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 3, 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 sha256:35ed9db430c0d51cafbe688ba0564ceb754907647dedae6aa6ad2b56610b6409
|
| 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 sha256:781d789e019b22dfee92f11aeebec379fb2bc986fa3102c432cd84ca34bf688d
|
| 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 sha256:5c1bb8c98e4c9601cc37584c9f035c165e9f4a96ae8c30b20f74e1f85716b92b
|
| 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 sha256:415b697b99817346464230aefa8ff375a377ce54ea66cab290b700e7cd622b03
|
| 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 sha256:2fc28870959a58b539474ac771d48ae872534a62904d0c58dbadf5a9b11aa133
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/tmp/tmph_3waeuv/deberta-multilabel/checkpoint-
|
| 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,
|
|
@@ -3587,6 +3587,1799 @@
|
|
| 3587 |
"eval_samples_per_second": 108.377,
|
| 3588 |
"eval_steps_per_second": 13.547,
|
| 3589 |
"step": 5094
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3590 |
}
|
| 3591 |
],
|
| 3592 |
"logging_steps": 10,
|
|
@@ -3615,7 +5408,7 @@
|
|
| 3615 |
"attributes": {}
|
| 3616 |
}
|
| 3617 |
},
|
| 3618 |
-
"total_flos": 1.
|
| 3619 |
"train_batch_size": 8,
|
| 3620 |
"trial_name": null,
|
| 3621 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 7641,
|
| 3 |
+
"best_metric": 0.05170644447207451,
|
| 4 |
+
"best_model_checkpoint": "/tmp/tmph_3waeuv/deberta-multilabel/checkpoint-7641",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7641,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3587 |
"eval_samples_per_second": 108.377,
|
| 3588 |
"eval_steps_per_second": 13.547,
|
| 3589 |
"step": 5094
|
| 3590 |
+
},
|
| 3591 |
+
{
|
| 3592 |
+
"epoch": 2.0023557126030624,
|
| 3593 |
+
"grad_norm": 0.2279011309146881,
|
| 3594 |
+
"learning_rate": 1.925663099115868e-05,
|
| 3595 |
+
"loss": 0.0237,
|
| 3596 |
+
"step": 5100
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 2.0062819002748333,
|
| 3600 |
+
"grad_norm": 2.168032646179199,
|
| 3601 |
+
"learning_rate": 1.925081433224756e-05,
|
| 3602 |
+
"loss": 0.0236,
|
| 3603 |
+
"step": 5110
|
| 3604 |
+
},
|
| 3605 |
+
{
|
| 3606 |
+
"epoch": 2.0102080879466038,
|
| 3607 |
+
"grad_norm": 0.3002466559410095,
|
| 3608 |
+
"learning_rate": 1.9244997673336435e-05,
|
| 3609 |
+
"loss": 0.0533,
|
| 3610 |
+
"step": 5120
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 2.0141342756183747,
|
| 3614 |
+
"grad_norm": 0.45628660917282104,
|
| 3615 |
+
"learning_rate": 1.9239181014425315e-05,
|
| 3616 |
+
"loss": 0.0141,
|
| 3617 |
+
"step": 5130
|
| 3618 |
+
},
|
| 3619 |
+
{
|
| 3620 |
+
"epoch": 2.018060463290145,
|
| 3621 |
+
"grad_norm": 0.042240504175424576,
|
| 3622 |
+
"learning_rate": 1.9233364355514195e-05,
|
| 3623 |
+
"loss": 0.0566,
|
| 3624 |
+
"step": 5140
|
| 3625 |
+
},
|
| 3626 |
+
{
|
| 3627 |
+
"epoch": 2.021986650961916,
|
| 3628 |
+
"grad_norm": 0.0029841673094779253,
|
| 3629 |
+
"learning_rate": 1.9227547696603074e-05,
|
| 3630 |
+
"loss": 0.2117,
|
| 3631 |
+
"step": 5150
|
| 3632 |
+
},
|
| 3633 |
+
{
|
| 3634 |
+
"epoch": 2.025912838633687,
|
| 3635 |
+
"grad_norm": 1.4892984628677368,
|
| 3636 |
+
"learning_rate": 1.922173103769195e-05,
|
| 3637 |
+
"loss": 0.0559,
|
| 3638 |
+
"step": 5160
|
| 3639 |
+
},
|
| 3640 |
+
{
|
| 3641 |
+
"epoch": 2.0298390263054573,
|
| 3642 |
+
"grad_norm": 0.15361247956752777,
|
| 3643 |
+
"learning_rate": 1.921591437878083e-05,
|
| 3644 |
+
"loss": 0.0728,
|
| 3645 |
+
"step": 5170
|
| 3646 |
+
},
|
| 3647 |
+
{
|
| 3648 |
+
"epoch": 2.033765213977228,
|
| 3649 |
+
"grad_norm": 1.8038830757141113,
|
| 3650 |
+
"learning_rate": 1.921009771986971e-05,
|
| 3651 |
+
"loss": 0.0356,
|
| 3652 |
+
"step": 5180
|
| 3653 |
+
},
|
| 3654 |
+
{
|
| 3655 |
+
"epoch": 2.0376914016489986,
|
| 3656 |
+
"grad_norm": 0.4968324601650238,
|
| 3657 |
+
"learning_rate": 1.9204281060958586e-05,
|
| 3658 |
+
"loss": 0.095,
|
| 3659 |
+
"step": 5190
|
| 3660 |
+
},
|
| 3661 |
+
{
|
| 3662 |
+
"epoch": 2.0416175893207695,
|
| 3663 |
+
"grad_norm": 0.28078097105026245,
|
| 3664 |
+
"learning_rate": 1.9198464402047466e-05,
|
| 3665 |
+
"loss": 0.0392,
|
| 3666 |
+
"step": 5200
|
| 3667 |
+
},
|
| 3668 |
+
{
|
| 3669 |
+
"epoch": 2.0455437769925404,
|
| 3670 |
+
"grad_norm": 0.4962281882762909,
|
| 3671 |
+
"learning_rate": 1.9192647743136342e-05,
|
| 3672 |
+
"loss": 0.0175,
|
| 3673 |
+
"step": 5210
|
| 3674 |
+
},
|
| 3675 |
+
{
|
| 3676 |
+
"epoch": 2.049469964664311,
|
| 3677 |
+
"grad_norm": 0.3737802803516388,
|
| 3678 |
+
"learning_rate": 1.9186831084225225e-05,
|
| 3679 |
+
"loss": 0.1967,
|
| 3680 |
+
"step": 5220
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 2.0533961523360817,
|
| 3684 |
+
"grad_norm": 0.4773881137371063,
|
| 3685 |
+
"learning_rate": 1.91810144253141e-05,
|
| 3686 |
+
"loss": 0.0255,
|
| 3687 |
+
"step": 5230
|
| 3688 |
+
},
|
| 3689 |
+
{
|
| 3690 |
+
"epoch": 2.057322340007852,
|
| 3691 |
+
"grad_norm": 14.505132675170898,
|
| 3692 |
+
"learning_rate": 1.917519776640298e-05,
|
| 3693 |
+
"loss": 0.0674,
|
| 3694 |
+
"step": 5240
|
| 3695 |
+
},
|
| 3696 |
+
{
|
| 3697 |
+
"epoch": 2.061248527679623,
|
| 3698 |
+
"grad_norm": 0.04960203170776367,
|
| 3699 |
+
"learning_rate": 1.9169381107491857e-05,
|
| 3700 |
+
"loss": 0.019,
|
| 3701 |
+
"step": 5250
|
| 3702 |
+
},
|
| 3703 |
+
{
|
| 3704 |
+
"epoch": 2.065174715351394,
|
| 3705 |
+
"grad_norm": 0.2507060170173645,
|
| 3706 |
+
"learning_rate": 1.9163564448580736e-05,
|
| 3707 |
+
"loss": 0.0964,
|
| 3708 |
+
"step": 5260
|
| 3709 |
+
},
|
| 3710 |
+
{
|
| 3711 |
+
"epoch": 2.0691009030231644,
|
| 3712 |
+
"grad_norm": 1.8199360370635986,
|
| 3713 |
+
"learning_rate": 1.9157747789669616e-05,
|
| 3714 |
+
"loss": 0.0788,
|
| 3715 |
+
"step": 5270
|
| 3716 |
+
},
|
| 3717 |
+
{
|
| 3718 |
+
"epoch": 2.0730270906949353,
|
| 3719 |
+
"grad_norm": 3.6587436199188232,
|
| 3720 |
+
"learning_rate": 1.9151931130758496e-05,
|
| 3721 |
+
"loss": 0.1014,
|
| 3722 |
+
"step": 5280
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 2.0769532783667057,
|
| 3726 |
+
"grad_norm": 0.10017173737287521,
|
| 3727 |
+
"learning_rate": 1.9146114471847372e-05,
|
| 3728 |
+
"loss": 0.06,
|
| 3729 |
+
"step": 5290
|
| 3730 |
+
},
|
| 3731 |
+
{
|
| 3732 |
+
"epoch": 2.0808794660384766,
|
| 3733 |
+
"grad_norm": 2.514589548110962,
|
| 3734 |
+
"learning_rate": 1.914029781293625e-05,
|
| 3735 |
+
"loss": 0.0155,
|
| 3736 |
+
"step": 5300
|
| 3737 |
+
},
|
| 3738 |
+
{
|
| 3739 |
+
"epoch": 2.0848056537102475,
|
| 3740 |
+
"grad_norm": 0.8474787473678589,
|
| 3741 |
+
"learning_rate": 1.9134481154025128e-05,
|
| 3742 |
+
"loss": 0.0709,
|
| 3743 |
+
"step": 5310
|
| 3744 |
+
},
|
| 3745 |
+
{
|
| 3746 |
+
"epoch": 2.088731841382018,
|
| 3747 |
+
"grad_norm": 1.115956425666809,
|
| 3748 |
+
"learning_rate": 1.9128664495114007e-05,
|
| 3749 |
+
"loss": 0.0159,
|
| 3750 |
+
"step": 5320
|
| 3751 |
+
},
|
| 3752 |
+
{
|
| 3753 |
+
"epoch": 2.092658029053789,
|
| 3754 |
+
"grad_norm": 1.0454119443893433,
|
| 3755 |
+
"learning_rate": 1.9122847836202887e-05,
|
| 3756 |
+
"loss": 0.096,
|
| 3757 |
+
"step": 5330
|
| 3758 |
+
},
|
| 3759 |
+
{
|
| 3760 |
+
"epoch": 2.0965842167255593,
|
| 3761 |
+
"grad_norm": 0.1053541824221611,
|
| 3762 |
+
"learning_rate": 1.9117031177291766e-05,
|
| 3763 |
+
"loss": 0.1359,
|
| 3764 |
+
"step": 5340
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 2.10051040439733,
|
| 3768 |
+
"grad_norm": 0.25928109884262085,
|
| 3769 |
+
"learning_rate": 1.9111214518380643e-05,
|
| 3770 |
+
"loss": 0.0399,
|
| 3771 |
+
"step": 5350
|
| 3772 |
+
},
|
| 3773 |
+
{
|
| 3774 |
+
"epoch": 2.104436592069101,
|
| 3775 |
+
"grad_norm": 0.7738245129585266,
|
| 3776 |
+
"learning_rate": 1.9105397859469522e-05,
|
| 3777 |
+
"loss": 0.0198,
|
| 3778 |
+
"step": 5360
|
| 3779 |
+
},
|
| 3780 |
+
{
|
| 3781 |
+
"epoch": 2.1083627797408715,
|
| 3782 |
+
"grad_norm": 0.07616060227155685,
|
| 3783 |
+
"learning_rate": 1.9099581200558402e-05,
|
| 3784 |
+
"loss": 0.0591,
|
| 3785 |
+
"step": 5370
|
| 3786 |
+
},
|
| 3787 |
+
{
|
| 3788 |
+
"epoch": 2.1122889674126424,
|
| 3789 |
+
"grad_norm": 0.11291632056236267,
|
| 3790 |
+
"learning_rate": 1.9093764541647278e-05,
|
| 3791 |
+
"loss": 0.0237,
|
| 3792 |
+
"step": 5380
|
| 3793 |
+
},
|
| 3794 |
+
{
|
| 3795 |
+
"epoch": 2.116215155084413,
|
| 3796 |
+
"grad_norm": 0.07854457944631577,
|
| 3797 |
+
"learning_rate": 1.9087947882736158e-05,
|
| 3798 |
+
"loss": 0.033,
|
| 3799 |
+
"step": 5390
|
| 3800 |
+
},
|
| 3801 |
+
{
|
| 3802 |
+
"epoch": 2.1201413427561837,
|
| 3803 |
+
"grad_norm": 0.048548270016908646,
|
| 3804 |
+
"learning_rate": 1.9082131223825034e-05,
|
| 3805 |
+
"loss": 0.3189,
|
| 3806 |
+
"step": 5400
|
| 3807 |
+
},
|
| 3808 |
+
{
|
| 3809 |
+
"epoch": 2.1240675304279546,
|
| 3810 |
+
"grad_norm": 13.434121131896973,
|
| 3811 |
+
"learning_rate": 1.9076314564913917e-05,
|
| 3812 |
+
"loss": 0.0526,
|
| 3813 |
+
"step": 5410
|
| 3814 |
+
},
|
| 3815 |
+
{
|
| 3816 |
+
"epoch": 2.127993718099725,
|
| 3817 |
+
"grad_norm": 0.10763205587863922,
|
| 3818 |
+
"learning_rate": 1.9070497906002793e-05,
|
| 3819 |
+
"loss": 0.2481,
|
| 3820 |
+
"step": 5420
|
| 3821 |
+
},
|
| 3822 |
+
{
|
| 3823 |
+
"epoch": 2.131919905771496,
|
| 3824 |
+
"grad_norm": 0.7192198634147644,
|
| 3825 |
+
"learning_rate": 1.9064681247091673e-05,
|
| 3826 |
+
"loss": 0.0186,
|
| 3827 |
+
"step": 5430
|
| 3828 |
+
},
|
| 3829 |
+
{
|
| 3830 |
+
"epoch": 2.1358460934432664,
|
| 3831 |
+
"grad_norm": 0.14636504650115967,
|
| 3832 |
+
"learning_rate": 1.905886458818055e-05,
|
| 3833 |
+
"loss": 0.0337,
|
| 3834 |
+
"step": 5440
|
| 3835 |
+
},
|
| 3836 |
+
{
|
| 3837 |
+
"epoch": 2.1397722811150373,
|
| 3838 |
+
"grad_norm": 0.9293457865715027,
|
| 3839 |
+
"learning_rate": 1.905304792926943e-05,
|
| 3840 |
+
"loss": 0.0137,
|
| 3841 |
+
"step": 5450
|
| 3842 |
+
},
|
| 3843 |
+
{
|
| 3844 |
+
"epoch": 2.143698468786808,
|
| 3845 |
+
"grad_norm": 1.6500604152679443,
|
| 3846 |
+
"learning_rate": 1.9047231270358308e-05,
|
| 3847 |
+
"loss": 0.1284,
|
| 3848 |
+
"step": 5460
|
| 3849 |
+
},
|
| 3850 |
+
{
|
| 3851 |
+
"epoch": 2.1476246564585786,
|
| 3852 |
+
"grad_norm": 0.0883244201540947,
|
| 3853 |
+
"learning_rate": 1.9041414611447188e-05,
|
| 3854 |
+
"loss": 0.0159,
|
| 3855 |
+
"step": 5470
|
| 3856 |
+
},
|
| 3857 |
+
{
|
| 3858 |
+
"epoch": 2.1515508441303495,
|
| 3859 |
+
"grad_norm": 0.6920208930969238,
|
| 3860 |
+
"learning_rate": 1.9035597952536064e-05,
|
| 3861 |
+
"loss": 0.1718,
|
| 3862 |
+
"step": 5480
|
| 3863 |
+
},
|
| 3864 |
+
{
|
| 3865 |
+
"epoch": 2.1554770318021204,
|
| 3866 |
+
"grad_norm": 1.8595269918441772,
|
| 3867 |
+
"learning_rate": 1.9029781293624944e-05,
|
| 3868 |
+
"loss": 0.0207,
|
| 3869 |
+
"step": 5490
|
| 3870 |
+
},
|
| 3871 |
+
{
|
| 3872 |
+
"epoch": 2.159403219473891,
|
| 3873 |
+
"grad_norm": 0.2765304744243622,
|
| 3874 |
+
"learning_rate": 1.9023964634713823e-05,
|
| 3875 |
+
"loss": 0.058,
|
| 3876 |
+
"step": 5500
|
| 3877 |
+
},
|
| 3878 |
+
{
|
| 3879 |
+
"epoch": 2.1633294071456617,
|
| 3880 |
+
"grad_norm": 18.157400131225586,
|
| 3881 |
+
"learning_rate": 1.90181479758027e-05,
|
| 3882 |
+
"loss": 0.1946,
|
| 3883 |
+
"step": 5510
|
| 3884 |
+
},
|
| 3885 |
+
{
|
| 3886 |
+
"epoch": 2.167255594817432,
|
| 3887 |
+
"grad_norm": 3.797417163848877,
|
| 3888 |
+
"learning_rate": 1.901233131689158e-05,
|
| 3889 |
+
"loss": 0.045,
|
| 3890 |
+
"step": 5520
|
| 3891 |
+
},
|
| 3892 |
+
{
|
| 3893 |
+
"epoch": 2.171181782489203,
|
| 3894 |
+
"grad_norm": 2.2270009517669678,
|
| 3895 |
+
"learning_rate": 1.900651465798046e-05,
|
| 3896 |
+
"loss": 0.0268,
|
| 3897 |
+
"step": 5530
|
| 3898 |
+
},
|
| 3899 |
+
{
|
| 3900 |
+
"epoch": 2.175107970160974,
|
| 3901 |
+
"grad_norm": 0.06735406816005707,
|
| 3902 |
+
"learning_rate": 1.9000697999069335e-05,
|
| 3903 |
+
"loss": 0.0543,
|
| 3904 |
+
"step": 5540
|
| 3905 |
+
},
|
| 3906 |
+
{
|
| 3907 |
+
"epoch": 2.1790341578327443,
|
| 3908 |
+
"grad_norm": 0.2913612723350525,
|
| 3909 |
+
"learning_rate": 1.8994881340158214e-05,
|
| 3910 |
+
"loss": 0.0941,
|
| 3911 |
+
"step": 5550
|
| 3912 |
+
},
|
| 3913 |
+
{
|
| 3914 |
+
"epoch": 2.1829603455045152,
|
| 3915 |
+
"grad_norm": 0.7347955703735352,
|
| 3916 |
+
"learning_rate": 1.8989064681247094e-05,
|
| 3917 |
+
"loss": 0.1395,
|
| 3918 |
+
"step": 5560
|
| 3919 |
+
},
|
| 3920 |
+
{
|
| 3921 |
+
"epoch": 2.1868865331762857,
|
| 3922 |
+
"grad_norm": 2.1317474842071533,
|
| 3923 |
+
"learning_rate": 1.898324802233597e-05,
|
| 3924 |
+
"loss": 0.0745,
|
| 3925 |
+
"step": 5570
|
| 3926 |
+
},
|
| 3927 |
+
{
|
| 3928 |
+
"epoch": 2.1908127208480566,
|
| 3929 |
+
"grad_norm": 1.4864833354949951,
|
| 3930 |
+
"learning_rate": 1.897743136342485e-05,
|
| 3931 |
+
"loss": 0.0831,
|
| 3932 |
+
"step": 5580
|
| 3933 |
+
},
|
| 3934 |
+
{
|
| 3935 |
+
"epoch": 2.1947389085198274,
|
| 3936 |
+
"grad_norm": 0.029011867940425873,
|
| 3937 |
+
"learning_rate": 1.897161470451373e-05,
|
| 3938 |
+
"loss": 0.0976,
|
| 3939 |
+
"step": 5590
|
| 3940 |
+
},
|
| 3941 |
+
{
|
| 3942 |
+
"epoch": 2.198665096191598,
|
| 3943 |
+
"grad_norm": 0.5562877655029297,
|
| 3944 |
+
"learning_rate": 1.896579804560261e-05,
|
| 3945 |
+
"loss": 0.0305,
|
| 3946 |
+
"step": 5600
|
| 3947 |
+
},
|
| 3948 |
+
{
|
| 3949 |
+
"epoch": 2.2025912838633688,
|
| 3950 |
+
"grad_norm": 0.5091537237167358,
|
| 3951 |
+
"learning_rate": 1.8959981386691485e-05,
|
| 3952 |
+
"loss": 0.0241,
|
| 3953 |
+
"step": 5610
|
| 3954 |
+
},
|
| 3955 |
+
{
|
| 3956 |
+
"epoch": 2.206517471535139,
|
| 3957 |
+
"grad_norm": 0.3060062527656555,
|
| 3958 |
+
"learning_rate": 1.8954164727780365e-05,
|
| 3959 |
+
"loss": 0.0423,
|
| 3960 |
+
"step": 5620
|
| 3961 |
+
},
|
| 3962 |
+
{
|
| 3963 |
+
"epoch": 2.21044365920691,
|
| 3964 |
+
"grad_norm": 1.2051234245300293,
|
| 3965 |
+
"learning_rate": 1.894834806886924e-05,
|
| 3966 |
+
"loss": 0.0287,
|
| 3967 |
+
"step": 5630
|
| 3968 |
+
},
|
| 3969 |
+
{
|
| 3970 |
+
"epoch": 2.214369846878681,
|
| 3971 |
+
"grad_norm": 2.3069636821746826,
|
| 3972 |
+
"learning_rate": 1.8942531409958124e-05,
|
| 3973 |
+
"loss": 0.0199,
|
| 3974 |
+
"step": 5640
|
| 3975 |
+
},
|
| 3976 |
+
{
|
| 3977 |
+
"epoch": 2.2182960345504514,
|
| 3978 |
+
"grad_norm": 0.05090007558465004,
|
| 3979 |
+
"learning_rate": 1.8936714751047e-05,
|
| 3980 |
+
"loss": 0.0168,
|
| 3981 |
+
"step": 5650
|
| 3982 |
+
},
|
| 3983 |
+
{
|
| 3984 |
+
"epoch": 2.2222222222222223,
|
| 3985 |
+
"grad_norm": 0.0673454999923706,
|
| 3986 |
+
"learning_rate": 1.893089809213588e-05,
|
| 3987 |
+
"loss": 0.0256,
|
| 3988 |
+
"step": 5660
|
| 3989 |
+
},
|
| 3990 |
+
{
|
| 3991 |
+
"epoch": 2.2261484098939928,
|
| 3992 |
+
"grad_norm": 0.13741399347782135,
|
| 3993 |
+
"learning_rate": 1.8925081433224756e-05,
|
| 3994 |
+
"loss": 0.0132,
|
| 3995 |
+
"step": 5670
|
| 3996 |
+
},
|
| 3997 |
+
{
|
| 3998 |
+
"epoch": 2.2300745975657636,
|
| 3999 |
+
"grad_norm": 0.14176325500011444,
|
| 4000 |
+
"learning_rate": 1.8919264774313636e-05,
|
| 4001 |
+
"loss": 0.0346,
|
| 4002 |
+
"step": 5680
|
| 4003 |
+
},
|
| 4004 |
+
{
|
| 4005 |
+
"epoch": 2.2340007852375345,
|
| 4006 |
+
"grad_norm": 0.10057776421308517,
|
| 4007 |
+
"learning_rate": 1.8913448115402515e-05,
|
| 4008 |
+
"loss": 0.019,
|
| 4009 |
+
"step": 5690
|
| 4010 |
+
},
|
| 4011 |
+
{
|
| 4012 |
+
"epoch": 2.237926972909305,
|
| 4013 |
+
"grad_norm": 0.14266249537467957,
|
| 4014 |
+
"learning_rate": 1.890763145649139e-05,
|
| 4015 |
+
"loss": 0.0594,
|
| 4016 |
+
"step": 5700
|
| 4017 |
+
},
|
| 4018 |
+
{
|
| 4019 |
+
"epoch": 2.241853160581076,
|
| 4020 |
+
"grad_norm": 0.5893344879150391,
|
| 4021 |
+
"learning_rate": 1.890181479758027e-05,
|
| 4022 |
+
"loss": 0.0122,
|
| 4023 |
+
"step": 5710
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 2.2457793482528463,
|
| 4027 |
+
"grad_norm": 0.2829204499721527,
|
| 4028 |
+
"learning_rate": 1.889599813866915e-05,
|
| 4029 |
+
"loss": 0.0345,
|
| 4030 |
+
"step": 5720
|
| 4031 |
+
},
|
| 4032 |
+
{
|
| 4033 |
+
"epoch": 2.249705535924617,
|
| 4034 |
+
"grad_norm": 0.06246631592512131,
|
| 4035 |
+
"learning_rate": 1.889018147975803e-05,
|
| 4036 |
+
"loss": 0.0755,
|
| 4037 |
+
"step": 5730
|
| 4038 |
+
},
|
| 4039 |
+
{
|
| 4040 |
+
"epoch": 2.253631723596388,
|
| 4041 |
+
"grad_norm": 11.822826385498047,
|
| 4042 |
+
"learning_rate": 1.8884364820846907e-05,
|
| 4043 |
+
"loss": 0.0405,
|
| 4044 |
+
"step": 5740
|
| 4045 |
+
},
|
| 4046 |
+
{
|
| 4047 |
+
"epoch": 2.2575579112681585,
|
| 4048 |
+
"grad_norm": 0.05194117873907089,
|
| 4049 |
+
"learning_rate": 1.8878548161935786e-05,
|
| 4050 |
+
"loss": 0.0173,
|
| 4051 |
+
"step": 5750
|
| 4052 |
+
},
|
| 4053 |
+
{
|
| 4054 |
+
"epoch": 2.2614840989399294,
|
| 4055 |
+
"grad_norm": 1.134953498840332,
|
| 4056 |
+
"learning_rate": 1.8872731503024662e-05,
|
| 4057 |
+
"loss": 0.0696,
|
| 4058 |
+
"step": 5760
|
| 4059 |
+
},
|
| 4060 |
+
{
|
| 4061 |
+
"epoch": 2.2654102866117,
|
| 4062 |
+
"grad_norm": 0.05437786132097244,
|
| 4063 |
+
"learning_rate": 1.8866914844113542e-05,
|
| 4064 |
+
"loss": 0.0162,
|
| 4065 |
+
"step": 5770
|
| 4066 |
+
},
|
| 4067 |
+
{
|
| 4068 |
+
"epoch": 2.2693364742834707,
|
| 4069 |
+
"grad_norm": 0.09542493522167206,
|
| 4070 |
+
"learning_rate": 1.886109818520242e-05,
|
| 4071 |
+
"loss": 0.028,
|
| 4072 |
+
"step": 5780
|
| 4073 |
+
},
|
| 4074 |
+
{
|
| 4075 |
+
"epoch": 2.2732626619552416,
|
| 4076 |
+
"grad_norm": 0.06297050416469574,
|
| 4077 |
+
"learning_rate": 1.88552815262913e-05,
|
| 4078 |
+
"loss": 0.0035,
|
| 4079 |
+
"step": 5790
|
| 4080 |
+
},
|
| 4081 |
+
{
|
| 4082 |
+
"epoch": 2.277188849627012,
|
| 4083 |
+
"grad_norm": 0.09117815643548965,
|
| 4084 |
+
"learning_rate": 1.8849464867380177e-05,
|
| 4085 |
+
"loss": 0.0079,
|
| 4086 |
+
"step": 5800
|
| 4087 |
+
},
|
| 4088 |
+
{
|
| 4089 |
+
"epoch": 2.281115037298783,
|
| 4090 |
+
"grad_norm": 0.16035327315330505,
|
| 4091 |
+
"learning_rate": 1.8843648208469057e-05,
|
| 4092 |
+
"loss": 0.0365,
|
| 4093 |
+
"step": 5810
|
| 4094 |
+
},
|
| 4095 |
+
{
|
| 4096 |
+
"epoch": 2.285041224970554,
|
| 4097 |
+
"grad_norm": 2.6382791996002197,
|
| 4098 |
+
"learning_rate": 1.8837831549557933e-05,
|
| 4099 |
+
"loss": 0.0122,
|
| 4100 |
+
"step": 5820
|
| 4101 |
+
},
|
| 4102 |
+
{
|
| 4103 |
+
"epoch": 2.2889674126423243,
|
| 4104 |
+
"grad_norm": 0.09289387613534927,
|
| 4105 |
+
"learning_rate": 1.8832014890646816e-05,
|
| 4106 |
+
"loss": 0.2199,
|
| 4107 |
+
"step": 5830
|
| 4108 |
+
},
|
| 4109 |
+
{
|
| 4110 |
+
"epoch": 2.292893600314095,
|
| 4111 |
+
"grad_norm": 0.016388915479183197,
|
| 4112 |
+
"learning_rate": 1.8826198231735692e-05,
|
| 4113 |
+
"loss": 0.0572,
|
| 4114 |
+
"step": 5840
|
| 4115 |
+
},
|
| 4116 |
+
{
|
| 4117 |
+
"epoch": 2.2968197879858656,
|
| 4118 |
+
"grad_norm": 3.7514560222625732,
|
| 4119 |
+
"learning_rate": 1.8820381572824572e-05,
|
| 4120 |
+
"loss": 0.0326,
|
| 4121 |
+
"step": 5850
|
| 4122 |
+
},
|
| 4123 |
+
{
|
| 4124 |
+
"epoch": 2.3007459756576365,
|
| 4125 |
+
"grad_norm": 3.835205078125,
|
| 4126 |
+
"learning_rate": 1.8814564913913448e-05,
|
| 4127 |
+
"loss": 0.106,
|
| 4128 |
+
"step": 5860
|
| 4129 |
+
},
|
| 4130 |
+
{
|
| 4131 |
+
"epoch": 2.304672163329407,
|
| 4132 |
+
"grad_norm": 0.6968238353729248,
|
| 4133 |
+
"learning_rate": 1.8808748255002328e-05,
|
| 4134 |
+
"loss": 0.0262,
|
| 4135 |
+
"step": 5870
|
| 4136 |
+
},
|
| 4137 |
+
{
|
| 4138 |
+
"epoch": 2.308598351001178,
|
| 4139 |
+
"grad_norm": 0.41381657123565674,
|
| 4140 |
+
"learning_rate": 1.8802931596091208e-05,
|
| 4141 |
+
"loss": 0.0158,
|
| 4142 |
+
"step": 5880
|
| 4143 |
+
},
|
| 4144 |
+
{
|
| 4145 |
+
"epoch": 2.3125245386729487,
|
| 4146 |
+
"grad_norm": 0.09539110213518143,
|
| 4147 |
+
"learning_rate": 1.8797114937180084e-05,
|
| 4148 |
+
"loss": 0.0825,
|
| 4149 |
+
"step": 5890
|
| 4150 |
+
},
|
| 4151 |
+
{
|
| 4152 |
+
"epoch": 2.316450726344719,
|
| 4153 |
+
"grad_norm": 2.0592257976531982,
|
| 4154 |
+
"learning_rate": 1.8791298278268963e-05,
|
| 4155 |
+
"loss": 0.0131,
|
| 4156 |
+
"step": 5900
|
| 4157 |
+
},
|
| 4158 |
+
{
|
| 4159 |
+
"epoch": 2.32037691401649,
|
| 4160 |
+
"grad_norm": 0.42865052819252014,
|
| 4161 |
+
"learning_rate": 1.8785481619357843e-05,
|
| 4162 |
+
"loss": 0.0468,
|
| 4163 |
+
"step": 5910
|
| 4164 |
+
},
|
| 4165 |
+
{
|
| 4166 |
+
"epoch": 2.324303101688261,
|
| 4167 |
+
"grad_norm": 0.31759971380233765,
|
| 4168 |
+
"learning_rate": 1.8779664960446723e-05,
|
| 4169 |
+
"loss": 0.0576,
|
| 4170 |
+
"step": 5920
|
| 4171 |
+
},
|
| 4172 |
+
{
|
| 4173 |
+
"epoch": 2.3282292893600314,
|
| 4174 |
+
"grad_norm": 1.3801558017730713,
|
| 4175 |
+
"learning_rate": 1.87738483015356e-05,
|
| 4176 |
+
"loss": 0.0513,
|
| 4177 |
+
"step": 5930
|
| 4178 |
+
},
|
| 4179 |
+
{
|
| 4180 |
+
"epoch": 2.3321554770318023,
|
| 4181 |
+
"grad_norm": 0.04240234196186066,
|
| 4182 |
+
"learning_rate": 1.876803164262448e-05,
|
| 4183 |
+
"loss": 0.0905,
|
| 4184 |
+
"step": 5940
|
| 4185 |
+
},
|
| 4186 |
+
{
|
| 4187 |
+
"epoch": 2.3360816647035727,
|
| 4188 |
+
"grad_norm": 1.111049771308899,
|
| 4189 |
+
"learning_rate": 1.8762214983713355e-05,
|
| 4190 |
+
"loss": 0.0637,
|
| 4191 |
+
"step": 5950
|
| 4192 |
+
},
|
| 4193 |
+
{
|
| 4194 |
+
"epoch": 2.3400078523753436,
|
| 4195 |
+
"grad_norm": 0.02671370841562748,
|
| 4196 |
+
"learning_rate": 1.8756398324802234e-05,
|
| 4197 |
+
"loss": 0.0272,
|
| 4198 |
+
"step": 5960
|
| 4199 |
+
},
|
| 4200 |
+
{
|
| 4201 |
+
"epoch": 2.343934040047114,
|
| 4202 |
+
"grad_norm": 0.13138671219348907,
|
| 4203 |
+
"learning_rate": 1.8750581665891114e-05,
|
| 4204 |
+
"loss": 0.0309,
|
| 4205 |
+
"step": 5970
|
| 4206 |
+
},
|
| 4207 |
+
{
|
| 4208 |
+
"epoch": 2.347860227718885,
|
| 4209 |
+
"grad_norm": 0.22526326775550842,
|
| 4210 |
+
"learning_rate": 1.8744765006979993e-05,
|
| 4211 |
+
"loss": 0.0175,
|
| 4212 |
+
"step": 5980
|
| 4213 |
+
},
|
| 4214 |
+
{
|
| 4215 |
+
"epoch": 2.351786415390656,
|
| 4216 |
+
"grad_norm": 0.4106248915195465,
|
| 4217 |
+
"learning_rate": 1.873894834806887e-05,
|
| 4218 |
+
"loss": 0.0404,
|
| 4219 |
+
"step": 5990
|
| 4220 |
+
},
|
| 4221 |
+
{
|
| 4222 |
+
"epoch": 2.3557126030624262,
|
| 4223 |
+
"grad_norm": 0.2012689858675003,
|
| 4224 |
+
"learning_rate": 1.873313168915775e-05,
|
| 4225 |
+
"loss": 0.2183,
|
| 4226 |
+
"step": 6000
|
| 4227 |
+
},
|
| 4228 |
+
{
|
| 4229 |
+
"epoch": 2.359638790734197,
|
| 4230 |
+
"grad_norm": 8.109643936157227,
|
| 4231 |
+
"learning_rate": 1.872731503024663e-05,
|
| 4232 |
+
"loss": 0.082,
|
| 4233 |
+
"step": 6010
|
| 4234 |
+
},
|
| 4235 |
+
{
|
| 4236 |
+
"epoch": 2.363564978405968,
|
| 4237 |
+
"grad_norm": 0.8117945790290833,
|
| 4238 |
+
"learning_rate": 1.872149837133551e-05,
|
| 4239 |
+
"loss": 0.0198,
|
| 4240 |
+
"step": 6020
|
| 4241 |
+
},
|
| 4242 |
+
{
|
| 4243 |
+
"epoch": 2.3674911660777385,
|
| 4244 |
+
"grad_norm": 14.238556861877441,
|
| 4245 |
+
"learning_rate": 1.8715681712424385e-05,
|
| 4246 |
+
"loss": 0.1072,
|
| 4247 |
+
"step": 6030
|
| 4248 |
+
},
|
| 4249 |
+
{
|
| 4250 |
+
"epoch": 2.3714173537495093,
|
| 4251 |
+
"grad_norm": 0.1917840540409088,
|
| 4252 |
+
"learning_rate": 1.8709865053513264e-05,
|
| 4253 |
+
"loss": 0.0594,
|
| 4254 |
+
"step": 6040
|
| 4255 |
+
},
|
| 4256 |
+
{
|
| 4257 |
+
"epoch": 2.37534354142128,
|
| 4258 |
+
"grad_norm": 0.4545725882053375,
|
| 4259 |
+
"learning_rate": 1.870404839460214e-05,
|
| 4260 |
+
"loss": 0.0846,
|
| 4261 |
+
"step": 6050
|
| 4262 |
+
},
|
| 4263 |
+
{
|
| 4264 |
+
"epoch": 2.3792697290930507,
|
| 4265 |
+
"grad_norm": 1.9747635126113892,
|
| 4266 |
+
"learning_rate": 1.869823173569102e-05,
|
| 4267 |
+
"loss": 0.0451,
|
| 4268 |
+
"step": 6060
|
| 4269 |
+
},
|
| 4270 |
+
{
|
| 4271 |
+
"epoch": 2.383195916764821,
|
| 4272 |
+
"grad_norm": 0.979232668876648,
|
| 4273 |
+
"learning_rate": 1.86924150767799e-05,
|
| 4274 |
+
"loss": 0.0238,
|
| 4275 |
+
"step": 6070
|
| 4276 |
+
},
|
| 4277 |
+
{
|
| 4278 |
+
"epoch": 2.387122104436592,
|
| 4279 |
+
"grad_norm": 0.5914800763130188,
|
| 4280 |
+
"learning_rate": 1.868659841786878e-05,
|
| 4281 |
+
"loss": 0.0638,
|
| 4282 |
+
"step": 6080
|
| 4283 |
+
},
|
| 4284 |
+
{
|
| 4285 |
+
"epoch": 2.391048292108363,
|
| 4286 |
+
"grad_norm": 18.003469467163086,
|
| 4287 |
+
"learning_rate": 1.8680781758957655e-05,
|
| 4288 |
+
"loss": 0.0415,
|
| 4289 |
+
"step": 6090
|
| 4290 |
+
},
|
| 4291 |
+
{
|
| 4292 |
+
"epoch": 2.3949744797801333,
|
| 4293 |
+
"grad_norm": 0.7248846292495728,
|
| 4294 |
+
"learning_rate": 1.8674965100046535e-05,
|
| 4295 |
+
"loss": 0.0272,
|
| 4296 |
+
"step": 6100
|
| 4297 |
+
},
|
| 4298 |
+
{
|
| 4299 |
+
"epoch": 2.3989006674519042,
|
| 4300 |
+
"grad_norm": 0.15681321918964386,
|
| 4301 |
+
"learning_rate": 1.8669148441135415e-05,
|
| 4302 |
+
"loss": 0.0211,
|
| 4303 |
+
"step": 6110
|
| 4304 |
+
},
|
| 4305 |
+
{
|
| 4306 |
+
"epoch": 2.402826855123675,
|
| 4307 |
+
"grad_norm": 0.16553650796413422,
|
| 4308 |
+
"learning_rate": 1.866333178222429e-05,
|
| 4309 |
+
"loss": 0.0866,
|
| 4310 |
+
"step": 6120
|
| 4311 |
+
},
|
| 4312 |
+
{
|
| 4313 |
+
"epoch": 2.4067530427954456,
|
| 4314 |
+
"grad_norm": 0.6389226913452148,
|
| 4315 |
+
"learning_rate": 1.865751512331317e-05,
|
| 4316 |
+
"loss": 0.1406,
|
| 4317 |
+
"step": 6130
|
| 4318 |
+
},
|
| 4319 |
+
{
|
| 4320 |
+
"epoch": 2.4106792304672164,
|
| 4321 |
+
"grad_norm": 0.14854027330875397,
|
| 4322 |
+
"learning_rate": 1.8651698464402047e-05,
|
| 4323 |
+
"loss": 0.2108,
|
| 4324 |
+
"step": 6140
|
| 4325 |
+
},
|
| 4326 |
+
{
|
| 4327 |
+
"epoch": 2.414605418138987,
|
| 4328 |
+
"grad_norm": 8.142239570617676,
|
| 4329 |
+
"learning_rate": 1.864588180549093e-05,
|
| 4330 |
+
"loss": 0.0649,
|
| 4331 |
+
"step": 6150
|
| 4332 |
+
},
|
| 4333 |
+
{
|
| 4334 |
+
"epoch": 2.4185316058107578,
|
| 4335 |
+
"grad_norm": 0.6469948887825012,
|
| 4336 |
+
"learning_rate": 1.8640065146579806e-05,
|
| 4337 |
+
"loss": 0.0177,
|
| 4338 |
+
"step": 6160
|
| 4339 |
+
},
|
| 4340 |
+
{
|
| 4341 |
+
"epoch": 2.4224577934825287,
|
| 4342 |
+
"grad_norm": 0.4531613886356354,
|
| 4343 |
+
"learning_rate": 1.8634248487668686e-05,
|
| 4344 |
+
"loss": 0.0852,
|
| 4345 |
+
"step": 6170
|
| 4346 |
+
},
|
| 4347 |
+
{
|
| 4348 |
+
"epoch": 2.426383981154299,
|
| 4349 |
+
"grad_norm": 0.17687055468559265,
|
| 4350 |
+
"learning_rate": 1.8628431828757562e-05,
|
| 4351 |
+
"loss": 0.0658,
|
| 4352 |
+
"step": 6180
|
| 4353 |
+
},
|
| 4354 |
+
{
|
| 4355 |
+
"epoch": 2.43031016882607,
|
| 4356 |
+
"grad_norm": 0.7062463760375977,
|
| 4357 |
+
"learning_rate": 1.862261516984644e-05,
|
| 4358 |
+
"loss": 0.0218,
|
| 4359 |
+
"step": 6190
|
| 4360 |
+
},
|
| 4361 |
+
{
|
| 4362 |
+
"epoch": 2.4342363564978404,
|
| 4363 |
+
"grad_norm": 0.39460620284080505,
|
| 4364 |
+
"learning_rate": 1.861679851093532e-05,
|
| 4365 |
+
"loss": 0.0108,
|
| 4366 |
+
"step": 6200
|
| 4367 |
+
},
|
| 4368 |
+
{
|
| 4369 |
+
"epoch": 2.4381625441696113,
|
| 4370 |
+
"grad_norm": 0.3463928699493408,
|
| 4371 |
+
"learning_rate": 1.86109818520242e-05,
|
| 4372 |
+
"loss": 0.0693,
|
| 4373 |
+
"step": 6210
|
| 4374 |
+
},
|
| 4375 |
+
{
|
| 4376 |
+
"epoch": 2.442088731841382,
|
| 4377 |
+
"grad_norm": 2.334592342376709,
|
| 4378 |
+
"learning_rate": 1.8605165193113077e-05,
|
| 4379 |
+
"loss": 0.0166,
|
| 4380 |
+
"step": 6220
|
| 4381 |
+
},
|
| 4382 |
+
{
|
| 4383 |
+
"epoch": 2.4460149195131526,
|
| 4384 |
+
"grad_norm": 0.10348457843065262,
|
| 4385 |
+
"learning_rate": 1.8599348534201956e-05,
|
| 4386 |
+
"loss": 0.0505,
|
| 4387 |
+
"step": 6230
|
| 4388 |
+
},
|
| 4389 |
+
{
|
| 4390 |
+
"epoch": 2.4499411071849235,
|
| 4391 |
+
"grad_norm": 3.8471474647521973,
|
| 4392 |
+
"learning_rate": 1.8593531875290833e-05,
|
| 4393 |
+
"loss": 0.0469,
|
| 4394 |
+
"step": 6240
|
| 4395 |
+
},
|
| 4396 |
+
{
|
| 4397 |
+
"epoch": 2.453867294856694,
|
| 4398 |
+
"grad_norm": 0.04129194840788841,
|
| 4399 |
+
"learning_rate": 1.8587715216379712e-05,
|
| 4400 |
+
"loss": 0.0798,
|
| 4401 |
+
"step": 6250
|
| 4402 |
+
},
|
| 4403 |
+
{
|
| 4404 |
+
"epoch": 2.457793482528465,
|
| 4405 |
+
"grad_norm": 7.038460731506348,
|
| 4406 |
+
"learning_rate": 1.8581898557468592e-05,
|
| 4407 |
+
"loss": 0.0742,
|
| 4408 |
+
"step": 6260
|
| 4409 |
+
},
|
| 4410 |
+
{
|
| 4411 |
+
"epoch": 2.4617196702002357,
|
| 4412 |
+
"grad_norm": 2.7772345542907715,
|
| 4413 |
+
"learning_rate": 1.857608189855747e-05,
|
| 4414 |
+
"loss": 0.0426,
|
| 4415 |
+
"step": 6270
|
| 4416 |
+
},
|
| 4417 |
+
{
|
| 4418 |
+
"epoch": 2.465645857872006,
|
| 4419 |
+
"grad_norm": 0.9958471059799194,
|
| 4420 |
+
"learning_rate": 1.8570265239646348e-05,
|
| 4421 |
+
"loss": 0.0269,
|
| 4422 |
+
"step": 6280
|
| 4423 |
+
},
|
| 4424 |
+
{
|
| 4425 |
+
"epoch": 2.469572045543777,
|
| 4426 |
+
"grad_norm": 0.05573103204369545,
|
| 4427 |
+
"learning_rate": 1.8564448580735227e-05,
|
| 4428 |
+
"loss": 0.014,
|
| 4429 |
+
"step": 6290
|
| 4430 |
+
},
|
| 4431 |
+
{
|
| 4432 |
+
"epoch": 2.4734982332155475,
|
| 4433 |
+
"grad_norm": 2.7148032188415527,
|
| 4434 |
+
"learning_rate": 1.8558631921824107e-05,
|
| 4435 |
+
"loss": 0.1954,
|
| 4436 |
+
"step": 6300
|
| 4437 |
+
},
|
| 4438 |
+
{
|
| 4439 |
+
"epoch": 2.4774244208873184,
|
| 4440 |
+
"grad_norm": 0.3286510109901428,
|
| 4441 |
+
"learning_rate": 1.8552815262912983e-05,
|
| 4442 |
+
"loss": 0.0108,
|
| 4443 |
+
"step": 6310
|
| 4444 |
+
},
|
| 4445 |
+
{
|
| 4446 |
+
"epoch": 2.4813506085590893,
|
| 4447 |
+
"grad_norm": 0.21208466589450836,
|
| 4448 |
+
"learning_rate": 1.8546998604001863e-05,
|
| 4449 |
+
"loss": 0.0127,
|
| 4450 |
+
"step": 6320
|
| 4451 |
+
},
|
| 4452 |
+
{
|
| 4453 |
+
"epoch": 2.4852767962308597,
|
| 4454 |
+
"grad_norm": 0.19506436586380005,
|
| 4455 |
+
"learning_rate": 1.854118194509074e-05,
|
| 4456 |
+
"loss": 0.0409,
|
| 4457 |
+
"step": 6330
|
| 4458 |
+
},
|
| 4459 |
+
{
|
| 4460 |
+
"epoch": 2.4892029839026306,
|
| 4461 |
+
"grad_norm": 0.13589324057102203,
|
| 4462 |
+
"learning_rate": 1.8535365286179622e-05,
|
| 4463 |
+
"loss": 0.0542,
|
| 4464 |
+
"step": 6340
|
| 4465 |
+
},
|
| 4466 |
+
{
|
| 4467 |
+
"epoch": 2.4931291715744015,
|
| 4468 |
+
"grad_norm": 0.40425020456314087,
|
| 4469 |
+
"learning_rate": 1.8529548627268498e-05,
|
| 4470 |
+
"loss": 0.0368,
|
| 4471 |
+
"step": 6350
|
| 4472 |
+
},
|
| 4473 |
+
{
|
| 4474 |
+
"epoch": 2.497055359246172,
|
| 4475 |
+
"grad_norm": 0.1685926616191864,
|
| 4476 |
+
"learning_rate": 1.8523731968357378e-05,
|
| 4477 |
+
"loss": 0.0225,
|
| 4478 |
+
"step": 6360
|
| 4479 |
+
},
|
| 4480 |
+
{
|
| 4481 |
+
"epoch": 2.500981546917943,
|
| 4482 |
+
"grad_norm": 0.09222166985273361,
|
| 4483 |
+
"learning_rate": 1.8517915309446254e-05,
|
| 4484 |
+
"loss": 0.0819,
|
| 4485 |
+
"step": 6370
|
| 4486 |
+
},
|
| 4487 |
+
{
|
| 4488 |
+
"epoch": 2.5049077345897133,
|
| 4489 |
+
"grad_norm": 0.01848895661532879,
|
| 4490 |
+
"learning_rate": 1.8512098650535134e-05,
|
| 4491 |
+
"loss": 0.0429,
|
| 4492 |
+
"step": 6380
|
| 4493 |
+
},
|
| 4494 |
+
{
|
| 4495 |
+
"epoch": 2.508833922261484,
|
| 4496 |
+
"grad_norm": 0.4906970262527466,
|
| 4497 |
+
"learning_rate": 1.8506281991624013e-05,
|
| 4498 |
+
"loss": 0.0381,
|
| 4499 |
+
"step": 6390
|
| 4500 |
+
},
|
| 4501 |
+
{
|
| 4502 |
+
"epoch": 2.5127601099332546,
|
| 4503 |
+
"grad_norm": 0.23962044715881348,
|
| 4504 |
+
"learning_rate": 1.8500465332712893e-05,
|
| 4505 |
+
"loss": 0.0546,
|
| 4506 |
+
"step": 6400
|
| 4507 |
+
},
|
| 4508 |
+
{
|
| 4509 |
+
"epoch": 2.5166862976050255,
|
| 4510 |
+
"grad_norm": 0.09415103495121002,
|
| 4511 |
+
"learning_rate": 1.849464867380177e-05,
|
| 4512 |
+
"loss": 0.0261,
|
| 4513 |
+
"step": 6410
|
| 4514 |
+
},
|
| 4515 |
+
{
|
| 4516 |
+
"epoch": 2.5206124852767964,
|
| 4517 |
+
"grad_norm": 0.001341794733889401,
|
| 4518 |
+
"learning_rate": 1.848883201489065e-05,
|
| 4519 |
+
"loss": 0.0195,
|
| 4520 |
+
"step": 6420
|
| 4521 |
+
},
|
| 4522 |
+
{
|
| 4523 |
+
"epoch": 2.524538672948567,
|
| 4524 |
+
"grad_norm": 0.0170123390853405,
|
| 4525 |
+
"learning_rate": 1.8483015355979528e-05,
|
| 4526 |
+
"loss": 0.0129,
|
| 4527 |
+
"step": 6430
|
| 4528 |
+
},
|
| 4529 |
+
{
|
| 4530 |
+
"epoch": 2.5284648606203377,
|
| 4531 |
+
"grad_norm": 0.1249653771519661,
|
| 4532 |
+
"learning_rate": 1.8477198697068404e-05,
|
| 4533 |
+
"loss": 0.1337,
|
| 4534 |
+
"step": 6440
|
| 4535 |
+
},
|
| 4536 |
+
{
|
| 4537 |
+
"epoch": 2.5323910482921086,
|
| 4538 |
+
"grad_norm": 2.9738686084747314,
|
| 4539 |
+
"learning_rate": 1.8471382038157284e-05,
|
| 4540 |
+
"loss": 0.0164,
|
| 4541 |
+
"step": 6450
|
| 4542 |
+
},
|
| 4543 |
+
{
|
| 4544 |
+
"epoch": 2.536317235963879,
|
| 4545 |
+
"grad_norm": 0.08162163943052292,
|
| 4546 |
+
"learning_rate": 1.8465565379246164e-05,
|
| 4547 |
+
"loss": 0.0469,
|
| 4548 |
+
"step": 6460
|
| 4549 |
+
},
|
| 4550 |
+
{
|
| 4551 |
+
"epoch": 2.54024342363565,
|
| 4552 |
+
"grad_norm": 10.08042049407959,
|
| 4553 |
+
"learning_rate": 1.845974872033504e-05,
|
| 4554 |
+
"loss": 0.0969,
|
| 4555 |
+
"step": 6470
|
| 4556 |
+
},
|
| 4557 |
+
{
|
| 4558 |
+
"epoch": 2.5441696113074204,
|
| 4559 |
+
"grad_norm": 3.968355178833008,
|
| 4560 |
+
"learning_rate": 1.845393206142392e-05,
|
| 4561 |
+
"loss": 0.0477,
|
| 4562 |
+
"step": 6480
|
| 4563 |
+
},
|
| 4564 |
+
{
|
| 4565 |
+
"epoch": 2.5480957989791913,
|
| 4566 |
+
"grad_norm": 0.8283434510231018,
|
| 4567 |
+
"learning_rate": 1.84481154025128e-05,
|
| 4568 |
+
"loss": 0.0268,
|
| 4569 |
+
"step": 6490
|
| 4570 |
+
},
|
| 4571 |
+
{
|
| 4572 |
+
"epoch": 2.5520219866509617,
|
| 4573 |
+
"grad_norm": 0.34472590684890747,
|
| 4574 |
+
"learning_rate": 1.8442298743601675e-05,
|
| 4575 |
+
"loss": 0.0178,
|
| 4576 |
+
"step": 6500
|
| 4577 |
+
},
|
| 4578 |
+
{
|
| 4579 |
+
"epoch": 2.5559481743227326,
|
| 4580 |
+
"grad_norm": 0.5678462982177734,
|
| 4581 |
+
"learning_rate": 1.8436482084690555e-05,
|
| 4582 |
+
"loss": 0.0315,
|
| 4583 |
+
"step": 6510
|
| 4584 |
+
},
|
| 4585 |
+
{
|
| 4586 |
+
"epoch": 2.5598743619945035,
|
| 4587 |
+
"grad_norm": 0.07179449498653412,
|
| 4588 |
+
"learning_rate": 1.8430665425779434e-05,
|
| 4589 |
+
"loss": 0.0413,
|
| 4590 |
+
"step": 6520
|
| 4591 |
+
},
|
| 4592 |
+
{
|
| 4593 |
+
"epoch": 2.563800549666274,
|
| 4594 |
+
"grad_norm": 0.026784837245941162,
|
| 4595 |
+
"learning_rate": 1.8424848766868314e-05,
|
| 4596 |
+
"loss": 0.1364,
|
| 4597 |
+
"step": 6530
|
| 4598 |
+
},
|
| 4599 |
+
{
|
| 4600 |
+
"epoch": 2.567726737338045,
|
| 4601 |
+
"grad_norm": 0.19193647801876068,
|
| 4602 |
+
"learning_rate": 1.841903210795719e-05,
|
| 4603 |
+
"loss": 0.0496,
|
| 4604 |
+
"step": 6540
|
| 4605 |
+
},
|
| 4606 |
+
{
|
| 4607 |
+
"epoch": 2.5716529250098157,
|
| 4608 |
+
"grad_norm": 4.466202735900879,
|
| 4609 |
+
"learning_rate": 1.841321544904607e-05,
|
| 4610 |
+
"loss": 0.0348,
|
| 4611 |
+
"step": 6550
|
| 4612 |
+
},
|
| 4613 |
+
{
|
| 4614 |
+
"epoch": 2.575579112681586,
|
| 4615 |
+
"grad_norm": 9.496248245239258,
|
| 4616 |
+
"learning_rate": 1.8407398790134946e-05,
|
| 4617 |
+
"loss": 0.0353,
|
| 4618 |
+
"step": 6560
|
| 4619 |
+
},
|
| 4620 |
+
{
|
| 4621 |
+
"epoch": 2.579505300353357,
|
| 4622 |
+
"grad_norm": 0.7381163239479065,
|
| 4623 |
+
"learning_rate": 1.840158213122383e-05,
|
| 4624 |
+
"loss": 0.014,
|
| 4625 |
+
"step": 6570
|
| 4626 |
+
},
|
| 4627 |
+
{
|
| 4628 |
+
"epoch": 2.5834314880251275,
|
| 4629 |
+
"grad_norm": 3.6246681213378906,
|
| 4630 |
+
"learning_rate": 1.8395765472312705e-05,
|
| 4631 |
+
"loss": 0.0191,
|
| 4632 |
+
"step": 6580
|
| 4633 |
+
},
|
| 4634 |
+
{
|
| 4635 |
+
"epoch": 2.5873576756968983,
|
| 4636 |
+
"grad_norm": 0.11710884422063828,
|
| 4637 |
+
"learning_rate": 1.8389948813401585e-05,
|
| 4638 |
+
"loss": 0.0351,
|
| 4639 |
+
"step": 6590
|
| 4640 |
+
},
|
| 4641 |
+
{
|
| 4642 |
+
"epoch": 2.591283863368669,
|
| 4643 |
+
"grad_norm": 3.1331663131713867,
|
| 4644 |
+
"learning_rate": 1.838413215449046e-05,
|
| 4645 |
+
"loss": 0.0189,
|
| 4646 |
+
"step": 6600
|
| 4647 |
+
},
|
| 4648 |
+
{
|
| 4649 |
+
"epoch": 2.5952100510404397,
|
| 4650 |
+
"grad_norm": 0.0657317191362381,
|
| 4651 |
+
"learning_rate": 1.837831549557934e-05,
|
| 4652 |
+
"loss": 0.0236,
|
| 4653 |
+
"step": 6610
|
| 4654 |
+
},
|
| 4655 |
+
{
|
| 4656 |
+
"epoch": 2.5991362387122106,
|
| 4657 |
+
"grad_norm": 0.33908069133758545,
|
| 4658 |
+
"learning_rate": 1.837249883666822e-05,
|
| 4659 |
+
"loss": 0.1141,
|
| 4660 |
+
"step": 6620
|
| 4661 |
+
},
|
| 4662 |
+
{
|
| 4663 |
+
"epoch": 2.603062426383981,
|
| 4664 |
+
"grad_norm": 0.7466123700141907,
|
| 4665 |
+
"learning_rate": 1.8366682177757097e-05,
|
| 4666 |
+
"loss": 0.0651,
|
| 4667 |
+
"step": 6630
|
| 4668 |
+
},
|
| 4669 |
+
{
|
| 4670 |
+
"epoch": 2.606988614055752,
|
| 4671 |
+
"grad_norm": 0.23283395171165466,
|
| 4672 |
+
"learning_rate": 1.8360865518845976e-05,
|
| 4673 |
+
"loss": 0.0085,
|
| 4674 |
+
"step": 6640
|
| 4675 |
+
},
|
| 4676 |
+
{
|
| 4677 |
+
"epoch": 2.6109148017275228,
|
| 4678 |
+
"grad_norm": 0.07894974946975708,
|
| 4679 |
+
"learning_rate": 1.8355048859934856e-05,
|
| 4680 |
+
"loss": 0.0215,
|
| 4681 |
+
"step": 6650
|
| 4682 |
+
},
|
| 4683 |
+
{
|
| 4684 |
+
"epoch": 2.614840989399293,
|
| 4685 |
+
"grad_norm": 0.1452864557504654,
|
| 4686 |
+
"learning_rate": 1.8349232201023735e-05,
|
| 4687 |
+
"loss": 0.0273,
|
| 4688 |
+
"step": 6660
|
| 4689 |
+
},
|
| 4690 |
+
{
|
| 4691 |
+
"epoch": 2.618767177071064,
|
| 4692 |
+
"grad_norm": 0.2596105635166168,
|
| 4693 |
+
"learning_rate": 1.834341554211261e-05,
|
| 4694 |
+
"loss": 0.048,
|
| 4695 |
+
"step": 6670
|
| 4696 |
+
},
|
| 4697 |
+
{
|
| 4698 |
+
"epoch": 2.6226933647428345,
|
| 4699 |
+
"grad_norm": 0.21748505532741547,
|
| 4700 |
+
"learning_rate": 1.833759888320149e-05,
|
| 4701 |
+
"loss": 0.018,
|
| 4702 |
+
"step": 6680
|
| 4703 |
+
},
|
| 4704 |
+
{
|
| 4705 |
+
"epoch": 2.6266195524146054,
|
| 4706 |
+
"grad_norm": 0.19484226405620575,
|
| 4707 |
+
"learning_rate": 1.8331782224290367e-05,
|
| 4708 |
+
"loss": 0.1591,
|
| 4709 |
+
"step": 6690
|
| 4710 |
+
},
|
| 4711 |
+
{
|
| 4712 |
+
"epoch": 2.630545740086376,
|
| 4713 |
+
"grad_norm": 5.54498291015625,
|
| 4714 |
+
"learning_rate": 1.8325965565379247e-05,
|
| 4715 |
+
"loss": 0.182,
|
| 4716 |
+
"step": 6700
|
| 4717 |
+
},
|
| 4718 |
+
{
|
| 4719 |
+
"epoch": 2.6344719277581468,
|
| 4720 |
+
"grad_norm": 0.01276903785765171,
|
| 4721 |
+
"learning_rate": 1.8320148906468127e-05,
|
| 4722 |
+
"loss": 0.0153,
|
| 4723 |
+
"step": 6710
|
| 4724 |
+
},
|
| 4725 |
+
{
|
| 4726 |
+
"epoch": 2.6383981154299176,
|
| 4727 |
+
"grad_norm": 0.45068636536598206,
|
| 4728 |
+
"learning_rate": 1.8314332247557006e-05,
|
| 4729 |
+
"loss": 0.1394,
|
| 4730 |
+
"step": 6720
|
| 4731 |
+
},
|
| 4732 |
+
{
|
| 4733 |
+
"epoch": 2.642324303101688,
|
| 4734 |
+
"grad_norm": 3.1541709899902344,
|
| 4735 |
+
"learning_rate": 1.8308515588645882e-05,
|
| 4736 |
+
"loss": 0.0279,
|
| 4737 |
+
"step": 6730
|
| 4738 |
+
},
|
| 4739 |
+
{
|
| 4740 |
+
"epoch": 2.646250490773459,
|
| 4741 |
+
"grad_norm": 0.3716357946395874,
|
| 4742 |
+
"learning_rate": 1.8302698929734762e-05,
|
| 4743 |
+
"loss": 0.0282,
|
| 4744 |
+
"step": 6740
|
| 4745 |
+
},
|
| 4746 |
+
{
|
| 4747 |
+
"epoch": 2.65017667844523,
|
| 4748 |
+
"grad_norm": 0.21294966340065002,
|
| 4749 |
+
"learning_rate": 1.8296882270823638e-05,
|
| 4750 |
+
"loss": 0.0186,
|
| 4751 |
+
"step": 6750
|
| 4752 |
+
},
|
| 4753 |
+
{
|
| 4754 |
+
"epoch": 2.6541028661170003,
|
| 4755 |
+
"grad_norm": 0.6643614172935486,
|
| 4756 |
+
"learning_rate": 1.829106561191252e-05,
|
| 4757 |
+
"loss": 0.012,
|
| 4758 |
+
"step": 6760
|
| 4759 |
+
},
|
| 4760 |
+
{
|
| 4761 |
+
"epoch": 2.658029053788771,
|
| 4762 |
+
"grad_norm": 0.9538233876228333,
|
| 4763 |
+
"learning_rate": 1.8285248953001397e-05,
|
| 4764 |
+
"loss": 0.0145,
|
| 4765 |
+
"step": 6770
|
| 4766 |
+
},
|
| 4767 |
+
{
|
| 4768 |
+
"epoch": 2.661955241460542,
|
| 4769 |
+
"grad_norm": 20.805286407470703,
|
| 4770 |
+
"learning_rate": 1.8279432294090277e-05,
|
| 4771 |
+
"loss": 0.0548,
|
| 4772 |
+
"step": 6780
|
| 4773 |
+
},
|
| 4774 |
+
{
|
| 4775 |
+
"epoch": 2.6658814291323125,
|
| 4776 |
+
"grad_norm": 0.4652757942676544,
|
| 4777 |
+
"learning_rate": 1.8273615635179153e-05,
|
| 4778 |
+
"loss": 0.0106,
|
| 4779 |
+
"step": 6790
|
| 4780 |
+
},
|
| 4781 |
+
{
|
| 4782 |
+
"epoch": 2.669807616804083,
|
| 4783 |
+
"grad_norm": 0.9060388803482056,
|
| 4784 |
+
"learning_rate": 1.8267798976268033e-05,
|
| 4785 |
+
"loss": 0.061,
|
| 4786 |
+
"step": 6800
|
| 4787 |
+
},
|
| 4788 |
+
{
|
| 4789 |
+
"epoch": 2.673733804475854,
|
| 4790 |
+
"grad_norm": 0.3647180199623108,
|
| 4791 |
+
"learning_rate": 1.8261982317356913e-05,
|
| 4792 |
+
"loss": 0.0245,
|
| 4793 |
+
"step": 6810
|
| 4794 |
+
},
|
| 4795 |
+
{
|
| 4796 |
+
"epoch": 2.6776599921476247,
|
| 4797 |
+
"grad_norm": 0.059377431869506836,
|
| 4798 |
+
"learning_rate": 1.825616565844579e-05,
|
| 4799 |
+
"loss": 0.0269,
|
| 4800 |
+
"step": 6820
|
| 4801 |
+
},
|
| 4802 |
+
{
|
| 4803 |
+
"epoch": 2.681586179819395,
|
| 4804 |
+
"grad_norm": 0.1523413062095642,
|
| 4805 |
+
"learning_rate": 1.825034899953467e-05,
|
| 4806 |
+
"loss": 0.0628,
|
| 4807 |
+
"step": 6830
|
| 4808 |
+
},
|
| 4809 |
+
{
|
| 4810 |
+
"epoch": 2.685512367491166,
|
| 4811 |
+
"grad_norm": 1.7642574310302734,
|
| 4812 |
+
"learning_rate": 1.8244532340623548e-05,
|
| 4813 |
+
"loss": 0.233,
|
| 4814 |
+
"step": 6840
|
| 4815 |
+
},
|
| 4816 |
+
{
|
| 4817 |
+
"epoch": 2.689438555162937,
|
| 4818 |
+
"grad_norm": 0.01628730446100235,
|
| 4819 |
+
"learning_rate": 1.8238715681712428e-05,
|
| 4820 |
+
"loss": 0.0086,
|
| 4821 |
+
"step": 6850
|
| 4822 |
+
},
|
| 4823 |
+
{
|
| 4824 |
+
"epoch": 2.6933647428347074,
|
| 4825 |
+
"grad_norm": 0.4826602041721344,
|
| 4826 |
+
"learning_rate": 1.8232899022801304e-05,
|
| 4827 |
+
"loss": 0.1457,
|
| 4828 |
+
"step": 6860
|
| 4829 |
+
},
|
| 4830 |
+
{
|
| 4831 |
+
"epoch": 2.6972909305064783,
|
| 4832 |
+
"grad_norm": 0.10257962346076965,
|
| 4833 |
+
"learning_rate": 1.8227082363890183e-05,
|
| 4834 |
+
"loss": 0.0517,
|
| 4835 |
+
"step": 6870
|
| 4836 |
+
},
|
| 4837 |
+
{
|
| 4838 |
+
"epoch": 2.701217118178249,
|
| 4839 |
+
"grad_norm": 0.381256639957428,
|
| 4840 |
+
"learning_rate": 1.822126570497906e-05,
|
| 4841 |
+
"loss": 0.0267,
|
| 4842 |
+
"step": 6880
|
| 4843 |
+
},
|
| 4844 |
+
{
|
| 4845 |
+
"epoch": 2.7051433058500196,
|
| 4846 |
+
"grad_norm": 0.047871120274066925,
|
| 4847 |
+
"learning_rate": 1.821544904606794e-05,
|
| 4848 |
+
"loss": 0.0337,
|
| 4849 |
+
"step": 6890
|
| 4850 |
+
},
|
| 4851 |
+
{
|
| 4852 |
+
"epoch": 2.7090694935217905,
|
| 4853 |
+
"grad_norm": 7.451597690582275,
|
| 4854 |
+
"learning_rate": 1.820963238715682e-05,
|
| 4855 |
+
"loss": 0.075,
|
| 4856 |
+
"step": 6900
|
| 4857 |
+
},
|
| 4858 |
+
{
|
| 4859 |
+
"epoch": 2.712995681193561,
|
| 4860 |
+
"grad_norm": 2.257664680480957,
|
| 4861 |
+
"learning_rate": 1.82038157282457e-05,
|
| 4862 |
+
"loss": 0.0277,
|
| 4863 |
+
"step": 6910
|
| 4864 |
+
},
|
| 4865 |
+
{
|
| 4866 |
+
"epoch": 2.716921868865332,
|
| 4867 |
+
"grad_norm": 1.1934517621994019,
|
| 4868 |
+
"learning_rate": 1.8197999069334575e-05,
|
| 4869 |
+
"loss": 0.0732,
|
| 4870 |
+
"step": 6920
|
| 4871 |
+
},
|
| 4872 |
+
{
|
| 4873 |
+
"epoch": 2.7208480565371023,
|
| 4874 |
+
"grad_norm": 0.8603946566581726,
|
| 4875 |
+
"learning_rate": 1.8192182410423454e-05,
|
| 4876 |
+
"loss": 0.0244,
|
| 4877 |
+
"step": 6930
|
| 4878 |
+
},
|
| 4879 |
+
{
|
| 4880 |
+
"epoch": 2.724774244208873,
|
| 4881 |
+
"grad_norm": 0.07749401032924652,
|
| 4882 |
+
"learning_rate": 1.8186365751512334e-05,
|
| 4883 |
+
"loss": 0.1541,
|
| 4884 |
+
"step": 6940
|
| 4885 |
+
},
|
| 4886 |
+
{
|
| 4887 |
+
"epoch": 2.728700431880644,
|
| 4888 |
+
"grad_norm": 0.24039405584335327,
|
| 4889 |
+
"learning_rate": 1.8180549092601213e-05,
|
| 4890 |
+
"loss": 0.0192,
|
| 4891 |
+
"step": 6950
|
| 4892 |
+
},
|
| 4893 |
+
{
|
| 4894 |
+
"epoch": 2.7326266195524145,
|
| 4895 |
+
"grad_norm": 0.30402588844299316,
|
| 4896 |
+
"learning_rate": 1.817473243369009e-05,
|
| 4897 |
+
"loss": 0.0098,
|
| 4898 |
+
"step": 6960
|
| 4899 |
+
},
|
| 4900 |
+
{
|
| 4901 |
+
"epoch": 2.7365528072241854,
|
| 4902 |
+
"grad_norm": 0.09738530963659286,
|
| 4903 |
+
"learning_rate": 1.816891577477897e-05,
|
| 4904 |
+
"loss": 0.0333,
|
| 4905 |
+
"step": 6970
|
| 4906 |
+
},
|
| 4907 |
+
{
|
| 4908 |
+
"epoch": 2.7404789948959563,
|
| 4909 |
+
"grad_norm": 0.01483571995049715,
|
| 4910 |
+
"learning_rate": 1.8163099115867845e-05,
|
| 4911 |
+
"loss": 0.0775,
|
| 4912 |
+
"step": 6980
|
| 4913 |
+
},
|
| 4914 |
+
{
|
| 4915 |
+
"epoch": 2.7444051825677267,
|
| 4916 |
+
"grad_norm": 2.90130352973938,
|
| 4917 |
+
"learning_rate": 1.8157282456956725e-05,
|
| 4918 |
+
"loss": 0.0182,
|
| 4919 |
+
"step": 6990
|
| 4920 |
+
},
|
| 4921 |
+
{
|
| 4922 |
+
"epoch": 2.7483313702394976,
|
| 4923 |
+
"grad_norm": 13.457353591918945,
|
| 4924 |
+
"learning_rate": 1.8151465798045605e-05,
|
| 4925 |
+
"loss": 0.0223,
|
| 4926 |
+
"step": 7000
|
| 4927 |
+
},
|
| 4928 |
+
{
|
| 4929 |
+
"epoch": 2.752257557911268,
|
| 4930 |
+
"grad_norm": 0.021053476259112358,
|
| 4931 |
+
"learning_rate": 1.814564913913448e-05,
|
| 4932 |
+
"loss": 0.0243,
|
| 4933 |
+
"step": 7010
|
| 4934 |
+
},
|
| 4935 |
+
{
|
| 4936 |
+
"epoch": 2.756183745583039,
|
| 4937 |
+
"grad_norm": 1.2639825344085693,
|
| 4938 |
+
"learning_rate": 1.813983248022336e-05,
|
| 4939 |
+
"loss": 0.044,
|
| 4940 |
+
"step": 7020
|
| 4941 |
+
},
|
| 4942 |
+
{
|
| 4943 |
+
"epoch": 2.7601099332548094,
|
| 4944 |
+
"grad_norm": 1.1557574272155762,
|
| 4945 |
+
"learning_rate": 1.813401582131224e-05,
|
| 4946 |
+
"loss": 0.1094,
|
| 4947 |
+
"step": 7030
|
| 4948 |
+
},
|
| 4949 |
+
{
|
| 4950 |
+
"epoch": 2.7640361209265802,
|
| 4951 |
+
"grad_norm": 0.021884240210056305,
|
| 4952 |
+
"learning_rate": 1.812819916240112e-05,
|
| 4953 |
+
"loss": 0.0347,
|
| 4954 |
+
"step": 7040
|
| 4955 |
+
},
|
| 4956 |
+
{
|
| 4957 |
+
"epoch": 2.767962308598351,
|
| 4958 |
+
"grad_norm": 0.09900932759046555,
|
| 4959 |
+
"learning_rate": 1.8122382503489996e-05,
|
| 4960 |
+
"loss": 0.0331,
|
| 4961 |
+
"step": 7050
|
| 4962 |
+
},
|
| 4963 |
+
{
|
| 4964 |
+
"epoch": 2.7718884962701216,
|
| 4965 |
+
"grad_norm": 0.12387429177761078,
|
| 4966 |
+
"learning_rate": 1.8116565844578876e-05,
|
| 4967 |
+
"loss": 0.0243,
|
| 4968 |
+
"step": 7060
|
| 4969 |
+
},
|
| 4970 |
+
{
|
| 4971 |
+
"epoch": 2.7758146839418925,
|
| 4972 |
+
"grad_norm": 0.13594873249530792,
|
| 4973 |
+
"learning_rate": 1.8110749185667752e-05,
|
| 4974 |
+
"loss": 0.1515,
|
| 4975 |
+
"step": 7070
|
| 4976 |
+
},
|
| 4977 |
+
{
|
| 4978 |
+
"epoch": 2.7797408716136633,
|
| 4979 |
+
"grad_norm": 0.7326244711875916,
|
| 4980 |
+
"learning_rate": 1.8104932526756635e-05,
|
| 4981 |
+
"loss": 0.0394,
|
| 4982 |
+
"step": 7080
|
| 4983 |
+
},
|
| 4984 |
+
{
|
| 4985 |
+
"epoch": 2.783667059285434,
|
| 4986 |
+
"grad_norm": 1.9351961612701416,
|
| 4987 |
+
"learning_rate": 1.809911586784551e-05,
|
| 4988 |
+
"loss": 0.0069,
|
| 4989 |
+
"step": 7090
|
| 4990 |
+
},
|
| 4991 |
+
{
|
| 4992 |
+
"epoch": 2.7875932469572047,
|
| 4993 |
+
"grad_norm": 0.10082808881998062,
|
| 4994 |
+
"learning_rate": 1.809329920893439e-05,
|
| 4995 |
+
"loss": 0.024,
|
| 4996 |
+
"step": 7100
|
| 4997 |
+
},
|
| 4998 |
+
{
|
| 4999 |
+
"epoch": 2.791519434628975,
|
| 5000 |
+
"grad_norm": 0.19662164151668549,
|
| 5001 |
+
"learning_rate": 1.8087482550023267e-05,
|
| 5002 |
+
"loss": 0.198,
|
| 5003 |
+
"step": 7110
|
| 5004 |
+
},
|
| 5005 |
+
{
|
| 5006 |
+
"epoch": 2.795445622300746,
|
| 5007 |
+
"grad_norm": 0.1136908009648323,
|
| 5008 |
+
"learning_rate": 1.8081665891112146e-05,
|
| 5009 |
+
"loss": 0.1621,
|
| 5010 |
+
"step": 7120
|
| 5011 |
+
},
|
| 5012 |
+
{
|
| 5013 |
+
"epoch": 2.7993718099725164,
|
| 5014 |
+
"grad_norm": 1.4741579294204712,
|
| 5015 |
+
"learning_rate": 1.8075849232201026e-05,
|
| 5016 |
+
"loss": 0.0566,
|
| 5017 |
+
"step": 7130
|
| 5018 |
+
},
|
| 5019 |
+
{
|
| 5020 |
+
"epoch": 2.8032979976442873,
|
| 5021 |
+
"grad_norm": 0.33349961042404175,
|
| 5022 |
+
"learning_rate": 1.8070032573289906e-05,
|
| 5023 |
+
"loss": 0.1354,
|
| 5024 |
+
"step": 7140
|
| 5025 |
+
},
|
| 5026 |
+
{
|
| 5027 |
+
"epoch": 2.807224185316058,
|
| 5028 |
+
"grad_norm": 5.291731357574463,
|
| 5029 |
+
"learning_rate": 1.8064215914378782e-05,
|
| 5030 |
+
"loss": 0.0225,
|
| 5031 |
+
"step": 7150
|
| 5032 |
+
},
|
| 5033 |
+
{
|
| 5034 |
+
"epoch": 2.8111503729878287,
|
| 5035 |
+
"grad_norm": 0.2322790026664734,
|
| 5036 |
+
"learning_rate": 1.805839925546766e-05,
|
| 5037 |
+
"loss": 0.0256,
|
| 5038 |
+
"step": 7160
|
| 5039 |
+
},
|
| 5040 |
+
{
|
| 5041 |
+
"epoch": 2.8150765606595995,
|
| 5042 |
+
"grad_norm": 1.0785599946975708,
|
| 5043 |
+
"learning_rate": 1.805258259655654e-05,
|
| 5044 |
+
"loss": 0.032,
|
| 5045 |
+
"step": 7170
|
| 5046 |
+
},
|
| 5047 |
+
{
|
| 5048 |
+
"epoch": 2.8190027483313704,
|
| 5049 |
+
"grad_norm": 0.11029823869466782,
|
| 5050 |
+
"learning_rate": 1.8046765937645417e-05,
|
| 5051 |
+
"loss": 0.1076,
|
| 5052 |
+
"step": 7180
|
| 5053 |
+
},
|
| 5054 |
+
{
|
| 5055 |
+
"epoch": 2.822928936003141,
|
| 5056 |
+
"grad_norm": 0.49343523383140564,
|
| 5057 |
+
"learning_rate": 1.8040949278734297e-05,
|
| 5058 |
+
"loss": 0.0229,
|
| 5059 |
+
"step": 7190
|
| 5060 |
+
},
|
| 5061 |
+
{
|
| 5062 |
+
"epoch": 2.8268551236749118,
|
| 5063 |
+
"grad_norm": 0.029380250722169876,
|
| 5064 |
+
"learning_rate": 1.8035132619823173e-05,
|
| 5065 |
+
"loss": 0.0611,
|
| 5066 |
+
"step": 7200
|
| 5067 |
+
},
|
| 5068 |
+
{
|
| 5069 |
+
"epoch": 2.830781311346682,
|
| 5070 |
+
"grad_norm": 0.10703462362289429,
|
| 5071 |
+
"learning_rate": 1.8029315960912053e-05,
|
| 5072 |
+
"loss": 0.0806,
|
| 5073 |
+
"step": 7210
|
| 5074 |
+
},
|
| 5075 |
+
{
|
| 5076 |
+
"epoch": 2.834707499018453,
|
| 5077 |
+
"grad_norm": 0.20559871196746826,
|
| 5078 |
+
"learning_rate": 1.8023499302000932e-05,
|
| 5079 |
+
"loss": 0.031,
|
| 5080 |
+
"step": 7220
|
| 5081 |
+
},
|
| 5082 |
+
{
|
| 5083 |
+
"epoch": 2.8386336866902235,
|
| 5084 |
+
"grad_norm": 0.46448788046836853,
|
| 5085 |
+
"learning_rate": 1.8017682643089812e-05,
|
| 5086 |
+
"loss": 0.0935,
|
| 5087 |
+
"step": 7230
|
| 5088 |
+
},
|
| 5089 |
+
{
|
| 5090 |
+
"epoch": 2.8425598743619944,
|
| 5091 |
+
"grad_norm": 0.01558899786323309,
|
| 5092 |
+
"learning_rate": 1.8011865984178688e-05,
|
| 5093 |
+
"loss": 0.0136,
|
| 5094 |
+
"step": 7240
|
| 5095 |
+
},
|
| 5096 |
+
{
|
| 5097 |
+
"epoch": 2.8464860620337653,
|
| 5098 |
+
"grad_norm": 0.20479479432106018,
|
| 5099 |
+
"learning_rate": 1.8006049325267568e-05,
|
| 5100 |
+
"loss": 0.0703,
|
| 5101 |
+
"step": 7250
|
| 5102 |
+
},
|
| 5103 |
+
{
|
| 5104 |
+
"epoch": 2.8504122497055357,
|
| 5105 |
+
"grad_norm": 0.7157366871833801,
|
| 5106 |
+
"learning_rate": 1.8000232666356444e-05,
|
| 5107 |
+
"loss": 0.0235,
|
| 5108 |
+
"step": 7260
|
| 5109 |
+
},
|
| 5110 |
+
{
|
| 5111 |
+
"epoch": 2.8543384373773066,
|
| 5112 |
+
"grad_norm": 1.7429962158203125,
|
| 5113 |
+
"learning_rate": 1.7994416007445327e-05,
|
| 5114 |
+
"loss": 0.0246,
|
| 5115 |
+
"step": 7270
|
| 5116 |
+
},
|
| 5117 |
+
{
|
| 5118 |
+
"epoch": 2.8582646250490775,
|
| 5119 |
+
"grad_norm": 0.028108160942792892,
|
| 5120 |
+
"learning_rate": 1.7988599348534203e-05,
|
| 5121 |
+
"loss": 0.0054,
|
| 5122 |
+
"step": 7280
|
| 5123 |
+
},
|
| 5124 |
+
{
|
| 5125 |
+
"epoch": 2.862190812720848,
|
| 5126 |
+
"grad_norm": 11.914875030517578,
|
| 5127 |
+
"learning_rate": 1.7982782689623083e-05,
|
| 5128 |
+
"loss": 0.0368,
|
| 5129 |
+
"step": 7290
|
| 5130 |
+
},
|
| 5131 |
+
{
|
| 5132 |
+
"epoch": 2.866117000392619,
|
| 5133 |
+
"grad_norm": 0.10080993920564651,
|
| 5134 |
+
"learning_rate": 1.797696603071196e-05,
|
| 5135 |
+
"loss": 0.0202,
|
| 5136 |
+
"step": 7300
|
| 5137 |
+
},
|
| 5138 |
+
{
|
| 5139 |
+
"epoch": 2.8700431880643897,
|
| 5140 |
+
"grad_norm": 0.29270097613334656,
|
| 5141 |
+
"learning_rate": 1.797114937180084e-05,
|
| 5142 |
+
"loss": 0.1268,
|
| 5143 |
+
"step": 7310
|
| 5144 |
+
},
|
| 5145 |
+
{
|
| 5146 |
+
"epoch": 2.87396937573616,
|
| 5147 |
+
"grad_norm": 0.0075101228430867195,
|
| 5148 |
+
"learning_rate": 1.7965332712889718e-05,
|
| 5149 |
+
"loss": 0.0607,
|
| 5150 |
+
"step": 7320
|
| 5151 |
+
},
|
| 5152 |
+
{
|
| 5153 |
+
"epoch": 2.8778955634079306,
|
| 5154 |
+
"grad_norm": 0.14158380031585693,
|
| 5155 |
+
"learning_rate": 1.7959516053978598e-05,
|
| 5156 |
+
"loss": 0.1446,
|
| 5157 |
+
"step": 7330
|
| 5158 |
+
},
|
| 5159 |
+
{
|
| 5160 |
+
"epoch": 2.8818217510797015,
|
| 5161 |
+
"grad_norm": 0.2636829614639282,
|
| 5162 |
+
"learning_rate": 1.7953699395067474e-05,
|
| 5163 |
+
"loss": 0.0527,
|
| 5164 |
+
"step": 7340
|
| 5165 |
+
},
|
| 5166 |
+
{
|
| 5167 |
+
"epoch": 2.8857479387514724,
|
| 5168 |
+
"grad_norm": 0.23100285232067108,
|
| 5169 |
+
"learning_rate": 1.7947882736156354e-05,
|
| 5170 |
+
"loss": 0.019,
|
| 5171 |
+
"step": 7350
|
| 5172 |
+
},
|
| 5173 |
+
{
|
| 5174 |
+
"epoch": 2.889674126423243,
|
| 5175 |
+
"grad_norm": 0.03932677209377289,
|
| 5176 |
+
"learning_rate": 1.7942066077245233e-05,
|
| 5177 |
+
"loss": 0.0273,
|
| 5178 |
+
"step": 7360
|
| 5179 |
+
},
|
| 5180 |
+
{
|
| 5181 |
+
"epoch": 2.8936003140950137,
|
| 5182 |
+
"grad_norm": 0.10466849058866501,
|
| 5183 |
+
"learning_rate": 1.793624941833411e-05,
|
| 5184 |
+
"loss": 0.0405,
|
| 5185 |
+
"step": 7370
|
| 5186 |
+
},
|
| 5187 |
+
{
|
| 5188 |
+
"epoch": 2.8975265017667846,
|
| 5189 |
+
"grad_norm": 0.0056775761768221855,
|
| 5190 |
+
"learning_rate": 1.793043275942299e-05,
|
| 5191 |
+
"loss": 0.0364,
|
| 5192 |
+
"step": 7380
|
| 5193 |
+
},
|
| 5194 |
+
{
|
| 5195 |
+
"epoch": 2.901452689438555,
|
| 5196 |
+
"grad_norm": 0.6241567730903625,
|
| 5197 |
+
"learning_rate": 1.7924616100511865e-05,
|
| 5198 |
+
"loss": 0.034,
|
| 5199 |
+
"step": 7390
|
| 5200 |
+
},
|
| 5201 |
+
{
|
| 5202 |
+
"epoch": 2.905378877110326,
|
| 5203 |
+
"grad_norm": 0.08314551413059235,
|
| 5204 |
+
"learning_rate": 1.7918799441600745e-05,
|
| 5205 |
+
"loss": 0.0161,
|
| 5206 |
+
"step": 7400
|
| 5207 |
+
},
|
| 5208 |
+
{
|
| 5209 |
+
"epoch": 2.909305064782097,
|
| 5210 |
+
"grad_norm": 2.2995920181274414,
|
| 5211 |
+
"learning_rate": 1.7912982782689624e-05,
|
| 5212 |
+
"loss": 0.0184,
|
| 5213 |
+
"step": 7410
|
| 5214 |
+
},
|
| 5215 |
+
{
|
| 5216 |
+
"epoch": 2.9132312524538673,
|
| 5217 |
+
"grad_norm": 0.13308770954608917,
|
| 5218 |
+
"learning_rate": 1.7907166123778504e-05,
|
| 5219 |
+
"loss": 0.0711,
|
| 5220 |
+
"step": 7420
|
| 5221 |
+
},
|
| 5222 |
+
{
|
| 5223 |
+
"epoch": 2.917157440125638,
|
| 5224 |
+
"grad_norm": 0.16322386264801025,
|
| 5225 |
+
"learning_rate": 1.790134946486738e-05,
|
| 5226 |
+
"loss": 0.0487,
|
| 5227 |
+
"step": 7430
|
| 5228 |
+
},
|
| 5229 |
+
{
|
| 5230 |
+
"epoch": 2.9210836277974086,
|
| 5231 |
+
"grad_norm": 10.037577629089355,
|
| 5232 |
+
"learning_rate": 1.789553280595626e-05,
|
| 5233 |
+
"loss": 0.061,
|
| 5234 |
+
"step": 7440
|
| 5235 |
+
},
|
| 5236 |
+
{
|
| 5237 |
+
"epoch": 2.9250098154691795,
|
| 5238 |
+
"grad_norm": 1.2944895029067993,
|
| 5239 |
+
"learning_rate": 1.788971614704514e-05,
|
| 5240 |
+
"loss": 0.0225,
|
| 5241 |
+
"step": 7450
|
| 5242 |
+
},
|
| 5243 |
+
{
|
| 5244 |
+
"epoch": 2.92893600314095,
|
| 5245 |
+
"grad_norm": 1.7180625200271606,
|
| 5246 |
+
"learning_rate": 1.788389948813402e-05,
|
| 5247 |
+
"loss": 0.0655,
|
| 5248 |
+
"step": 7460
|
| 5249 |
+
},
|
| 5250 |
+
{
|
| 5251 |
+
"epoch": 2.932862190812721,
|
| 5252 |
+
"grad_norm": 0.08827504515647888,
|
| 5253 |
+
"learning_rate": 1.7878082829222895e-05,
|
| 5254 |
+
"loss": 0.1432,
|
| 5255 |
+
"step": 7470
|
| 5256 |
+
},
|
| 5257 |
+
{
|
| 5258 |
+
"epoch": 2.9367883784844917,
|
| 5259 |
+
"grad_norm": 0.06459765136241913,
|
| 5260 |
+
"learning_rate": 1.7872266170311775e-05,
|
| 5261 |
+
"loss": 0.0621,
|
| 5262 |
+
"step": 7480
|
| 5263 |
+
},
|
| 5264 |
+
{
|
| 5265 |
+
"epoch": 2.940714566156262,
|
| 5266 |
+
"grad_norm": 1.7105767726898193,
|
| 5267 |
+
"learning_rate": 1.786644951140065e-05,
|
| 5268 |
+
"loss": 0.023,
|
| 5269 |
+
"step": 7490
|
| 5270 |
+
},
|
| 5271 |
+
{
|
| 5272 |
+
"epoch": 2.944640753828033,
|
| 5273 |
+
"grad_norm": 1.1304662227630615,
|
| 5274 |
+
"learning_rate": 1.786063285248953e-05,
|
| 5275 |
+
"loss": 0.0589,
|
| 5276 |
+
"step": 7500
|
| 5277 |
+
},
|
| 5278 |
+
{
|
| 5279 |
+
"epoch": 2.948566941499804,
|
| 5280 |
+
"grad_norm": 0.9976340532302856,
|
| 5281 |
+
"learning_rate": 1.785481619357841e-05,
|
| 5282 |
+
"loss": 0.0221,
|
| 5283 |
+
"step": 7510
|
| 5284 |
+
},
|
| 5285 |
+
{
|
| 5286 |
+
"epoch": 2.9524931291715744,
|
| 5287 |
+
"grad_norm": 0.015793463215231895,
|
| 5288 |
+
"learning_rate": 1.784899953466729e-05,
|
| 5289 |
+
"loss": 0.0097,
|
| 5290 |
+
"step": 7520
|
| 5291 |
+
},
|
| 5292 |
+
{
|
| 5293 |
+
"epoch": 2.9564193168433452,
|
| 5294 |
+
"grad_norm": 0.11538520455360413,
|
| 5295 |
+
"learning_rate": 1.7843182875756166e-05,
|
| 5296 |
+
"loss": 0.0384,
|
| 5297 |
+
"step": 7530
|
| 5298 |
+
},
|
| 5299 |
+
{
|
| 5300 |
+
"epoch": 2.9603455045151157,
|
| 5301 |
+
"grad_norm": 1.7094212770462036,
|
| 5302 |
+
"learning_rate": 1.7837366216845046e-05,
|
| 5303 |
+
"loss": 0.1783,
|
| 5304 |
+
"step": 7540
|
| 5305 |
+
},
|
| 5306 |
+
{
|
| 5307 |
+
"epoch": 2.9642716921868866,
|
| 5308 |
+
"grad_norm": 0.2246238887310028,
|
| 5309 |
+
"learning_rate": 1.7831549557933925e-05,
|
| 5310 |
+
"loss": 0.0187,
|
| 5311 |
+
"step": 7550
|
| 5312 |
+
},
|
| 5313 |
+
{
|
| 5314 |
+
"epoch": 2.968197879858657,
|
| 5315 |
+
"grad_norm": 11.894949913024902,
|
| 5316 |
+
"learning_rate": 1.78257328990228e-05,
|
| 5317 |
+
"loss": 0.024,
|
| 5318 |
+
"step": 7560
|
| 5319 |
+
},
|
| 5320 |
+
{
|
| 5321 |
+
"epoch": 2.972124067530428,
|
| 5322 |
+
"grad_norm": 0.056449778378009796,
|
| 5323 |
+
"learning_rate": 1.781991624011168e-05,
|
| 5324 |
+
"loss": 0.0183,
|
| 5325 |
+
"step": 7570
|
| 5326 |
+
},
|
| 5327 |
+
{
|
| 5328 |
+
"epoch": 2.976050255202199,
|
| 5329 |
+
"grad_norm": 5.282381534576416,
|
| 5330 |
+
"learning_rate": 1.7814099581200557e-05,
|
| 5331 |
+
"loss": 0.0344,
|
| 5332 |
+
"step": 7580
|
| 5333 |
+
},
|
| 5334 |
+
{
|
| 5335 |
+
"epoch": 2.9799764428739692,
|
| 5336 |
+
"grad_norm": 7.19214391708374,
|
| 5337 |
+
"learning_rate": 1.780828292228944e-05,
|
| 5338 |
+
"loss": 0.1606,
|
| 5339 |
+
"step": 7590
|
| 5340 |
+
},
|
| 5341 |
+
{
|
| 5342 |
+
"epoch": 2.98390263054574,
|
| 5343 |
+
"grad_norm": 0.2313212752342224,
|
| 5344 |
+
"learning_rate": 1.7802466263378317e-05,
|
| 5345 |
+
"loss": 0.1364,
|
| 5346 |
+
"step": 7600
|
| 5347 |
+
},
|
| 5348 |
+
{
|
| 5349 |
+
"epoch": 2.987828818217511,
|
| 5350 |
+
"grad_norm": 0.07578112930059433,
|
| 5351 |
+
"learning_rate": 1.7796649604467196e-05,
|
| 5352 |
+
"loss": 0.0148,
|
| 5353 |
+
"step": 7610
|
| 5354 |
+
},
|
| 5355 |
+
{
|
| 5356 |
+
"epoch": 2.9917550058892814,
|
| 5357 |
+
"grad_norm": 0.8685612082481384,
|
| 5358 |
+
"learning_rate": 1.7790832945556072e-05,
|
| 5359 |
+
"loss": 0.0124,
|
| 5360 |
+
"step": 7620
|
| 5361 |
+
},
|
| 5362 |
+
{
|
| 5363 |
+
"epoch": 2.9956811935610523,
|
| 5364 |
+
"grad_norm": 2.157496213912964,
|
| 5365 |
+
"learning_rate": 1.7785016286644952e-05,
|
| 5366 |
+
"loss": 0.0189,
|
| 5367 |
+
"step": 7630
|
| 5368 |
+
},
|
| 5369 |
+
{
|
| 5370 |
+
"epoch": 2.999607381232823,
|
| 5371 |
+
"grad_norm": 0.6778295040130615,
|
| 5372 |
+
"learning_rate": 1.777919962773383e-05,
|
| 5373 |
+
"loss": 0.0634,
|
| 5374 |
+
"step": 7640
|
| 5375 |
+
},
|
| 5376 |
+
{
|
| 5377 |
+
"epoch": 3.0,
|
| 5378 |
+
"eval_loss": 0.05170644447207451,
|
| 5379 |
+
"eval_runtime": 20.9195,
|
| 5380 |
+
"eval_samples_per_second": 108.224,
|
| 5381 |
+
"eval_steps_per_second": 13.528,
|
| 5382 |
+
"step": 7641
|
| 5383 |
}
|
| 5384 |
],
|
| 5385 |
"logging_steps": 10,
|
|
|
|
| 5408 |
"attributes": {}
|
| 5409 |
}
|
| 5410 |
},
|
| 5411 |
+
"total_flos": 1.607894914938768e+16,
|
| 5412 |
"train_batch_size": 8,
|
| 5413 |
"trial_name": null,
|
| 5414 |
"trial_params": null
|