Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep23_16-02-16_COE-CS-sv003/events.out.tfevents.1727107643.COE-CS-sv003.738220.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2667 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: feedback_p0.1_seed42_level2_styledirtybatch16_reverse
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# feedback_p0.1_seed42_level2_styledirtybatch16_reverse
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- total_eval_batch_size: 4
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.44.2
|
| 58 |
+
- Pytorch 2.3.1+cu121
|
| 59 |
+
- Datasets 2.19.1
|
| 60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 195665288232960.0,
|
| 4 |
+
"train_loss": 0.5137065978787556,
|
| 5 |
+
"train_runtime": 16737.1252,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.786,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.44.2"
|
| 6 |
+
}
|
runs/Sep23_16-02-16_COE-CS-sv003/events.out.tfevents.1727107643.COE-CS-sv003.738220.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfa09ee38b63abbd44b2c3582fe851aaa6297ed9dfc0ae860309e849e4c209b3
|
| 3 |
+
size 84689
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 195665288232960.0,
|
| 4 |
+
"train_loss": 0.5137065978787556,
|
| 5 |
+
"train_runtime": 16737.1252,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.786,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2667 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1869,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0005350454788657035,
|
| 13 |
+
"grad_norm": 23.14862717209723,
|
| 14 |
+
"learning_rate": 5.3475935828877005e-08,
|
| 15 |
+
"loss": 1.3341,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002675227394328518,
|
| 20 |
+
"grad_norm": 23.77620185109602,
|
| 21 |
+
"learning_rate": 2.6737967914438503e-07,
|
| 22 |
+
"loss": 1.355,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.005350454788657036,
|
| 27 |
+
"grad_norm": 14.708477613885714,
|
| 28 |
+
"learning_rate": 5.347593582887701e-07,
|
| 29 |
+
"loss": 1.3095,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008025682182985553,
|
| 34 |
+
"grad_norm": 12.246536127500569,
|
| 35 |
+
"learning_rate": 8.021390374331551e-07,
|
| 36 |
+
"loss": 1.1577,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010700909577314071,
|
| 41 |
+
"grad_norm": 9.616225734354739,
|
| 42 |
+
"learning_rate": 1.0695187165775401e-06,
|
| 43 |
+
"loss": 1.042,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01337613697164259,
|
| 48 |
+
"grad_norm": 3.4924370385559005,
|
| 49 |
+
"learning_rate": 1.3368983957219254e-06,
|
| 50 |
+
"loss": 0.9362,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.016051364365971106,
|
| 55 |
+
"grad_norm": 3.5822272920001237,
|
| 56 |
+
"learning_rate": 1.6042780748663103e-06,
|
| 57 |
+
"loss": 0.9197,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.018726591760299626,
|
| 62 |
+
"grad_norm": 2.9720674905316393,
|
| 63 |
+
"learning_rate": 1.8716577540106954e-06,
|
| 64 |
+
"loss": 0.8822,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.021401819154628143,
|
| 69 |
+
"grad_norm": 3.0124107376781093,
|
| 70 |
+
"learning_rate": 2.1390374331550802e-06,
|
| 71 |
+
"loss": 0.8698,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.024077046548956663,
|
| 76 |
+
"grad_norm": 2.963506013876851,
|
| 77 |
+
"learning_rate": 2.4064171122994653e-06,
|
| 78 |
+
"loss": 0.8525,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02675227394328518,
|
| 83 |
+
"grad_norm": 3.160528243293502,
|
| 84 |
+
"learning_rate": 2.673796791443851e-06,
|
| 85 |
+
"loss": 0.849,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.029427501337613696,
|
| 90 |
+
"grad_norm": 2.8952214901225934,
|
| 91 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 92 |
+
"loss": 0.8312,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03210272873194221,
|
| 97 |
+
"grad_norm": 3.173564660838415,
|
| 98 |
+
"learning_rate": 3.2085561497326205e-06,
|
| 99 |
+
"loss": 0.8168,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.034777956126270736,
|
| 104 |
+
"grad_norm": 3.0478716727585176,
|
| 105 |
+
"learning_rate": 3.4759358288770056e-06,
|
| 106 |
+
"loss": 0.818,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03745318352059925,
|
| 111 |
+
"grad_norm": 3.194717995617946,
|
| 112 |
+
"learning_rate": 3.7433155080213907e-06,
|
| 113 |
+
"loss": 0.7971,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04012841091492777,
|
| 118 |
+
"grad_norm": 3.1820878704526296,
|
| 119 |
+
"learning_rate": 4.010695187165775e-06,
|
| 120 |
+
"loss": 0.7929,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.042803638309256285,
|
| 125 |
+
"grad_norm": 3.228418173848044,
|
| 126 |
+
"learning_rate": 4.2780748663101604e-06,
|
| 127 |
+
"loss": 0.7792,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0454788657035848,
|
| 132 |
+
"grad_norm": 3.384522613177732,
|
| 133 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 134 |
+
"loss": 0.7775,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.048154093097913325,
|
| 139 |
+
"grad_norm": 3.183805408679174,
|
| 140 |
+
"learning_rate": 4.812834224598931e-06,
|
| 141 |
+
"loss": 0.7577,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05082932049224184,
|
| 146 |
+
"grad_norm": 3.4760481232015388,
|
| 147 |
+
"learning_rate": 5.0802139037433165e-06,
|
| 148 |
+
"loss": 0.7563,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05350454788657036,
|
| 153 |
+
"grad_norm": 3.1673853649146277,
|
| 154 |
+
"learning_rate": 5.347593582887702e-06,
|
| 155 |
+
"loss": 0.749,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.056179775280898875,
|
| 160 |
+
"grad_norm": 3.0292770505818254,
|
| 161 |
+
"learning_rate": 5.614973262032086e-06,
|
| 162 |
+
"loss": 0.7446,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.05885500267522739,
|
| 167 |
+
"grad_norm": 3.116848479877184,
|
| 168 |
+
"learning_rate": 5.882352941176471e-06,
|
| 169 |
+
"loss": 0.7439,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.061530230069555915,
|
| 174 |
+
"grad_norm": 3.2398528780308067,
|
| 175 |
+
"learning_rate": 6.149732620320856e-06,
|
| 176 |
+
"loss": 0.7466,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06420545746388442,
|
| 181 |
+
"grad_norm": 3.303341515373773,
|
| 182 |
+
"learning_rate": 6.417112299465241e-06,
|
| 183 |
+
"loss": 0.7311,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06688068485821295,
|
| 188 |
+
"grad_norm": 3.29094819560745,
|
| 189 |
+
"learning_rate": 6.684491978609626e-06,
|
| 190 |
+
"loss": 0.7417,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.06955591225254147,
|
| 195 |
+
"grad_norm": 3.0583806564933314,
|
| 196 |
+
"learning_rate": 6.951871657754011e-06,
|
| 197 |
+
"loss": 0.7215,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07223113964686999,
|
| 202 |
+
"grad_norm": 2.922761971640661,
|
| 203 |
+
"learning_rate": 7.219251336898396e-06,
|
| 204 |
+
"loss": 0.7148,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0749063670411985,
|
| 209 |
+
"grad_norm": 3.0911163153076058,
|
| 210 |
+
"learning_rate": 7.486631016042781e-06,
|
| 211 |
+
"loss": 0.7383,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07758159443552702,
|
| 216 |
+
"grad_norm": 2.8281929004877924,
|
| 217 |
+
"learning_rate": 7.754010695187166e-06,
|
| 218 |
+
"loss": 0.7043,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08025682182985554,
|
| 223 |
+
"grad_norm": 3.1040357514576953,
|
| 224 |
+
"learning_rate": 8.02139037433155e-06,
|
| 225 |
+
"loss": 0.7151,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08293204922418405,
|
| 230 |
+
"grad_norm": 3.1558916042229908,
|
| 231 |
+
"learning_rate": 8.288770053475937e-06,
|
| 232 |
+
"loss": 0.7143,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.08560727661851257,
|
| 237 |
+
"grad_norm": 2.943346250498008,
|
| 238 |
+
"learning_rate": 8.556149732620321e-06,
|
| 239 |
+
"loss": 0.7013,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08828250401284109,
|
| 244 |
+
"grad_norm": 3.00338601363791,
|
| 245 |
+
"learning_rate": 8.823529411764707e-06,
|
| 246 |
+
"loss": 0.7168,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.0909577314071696,
|
| 251 |
+
"grad_norm": 2.9568937036058505,
|
| 252 |
+
"learning_rate": 9.090909090909091e-06,
|
| 253 |
+
"loss": 0.7077,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09363295880149813,
|
| 258 |
+
"grad_norm": 3.0004482748153056,
|
| 259 |
+
"learning_rate": 9.358288770053477e-06,
|
| 260 |
+
"loss": 0.7111,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09630818619582665,
|
| 265 |
+
"grad_norm": 2.7753342166626074,
|
| 266 |
+
"learning_rate": 9.625668449197861e-06,
|
| 267 |
+
"loss": 0.7216,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09898341359015517,
|
| 272 |
+
"grad_norm": 2.9030858254206264,
|
| 273 |
+
"learning_rate": 9.893048128342247e-06,
|
| 274 |
+
"loss": 0.7118,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.10165864098448368,
|
| 279 |
+
"grad_norm": 2.685107361232292,
|
| 280 |
+
"learning_rate": 9.999921507322408e-06,
|
| 281 |
+
"loss": 0.7021,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1043338683788122,
|
| 286 |
+
"grad_norm": 2.685192038995974,
|
| 287 |
+
"learning_rate": 9.999441838772916e-06,
|
| 288 |
+
"loss": 0.6988,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.10700909577314072,
|
| 293 |
+
"grad_norm": 2.918955400249994,
|
| 294 |
+
"learning_rate": 9.99852615049999e-06,
|
| 295 |
+
"loss": 0.6967,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.10968432316746923,
|
| 300 |
+
"grad_norm": 2.869330230423005,
|
| 301 |
+
"learning_rate": 9.997174522364177e-06,
|
| 302 |
+
"loss": 0.6947,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11235955056179775,
|
| 307 |
+
"grad_norm": 2.703271557308526,
|
| 308 |
+
"learning_rate": 9.995387072245939e-06,
|
| 309 |
+
"loss": 0.7111,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.11503477795612627,
|
| 314 |
+
"grad_norm": 2.747549810108466,
|
| 315 |
+
"learning_rate": 9.993163956035381e-06,
|
| 316 |
+
"loss": 0.7059,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.11771000535045478,
|
| 321 |
+
"grad_norm": 3.111810523251162,
|
| 322 |
+
"learning_rate": 9.990505367618647e-06,
|
| 323 |
+
"loss": 0.7081,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.12038523274478331,
|
| 328 |
+
"grad_norm": 2.59798000022919,
|
| 329 |
+
"learning_rate": 9.987411538861023e-06,
|
| 330 |
+
"loss": 0.6963,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12306046013911183,
|
| 335 |
+
"grad_norm": 2.6949538130277695,
|
| 336 |
+
"learning_rate": 9.9838827395867e-06,
|
| 337 |
+
"loss": 0.6935,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.12573568753344033,
|
| 342 |
+
"grad_norm": 2.628051172115821,
|
| 343 |
+
"learning_rate": 9.979919277555247e-06,
|
| 344 |
+
"loss": 0.6869,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12841091492776885,
|
| 349 |
+
"grad_norm": 2.5260508130338133,
|
| 350 |
+
"learning_rate": 9.97552149843478e-06,
|
| 351 |
+
"loss": 0.6975,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.13108614232209737,
|
| 356 |
+
"grad_norm": 2.6307934786366896,
|
| 357 |
+
"learning_rate": 9.970689785771798e-06,
|
| 358 |
+
"loss": 0.6972,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.1337613697164259,
|
| 363 |
+
"grad_norm": 2.9060873285695155,
|
| 364 |
+
"learning_rate": 9.96542456095775e-06,
|
| 365 |
+
"loss": 0.6914,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.13643659711075443,
|
| 370 |
+
"grad_norm": 2.758259640760469,
|
| 371 |
+
"learning_rate": 9.95972628319227e-06,
|
| 372 |
+
"loss": 0.6899,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.13911182450508294,
|
| 377 |
+
"grad_norm": 2.686451625364134,
|
| 378 |
+
"learning_rate": 9.953595449443134e-06,
|
| 379 |
+
"loss": 0.6975,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.14178705189941146,
|
| 384 |
+
"grad_norm": 2.654857011678671,
|
| 385 |
+
"learning_rate": 9.947032594402917e-06,
|
| 386 |
+
"loss": 0.6882,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14446227929373998,
|
| 391 |
+
"grad_norm": 3.0168306473010813,
|
| 392 |
+
"learning_rate": 9.940038290442362e-06,
|
| 393 |
+
"loss": 0.6798,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1471375066880685,
|
| 398 |
+
"grad_norm": 2.581123619862379,
|
| 399 |
+
"learning_rate": 9.932613147560464e-06,
|
| 400 |
+
"loss": 0.6996,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.149812734082397,
|
| 405 |
+
"grad_norm": 2.5125742789046988,
|
| 406 |
+
"learning_rate": 9.924757813331256e-06,
|
| 407 |
+
"loss": 0.6792,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.15248796147672553,
|
| 412 |
+
"grad_norm": 2.6254290649886274,
|
| 413 |
+
"learning_rate": 9.916472972847353e-06,
|
| 414 |
+
"loss": 0.681,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15516318887105404,
|
| 419 |
+
"grad_norm": 2.5307860850663197,
|
| 420 |
+
"learning_rate": 9.907759348660186e-06,
|
| 421 |
+
"loss": 0.6597,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.15783841626538256,
|
| 426 |
+
"grad_norm": 2.7548412137167997,
|
| 427 |
+
"learning_rate": 9.898617700716988e-06,
|
| 428 |
+
"loss": 0.6708,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16051364365971107,
|
| 433 |
+
"grad_norm": 2.5617275751142894,
|
| 434 |
+
"learning_rate": 9.889048826294527e-06,
|
| 435 |
+
"loss": 0.6816,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1631888710540396,
|
| 440 |
+
"grad_norm": 2.454236841573611,
|
| 441 |
+
"learning_rate": 9.879053559929556e-06,
|
| 442 |
+
"loss": 0.6685,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.1658640984483681,
|
| 447 |
+
"grad_norm": 2.522665651038106,
|
| 448 |
+
"learning_rate": 9.868632773346044e-06,
|
| 449 |
+
"loss": 0.6689,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.16853932584269662,
|
| 454 |
+
"grad_norm": 2.531527428246295,
|
| 455 |
+
"learning_rate": 9.857787375379144e-06,
|
| 456 |
+
"loss": 0.6681,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17121455323702514,
|
| 461 |
+
"grad_norm": 2.4693271769445175,
|
| 462 |
+
"learning_rate": 9.84651831189593e-06,
|
| 463 |
+
"loss": 0.6616,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.17388978063135366,
|
| 468 |
+
"grad_norm": 2.537474607100158,
|
| 469 |
+
"learning_rate": 9.834826565712901e-06,
|
| 470 |
+
"loss": 0.6613,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.17656500802568217,
|
| 475 |
+
"grad_norm": 2.908331796282016,
|
| 476 |
+
"learning_rate": 9.822713156510278e-06,
|
| 477 |
+
"loss": 0.6542,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1792402354200107,
|
| 482 |
+
"grad_norm": 2.536053924127175,
|
| 483 |
+
"learning_rate": 9.81017914074306e-06,
|
| 484 |
+
"loss": 0.6596,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.1819154628143392,
|
| 489 |
+
"grad_norm": 2.392506050203404,
|
| 490 |
+
"learning_rate": 9.797225611548896e-06,
|
| 491 |
+
"loss": 0.6466,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.18459069020866772,
|
| 496 |
+
"grad_norm": 2.4001855751228414,
|
| 497 |
+
"learning_rate": 9.783853698652737e-06,
|
| 498 |
+
"loss": 0.6726,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.18726591760299627,
|
| 503 |
+
"grad_norm": 2.4631052280555163,
|
| 504 |
+
"learning_rate": 9.770064568268329e-06,
|
| 505 |
+
"loss": 0.6531,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.18994114499732478,
|
| 510 |
+
"grad_norm": 2.5426722525248384,
|
| 511 |
+
"learning_rate": 9.75585942299648e-06,
|
| 512 |
+
"loss": 0.6506,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1926163723916533,
|
| 517 |
+
"grad_norm": 2.5531515576743997,
|
| 518 |
+
"learning_rate": 9.741239501720197e-06,
|
| 519 |
+
"loss": 0.6687,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.19529159978598182,
|
| 524 |
+
"grad_norm": 2.5933299113098416,
|
| 525 |
+
"learning_rate": 9.726206079496619e-06,
|
| 526 |
+
"loss": 0.649,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.19796682718031033,
|
| 531 |
+
"grad_norm": 2.556848619149725,
|
| 532 |
+
"learning_rate": 9.71076046744583e-06,
|
| 533 |
+
"loss": 0.6557,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.20064205457463885,
|
| 538 |
+
"grad_norm": 2.5209850469412944,
|
| 539 |
+
"learning_rate": 9.694904012636509e-06,
|
| 540 |
+
"loss": 0.6386,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.20331728196896737,
|
| 545 |
+
"grad_norm": 2.630494859882968,
|
| 546 |
+
"learning_rate": 9.678638097968435e-06,
|
| 547 |
+
"loss": 0.6565,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.20599250936329588,
|
| 552 |
+
"grad_norm": 2.4636175372087408,
|
| 553 |
+
"learning_rate": 9.661964142051896e-06,
|
| 554 |
+
"loss": 0.6592,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2086677367576244,
|
| 559 |
+
"grad_norm": 2.608708318283724,
|
| 560 |
+
"learning_rate": 9.644883599083959e-06,
|
| 561 |
+
"loss": 0.6462,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.21134296415195292,
|
| 566 |
+
"grad_norm": 2.4564835809094094,
|
| 567 |
+
"learning_rate": 9.627397958721638e-06,
|
| 568 |
+
"loss": 0.6303,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21401819154628143,
|
| 573 |
+
"grad_norm": 2.628178024205104,
|
| 574 |
+
"learning_rate": 9.609508745951988e-06,
|
| 575 |
+
"loss": 0.6531,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.21669341894060995,
|
| 580 |
+
"grad_norm": 2.3740161535009086,
|
| 581 |
+
"learning_rate": 9.591217520959095e-06,
|
| 582 |
+
"loss": 0.6378,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.21936864633493847,
|
| 587 |
+
"grad_norm": 2.543725289784257,
|
| 588 |
+
"learning_rate": 9.572525878988014e-06,
|
| 589 |
+
"loss": 0.6499,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.22204387372926698,
|
| 594 |
+
"grad_norm": 2.500580635281771,
|
| 595 |
+
"learning_rate": 9.55343545020564e-06,
|
| 596 |
+
"loss": 0.6584,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2247191011235955,
|
| 601 |
+
"grad_norm": 2.505489876568994,
|
| 602 |
+
"learning_rate": 9.533947899558521e-06,
|
| 603 |
+
"loss": 0.613,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.22739432851792402,
|
| 608 |
+
"grad_norm": 2.3654360169031095,
|
| 609 |
+
"learning_rate": 9.514064926627684e-06,
|
| 610 |
+
"loss": 0.6378,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23006955591225253,
|
| 615 |
+
"grad_norm": 2.4607999942944696,
|
| 616 |
+
"learning_rate": 9.49378826548037e-06,
|
| 617 |
+
"loss": 0.6315,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.23274478330658105,
|
| 622 |
+
"grad_norm": 2.5106286517681893,
|
| 623 |
+
"learning_rate": 9.473119684518834e-06,
|
| 624 |
+
"loss": 0.6093,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23542001070090957,
|
| 629 |
+
"grad_norm": 2.3439624704485684,
|
| 630 |
+
"learning_rate": 9.452060986326088e-06,
|
| 631 |
+
"loss": 0.6158,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.23809523809523808,
|
| 636 |
+
"grad_norm": 2.5382097517829103,
|
| 637 |
+
"learning_rate": 9.430614007508712e-06,
|
| 638 |
+
"loss": 0.6404,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24077046548956663,
|
| 643 |
+
"grad_norm": 2.3306242351666304,
|
| 644 |
+
"learning_rate": 9.408780618536664e-06,
|
| 645 |
+
"loss": 0.6287,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.24344569288389514,
|
| 650 |
+
"grad_norm": 2.4713046988918976,
|
| 651 |
+
"learning_rate": 9.386562723580155e-06,
|
| 652 |
+
"loss": 0.639,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.24612092027822366,
|
| 657 |
+
"grad_norm": 2.504614194214681,
|
| 658 |
+
"learning_rate": 9.363962260343577e-06,
|
| 659 |
+
"loss": 0.6267,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.24879614767255218,
|
| 664 |
+
"grad_norm": 2.401453830090896,
|
| 665 |
+
"learning_rate": 9.340981199896515e-06,
|
| 666 |
+
"loss": 0.6193,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25147137506688066,
|
| 671 |
+
"grad_norm": 2.529978330035686,
|
| 672 |
+
"learning_rate": 9.317621546501827e-06,
|
| 673 |
+
"loss": 0.6306,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.2541466024612092,
|
| 678 |
+
"grad_norm": 2.4063433996440384,
|
| 679 |
+
"learning_rate": 9.293885337440869e-06,
|
| 680 |
+
"loss": 0.6245,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.2568218298555377,
|
| 685 |
+
"grad_norm": 2.4727301792403638,
|
| 686 |
+
"learning_rate": 9.26977464283579e-06,
|
| 687 |
+
"loss": 0.6218,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.2594970572498662,
|
| 692 |
+
"grad_norm": 2.5289972466377906,
|
| 693 |
+
"learning_rate": 9.245291565469007e-06,
|
| 694 |
+
"loss": 0.5927,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26217228464419473,
|
| 699 |
+
"grad_norm": 2.4439695346708765,
|
| 700 |
+
"learning_rate": 9.220438240599813e-06,
|
| 701 |
+
"loss": 0.6207,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.26484751203852325,
|
| 706 |
+
"grad_norm": 2.5321941557330914,
|
| 707 |
+
"learning_rate": 9.19521683577814e-06,
|
| 708 |
+
"loss": 0.6036,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2675227394328518,
|
| 713 |
+
"grad_norm": 2.6711898378305117,
|
| 714 |
+
"learning_rate": 9.169629550655532e-06,
|
| 715 |
+
"loss": 0.6146,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.27019796682718034,
|
| 720 |
+
"grad_norm": 2.656233077443392,
|
| 721 |
+
"learning_rate": 9.143678616793299e-06,
|
| 722 |
+
"loss": 0.5851,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27287319422150885,
|
| 727 |
+
"grad_norm": 2.4406113611708684,
|
| 728 |
+
"learning_rate": 9.117366297467899e-06,
|
| 729 |
+
"loss": 0.6103,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.27554842161583737,
|
| 734 |
+
"grad_norm": 2.4790430946398656,
|
| 735 |
+
"learning_rate": 9.090694887473539e-06,
|
| 736 |
+
"loss": 0.6112,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2782236490101659,
|
| 741 |
+
"grad_norm": 2.543863410127765,
|
| 742 |
+
"learning_rate": 9.063666712922054e-06,
|
| 743 |
+
"loss": 0.5993,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.2808988764044944,
|
| 748 |
+
"grad_norm": 2.4241050160355586,
|
| 749 |
+
"learning_rate": 9.036284131040027e-06,
|
| 750 |
+
"loss": 0.5915,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2835741037988229,
|
| 755 |
+
"grad_norm": 2.4022785872888774,
|
| 756 |
+
"learning_rate": 9.008549529963202e-06,
|
| 757 |
+
"loss": 0.5786,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.28624933119315144,
|
| 762 |
+
"grad_norm": 2.426209034424006,
|
| 763 |
+
"learning_rate": 8.98046532852822e-06,
|
| 764 |
+
"loss": 0.6024,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.28892455858747995,
|
| 769 |
+
"grad_norm": 2.576690122159131,
|
| 770 |
+
"learning_rate": 8.952033976061651e-06,
|
| 771 |
+
"loss": 0.604,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.29159978598180847,
|
| 776 |
+
"grad_norm": 2.3829850107227957,
|
| 777 |
+
"learning_rate": 8.923257952166391e-06,
|
| 778 |
+
"loss": 0.605,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.294275013376137,
|
| 783 |
+
"grad_norm": 2.4150085111527386,
|
| 784 |
+
"learning_rate": 8.894139766505391e-06,
|
| 785 |
+
"loss": 0.5758,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2969502407704655,
|
| 790 |
+
"grad_norm": 2.4302320504990322,
|
| 791 |
+
"learning_rate": 8.864681958582795e-06,
|
| 792 |
+
"loss": 0.5879,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.299625468164794,
|
| 797 |
+
"grad_norm": 2.3024260962101106,
|
| 798 |
+
"learning_rate": 8.834887097522452e-06,
|
| 799 |
+
"loss": 0.5811,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.30230069555912253,
|
| 804 |
+
"grad_norm": 2.658836269132944,
|
| 805 |
+
"learning_rate": 8.80475778184386e-06,
|
| 806 |
+
"loss": 0.5935,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.30497592295345105,
|
| 811 |
+
"grad_norm": 2.3872106733021194,
|
| 812 |
+
"learning_rate": 8.774296639235527e-06,
|
| 813 |
+
"loss": 0.5822,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.30765115034777957,
|
| 818 |
+
"grad_norm": 2.471165118682251,
|
| 819 |
+
"learning_rate": 8.743506326325814e-06,
|
| 820 |
+
"loss": 0.59,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3103263777421081,
|
| 825 |
+
"grad_norm": 2.4868757117121727,
|
| 826 |
+
"learning_rate": 8.712389528451236e-06,
|
| 827 |
+
"loss": 0.5883,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.3130016051364366,
|
| 832 |
+
"grad_norm": 2.4138883516606224,
|
| 833 |
+
"learning_rate": 8.680948959422266e-06,
|
| 834 |
+
"loss": 0.5742,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3156768325307651,
|
| 839 |
+
"grad_norm": 2.507100593913838,
|
| 840 |
+
"learning_rate": 8.649187361286641e-06,
|
| 841 |
+
"loss": 0.5898,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.31835205992509363,
|
| 846 |
+
"grad_norm": 2.4100835783974643,
|
| 847 |
+
"learning_rate": 8.617107504090239e-06,
|
| 848 |
+
"loss": 0.5697,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32102728731942215,
|
| 853 |
+
"grad_norm": 3.2433002290475343,
|
| 854 |
+
"learning_rate": 8.584712185635477e-06,
|
| 855 |
+
"loss": 0.5831,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.32370251471375067,
|
| 860 |
+
"grad_norm": 2.3571626089226743,
|
| 861 |
+
"learning_rate": 8.552004231237308e-06,
|
| 862 |
+
"loss": 0.5565,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3263777421080792,
|
| 867 |
+
"grad_norm": 2.4172002061114326,
|
| 868 |
+
"learning_rate": 8.518986493476819e-06,
|
| 869 |
+
"loss": 0.5624,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.3290529695024077,
|
| 874 |
+
"grad_norm": 2.3953355643764143,
|
| 875 |
+
"learning_rate": 8.485661851952443e-06,
|
| 876 |
+
"loss": 0.5765,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.3317281968967362,
|
| 881 |
+
"grad_norm": 2.286011388064113,
|
| 882 |
+
"learning_rate": 8.452033213028822e-06,
|
| 883 |
+
"loss": 0.5658,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.33440342429106473,
|
| 888 |
+
"grad_norm": 2.648351244045331,
|
| 889 |
+
"learning_rate": 8.418103509583323e-06,
|
| 890 |
+
"loss": 0.5648,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.33707865168539325,
|
| 895 |
+
"grad_norm": 2.5355298785191813,
|
| 896 |
+
"learning_rate": 8.383875700750272e-06,
|
| 897 |
+
"loss": 0.5607,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.33975387907972177,
|
| 902 |
+
"grad_norm": 2.317259690798318,
|
| 903 |
+
"learning_rate": 8.349352771662848e-06,
|
| 904 |
+
"loss": 0.5779,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.3424291064740503,
|
| 909 |
+
"grad_norm": 2.2963059012347946,
|
| 910 |
+
"learning_rate": 8.314537733192762e-06,
|
| 911 |
+
"loss": 0.5791,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.3451043338683788,
|
| 916 |
+
"grad_norm": 2.3822664292618714,
|
| 917 |
+
"learning_rate": 8.279433621687658e-06,
|
| 918 |
+
"loss": 0.5664,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3477795612627073,
|
| 923 |
+
"grad_norm": 2.405118103743639,
|
| 924 |
+
"learning_rate": 8.2440434987063e-06,
|
| 925 |
+
"loss": 0.5886,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.35045478865703583,
|
| 930 |
+
"grad_norm": 2.4776915022762425,
|
| 931 |
+
"learning_rate": 8.208370450751568e-06,
|
| 932 |
+
"loss": 0.5581,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35313001605136435,
|
| 937 |
+
"grad_norm": 2.2672895652439675,
|
| 938 |
+
"learning_rate": 8.172417589001275e-06,
|
| 939 |
+
"loss": 0.5775,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.35580524344569286,
|
| 944 |
+
"grad_norm": 2.3099031427696533,
|
| 945 |
+
"learning_rate": 8.136188049036817e-06,
|
| 946 |
+
"loss": 0.5547,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3584804708400214,
|
| 951 |
+
"grad_norm": 2.3577031703387408,
|
| 952 |
+
"learning_rate": 8.099684990569717e-06,
|
| 953 |
+
"loss": 0.5659,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.3611556982343499,
|
| 958 |
+
"grad_norm": 2.3991198530773383,
|
| 959 |
+
"learning_rate": 8.06291159716606e-06,
|
| 960 |
+
"loss": 0.5619,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.3638309256286784,
|
| 965 |
+
"grad_norm": 2.5099299299975297,
|
| 966 |
+
"learning_rate": 8.025871075968828e-06,
|
| 967 |
+
"loss": 0.5435,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.36650615302300693,
|
| 972 |
+
"grad_norm": 2.4698105344888814,
|
| 973 |
+
"learning_rate": 7.988566657418202e-06,
|
| 974 |
+
"loss": 0.5406,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.36918138041733545,
|
| 979 |
+
"grad_norm": 2.4691995327954577,
|
| 980 |
+
"learning_rate": 7.951001594969827e-06,
|
| 981 |
+
"loss": 0.5299,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.37185660781166396,
|
| 986 |
+
"grad_norm": 2.4264629578672716,
|
| 987 |
+
"learning_rate": 7.91317916481106e-06,
|
| 988 |
+
"loss": 0.5576,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37453183520599254,
|
| 993 |
+
"grad_norm": 2.551658003203302,
|
| 994 |
+
"learning_rate": 7.875102665575241e-06,
|
| 995 |
+
"loss": 0.543,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.37720706260032105,
|
| 1000 |
+
"grad_norm": 6.107040089103125,
|
| 1001 |
+
"learning_rate": 7.83677541805401e-06,
|
| 1002 |
+
"loss": 0.5466,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.37988228999464957,
|
| 1007 |
+
"grad_norm": 2.579913197271776,
|
| 1008 |
+
"learning_rate": 7.798200764907691e-06,
|
| 1009 |
+
"loss": 0.5392,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.3825575173889781,
|
| 1014 |
+
"grad_norm": 2.401363945793991,
|
| 1015 |
+
"learning_rate": 7.759382070373755e-06,
|
| 1016 |
+
"loss": 0.5441,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.3852327447833066,
|
| 1021 |
+
"grad_norm": 2.3279189361371366,
|
| 1022 |
+
"learning_rate": 7.720322719973433e-06,
|
| 1023 |
+
"loss": 0.546,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.3879079721776351,
|
| 1028 |
+
"grad_norm": 2.5184518351120855,
|
| 1029 |
+
"learning_rate": 7.68102612021643e-06,
|
| 1030 |
+
"loss": 0.5433,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39058319957196364,
|
| 1035 |
+
"grad_norm": 2.3841613948426184,
|
| 1036 |
+
"learning_rate": 7.641495698303844e-06,
|
| 1037 |
+
"loss": 0.5291,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.39325842696629215,
|
| 1042 |
+
"grad_norm": 2.342459814244885,
|
| 1043 |
+
"learning_rate": 7.60173490182926e-06,
|
| 1044 |
+
"loss": 0.5101,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39593365436062067,
|
| 1049 |
+
"grad_norm": 2.492506659424794,
|
| 1050 |
+
"learning_rate": 7.5617471984780885e-06,
|
| 1051 |
+
"loss": 0.5454,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.3986088817549492,
|
| 1056 |
+
"grad_norm": 2.515570336738518,
|
| 1057 |
+
"learning_rate": 7.521536075725106e-06,
|
| 1058 |
+
"loss": 0.5367,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4012841091492777,
|
| 1063 |
+
"grad_norm": 2.460454444661722,
|
| 1064 |
+
"learning_rate": 7.481105040530334e-06,
|
| 1065 |
+
"loss": 0.5207,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4039593365436062,
|
| 1070 |
+
"grad_norm": 2.4664528062162603,
|
| 1071 |
+
"learning_rate": 7.440457619033155e-06,
|
| 1072 |
+
"loss": 0.5368,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.40663456393793473,
|
| 1077 |
+
"grad_norm": 2.458451790530426,
|
| 1078 |
+
"learning_rate": 7.3995973562448065e-06,
|
| 1079 |
+
"loss": 0.541,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.40930979133226325,
|
| 1084 |
+
"grad_norm": 2.388965484607956,
|
| 1085 |
+
"learning_rate": 7.358527815739192e-06,
|
| 1086 |
+
"loss": 0.5263,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41198501872659177,
|
| 1091 |
+
"grad_norm": 2.350342470688958,
|
| 1092 |
+
"learning_rate": 7.317252579342096e-06,
|
| 1093 |
+
"loss": 0.5189,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.4146602461209203,
|
| 1098 |
+
"grad_norm": 2.334939004267835,
|
| 1099 |
+
"learning_rate": 7.275775246818802e-06,
|
| 1100 |
+
"loss": 0.5355,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.4173354735152488,
|
| 1105 |
+
"grad_norm": 2.466335488768805,
|
| 1106 |
+
"learning_rate": 7.23409943556014e-06,
|
| 1107 |
+
"loss": 0.5411,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.4200107009095773,
|
| 1112 |
+
"grad_norm": 2.3840732023117575,
|
| 1113 |
+
"learning_rate": 7.192228780266997e-06,
|
| 1114 |
+
"loss": 0.5103,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42268592830390583,
|
| 1119 |
+
"grad_norm": 2.2931802265917054,
|
| 1120 |
+
"learning_rate": 7.150166932633328e-06,
|
| 1121 |
+
"loss": 0.5204,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.42536115569823435,
|
| 1126 |
+
"grad_norm": 2.4464517807290287,
|
| 1127 |
+
"learning_rate": 7.1079175610276775e-06,
|
| 1128 |
+
"loss": 0.5145,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.42803638309256287,
|
| 1133 |
+
"grad_norm": 3.062201453967221,
|
| 1134 |
+
"learning_rate": 7.065484350173242e-06,
|
| 1135 |
+
"loss": 0.5089,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.4307116104868914,
|
| 1140 |
+
"grad_norm": 2.3975551612190507,
|
| 1141 |
+
"learning_rate": 7.022871000826519e-06,
|
| 1142 |
+
"loss": 0.518,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4333868378812199,
|
| 1147 |
+
"grad_norm": 2.393531302974144,
|
| 1148 |
+
"learning_rate": 6.980081229454545e-06,
|
| 1149 |
+
"loss": 0.5296,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.4360620652755484,
|
| 1154 |
+
"grad_norm": 2.3389658387842145,
|
| 1155 |
+
"learning_rate": 6.937118767910771e-06,
|
| 1156 |
+
"loss": 0.5225,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.43873729266987693,
|
| 1161 |
+
"grad_norm": 2.304590616472174,
|
| 1162 |
+
"learning_rate": 6.893987363109595e-06,
|
| 1163 |
+
"loss": 0.5174,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.44141252006420545,
|
| 1168 |
+
"grad_norm": 2.2893102909832703,
|
| 1169 |
+
"learning_rate": 6.850690776699574e-06,
|
| 1170 |
+
"loss": 0.5157,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44408774745853397,
|
| 1175 |
+
"grad_norm": 2.3528835058549693,
|
| 1176 |
+
"learning_rate": 6.807232784735363e-06,
|
| 1177 |
+
"loss": 0.5186,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.4467629748528625,
|
| 1182 |
+
"grad_norm": 2.3960495391474916,
|
| 1183 |
+
"learning_rate": 6.763617177348394e-06,
|
| 1184 |
+
"loss": 0.494,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.449438202247191,
|
| 1189 |
+
"grad_norm": 2.391730693829397,
|
| 1190 |
+
"learning_rate": 6.719847758416316e-06,
|
| 1191 |
+
"loss": 0.4952,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.4521134296415195,
|
| 1196 |
+
"grad_norm": 2.3102028249018027,
|
| 1197 |
+
"learning_rate": 6.675928345231248e-06,
|
| 1198 |
+
"loss": 0.4945,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45478865703584803,
|
| 1203 |
+
"grad_norm": 2.340089688669794,
|
| 1204 |
+
"learning_rate": 6.631862768166861e-06,
|
| 1205 |
+
"loss": 0.5206,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.45746388443017655,
|
| 1210 |
+
"grad_norm": 2.3869663318928818,
|
| 1211 |
+
"learning_rate": 6.587654870344318e-06,
|
| 1212 |
+
"loss": 0.4904,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46013911182450506,
|
| 1217 |
+
"grad_norm": 2.3186471369565016,
|
| 1218 |
+
"learning_rate": 6.543308507297094e-06,
|
| 1219 |
+
"loss": 0.4955,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.4628143392188336,
|
| 1224 |
+
"grad_norm": 2.348787884210591,
|
| 1225 |
+
"learning_rate": 6.498827546634733e-06,
|
| 1226 |
+
"loss": 0.4857,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.4654895666131621,
|
| 1231 |
+
"grad_norm": 2.3022368035042313,
|
| 1232 |
+
"learning_rate": 6.454215867705526e-06,
|
| 1233 |
+
"loss": 0.5017,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.4681647940074906,
|
| 1238 |
+
"grad_norm": 2.2741836629628804,
|
| 1239 |
+
"learning_rate": 6.409477361258188e-06,
|
| 1240 |
+
"loss": 0.5068,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47084002140181913,
|
| 1245 |
+
"grad_norm": 2.360316687024575,
|
| 1246 |
+
"learning_rate": 6.364615929102531e-06,
|
| 1247 |
+
"loss": 0.494,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.47351524879614765,
|
| 1252 |
+
"grad_norm": 2.379176924172674,
|
| 1253 |
+
"learning_rate": 6.319635483769164e-06,
|
| 1254 |
+
"loss": 0.4897,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47619047619047616,
|
| 1259 |
+
"grad_norm": 2.3319354135997843,
|
| 1260 |
+
"learning_rate": 6.274539948168279e-06,
|
| 1261 |
+
"loss": 0.5032,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.47886570358480474,
|
| 1266 |
+
"grad_norm": 2.3550908404304067,
|
| 1267 |
+
"learning_rate": 6.229333255247511e-06,
|
| 1268 |
+
"loss": 0.4881,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48154093097913325,
|
| 1273 |
+
"grad_norm": 2.3143929315173044,
|
| 1274 |
+
"learning_rate": 6.184019347648939e-06,
|
| 1275 |
+
"loss": 0.4836,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.48421615837346177,
|
| 1280 |
+
"grad_norm": 2.48991053989977,
|
| 1281 |
+
"learning_rate": 6.138602177365218e-06,
|
| 1282 |
+
"loss": 0.4929,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.4868913857677903,
|
| 1287 |
+
"grad_norm": 2.3913793797288783,
|
| 1288 |
+
"learning_rate": 6.093085705394934e-06,
|
| 1289 |
+
"loss": 0.4693,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.4895666131621188,
|
| 1294 |
+
"grad_norm": 2.2543254040593763,
|
| 1295 |
+
"learning_rate": 6.04747390139713e-06,
|
| 1296 |
+
"loss": 0.4743,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.4922418405564473,
|
| 1301 |
+
"grad_norm": 2.348339630964883,
|
| 1302 |
+
"learning_rate": 6.001770743345108e-06,
|
| 1303 |
+
"loss": 0.4823,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.49491706795077584,
|
| 1308 |
+
"grad_norm": 2.2449795227494005,
|
| 1309 |
+
"learning_rate": 5.9559802171794955e-06,
|
| 1310 |
+
"loss": 0.4846,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.49759229534510435,
|
| 1315 |
+
"grad_norm": 2.241213857361928,
|
| 1316 |
+
"learning_rate": 5.9101063164606165e-06,
|
| 1317 |
+
"loss": 0.4805,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5002675227394329,
|
| 1322 |
+
"grad_norm": 2.4169638599052523,
|
| 1323 |
+
"learning_rate": 5.864153042020191e-06,
|
| 1324 |
+
"loss": 0.4691,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5029427501337613,
|
| 1329 |
+
"grad_norm": 2.25529384343331,
|
| 1330 |
+
"learning_rate": 5.818124401612416e-06,
|
| 1331 |
+
"loss": 0.4899,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.5056179775280899,
|
| 1336 |
+
"grad_norm": 2.383950239796953,
|
| 1337 |
+
"learning_rate": 5.7720244095644305e-06,
|
| 1338 |
+
"loss": 0.4741,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5082932049224184,
|
| 1343 |
+
"grad_norm": 2.502424957725384,
|
| 1344 |
+
"learning_rate": 5.725857086426216e-06,
|
| 1345 |
+
"loss": 0.4771,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.5109684323167469,
|
| 1350 |
+
"grad_norm": 2.3038774447416808,
|
| 1351 |
+
"learning_rate": 5.679626458619947e-06,
|
| 1352 |
+
"loss": 0.4703,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5136436597110754,
|
| 1357 |
+
"grad_norm": 2.346899662548698,
|
| 1358 |
+
"learning_rate": 5.633336558088823e-06,
|
| 1359 |
+
"loss": 0.4887,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.516318887105404,
|
| 1364 |
+
"grad_norm": 2.2355161245769843,
|
| 1365 |
+
"learning_rate": 5.586991421945445e-06,
|
| 1366 |
+
"loss": 0.4656,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.5189941144997324,
|
| 1371 |
+
"grad_norm": 2.3292739097458153,
|
| 1372 |
+
"learning_rate": 5.540595092119709e-06,
|
| 1373 |
+
"loss": 0.4585,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.521669341894061,
|
| 1378 |
+
"grad_norm": 2.4214982730972414,
|
| 1379 |
+
"learning_rate": 5.494151615006307e-06,
|
| 1380 |
+
"loss": 0.4694,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.5243445692883895,
|
| 1385 |
+
"grad_norm": 2.3116711052429353,
|
| 1386 |
+
"learning_rate": 5.44766504111181e-06,
|
| 1387 |
+
"loss": 0.4527,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.527019796682718,
|
| 1392 |
+
"grad_norm": 2.36653247169498,
|
| 1393 |
+
"learning_rate": 5.401139424701427e-06,
|
| 1394 |
+
"loss": 0.4663,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5296950240770465,
|
| 1399 |
+
"grad_norm": 2.41785279589817,
|
| 1400 |
+
"learning_rate": 5.354578823445404e-06,
|
| 1401 |
+
"loss": 0.4645,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5323702514713751,
|
| 1406 |
+
"grad_norm": 2.2795559605311935,
|
| 1407 |
+
"learning_rate": 5.307987298065145e-06,
|
| 1408 |
+
"loss": 0.4688,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.5350454788657036,
|
| 1413 |
+
"grad_norm": 2.420758151365417,
|
| 1414 |
+
"learning_rate": 5.26136891197906e-06,
|
| 1415 |
+
"loss": 0.4772,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5377207062600321,
|
| 1420 |
+
"grad_norm": 2.286837120031368,
|
| 1421 |
+
"learning_rate": 5.214727730948181e-06,
|
| 1422 |
+
"loss": 0.4579,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.5403959336543607,
|
| 1427 |
+
"grad_norm": 2.5357314724486684,
|
| 1428 |
+
"learning_rate": 5.1680678227215705e-06,
|
| 1429 |
+
"loss": 0.4448,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.5430711610486891,
|
| 1434 |
+
"grad_norm": 2.4433154714045737,
|
| 1435 |
+
"learning_rate": 5.121393256681561e-06,
|
| 1436 |
+
"loss": 0.4512,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.5457463884430177,
|
| 1441 |
+
"grad_norm": 2.3443908369260584,
|
| 1442 |
+
"learning_rate": 5.07470810348884e-06,
|
| 1443 |
+
"loss": 0.445,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.5484216158373462,
|
| 1448 |
+
"grad_norm": 2.341118659715022,
|
| 1449 |
+
"learning_rate": 5.02801643472745e-06,
|
| 1450 |
+
"loss": 0.4547,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.5510968432316747,
|
| 1455 |
+
"grad_norm": 2.5523488397688445,
|
| 1456 |
+
"learning_rate": 4.98132232254967e-06,
|
| 1457 |
+
"loss": 0.4551,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5537720706260032,
|
| 1462 |
+
"grad_norm": 2.341888099144205,
|
| 1463 |
+
"learning_rate": 4.934629839320885e-06,
|
| 1464 |
+
"loss": 0.447,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.5564472980203318,
|
| 1469 |
+
"grad_norm": 2.367969391536302,
|
| 1470 |
+
"learning_rate": 4.88794305726441e-06,
|
| 1471 |
+
"loss": 0.4562,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5591225254146602,
|
| 1476 |
+
"grad_norm": 2.4141297608989505,
|
| 1477 |
+
"learning_rate": 4.841266048106343e-06,
|
| 1478 |
+
"loss": 0.4588,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.5617977528089888,
|
| 1483 |
+
"grad_norm": 2.2942217661884463,
|
| 1484 |
+
"learning_rate": 4.794602882720448e-06,
|
| 1485 |
+
"loss": 0.4519,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.5644729802033173,
|
| 1490 |
+
"grad_norm": 2.4388470304507184,
|
| 1491 |
+
"learning_rate": 4.747957630773124e-06,
|
| 1492 |
+
"loss": 0.4381,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.5671482075976458,
|
| 1497 |
+
"grad_norm": 2.426362017801771,
|
| 1498 |
+
"learning_rate": 4.701334360368473e-06,
|
| 1499 |
+
"loss": 0.4389,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5698234349919743,
|
| 1504 |
+
"grad_norm": 2.187091633024644,
|
| 1505 |
+
"learning_rate": 4.654737137693508e-06,
|
| 1506 |
+
"loss": 0.4443,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.5724986623863029,
|
| 1511 |
+
"grad_norm": 2.2703979543148227,
|
| 1512 |
+
"learning_rate": 4.6081700266635195e-06,
|
| 1513 |
+
"loss": 0.4495,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.5751738897806313,
|
| 1518 |
+
"grad_norm": 2.583776287215632,
|
| 1519 |
+
"learning_rate": 4.561637088567654e-06,
|
| 1520 |
+
"loss": 0.4461,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.5778491171749599,
|
| 1525 |
+
"grad_norm": 2.2365322610979295,
|
| 1526 |
+
"learning_rate": 4.51514238171471e-06,
|
| 1527 |
+
"loss": 0.4529,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.5805243445692884,
|
| 1532 |
+
"grad_norm": 2.180037600496683,
|
| 1533 |
+
"learning_rate": 4.468689961079195e-06,
|
| 1534 |
+
"loss": 0.4323,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5831995719636169,
|
| 1539 |
+
"grad_norm": 2.081559354724233,
|
| 1540 |
+
"learning_rate": 4.4222838779476866e-06,
|
| 1541 |
+
"loss": 0.4214,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.5858747993579454,
|
| 1546 |
+
"grad_norm": 2.3076982125413372,
|
| 1547 |
+
"learning_rate": 4.375928179565494e-06,
|
| 1548 |
+
"loss": 0.4468,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.588550026752274,
|
| 1553 |
+
"grad_norm": 2.283053955784425,
|
| 1554 |
+
"learning_rate": 4.329626908783685e-06,
|
| 1555 |
+
"loss": 0.4417,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.5912252541466024,
|
| 1560 |
+
"grad_norm": 2.254830049137223,
|
| 1561 |
+
"learning_rate": 4.2833841037065e-06,
|
| 1562 |
+
"loss": 0.4423,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.593900481540931,
|
| 1567 |
+
"grad_norm": 2.3109882572246687,
|
| 1568 |
+
"learning_rate": 4.237203797339169e-06,
|
| 1569 |
+
"loss": 0.4431,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5965757089352595,
|
| 1574 |
+
"grad_norm": 2.3244488841789597,
|
| 1575 |
+
"learning_rate": 4.191090017236177e-06,
|
| 1576 |
+
"loss": 0.4283,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.599250936329588,
|
| 1581 |
+
"grad_norm": 2.257838237616692,
|
| 1582 |
+
"learning_rate": 4.145046785150013e-06,
|
| 1583 |
+
"loss": 0.433,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.6019261637239165,
|
| 1588 |
+
"grad_norm": 2.1584220334955293,
|
| 1589 |
+
"learning_rate": 4.09907811668041e-06,
|
| 1590 |
+
"loss": 0.4162,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6046013911182451,
|
| 1595 |
+
"grad_norm": 2.298272375780168,
|
| 1596 |
+
"learning_rate": 4.0531880209241356e-06,
|
| 1597 |
+
"loss": 0.426,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6072766185125735,
|
| 1602 |
+
"grad_norm": 2.215799524593221,
|
| 1603 |
+
"learning_rate": 4.0073805001253405e-06,
|
| 1604 |
+
"loss": 0.4326,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6099518459069021,
|
| 1609 |
+
"grad_norm": 2.2218734417372414,
|
| 1610 |
+
"learning_rate": 3.961659549326512e-06,
|
| 1611 |
+
"loss": 0.4227,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.6126270733012306,
|
| 1616 |
+
"grad_norm": 2.208228128926267,
|
| 1617 |
+
"learning_rate": 3.916029156020044e-06,
|
| 1618 |
+
"loss": 0.4341,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6153023006955591,
|
| 1623 |
+
"grad_norm": 2.306119953673732,
|
| 1624 |
+
"learning_rate": 3.870493299800484e-06,
|
| 1625 |
+
"loss": 0.4173,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6179775280898876,
|
| 1630 |
+
"grad_norm": 2.1515931379516977,
|
| 1631 |
+
"learning_rate": 3.82505595201745e-06,
|
| 1632 |
+
"loss": 0.4133,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.6206527554842162,
|
| 1637 |
+
"grad_norm": 2.2524460175233503,
|
| 1638 |
+
"learning_rate": 3.7797210754292766e-06,
|
| 1639 |
+
"loss": 0.4162,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.6233279828785446,
|
| 1644 |
+
"grad_norm": 2.301799592604272,
|
| 1645 |
+
"learning_rate": 3.7344926238574074e-06,
|
| 1646 |
+
"loss": 0.4006,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.6260032102728732,
|
| 1651 |
+
"grad_norm": 2.1524308460470527,
|
| 1652 |
+
"learning_rate": 3.6893745418415692e-06,
|
| 1653 |
+
"loss": 0.4263,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.6286784376672017,
|
| 1658 |
+
"grad_norm": 2.2748089398628597,
|
| 1659 |
+
"learning_rate": 3.6443707642957526e-06,
|
| 1660 |
+
"loss": 0.4205,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.6313536650615302,
|
| 1665 |
+
"grad_norm": 2.2999788424441974,
|
| 1666 |
+
"learning_rate": 3.5994852161650386e-06,
|
| 1667 |
+
"loss": 0.4114,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.6340288924558587,
|
| 1672 |
+
"grad_norm": 2.250922812696413,
|
| 1673 |
+
"learning_rate": 3.5547218120832807e-06,
|
| 1674 |
+
"loss": 0.4272,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6367041198501873,
|
| 1679 |
+
"grad_norm": 2.199876026491523,
|
| 1680 |
+
"learning_rate": 3.5100844560317028e-06,
|
| 1681 |
+
"loss": 0.4263,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6393793472445158,
|
| 1686 |
+
"grad_norm": 2.4231067314017607,
|
| 1687 |
+
"learning_rate": 3.465577040998417e-06,
|
| 1688 |
+
"loss": 0.4081,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.6420545746388443,
|
| 1693 |
+
"grad_norm": 2.329769969490132,
|
| 1694 |
+
"learning_rate": 3.4212034486388972e-06,
|
| 1695 |
+
"loss": 0.4162,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.6447298020331729,
|
| 1700 |
+
"grad_norm": 2.2358270007097603,
|
| 1701 |
+
"learning_rate": 3.376967548937457e-06,
|
| 1702 |
+
"loss": 0.4104,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.6474050294275013,
|
| 1707 |
+
"grad_norm": 2.232847334212105,
|
| 1708 |
+
"learning_rate": 3.332873199869719e-06,
|
| 1709 |
+
"loss": 0.4224,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.6500802568218299,
|
| 1714 |
+
"grad_norm": 2.2160061126201525,
|
| 1715 |
+
"learning_rate": 3.2889242470661553e-06,
|
| 1716 |
+
"loss": 0.4225,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.6527554842161584,
|
| 1721 |
+
"grad_norm": 2.336455552359997,
|
| 1722 |
+
"learning_rate": 3.245124523476699e-06,
|
| 1723 |
+
"loss": 0.413,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.6554307116104869,
|
| 1728 |
+
"grad_norm": 2.180496144947931,
|
| 1729 |
+
"learning_rate": 3.2014778490364484e-06,
|
| 1730 |
+
"loss": 0.4101,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.6581059390048154,
|
| 1735 |
+
"grad_norm": 2.208527174103595,
|
| 1736 |
+
"learning_rate": 3.157988030332526e-06,
|
| 1737 |
+
"loss": 0.4028,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.660781166399144,
|
| 1742 |
+
"grad_norm": 2.1964688689281195,
|
| 1743 |
+
"learning_rate": 3.1146588602720884e-06,
|
| 1744 |
+
"loss": 0.3957,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.6634563937934724,
|
| 1749 |
+
"grad_norm": 2.259624100422769,
|
| 1750 |
+
"learning_rate": 3.0714941177515307e-06,
|
| 1751 |
+
"loss": 0.4073,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.666131621187801,
|
| 1756 |
+
"grad_norm": 2.193290344140555,
|
| 1757 |
+
"learning_rate": 3.0284975673269175e-06,
|
| 1758 |
+
"loss": 0.4093,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.6688068485821295,
|
| 1763 |
+
"grad_norm": 2.1954151969989586,
|
| 1764 |
+
"learning_rate": 2.9856729588856615e-06,
|
| 1765 |
+
"loss": 0.4117,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.671482075976458,
|
| 1770 |
+
"grad_norm": 2.2138053404473195,
|
| 1771 |
+
"learning_rate": 2.9430240273194844e-06,
|
| 1772 |
+
"loss": 0.4082,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.6741573033707865,
|
| 1777 |
+
"grad_norm": 2.257221465226075,
|
| 1778 |
+
"learning_rate": 2.9005544921986774e-06,
|
| 1779 |
+
"loss": 0.4069,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.6768325307651151,
|
| 1784 |
+
"grad_norm": 2.1775802118360277,
|
| 1785 |
+
"learning_rate": 2.858268057447712e-06,
|
| 1786 |
+
"loss": 0.3973,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.6795077581594435,
|
| 1791 |
+
"grad_norm": 2.436885814724992,
|
| 1792 |
+
"learning_rate": 2.8161684110221987e-06,
|
| 1793 |
+
"loss": 0.403,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.6821829855537721,
|
| 1798 |
+
"grad_norm": 2.2209153390752077,
|
| 1799 |
+
"learning_rate": 2.7742592245872523e-06,
|
| 1800 |
+
"loss": 0.4023,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.6848582129481006,
|
| 1805 |
+
"grad_norm": 2.2109764032679537,
|
| 1806 |
+
"learning_rate": 2.7325441531972685e-06,
|
| 1807 |
+
"loss": 0.3994,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.6875334403424291,
|
| 1812 |
+
"grad_norm": 2.1795809319816333,
|
| 1813 |
+
"learning_rate": 2.691026834977161e-06,
|
| 1814 |
+
"loss": 0.3986,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.6902086677367576,
|
| 1819 |
+
"grad_norm": 2.2391940715660676,
|
| 1820 |
+
"learning_rate": 2.649710890805055e-06,
|
| 1821 |
+
"loss": 0.3935,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.6928838951310862,
|
| 1826 |
+
"grad_norm": 2.2035616343677322,
|
| 1827 |
+
"learning_rate": 2.6085999239965094e-06,
|
| 1828 |
+
"loss": 0.387,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.6955591225254146,
|
| 1833 |
+
"grad_norm": 2.22131504261394,
|
| 1834 |
+
"learning_rate": 2.567697519990249e-06,
|
| 1835 |
+
"loss": 0.3973,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.6982343499197432,
|
| 1840 |
+
"grad_norm": 2.098207954779385,
|
| 1841 |
+
"learning_rate": 2.52700724603547e-06,
|
| 1842 |
+
"loss": 0.3871,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7009095773140717,
|
| 1847 |
+
"grad_norm": 2.2983786280371348,
|
| 1848 |
+
"learning_rate": 2.4865326508807274e-06,
|
| 1849 |
+
"loss": 0.3977,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.7035848047084002,
|
| 1854 |
+
"grad_norm": 2.319405000990969,
|
| 1855 |
+
"learning_rate": 2.446277264464431e-06,
|
| 1856 |
+
"loss": 0.4034,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7062600321027287,
|
| 1861 |
+
"grad_norm": 2.109060490520534,
|
| 1862 |
+
"learning_rate": 2.406244597606994e-06,
|
| 1863 |
+
"loss": 0.3811,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7089352594970573,
|
| 1868 |
+
"grad_norm": 2.177607834388425,
|
| 1869 |
+
"learning_rate": 2.3664381417046362e-06,
|
| 1870 |
+
"loss": 0.3786,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7116104868913857,
|
| 1875 |
+
"grad_norm": 2.1527244194926785,
|
| 1876 |
+
"learning_rate": 2.3268613684248846e-06,
|
| 1877 |
+
"loss": 0.3747,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.7142857142857143,
|
| 1882 |
+
"grad_norm": 2.205331372771754,
|
| 1883 |
+
"learning_rate": 2.287517729403802e-06,
|
| 1884 |
+
"loss": 0.4021,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.7169609416800428,
|
| 1889 |
+
"grad_norm": 2.248309322312752,
|
| 1890 |
+
"learning_rate": 2.2484106559449527e-06,
|
| 1891 |
+
"loss": 0.3822,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.7196361690743713,
|
| 1896 |
+
"grad_norm": 2.253569974888193,
|
| 1897 |
+
"learning_rate": 2.2095435587201487e-06,
|
| 1898 |
+
"loss": 0.3933,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.7223113964686998,
|
| 1903 |
+
"grad_norm": 2.1475317223597834,
|
| 1904 |
+
"learning_rate": 2.1709198274719908e-06,
|
| 1905 |
+
"loss": 0.383,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.7249866238630284,
|
| 1910 |
+
"grad_norm": 2.156341132086858,
|
| 1911 |
+
"learning_rate": 2.1325428307182357e-06,
|
| 1912 |
+
"loss": 0.3937,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.7276618512573568,
|
| 1917 |
+
"grad_norm": 2.3908806324651497,
|
| 1918 |
+
"learning_rate": 2.0944159154580225e-06,
|
| 1919 |
+
"loss": 0.384,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.7303370786516854,
|
| 1924 |
+
"grad_norm": 2.1302675049467847,
|
| 1925 |
+
"learning_rate": 2.056542406879957e-06,
|
| 1926 |
+
"loss": 0.3985,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.7330123060460139,
|
| 1931 |
+
"grad_norm": 2.1818319060840143,
|
| 1932 |
+
"learning_rate": 2.018925608072118e-06,
|
| 1933 |
+
"loss": 0.3911,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.7356875334403424,
|
| 1938 |
+
"grad_norm": 2.3780828415180326,
|
| 1939 |
+
"learning_rate": 1.981568799733979e-06,
|
| 1940 |
+
"loss": 0.3948,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.7383627608346709,
|
| 1945 |
+
"grad_norm": 2.1564398789314896,
|
| 1946 |
+
"learning_rate": 1.9444752398902874e-06,
|
| 1947 |
+
"loss": 0.393,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.7410379882289995,
|
| 1952 |
+
"grad_norm": 2.225312239443466,
|
| 1953 |
+
"learning_rate": 1.907648163606925e-06,
|
| 1954 |
+
"loss": 0.3797,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.7437132156233279,
|
| 1959 |
+
"grad_norm": 2.1676481802841594,
|
| 1960 |
+
"learning_rate": 1.871090782708756e-06,
|
| 1961 |
+
"loss": 0.3717,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7463884430176565,
|
| 1966 |
+
"grad_norm": 2.1201954498907543,
|
| 1967 |
+
"learning_rate": 1.834806285499519e-06,
|
| 1968 |
+
"loss": 0.3847,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.7490636704119851,
|
| 1973 |
+
"grad_norm": 2.0493679026239997,
|
| 1974 |
+
"learning_rate": 1.7987978364837649e-06,
|
| 1975 |
+
"loss": 0.3783,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.7517388978063135,
|
| 1980 |
+
"grad_norm": 2.240394083021461,
|
| 1981 |
+
"learning_rate": 1.7630685760908623e-06,
|
| 1982 |
+
"loss": 0.3787,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.7544141252006421,
|
| 1987 |
+
"grad_norm": 2.2507322502146,
|
| 1988 |
+
"learning_rate": 1.727621620401112e-06,
|
| 1989 |
+
"loss": 0.3839,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.7570893525949706,
|
| 1994 |
+
"grad_norm": 2.050018308953964,
|
| 1995 |
+
"learning_rate": 1.6924600608739843e-06,
|
| 1996 |
+
"loss": 0.3805,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.7597645799892991,
|
| 2001 |
+
"grad_norm": 2.216364526482266,
|
| 2002 |
+
"learning_rate": 1.6575869640784998e-06,
|
| 2003 |
+
"loss": 0.3874,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.7624398073836276,
|
| 2008 |
+
"grad_norm": 2.415575248697165,
|
| 2009 |
+
"learning_rate": 1.6230053714257821e-06,
|
| 2010 |
+
"loss": 0.3813,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.7651150347779562,
|
| 2015 |
+
"grad_norm": 2.2306031322832034,
|
| 2016 |
+
"learning_rate": 1.588718298903803e-06,
|
| 2017 |
+
"loss": 0.3864,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.7677902621722846,
|
| 2022 |
+
"grad_norm": 2.111010889830229,
|
| 2023 |
+
"learning_rate": 1.554728736814356e-06,
|
| 2024 |
+
"loss": 0.3802,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.7704654895666132,
|
| 2029 |
+
"grad_norm": 2.121564095465321,
|
| 2030 |
+
"learning_rate": 1.5210396495122481e-06,
|
| 2031 |
+
"loss": 0.3754,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.7731407169609417,
|
| 2036 |
+
"grad_norm": 2.120725109177726,
|
| 2037 |
+
"learning_rate": 1.4876539751467806e-06,
|
| 2038 |
+
"loss": 0.3689,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.7758159443552702,
|
| 2043 |
+
"grad_norm": 2.3772037200731435,
|
| 2044 |
+
"learning_rate": 1.45457462540549e-06,
|
| 2045 |
+
"loss": 0.3814,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.7784911717495987,
|
| 2050 |
+
"grad_norm": 2.2229585889968937,
|
| 2051 |
+
"learning_rate": 1.4218044852602176e-06,
|
| 2052 |
+
"loss": 0.3647,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.7811663991439273,
|
| 2057 |
+
"grad_norm": 2.1273873598379405,
|
| 2058 |
+
"learning_rate": 1.3893464127154976e-06,
|
| 2059 |
+
"loss": 0.3641,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.7838416265382557,
|
| 2064 |
+
"grad_norm": 2.238369501132279,
|
| 2065 |
+
"learning_rate": 1.3572032385592999e-06,
|
| 2066 |
+
"loss": 0.3736,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.7865168539325843,
|
| 2071 |
+
"grad_norm": 2.367411256466404,
|
| 2072 |
+
"learning_rate": 1.325377766116146e-06,
|
| 2073 |
+
"loss": 0.3695,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.7891920813269128,
|
| 2078 |
+
"grad_norm": 2.154614847558025,
|
| 2079 |
+
"learning_rate": 1.293872771002625e-06,
|
| 2080 |
+
"loss": 0.3668,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.7918673087212413,
|
| 2085 |
+
"grad_norm": 2.0973822868623198,
|
| 2086 |
+
"learning_rate": 1.2626910008853154e-06,
|
| 2087 |
+
"loss": 0.3605,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.7945425361155698,
|
| 2092 |
+
"grad_norm": 2.2044842996768637,
|
| 2093 |
+
"learning_rate": 1.231835175241155e-06,
|
| 2094 |
+
"loss": 0.3608,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.7972177635098984,
|
| 2099 |
+
"grad_norm": 2.1338982634951984,
|
| 2100 |
+
"learning_rate": 1.2013079851202642e-06,
|
| 2101 |
+
"loss": 0.3633,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.7998929909042268,
|
| 2106 |
+
"grad_norm": 2.26851173489404,
|
| 2107 |
+
"learning_rate": 1.1711120929112507e-06,
|
| 2108 |
+
"loss": 0.369,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8025682182985554,
|
| 2113 |
+
"grad_norm": 2.1372863507277753,
|
| 2114 |
+
"learning_rate": 1.141250132109009e-06,
|
| 2115 |
+
"loss": 0.3828,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.8052434456928839,
|
| 2120 |
+
"grad_norm": 2.1821710728521206,
|
| 2121 |
+
"learning_rate": 1.1117247070850534e-06,
|
| 2122 |
+
"loss": 0.3751,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8079186730872124,
|
| 2127 |
+
"grad_norm": 2.289464427582727,
|
| 2128 |
+
"learning_rate": 1.0825383928603656e-06,
|
| 2129 |
+
"loss": 0.3689,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.8105939004815409,
|
| 2134 |
+
"grad_norm": 2.144427258095427,
|
| 2135 |
+
"learning_rate": 1.0536937348808341e-06,
|
| 2136 |
+
"loss": 0.3625,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.8132691278758695,
|
| 2141 |
+
"grad_norm": 2.1622070889222695,
|
| 2142 |
+
"learning_rate": 1.0251932487952437e-06,
|
| 2143 |
+
"loss": 0.3724,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.8159443552701979,
|
| 2148 |
+
"grad_norm": 2.343707532992404,
|
| 2149 |
+
"learning_rate": 9.97039420235884e-07,
|
| 2150 |
+
"loss": 0.3685,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.8186195826645265,
|
| 2155 |
+
"grad_norm": 2.044139501535542,
|
| 2156 |
+
"learning_rate": 9.692347046017647e-07,
|
| 2157 |
+
"loss": 0.3593,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.821294810058855,
|
| 2162 |
+
"grad_norm": 2.070900945818719,
|
| 2163 |
+
"learning_rate": 9.417815268444719e-07,
|
| 2164 |
+
"loss": 0.3795,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8239700374531835,
|
| 2169 |
+
"grad_norm": 2.202544122311645,
|
| 2170 |
+
"learning_rate": 9.146822812566819e-07,
|
| 2171 |
+
"loss": 0.3628,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.826645264847512,
|
| 2176 |
+
"grad_norm": 2.2552592796377535,
|
| 2177 |
+
"learning_rate": 8.879393312633405e-07,
|
| 2178 |
+
"loss": 0.3626,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8293204922418406,
|
| 2183 |
+
"grad_norm": 2.056735418503588,
|
| 2184 |
+
"learning_rate": 8.615550092155478e-07,
|
| 2185 |
+
"loss": 0.3633,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.831995719636169,
|
| 2190 |
+
"grad_norm": 2.2605962525988486,
|
| 2191 |
+
"learning_rate": 8.355316161871369e-07,
|
| 2192 |
+
"loss": 0.3576,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.8346709470304976,
|
| 2197 |
+
"grad_norm": 1.9325644963312696,
|
| 2198 |
+
"learning_rate": 8.098714217739928e-07,
|
| 2199 |
+
"loss": 0.3592,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.8373461744248261,
|
| 2204 |
+
"grad_norm": 2.062402471762311,
|
| 2205 |
+
"learning_rate": 7.845766638961172e-07,
|
| 2206 |
+
"loss": 0.3471,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.8400214018191546,
|
| 2211 |
+
"grad_norm": 1.881539114622424,
|
| 2212 |
+
"learning_rate": 7.596495486024402e-07,
|
| 2213 |
+
"loss": 0.3514,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.8426966292134831,
|
| 2218 |
+
"grad_norm": 1.950588612928137,
|
| 2219 |
+
"learning_rate": 7.350922498784335e-07,
|
| 2220 |
+
"loss": 0.353,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8453718566078117,
|
| 2225 |
+
"grad_norm": 2.1988421073847575,
|
| 2226 |
+
"learning_rate": 7.109069094565024e-07,
|
| 2227 |
+
"loss": 0.3681,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8480470840021401,
|
| 2232 |
+
"grad_norm": 2.113659026819843,
|
| 2233 |
+
"learning_rate": 6.870956366291998e-07,
|
| 2234 |
+
"loss": 0.3544,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8507223113964687,
|
| 2239 |
+
"grad_norm": 2.33180266595057,
|
| 2240 |
+
"learning_rate": 6.636605080652686e-07,
|
| 2241 |
+
"loss": 0.3724,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.8533975387907973,
|
| 2246 |
+
"grad_norm": 1.867424119206801,
|
| 2247 |
+
"learning_rate": 6.406035676285244e-07,
|
| 2248 |
+
"loss": 0.362,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.8560727661851257,
|
| 2253 |
+
"grad_norm": 2.0665126499518767,
|
| 2254 |
+
"learning_rate": 6.179268261996052e-07,
|
| 2255 |
+
"loss": 0.3595,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.8587479935794543,
|
| 2260 |
+
"grad_norm": 1.9884903895103176,
|
| 2261 |
+
"learning_rate": 5.956322615005928e-07,
|
| 2262 |
+
"loss": 0.3575,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.8614232209737828,
|
| 2267 |
+
"grad_norm": 2.2045330930282083,
|
| 2268 |
+
"learning_rate": 5.737218179225318e-07,
|
| 2269 |
+
"loss": 0.3606,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.8640984483681113,
|
| 2274 |
+
"grad_norm": 2.055450620418203,
|
| 2275 |
+
"learning_rate": 5.521974063558477e-07,
|
| 2276 |
+
"loss": 0.3674,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.8667736757624398,
|
| 2281 |
+
"grad_norm": 1.9535432905188745,
|
| 2282 |
+
"learning_rate": 5.310609040236963e-07,
|
| 2283 |
+
"loss": 0.3554,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.8694489031567684,
|
| 2288 |
+
"grad_norm": 2.119370192450794,
|
| 2289 |
+
"learning_rate": 5.103141543182389e-07,
|
| 2290 |
+
"loss": 0.3526,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.8721241305510968,
|
| 2295 |
+
"grad_norm": 1.954481761832286,
|
| 2296 |
+
"learning_rate": 4.89958966639878e-07,
|
| 2297 |
+
"loss": 0.3481,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.8747993579454254,
|
| 2302 |
+
"grad_norm": 2.133312045046774,
|
| 2303 |
+
"learning_rate": 4.6999711623944787e-07,
|
| 2304 |
+
"loss": 0.3472,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.8774745853397539,
|
| 2309 |
+
"grad_norm": 2.180255754156536,
|
| 2310 |
+
"learning_rate": 4.504303440633928e-07,
|
| 2311 |
+
"loss": 0.3511,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.8801498127340824,
|
| 2316 |
+
"grad_norm": 2.1358891158089612,
|
| 2317 |
+
"learning_rate": 4.3126035660193076e-07,
|
| 2318 |
+
"loss": 0.3571,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.8828250401284109,
|
| 2323 |
+
"grad_norm": 1.84315836717447,
|
| 2324 |
+
"learning_rate": 4.124888257402243e-07,
|
| 2325 |
+
"loss": 0.3624,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.8855002675227395,
|
| 2330 |
+
"grad_norm": 2.0554826944518663,
|
| 2331 |
+
"learning_rate": 3.9411738861256934e-07,
|
| 2332 |
+
"loss": 0.3579,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.8881754949170679,
|
| 2337 |
+
"grad_norm": 2.4601678197896897,
|
| 2338 |
+
"learning_rate": 3.7614764745961377e-07,
|
| 2339 |
+
"loss": 0.3531,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.8908507223113965,
|
| 2344 |
+
"grad_norm": 2.012754969035083,
|
| 2345 |
+
"learning_rate": 3.585811694886232e-07,
|
| 2346 |
+
"loss": 0.349,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.893525949705725,
|
| 2351 |
+
"grad_norm": 2.0385968561479237,
|
| 2352 |
+
"learning_rate": 3.4141948673679593e-07,
|
| 2353 |
+
"loss": 0.3616,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.8962011771000535,
|
| 2358 |
+
"grad_norm": 2.244778290107756,
|
| 2359 |
+
"learning_rate": 3.2466409593764734e-07,
|
| 2360 |
+
"loss": 0.3564,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.898876404494382,
|
| 2365 |
+
"grad_norm": 1.9854065627744804,
|
| 2366 |
+
"learning_rate": 3.083164583904802e-07,
|
| 2367 |
+
"loss": 0.3612,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.9015516318887106,
|
| 2372 |
+
"grad_norm": 1.9752335861803505,
|
| 2373 |
+
"learning_rate": 2.923779998329318e-07,
|
| 2374 |
+
"loss": 0.3564,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.904226859283039,
|
| 2379 |
+
"grad_norm": 2.158162194461494,
|
| 2380 |
+
"learning_rate": 2.76850110316636e-07,
|
| 2381 |
+
"loss": 0.3529,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.9069020866773676,
|
| 2386 |
+
"grad_norm": 2.0891285570667555,
|
| 2387 |
+
"learning_rate": 2.617341440859883e-07,
|
| 2388 |
+
"loss": 0.3492,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.9095773140716961,
|
| 2393 |
+
"grad_norm": 2.0909554368961816,
|
| 2394 |
+
"learning_rate": 2.470314194600376e-07,
|
| 2395 |
+
"loss": 0.3468,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.9122525414660246,
|
| 2400 |
+
"grad_norm": 2.1078161689569015,
|
| 2401 |
+
"learning_rate": 2.3274321871751436e-07,
|
| 2402 |
+
"loss": 0.3461,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.9149277688603531,
|
| 2407 |
+
"grad_norm": 2.2260290109873155,
|
| 2408 |
+
"learning_rate": 2.1887078798499272e-07,
|
| 2409 |
+
"loss": 0.3422,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9176029962546817,
|
| 2414 |
+
"grad_norm": 1.962831389446335,
|
| 2415 |
+
"learning_rate": 2.0541533712821527e-07,
|
| 2416 |
+
"loss": 0.3519,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.9202782236490101,
|
| 2421 |
+
"grad_norm": 1.930590364778258,
|
| 2422 |
+
"learning_rate": 1.923780396465741e-07,
|
| 2423 |
+
"loss": 0.3495,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.9229534510433387,
|
| 2428 |
+
"grad_norm": 2.021344220414449,
|
| 2429 |
+
"learning_rate": 1.7976003257076823e-07,
|
| 2430 |
+
"loss": 0.3488,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.9256286784376672,
|
| 2435 |
+
"grad_norm": 2.247214559592625,
|
| 2436 |
+
"learning_rate": 1.6756241636363413e-07,
|
| 2437 |
+
"loss": 0.3559,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.9283039058319957,
|
| 2442 |
+
"grad_norm": 2.134980518478257,
|
| 2443 |
+
"learning_rate": 1.557862548241762e-07,
|
| 2444 |
+
"loss": 0.3489,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.9309791332263242,
|
| 2449 |
+
"grad_norm": 2.0441140794451655,
|
| 2450 |
+
"learning_rate": 1.4443257499478447e-07,
|
| 2451 |
+
"loss": 0.3642,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.9336543606206528,
|
| 2456 |
+
"grad_norm": 2.109259605080949,
|
| 2457 |
+
"learning_rate": 1.3350236707166508e-07,
|
| 2458 |
+
"loss": 0.3587,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.9363295880149812,
|
| 2463 |
+
"grad_norm": 1.9915781898230962,
|
| 2464 |
+
"learning_rate": 1.229965843184805e-07,
|
| 2465 |
+
"loss": 0.3525,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.9390048154093098,
|
| 2470 |
+
"grad_norm": 2.127228440866396,
|
| 2471 |
+
"learning_rate": 1.1291614298321097e-07,
|
| 2472 |
+
"loss": 0.3432,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.9416800428036383,
|
| 2477 |
+
"grad_norm": 2.0576461493114833,
|
| 2478 |
+
"learning_rate": 1.0326192221824738e-07,
|
| 2479 |
+
"loss": 0.3535,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.9443552701979668,
|
| 2484 |
+
"grad_norm": 1.9060966657777367,
|
| 2485 |
+
"learning_rate": 9.403476400371425e-08,
|
| 2486 |
+
"loss": 0.357,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9470304975922953,
|
| 2491 |
+
"grad_norm": 2.1105664370498967,
|
| 2492 |
+
"learning_rate": 8.523547307404179e-08,
|
| 2493 |
+
"loss": 0.3522,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9497057249866239,
|
| 2498 |
+
"grad_norm": 1.9675175424050448,
|
| 2499 |
+
"learning_rate": 7.686481684777758e-08,
|
| 2500 |
+
"loss": 0.3507,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.9523809523809523,
|
| 2505 |
+
"grad_norm": 2.042054668983028,
|
| 2506 |
+
"learning_rate": 6.89235253606596e-08,
|
| 2507 |
+
"loss": 0.3433,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.9550561797752809,
|
| 2512 |
+
"grad_norm": 2.1508400346866097,
|
| 2513 |
+
"learning_rate": 6.141229120194714e-08,
|
| 2514 |
+
"loss": 0.339,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.9577314071696095,
|
| 2519 |
+
"grad_norm": 2.2052606813491997,
|
| 2520 |
+
"learning_rate": 5.4331769454016306e-08,
|
| 2521 |
+
"loss": 0.3517,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.9604066345639379,
|
| 2526 |
+
"grad_norm": 2.198267503179661,
|
| 2527 |
+
"learning_rate": 4.76825776352291e-08,
|
| 2528 |
+
"loss": 0.3551,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.9630818619582665,
|
| 2533 |
+
"grad_norm": 1.908998457696475,
|
| 2534 |
+
"learning_rate": 4.1465295646076484e-08,
|
| 2535 |
+
"loss": 0.3478,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.965757089352595,
|
| 2540 |
+
"grad_norm": 1.9536183637810103,
|
| 2541 |
+
"learning_rate": 3.568046571860384e-08,
|
| 2542 |
+
"loss": 0.3491,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.9684323167469235,
|
| 2547 |
+
"grad_norm": 1.9559281422900325,
|
| 2548 |
+
"learning_rate": 3.0328592369120443e-08,
|
| 2549 |
+
"loss": 0.3458,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.971107544141252,
|
| 2554 |
+
"grad_norm": 2.0469193106737666,
|
| 2555 |
+
"learning_rate": 2.541014235419914e-08,
|
| 2556 |
+
"loss": 0.3499,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.9737827715355806,
|
| 2561 |
+
"grad_norm": 2.1719220701561417,
|
| 2562 |
+
"learning_rate": 2.0925544629967763e-08,
|
| 2563 |
+
"loss": 0.3513,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.976457998929909,
|
| 2568 |
+
"grad_norm": 2.0542316026685015,
|
| 2569 |
+
"learning_rate": 1.6875190314700197e-08,
|
| 2570 |
+
"loss": 0.3469,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.9791332263242376,
|
| 2575 |
+
"grad_norm": 1.9390094223227383,
|
| 2576 |
+
"learning_rate": 1.3259432654703641e-08,
|
| 2577 |
+
"loss": 0.3597,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.9818084537185661,
|
| 2582 |
+
"grad_norm": 1.9765858839925157,
|
| 2583 |
+
"learning_rate": 1.0078586993511052e-08,
|
| 2584 |
+
"loss": 0.3415,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.9844836811128946,
|
| 2589 |
+
"grad_norm": 2.124520750341455,
|
| 2590 |
+
"learning_rate": 7.332930744380906e-09,
|
| 2591 |
+
"loss": 0.3558,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.9871589085072231,
|
| 2596 |
+
"grad_norm": 2.046502566885212,
|
| 2597 |
+
"learning_rate": 5.0227033660987804e-09,
|
| 2598 |
+
"loss": 0.3552,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.9898341359015517,
|
| 2603 |
+
"grad_norm": 2.166766019345835,
|
| 2604 |
+
"learning_rate": 3.1481063420985e-09,
|
| 2605 |
+
"loss": 0.3501,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.9925093632958801,
|
| 2610 |
+
"grad_norm": 2.1135732207205677,
|
| 2611 |
+
"learning_rate": 1.7093031628850899e-09,
|
| 2612 |
+
"loss": 0.342,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.9951845906902087,
|
| 2617 |
+
"grad_norm": 2.0348406821892095,
|
| 2618 |
+
"learning_rate": 7.064193117806151e-10,
|
| 2619 |
+
"loss": 0.3518,
|
| 2620 |
+
"step": 1860
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.9978598180845372,
|
| 2624 |
+
"grad_norm": 2.0634139080985343,
|
| 2625 |
+
"learning_rate": 1.3954225397516673e-10,
|
| 2626 |
+
"loss": 0.3575,
|
| 2627 |
+
"step": 1865
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"eval_runtime": 3.3837,
|
| 2632 |
+
"eval_samples_per_second": 2.955,
|
| 2633 |
+
"eval_steps_per_second": 0.887,
|
| 2634 |
+
"step": 1869
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 1.0,
|
| 2638 |
+
"step": 1869,
|
| 2639 |
+
"total_flos": 195665288232960.0,
|
| 2640 |
+
"train_loss": 0.5137065978787556,
|
| 2641 |
+
"train_runtime": 16737.1252,
|
| 2642 |
+
"train_samples_per_second": 1.786,
|
| 2643 |
+
"train_steps_per_second": 0.112
|
| 2644 |
+
}
|
| 2645 |
+
],
|
| 2646 |
+
"logging_steps": 5,
|
| 2647 |
+
"max_steps": 1869,
|
| 2648 |
+
"num_input_tokens_seen": 0,
|
| 2649 |
+
"num_train_epochs": 1,
|
| 2650 |
+
"save_steps": 100,
|
| 2651 |
+
"stateful_callbacks": {
|
| 2652 |
+
"TrainerControl": {
|
| 2653 |
+
"args": {
|
| 2654 |
+
"should_epoch_stop": false,
|
| 2655 |
+
"should_evaluate": false,
|
| 2656 |
+
"should_log": false,
|
| 2657 |
+
"should_save": true,
|
| 2658 |
+
"should_training_stop": true
|
| 2659 |
+
},
|
| 2660 |
+
"attributes": {}
|
| 2661 |
+
}
|
| 2662 |
+
},
|
| 2663 |
+
"total_flos": 195665288232960.0,
|
| 2664 |
+
"train_batch_size": 4,
|
| 2665 |
+
"trial_name": null,
|
| 2666 |
+
"trial_params": null
|
| 2667 |
+
}
|