+
"epoch": 5.060855908912446,
|
| 9070 |
+
"grad_norm": 0.6654744148254395,
|
| 9071 |
+
"learning_rate": 3.4799680069802953e-06,
|
| 9072 |
+
"loss": 0.1497,
|
| 9073 |
+
"step": 12890
|
| 9074 |
+
},
|
| 9075 |
+
{
|
| 9076 |
+
"epoch": 5.064782096584216,
|
| 9077 |
+
"grad_norm": 3.004603385925293,
|
| 9078 |
+
"learning_rate": 3.4654257252962993e-06,
|
| 9079 |
+
"loss": 0.0356,
|
| 9080 |
+
"step": 12900
|
| 9081 |
+
},
|
| 9082 |
+
{
|
| 9083 |
+
"epoch": 5.068708284255988,
|
| 9084 |
+
"grad_norm": 0.0019843250047415495,
|
| 9085 |
+
"learning_rate": 3.450883443612303e-06,
|
| 9086 |
+
"loss": 0.0117,
|
| 9087 |
+
"step": 12910
|
| 9088 |
+
},
|
| 9089 |
+
{
|
| 9090 |
+
"epoch": 5.072634471927758,
|
| 9091 |
+
"grad_norm": 0.25481170415878296,
|
| 9092 |
+
"learning_rate": 3.4363411619283068e-06,
|
| 9093 |
+
"loss": 0.0484,
|
| 9094 |
+
"step": 12920
|
| 9095 |
+
},
|
| 9096 |
+
{
|
| 9097 |
+
"epoch": 5.0765606595995285,
|
| 9098 |
+
"grad_norm": 0.009659300558269024,
|
| 9099 |
+
"learning_rate": 3.4217988802443107e-06,
|
| 9100 |
+
"loss": 0.0015,
|
| 9101 |
+
"step": 12930
|
| 9102 |
+
},
|
| 9103 |
+
{
|
| 9104 |
+
"epoch": 5.0804868472713,
|
| 9105 |
+
"grad_norm": 0.09942436963319778,
|
| 9106 |
+
"learning_rate": 3.4072565985603147e-06,
|
| 9107 |
+
"loss": 0.2318,
|
| 9108 |
+
"step": 12940
|
| 9109 |
+
},
|
| 9110 |
+
{
|
| 9111 |
+
"epoch": 5.08441303494307,
|
| 9112 |
+
"grad_norm": 0.8782022595405579,
|
| 9113 |
+
"learning_rate": 3.3927143168763182e-06,
|
| 9114 |
+
"loss": 0.0317,
|
| 9115 |
+
"step": 12950
|
| 9116 |
+
},
|
| 9117 |
+
{
|
| 9118 |
+
"epoch": 5.088339222614841,
|
| 9119 |
+
"grad_norm": 0.0032021747902035713,
|
| 9120 |
+
"learning_rate": 3.378172035192322e-06,
|
| 9121 |
+
"loss": 0.1593,
|
| 9122 |
+
"step": 12960
|
| 9123 |
+
},
|
| 9124 |
+
{
|
| 9125 |
+
"epoch": 5.092265410286612,
|
| 9126 |
+
"grad_norm": 4.000266075134277,
|
| 9127 |
+
"learning_rate": 3.3636297535083258e-06,
|
| 9128 |
+
"loss": 0.1923,
|
| 9129 |
+
"step": 12970
|
| 9130 |
+
},
|
| 9131 |
+
{
|
| 9132 |
+
"epoch": 5.0961915979583825,
|
| 9133 |
+
"grad_norm": 0.15721705555915833,
|
| 9134 |
+
"learning_rate": 3.3490874718243293e-06,
|
| 9135 |
+
"loss": 0.0083,
|
| 9136 |
+
"step": 12980
|
| 9137 |
+
},
|
| 9138 |
+
{
|
| 9139 |
+
"epoch": 5.100117785630153,
|
| 9140 |
+
"grad_norm": 0.15064933896064758,
|
| 9141 |
+
"learning_rate": 3.3345451901403333e-06,
|
| 9142 |
+
"loss": 0.0144,
|
| 9143 |
+
"step": 12990
|
| 9144 |
+
},
|
| 9145 |
+
{
|
| 9146 |
+
"epoch": 5.104043973301923,
|
| 9147 |
+
"grad_norm": 0.9322262406349182,
|
| 9148 |
+
"learning_rate": 3.3200029084563372e-06,
|
| 9149 |
+
"loss": 0.2868,
|
| 9150 |
+
"step": 13000
|
| 9151 |
+
},
|
| 9152 |
+
{
|
| 9153 |
+
"epoch": 5.107970160973695,
|
| 9154 |
+
"grad_norm": 0.018538326025009155,
|
| 9155 |
+
"learning_rate": 3.3054606267723412e-06,
|
| 9156 |
+
"loss": 0.009,
|
| 9157 |
+
"step": 13010
|
| 9158 |
+
},
|
| 9159 |
+
{
|
| 9160 |
+
"epoch": 5.111896348645465,
|
| 9161 |
+
"grad_norm": 6.400797367095947,
|
| 9162 |
+
"learning_rate": 3.2909183450883448e-06,
|
| 9163 |
+
"loss": 0.0241,
|
| 9164 |
+
"step": 13020
|
| 9165 |
+
},
|
| 9166 |
+
{
|
| 9167 |
+
"epoch": 5.115822536317236,
|
| 9168 |
+
"grad_norm": 0.2767089605331421,
|
| 9169 |
+
"learning_rate": 3.2763760634043483e-06,
|
| 9170 |
+
"loss": 0.019,
|
| 9171 |
+
"step": 13030
|
| 9172 |
+
},
|
| 9173 |
+
{
|
| 9174 |
+
"epoch": 5.119748723989007,
|
| 9175 |
+
"grad_norm": 0.010737679898738861,
|
| 9176 |
+
"learning_rate": 3.2618337817203523e-06,
|
| 9177 |
+
"loss": 0.0898,
|
| 9178 |
+
"step": 13040
|
| 9179 |
+
},
|
| 9180 |
+
{
|
| 9181 |
+
"epoch": 5.123674911660777,
|
| 9182 |
+
"grad_norm": 0.3357734978199005,
|
| 9183 |
+
"learning_rate": 3.247291500036356e-06,
|
| 9184 |
+
"loss": 0.0022,
|
| 9185 |
+
"step": 13050
|
| 9186 |
+
},
|
| 9187 |
+
{
|
| 9188 |
+
"epoch": 5.127601099332548,
|
| 9189 |
+
"grad_norm": 0.04939505457878113,
|
| 9190 |
+
"learning_rate": 3.2327492183523594e-06,
|
| 9191 |
+
"loss": 0.0508,
|
| 9192 |
+
"step": 13060
|
| 9193 |
+
},
|
| 9194 |
+
{
|
| 9195 |
+
"epoch": 5.131527287004319,
|
| 9196 |
+
"grad_norm": 13.421435356140137,
|
| 9197 |
+
"learning_rate": 3.2182069366683633e-06,
|
| 9198 |
+
"loss": 0.0488,
|
| 9199 |
+
"step": 13070
|
| 9200 |
+
},
|
| 9201 |
+
{
|
| 9202 |
+
"epoch": 5.13545347467609,
|
| 9203 |
+
"grad_norm": 0.19884084165096283,
|
| 9204 |
+
"learning_rate": 3.2036646549843677e-06,
|
| 9205 |
+
"loss": 0.1327,
|
| 9206 |
+
"step": 13080
|
| 9207 |
+
},
|
| 9208 |
+
{
|
| 9209 |
+
"epoch": 5.13937966234786,
|
| 9210 |
+
"grad_norm": 0.0239251721650362,
|
| 9211 |
+
"learning_rate": 3.1891223733003713e-06,
|
| 9212 |
+
"loss": 0.0513,
|
| 9213 |
+
"step": 13090
|
| 9214 |
+
},
|
| 9215 |
+
{
|
| 9216 |
+
"epoch": 5.143305850019631,
|
| 9217 |
+
"grad_norm": 0.006924458313733339,
|
| 9218 |
+
"learning_rate": 3.174580091616375e-06,
|
| 9219 |
+
"loss": 0.0133,
|
| 9220 |
+
"step": 13100
|
| 9221 |
+
},
|
| 9222 |
+
{
|
| 9223 |
+
"epoch": 5.147232037691402,
|
| 9224 |
+
"grad_norm": 0.4384118914604187,
|
| 9225 |
+
"learning_rate": 3.1600378099323788e-06,
|
| 9226 |
+
"loss": 0.0916,
|
| 9227 |
+
"step": 13110
|
| 9228 |
+
},
|
| 9229 |
+
{
|
| 9230 |
+
"epoch": 5.151158225363172,
|
| 9231 |
+
"grad_norm": 0.001333769061602652,
|
| 9232 |
+
"learning_rate": 3.1454955282483823e-06,
|
| 9233 |
+
"loss": 0.0052,
|
| 9234 |
+
"step": 13120
|
| 9235 |
+
},
|
| 9236 |
+
{
|
| 9237 |
+
"epoch": 5.155084413034943,
|
| 9238 |
+
"grad_norm": 0.007520567160099745,
|
| 9239 |
+
"learning_rate": 3.130953246564386e-06,
|
| 9240 |
+
"loss": 0.0046,
|
| 9241 |
+
"step": 13130
|
| 9242 |
+
},
|
| 9243 |
+
{
|
| 9244 |
+
"epoch": 5.159010600706714,
|
| 9245 |
+
"grad_norm": 0.16920150816440582,
|
| 9246 |
+
"learning_rate": 3.11641096488039e-06,
|
| 9247 |
+
"loss": 0.0017,
|
| 9248 |
+
"step": 13140
|
| 9249 |
+
},
|
| 9250 |
+
{
|
| 9251 |
+
"epoch": 5.1629367883784845,
|
| 9252 |
+
"grad_norm": 0.34078341722488403,
|
| 9253 |
+
"learning_rate": 3.101868683196394e-06,
|
| 9254 |
+
"loss": 0.0406,
|
| 9255 |
+
"step": 13150
|
| 9256 |
+
},
|
| 9257 |
+
{
|
| 9258 |
+
"epoch": 5.166862976050255,
|
| 9259 |
+
"grad_norm": 0.0028604476246982813,
|
| 9260 |
+
"learning_rate": 3.0873264015123978e-06,
|
| 9261 |
+
"loss": 0.0572,
|
| 9262 |
+
"step": 13160
|
| 9263 |
+
},
|
| 9264 |
+
{
|
| 9265 |
+
"epoch": 5.170789163722026,
|
| 9266 |
+
"grad_norm": 0.2515994906425476,
|
| 9267 |
+
"learning_rate": 3.0727841198284013e-06,
|
| 9268 |
+
"loss": 0.0196,
|
| 9269 |
+
"step": 13170
|
| 9270 |
+
},
|
| 9271 |
+
{
|
| 9272 |
+
"epoch": 5.174715351393797,
|
| 9273 |
+
"grad_norm": 0.00822716485708952,
|
| 9274 |
+
"learning_rate": 3.0582418381444053e-06,
|
| 9275 |
+
"loss": 0.0676,
|
| 9276 |
+
"step": 13180
|
| 9277 |
+
},
|
| 9278 |
+
{
|
| 9279 |
+
"epoch": 5.178641539065567,
|
| 9280 |
+
"grad_norm": 0.03895296901464462,
|
| 9281 |
+
"learning_rate": 3.043699556460409e-06,
|
| 9282 |
+
"loss": 0.0208,
|
| 9283 |
+
"step": 13190
|
| 9284 |
+
},
|
| 9285 |
+
{
|
| 9286 |
+
"epoch": 5.1825677267373385,
|
| 9287 |
+
"grad_norm": 0.027789801359176636,
|
| 9288 |
+
"learning_rate": 3.0291572747764124e-06,
|
| 9289 |
+
"loss": 0.1947,
|
| 9290 |
+
"step": 13200
|
| 9291 |
+
},
|
| 9292 |
+
{
|
| 9293 |
+
"epoch": 5.186493914409109,
|
| 9294 |
+
"grad_norm": 0.12390786409378052,
|
| 9295 |
+
"learning_rate": 3.0146149930924164e-06,
|
| 9296 |
+
"loss": 0.025,
|
| 9297 |
+
"step": 13210
|
| 9298 |
+
},
|
| 9299 |
+
{
|
| 9300 |
+
"epoch": 5.190420102080879,
|
| 9301 |
+
"grad_norm": 0.4857393205165863,
|
| 9302 |
+
"learning_rate": 3.0000727114084203e-06,
|
| 9303 |
+
"loss": 0.0173,
|
| 9304 |
+
"step": 13220
|
| 9305 |
+
},
|
| 9306 |
+
{
|
| 9307 |
+
"epoch": 5.19434628975265,
|
| 9308 |
+
"grad_norm": 0.05573948845267296,
|
| 9309 |
+
"learning_rate": 2.9855304297244243e-06,
|
| 9310 |
+
"loss": 0.0219,
|
| 9311 |
+
"step": 13230
|
| 9312 |
+
},
|
| 9313 |
+
{
|
| 9314 |
+
"epoch": 5.198272477424421,
|
| 9315 |
+
"grad_norm": 1.2702642679214478,
|
| 9316 |
+
"learning_rate": 2.970988148040428e-06,
|
| 9317 |
+
"loss": 0.0115,
|
| 9318 |
+
"step": 13240
|
| 9319 |
+
},
|
| 9320 |
+
{
|
| 9321 |
+
"epoch": 5.2021986650961916,
|
| 9322 |
+
"grad_norm": 0.022528905421495438,
|
| 9323 |
+
"learning_rate": 2.956445866356432e-06,
|
| 9324 |
+
"loss": 0.0039,
|
| 9325 |
+
"step": 13250
|
| 9326 |
+
},
|
| 9327 |
+
{
|
| 9328 |
+
"epoch": 5.206124852767962,
|
| 9329 |
+
"grad_norm": 3.9462780952453613,
|
| 9330 |
+
"learning_rate": 2.9419035846724353e-06,
|
| 9331 |
+
"loss": 0.2247,
|
| 9332 |
+
"step": 13260
|
| 9333 |
+
},
|
| 9334 |
+
{
|
| 9335 |
+
"epoch": 5.210051040439733,
|
| 9336 |
+
"grad_norm": 0.5228520035743713,
|
| 9337 |
+
"learning_rate": 2.927361302988439e-06,
|
| 9338 |
+
"loss": 0.068,
|
| 9339 |
+
"step": 13270
|
| 9340 |
+
},
|
| 9341 |
+
{
|
| 9342 |
+
"epoch": 5.213977228111504,
|
| 9343 |
+
"grad_norm": 0.013452913612127304,
|
| 9344 |
+
"learning_rate": 2.912819021304443e-06,
|
| 9345 |
+
"loss": 0.0597,
|
| 9346 |
+
"step": 13280
|
| 9347 |
+
},
|
| 9348 |
+
{
|
| 9349 |
+
"epoch": 5.217903415783274,
|
| 9350 |
+
"grad_norm": 0.8905442953109741,
|
| 9351 |
+
"learning_rate": 2.8982767396204464e-06,
|
| 9352 |
+
"loss": 0.0654,
|
| 9353 |
+
"step": 13290
|
| 9354 |
+
},
|
| 9355 |
+
{
|
| 9356 |
+
"epoch": 5.2218296034550455,
|
| 9357 |
+
"grad_norm": 0.011509922333061695,
|
| 9358 |
+
"learning_rate": 2.883734457936451e-06,
|
| 9359 |
+
"loss": 0.0213,
|
| 9360 |
+
"step": 13300
|
| 9361 |
+
},
|
| 9362 |
+
{
|
| 9363 |
+
"epoch": 5.225755791126816,
|
| 9364 |
+
"grad_norm": 0.025475185364484787,
|
| 9365 |
+
"learning_rate": 2.8691921762524543e-06,
|
| 9366 |
+
"loss": 0.045,
|
| 9367 |
+
"step": 13310
|
| 9368 |
+
},
|
| 9369 |
+
{
|
| 9370 |
+
"epoch": 5.229681978798586,
|
| 9371 |
+
"grad_norm": 1.049399495124817,
|
| 9372 |
+
"learning_rate": 2.854649894568458e-06,
|
| 9373 |
+
"loss": 0.0823,
|
| 9374 |
+
"step": 13320
|
| 9375 |
+
},
|
| 9376 |
+
{
|
| 9377 |
+
"epoch": 5.233608166470357,
|
| 9378 |
+
"grad_norm": 0.016877299174666405,
|
| 9379 |
+
"learning_rate": 2.840107612884462e-06,
|
| 9380 |
+
"loss": 0.0024,
|
| 9381 |
+
"step": 13330
|
| 9382 |
+
},
|
| 9383 |
+
{
|
| 9384 |
+
"epoch": 5.237534354142128,
|
| 9385 |
+
"grad_norm": 1.3382182121276855,
|
| 9386 |
+
"learning_rate": 2.8255653312004654e-06,
|
| 9387 |
+
"loss": 0.0355,
|
| 9388 |
+
"step": 13340
|
| 9389 |
+
},
|
| 9390 |
+
{
|
| 9391 |
+
"epoch": 5.241460541813899,
|
| 9392 |
+
"grad_norm": 0.006417367607355118,
|
| 9393 |
+
"learning_rate": 2.8110230495164694e-06,
|
| 9394 |
+
"loss": 0.0189,
|
| 9395 |
+
"step": 13350
|
| 9396 |
+
},
|
| 9397 |
+
{
|
| 9398 |
+
"epoch": 5.245386729485669,
|
| 9399 |
+
"grad_norm": 0.4398579001426697,
|
| 9400 |
+
"learning_rate": 2.796480767832473e-06,
|
| 9401 |
+
"loss": 0.0087,
|
| 9402 |
+
"step": 13360
|
| 9403 |
+
},
|
| 9404 |
+
{
|
| 9405 |
+
"epoch": 5.24931291715744,
|
| 9406 |
+
"grad_norm": 0.017184341326355934,
|
| 9407 |
+
"learning_rate": 2.7819384861484773e-06,
|
| 9408 |
+
"loss": 0.0061,
|
| 9409 |
+
"step": 13370
|
| 9410 |
+
},
|
| 9411 |
+
{
|
| 9412 |
+
"epoch": 5.253239104829211,
|
| 9413 |
+
"grad_norm": 0.03131440281867981,
|
| 9414 |
+
"learning_rate": 2.767396204464481e-06,
|
| 9415 |
+
"loss": 0.0205,
|
| 9416 |
+
"step": 13380
|
| 9417 |
+
},
|
| 9418 |
+
{
|
| 9419 |
+
"epoch": 5.257165292500981,
|
| 9420 |
+
"grad_norm": 27.15860939025879,
|
| 9421 |
+
"learning_rate": 2.7528539227804844e-06,
|
| 9422 |
+
"loss": 0.0403,
|
| 9423 |
+
"step": 13390
|
| 9424 |
+
},
|
| 9425 |
+
{
|
| 9426 |
+
"epoch": 5.261091480172753,
|
| 9427 |
+
"grad_norm": 0.0036987257190048695,
|
| 9428 |
+
"learning_rate": 2.7383116410964884e-06,
|
| 9429 |
+
"loss": 0.0332,
|
| 9430 |
+
"step": 13400
|
| 9431 |
+
},
|
| 9432 |
+
{
|
| 9433 |
+
"epoch": 5.265017667844523,
|
| 9434 |
+
"grad_norm": 0.025162002071738243,
|
| 9435 |
+
"learning_rate": 2.723769359412492e-06,
|
| 9436 |
+
"loss": 0.0007,
|
| 9437 |
+
"step": 13410
|
| 9438 |
+
},
|
| 9439 |
+
{
|
| 9440 |
+
"epoch": 5.2689438555162935,
|
| 9441 |
+
"grad_norm": 0.07918771356344223,
|
| 9442 |
+
"learning_rate": 2.709227077728496e-06,
|
| 9443 |
+
"loss": 0.0028,
|
| 9444 |
+
"step": 13420
|
| 9445 |
+
},
|
| 9446 |
+
{
|
| 9447 |
+
"epoch": 5.272870043188064,
|
| 9448 |
+
"grad_norm": 0.01032128743827343,
|
| 9449 |
+
"learning_rate": 2.6946847960444994e-06,
|
| 9450 |
+
"loss": 0.0229,
|
| 9451 |
+
"step": 13430
|
| 9452 |
+
},
|
| 9453 |
+
{
|
| 9454 |
+
"epoch": 5.276796230859835,
|
| 9455 |
+
"grad_norm": 0.0171279888600111,
|
| 9456 |
+
"learning_rate": 2.680142514360504e-06,
|
| 9457 |
+
"loss": 0.0831,
|
| 9458 |
+
"step": 13440
|
| 9459 |
+
},
|
| 9460 |
+
{
|
| 9461 |
+
"epoch": 5.280722418531606,
|
| 9462 |
+
"grad_norm": 0.0037733076605945826,
|
| 9463 |
+
"learning_rate": 2.6656002326765074e-06,
|
| 9464 |
+
"loss": 0.0175,
|
| 9465 |
+
"step": 13450
|
| 9466 |
+
},
|
| 9467 |
+
{
|
| 9468 |
+
"epoch": 5.284648606203376,
|
| 9469 |
+
"grad_norm": 0.09834250062704086,
|
| 9470 |
+
"learning_rate": 2.651057950992511e-06,
|
| 9471 |
+
"loss": 0.2822,
|
| 9472 |
+
"step": 13460
|
| 9473 |
+
},
|
| 9474 |
+
{
|
| 9475 |
+
"epoch": 5.2885747938751475,
|
| 9476 |
+
"grad_norm": 0.055377691984176636,
|
| 9477 |
+
"learning_rate": 2.636515669308515e-06,
|
| 9478 |
+
"loss": 0.0766,
|
| 9479 |
+
"step": 13470
|
| 9480 |
+
},
|
| 9481 |
+
{
|
| 9482 |
+
"epoch": 5.292500981546918,
|
| 9483 |
+
"grad_norm": 0.008076394908130169,
|
| 9484 |
+
"learning_rate": 2.6219733876245184e-06,
|
| 9485 |
+
"loss": 0.0031,
|
| 9486 |
+
"step": 13480
|
| 9487 |
+
},
|
| 9488 |
+
{
|
| 9489 |
+
"epoch": 5.296427169218688,
|
| 9490 |
+
"grad_norm": 81.10934448242188,
|
| 9491 |
+
"learning_rate": 2.6074311059405224e-06,
|
| 9492 |
+
"loss": 0.1855,
|
| 9493 |
+
"step": 13490
|
| 9494 |
+
},
|
| 9495 |
+
{
|
| 9496 |
+
"epoch": 5.30035335689046,
|
| 9497 |
+
"grad_norm": 1.0699714422225952,
|
| 9498 |
+
"learning_rate": 2.592888824256526e-06,
|
| 9499 |
+
"loss": 0.0262,
|
| 9500 |
+
"step": 13500
|
| 9501 |
+
},
|
| 9502 |
+
{
|
| 9503 |
+
"epoch": 5.30427954456223,
|
| 9504 |
+
"grad_norm": 0.4267910122871399,
|
| 9505 |
+
"learning_rate": 2.5783465425725295e-06,
|
| 9506 |
+
"loss": 0.018,
|
| 9507 |
+
"step": 13510
|
| 9508 |
+
},
|
| 9509 |
+
{
|
| 9510 |
+
"epoch": 5.308205732234001,
|
| 9511 |
+
"grad_norm": 0.011763975955545902,
|
| 9512 |
+
"learning_rate": 2.563804260888534e-06,
|
| 9513 |
+
"loss": 0.0096,
|
| 9514 |
+
"step": 13520
|
| 9515 |
+
},
|
| 9516 |
+
{
|
| 9517 |
+
"epoch": 5.312131919905772,
|
| 9518 |
+
"grad_norm": 0.5770227313041687,
|
| 9519 |
+
"learning_rate": 2.5492619792045374e-06,
|
| 9520 |
+
"loss": 0.1769,
|
| 9521 |
+
"step": 13530
|
| 9522 |
+
},
|
| 9523 |
+
{
|
| 9524 |
+
"epoch": 5.316058107577542,
|
| 9525 |
+
"grad_norm": 0.09178698062896729,
|
| 9526 |
+
"learning_rate": 2.5347196975205414e-06,
|
| 9527 |
+
"loss": 0.0902,
|
| 9528 |
+
"step": 13540
|
| 9529 |
+
},
|
| 9530 |
+
{
|
| 9531 |
+
"epoch": 5.319984295249313,
|
| 9532 |
+
"grad_norm": 0.048630207777023315,
|
| 9533 |
+
"learning_rate": 2.520177415836545e-06,
|
| 9534 |
+
"loss": 0.0019,
|
| 9535 |
+
"step": 13550
|
| 9536 |
+
},
|
| 9537 |
+
{
|
| 9538 |
+
"epoch": 5.323910482921083,
|
| 9539 |
+
"grad_norm": 0.5550425052642822,
|
| 9540 |
+
"learning_rate": 2.5056351341525485e-06,
|
| 9541 |
+
"loss": 0.0792,
|
| 9542 |
+
"step": 13560
|
| 9543 |
+
},
|
| 9544 |
+
{
|
| 9545 |
+
"epoch": 5.327836670592855,
|
| 9546 |
+
"grad_norm": 0.016448715701699257,
|
| 9547 |
+
"learning_rate": 2.4910928524685524e-06,
|
| 9548 |
+
"loss": 0.0461,
|
| 9549 |
+
"step": 13570
|
| 9550 |
+
},
|
| 9551 |
+
{
|
| 9552 |
+
"epoch": 5.331762858264625,
|
| 9553 |
+
"grad_norm": 0.016715524718165398,
|
| 9554 |
+
"learning_rate": 2.4765505707845564e-06,
|
| 9555 |
+
"loss": 0.0056,
|
| 9556 |
+
"step": 13580
|
| 9557 |
+
},
|
| 9558 |
+
{
|
| 9559 |
+
"epoch": 5.3356890459363955,
|
| 9560 |
+
"grad_norm": 0.21879799664020538,
|
| 9561 |
+
"learning_rate": 2.46200828910056e-06,
|
| 9562 |
+
"loss": 0.0776,
|
| 9563 |
+
"step": 13590
|
| 9564 |
+
},
|
| 9565 |
+
{
|
| 9566 |
+
"epoch": 5.339615233608167,
|
| 9567 |
+
"grad_norm": 0.10707032680511475,
|
| 9568 |
+
"learning_rate": 2.447466007416564e-06,
|
| 9569 |
+
"loss": 0.0128,
|
| 9570 |
+
"step": 13600
|
| 9571 |
+
},
|
| 9572 |
+
{
|
| 9573 |
+
"epoch": 5.343541421279937,
|
| 9574 |
+
"grad_norm": 0.04921526834368706,
|
| 9575 |
+
"learning_rate": 2.432923725732568e-06,
|
| 9576 |
+
"loss": 0.0615,
|
| 9577 |
+
"step": 13610
|
| 9578 |
+
},
|
| 9579 |
+
{
|
| 9580 |
+
"epoch": 5.347467608951708,
|
| 9581 |
+
"grad_norm": 0.12561321258544922,
|
| 9582 |
+
"learning_rate": 2.4183814440485714e-06,
|
| 9583 |
+
"loss": 0.0084,
|
| 9584 |
+
"step": 13620
|
| 9585 |
+
},
|
| 9586 |
+
{
|
| 9587 |
+
"epoch": 5.351393796623478,
|
| 9588 |
+
"grad_norm": 0.02247566170990467,
|
| 9589 |
+
"learning_rate": 2.403839162364575e-06,
|
| 9590 |
+
"loss": 0.0126,
|
| 9591 |
+
"step": 13630
|
| 9592 |
+
},
|
| 9593 |
+
{
|
| 9594 |
+
"epoch": 5.3553199842952495,
|
| 9595 |
+
"grad_norm": 0.05497532710433006,
|
| 9596 |
+
"learning_rate": 2.389296880680579e-06,
|
| 9597 |
+
"loss": 0.024,
|
| 9598 |
+
"step": 13640
|
| 9599 |
+
},
|
| 9600 |
+
{
|
| 9601 |
+
"epoch": 5.35924617196702,
|
| 9602 |
+
"grad_norm": 0.12238848209381104,
|
| 9603 |
+
"learning_rate": 2.374754598996583e-06,
|
| 9604 |
+
"loss": 0.1796,
|
| 9605 |
+
"step": 13650
|
| 9606 |
+
},
|
| 9607 |
+
{
|
| 9608 |
+
"epoch": 5.36317235963879,
|
| 9609 |
+
"grad_norm": 0.17428678274154663,
|
| 9610 |
+
"learning_rate": 2.3602123173125865e-06,
|
| 9611 |
+
"loss": 0.0162,
|
| 9612 |
+
"step": 13660
|
| 9613 |
+
},
|
| 9614 |
+
{
|
| 9615 |
+
"epoch": 5.367098547310562,
|
| 9616 |
+
"grad_norm": 9.30865478515625,
|
| 9617 |
+
"learning_rate": 2.3456700356285904e-06,
|
| 9618 |
+
"loss": 0.1717,
|
| 9619 |
+
"step": 13670
|
| 9620 |
+
},
|
| 9621 |
+
{
|
| 9622 |
+
"epoch": 5.371024734982332,
|
| 9623 |
+
"grad_norm": 51.424686431884766,
|
| 9624 |
+
"learning_rate": 2.3311277539445944e-06,
|
| 9625 |
+
"loss": 0.1089,
|
| 9626 |
+
"step": 13680
|
| 9627 |
+
},
|
| 9628 |
+
{
|
| 9629 |
+
"epoch": 5.374950922654103,
|
| 9630 |
+
"grad_norm": 1.6587468385696411,
|
| 9631 |
+
"learning_rate": 2.316585472260598e-06,
|
| 9632 |
+
"loss": 0.0222,
|
| 9633 |
+
"step": 13690
|
| 9634 |
+
},
|
| 9635 |
+
{
|
| 9636 |
+
"epoch": 5.378877110325874,
|
| 9637 |
+
"grad_norm": 19.65317726135254,
|
| 9638 |
+
"learning_rate": 2.3020431905766015e-06,
|
| 9639 |
+
"loss": 0.0758,
|
| 9640 |
+
"step": 13700
|
| 9641 |
+
},
|
| 9642 |
+
{
|
| 9643 |
+
"epoch": 5.382803297997644,
|
| 9644 |
+
"grad_norm": 0.03584019094705582,
|
| 9645 |
+
"learning_rate": 2.2875009088926055e-06,
|
| 9646 |
+
"loss": 0.2242,
|
| 9647 |
+
"step": 13710
|
| 9648 |
+
},
|
| 9649 |
+
{
|
| 9650 |
+
"epoch": 5.386729485669415,
|
| 9651 |
+
"grad_norm": 0.07063400000333786,
|
| 9652 |
+
"learning_rate": 2.2729586272086094e-06,
|
| 9653 |
+
"loss": 0.0182,
|
| 9654 |
+
"step": 13720
|
| 9655 |
+
},
|
| 9656 |
+
{
|
| 9657 |
+
"epoch": 5.390655673341186,
|
| 9658 |
+
"grad_norm": 0.06738784164190292,
|
| 9659 |
+
"learning_rate": 2.258416345524613e-06,
|
| 9660 |
+
"loss": 0.0234,
|
| 9661 |
+
"step": 13730
|
| 9662 |
+
},
|
| 9663 |
+
{
|
| 9664 |
+
"epoch": 5.394581861012957,
|
| 9665 |
+
"grad_norm": 0.6667420864105225,
|
| 9666 |
+
"learning_rate": 2.2438740638406165e-06,
|
| 9667 |
+
"loss": 0.0051,
|
| 9668 |
+
"step": 13740
|
| 9669 |
+
},
|
| 9670 |
+
{
|
| 9671 |
+
"epoch": 5.398508048684727,
|
| 9672 |
+
"grad_norm": 1.8902767896652222,
|
| 9673 |
+
"learning_rate": 2.2293317821566205e-06,
|
| 9674 |
+
"loss": 0.0357,
|
| 9675 |
+
"step": 13750
|
| 9676 |
+
},
|
| 9677 |
+
{
|
| 9678 |
+
"epoch": 5.402434236356497,
|
| 9679 |
+
"grad_norm": 0.015472080558538437,
|
| 9680 |
+
"learning_rate": 2.2147895004726245e-06,
|
| 9681 |
+
"loss": 0.0078,
|
| 9682 |
+
"step": 13760
|
| 9683 |
+
},
|
| 9684 |
+
{
|
| 9685 |
+
"epoch": 5.406360424028269,
|
| 9686 |
+
"grad_norm": 0.03682781755924225,
|
| 9687 |
+
"learning_rate": 2.200247218788628e-06,
|
| 9688 |
+
"loss": 0.0639,
|
| 9689 |
+
"step": 13770
|
| 9690 |
+
},
|
| 9691 |
+
{
|
| 9692 |
+
"epoch": 5.410286611700039,
|
| 9693 |
+
"grad_norm": 0.0730796754360199,
|
| 9694 |
+
"learning_rate": 2.185704937104632e-06,
|
| 9695 |
+
"loss": 0.0012,
|
| 9696 |
+
"step": 13780
|
| 9697 |
+
},
|
| 9698 |
+
{
|
| 9699 |
+
"epoch": 5.41421279937181,
|
| 9700 |
+
"grad_norm": 0.009114271961152554,
|
| 9701 |
+
"learning_rate": 2.171162655420636e-06,
|
| 9702 |
+
"loss": 0.1224,
|
| 9703 |
+
"step": 13790
|
| 9704 |
+
},
|
| 9705 |
+
{
|
| 9706 |
+
"epoch": 5.418138987043581,
|
| 9707 |
+
"grad_norm": 0.09223034232854843,
|
| 9708 |
+
"learning_rate": 2.1566203737366395e-06,
|
| 9709 |
+
"loss": 0.002,
|
| 9710 |
+
"step": 13800
|
| 9711 |
+
},
|
| 9712 |
+
{
|
| 9713 |
+
"epoch": 5.422065174715351,
|
| 9714 |
+
"grad_norm": 0.0053596170619130135,
|
| 9715 |
+
"learning_rate": 2.142078092052643e-06,
|
| 9716 |
+
"loss": 0.0023,
|
| 9717 |
+
"step": 13810
|
| 9718 |
+
},
|
| 9719 |
+
{
|
| 9720 |
+
"epoch": 5.425991362387122,
|
| 9721 |
+
"grad_norm": 0.06519204378128052,
|
| 9722 |
+
"learning_rate": 2.127535810368647e-06,
|
| 9723 |
+
"loss": 0.0676,
|
| 9724 |
+
"step": 13820
|
| 9725 |
+
},
|
| 9726 |
+
{
|
| 9727 |
+
"epoch": 5.429917550058893,
|
| 9728 |
+
"grad_norm": 0.03809221833944321,
|
| 9729 |
+
"learning_rate": 2.112993528684651e-06,
|
| 9730 |
+
"loss": 0.0432,
|
| 9731 |
+
"step": 13830
|
| 9732 |
+
},
|
| 9733 |
+
{
|
| 9734 |
+
"epoch": 5.433843737730664,
|
| 9735 |
+
"grad_norm": 2.4985737800598145,
|
| 9736 |
+
"learning_rate": 2.0984512470006545e-06,
|
| 9737 |
+
"loss": 0.0927,
|
| 9738 |
+
"step": 13840
|
| 9739 |
+
},
|
| 9740 |
+
{
|
| 9741 |
+
"epoch": 5.437769925402434,
|
| 9742 |
+
"grad_norm": 0.021190524101257324,
|
| 9743 |
+
"learning_rate": 2.0839089653166585e-06,
|
| 9744 |
+
"loss": 0.1773,
|
| 9745 |
+
"step": 13850
|
| 9746 |
+
},
|
| 9747 |
+
{
|
| 9748 |
+
"epoch": 5.4416961130742045,
|
| 9749 |
+
"grad_norm": 0.016824249178171158,
|
| 9750 |
+
"learning_rate": 2.069366683632662e-06,
|
| 9751 |
+
"loss": 0.0068,
|
| 9752 |
+
"step": 13860
|
| 9753 |
+
},
|
| 9754 |
+
{
|
| 9755 |
+
"epoch": 5.445622300745976,
|
| 9756 |
+
"grad_norm": 20.109731674194336,
|
| 9757 |
+
"learning_rate": 2.054824401948666e-06,
|
| 9758 |
+
"loss": 0.0392,
|
| 9759 |
+
"step": 13870
|
| 9760 |
+
},
|
| 9761 |
+
{
|
| 9762 |
+
"epoch": 5.449548488417746,
|
| 9763 |
+
"grad_norm": 0.08417905867099762,
|
| 9764 |
+
"learning_rate": 2.0402821202646695e-06,
|
| 9765 |
+
"loss": 0.0566,
|
| 9766 |
+
"step": 13880
|
| 9767 |
+
},
|
| 9768 |
+
{
|
| 9769 |
+
"epoch": 5.453474676089517,
|
| 9770 |
+
"grad_norm": 0.023470373824238777,
|
| 9771 |
+
"learning_rate": 2.0257398385806735e-06,
|
| 9772 |
+
"loss": 0.0124,
|
| 9773 |
+
"step": 13890
|
| 9774 |
+
},
|
| 9775 |
+
{
|
| 9776 |
+
"epoch": 5.457400863761288,
|
| 9777 |
+
"grad_norm": 7.295632839202881,
|
| 9778 |
+
"learning_rate": 2.011197556896677e-06,
|
| 9779 |
+
"loss": 0.1492,
|
| 9780 |
+
"step": 13900
|
| 9781 |
+
},
|
| 9782 |
+
{
|
| 9783 |
+
"epoch": 5.4613270514330585,
|
| 9784 |
+
"grad_norm": 0.026961902156472206,
|
| 9785 |
+
"learning_rate": 1.996655275212681e-06,
|
| 9786 |
+
"loss": 0.0831,
|
| 9787 |
+
"step": 13910
|
| 9788 |
+
},
|
| 9789 |
+
{
|
| 9790 |
+
"epoch": 5.465253239104829,
|
| 9791 |
+
"grad_norm": 2.058932065963745,
|
| 9792 |
+
"learning_rate": 1.982112993528685e-06,
|
| 9793 |
+
"loss": 0.0711,
|
| 9794 |
+
"step": 13920
|
| 9795 |
+
},
|
| 9796 |
+
{
|
| 9797 |
+
"epoch": 5.4691794267766,
|
| 9798 |
+
"grad_norm": 0.045518700033426285,
|
| 9799 |
+
"learning_rate": 1.9675707118446885e-06,
|
| 9800 |
+
"loss": 0.0101,
|
| 9801 |
+
"step": 13930
|
| 9802 |
+
},
|
| 9803 |
+
{
|
| 9804 |
+
"epoch": 5.473105614448371,
|
| 9805 |
+
"grad_norm": 0.006427444517612457,
|
| 9806 |
+
"learning_rate": 1.9530284301606925e-06,
|
| 9807 |
+
"loss": 0.0352,
|
| 9808 |
+
"step": 13940
|
| 9809 |
+
},
|
| 9810 |
+
{
|
| 9811 |
+
"epoch": 5.477031802120141,
|
| 9812 |
+
"grad_norm": 0.11437901854515076,
|
| 9813 |
+
"learning_rate": 1.938486148476696e-06,
|
| 9814 |
+
"loss": 0.0822,
|
| 9815 |
+
"step": 13950
|
| 9816 |
+
},
|
| 9817 |
+
{
|
| 9818 |
+
"epoch": 5.4809579897919125,
|
| 9819 |
+
"grad_norm": 0.012722511775791645,
|
| 9820 |
+
"learning_rate": 1.9239438667927e-06,
|
| 9821 |
+
"loss": 0.0361,
|
| 9822 |
+
"step": 13960
|
| 9823 |
+
},
|
| 9824 |
+
{
|
| 9825 |
+
"epoch": 5.484884177463683,
|
| 9826 |
+
"grad_norm": 0.2673863470554352,
|
| 9827 |
+
"learning_rate": 1.9094015851087036e-06,
|
| 9828 |
+
"loss": 0.0152,
|
| 9829 |
+
"step": 13970
|
| 9830 |
+
},
|
| 9831 |
+
{
|
| 9832 |
+
"epoch": 5.488810365135453,
|
| 9833 |
+
"grad_norm": 0.3240662217140198,
|
| 9834 |
+
"learning_rate": 1.8948593034247075e-06,
|
| 9835 |
+
"loss": 0.0965,
|
| 9836 |
+
"step": 13980
|
| 9837 |
+
},
|
| 9838 |
+
{
|
| 9839 |
+
"epoch": 5.492736552807224,
|
| 9840 |
+
"grad_norm": 0.0017553267534822226,
|
| 9841 |
+
"learning_rate": 1.8803170217407113e-06,
|
| 9842 |
+
"loss": 0.0363,
|
| 9843 |
+
"step": 13990
|
| 9844 |
+
},
|
| 9845 |
+
{
|
| 9846 |
+
"epoch": 5.496662740478995,
|
| 9847 |
+
"grad_norm": 3.0169355869293213,
|
| 9848 |
+
"learning_rate": 1.865774740056715e-06,
|
| 9849 |
+
"loss": 0.0102,
|
| 9850 |
+
"step": 14000
|
| 9851 |
+
},
|
| 9852 |
+
{
|
| 9853 |
+
"epoch": 5.500588928150766,
|
| 9854 |
+
"grad_norm": 0.11221221089363098,
|
| 9855 |
+
"learning_rate": 1.8512324583727186e-06,
|
| 9856 |
+
"loss": 0.1418,
|
| 9857 |
+
"step": 14010
|
| 9858 |
+
},
|
| 9859 |
+
{
|
| 9860 |
+
"epoch": 5.504515115822536,
|
| 9861 |
+
"grad_norm": 0.052316613495349884,
|
| 9862 |
+
"learning_rate": 1.8366901766887228e-06,
|
| 9863 |
+
"loss": 0.0438,
|
| 9864 |
+
"step": 14020
|
| 9865 |
+
},
|
| 9866 |
+
{
|
| 9867 |
+
"epoch": 5.508441303494307,
|
| 9868 |
+
"grad_norm": 0.19758369028568268,
|
| 9869 |
+
"learning_rate": 1.8221478950047263e-06,
|
| 9870 |
+
"loss": 0.0169,
|
| 9871 |
+
"step": 14030
|
| 9872 |
+
},
|
| 9873 |
+
{
|
| 9874 |
+
"epoch": 5.512367491166078,
|
| 9875 |
+
"grad_norm": 0.05802454426884651,
|
| 9876 |
+
"learning_rate": 1.80760561332073e-06,
|
| 9877 |
+
"loss": 0.0121,
|
| 9878 |
+
"step": 14040
|
| 9879 |
+
},
|
| 9880 |
+
{
|
| 9881 |
+
"epoch": 5.516293678837848,
|
| 9882 |
+
"grad_norm": 0.2266709953546524,
|
| 9883 |
+
"learning_rate": 1.793063331636734e-06,
|
| 9884 |
+
"loss": 0.0036,
|
| 9885 |
+
"step": 14050
|
| 9886 |
+
},
|
| 9887 |
+
{
|
| 9888 |
+
"epoch": 5.520219866509619,
|
| 9889 |
+
"grad_norm": 0.007310713175684214,
|
| 9890 |
+
"learning_rate": 1.7785210499527378e-06,
|
| 9891 |
+
"loss": 0.007,
|
| 9892 |
+
"step": 14060
|
| 9893 |
+
},
|
| 9894 |
+
{
|
| 9895 |
+
"epoch": 5.52414605418139,
|
| 9896 |
+
"grad_norm": 1.3063634634017944,
|
| 9897 |
+
"learning_rate": 1.7639787682687416e-06,
|
| 9898 |
+
"loss": 0.2725,
|
| 9899 |
+
"step": 14070
|
| 9900 |
+
},
|
| 9901 |
+
{
|
| 9902 |
+
"epoch": 5.5280722418531605,
|
| 9903 |
+
"grad_norm": 0.008820558898150921,
|
| 9904 |
+
"learning_rate": 1.749436486584745e-06,
|
| 9905 |
+
"loss": 0.0774,
|
| 9906 |
+
"step": 14080
|
| 9907 |
+
},
|
| 9908 |
+
{
|
| 9909 |
+
"epoch": 5.531998429524931,
|
| 9910 |
+
"grad_norm": 1.2626054286956787,
|
| 9911 |
+
"learning_rate": 1.734894204900749e-06,
|
| 9912 |
+
"loss": 0.0511,
|
| 9913 |
+
"step": 14090
|
| 9914 |
+
},
|
| 9915 |
+
{
|
| 9916 |
+
"epoch": 5.535924617196702,
|
| 9917 |
+
"grad_norm": 3.019049644470215,
|
| 9918 |
+
"learning_rate": 1.7203519232167528e-06,
|
| 9919 |
+
"loss": 0.0176,
|
| 9920 |
+
"step": 14100
|
| 9921 |
+
},
|
| 9922 |
+
{
|
| 9923 |
+
"epoch": 5.539850804868473,
|
| 9924 |
+
"grad_norm": 0.016724396497011185,
|
| 9925 |
+
"learning_rate": 1.7058096415327566e-06,
|
| 9926 |
+
"loss": 0.0213,
|
| 9927 |
+
"step": 14110
|
| 9928 |
+
},
|
| 9929 |
+
{
|
| 9930 |
+
"epoch": 5.543776992540243,
|
| 9931 |
+
"grad_norm": 0.0938519686460495,
|
| 9932 |
+
"learning_rate": 1.6912673598487603e-06,
|
| 9933 |
+
"loss": 0.0188,
|
| 9934 |
+
"step": 14120
|
| 9935 |
+
},
|
| 9936 |
+
{
|
| 9937 |
+
"epoch": 5.5477031802120145,
|
| 9938 |
+
"grad_norm": 0.25192487239837646,
|
| 9939 |
+
"learning_rate": 1.6767250781647643e-06,
|
| 9940 |
+
"loss": 0.0961,
|
| 9941 |
+
"step": 14130
|
| 9942 |
+
},
|
| 9943 |
+
{
|
| 9944 |
+
"epoch": 5.551629367883785,
|
| 9945 |
+
"grad_norm": 0.08271001279354095,
|
| 9946 |
+
"learning_rate": 1.662182796480768e-06,
|
| 9947 |
+
"loss": 0.0171,
|
| 9948 |
+
"step": 14140
|
| 9949 |
+
},
|
| 9950 |
+
{
|
| 9951 |
+
"epoch": 5.555555555555555,
|
| 9952 |
+
"grad_norm": 0.005356936249881983,
|
| 9953 |
+
"learning_rate": 1.6476405147967716e-06,
|
| 9954 |
+
"loss": 0.003,
|
| 9955 |
+
"step": 14150
|
| 9956 |
+
},
|
| 9957 |
+
{
|
| 9958 |
+
"epoch": 5.559481743227327,
|
| 9959 |
+
"grad_norm": 0.024072032421827316,
|
| 9960 |
+
"learning_rate": 1.6330982331127756e-06,
|
| 9961 |
+
"loss": 0.0323,
|
| 9962 |
+
"step": 14160
|
| 9963 |
+
},
|
| 9964 |
+
{
|
| 9965 |
+
"epoch": 5.563407930899097,
|
| 9966 |
+
"grad_norm": 2.456899404525757,
|
| 9967 |
+
"learning_rate": 1.6185559514287793e-06,
|
| 9968 |
+
"loss": 0.074,
|
| 9969 |
+
"step": 14170
|
| 9970 |
+
},
|
| 9971 |
+
{
|
| 9972 |
+
"epoch": 5.567334118570868,
|
| 9973 |
+
"grad_norm": 0.035430874675512314,
|
| 9974 |
+
"learning_rate": 1.604013669744783e-06,
|
| 9975 |
+
"loss": 0.0148,
|
| 9976 |
+
"step": 14180
|
| 9977 |
+
},
|
| 9978 |
+
{
|
| 9979 |
+
"epoch": 5.571260306242638,
|
| 9980 |
+
"grad_norm": 0.46541786193847656,
|
| 9981 |
+
"learning_rate": 1.5894713880607869e-06,
|
| 9982 |
+
"loss": 0.0057,
|
| 9983 |
+
"step": 14190
|
| 9984 |
+
},
|
| 9985 |
+
{
|
| 9986 |
+
"epoch": 5.575186493914409,
|
| 9987 |
+
"grad_norm": 0.0735827088356018,
|
| 9988 |
+
"learning_rate": 1.5749291063767908e-06,
|
| 9989 |
+
"loss": 0.0047,
|
| 9990 |
+
"step": 14200
|
| 9991 |
+
},
|
| 9992 |
+
{
|
| 9993 |
+
"epoch": 5.57911268158618,
|
| 9994 |
+
"grad_norm": 17.190523147583008,
|
| 9995 |
+
"learning_rate": 1.5603868246927944e-06,
|
| 9996 |
+
"loss": 0.2135,
|
| 9997 |
+
"step": 14210
|
| 9998 |
+
},
|
| 9999 |
+
{
|
| 10000 |
+
"epoch": 5.58303886925795,
|
| 10001 |
+
"grad_norm": 0.019281059503555298,
|
| 10002 |
+
"learning_rate": 1.5458445430087981e-06,
|
| 10003 |
+
"loss": 0.1011,
|
| 10004 |
+
"step": 14220
|
| 10005 |
+
},
|
| 10006 |
+
{
|
| 10007 |
+
"epoch": 5.586965056929722,
|
| 10008 |
+
"grad_norm": 0.0035344010684639215,
|
| 10009 |
+
"learning_rate": 1.5313022613248019e-06,
|
| 10010 |
+
"loss": 0.1228,
|
| 10011 |
+
"step": 14230
|
| 10012 |
+
},
|
| 10013 |
+
{
|
| 10014 |
+
"epoch": 5.590891244601492,
|
| 10015 |
+
"grad_norm": 0.035331860184669495,
|
| 10016 |
+
"learning_rate": 1.5167599796408058e-06,
|
| 10017 |
+
"loss": 0.0073,
|
| 10018 |
+
"step": 14240
|
| 10019 |
+
},
|
| 10020 |
+
{
|
| 10021 |
+
"epoch": 5.5948174322732624,
|
| 10022 |
+
"grad_norm": 0.48911577463150024,
|
| 10023 |
+
"learning_rate": 1.5022176979568096e-06,
|
| 10024 |
+
"loss": 0.0227,
|
| 10025 |
+
"step": 14250
|
| 10026 |
+
},
|
| 10027 |
+
{
|
| 10028 |
+
"epoch": 5.598743619945033,
|
| 10029 |
+
"grad_norm": 0.4395599663257599,
|
| 10030 |
+
"learning_rate": 1.4876754162728132e-06,
|
| 10031 |
+
"loss": 0.1172,
|
| 10032 |
+
"step": 14260
|
| 10033 |
+
},
|
| 10034 |
+
{
|
| 10035 |
+
"epoch": 5.602669807616804,
|
| 10036 |
+
"grad_norm": 25.795352935791016,
|
| 10037 |
+
"learning_rate": 1.4731331345888173e-06,
|
| 10038 |
+
"loss": 0.0476,
|
| 10039 |
+
"step": 14270
|
| 10040 |
+
},
|
| 10041 |
+
{
|
| 10042 |
+
"epoch": 5.606595995288575,
|
| 10043 |
+
"grad_norm": 0.12749771773815155,
|
| 10044 |
+
"learning_rate": 1.4585908529048209e-06,
|
| 10045 |
+
"loss": 0.0039,
|
| 10046 |
+
"step": 14280
|
| 10047 |
+
},
|
| 10048 |
+
{
|
| 10049 |
+
"epoch": 5.610522182960345,
|
| 10050 |
+
"grad_norm": 0.06636939942836761,
|
| 10051 |
+
"learning_rate": 1.4440485712208246e-06,
|
| 10052 |
+
"loss": 0.0695,
|
| 10053 |
+
"step": 14290
|
| 10054 |
+
},
|
| 10055 |
+
{
|
| 10056 |
+
"epoch": 5.614448370632116,
|
| 10057 |
+
"grad_norm": 0.0034394601825624704,
|
| 10058 |
+
"learning_rate": 1.4295062895368284e-06,
|
| 10059 |
+
"loss": 0.0889,
|
| 10060 |
+
"step": 14300
|
| 10061 |
+
},
|
| 10062 |
+
{
|
| 10063 |
+
"epoch": 5.618374558303887,
|
| 10064 |
+
"grad_norm": 1.0628284215927124,
|
| 10065 |
+
"learning_rate": 1.4149640078528324e-06,
|
| 10066 |
+
"loss": 0.006,
|
| 10067 |
+
"step": 14310
|
| 10068 |
+
},
|
| 10069 |
+
{
|
| 10070 |
+
"epoch": 5.622300745975657,
|
| 10071 |
+
"grad_norm": 0.9704715609550476,
|
| 10072 |
+
"learning_rate": 1.4004217261688361e-06,
|
| 10073 |
+
"loss": 0.004,
|
| 10074 |
+
"step": 14320
|
| 10075 |
+
},
|
| 10076 |
+
{
|
| 10077 |
+
"epoch": 5.626226933647429,
|
| 10078 |
+
"grad_norm": 0.07156730443239212,
|
| 10079 |
+
"learning_rate": 1.3858794444848397e-06,
|
| 10080 |
+
"loss": 0.0482,
|
| 10081 |
+
"step": 14330
|
| 10082 |
+
},
|
| 10083 |
+
{
|
| 10084 |
+
"epoch": 5.630153121319199,
|
| 10085 |
+
"grad_norm": 1.9203593730926514,
|
| 10086 |
+
"learning_rate": 1.3713371628008434e-06,
|
| 10087 |
+
"loss": 0.0251,
|
| 10088 |
+
"step": 14340
|
| 10089 |
+
},
|
| 10090 |
+
{
|
| 10091 |
+
"epoch": 5.6340793089909695,
|
| 10092 |
+
"grad_norm": 0.04148911312222481,
|
| 10093 |
+
"learning_rate": 1.3567948811168474e-06,
|
| 10094 |
+
"loss": 0.0032,
|
| 10095 |
+
"step": 14350
|
| 10096 |
+
},
|
| 10097 |
+
{
|
| 10098 |
+
"epoch": 5.638005496662741,
|
| 10099 |
+
"grad_norm": 0.8570902943611145,
|
| 10100 |
+
"learning_rate": 1.3422525994328511e-06,
|
| 10101 |
+
"loss": 0.0233,
|
| 10102 |
+
"step": 14360
|
| 10103 |
+
},
|
| 10104 |
+
{
|
| 10105 |
+
"epoch": 5.641931684334511,
|
| 10106 |
+
"grad_norm": 0.020535767078399658,
|
| 10107 |
+
"learning_rate": 1.327710317748855e-06,
|
| 10108 |
+
"loss": 0.0145,
|
| 10109 |
+
"step": 14370
|
| 10110 |
+
},
|
| 10111 |
+
{
|
| 10112 |
+
"epoch": 5.645857872006282,
|
| 10113 |
+
"grad_norm": 0.1849496066570282,
|
| 10114 |
+
"learning_rate": 1.3131680360648589e-06,
|
| 10115 |
+
"loss": 0.0618,
|
| 10116 |
+
"step": 14380
|
| 10117 |
+
},
|
| 10118 |
+
{
|
| 10119 |
+
"epoch": 5.649784059678053,
|
| 10120 |
+
"grad_norm": 0.13416092097759247,
|
| 10121 |
+
"learning_rate": 1.2986257543808626e-06,
|
| 10122 |
+
"loss": 0.0015,
|
| 10123 |
+
"step": 14390
|
| 10124 |
+
},
|
| 10125 |
+
{
|
| 10126 |
+
"epoch": 5.6537102473498235,
|
| 10127 |
+
"grad_norm": 0.45092448592185974,
|
| 10128 |
+
"learning_rate": 1.2840834726968662e-06,
|
| 10129 |
+
"loss": 0.1596,
|
| 10130 |
+
"step": 14400
|
| 10131 |
+
},
|
| 10132 |
+
{
|
| 10133 |
+
"epoch": 5.657636435021594,
|
| 10134 |
+
"grad_norm": 3.510319232940674,
|
| 10135 |
+
"learning_rate": 1.26954119101287e-06,
|
| 10136 |
+
"loss": 0.0189,
|
| 10137 |
+
"step": 14410
|
| 10138 |
+
},
|
| 10139 |
+
{
|
| 10140 |
+
"epoch": 5.661562622693364,
|
| 10141 |
+
"grad_norm": 0.002187862992286682,
|
| 10142 |
+
"learning_rate": 1.254998909328874e-06,
|
| 10143 |
+
"loss": 0.0257,
|
| 10144 |
+
"step": 14420
|
| 10145 |
+
},
|
| 10146 |
+
{
|
| 10147 |
+
"epoch": 5.665488810365136,
|
| 10148 |
+
"grad_norm": 0.0790225937962532,
|
| 10149 |
+
"learning_rate": 1.2404566276448777e-06,
|
| 10150 |
+
"loss": 0.208,
|
| 10151 |
+
"step": 14430
|
| 10152 |
+
},
|
| 10153 |
+
{
|
| 10154 |
+
"epoch": 5.669414998036906,
|
| 10155 |
+
"grad_norm": 0.056631043553352356,
|
| 10156 |
+
"learning_rate": 1.2259143459608814e-06,
|
| 10157 |
+
"loss": 0.0173,
|
| 10158 |
+
"step": 14440
|
| 10159 |
+
},
|
| 10160 |
+
{
|
| 10161 |
+
"epoch": 5.673341185708677,
|
| 10162 |
+
"grad_norm": 0.01783832348883152,
|
| 10163 |
+
"learning_rate": 1.2113720642768852e-06,
|
| 10164 |
+
"loss": 0.0138,
|
| 10165 |
+
"step": 14450
|
| 10166 |
+
},
|
| 10167 |
+
{
|
| 10168 |
+
"epoch": 5.677267373380448,
|
| 10169 |
+
"grad_norm": 0.05720403790473938,
|
| 10170 |
+
"learning_rate": 1.196829782592889e-06,
|
| 10171 |
+
"loss": 0.0036,
|
| 10172 |
+
"step": 14460
|
| 10173 |
+
},
|
| 10174 |
+
{
|
| 10175 |
+
"epoch": 5.681193561052218,
|
| 10176 |
+
"grad_norm": 0.009933676570653915,
|
| 10177 |
+
"learning_rate": 1.1822875009088927e-06,
|
| 10178 |
+
"loss": 0.0026,
|
| 10179 |
+
"step": 14470
|
| 10180 |
+
},
|
| 10181 |
+
{
|
| 10182 |
+
"epoch": 5.685119748723989,
|
| 10183 |
+
"grad_norm": 0.006784483790397644,
|
| 10184 |
+
"learning_rate": 1.1677452192248964e-06,
|
| 10185 |
+
"loss": 0.0122,
|
| 10186 |
+
"step": 14480
|
| 10187 |
+
},
|
| 10188 |
+
{
|
| 10189 |
+
"epoch": 5.689045936395759,
|
| 10190 |
+
"grad_norm": 0.2829114496707916,
|
| 10191 |
+
"learning_rate": 1.1532029375409002e-06,
|
| 10192 |
+
"loss": 0.1554,
|
| 10193 |
+
"step": 14490
|
| 10194 |
+
},
|
| 10195 |
+
{
|
| 10196 |
+
"epoch": 5.692972124067531,
|
| 10197 |
+
"grad_norm": 1.6247832775115967,
|
| 10198 |
+
"learning_rate": 1.1386606558569042e-06,
|
| 10199 |
+
"loss": 0.025,
|
| 10200 |
+
"step": 14500
|
| 10201 |
+
},
|
| 10202 |
+
{
|
| 10203 |
+
"epoch": 5.696898311739301,
|
| 10204 |
+
"grad_norm": 0.23121963441371918,
|
| 10205 |
+
"learning_rate": 1.1241183741729077e-06,
|
| 10206 |
+
"loss": 0.0063,
|
| 10207 |
+
"step": 14510
|
| 10208 |
+
},
|
| 10209 |
+
{
|
| 10210 |
+
"epoch": 5.7008244994110715,
|
| 10211 |
+
"grad_norm": 0.027603790163993835,
|
| 10212 |
+
"learning_rate": 1.1095760924889117e-06,
|
| 10213 |
+
"loss": 0.2143,
|
| 10214 |
+
"step": 14520
|
| 10215 |
+
},
|
| 10216 |
+
{
|
| 10217 |
+
"epoch": 5.704750687082843,
|
| 10218 |
+
"grad_norm": 0.025430187582969666,
|
| 10219 |
+
"learning_rate": 1.0950338108049154e-06,
|
| 10220 |
+
"loss": 0.0041,
|
| 10221 |
+
"step": 14530
|
| 10222 |
+
},
|
| 10223 |
+
{
|
| 10224 |
+
"epoch": 5.708676874754613,
|
| 10225 |
+
"grad_norm": 4.559391498565674,
|
| 10226 |
+
"learning_rate": 1.0804915291209192e-06,
|
| 10227 |
+
"loss": 0.0114,
|
| 10228 |
+
"step": 14540
|
| 10229 |
+
},
|
| 10230 |
+
{
|
| 10231 |
+
"epoch": 5.712603062426384,
|
| 10232 |
+
"grad_norm": 0.20368392765522003,
|
| 10233 |
+
"learning_rate": 1.065949247436923e-06,
|
| 10234 |
+
"loss": 0.0024,
|
| 10235 |
+
"step": 14550
|
| 10236 |
+
},
|
| 10237 |
+
{
|
| 10238 |
+
"epoch": 5.716529250098155,
|
| 10239 |
+
"grad_norm": 0.006946520879864693,
|
| 10240 |
+
"learning_rate": 1.0514069657529267e-06,
|
| 10241 |
+
"loss": 0.0307,
|
| 10242 |
+
"step": 14560
|
| 10243 |
+
},
|
| 10244 |
+
{
|
| 10245 |
+
"epoch": 5.7204554377699255,
|
| 10246 |
+
"grad_norm": 3.4614949226379395,
|
| 10247 |
+
"learning_rate": 1.0368646840689305e-06,
|
| 10248 |
+
"loss": 0.0772,
|
| 10249 |
+
"step": 14570
|
| 10250 |
+
},
|
| 10251 |
+
{
|
| 10252 |
+
"epoch": 5.724381625441696,
|
| 10253 |
+
"grad_norm": 0.05242728441953659,
|
| 10254 |
+
"learning_rate": 1.0223224023849342e-06,
|
| 10255 |
+
"loss": 0.0095,
|
| 10256 |
+
"step": 14580
|
| 10257 |
+
},
|
| 10258 |
+
{
|
| 10259 |
+
"epoch": 5.728307813113467,
|
| 10260 |
+
"grad_norm": 40.201961517333984,
|
| 10261 |
+
"learning_rate": 1.007780120700938e-06,
|
| 10262 |
+
"loss": 0.1323,
|
| 10263 |
+
"step": 14590
|
| 10264 |
+
},
|
| 10265 |
+
{
|
| 10266 |
+
"epoch": 5.732234000785238,
|
| 10267 |
+
"grad_norm": 0.005555798299610615,
|
| 10268 |
+
"learning_rate": 9.93237839016942e-07,
|
| 10269 |
+
"loss": 0.0315,
|
| 10270 |
+
"step": 14600
|
| 10271 |
+
},
|
| 10272 |
+
{
|
| 10273 |
+
"epoch": 5.736160188457008,
|
| 10274 |
+
"grad_norm": 0.00913204438984394,
|
| 10275 |
+
"learning_rate": 9.786955573329455e-07,
|
| 10276 |
+
"loss": 0.009,
|
| 10277 |
+
"step": 14610
|
| 10278 |
+
},
|
| 10279 |
+
{
|
| 10280 |
+
"epoch": 5.740086376128779,
|
| 10281 |
+
"grad_norm": 0.07541371136903763,
|
| 10282 |
+
"learning_rate": 9.641532756489495e-07,
|
| 10283 |
+
"loss": 0.0079,
|
| 10284 |
+
"step": 14620
|
| 10285 |
+
},
|
| 10286 |
+
{
|
| 10287 |
+
"epoch": 5.74401256380055,
|
| 10288 |
+
"grad_norm": 0.07345477491617203,
|
| 10289 |
+
"learning_rate": 9.496109939649532e-07,
|
| 10290 |
+
"loss": 0.0754,
|
| 10291 |
+
"step": 14630
|
| 10292 |
+
},
|
| 10293 |
+
{
|
| 10294 |
+
"epoch": 5.74793875147232,
|
| 10295 |
+
"grad_norm": 0.007082406897097826,
|
| 10296 |
+
"learning_rate": 9.35068712280957e-07,
|
| 10297 |
+
"loss": 0.0039,
|
| 10298 |
+
"step": 14640
|
| 10299 |
+
},
|
| 10300 |
+
{
|
| 10301 |
+
"epoch": 5.751864939144091,
|
| 10302 |
+
"grad_norm": 0.07387743145227432,
|
| 10303 |
+
"learning_rate": 9.205264305969608e-07,
|
| 10304 |
+
"loss": 0.0176,
|
| 10305 |
+
"step": 14650
|
| 10306 |
+
},
|
| 10307 |
+
{
|
| 10308 |
+
"epoch": 5.755791126815862,
|
| 10309 |
+
"grad_norm": 0.015638642013072968,
|
| 10310 |
+
"learning_rate": 9.059841489129645e-07,
|
| 10311 |
+
"loss": 0.0015,
|
| 10312 |
+
"step": 14660
|
| 10313 |
+
},
|
| 10314 |
+
{
|
| 10315 |
+
"epoch": 5.759717314487633,
|
| 10316 |
+
"grad_norm": 0.4665980935096741,
|
| 10317 |
+
"learning_rate": 8.914418672289683e-07,
|
| 10318 |
+
"loss": 0.0108,
|
| 10319 |
+
"step": 14670
|
| 10320 |
+
},
|
| 10321 |
+
{
|
| 10322 |
+
"epoch": 5.763643502159403,
|
| 10323 |
+
"grad_norm": 44.496177673339844,
|
| 10324 |
+
"learning_rate": 8.76899585544972e-07,
|
| 10325 |
+
"loss": 0.1702,
|
| 10326 |
+
"step": 14680
|
| 10327 |
+
},
|
| 10328 |
+
{
|
| 10329 |
+
"epoch": 5.7675696898311735,
|
| 10330 |
+
"grad_norm": 33.924495697021484,
|
| 10331 |
+
"learning_rate": 8.623573038609759e-07,
|
| 10332 |
+
"loss": 0.0503,
|
| 10333 |
+
"step": 14690
|
| 10334 |
+
},
|
| 10335 |
+
{
|
| 10336 |
+
"epoch": 5.771495877502945,
|
| 10337 |
+
"grad_norm": 0.014301096089184284,
|
| 10338 |
+
"learning_rate": 8.478150221769796e-07,
|
| 10339 |
+
"loss": 0.0757,
|
| 10340 |
+
"step": 14700
|
| 10341 |
+
},
|
| 10342 |
+
{
|
| 10343 |
+
"epoch": 5.775422065174715,
|
| 10344 |
+
"grad_norm": 11.683112144470215,
|
| 10345 |
+
"learning_rate": 8.332727404929834e-07,
|
| 10346 |
+
"loss": 0.0106,
|
| 10347 |
+
"step": 14710
|
| 10348 |
+
},
|
| 10349 |
+
{
|
| 10350 |
+
"epoch": 5.779348252846486,
|
| 10351 |
+
"grad_norm": 0.054620411247015,
|
| 10352 |
+
"learning_rate": 8.187304588089871e-07,
|
| 10353 |
+
"loss": 0.0125,
|
| 10354 |
+
"step": 14720
|
| 10355 |
+
},
|
| 10356 |
+
{
|
| 10357 |
+
"epoch": 5.783274440518257,
|
| 10358 |
+
"grad_norm": 1.8667157888412476,
|
| 10359 |
+
"learning_rate": 8.04188177124991e-07,
|
| 10360 |
+
"loss": 0.0669,
|
| 10361 |
+
"step": 14730
|
| 10362 |
+
},
|
| 10363 |
+
{
|
| 10364 |
+
"epoch": 5.7872006281900275,
|
| 10365 |
+
"grad_norm": 0.0034203925170004368,
|
| 10366 |
+
"learning_rate": 7.896458954409949e-07,
|
| 10367 |
+
"loss": 0.0022,
|
| 10368 |
+
"step": 14740
|
| 10369 |
+
},
|
| 10370 |
+
{
|
| 10371 |
+
"epoch": 5.791126815861798,
|
| 10372 |
+
"grad_norm": 5.37122106552124,
|
| 10373 |
+
"learning_rate": 7.751036137569985e-07,
|
| 10374 |
+
"loss": 0.0382,
|
| 10375 |
+
"step": 14750
|
| 10376 |
+
},
|
| 10377 |
+
{
|
| 10378 |
+
"epoch": 5.795053003533569,
|
| 10379 |
+
"grad_norm": 1.0283739566802979,
|
| 10380 |
+
"learning_rate": 7.605613320730024e-07,
|
| 10381 |
+
"loss": 0.0078,
|
| 10382 |
+
"step": 14760
|
| 10383 |
+
},
|
| 10384 |
+
{
|
| 10385 |
+
"epoch": 5.79897919120534,
|
| 10386 |
+
"grad_norm": 0.35248079895973206,
|
| 10387 |
+
"learning_rate": 7.46019050389006e-07,
|
| 10388 |
+
"loss": 0.0153,
|
| 10389 |
+
"step": 14770
|
| 10390 |
+
},
|
| 10391 |
+
{
|
| 10392 |
+
"epoch": 5.80290537887711,
|
| 10393 |
+
"grad_norm": 5.8855366706848145,
|
| 10394 |
+
"learning_rate": 7.314767687050099e-07,
|
| 10395 |
+
"loss": 0.0404,
|
| 10396 |
+
"step": 14780
|
| 10397 |
+
},
|
| 10398 |
+
{
|
| 10399 |
+
"epoch": 5.806831566548881,
|
| 10400 |
+
"grad_norm": 0.21485786139965057,
|
| 10401 |
+
"learning_rate": 7.169344870210136e-07,
|
| 10402 |
+
"loss": 0.0046,
|
| 10403 |
+
"step": 14790
|
| 10404 |
+
},
|
| 10405 |
+
{
|
| 10406 |
+
"epoch": 5.810757754220652,
|
| 10407 |
+
"grad_norm": 0.1697346419095993,
|
| 10408 |
+
"learning_rate": 7.023922053370175e-07,
|
| 10409 |
+
"loss": 0.0538,
|
| 10410 |
+
"step": 14800
|
| 10411 |
+
},
|
| 10412 |
+
{
|
| 10413 |
+
"epoch": 5.814683941892422,
|
| 10414 |
+
"grad_norm": 3.940727472305298,
|
| 10415 |
+
"learning_rate": 6.878499236530212e-07,
|
| 10416 |
+
"loss": 0.0893,
|
| 10417 |
+
"step": 14810
|
| 10418 |
+
},
|
| 10419 |
+
{
|
| 10420 |
+
"epoch": 5.818610129564194,
|
| 10421 |
+
"grad_norm": 0.022784672677516937,
|
| 10422 |
+
"learning_rate": 6.73307641969025e-07,
|
| 10423 |
+
"loss": 0.0043,
|
| 10424 |
+
"step": 14820
|
| 10425 |
+
},
|
| 10426 |
+
{
|
| 10427 |
+
"epoch": 5.822536317235964,
|
| 10428 |
+
"grad_norm": 0.024461161345243454,
|
| 10429 |
+
"learning_rate": 6.587653602850287e-07,
|
| 10430 |
+
"loss": 0.0065,
|
| 10431 |
+
"step": 14830
|
| 10432 |
+
},
|
| 10433 |
+
{
|
| 10434 |
+
"epoch": 5.8264625049077345,
|
| 10435 |
+
"grad_norm": 0.07929394394159317,
|
| 10436 |
+
"learning_rate": 6.442230786010325e-07,
|
| 10437 |
+
"loss": 0.0066,
|
| 10438 |
+
"step": 14840
|
| 10439 |
+
},
|
| 10440 |
+
{
|
| 10441 |
+
"epoch": 5.830388692579505,
|
| 10442 |
+
"grad_norm": 1.7705389261245728,
|
| 10443 |
+
"learning_rate": 6.296807969170364e-07,
|
| 10444 |
+
"loss": 0.013,
|
| 10445 |
+
"step": 14850
|
| 10446 |
+
},
|
| 10447 |
+
{
|
| 10448 |
+
"epoch": 5.834314880251276,
|
| 10449 |
+
"grad_norm": 8.195009231567383,
|
| 10450 |
+
"learning_rate": 6.151385152330402e-07,
|
| 10451 |
+
"loss": 0.1298,
|
| 10452 |
+
"step": 14860
|
| 10453 |
+
},
|
| 10454 |
+
{
|
| 10455 |
+
"epoch": 5.838241067923047,
|
| 10456 |
+
"grad_norm": 39.31391143798828,
|
| 10457 |
+
"learning_rate": 6.005962335490439e-07,
|
| 10458 |
+
"loss": 0.1349,
|
| 10459 |
+
"step": 14870
|
| 10460 |
+
},
|
| 10461 |
+
{
|
| 10462 |
+
"epoch": 5.842167255594817,
|
| 10463 |
+
"grad_norm": 0.35662949085235596,
|
| 10464 |
+
"learning_rate": 5.860539518650477e-07,
|
| 10465 |
+
"loss": 0.0336,
|
| 10466 |
+
"step": 14880
|
| 10467 |
+
},
|
| 10468 |
+
{
|
| 10469 |
+
"epoch": 5.8460934432665885,
|
| 10470 |
+
"grad_norm": 0.0659799724817276,
|
| 10471 |
+
"learning_rate": 5.715116701810514e-07,
|
| 10472 |
+
"loss": 0.0024,
|
| 10473 |
+
"step": 14890
|
| 10474 |
+
},
|
| 10475 |
+
{
|
| 10476 |
+
"epoch": 5.850019630938359,
|
| 10477 |
+
"grad_norm": 0.0031293316278606653,
|
| 10478 |
+
"learning_rate": 5.569693884970552e-07,
|
| 10479 |
+
"loss": 0.0049,
|
| 10480 |
+
"step": 14900
|
| 10481 |
+
},
|
| 10482 |
+
{
|
| 10483 |
+
"epoch": 5.853945818610129,
|
| 10484 |
+
"grad_norm": 0.02747061289846897,
|
| 10485 |
+
"learning_rate": 5.42427106813059e-07,
|
| 10486 |
+
"loss": 0.2643,
|
| 10487 |
+
"step": 14910
|
| 10488 |
+
},
|
| 10489 |
+
{
|
| 10490 |
+
"epoch": 5.8578720062819,
|
| 10491 |
+
"grad_norm": 0.35784733295440674,
|
| 10492 |
+
"learning_rate": 5.278848251290628e-07,
|
| 10493 |
+
"loss": 0.046,
|
| 10494 |
+
"step": 14920
|
| 10495 |
+
},
|
| 10496 |
+
{
|
| 10497 |
+
"epoch": 5.861798193953671,
|
| 10498 |
+
"grad_norm": 0.09811792522668839,
|
| 10499 |
+
"learning_rate": 5.133425434450666e-07,
|
| 10500 |
+
"loss": 0.0113,
|
| 10501 |
+
"step": 14930
|
| 10502 |
+
},
|
| 10503 |
+
{
|
| 10504 |
+
"epoch": 5.865724381625442,
|
| 10505 |
+
"grad_norm": 0.014723632484674454,
|
| 10506 |
+
"learning_rate": 4.988002617610704e-07,
|
| 10507 |
+
"loss": 0.0503,
|
| 10508 |
+
"step": 14940
|
| 10509 |
+
},
|
| 10510 |
+
{
|
| 10511 |
+
"epoch": 5.869650569297212,
|
| 10512 |
+
"grad_norm": 19.55420684814453,
|
| 10513 |
+
"learning_rate": 4.842579800770742e-07,
|
| 10514 |
+
"loss": 0.0909,
|
| 10515 |
+
"step": 14950
|
| 10516 |
+
},
|
| 10517 |
+
{
|
| 10518 |
+
"epoch": 5.873576756968983,
|
| 10519 |
+
"grad_norm": 0.037530459463596344,
|
| 10520 |
+
"learning_rate": 4.6971569839307793e-07,
|
| 10521 |
+
"loss": 0.0336,
|
| 10522 |
+
"step": 14960
|
| 10523 |
+
},
|
| 10524 |
+
{
|
| 10525 |
+
"epoch": 5.877502944640754,
|
| 10526 |
+
"grad_norm": 0.08942714333534241,
|
| 10527 |
+
"learning_rate": 4.551734167090817e-07,
|
| 10528 |
+
"loss": 0.0887,
|
| 10529 |
+
"step": 14970
|
| 10530 |
+
},
|
| 10531 |
+
{
|
| 10532 |
+
"epoch": 5.881429132312524,
|
| 10533 |
+
"grad_norm": 0.004598001018166542,
|
| 10534 |
+
"learning_rate": 4.4063113502508545e-07,
|
| 10535 |
+
"loss": 0.0355,
|
| 10536 |
+
"step": 14980
|
| 10537 |
+
},
|
| 10538 |
+
{
|
| 10539 |
+
"epoch": 5.885355319984296,
|
| 10540 |
+
"grad_norm": 6.1255974769592285,
|
| 10541 |
+
"learning_rate": 4.2608885334108926e-07,
|
| 10542 |
+
"loss": 0.0275,
|
| 10543 |
+
"step": 14990
|
| 10544 |
+
},
|
| 10545 |
+
{
|
| 10546 |
+
"epoch": 5.889281507656066,
|
| 10547 |
+
"grad_norm": 11.237669944763184,
|
| 10548 |
+
"learning_rate": 4.11546571657093e-07,
|
| 10549 |
+
"loss": 0.0115,
|
| 10550 |
+
"step": 15000
|
| 10551 |
+
},
|
| 10552 |
+
{
|
| 10553 |
+
"epoch": 5.8932076953278365,
|
| 10554 |
+
"grad_norm": 2.900330066680908,
|
| 10555 |
+
"learning_rate": 3.9700428997309677e-07,
|
| 10556 |
+
"loss": 0.1485,
|
| 10557 |
+
"step": 15010
|
| 10558 |
+
},
|
| 10559 |
+
{
|
| 10560 |
+
"epoch": 5.897133882999608,
|
| 10561 |
+
"grad_norm": 0.5105991363525391,
|
| 10562 |
+
"learning_rate": 3.824620082891006e-07,
|
| 10563 |
+
"loss": 0.106,
|
| 10564 |
+
"step": 15020
|
| 10565 |
+
},
|
| 10566 |
+
{
|
| 10567 |
+
"epoch": 5.901060070671378,
|
| 10568 |
+
"grad_norm": 0.3964107632637024,
|
| 10569 |
+
"learning_rate": 3.679197266051044e-07,
|
| 10570 |
+
"loss": 0.0114,
|
| 10571 |
+
"step": 15030
|
| 10572 |
+
},
|
| 10573 |
+
{
|
| 10574 |
+
"epoch": 5.904986258343149,
|
| 10575 |
+
"grad_norm": 0.12103541940450668,
|
| 10576 |
+
"learning_rate": 3.533774449211082e-07,
|
| 10577 |
+
"loss": 0.026,
|
| 10578 |
+
"step": 15040
|
| 10579 |
+
},
|
| 10580 |
+
{
|
| 10581 |
+
"epoch": 5.908912446014919,
|
| 10582 |
+
"grad_norm": 0.590338945388794,
|
| 10583 |
+
"learning_rate": 3.3883516323711196e-07,
|
| 10584 |
+
"loss": 0.0431,
|
| 10585 |
+
"step": 15050
|
| 10586 |
+
},
|
| 10587 |
+
{
|
| 10588 |
+
"epoch": 5.9128386336866905,
|
| 10589 |
+
"grad_norm": 21.76214599609375,
|
| 10590 |
+
"learning_rate": 3.242928815531157e-07,
|
| 10591 |
+
"loss": 0.1412,
|
| 10592 |
+
"step": 15060
|
| 10593 |
+
},
|
| 10594 |
+
{
|
| 10595 |
+
"epoch": 5.916764821358461,
|
| 10596 |
+
"grad_norm": 0.22498223185539246,
|
| 10597 |
+
"learning_rate": 3.097505998691195e-07,
|
| 10598 |
+
"loss": 0.0033,
|
| 10599 |
+
"step": 15070
|
| 10600 |
+
},
|
| 10601 |
+
{
|
| 10602 |
+
"epoch": 5.920691009030231,
|
| 10603 |
+
"grad_norm": 0.9044221639633179,
|
| 10604 |
+
"learning_rate": 2.952083181851233e-07,
|
| 10605 |
+
"loss": 0.0123,
|
| 10606 |
+
"step": 15080
|
| 10607 |
+
},
|
| 10608 |
+
{
|
| 10609 |
+
"epoch": 5.924617196702003,
|
| 10610 |
+
"grad_norm": 0.181316539645195,
|
| 10611 |
+
"learning_rate": 2.8066603650112704e-07,
|
| 10612 |
+
"loss": 0.1664,
|
| 10613 |
+
"step": 15090
|
| 10614 |
+
},
|
| 10615 |
+
{
|
| 10616 |
+
"epoch": 5.928543384373773,
|
| 10617 |
+
"grad_norm": 0.27284035086631775,
|
| 10618 |
+
"learning_rate": 2.661237548171308e-07,
|
| 10619 |
+
"loss": 0.0162,
|
| 10620 |
+
"step": 15100
|
| 10621 |
+
},
|
| 10622 |
+
{
|
| 10623 |
+
"epoch": 5.932469572045544,
|
| 10624 |
+
"grad_norm": 0.3034082055091858,
|
| 10625 |
+
"learning_rate": 2.515814731331346e-07,
|
| 10626 |
+
"loss": 0.0024,
|
| 10627 |
+
"step": 15110
|
| 10628 |
+
},
|
| 10629 |
+
{
|
| 10630 |
+
"epoch": 5.936395759717314,
|
| 10631 |
+
"grad_norm": 0.45165276527404785,
|
| 10632 |
+
"learning_rate": 2.3703919144913841e-07,
|
| 10633 |
+
"loss": 0.0044,
|
| 10634 |
+
"step": 15120
|
| 10635 |
+
},
|
| 10636 |
+
{
|
| 10637 |
+
"epoch": 5.940321947389085,
|
| 10638 |
+
"grad_norm": 1.5585776567459106,
|
| 10639 |
+
"learning_rate": 2.2249690976514217e-07,
|
| 10640 |
+
"loss": 0.0092,
|
| 10641 |
+
"step": 15130
|
| 10642 |
+
},
|
| 10643 |
+
{
|
| 10644 |
+
"epoch": 5.944248135060856,
|
| 10645 |
+
"grad_norm": 5.817608833312988,
|
| 10646 |
+
"learning_rate": 2.0795462808114595e-07,
|
| 10647 |
+
"loss": 0.0279,
|
| 10648 |
+
"step": 15140
|
| 10649 |
+
},
|
| 10650 |
+
{
|
| 10651 |
+
"epoch": 5.948174322732626,
|
| 10652 |
+
"grad_norm": 1.1541281938552856,
|
| 10653 |
+
"learning_rate": 1.934123463971497e-07,
|
| 10654 |
+
"loss": 0.0049,
|
| 10655 |
+
"step": 15150
|
| 10656 |
+
},
|
| 10657 |
+
{
|
| 10658 |
+
"epoch": 5.952100510404398,
|
| 10659 |
+
"grad_norm": 0.01794552430510521,
|
| 10660 |
+
"learning_rate": 1.788700647131535e-07,
|
| 10661 |
+
"loss": 0.008,
|
| 10662 |
+
"step": 15160
|
| 10663 |
+
},
|
| 10664 |
+
{
|
| 10665 |
+
"epoch": 5.956026698076168,
|
| 10666 |
+
"grad_norm": 0.5125005841255188,
|
| 10667 |
+
"learning_rate": 1.6432778302915728e-07,
|
| 10668 |
+
"loss": 0.0146,
|
| 10669 |
+
"step": 15170
|
| 10670 |
+
},
|
| 10671 |
+
{
|
| 10672 |
+
"epoch": 5.9599528857479385,
|
| 10673 |
+
"grad_norm": 0.008531455881893635,
|
| 10674 |
+
"learning_rate": 1.4978550134516106e-07,
|
| 10675 |
+
"loss": 0.0339,
|
| 10676 |
+
"step": 15180
|
| 10677 |
+
},
|
| 10678 |
+
{
|
| 10679 |
+
"epoch": 5.96387907341971,
|
| 10680 |
+
"grad_norm": 0.3953339457511902,
|
| 10681 |
+
"learning_rate": 1.3524321966116484e-07,
|
| 10682 |
+
"loss": 0.1486,
|
| 10683 |
+
"step": 15190
|
| 10684 |
+
},
|
| 10685 |
+
{
|
| 10686 |
+
"epoch": 5.96780526109148,
|
| 10687 |
+
"grad_norm": 0.0701107308268547,
|
| 10688 |
+
"learning_rate": 1.2070093797716863e-07,
|
| 10689 |
+
"loss": 0.0118,
|
| 10690 |
+
"step": 15200
|
| 10691 |
+
},
|
| 10692 |
+
{
|
| 10693 |
+
"epoch": 5.971731448763251,
|
| 10694 |
+
"grad_norm": 0.2871693968772888,
|
| 10695 |
+
"learning_rate": 1.061586562931724e-07,
|
| 10696 |
+
"loss": 0.0971,
|
| 10697 |
+
"step": 15210
|
| 10698 |
+
},
|
| 10699 |
+
{
|
| 10700 |
+
"epoch": 5.975657636435022,
|
| 10701 |
+
"grad_norm": 0.07807981967926025,
|
| 10702 |
+
"learning_rate": 9.16163746091762e-08,
|
| 10703 |
+
"loss": 0.01,
|
| 10704 |
+
"step": 15220
|
| 10705 |
+
},
|
| 10706 |
+
{
|
| 10707 |
+
"epoch": 5.9795838241067925,
|
| 10708 |
+
"grad_norm": 0.3016345500946045,
|
| 10709 |
+
"learning_rate": 7.707409292517996e-08,
|
| 10710 |
+
"loss": 0.0375,
|
| 10711 |
+
"step": 15230
|
| 10712 |
+
},
|
| 10713 |
+
{
|
| 10714 |
+
"epoch": 5.983510011778563,
|
| 10715 |
+
"grad_norm": 0.28545162081718445,
|
| 10716 |
+
"learning_rate": 6.253181124118375e-08,
|
| 10717 |
+
"loss": 0.1007,
|
| 10718 |
+
"step": 15240
|
| 10719 |
+
},
|
| 10720 |
+
{
|
| 10721 |
+
"epoch": 5.987436199450333,
|
| 10722 |
+
"grad_norm": 0.012656458653509617,
|
| 10723 |
+
"learning_rate": 4.7989529557187524e-08,
|
| 10724 |
+
"loss": 0.0932,
|
| 10725 |
+
"step": 15250
|
| 10726 |
+
},
|
| 10727 |
+
{
|
| 10728 |
+
"epoch": 5.991362387122105,
|
| 10729 |
+
"grad_norm": 0.059258054941892624,
|
| 10730 |
+
"learning_rate": 3.344724787319131e-08,
|
| 10731 |
+
"loss": 0.0399,
|
| 10732 |
+
"step": 15260
|
| 10733 |
+
},
|
| 10734 |
+
{
|
| 10735 |
+
"epoch": 5.995288574793875,
|
| 10736 |
+
"grad_norm": 0.2904854118824005,
|
| 10737 |
+
"learning_rate": 1.8904966189195088e-08,
|
| 10738 |
+
"loss": 0.1854,
|
| 10739 |
+
"step": 15270
|
| 10740 |
+
},
|
| 10741 |
+
{
|
| 10742 |
+
"epoch": 5.999214762465646,
|
| 10743 |
+
"grad_norm": 1.152124047279358,
|
| 10744 |
+
"learning_rate": 4.362684505198866e-09,
|
| 10745 |
+
"loss": 0.0027,
|
| 10746 |
+
"step": 15280
|
| 10747 |
+
},
|
| 10748 |
+
{
|
| 10749 |
+
"epoch": 6.0,
|
| 10750 |
+
"eval_loss": 0.13578836619853973,
|
| 10751 |
+
"eval_runtime": 20.5714,
|
| 10752 |
+
"eval_samples_per_second": 110.056,
|
| 10753 |
+
"eval_steps_per_second": 13.757,
|
| 10754 |
+
"step": 15282
|
| 10755 |
}
|
| 10756 |
],
|
| 10757 |
"logging_steps": 10,
|
|
|
|
| 10766 |
"early_stopping_threshold": 0.0
|
| 10767 |
},
|
| 10768 |
"attributes": {
|
| 10769 |
+
"early_stopping_patience_counter": 2
|
| 10770 |
}
|
| 10771 |
},
|
| 10772 |
"TrainerControl": {
|
|
|
|
| 10775 |
"should_evaluate": false,
|
| 10776 |
"should_log": false,
|
| 10777 |
"should_save": true,
|
| 10778 |
+
"should_training_stop": true
|
| 10779 |
},
|
| 10780 |
"attributes": {}
|
| 10781 |
}
|
| 10782 |
},
|
| 10783 |
+
"total_flos": 3.21580308916008e+16,
|
| 10784 |
"train_batch_size": 8,
|
| 10785 |
"trial_name": null,
|
| 10786 |
"trial_params": null
|