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 5, 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:d325a08ecc1db7da391fc54c3b9ae749d1748cbb63b6a9394da25fa1fd97f1c0
|
| 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 sha256:08f5c47d4d04f87a60d150cdea79f064dad95ba49e16cdaeab6ee1f34ec6aecd
|
| 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 sha256:0211bc3263ec4f7de19bf975d0c6ee71ca296acfd38d65cf13b02ed30481263b
|
| 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 sha256:5eee1266116b55a4d5adb35bff771153557b2c3127e5c670ee86cb660bf9c040
|
| 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 sha256:28bf0a5a1ff21bb7289b8adaa0abdca1931197fd869554bc1e22af6c2e8e4b51
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 10188,
|
| 3 |
"best_metric": 0.03723596781492233,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpmisnhqpx/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,
|
|
@@ -7166,6 +7166,1799 @@
|
|
| 7166 |
"eval_samples_per_second": 108.726,
|
| 7167 |
"eval_steps_per_second": 13.591,
|
| 7168 |
"step": 10188
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7169 |
}
|
| 7170 |
],
|
| 7171 |
"logging_steps": 10,
|
|
@@ -7180,7 +8973,7 @@
|
|
| 7180 |
"early_stopping_threshold": 0.0
|
| 7181 |
},
|
| 7182 |
"attributes": {
|
| 7183 |
-
"early_stopping_patience_counter":
|
| 7184 |
}
|
| 7185 |
},
|
| 7186 |
"TrainerControl": {
|
|
@@ -7194,7 +8987,7 @@
|
|
| 7194 |
"attributes": {}
|
| 7195 |
}
|
| 7196 |
},
|
| 7197 |
-
"total_flos": 2.
|
| 7198 |
"train_batch_size": 8,
|
| 7199 |
"trial_name": null,
|
| 7200 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 10188,
|
| 3 |
"best_metric": 0.03723596781492233,
|
| 4 |
"best_model_checkpoint": "/tmp/tmpmisnhqpx/deberta-multilabel/checkpoint-10188",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12735,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7166 |
"eval_samples_per_second": 108.726,
|
| 7167 |
"eval_steps_per_second": 13.591,
|
| 7168 |
"step": 10188
|
| 7169 |
+
},
|
| 7170 |
+
{
|
| 7171 |
+
"epoch": 4.000785237534354,
|
| 7172 |
+
"grad_norm": 0.04305413365364075,
|
| 7173 |
+
"learning_rate": 1.6295951605397863e-05,
|
| 7174 |
+
"loss": 0.0192,
|
| 7175 |
+
"step": 10190
|
| 7176 |
+
},
|
| 7177 |
+
{
|
| 7178 |
+
"epoch": 4.004711425206125,
|
| 7179 |
+
"grad_norm": 2.3437047004699707,
|
| 7180 |
+
"learning_rate": 1.629013494648674e-05,
|
| 7181 |
+
"loss": 0.0125,
|
| 7182 |
+
"step": 10200
|
| 7183 |
+
},
|
| 7184 |
+
{
|
| 7185 |
+
"epoch": 4.008637612877895,
|
| 7186 |
+
"grad_norm": 0.3391348421573639,
|
| 7187 |
+
"learning_rate": 1.628431828757562e-05,
|
| 7188 |
+
"loss": 0.0074,
|
| 7189 |
+
"step": 10210
|
| 7190 |
+
},
|
| 7191 |
+
{
|
| 7192 |
+
"epoch": 4.012563800549667,
|
| 7193 |
+
"grad_norm": 0.21356984972953796,
|
| 7194 |
+
"learning_rate": 1.6278501628664495e-05,
|
| 7195 |
+
"loss": 0.1227,
|
| 7196 |
+
"step": 10220
|
| 7197 |
+
},
|
| 7198 |
+
{
|
| 7199 |
+
"epoch": 4.016489988221437,
|
| 7200 |
+
"grad_norm": 0.565312385559082,
|
| 7201 |
+
"learning_rate": 1.6272684969753375e-05,
|
| 7202 |
+
"loss": 0.112,
|
| 7203 |
+
"step": 10230
|
| 7204 |
+
},
|
| 7205 |
+
{
|
| 7206 |
+
"epoch": 4.0204161758932075,
|
| 7207 |
+
"grad_norm": 0.07333213090896606,
|
| 7208 |
+
"learning_rate": 1.6266868310842254e-05,
|
| 7209 |
+
"loss": 0.0287,
|
| 7210 |
+
"step": 10240
|
| 7211 |
+
},
|
| 7212 |
+
{
|
| 7213 |
+
"epoch": 4.024342363564978,
|
| 7214 |
+
"grad_norm": 0.006115520838648081,
|
| 7215 |
+
"learning_rate": 1.626105165193113e-05,
|
| 7216 |
+
"loss": 0.0167,
|
| 7217 |
+
"step": 10250
|
| 7218 |
+
},
|
| 7219 |
+
{
|
| 7220 |
+
"epoch": 4.028268551236749,
|
| 7221 |
+
"grad_norm": 0.0721532478928566,
|
| 7222 |
+
"learning_rate": 1.625523499302001e-05,
|
| 7223 |
+
"loss": 0.0431,
|
| 7224 |
+
"step": 10260
|
| 7225 |
+
},
|
| 7226 |
+
{
|
| 7227 |
+
"epoch": 4.03219473890852,
|
| 7228 |
+
"grad_norm": 0.042635880410671234,
|
| 7229 |
+
"learning_rate": 1.624941833410889e-05,
|
| 7230 |
+
"loss": 0.0144,
|
| 7231 |
+
"step": 10270
|
| 7232 |
+
},
|
| 7233 |
+
{
|
| 7234 |
+
"epoch": 4.03612092658029,
|
| 7235 |
+
"grad_norm": 0.36595016717910767,
|
| 7236 |
+
"learning_rate": 1.624360167519777e-05,
|
| 7237 |
+
"loss": 0.0934,
|
| 7238 |
+
"step": 10280
|
| 7239 |
+
},
|
| 7240 |
+
{
|
| 7241 |
+
"epoch": 4.0400471142520615,
|
| 7242 |
+
"grad_norm": 0.3813411593437195,
|
| 7243 |
+
"learning_rate": 1.6237785016286646e-05,
|
| 7244 |
+
"loss": 0.0105,
|
| 7245 |
+
"step": 10290
|
| 7246 |
+
},
|
| 7247 |
+
{
|
| 7248 |
+
"epoch": 4.043973301923832,
|
| 7249 |
+
"grad_norm": 0.38717159628868103,
|
| 7250 |
+
"learning_rate": 1.6231968357375525e-05,
|
| 7251 |
+
"loss": 0.2739,
|
| 7252 |
+
"step": 10300
|
| 7253 |
+
},
|
| 7254 |
+
{
|
| 7255 |
+
"epoch": 4.047899489595602,
|
| 7256 |
+
"grad_norm": 0.07045949250459671,
|
| 7257 |
+
"learning_rate": 1.62261516984644e-05,
|
| 7258 |
+
"loss": 0.0059,
|
| 7259 |
+
"step": 10310
|
| 7260 |
+
},
|
| 7261 |
+
{
|
| 7262 |
+
"epoch": 4.051825677267374,
|
| 7263 |
+
"grad_norm": 0.11328592151403427,
|
| 7264 |
+
"learning_rate": 1.622033503955328e-05,
|
| 7265 |
+
"loss": 0.0481,
|
| 7266 |
+
"step": 10320
|
| 7267 |
+
},
|
| 7268 |
+
{
|
| 7269 |
+
"epoch": 4.055751864939144,
|
| 7270 |
+
"grad_norm": 0.0012176806339994073,
|
| 7271 |
+
"learning_rate": 1.621451838064216e-05,
|
| 7272 |
+
"loss": 0.0071,
|
| 7273 |
+
"step": 10330
|
| 7274 |
+
},
|
| 7275 |
+
{
|
| 7276 |
+
"epoch": 4.059678052610915,
|
| 7277 |
+
"grad_norm": 0.08526414632797241,
|
| 7278 |
+
"learning_rate": 1.620870172173104e-05,
|
| 7279 |
+
"loss": 0.0141,
|
| 7280 |
+
"step": 10340
|
| 7281 |
+
},
|
| 7282 |
+
{
|
| 7283 |
+
"epoch": 4.063604240282685,
|
| 7284 |
+
"grad_norm": 0.06462130695581436,
|
| 7285 |
+
"learning_rate": 1.6202885062819917e-05,
|
| 7286 |
+
"loss": 0.0091,
|
| 7287 |
+
"step": 10350
|
| 7288 |
+
},
|
| 7289 |
+
{
|
| 7290 |
+
"epoch": 4.067530427954456,
|
| 7291 |
+
"grad_norm": 0.09771827608346939,
|
| 7292 |
+
"learning_rate": 1.6197068403908796e-05,
|
| 7293 |
+
"loss": 0.0318,
|
| 7294 |
+
"step": 10360
|
| 7295 |
+
},
|
| 7296 |
+
{
|
| 7297 |
+
"epoch": 4.071456615626227,
|
| 7298 |
+
"grad_norm": 4.478272438049316,
|
| 7299 |
+
"learning_rate": 1.6191251744997672e-05,
|
| 7300 |
+
"loss": 0.0075,
|
| 7301 |
+
"step": 10370
|
| 7302 |
+
},
|
| 7303 |
+
{
|
| 7304 |
+
"epoch": 4.075382803297997,
|
| 7305 |
+
"grad_norm": 0.012336178682744503,
|
| 7306 |
+
"learning_rate": 1.6185435086086555e-05,
|
| 7307 |
+
"loss": 0.0053,
|
| 7308 |
+
"step": 10380
|
| 7309 |
+
},
|
| 7310 |
+
{
|
| 7311 |
+
"epoch": 4.079308990969769,
|
| 7312 |
+
"grad_norm": 0.05946045741438866,
|
| 7313 |
+
"learning_rate": 1.617961842717543e-05,
|
| 7314 |
+
"loss": 0.0087,
|
| 7315 |
+
"step": 10390
|
| 7316 |
+
},
|
| 7317 |
+
{
|
| 7318 |
+
"epoch": 4.083235178641539,
|
| 7319 |
+
"grad_norm": 0.09730261564254761,
|
| 7320 |
+
"learning_rate": 1.617380176826431e-05,
|
| 7321 |
+
"loss": 0.0095,
|
| 7322 |
+
"step": 10400
|
| 7323 |
+
},
|
| 7324 |
+
{
|
| 7325 |
+
"epoch": 4.0871613663133095,
|
| 7326 |
+
"grad_norm": 0.216200590133667,
|
| 7327 |
+
"learning_rate": 1.6167985109353187e-05,
|
| 7328 |
+
"loss": 0.0041,
|
| 7329 |
+
"step": 10410
|
| 7330 |
+
},
|
| 7331 |
+
{
|
| 7332 |
+
"epoch": 4.091087553985081,
|
| 7333 |
+
"grad_norm": 0.07942214608192444,
|
| 7334 |
+
"learning_rate": 1.6162168450442067e-05,
|
| 7335 |
+
"loss": 0.0043,
|
| 7336 |
+
"step": 10420
|
| 7337 |
+
},
|
| 7338 |
+
{
|
| 7339 |
+
"epoch": 4.095013741656851,
|
| 7340 |
+
"grad_norm": 0.29191839694976807,
|
| 7341 |
+
"learning_rate": 1.6156351791530947e-05,
|
| 7342 |
+
"loss": 0.056,
|
| 7343 |
+
"step": 10430
|
| 7344 |
+
},
|
| 7345 |
+
{
|
| 7346 |
+
"epoch": 4.098939929328622,
|
| 7347 |
+
"grad_norm": 0.4860270619392395,
|
| 7348 |
+
"learning_rate": 1.6150535132619823e-05,
|
| 7349 |
+
"loss": 0.0168,
|
| 7350 |
+
"step": 10440
|
| 7351 |
+
},
|
| 7352 |
+
{
|
| 7353 |
+
"epoch": 4.102866117000393,
|
| 7354 |
+
"grad_norm": 0.2040068656206131,
|
| 7355 |
+
"learning_rate": 1.6144718473708702e-05,
|
| 7356 |
+
"loss": 0.1326,
|
| 7357 |
+
"step": 10450
|
| 7358 |
+
},
|
| 7359 |
+
{
|
| 7360 |
+
"epoch": 4.1067923046721635,
|
| 7361 |
+
"grad_norm": 0.06530219316482544,
|
| 7362 |
+
"learning_rate": 1.6138901814797582e-05,
|
| 7363 |
+
"loss": 0.057,
|
| 7364 |
+
"step": 10460
|
| 7365 |
+
},
|
| 7366 |
+
{
|
| 7367 |
+
"epoch": 4.110718492343934,
|
| 7368 |
+
"grad_norm": 0.043570950627326965,
|
| 7369 |
+
"learning_rate": 1.6133085155886462e-05,
|
| 7370 |
+
"loss": 0.0415,
|
| 7371 |
+
"step": 10470
|
| 7372 |
+
},
|
| 7373 |
+
{
|
| 7374 |
+
"epoch": 4.114644680015704,
|
| 7375 |
+
"grad_norm": 0.07635116577148438,
|
| 7376 |
+
"learning_rate": 1.6127268496975338e-05,
|
| 7377 |
+
"loss": 0.01,
|
| 7378 |
+
"step": 10480
|
| 7379 |
+
},
|
| 7380 |
+
{
|
| 7381 |
+
"epoch": 4.118570867687476,
|
| 7382 |
+
"grad_norm": 10.04716682434082,
|
| 7383 |
+
"learning_rate": 1.6121451838064218e-05,
|
| 7384 |
+
"loss": 0.026,
|
| 7385 |
+
"step": 10490
|
| 7386 |
+
},
|
| 7387 |
+
{
|
| 7388 |
+
"epoch": 4.122497055359246,
|
| 7389 |
+
"grad_norm": 0.2828063368797302,
|
| 7390 |
+
"learning_rate": 1.6115635179153094e-05,
|
| 7391 |
+
"loss": 0.0264,
|
| 7392 |
+
"step": 10500
|
| 7393 |
+
},
|
| 7394 |
+
{
|
| 7395 |
+
"epoch": 4.126423243031017,
|
| 7396 |
+
"grad_norm": 0.08323416113853455,
|
| 7397 |
+
"learning_rate": 1.6109818520241973e-05,
|
| 7398 |
+
"loss": 0.0061,
|
| 7399 |
+
"step": 10510
|
| 7400 |
+
},
|
| 7401 |
+
{
|
| 7402 |
+
"epoch": 4.130349430702788,
|
| 7403 |
+
"grad_norm": 0.022773122414946556,
|
| 7404 |
+
"learning_rate": 1.6104001861330853e-05,
|
| 7405 |
+
"loss": 0.0328,
|
| 7406 |
+
"step": 10520
|
| 7407 |
+
},
|
| 7408 |
+
{
|
| 7409 |
+
"epoch": 4.134275618374558,
|
| 7410 |
+
"grad_norm": 0.8593135476112366,
|
| 7411 |
+
"learning_rate": 1.6098185202419733e-05,
|
| 7412 |
+
"loss": 0.0449,
|
| 7413 |
+
"step": 10530
|
| 7414 |
+
},
|
| 7415 |
+
{
|
| 7416 |
+
"epoch": 4.138201806046329,
|
| 7417 |
+
"grad_norm": 0.1534629613161087,
|
| 7418 |
+
"learning_rate": 1.609236854350861e-05,
|
| 7419 |
+
"loss": 0.0498,
|
| 7420 |
+
"step": 10540
|
| 7421 |
+
},
|
| 7422 |
+
{
|
| 7423 |
+
"epoch": 4.1421279937181,
|
| 7424 |
+
"grad_norm": 0.012216039933264256,
|
| 7425 |
+
"learning_rate": 1.608655188459749e-05,
|
| 7426 |
+
"loss": 0.0181,
|
| 7427 |
+
"step": 10550
|
| 7428 |
+
},
|
| 7429 |
+
{
|
| 7430 |
+
"epoch": 4.146054181389871,
|
| 7431 |
+
"grad_norm": 0.1347481608390808,
|
| 7432 |
+
"learning_rate": 1.6080735225686368e-05,
|
| 7433 |
+
"loss": 0.007,
|
| 7434 |
+
"step": 10560
|
| 7435 |
+
},
|
| 7436 |
+
{
|
| 7437 |
+
"epoch": 4.149980369061641,
|
| 7438 |
+
"grad_norm": 0.007442166097462177,
|
| 7439 |
+
"learning_rate": 1.6074918566775248e-05,
|
| 7440 |
+
"loss": 0.0432,
|
| 7441 |
+
"step": 10570
|
| 7442 |
+
},
|
| 7443 |
+
{
|
| 7444 |
+
"epoch": 4.1539065567334115,
|
| 7445 |
+
"grad_norm": 0.1816093921661377,
|
| 7446 |
+
"learning_rate": 1.6069101907864124e-05,
|
| 7447 |
+
"loss": 0.0242,
|
| 7448 |
+
"step": 10580
|
| 7449 |
+
},
|
| 7450 |
+
{
|
| 7451 |
+
"epoch": 4.157832744405183,
|
| 7452 |
+
"grad_norm": 25.47596549987793,
|
| 7453 |
+
"learning_rate": 1.6063285248953003e-05,
|
| 7454 |
+
"loss": 0.0121,
|
| 7455 |
+
"step": 10590
|
| 7456 |
+
},
|
| 7457 |
+
{
|
| 7458 |
+
"epoch": 4.161758932076953,
|
| 7459 |
+
"grad_norm": 0.01696295291185379,
|
| 7460 |
+
"learning_rate": 1.605746859004188e-05,
|
| 7461 |
+
"loss": 0.0026,
|
| 7462 |
+
"step": 10600
|
| 7463 |
+
},
|
| 7464 |
+
{
|
| 7465 |
+
"epoch": 4.165685119748724,
|
| 7466 |
+
"grad_norm": 1.0690293312072754,
|
| 7467 |
+
"learning_rate": 1.605165193113076e-05,
|
| 7468 |
+
"loss": 0.0074,
|
| 7469 |
+
"step": 10610
|
| 7470 |
+
},
|
| 7471 |
+
{
|
| 7472 |
+
"epoch": 4.169611307420495,
|
| 7473 |
+
"grad_norm": 0.03463326767086983,
|
| 7474 |
+
"learning_rate": 1.604583527221964e-05,
|
| 7475 |
+
"loss": 0.0134,
|
| 7476 |
+
"step": 10620
|
| 7477 |
+
},
|
| 7478 |
+
{
|
| 7479 |
+
"epoch": 4.1735374950922655,
|
| 7480 |
+
"grad_norm": 0.0349225178360939,
|
| 7481 |
+
"learning_rate": 1.6040018613308515e-05,
|
| 7482 |
+
"loss": 0.0077,
|
| 7483 |
+
"step": 10630
|
| 7484 |
+
},
|
| 7485 |
+
{
|
| 7486 |
+
"epoch": 4.177463682764036,
|
| 7487 |
+
"grad_norm": 0.00339132291264832,
|
| 7488 |
+
"learning_rate": 1.6034201954397395e-05,
|
| 7489 |
+
"loss": 0.005,
|
| 7490 |
+
"step": 10640
|
| 7491 |
+
},
|
| 7492 |
+
{
|
| 7493 |
+
"epoch": 4.181389870435807,
|
| 7494 |
+
"grad_norm": 0.02371530421078205,
|
| 7495 |
+
"learning_rate": 1.6028385295486274e-05,
|
| 7496 |
+
"loss": 0.003,
|
| 7497 |
+
"step": 10650
|
| 7498 |
+
},
|
| 7499 |
+
{
|
| 7500 |
+
"epoch": 4.185316058107578,
|
| 7501 |
+
"grad_norm": 4.928411960601807,
|
| 7502 |
+
"learning_rate": 1.6022568636575154e-05,
|
| 7503 |
+
"loss": 0.0827,
|
| 7504 |
+
"step": 10660
|
| 7505 |
+
},
|
| 7506 |
+
{
|
| 7507 |
+
"epoch": 4.189242245779348,
|
| 7508 |
+
"grad_norm": 0.14356833696365356,
|
| 7509 |
+
"learning_rate": 1.601675197766403e-05,
|
| 7510 |
+
"loss": 0.0085,
|
| 7511 |
+
"step": 10670
|
| 7512 |
+
},
|
| 7513 |
+
{
|
| 7514 |
+
"epoch": 4.193168433451119,
|
| 7515 |
+
"grad_norm": 0.9613977074623108,
|
| 7516 |
+
"learning_rate": 1.601093531875291e-05,
|
| 7517 |
+
"loss": 0.0109,
|
| 7518 |
+
"step": 10680
|
| 7519 |
+
},
|
| 7520 |
+
{
|
| 7521 |
+
"epoch": 4.19709462112289,
|
| 7522 |
+
"grad_norm": 0.0465816929936409,
|
| 7523 |
+
"learning_rate": 1.6005118659841786e-05,
|
| 7524 |
+
"loss": 0.0084,
|
| 7525 |
+
"step": 10690
|
| 7526 |
+
},
|
| 7527 |
+
{
|
| 7528 |
+
"epoch": 4.20102080879466,
|
| 7529 |
+
"grad_norm": 0.6129805445671082,
|
| 7530 |
+
"learning_rate": 1.599930200093067e-05,
|
| 7531 |
+
"loss": 0.0401,
|
| 7532 |
+
"step": 10700
|
| 7533 |
+
},
|
| 7534 |
+
{
|
| 7535 |
+
"epoch": 4.204946996466431,
|
| 7536 |
+
"grad_norm": 0.0340413935482502,
|
| 7537 |
+
"learning_rate": 1.5993485342019545e-05,
|
| 7538 |
+
"loss": 0.0113,
|
| 7539 |
+
"step": 10710
|
| 7540 |
+
},
|
| 7541 |
+
{
|
| 7542 |
+
"epoch": 4.208873184138202,
|
| 7543 |
+
"grad_norm": 0.12400192022323608,
|
| 7544 |
+
"learning_rate": 1.5987668683108425e-05,
|
| 7545 |
+
"loss": 0.1624,
|
| 7546 |
+
"step": 10720
|
| 7547 |
+
},
|
| 7548 |
+
{
|
| 7549 |
+
"epoch": 4.2127993718099725,
|
| 7550 |
+
"grad_norm": 11.701301574707031,
|
| 7551 |
+
"learning_rate": 1.59818520241973e-05,
|
| 7552 |
+
"loss": 0.182,
|
| 7553 |
+
"step": 10730
|
| 7554 |
+
},
|
| 7555 |
+
{
|
| 7556 |
+
"epoch": 4.216725559481743,
|
| 7557 |
+
"grad_norm": 0.04973774403333664,
|
| 7558 |
+
"learning_rate": 1.597603536528618e-05,
|
| 7559 |
+
"loss": 0.0379,
|
| 7560 |
+
"step": 10740
|
| 7561 |
+
},
|
| 7562 |
+
{
|
| 7563 |
+
"epoch": 4.220651747153514,
|
| 7564 |
+
"grad_norm": 0.3770604431629181,
|
| 7565 |
+
"learning_rate": 1.597021870637506e-05,
|
| 7566 |
+
"loss": 0.0149,
|
| 7567 |
+
"step": 10750
|
| 7568 |
+
},
|
| 7569 |
+
{
|
| 7570 |
+
"epoch": 4.224577934825285,
|
| 7571 |
+
"grad_norm": 0.007606038358062506,
|
| 7572 |
+
"learning_rate": 1.596440204746394e-05,
|
| 7573 |
+
"loss": 0.0204,
|
| 7574 |
+
"step": 10760
|
| 7575 |
+
},
|
| 7576 |
+
{
|
| 7577 |
+
"epoch": 4.228504122497055,
|
| 7578 |
+
"grad_norm": 0.013688049279153347,
|
| 7579 |
+
"learning_rate": 1.5958585388552816e-05,
|
| 7580 |
+
"loss": 0.0164,
|
| 7581 |
+
"step": 10770
|
| 7582 |
+
},
|
| 7583 |
+
{
|
| 7584 |
+
"epoch": 4.232430310168826,
|
| 7585 |
+
"grad_norm": 0.46689000725746155,
|
| 7586 |
+
"learning_rate": 1.5952768729641696e-05,
|
| 7587 |
+
"loss": 0.0113,
|
| 7588 |
+
"step": 10780
|
| 7589 |
+
},
|
| 7590 |
+
{
|
| 7591 |
+
"epoch": 4.236356497840597,
|
| 7592 |
+
"grad_norm": 0.002636290155351162,
|
| 7593 |
+
"learning_rate": 1.5946952070730575e-05,
|
| 7594 |
+
"loss": 0.0123,
|
| 7595 |
+
"step": 10790
|
| 7596 |
+
},
|
| 7597 |
+
{
|
| 7598 |
+
"epoch": 4.240282685512367,
|
| 7599 |
+
"grad_norm": 3.919311761856079,
|
| 7600 |
+
"learning_rate": 1.594113541181945e-05,
|
| 7601 |
+
"loss": 0.0153,
|
| 7602 |
+
"step": 10800
|
| 7603 |
+
},
|
| 7604 |
+
{
|
| 7605 |
+
"epoch": 4.244208873184138,
|
| 7606 |
+
"grad_norm": 0.34922903776168823,
|
| 7607 |
+
"learning_rate": 1.593531875290833e-05,
|
| 7608 |
+
"loss": 0.008,
|
| 7609 |
+
"step": 10810
|
| 7610 |
+
},
|
| 7611 |
+
{
|
| 7612 |
+
"epoch": 4.248135060855909,
|
| 7613 |
+
"grad_norm": 0.05498547852039337,
|
| 7614 |
+
"learning_rate": 1.592950209399721e-05,
|
| 7615 |
+
"loss": 0.0143,
|
| 7616 |
+
"step": 10820
|
| 7617 |
+
},
|
| 7618 |
+
{
|
| 7619 |
+
"epoch": 4.25206124852768,
|
| 7620 |
+
"grad_norm": 0.07610869407653809,
|
| 7621 |
+
"learning_rate": 1.5923685435086087e-05,
|
| 7622 |
+
"loss": 0.1659,
|
| 7623 |
+
"step": 10830
|
| 7624 |
+
},
|
| 7625 |
+
{
|
| 7626 |
+
"epoch": 4.25598743619945,
|
| 7627 |
+
"grad_norm": 0.3314012289047241,
|
| 7628 |
+
"learning_rate": 1.5917868776174966e-05,
|
| 7629 |
+
"loss": 0.0042,
|
| 7630 |
+
"step": 10840
|
| 7631 |
+
},
|
| 7632 |
+
{
|
| 7633 |
+
"epoch": 4.259913623871221,
|
| 7634 |
+
"grad_norm": 0.057981960475444794,
|
| 7635 |
+
"learning_rate": 1.5912052117263846e-05,
|
| 7636 |
+
"loss": 0.0334,
|
| 7637 |
+
"step": 10850
|
| 7638 |
+
},
|
| 7639 |
+
{
|
| 7640 |
+
"epoch": 4.263839811542992,
|
| 7641 |
+
"grad_norm": 0.8713974356651306,
|
| 7642 |
+
"learning_rate": 1.5906235458352722e-05,
|
| 7643 |
+
"loss": 0.0167,
|
| 7644 |
+
"step": 10860
|
| 7645 |
+
},
|
| 7646 |
+
{
|
| 7647 |
+
"epoch": 4.267765999214762,
|
| 7648 |
+
"grad_norm": 20.447690963745117,
|
| 7649 |
+
"learning_rate": 1.5900418799441602e-05,
|
| 7650 |
+
"loss": 0.1332,
|
| 7651 |
+
"step": 10870
|
| 7652 |
+
},
|
| 7653 |
+
{
|
| 7654 |
+
"epoch": 4.271692186886533,
|
| 7655 |
+
"grad_norm": 0.10746438056230545,
|
| 7656 |
+
"learning_rate": 1.5894602140530478e-05,
|
| 7657 |
+
"loss": 0.005,
|
| 7658 |
+
"step": 10880
|
| 7659 |
+
},
|
| 7660 |
+
{
|
| 7661 |
+
"epoch": 4.275618374558304,
|
| 7662 |
+
"grad_norm": 0.09286653995513916,
|
| 7663 |
+
"learning_rate": 1.588878548161936e-05,
|
| 7664 |
+
"loss": 0.0101,
|
| 7665 |
+
"step": 10890
|
| 7666 |
+
},
|
| 7667 |
+
{
|
| 7668 |
+
"epoch": 4.2795445622300745,
|
| 7669 |
+
"grad_norm": 0.14766548573970795,
|
| 7670 |
+
"learning_rate": 1.5882968822708237e-05,
|
| 7671 |
+
"loss": 0.0406,
|
| 7672 |
+
"step": 10900
|
| 7673 |
+
},
|
| 7674 |
+
{
|
| 7675 |
+
"epoch": 4.283470749901845,
|
| 7676 |
+
"grad_norm": 56.67782211303711,
|
| 7677 |
+
"learning_rate": 1.5877152163797117e-05,
|
| 7678 |
+
"loss": 0.0784,
|
| 7679 |
+
"step": 10910
|
| 7680 |
+
},
|
| 7681 |
+
{
|
| 7682 |
+
"epoch": 4.287396937573616,
|
| 7683 |
+
"grad_norm": 0.03442571684718132,
|
| 7684 |
+
"learning_rate": 1.5871335504885993e-05,
|
| 7685 |
+
"loss": 0.0555,
|
| 7686 |
+
"step": 10920
|
| 7687 |
+
},
|
| 7688 |
+
{
|
| 7689 |
+
"epoch": 4.291323125245387,
|
| 7690 |
+
"grad_norm": 0.22045926749706268,
|
| 7691 |
+
"learning_rate": 1.5865518845974873e-05,
|
| 7692 |
+
"loss": 0.0119,
|
| 7693 |
+
"step": 10930
|
| 7694 |
+
},
|
| 7695 |
+
{
|
| 7696 |
+
"epoch": 4.295249312917157,
|
| 7697 |
+
"grad_norm": 0.027600066736340523,
|
| 7698 |
+
"learning_rate": 1.5859702187063752e-05,
|
| 7699 |
+
"loss": 0.0053,
|
| 7700 |
+
"step": 10940
|
| 7701 |
+
},
|
| 7702 |
+
{
|
| 7703 |
+
"epoch": 4.2991755005889285,
|
| 7704 |
+
"grad_norm": 0.04487202689051628,
|
| 7705 |
+
"learning_rate": 1.5853885528152632e-05,
|
| 7706 |
+
"loss": 0.0105,
|
| 7707 |
+
"step": 10950
|
| 7708 |
+
},
|
| 7709 |
+
{
|
| 7710 |
+
"epoch": 4.303101688260699,
|
| 7711 |
+
"grad_norm": 0.24484175443649292,
|
| 7712 |
+
"learning_rate": 1.5848068869241508e-05,
|
| 7713 |
+
"loss": 0.0157,
|
| 7714 |
+
"step": 10960
|
| 7715 |
+
},
|
| 7716 |
+
{
|
| 7717 |
+
"epoch": 4.307027875932469,
|
| 7718 |
+
"grad_norm": 42.34819412231445,
|
| 7719 |
+
"learning_rate": 1.5842252210330388e-05,
|
| 7720 |
+
"loss": 0.0442,
|
| 7721 |
+
"step": 10970
|
| 7722 |
+
},
|
| 7723 |
+
{
|
| 7724 |
+
"epoch": 4.310954063604241,
|
| 7725 |
+
"grad_norm": 0.003911723382771015,
|
| 7726 |
+
"learning_rate": 1.5836435551419267e-05,
|
| 7727 |
+
"loss": 0.0065,
|
| 7728 |
+
"step": 10980
|
| 7729 |
+
},
|
| 7730 |
+
{
|
| 7731 |
+
"epoch": 4.314880251276011,
|
| 7732 |
+
"grad_norm": 0.06312620639801025,
|
| 7733 |
+
"learning_rate": 1.5830618892508144e-05,
|
| 7734 |
+
"loss": 0.0026,
|
| 7735 |
+
"step": 10990
|
| 7736 |
+
},
|
| 7737 |
+
{
|
| 7738 |
+
"epoch": 4.318806438947782,
|
| 7739 |
+
"grad_norm": 0.08260048180818558,
|
| 7740 |
+
"learning_rate": 1.5824802233597023e-05,
|
| 7741 |
+
"loss": 0.0623,
|
| 7742 |
+
"step": 11000
|
| 7743 |
+
},
|
| 7744 |
+
{
|
| 7745 |
+
"epoch": 4.322732626619552,
|
| 7746 |
+
"grad_norm": 0.0410366915166378,
|
| 7747 |
+
"learning_rate": 1.5818985574685903e-05,
|
| 7748 |
+
"loss": 0.0101,
|
| 7749 |
+
"step": 11010
|
| 7750 |
+
},
|
| 7751 |
+
{
|
| 7752 |
+
"epoch": 4.326658814291323,
|
| 7753 |
+
"grad_norm": 7.144087314605713,
|
| 7754 |
+
"learning_rate": 1.581316891577478e-05,
|
| 7755 |
+
"loss": 0.0235,
|
| 7756 |
+
"step": 11020
|
| 7757 |
+
},
|
| 7758 |
+
{
|
| 7759 |
+
"epoch": 4.330585001963094,
|
| 7760 |
+
"grad_norm": 0.3121587932109833,
|
| 7761 |
+
"learning_rate": 1.580735225686366e-05,
|
| 7762 |
+
"loss": 0.0052,
|
| 7763 |
+
"step": 11030
|
| 7764 |
+
},
|
| 7765 |
+
{
|
| 7766 |
+
"epoch": 4.334511189634864,
|
| 7767 |
+
"grad_norm": 0.13531596958637238,
|
| 7768 |
+
"learning_rate": 1.5801535597952538e-05,
|
| 7769 |
+
"loss": 0.0043,
|
| 7770 |
+
"step": 11040
|
| 7771 |
+
},
|
| 7772 |
+
{
|
| 7773 |
+
"epoch": 4.338437377306636,
|
| 7774 |
+
"grad_norm": 0.12413951754570007,
|
| 7775 |
+
"learning_rate": 1.5795718939041414e-05,
|
| 7776 |
+
"loss": 0.0499,
|
| 7777 |
+
"step": 11050
|
| 7778 |
+
},
|
| 7779 |
+
{
|
| 7780 |
+
"epoch": 4.342363564978406,
|
| 7781 |
+
"grad_norm": 0.08380908519029617,
|
| 7782 |
+
"learning_rate": 1.5789902280130294e-05,
|
| 7783 |
+
"loss": 0.0081,
|
| 7784 |
+
"step": 11060
|
| 7785 |
+
},
|
| 7786 |
+
{
|
| 7787 |
+
"epoch": 4.3462897526501765,
|
| 7788 |
+
"grad_norm": 0.10234778374433517,
|
| 7789 |
+
"learning_rate": 1.5784085621219174e-05,
|
| 7790 |
+
"loss": 0.014,
|
| 7791 |
+
"step": 11070
|
| 7792 |
+
},
|
| 7793 |
+
{
|
| 7794 |
+
"epoch": 4.350215940321948,
|
| 7795 |
+
"grad_norm": 10.324699401855469,
|
| 7796 |
+
"learning_rate": 1.5778268962308053e-05,
|
| 7797 |
+
"loss": 0.0682,
|
| 7798 |
+
"step": 11080
|
| 7799 |
+
},
|
| 7800 |
+
{
|
| 7801 |
+
"epoch": 4.354142127993718,
|
| 7802 |
+
"grad_norm": 1.0202091932296753,
|
| 7803 |
+
"learning_rate": 1.577245230339693e-05,
|
| 7804 |
+
"loss": 0.0038,
|
| 7805 |
+
"step": 11090
|
| 7806 |
+
},
|
| 7807 |
+
{
|
| 7808 |
+
"epoch": 4.358068315665489,
|
| 7809 |
+
"grad_norm": 0.794123113155365,
|
| 7810 |
+
"learning_rate": 1.576663564448581e-05,
|
| 7811 |
+
"loss": 0.0237,
|
| 7812 |
+
"step": 11100
|
| 7813 |
+
},
|
| 7814 |
+
{
|
| 7815 |
+
"epoch": 4.361994503337259,
|
| 7816 |
+
"grad_norm": 1.1392648220062256,
|
| 7817 |
+
"learning_rate": 1.5760818985574685e-05,
|
| 7818 |
+
"loss": 0.017,
|
| 7819 |
+
"step": 11110
|
| 7820 |
+
},
|
| 7821 |
+
{
|
| 7822 |
+
"epoch": 4.3659206910090305,
|
| 7823 |
+
"grad_norm": 0.05079807713627815,
|
| 7824 |
+
"learning_rate": 1.5755002326663565e-05,
|
| 7825 |
+
"loss": 0.0074,
|
| 7826 |
+
"step": 11120
|
| 7827 |
+
},
|
| 7828 |
+
{
|
| 7829 |
+
"epoch": 4.369846878680801,
|
| 7830 |
+
"grad_norm": 0.011696847155690193,
|
| 7831 |
+
"learning_rate": 1.5749185667752444e-05,
|
| 7832 |
+
"loss": 0.0112,
|
| 7833 |
+
"step": 11130
|
| 7834 |
+
},
|
| 7835 |
+
{
|
| 7836 |
+
"epoch": 4.373773066352571,
|
| 7837 |
+
"grad_norm": 0.5746485590934753,
|
| 7838 |
+
"learning_rate": 1.5743369008841324e-05,
|
| 7839 |
+
"loss": 0.0134,
|
| 7840 |
+
"step": 11140
|
| 7841 |
+
},
|
| 7842 |
+
{
|
| 7843 |
+
"epoch": 4.377699254024343,
|
| 7844 |
+
"grad_norm": 0.19490380585193634,
|
| 7845 |
+
"learning_rate": 1.57375523499302e-05,
|
| 7846 |
+
"loss": 0.1024,
|
| 7847 |
+
"step": 11150
|
| 7848 |
+
},
|
| 7849 |
+
{
|
| 7850 |
+
"epoch": 4.381625441696113,
|
| 7851 |
+
"grad_norm": 0.05230716988444328,
|
| 7852 |
+
"learning_rate": 1.573173569101908e-05,
|
| 7853 |
+
"loss": 0.0084,
|
| 7854 |
+
"step": 11160
|
| 7855 |
+
},
|
| 7856 |
+
{
|
| 7857 |
+
"epoch": 4.385551629367884,
|
| 7858 |
+
"grad_norm": 0.12956352531909943,
|
| 7859 |
+
"learning_rate": 1.572591903210796e-05,
|
| 7860 |
+
"loss": 0.0028,
|
| 7861 |
+
"step": 11170
|
| 7862 |
+
},
|
| 7863 |
+
{
|
| 7864 |
+
"epoch": 4.389477817039655,
|
| 7865 |
+
"grad_norm": 0.047844670712947845,
|
| 7866 |
+
"learning_rate": 1.5720102373196836e-05,
|
| 7867 |
+
"loss": 0.0035,
|
| 7868 |
+
"step": 11180
|
| 7869 |
+
},
|
| 7870 |
+
{
|
| 7871 |
+
"epoch": 4.393404004711425,
|
| 7872 |
+
"grad_norm": 1.61209237575531,
|
| 7873 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 7874 |
+
"loss": 0.0657,
|
| 7875 |
+
"step": 11190
|
| 7876 |
+
},
|
| 7877 |
+
{
|
| 7878 |
+
"epoch": 4.397330192383196,
|
| 7879 |
+
"grad_norm": 0.16978521645069122,
|
| 7880 |
+
"learning_rate": 1.5708469055374595e-05,
|
| 7881 |
+
"loss": 0.007,
|
| 7882 |
+
"step": 11200
|
| 7883 |
+
},
|
| 7884 |
+
{
|
| 7885 |
+
"epoch": 4.401256380054966,
|
| 7886 |
+
"grad_norm": 0.017411168664693832,
|
| 7887 |
+
"learning_rate": 1.5702652396463475e-05,
|
| 7888 |
+
"loss": 0.0032,
|
| 7889 |
+
"step": 11210
|
| 7890 |
+
},
|
| 7891 |
+
{
|
| 7892 |
+
"epoch": 4.4051825677267376,
|
| 7893 |
+
"grad_norm": 0.5619922876358032,
|
| 7894 |
+
"learning_rate": 1.569683573755235e-05,
|
| 7895 |
+
"loss": 0.014,
|
| 7896 |
+
"step": 11220
|
| 7897 |
+
},
|
| 7898 |
+
{
|
| 7899 |
+
"epoch": 4.409108755398508,
|
| 7900 |
+
"grad_norm": 0.01849539391696453,
|
| 7901 |
+
"learning_rate": 1.569101907864123e-05,
|
| 7902 |
+
"loss": 0.0135,
|
| 7903 |
+
"step": 11230
|
| 7904 |
+
},
|
| 7905 |
+
{
|
| 7906 |
+
"epoch": 4.413034943070278,
|
| 7907 |
+
"grad_norm": 0.07227998226881027,
|
| 7908 |
+
"learning_rate": 1.5685202419730107e-05,
|
| 7909 |
+
"loss": 0.0033,
|
| 7910 |
+
"step": 11240
|
| 7911 |
+
},
|
| 7912 |
+
{
|
| 7913 |
+
"epoch": 4.41696113074205,
|
| 7914 |
+
"grad_norm": 0.07125813513994217,
|
| 7915 |
+
"learning_rate": 1.5679385760818986e-05,
|
| 7916 |
+
"loss": 0.0045,
|
| 7917 |
+
"step": 11250
|
| 7918 |
+
},
|
| 7919 |
+
{
|
| 7920 |
+
"epoch": 4.42088731841382,
|
| 7921 |
+
"grad_norm": 1.4216877222061157,
|
| 7922 |
+
"learning_rate": 1.5673569101907866e-05,
|
| 7923 |
+
"loss": 0.0267,
|
| 7924 |
+
"step": 11260
|
| 7925 |
+
},
|
| 7926 |
+
{
|
| 7927 |
+
"epoch": 4.424813506085591,
|
| 7928 |
+
"grad_norm": 0.22042542695999146,
|
| 7929 |
+
"learning_rate": 1.5667752442996745e-05,
|
| 7930 |
+
"loss": 0.0035,
|
| 7931 |
+
"step": 11270
|
| 7932 |
+
},
|
| 7933 |
+
{
|
| 7934 |
+
"epoch": 4.428739693757362,
|
| 7935 |
+
"grad_norm": 0.028004225343465805,
|
| 7936 |
+
"learning_rate": 1.566193578408562e-05,
|
| 7937 |
+
"loss": 0.0041,
|
| 7938 |
+
"step": 11280
|
| 7939 |
+
},
|
| 7940 |
+
{
|
| 7941 |
+
"epoch": 4.432665881429132,
|
| 7942 |
+
"grad_norm": 0.458158403635025,
|
| 7943 |
+
"learning_rate": 1.56561191251745e-05,
|
| 7944 |
+
"loss": 0.1524,
|
| 7945 |
+
"step": 11290
|
| 7946 |
+
},
|
| 7947 |
+
{
|
| 7948 |
+
"epoch": 4.436592069100903,
|
| 7949 |
+
"grad_norm": 0.04216272383928299,
|
| 7950 |
+
"learning_rate": 1.565030246626338e-05,
|
| 7951 |
+
"loss": 0.0393,
|
| 7952 |
+
"step": 11300
|
| 7953 |
+
},
|
| 7954 |
+
{
|
| 7955 |
+
"epoch": 4.440518256772673,
|
| 7956 |
+
"grad_norm": 0.11112450063228607,
|
| 7957 |
+
"learning_rate": 1.564448580735226e-05,
|
| 7958 |
+
"loss": 0.0152,
|
| 7959 |
+
"step": 11310
|
| 7960 |
+
},
|
| 7961 |
+
{
|
| 7962 |
+
"epoch": 4.444444444444445,
|
| 7963 |
+
"grad_norm": 0.08090470731258392,
|
| 7964 |
+
"learning_rate": 1.5638669148441137e-05,
|
| 7965 |
+
"loss": 0.1268,
|
| 7966 |
+
"step": 11320
|
| 7967 |
+
},
|
| 7968 |
+
{
|
| 7969 |
+
"epoch": 4.448370632116215,
|
| 7970 |
+
"grad_norm": 0.06384973227977753,
|
| 7971 |
+
"learning_rate": 1.5632852489530016e-05,
|
| 7972 |
+
"loss": 0.0104,
|
| 7973 |
+
"step": 11330
|
| 7974 |
+
},
|
| 7975 |
+
{
|
| 7976 |
+
"epoch": 4.4522968197879855,
|
| 7977 |
+
"grad_norm": 0.001733550219796598,
|
| 7978 |
+
"learning_rate": 1.5627035830618892e-05,
|
| 7979 |
+
"loss": 0.0027,
|
| 7980 |
+
"step": 11340
|
| 7981 |
+
},
|
| 7982 |
+
{
|
| 7983 |
+
"epoch": 4.456223007459757,
|
| 7984 |
+
"grad_norm": 0.08710963279008865,
|
| 7985 |
+
"learning_rate": 1.5621219171707772e-05,
|
| 7986 |
+
"loss": 0.0032,
|
| 7987 |
+
"step": 11350
|
| 7988 |
+
},
|
| 7989 |
+
{
|
| 7990 |
+
"epoch": 4.460149195131527,
|
| 7991 |
+
"grad_norm": 12.456275939941406,
|
| 7992 |
+
"learning_rate": 1.561540251279665e-05,
|
| 7993 |
+
"loss": 0.0809,
|
| 7994 |
+
"step": 11360
|
| 7995 |
+
},
|
| 7996 |
+
{
|
| 7997 |
+
"epoch": 4.464075382803298,
|
| 7998 |
+
"grad_norm": 0.07640429586172104,
|
| 7999 |
+
"learning_rate": 1.5609585853885528e-05,
|
| 8000 |
+
"loss": 0.0034,
|
| 8001 |
+
"step": 11370
|
| 8002 |
+
},
|
| 8003 |
+
{
|
| 8004 |
+
"epoch": 4.468001570475069,
|
| 8005 |
+
"grad_norm": 0.005106847733259201,
|
| 8006 |
+
"learning_rate": 1.5603769194974407e-05,
|
| 8007 |
+
"loss": 0.0072,
|
| 8008 |
+
"step": 11380
|
| 8009 |
+
},
|
| 8010 |
+
{
|
| 8011 |
+
"epoch": 4.4719277581468395,
|
| 8012 |
+
"grad_norm": 5.56498908996582,
|
| 8013 |
+
"learning_rate": 1.5597952536063287e-05,
|
| 8014 |
+
"loss": 0.0083,
|
| 8015 |
+
"step": 11390
|
| 8016 |
+
},
|
| 8017 |
+
{
|
| 8018 |
+
"epoch": 4.47585394581861,
|
| 8019 |
+
"grad_norm": 0.08046433329582214,
|
| 8020 |
+
"learning_rate": 1.5592135877152167e-05,
|
| 8021 |
+
"loss": 0.015,
|
| 8022 |
+
"step": 11400
|
| 8023 |
+
},
|
| 8024 |
+
{
|
| 8025 |
+
"epoch": 4.479780133490381,
|
| 8026 |
+
"grad_norm": 0.04846687242388725,
|
| 8027 |
+
"learning_rate": 1.5586319218241043e-05,
|
| 8028 |
+
"loss": 0.0699,
|
| 8029 |
+
"step": 11410
|
| 8030 |
+
},
|
| 8031 |
+
{
|
| 8032 |
+
"epoch": 4.483706321162152,
|
| 8033 |
+
"grad_norm": 1.5786051750183105,
|
| 8034 |
+
"learning_rate": 1.5580502559329923e-05,
|
| 8035 |
+
"loss": 0.0098,
|
| 8036 |
+
"step": 11420
|
| 8037 |
+
},
|
| 8038 |
+
{
|
| 8039 |
+
"epoch": 4.487632508833922,
|
| 8040 |
+
"grad_norm": 13.047212600708008,
|
| 8041 |
+
"learning_rate": 1.55746859004188e-05,
|
| 8042 |
+
"loss": 0.0127,
|
| 8043 |
+
"step": 11430
|
| 8044 |
+
},
|
| 8045 |
+
{
|
| 8046 |
+
"epoch": 4.491558696505693,
|
| 8047 |
+
"grad_norm": 0.4843318462371826,
|
| 8048 |
+
"learning_rate": 1.5568869241507682e-05,
|
| 8049 |
+
"loss": 0.0132,
|
| 8050 |
+
"step": 11440
|
| 8051 |
+
},
|
| 8052 |
+
{
|
| 8053 |
+
"epoch": 4.495484884177464,
|
| 8054 |
+
"grad_norm": 3.5573298931121826,
|
| 8055 |
+
"learning_rate": 1.5563052582596558e-05,
|
| 8056 |
+
"loss": 0.0441,
|
| 8057 |
+
"step": 11450
|
| 8058 |
+
},
|
| 8059 |
+
{
|
| 8060 |
+
"epoch": 4.499411071849234,
|
| 8061 |
+
"grad_norm": 0.06063020974397659,
|
| 8062 |
+
"learning_rate": 1.5557235923685438e-05,
|
| 8063 |
+
"loss": 0.0222,
|
| 8064 |
+
"step": 11460
|
| 8065 |
+
},
|
| 8066 |
+
{
|
| 8067 |
+
"epoch": 4.503337259521005,
|
| 8068 |
+
"grad_norm": 0.5302808284759521,
|
| 8069 |
+
"learning_rate": 1.5551419264774314e-05,
|
| 8070 |
+
"loss": 0.0428,
|
| 8071 |
+
"step": 11470
|
| 8072 |
+
},
|
| 8073 |
+
{
|
| 8074 |
+
"epoch": 4.507263447192776,
|
| 8075 |
+
"grad_norm": 0.308036744594574,
|
| 8076 |
+
"learning_rate": 1.5545602605863193e-05,
|
| 8077 |
+
"loss": 0.0169,
|
| 8078 |
+
"step": 11480
|
| 8079 |
+
},
|
| 8080 |
+
{
|
| 8081 |
+
"epoch": 4.511189634864547,
|
| 8082 |
+
"grad_norm": 0.36352574825286865,
|
| 8083 |
+
"learning_rate": 1.5539785946952073e-05,
|
| 8084 |
+
"loss": 0.041,
|
| 8085 |
+
"step": 11490
|
| 8086 |
+
},
|
| 8087 |
+
{
|
| 8088 |
+
"epoch": 4.515115822536317,
|
| 8089 |
+
"grad_norm": 0.6225147247314453,
|
| 8090 |
+
"learning_rate": 1.5533969288040953e-05,
|
| 8091 |
+
"loss": 0.015,
|
| 8092 |
+
"step": 11500
|
| 8093 |
+
},
|
| 8094 |
+
{
|
| 8095 |
+
"epoch": 4.5190420102080875,
|
| 8096 |
+
"grad_norm": 0.12292739003896713,
|
| 8097 |
+
"learning_rate": 1.552815262912983e-05,
|
| 8098 |
+
"loss": 0.0138,
|
| 8099 |
+
"step": 11510
|
| 8100 |
+
},
|
| 8101 |
+
{
|
| 8102 |
+
"epoch": 4.522968197879859,
|
| 8103 |
+
"grad_norm": 0.020481614395976067,
|
| 8104 |
+
"learning_rate": 1.552233597021871e-05,
|
| 8105 |
+
"loss": 0.1001,
|
| 8106 |
+
"step": 11520
|
| 8107 |
+
},
|
| 8108 |
+
{
|
| 8109 |
+
"epoch": 4.526894385551629,
|
| 8110 |
+
"grad_norm": 0.07435489445924759,
|
| 8111 |
+
"learning_rate": 1.5516519311307585e-05,
|
| 8112 |
+
"loss": 0.0785,
|
| 8113 |
+
"step": 11530
|
| 8114 |
+
},
|
| 8115 |
+
{
|
| 8116 |
+
"epoch": 4.5308205732234,
|
| 8117 |
+
"grad_norm": 0.06456819921731949,
|
| 8118 |
+
"learning_rate": 1.5510702652396464e-05,
|
| 8119 |
+
"loss": 0.0045,
|
| 8120 |
+
"step": 11540
|
| 8121 |
+
},
|
| 8122 |
+
{
|
| 8123 |
+
"epoch": 4.534746760895171,
|
| 8124 |
+
"grad_norm": 0.03821583092212677,
|
| 8125 |
+
"learning_rate": 1.5504885993485344e-05,
|
| 8126 |
+
"loss": 0.0114,
|
| 8127 |
+
"step": 11550
|
| 8128 |
+
},
|
| 8129 |
+
{
|
| 8130 |
+
"epoch": 4.5386729485669415,
|
| 8131 |
+
"grad_norm": 0.049177899956703186,
|
| 8132 |
+
"learning_rate": 1.549906933457422e-05,
|
| 8133 |
+
"loss": 0.0089,
|
| 8134 |
+
"step": 11560
|
| 8135 |
+
},
|
| 8136 |
+
{
|
| 8137 |
+
"epoch": 4.542599136238712,
|
| 8138 |
+
"grad_norm": 0.4933866560459137,
|
| 8139 |
+
"learning_rate": 1.54932526756631e-05,
|
| 8140 |
+
"loss": 0.0215,
|
| 8141 |
+
"step": 11570
|
| 8142 |
+
},
|
| 8143 |
+
{
|
| 8144 |
+
"epoch": 4.546525323910483,
|
| 8145 |
+
"grad_norm": 0.39573410153388977,
|
| 8146 |
+
"learning_rate": 1.548743601675198e-05,
|
| 8147 |
+
"loss": 0.0384,
|
| 8148 |
+
"step": 11580
|
| 8149 |
+
},
|
| 8150 |
+
{
|
| 8151 |
+
"epoch": 4.550451511582254,
|
| 8152 |
+
"grad_norm": 0.2475963681936264,
|
| 8153 |
+
"learning_rate": 1.548161935784086e-05,
|
| 8154 |
+
"loss": 0.0619,
|
| 8155 |
+
"step": 11590
|
| 8156 |
+
},
|
| 8157 |
+
{
|
| 8158 |
+
"epoch": 4.554377699254024,
|
| 8159 |
+
"grad_norm": 1.9321954250335693,
|
| 8160 |
+
"learning_rate": 1.5475802698929735e-05,
|
| 8161 |
+
"loss": 0.0102,
|
| 8162 |
+
"step": 11600
|
| 8163 |
+
},
|
| 8164 |
+
{
|
| 8165 |
+
"epoch": 4.5583038869257955,
|
| 8166 |
+
"grad_norm": 0.04566175118088722,
|
| 8167 |
+
"learning_rate": 1.5469986040018615e-05,
|
| 8168 |
+
"loss": 0.0236,
|
| 8169 |
+
"step": 11610
|
| 8170 |
+
},
|
| 8171 |
+
{
|
| 8172 |
+
"epoch": 4.562230074597566,
|
| 8173 |
+
"grad_norm": 1.440490484237671,
|
| 8174 |
+
"learning_rate": 1.546416938110749e-05,
|
| 8175 |
+
"loss": 0.1341,
|
| 8176 |
+
"step": 11620
|
| 8177 |
+
},
|
| 8178 |
+
{
|
| 8179 |
+
"epoch": 4.566156262269336,
|
| 8180 |
+
"grad_norm": 0.025782562792301178,
|
| 8181 |
+
"learning_rate": 1.5458352722196374e-05,
|
| 8182 |
+
"loss": 0.0967,
|
| 8183 |
+
"step": 11630
|
| 8184 |
+
},
|
| 8185 |
+
{
|
| 8186 |
+
"epoch": 4.570082449941108,
|
| 8187 |
+
"grad_norm": 0.6532251834869385,
|
| 8188 |
+
"learning_rate": 1.545253606328525e-05,
|
| 8189 |
+
"loss": 0.0135,
|
| 8190 |
+
"step": 11640
|
| 8191 |
+
},
|
| 8192 |
+
{
|
| 8193 |
+
"epoch": 4.574008637612878,
|
| 8194 |
+
"grad_norm": 0.47374337911605835,
|
| 8195 |
+
"learning_rate": 1.544671940437413e-05,
|
| 8196 |
+
"loss": 0.0861,
|
| 8197 |
+
"step": 11650
|
| 8198 |
+
},
|
| 8199 |
+
{
|
| 8200 |
+
"epoch": 4.577934825284649,
|
| 8201 |
+
"grad_norm": 0.13000331819057465,
|
| 8202 |
+
"learning_rate": 1.5440902745463006e-05,
|
| 8203 |
+
"loss": 0.0955,
|
| 8204 |
+
"step": 11660
|
| 8205 |
+
},
|
| 8206 |
+
{
|
| 8207 |
+
"epoch": 4.581861012956419,
|
| 8208 |
+
"grad_norm": 0.06118248775601387,
|
| 8209 |
+
"learning_rate": 1.5435086086551886e-05,
|
| 8210 |
+
"loss": 0.0049,
|
| 8211 |
+
"step": 11670
|
| 8212 |
+
},
|
| 8213 |
+
{
|
| 8214 |
+
"epoch": 4.58578720062819,
|
| 8215 |
+
"grad_norm": 0.14873720705509186,
|
| 8216 |
+
"learning_rate": 1.5429269427640765e-05,
|
| 8217 |
+
"loss": 0.1093,
|
| 8218 |
+
"step": 11680
|
| 8219 |
+
},
|
| 8220 |
+
{
|
| 8221 |
+
"epoch": 4.589713388299961,
|
| 8222 |
+
"grad_norm": 0.085589699447155,
|
| 8223 |
+
"learning_rate": 1.5423452768729645e-05,
|
| 8224 |
+
"loss": 0.1624,
|
| 8225 |
+
"step": 11690
|
| 8226 |
+
},
|
| 8227 |
+
{
|
| 8228 |
+
"epoch": 4.593639575971731,
|
| 8229 |
+
"grad_norm": 0.09361565113067627,
|
| 8230 |
+
"learning_rate": 1.541763610981852e-05,
|
| 8231 |
+
"loss": 0.0065,
|
| 8232 |
+
"step": 11700
|
| 8233 |
+
},
|
| 8234 |
+
{
|
| 8235 |
+
"epoch": 4.597565763643502,
|
| 8236 |
+
"grad_norm": 1.138765811920166,
|
| 8237 |
+
"learning_rate": 1.54118194509074e-05,
|
| 8238 |
+
"loss": 0.0115,
|
| 8239 |
+
"step": 11710
|
| 8240 |
+
},
|
| 8241 |
+
{
|
| 8242 |
+
"epoch": 4.601491951315273,
|
| 8243 |
+
"grad_norm": 0.021475637331604958,
|
| 8244 |
+
"learning_rate": 1.540600279199628e-05,
|
| 8245 |
+
"loss": 0.0089,
|
| 8246 |
+
"step": 11720
|
| 8247 |
+
},
|
| 8248 |
+
{
|
| 8249 |
+
"epoch": 4.605418138987043,
|
| 8250 |
+
"grad_norm": 0.19915173947811127,
|
| 8251 |
+
"learning_rate": 1.5400186133085156e-05,
|
| 8252 |
+
"loss": 0.0336,
|
| 8253 |
+
"step": 11730
|
| 8254 |
+
},
|
| 8255 |
+
{
|
| 8256 |
+
"epoch": 4.609344326658814,
|
| 8257 |
+
"grad_norm": 0.14634615182876587,
|
| 8258 |
+
"learning_rate": 1.5394369474174036e-05,
|
| 8259 |
+
"loss": 0.0371,
|
| 8260 |
+
"step": 11740
|
| 8261 |
+
},
|
| 8262 |
+
{
|
| 8263 |
+
"epoch": 4.613270514330585,
|
| 8264 |
+
"grad_norm": 0.0471196211874485,
|
| 8265 |
+
"learning_rate": 1.5388552815262912e-05,
|
| 8266 |
+
"loss": 0.0339,
|
| 8267 |
+
"step": 11750
|
| 8268 |
+
},
|
| 8269 |
+
{
|
| 8270 |
+
"epoch": 4.617196702002356,
|
| 8271 |
+
"grad_norm": 0.062157005071640015,
|
| 8272 |
+
"learning_rate": 1.5382736156351792e-05,
|
| 8273 |
+
"loss": 0.015,
|
| 8274 |
+
"step": 11760
|
| 8275 |
+
},
|
| 8276 |
+
{
|
| 8277 |
+
"epoch": 4.621122889674126,
|
| 8278 |
+
"grad_norm": 0.43638792634010315,
|
| 8279 |
+
"learning_rate": 1.537691949744067e-05,
|
| 8280 |
+
"loss": 0.0089,
|
| 8281 |
+
"step": 11770
|
| 8282 |
+
},
|
| 8283 |
+
{
|
| 8284 |
+
"epoch": 4.625049077345897,
|
| 8285 |
+
"grad_norm": 1.371751308441162,
|
| 8286 |
+
"learning_rate": 1.537110283852955e-05,
|
| 8287 |
+
"loss": 0.0324,
|
| 8288 |
+
"step": 11780
|
| 8289 |
+
},
|
| 8290 |
+
{
|
| 8291 |
+
"epoch": 4.628975265017668,
|
| 8292 |
+
"grad_norm": 0.00786020141094923,
|
| 8293 |
+
"learning_rate": 1.5365286179618427e-05,
|
| 8294 |
+
"loss": 0.0057,
|
| 8295 |
+
"step": 11790
|
| 8296 |
+
},
|
| 8297 |
+
{
|
| 8298 |
+
"epoch": 4.632901452689438,
|
| 8299 |
+
"grad_norm": 13.441558837890625,
|
| 8300 |
+
"learning_rate": 1.5359469520707307e-05,
|
| 8301 |
+
"loss": 0.0128,
|
| 8302 |
+
"step": 11800
|
| 8303 |
+
},
|
| 8304 |
+
{
|
| 8305 |
+
"epoch": 4.63682764036121,
|
| 8306 |
+
"grad_norm": 0.0014243257464841008,
|
| 8307 |
+
"learning_rate": 1.5353652861796186e-05,
|
| 8308 |
+
"loss": 0.0468,
|
| 8309 |
+
"step": 11810
|
| 8310 |
+
},
|
| 8311 |
+
{
|
| 8312 |
+
"epoch": 4.64075382803298,
|
| 8313 |
+
"grad_norm": 0.039208512753248215,
|
| 8314 |
+
"learning_rate": 1.5347836202885066e-05,
|
| 8315 |
+
"loss": 0.0082,
|
| 8316 |
+
"step": 11820
|
| 8317 |
+
},
|
| 8318 |
+
{
|
| 8319 |
+
"epoch": 4.6446800157047505,
|
| 8320 |
+
"grad_norm": 0.06675128638744354,
|
| 8321 |
+
"learning_rate": 1.5342019543973942e-05,
|
| 8322 |
+
"loss": 0.0044,
|
| 8323 |
+
"step": 11830
|
| 8324 |
+
},
|
| 8325 |
+
{
|
| 8326 |
+
"epoch": 4.648606203376522,
|
| 8327 |
+
"grad_norm": 0.020232301205396652,
|
| 8328 |
+
"learning_rate": 1.5336202885062822e-05,
|
| 8329 |
+
"loss": 0.0126,
|
| 8330 |
+
"step": 11840
|
| 8331 |
+
},
|
| 8332 |
+
{
|
| 8333 |
+
"epoch": 4.652532391048292,
|
| 8334 |
+
"grad_norm": 0.01076700072735548,
|
| 8335 |
+
"learning_rate": 1.5330386226151698e-05,
|
| 8336 |
+
"loss": 0.0702,
|
| 8337 |
+
"step": 11850
|
| 8338 |
+
},
|
| 8339 |
+
{
|
| 8340 |
+
"epoch": 4.656458578720063,
|
| 8341 |
+
"grad_norm": 0.015694594010710716,
|
| 8342 |
+
"learning_rate": 1.5324569567240578e-05,
|
| 8343 |
+
"loss": 0.0067,
|
| 8344 |
+
"step": 11860
|
| 8345 |
+
},
|
| 8346 |
+
{
|
| 8347 |
+
"epoch": 4.660384766391833,
|
| 8348 |
+
"grad_norm": 0.00826133694499731,
|
| 8349 |
+
"learning_rate": 1.5318752908329457e-05,
|
| 8350 |
+
"loss": 0.0022,
|
| 8351 |
+
"step": 11870
|
| 8352 |
+
},
|
| 8353 |
+
{
|
| 8354 |
+
"epoch": 4.6643109540636045,
|
| 8355 |
+
"grad_norm": 0.02804211527109146,
|
| 8356 |
+
"learning_rate": 1.5312936249418337e-05,
|
| 8357 |
+
"loss": 0.0115,
|
| 8358 |
+
"step": 11880
|
| 8359 |
+
},
|
| 8360 |
+
{
|
| 8361 |
+
"epoch": 4.668237141735375,
|
| 8362 |
+
"grad_norm": 0.04526368901133537,
|
| 8363 |
+
"learning_rate": 1.5307119590507213e-05,
|
| 8364 |
+
"loss": 0.0043,
|
| 8365 |
+
"step": 11890
|
| 8366 |
+
},
|
| 8367 |
+
{
|
| 8368 |
+
"epoch": 4.672163329407145,
|
| 8369 |
+
"grad_norm": 0.05062778294086456,
|
| 8370 |
+
"learning_rate": 1.5301302931596093e-05,
|
| 8371 |
+
"loss": 0.0071,
|
| 8372 |
+
"step": 11900
|
| 8373 |
+
},
|
| 8374 |
+
{
|
| 8375 |
+
"epoch": 4.676089517078917,
|
| 8376 |
+
"grad_norm": 0.6552804708480835,
|
| 8377 |
+
"learning_rate": 1.5295486272684972e-05,
|
| 8378 |
+
"loss": 0.0071,
|
| 8379 |
+
"step": 11910
|
| 8380 |
+
},
|
| 8381 |
+
{
|
| 8382 |
+
"epoch": 4.680015704750687,
|
| 8383 |
+
"grad_norm": 0.040547601878643036,
|
| 8384 |
+
"learning_rate": 1.528966961377385e-05,
|
| 8385 |
+
"loss": 0.0078,
|
| 8386 |
+
"step": 11920
|
| 8387 |
+
},
|
| 8388 |
+
{
|
| 8389 |
+
"epoch": 4.683941892422458,
|
| 8390 |
+
"grad_norm": 0.9708958864212036,
|
| 8391 |
+
"learning_rate": 1.5283852954862728e-05,
|
| 8392 |
+
"loss": 0.0251,
|
| 8393 |
+
"step": 11930
|
| 8394 |
+
},
|
| 8395 |
+
{
|
| 8396 |
+
"epoch": 4.687868080094228,
|
| 8397 |
+
"grad_norm": 0.006763842422515154,
|
| 8398 |
+
"learning_rate": 1.5278036295951604e-05,
|
| 8399 |
+
"loss": 0.0161,
|
| 8400 |
+
"step": 11940
|
| 8401 |
+
},
|
| 8402 |
+
{
|
| 8403 |
+
"epoch": 4.691794267765999,
|
| 8404 |
+
"grad_norm": 0.020528485998511314,
|
| 8405 |
+
"learning_rate": 1.5272219637040487e-05,
|
| 8406 |
+
"loss": 0.0307,
|
| 8407 |
+
"step": 11950
|
| 8408 |
+
},
|
| 8409 |
+
{
|
| 8410 |
+
"epoch": 4.69572045543777,
|
| 8411 |
+
"grad_norm": 0.525425910949707,
|
| 8412 |
+
"learning_rate": 1.5266402978129364e-05,
|
| 8413 |
+
"loss": 0.0091,
|
| 8414 |
+
"step": 11960
|
| 8415 |
+
},
|
| 8416 |
+
{
|
| 8417 |
+
"epoch": 4.69964664310954,
|
| 8418 |
+
"grad_norm": 0.03158989176154137,
|
| 8419 |
+
"learning_rate": 1.5260586319218243e-05,
|
| 8420 |
+
"loss": 0.0276,
|
| 8421 |
+
"step": 11970
|
| 8422 |
+
},
|
| 8423 |
+
{
|
| 8424 |
+
"epoch": 4.703572830781312,
|
| 8425 |
+
"grad_norm": 1.334675669670105,
|
| 8426 |
+
"learning_rate": 1.5254769660307121e-05,
|
| 8427 |
+
"loss": 0.0081,
|
| 8428 |
+
"step": 11980
|
| 8429 |
+
},
|
| 8430 |
+
{
|
| 8431 |
+
"epoch": 4.707499018453082,
|
| 8432 |
+
"grad_norm": 0.0012855808017775416,
|
| 8433 |
+
"learning_rate": 1.5248953001395999e-05,
|
| 8434 |
+
"loss": 0.0186,
|
| 8435 |
+
"step": 11990
|
| 8436 |
+
},
|
| 8437 |
+
{
|
| 8438 |
+
"epoch": 4.7114252061248525,
|
| 8439 |
+
"grad_norm": 1.067096471786499,
|
| 8440 |
+
"learning_rate": 1.5243136342484879e-05,
|
| 8441 |
+
"loss": 0.0297,
|
| 8442 |
+
"step": 12000
|
| 8443 |
+
},
|
| 8444 |
+
{
|
| 8445 |
+
"epoch": 4.715351393796624,
|
| 8446 |
+
"grad_norm": 0.03623766452074051,
|
| 8447 |
+
"learning_rate": 1.5237319683573757e-05,
|
| 8448 |
+
"loss": 0.0054,
|
| 8449 |
+
"step": 12010
|
| 8450 |
+
},
|
| 8451 |
+
{
|
| 8452 |
+
"epoch": 4.719277581468394,
|
| 8453 |
+
"grad_norm": 0.34463736414909363,
|
| 8454 |
+
"learning_rate": 1.5231503024662634e-05,
|
| 8455 |
+
"loss": 0.0305,
|
| 8456 |
+
"step": 12020
|
| 8457 |
+
},
|
| 8458 |
+
{
|
| 8459 |
+
"epoch": 4.723203769140165,
|
| 8460 |
+
"grad_norm": 0.09803997725248337,
|
| 8461 |
+
"learning_rate": 1.5225686365751512e-05,
|
| 8462 |
+
"loss": 0.0078,
|
| 8463 |
+
"step": 12030
|
| 8464 |
+
},
|
| 8465 |
+
{
|
| 8466 |
+
"epoch": 4.727129956811936,
|
| 8467 |
+
"grad_norm": 0.004908048547804356,
|
| 8468 |
+
"learning_rate": 1.521986970684039e-05,
|
| 8469 |
+
"loss": 0.0069,
|
| 8470 |
+
"step": 12040
|
| 8471 |
+
},
|
| 8472 |
+
{
|
| 8473 |
+
"epoch": 4.7310561444837065,
|
| 8474 |
+
"grad_norm": 0.43726402521133423,
|
| 8475 |
+
"learning_rate": 1.5214053047929272e-05,
|
| 8476 |
+
"loss": 0.3352,
|
| 8477 |
+
"step": 12050
|
| 8478 |
+
},
|
| 8479 |
+
{
|
| 8480 |
+
"epoch": 4.734982332155477,
|
| 8481 |
+
"grad_norm": 0.004280575085431337,
|
| 8482 |
+
"learning_rate": 1.520823638901815e-05,
|
| 8483 |
+
"loss": 0.0325,
|
| 8484 |
+
"step": 12060
|
| 8485 |
+
},
|
| 8486 |
+
{
|
| 8487 |
+
"epoch": 4.738908519827247,
|
| 8488 |
+
"grad_norm": 0.29638102650642395,
|
| 8489 |
+
"learning_rate": 1.5202419730107027e-05,
|
| 8490 |
+
"loss": 0.0079,
|
| 8491 |
+
"step": 12070
|
| 8492 |
+
},
|
| 8493 |
+
{
|
| 8494 |
+
"epoch": 4.742834707499019,
|
| 8495 |
+
"grad_norm": 1.0755102634429932,
|
| 8496 |
+
"learning_rate": 1.5196603071195905e-05,
|
| 8497 |
+
"loss": 0.011,
|
| 8498 |
+
"step": 12080
|
| 8499 |
+
},
|
| 8500 |
+
{
|
| 8501 |
+
"epoch": 4.746760895170789,
|
| 8502 |
+
"grad_norm": 12.56951904296875,
|
| 8503 |
+
"learning_rate": 1.5190786412284787e-05,
|
| 8504 |
+
"loss": 0.0195,
|
| 8505 |
+
"step": 12090
|
| 8506 |
+
},
|
| 8507 |
+
{
|
| 8508 |
+
"epoch": 4.75068708284256,
|
| 8509 |
+
"grad_norm": 3.100621461868286,
|
| 8510 |
+
"learning_rate": 1.5184969753373665e-05,
|
| 8511 |
+
"loss": 0.0278,
|
| 8512 |
+
"step": 12100
|
| 8513 |
+
},
|
| 8514 |
+
{
|
| 8515 |
+
"epoch": 4.754613270514331,
|
| 8516 |
+
"grad_norm": 0.47880253195762634,
|
| 8517 |
+
"learning_rate": 1.5179153094462542e-05,
|
| 8518 |
+
"loss": 0.0146,
|
| 8519 |
+
"step": 12110
|
| 8520 |
+
},
|
| 8521 |
+
{
|
| 8522 |
+
"epoch": 4.758539458186101,
|
| 8523 |
+
"grad_norm": 0.6161695718765259,
|
| 8524 |
+
"learning_rate": 1.517333643555142e-05,
|
| 8525 |
+
"loss": 0.0095,
|
| 8526 |
+
"step": 12120
|
| 8527 |
+
},
|
| 8528 |
+
{
|
| 8529 |
+
"epoch": 4.762465645857872,
|
| 8530 |
+
"grad_norm": 0.12641766667366028,
|
| 8531 |
+
"learning_rate": 1.5167519776640298e-05,
|
| 8532 |
+
"loss": 0.0094,
|
| 8533 |
+
"step": 12130
|
| 8534 |
+
},
|
| 8535 |
+
{
|
| 8536 |
+
"epoch": 4.766391833529642,
|
| 8537 |
+
"grad_norm": 0.4253664016723633,
|
| 8538 |
+
"learning_rate": 1.5161703117729178e-05,
|
| 8539 |
+
"loss": 0.0193,
|
| 8540 |
+
"step": 12140
|
| 8541 |
+
},
|
| 8542 |
+
{
|
| 8543 |
+
"epoch": 4.770318021201414,
|
| 8544 |
+
"grad_norm": 0.05081826075911522,
|
| 8545 |
+
"learning_rate": 1.5155886458818056e-05,
|
| 8546 |
+
"loss": 0.0063,
|
| 8547 |
+
"step": 12150
|
| 8548 |
+
},
|
| 8549 |
+
{
|
| 8550 |
+
"epoch": 4.774244208873184,
|
| 8551 |
+
"grad_norm": 0.0076652648858726025,
|
| 8552 |
+
"learning_rate": 1.5150069799906935e-05,
|
| 8553 |
+
"loss": 0.0059,
|
| 8554 |
+
"step": 12160
|
| 8555 |
+
},
|
| 8556 |
+
{
|
| 8557 |
+
"epoch": 4.7781703965449545,
|
| 8558 |
+
"grad_norm": 0.1754598319530487,
|
| 8559 |
+
"learning_rate": 1.5144253140995813e-05,
|
| 8560 |
+
"loss": 0.0043,
|
| 8561 |
+
"step": 12170
|
| 8562 |
+
},
|
| 8563 |
+
{
|
| 8564 |
+
"epoch": 4.782096584216726,
|
| 8565 |
+
"grad_norm": 0.9394005537033081,
|
| 8566 |
+
"learning_rate": 1.5138436482084691e-05,
|
| 8567 |
+
"loss": 0.0405,
|
| 8568 |
+
"step": 12180
|
| 8569 |
+
},
|
| 8570 |
+
{
|
| 8571 |
+
"epoch": 4.786022771888496,
|
| 8572 |
+
"grad_norm": 0.04205586761236191,
|
| 8573 |
+
"learning_rate": 1.513261982317357e-05,
|
| 8574 |
+
"loss": 0.0024,
|
| 8575 |
+
"step": 12190
|
| 8576 |
+
},
|
| 8577 |
+
{
|
| 8578 |
+
"epoch": 4.789948959560267,
|
| 8579 |
+
"grad_norm": 0.032274823635816574,
|
| 8580 |
+
"learning_rate": 1.5126803164262449e-05,
|
| 8581 |
+
"loss": 0.0259,
|
| 8582 |
+
"step": 12200
|
| 8583 |
+
},
|
| 8584 |
+
{
|
| 8585 |
+
"epoch": 4.793875147232038,
|
| 8586 |
+
"grad_norm": 0.4521788954734802,
|
| 8587 |
+
"learning_rate": 1.5120986505351327e-05,
|
| 8588 |
+
"loss": 0.0497,
|
| 8589 |
+
"step": 12210
|
| 8590 |
+
},
|
| 8591 |
+
{
|
| 8592 |
+
"epoch": 4.7978013349038084,
|
| 8593 |
+
"grad_norm": 0.04389417916536331,
|
| 8594 |
+
"learning_rate": 1.5115169846440205e-05,
|
| 8595 |
+
"loss": 0.0121,
|
| 8596 |
+
"step": 12220
|
| 8597 |
+
},
|
| 8598 |
+
{
|
| 8599 |
+
"epoch": 4.801727522575579,
|
| 8600 |
+
"grad_norm": 1.2509561777114868,
|
| 8601 |
+
"learning_rate": 1.5109353187529086e-05,
|
| 8602 |
+
"loss": 0.0191,
|
| 8603 |
+
"step": 12230
|
| 8604 |
+
},
|
| 8605 |
+
{
|
| 8606 |
+
"epoch": 4.80565371024735,
|
| 8607 |
+
"grad_norm": 0.95953369140625,
|
| 8608 |
+
"learning_rate": 1.5103536528617964e-05,
|
| 8609 |
+
"loss": 0.0052,
|
| 8610 |
+
"step": 12240
|
| 8611 |
+
},
|
| 8612 |
+
{
|
| 8613 |
+
"epoch": 4.809579897919121,
|
| 8614 |
+
"grad_norm": 0.04999528080224991,
|
| 8615 |
+
"learning_rate": 1.5097719869706842e-05,
|
| 8616 |
+
"loss": 0.0076,
|
| 8617 |
+
"step": 12250
|
| 8618 |
+
},
|
| 8619 |
+
{
|
| 8620 |
+
"epoch": 4.813506085590891,
|
| 8621 |
+
"grad_norm": 3.544628620147705,
|
| 8622 |
+
"learning_rate": 1.509190321079572e-05,
|
| 8623 |
+
"loss": 0.0319,
|
| 8624 |
+
"step": 12260
|
| 8625 |
+
},
|
| 8626 |
+
{
|
| 8627 |
+
"epoch": 4.817432273262662,
|
| 8628 |
+
"grad_norm": 0.30969640612602234,
|
| 8629 |
+
"learning_rate": 1.5086086551884597e-05,
|
| 8630 |
+
"loss": 0.0087,
|
| 8631 |
+
"step": 12270
|
| 8632 |
+
},
|
| 8633 |
+
{
|
| 8634 |
+
"epoch": 4.821358460934433,
|
| 8635 |
+
"grad_norm": 17.58157730102539,
|
| 8636 |
+
"learning_rate": 1.5080269892973479e-05,
|
| 8637 |
+
"loss": 0.0322,
|
| 8638 |
+
"step": 12280
|
| 8639 |
+
},
|
| 8640 |
+
{
|
| 8641 |
+
"epoch": 4.825284648606203,
|
| 8642 |
+
"grad_norm": 0.2542928457260132,
|
| 8643 |
+
"learning_rate": 1.5074453234062357e-05,
|
| 8644 |
+
"loss": 0.0106,
|
| 8645 |
+
"step": 12290
|
| 8646 |
+
},
|
| 8647 |
+
{
|
| 8648 |
+
"epoch": 4.829210836277974,
|
| 8649 |
+
"grad_norm": 0.04144106060266495,
|
| 8650 |
+
"learning_rate": 1.5068636575151235e-05,
|
| 8651 |
+
"loss": 0.0267,
|
| 8652 |
+
"step": 12300
|
| 8653 |
+
},
|
| 8654 |
+
{
|
| 8655 |
+
"epoch": 4.833137023949745,
|
| 8656 |
+
"grad_norm": 0.1945629119873047,
|
| 8657 |
+
"learning_rate": 1.5062819916240113e-05,
|
| 8658 |
+
"loss": 0.0445,
|
| 8659 |
+
"step": 12310
|
| 8660 |
+
},
|
| 8661 |
+
{
|
| 8662 |
+
"epoch": 4.8370632116215155,
|
| 8663 |
+
"grad_norm": 0.10748885571956635,
|
| 8664 |
+
"learning_rate": 1.505700325732899e-05,
|
| 8665 |
+
"loss": 0.0713,
|
| 8666 |
+
"step": 12320
|
| 8667 |
+
},
|
| 8668 |
+
{
|
| 8669 |
+
"epoch": 4.840989399293286,
|
| 8670 |
+
"grad_norm": 0.35963451862335205,
|
| 8671 |
+
"learning_rate": 1.505118659841787e-05,
|
| 8672 |
+
"loss": 0.0062,
|
| 8673 |
+
"step": 12330
|
| 8674 |
+
},
|
| 8675 |
+
{
|
| 8676 |
+
"epoch": 4.844915586965057,
|
| 8677 |
+
"grad_norm": 0.73185795545578,
|
| 8678 |
+
"learning_rate": 1.5045369939506748e-05,
|
| 8679 |
+
"loss": 0.0171,
|
| 8680 |
+
"step": 12340
|
| 8681 |
+
},
|
| 8682 |
+
{
|
| 8683 |
+
"epoch": 4.848841774636828,
|
| 8684 |
+
"grad_norm": 0.9059085249900818,
|
| 8685 |
+
"learning_rate": 1.5039553280595628e-05,
|
| 8686 |
+
"loss": 0.0121,
|
| 8687 |
+
"step": 12350
|
| 8688 |
+
},
|
| 8689 |
+
{
|
| 8690 |
+
"epoch": 4.852767962308598,
|
| 8691 |
+
"grad_norm": 1.2093955278396606,
|
| 8692 |
+
"learning_rate": 1.5033736621684505e-05,
|
| 8693 |
+
"loss": 0.0355,
|
| 8694 |
+
"step": 12360
|
| 8695 |
+
},
|
| 8696 |
+
{
|
| 8697 |
+
"epoch": 4.856694149980369,
|
| 8698 |
+
"grad_norm": 0.0915590301156044,
|
| 8699 |
+
"learning_rate": 1.5027919962773385e-05,
|
| 8700 |
+
"loss": 0.0718,
|
| 8701 |
+
"step": 12370
|
| 8702 |
+
},
|
| 8703 |
+
{
|
| 8704 |
+
"epoch": 4.86062033765214,
|
| 8705 |
+
"grad_norm": 0.03942778706550598,
|
| 8706 |
+
"learning_rate": 1.5022103303862263e-05,
|
| 8707 |
+
"loss": 0.009,
|
| 8708 |
+
"step": 12380
|
| 8709 |
+
},
|
| 8710 |
+
{
|
| 8711 |
+
"epoch": 4.86454652532391,
|
| 8712 |
+
"grad_norm": 8.495245933532715,
|
| 8713 |
+
"learning_rate": 1.5016286644951141e-05,
|
| 8714 |
+
"loss": 0.0198,
|
| 8715 |
+
"step": 12390
|
| 8716 |
+
},
|
| 8717 |
+
{
|
| 8718 |
+
"epoch": 4.868472712995681,
|
| 8719 |
+
"grad_norm": 0.015669044107198715,
|
| 8720 |
+
"learning_rate": 1.5010469986040019e-05,
|
| 8721 |
+
"loss": 0.0058,
|
| 8722 |
+
"step": 12400
|
| 8723 |
+
},
|
| 8724 |
+
{
|
| 8725 |
+
"epoch": 4.872398900667452,
|
| 8726 |
+
"grad_norm": 0.058739807456731796,
|
| 8727 |
+
"learning_rate": 1.5004653327128897e-05,
|
| 8728 |
+
"loss": 0.0693,
|
| 8729 |
+
"step": 12410
|
| 8730 |
+
},
|
| 8731 |
+
{
|
| 8732 |
+
"epoch": 4.876325088339223,
|
| 8733 |
+
"grad_norm": 0.041007980704307556,
|
| 8734 |
+
"learning_rate": 1.4998836668217778e-05,
|
| 8735 |
+
"loss": 0.013,
|
| 8736 |
+
"step": 12420
|
| 8737 |
+
},
|
| 8738 |
+
{
|
| 8739 |
+
"epoch": 4.880251276010993,
|
| 8740 |
+
"grad_norm": 0.34795665740966797,
|
| 8741 |
+
"learning_rate": 1.4993020009306656e-05,
|
| 8742 |
+
"loss": 0.0142,
|
| 8743 |
+
"step": 12430
|
| 8744 |
+
},
|
| 8745 |
+
{
|
| 8746 |
+
"epoch": 4.884177463682764,
|
| 8747 |
+
"grad_norm": 0.47241175174713135,
|
| 8748 |
+
"learning_rate": 1.4987203350395534e-05,
|
| 8749 |
+
"loss": 0.0131,
|
| 8750 |
+
"step": 12440
|
| 8751 |
+
},
|
| 8752 |
+
{
|
| 8753 |
+
"epoch": 4.888103651354535,
|
| 8754 |
+
"grad_norm": 5.519250869750977,
|
| 8755 |
+
"learning_rate": 1.4981386691484412e-05,
|
| 8756 |
+
"loss": 0.028,
|
| 8757 |
+
"step": 12450
|
| 8758 |
+
},
|
| 8759 |
+
{
|
| 8760 |
+
"epoch": 4.892029839026305,
|
| 8761 |
+
"grad_norm": 0.02329498715698719,
|
| 8762 |
+
"learning_rate": 1.4975570032573293e-05,
|
| 8763 |
+
"loss": 0.0135,
|
| 8764 |
+
"step": 12460
|
| 8765 |
+
},
|
| 8766 |
+
{
|
| 8767 |
+
"epoch": 4.895956026698077,
|
| 8768 |
+
"grad_norm": 0.0213804729282856,
|
| 8769 |
+
"learning_rate": 1.4969753373662171e-05,
|
| 8770 |
+
"loss": 0.0031,
|
| 8771 |
+
"step": 12470
|
| 8772 |
+
},
|
| 8773 |
+
{
|
| 8774 |
+
"epoch": 4.899882214369847,
|
| 8775 |
+
"grad_norm": 0.0839194506406784,
|
| 8776 |
+
"learning_rate": 1.4963936714751049e-05,
|
| 8777 |
+
"loss": 0.0177,
|
| 8778 |
+
"step": 12480
|
| 8779 |
+
},
|
| 8780 |
+
{
|
| 8781 |
+
"epoch": 4.9038084020416175,
|
| 8782 |
+
"grad_norm": 0.04029995948076248,
|
| 8783 |
+
"learning_rate": 1.4958120055839927e-05,
|
| 8784 |
+
"loss": 0.2083,
|
| 8785 |
+
"step": 12490
|
| 8786 |
+
},
|
| 8787 |
+
{
|
| 8788 |
+
"epoch": 4.907734589713388,
|
| 8789 |
+
"grad_norm": 4.740542888641357,
|
| 8790 |
+
"learning_rate": 1.4952303396928805e-05,
|
| 8791 |
+
"loss": 0.012,
|
| 8792 |
+
"step": 12500
|
| 8793 |
+
},
|
| 8794 |
+
{
|
| 8795 |
+
"epoch": 4.911660777385159,
|
| 8796 |
+
"grad_norm": 6.482239723205566,
|
| 8797 |
+
"learning_rate": 1.4946486738017684e-05,
|
| 8798 |
+
"loss": 0.0172,
|
| 8799 |
+
"step": 12510
|
| 8800 |
+
},
|
| 8801 |
+
{
|
| 8802 |
+
"epoch": 4.91558696505693,
|
| 8803 |
+
"grad_norm": 0.8036333322525024,
|
| 8804 |
+
"learning_rate": 1.4940670079106562e-05,
|
| 8805 |
+
"loss": 0.0106,
|
| 8806 |
+
"step": 12520
|
| 8807 |
+
},
|
| 8808 |
+
{
|
| 8809 |
+
"epoch": 4.9195131527287,
|
| 8810 |
+
"grad_norm": 2.3662140369415283,
|
| 8811 |
+
"learning_rate": 1.493485342019544e-05,
|
| 8812 |
+
"loss": 0.0143,
|
| 8813 |
+
"step": 12530
|
| 8814 |
+
},
|
| 8815 |
+
{
|
| 8816 |
+
"epoch": 4.9234393404004715,
|
| 8817 |
+
"grad_norm": 0.06163240596652031,
|
| 8818 |
+
"learning_rate": 1.492903676128432e-05,
|
| 8819 |
+
"loss": 0.0123,
|
| 8820 |
+
"step": 12540
|
| 8821 |
+
},
|
| 8822 |
+
{
|
| 8823 |
+
"epoch": 4.927365528072242,
|
| 8824 |
+
"grad_norm": 0.6264298558235168,
|
| 8825 |
+
"learning_rate": 1.4923220102373198e-05,
|
| 8826 |
+
"loss": 0.0155,
|
| 8827 |
+
"step": 12550
|
| 8828 |
+
},
|
| 8829 |
+
{
|
| 8830 |
+
"epoch": 4.931291715744012,
|
| 8831 |
+
"grad_norm": 0.10601702332496643,
|
| 8832 |
+
"learning_rate": 1.4917403443462077e-05,
|
| 8833 |
+
"loss": 0.0167,
|
| 8834 |
+
"step": 12560
|
| 8835 |
+
},
|
| 8836 |
+
{
|
| 8837 |
+
"epoch": 4.935217903415783,
|
| 8838 |
+
"grad_norm": 0.5394860506057739,
|
| 8839 |
+
"learning_rate": 1.4911586784550955e-05,
|
| 8840 |
+
"loss": 0.0064,
|
| 8841 |
+
"step": 12570
|
| 8842 |
+
},
|
| 8843 |
+
{
|
| 8844 |
+
"epoch": 4.939144091087554,
|
| 8845 |
+
"grad_norm": 0.08920938521623611,
|
| 8846 |
+
"learning_rate": 1.4905770125639833e-05,
|
| 8847 |
+
"loss": 0.0088,
|
| 8848 |
+
"step": 12580
|
| 8849 |
+
},
|
| 8850 |
+
{
|
| 8851 |
+
"epoch": 4.943070278759325,
|
| 8852 |
+
"grad_norm": 0.0034480299800634384,
|
| 8853 |
+
"learning_rate": 1.4899953466728711e-05,
|
| 8854 |
+
"loss": 0.0087,
|
| 8855 |
+
"step": 12590
|
| 8856 |
+
},
|
| 8857 |
+
{
|
| 8858 |
+
"epoch": 4.946996466431095,
|
| 8859 |
+
"grad_norm": 0.016266481950879097,
|
| 8860 |
+
"learning_rate": 1.4894136807817592e-05,
|
| 8861 |
+
"loss": 0.0058,
|
| 8862 |
+
"step": 12600
|
| 8863 |
+
},
|
| 8864 |
+
{
|
| 8865 |
+
"epoch": 4.950922654102866,
|
| 8866 |
+
"grad_norm": 0.24764353036880493,
|
| 8867 |
+
"learning_rate": 1.488832014890647e-05,
|
| 8868 |
+
"loss": 0.0059,
|
| 8869 |
+
"step": 12610
|
| 8870 |
+
},
|
| 8871 |
+
{
|
| 8872 |
+
"epoch": 4.954848841774637,
|
| 8873 |
+
"grad_norm": 0.1810390055179596,
|
| 8874 |
+
"learning_rate": 1.4882503489995348e-05,
|
| 8875 |
+
"loss": 0.0183,
|
| 8876 |
+
"step": 12620
|
| 8877 |
+
},
|
| 8878 |
+
{
|
| 8879 |
+
"epoch": 4.958775029446407,
|
| 8880 |
+
"grad_norm": 0.001492789015173912,
|
| 8881 |
+
"learning_rate": 1.4876686831084226e-05,
|
| 8882 |
+
"loss": 0.0277,
|
| 8883 |
+
"step": 12630
|
| 8884 |
+
},
|
| 8885 |
+
{
|
| 8886 |
+
"epoch": 4.962701217118179,
|
| 8887 |
+
"grad_norm": 0.10155470669269562,
|
| 8888 |
+
"learning_rate": 1.4870870172173104e-05,
|
| 8889 |
+
"loss": 0.0068,
|
| 8890 |
+
"step": 12640
|
| 8891 |
+
},
|
| 8892 |
+
{
|
| 8893 |
+
"epoch": 4.966627404789949,
|
| 8894 |
+
"grad_norm": 14.543069839477539,
|
| 8895 |
+
"learning_rate": 1.4865053513261985e-05,
|
| 8896 |
+
"loss": 0.0295,
|
| 8897 |
+
"step": 12650
|
| 8898 |
+
},
|
| 8899 |
+
{
|
| 8900 |
+
"epoch": 4.9705535924617195,
|
| 8901 |
+
"grad_norm": 0.024104053154587746,
|
| 8902 |
+
"learning_rate": 1.4859236854350863e-05,
|
| 8903 |
+
"loss": 0.0056,
|
| 8904 |
+
"step": 12660
|
| 8905 |
+
},
|
| 8906 |
+
{
|
| 8907 |
+
"epoch": 4.974479780133491,
|
| 8908 |
+
"grad_norm": 0.36809274554252625,
|
| 8909 |
+
"learning_rate": 1.4853420195439741e-05,
|
| 8910 |
+
"loss": 0.0502,
|
| 8911 |
+
"step": 12670
|
| 8912 |
+
},
|
| 8913 |
+
{
|
| 8914 |
+
"epoch": 4.978405967805261,
|
| 8915 |
+
"grad_norm": 5.340637683868408,
|
| 8916 |
+
"learning_rate": 1.4847603536528619e-05,
|
| 8917 |
+
"loss": 0.011,
|
| 8918 |
+
"step": 12680
|
| 8919 |
+
},
|
| 8920 |
+
{
|
| 8921 |
+
"epoch": 4.982332155477032,
|
| 8922 |
+
"grad_norm": 8.512194633483887,
|
| 8923 |
+
"learning_rate": 1.4841786877617497e-05,
|
| 8924 |
+
"loss": 0.0372,
|
| 8925 |
+
"step": 12690
|
| 8926 |
+
},
|
| 8927 |
+
{
|
| 8928 |
+
"epoch": 4.986258343148803,
|
| 8929 |
+
"grad_norm": 0.029954668134450912,
|
| 8930 |
+
"learning_rate": 1.4835970218706376e-05,
|
| 8931 |
+
"loss": 0.0031,
|
| 8932 |
+
"step": 12700
|
| 8933 |
+
},
|
| 8934 |
+
{
|
| 8935 |
+
"epoch": 4.9901845308205734,
|
| 8936 |
+
"grad_norm": 0.0016500629717484117,
|
| 8937 |
+
"learning_rate": 1.4830153559795254e-05,
|
| 8938 |
+
"loss": 0.0025,
|
| 8939 |
+
"step": 12710
|
| 8940 |
+
},
|
| 8941 |
+
{
|
| 8942 |
+
"epoch": 4.994110718492344,
|
| 8943 |
+
"grad_norm": 0.16582971811294556,
|
| 8944 |
+
"learning_rate": 1.4824336900884134e-05,
|
| 8945 |
+
"loss": 0.046,
|
| 8946 |
+
"step": 12720
|
| 8947 |
+
},
|
| 8948 |
+
{
|
| 8949 |
+
"epoch": 4.998036906164114,
|
| 8950 |
+
"grad_norm": 0.12066315859556198,
|
| 8951 |
+
"learning_rate": 1.4818520241973012e-05,
|
| 8952 |
+
"loss": 0.0011,
|
| 8953 |
+
"step": 12730
|
| 8954 |
+
},
|
| 8955 |
+
{
|
| 8956 |
+
"epoch": 5.0,
|
| 8957 |
+
"eval_loss": 0.043506357818841934,
|
| 8958 |
+
"eval_runtime": 20.8005,
|
| 8959 |
+
"eval_samples_per_second": 108.843,
|
| 8960 |
+
"eval_steps_per_second": 13.605,
|
| 8961 |
+
"step": 12735
|
| 8962 |
}
|
| 8963 |
],
|
| 8964 |
"logging_steps": 10,
|
|
|
|
| 8973 |
"early_stopping_threshold": 0.0
|
| 8974 |
},
|
| 8975 |
"attributes": {
|
| 8976 |
+
"early_stopping_patience_counter": 1
|
| 8977 |
}
|
| 8978 |
},
|
| 8979 |
"TrainerControl": {
|
|
|
|
| 8987 |
"attributes": {}
|
| 8988 |
}
|
| 8989 |
},
|
| 8990 |
+
"total_flos": 2.679833697752976e+16,
|
| 8991 |
"train_batch_size": 8,
|
| 8992 |
"trial_name": null,
|
| 8993 |
"trial_params": null
|