Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep23_01-34-06_COE-CS-sv003/events.out.tfevents.1727055551.COE-CS-sv003.724332.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2660 -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_raredirtybatch16_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_raredirtybatch16_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": 194827769610240.0,
|
| 4 |
+
"train_loss": 0.5009698675307838,
|
| 5 |
+
"train_runtime": 16706.09,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.782,
|
| 8 |
+
"train_steps_per_second": 0.111
|
| 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_01-34-06_COE-CS-sv003/events.out.tfevents.1727055551.COE-CS-sv003.724332.0
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:d9edbd17cbcb2764f7c0946dc6ff730faa48f37d9fa80bd95a4e27698b9a42bc
|
| 3 |
+
size 84474
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 194827769610240.0,
|
| 4 |
+
"train_loss": 0.5009698675307838,
|
| 5 |
+
"train_runtime": 16706.09,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.782,
|
| 8 |
+
"train_steps_per_second": 0.111
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2660 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1861,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0005373455131649651,
|
| 13 |
+
"grad_norm": 23.072626458069166,
|
| 14 |
+
"learning_rate": 5.3475935828877005e-08,
|
| 15 |
+
"loss": 1.329,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0026867275658248252,
|
| 20 |
+
"grad_norm": 23.380544253320735,
|
| 21 |
+
"learning_rate": 2.6737967914438503e-07,
|
| 22 |
+
"loss": 1.3238,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0053734551316496505,
|
| 27 |
+
"grad_norm": 14.233532908496148,
|
| 28 |
+
"learning_rate": 5.347593582887701e-07,
|
| 29 |
+
"loss": 1.2647,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008060182697474477,
|
| 34 |
+
"grad_norm": 11.791057381257374,
|
| 35 |
+
"learning_rate": 8.021390374331551e-07,
|
| 36 |
+
"loss": 1.1476,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010746910263299301,
|
| 41 |
+
"grad_norm": 7.369104708436159,
|
| 42 |
+
"learning_rate": 1.0695187165775401e-06,
|
| 43 |
+
"loss": 1.0118,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.013433637829124127,
|
| 48 |
+
"grad_norm": 3.790654764997102,
|
| 49 |
+
"learning_rate": 1.3368983957219254e-06,
|
| 50 |
+
"loss": 0.9345,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.016120365394948953,
|
| 55 |
+
"grad_norm": 3.447275461870041,
|
| 56 |
+
"learning_rate": 1.6042780748663103e-06,
|
| 57 |
+
"loss": 0.8918,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.018807092960773777,
|
| 62 |
+
"grad_norm": 2.9186352407291847,
|
| 63 |
+
"learning_rate": 1.8716577540106954e-06,
|
| 64 |
+
"loss": 0.8518,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.021493820526598602,
|
| 69 |
+
"grad_norm": 2.9408795060935695,
|
| 70 |
+
"learning_rate": 2.1390374331550802e-06,
|
| 71 |
+
"loss": 0.844,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02418054809242343,
|
| 76 |
+
"grad_norm": 2.8790720251278565,
|
| 77 |
+
"learning_rate": 2.4064171122994653e-06,
|
| 78 |
+
"loss": 0.8318,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.026867275658248254,
|
| 83 |
+
"grad_norm": 2.963731808583039,
|
| 84 |
+
"learning_rate": 2.673796791443851e-06,
|
| 85 |
+
"loss": 0.8099,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02955400322407308,
|
| 90 |
+
"grad_norm": 2.8588219846284297,
|
| 91 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 92 |
+
"loss": 0.8054,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.032240730789897906,
|
| 97 |
+
"grad_norm": 3.105229156653952,
|
| 98 |
+
"learning_rate": 3.2085561497326205e-06,
|
| 99 |
+
"loss": 0.7913,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03492745835572273,
|
| 104 |
+
"grad_norm": 3.1413414626518943,
|
| 105 |
+
"learning_rate": 3.4759358288770056e-06,
|
| 106 |
+
"loss": 0.7867,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.037614185921547555,
|
| 111 |
+
"grad_norm": 3.132841956959321,
|
| 112 |
+
"learning_rate": 3.7433155080213907e-06,
|
| 113 |
+
"loss": 0.7893,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04030091348737238,
|
| 118 |
+
"grad_norm": 3.0623425732500142,
|
| 119 |
+
"learning_rate": 4.010695187165775e-06,
|
| 120 |
+
"loss": 0.7717,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.042987641053197204,
|
| 125 |
+
"grad_norm": 9.233814569420407,
|
| 126 |
+
"learning_rate": 4.2780748663101604e-06,
|
| 127 |
+
"loss": 0.7715,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.04567436861902203,
|
| 132 |
+
"grad_norm": 3.3097521575259368,
|
| 133 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 134 |
+
"loss": 0.761,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04836109618484686,
|
| 139 |
+
"grad_norm": 3.0349283160634597,
|
| 140 |
+
"learning_rate": 4.812834224598931e-06,
|
| 141 |
+
"loss": 0.7621,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.051047823750671684,
|
| 146 |
+
"grad_norm": 3.1760527715984153,
|
| 147 |
+
"learning_rate": 5.0802139037433165e-06,
|
| 148 |
+
"loss": 0.7591,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05373455131649651,
|
| 153 |
+
"grad_norm": 2.928755685153135,
|
| 154 |
+
"learning_rate": 5.347593582887702e-06,
|
| 155 |
+
"loss": 0.7433,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.05642127888232133,
|
| 160 |
+
"grad_norm": 3.0202006224727174,
|
| 161 |
+
"learning_rate": 5.614973262032086e-06,
|
| 162 |
+
"loss": 0.7314,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.05910800644814616,
|
| 167 |
+
"grad_norm": 3.1295278900578682,
|
| 168 |
+
"learning_rate": 5.882352941176471e-06,
|
| 169 |
+
"loss": 0.7483,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06179473401397098,
|
| 174 |
+
"grad_norm": 3.0863071896945167,
|
| 175 |
+
"learning_rate": 6.149732620320856e-06,
|
| 176 |
+
"loss": 0.7276,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06448146157979581,
|
| 181 |
+
"grad_norm": 3.0744127119070526,
|
| 182 |
+
"learning_rate": 6.417112299465241e-06,
|
| 183 |
+
"loss": 0.7183,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06716818914562063,
|
| 188 |
+
"grad_norm": 3.22926416708401,
|
| 189 |
+
"learning_rate": 6.684491978609626e-06,
|
| 190 |
+
"loss": 0.7242,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.06985491671144546,
|
| 195 |
+
"grad_norm": 2.9238184305563033,
|
| 196 |
+
"learning_rate": 6.951871657754011e-06,
|
| 197 |
+
"loss": 0.7194,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07254164427727028,
|
| 202 |
+
"grad_norm": 2.907399933470749,
|
| 203 |
+
"learning_rate": 7.219251336898396e-06,
|
| 204 |
+
"loss": 0.7204,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07522837184309511,
|
| 209 |
+
"grad_norm": 2.8941698993873137,
|
| 210 |
+
"learning_rate": 7.486631016042781e-06,
|
| 211 |
+
"loss": 0.6986,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07791509940891994,
|
| 216 |
+
"grad_norm": 2.899562495835514,
|
| 217 |
+
"learning_rate": 7.754010695187166e-06,
|
| 218 |
+
"loss": 0.7021,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08060182697474476,
|
| 223 |
+
"grad_norm": 2.8740571869341687,
|
| 224 |
+
"learning_rate": 8.02139037433155e-06,
|
| 225 |
+
"loss": 0.7096,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08328855454056959,
|
| 230 |
+
"grad_norm": 2.912059141124366,
|
| 231 |
+
"learning_rate": 8.288770053475937e-06,
|
| 232 |
+
"loss": 0.7012,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.08597528210639441,
|
| 237 |
+
"grad_norm": 2.933852566630193,
|
| 238 |
+
"learning_rate": 8.556149732620321e-06,
|
| 239 |
+
"loss": 0.6909,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08866200967221924,
|
| 244 |
+
"grad_norm": 2.954361982135904,
|
| 245 |
+
"learning_rate": 8.823529411764707e-06,
|
| 246 |
+
"loss": 0.6947,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09134873723804406,
|
| 251 |
+
"grad_norm": 2.914429965048127,
|
| 252 |
+
"learning_rate": 9.090909090909091e-06,
|
| 253 |
+
"loss": 0.7064,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09403546480386889,
|
| 258 |
+
"grad_norm": 2.824165175450085,
|
| 259 |
+
"learning_rate": 9.358288770053477e-06,
|
| 260 |
+
"loss": 0.6962,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09672219236969372,
|
| 265 |
+
"grad_norm": 2.7629699563001724,
|
| 266 |
+
"learning_rate": 9.625668449197861e-06,
|
| 267 |
+
"loss": 0.7093,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09940891993551854,
|
| 272 |
+
"grad_norm": 2.9700788007957484,
|
| 273 |
+
"learning_rate": 9.893048128342247e-06,
|
| 274 |
+
"loss": 0.7001,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.10209564750134337,
|
| 279 |
+
"grad_norm": 2.720187963907155,
|
| 280 |
+
"learning_rate": 9.999920755303033e-06,
|
| 281 |
+
"loss": 0.6972,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.10478237506716818,
|
| 286 |
+
"grad_norm": 2.579060861199631,
|
| 287 |
+
"learning_rate": 9.999436491251425e-06,
|
| 288 |
+
"loss": 0.7011,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.10746910263299302,
|
| 293 |
+
"grad_norm": 2.650831290761427,
|
| 294 |
+
"learning_rate": 9.998512030567253e-06,
|
| 295 |
+
"loss": 0.7045,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.11015583019881783,
|
| 300 |
+
"grad_norm": 3.3197406459470673,
|
| 301 |
+
"learning_rate": 9.99714745464859e-06,
|
| 302 |
+
"loss": 0.6992,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11284255776464266,
|
| 307 |
+
"grad_norm": 3.0709444563569126,
|
| 308 |
+
"learning_rate": 9.995342883645325e-06,
|
| 309 |
+
"loss": 0.708,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.1155292853304675,
|
| 314 |
+
"grad_norm": 2.815374931010047,
|
| 315 |
+
"learning_rate": 9.993098476448576e-06,
|
| 316 |
+
"loss": 0.7011,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.11821601289629231,
|
| 321 |
+
"grad_norm": 2.9613320208688005,
|
| 322 |
+
"learning_rate": 9.990414430676716e-06,
|
| 323 |
+
"loss": 0.6821,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.12090274046211714,
|
| 328 |
+
"grad_norm": 2.690351994232397,
|
| 329 |
+
"learning_rate": 9.987290982657961e-06,
|
| 330 |
+
"loss": 0.6848,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12358946802794196,
|
| 335 |
+
"grad_norm": 3.5601408393747445,
|
| 336 |
+
"learning_rate": 9.983728407409565e-06,
|
| 337 |
+
"loss": 0.6832,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.1262761955937668,
|
| 342 |
+
"grad_norm": 2.4701820214975014,
|
| 343 |
+
"learning_rate": 9.979727018613607e-06,
|
| 344 |
+
"loss": 0.6934,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12896292315959162,
|
| 349 |
+
"grad_norm": 2.4626384928709983,
|
| 350 |
+
"learning_rate": 9.975287168589369e-06,
|
| 351 |
+
"loss": 0.6785,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.13164965072541646,
|
| 356 |
+
"grad_norm": 2.588440598744194,
|
| 357 |
+
"learning_rate": 9.970409248262314e-06,
|
| 358 |
+
"loss": 0.6978,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13433637829124126,
|
| 363 |
+
"grad_norm": 2.6880919710650413,
|
| 364 |
+
"learning_rate": 9.965093687129669e-06,
|
| 365 |
+
"loss": 0.6808,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1370231058570661,
|
| 370 |
+
"grad_norm": 2.9087730515287955,
|
| 371 |
+
"learning_rate": 9.959340953222602e-06,
|
| 372 |
+
"loss": 0.6758,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.13970983342289092,
|
| 377 |
+
"grad_norm": 2.6772738824086075,
|
| 378 |
+
"learning_rate": 9.953151553065019e-06,
|
| 379 |
+
"loss": 0.6698,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.14239656098871575,
|
| 384 |
+
"grad_norm": 2.669218732871304,
|
| 385 |
+
"learning_rate": 9.94652603162896e-06,
|
| 386 |
+
"loss": 0.6939,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14508328855454056,
|
| 391 |
+
"grad_norm": 2.4902462796339457,
|
| 392 |
+
"learning_rate": 9.939464972286618e-06,
|
| 393 |
+
"loss": 0.6702,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1477700161203654,
|
| 398 |
+
"grad_norm": 2.4766182391586975,
|
| 399 |
+
"learning_rate": 9.931968996758972e-06,
|
| 400 |
+
"loss": 0.6697,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15045674368619022,
|
| 405 |
+
"grad_norm": 2.5255485155595228,
|
| 406 |
+
"learning_rate": 9.924038765061042e-06,
|
| 407 |
+
"loss": 0.6665,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.15314347125201505,
|
| 412 |
+
"grad_norm": 2.5656888228811794,
|
| 413 |
+
"learning_rate": 9.915674975443779e-06,
|
| 414 |
+
"loss": 0.6565,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15583019881783988,
|
| 419 |
+
"grad_norm": 2.825801360492887,
|
| 420 |
+
"learning_rate": 9.906878364332586e-06,
|
| 421 |
+
"loss": 0.6642,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.15851692638366469,
|
| 426 |
+
"grad_norm": 2.6497249215881253,
|
| 427 |
+
"learning_rate": 9.897649706262474e-06,
|
| 428 |
+
"loss": 0.6624,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16120365394948952,
|
| 433 |
+
"grad_norm": 2.6523672302785575,
|
| 434 |
+
"learning_rate": 9.88798981380986e-06,
|
| 435 |
+
"loss": 0.6659,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.16389038151531435,
|
| 440 |
+
"grad_norm": 2.6257923259309495,
|
| 441 |
+
"learning_rate": 9.877899537521028e-06,
|
| 442 |
+
"loss": 0.6533,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.16657710908113918,
|
| 447 |
+
"grad_norm": 2.465767578464491,
|
| 448 |
+
"learning_rate": 9.867379765837237e-06,
|
| 449 |
+
"loss": 0.6518,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.169263836646964,
|
| 454 |
+
"grad_norm": 2.556282218650964,
|
| 455 |
+
"learning_rate": 9.85643142501649e-06,
|
| 456 |
+
"loss": 0.6559,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17195056421278881,
|
| 461 |
+
"grad_norm": 2.6286087389340227,
|
| 462 |
+
"learning_rate": 9.845055479051986e-06,
|
| 463 |
+
"loss": 0.6469,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.17463729177861365,
|
| 468 |
+
"grad_norm": 2.419535618698552,
|
| 469 |
+
"learning_rate": 9.833252929587231e-06,
|
| 470 |
+
"loss": 0.6631,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.17732401934443848,
|
| 475 |
+
"grad_norm": 2.4542391410254956,
|
| 476 |
+
"learning_rate": 9.821024815827854e-06,
|
| 477 |
+
"loss": 0.6591,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1800107469102633,
|
| 482 |
+
"grad_norm": 2.4908873755968997,
|
| 483 |
+
"learning_rate": 9.808372214450093e-06,
|
| 484 |
+
"loss": 0.6658,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.1826974744760881,
|
| 489 |
+
"grad_norm": 2.3733848426387176,
|
| 490 |
+
"learning_rate": 9.795296239506011e-06,
|
| 491 |
+
"loss": 0.662,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.18538420204191294,
|
| 496 |
+
"grad_norm": 2.865296798119886,
|
| 497 |
+
"learning_rate": 9.781798042325392e-06,
|
| 498 |
+
"loss": 0.6526,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.18807092960773777,
|
| 503 |
+
"grad_norm": 2.487445934484789,
|
| 504 |
+
"learning_rate": 9.767878811414373e-06,
|
| 505 |
+
"loss": 0.6525,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.1907576571735626,
|
| 510 |
+
"grad_norm": 2.388699669948045,
|
| 511 |
+
"learning_rate": 9.753539772350792e-06,
|
| 512 |
+
"loss": 0.647,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19344438473938744,
|
| 517 |
+
"grad_norm": 2.445554737991476,
|
| 518 |
+
"learning_rate": 9.738782187676282e-06,
|
| 519 |
+
"loss": 0.6425,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.19613111230521224,
|
| 524 |
+
"grad_norm": 2.435104584478995,
|
| 525 |
+
"learning_rate": 9.723607356785103e-06,
|
| 526 |
+
"loss": 0.6443,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.19881783987103707,
|
| 531 |
+
"grad_norm": 2.479158175926532,
|
| 532 |
+
"learning_rate": 9.70801661580973e-06,
|
| 533 |
+
"loss": 0.6575,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.2015045674368619,
|
| 538 |
+
"grad_norm": 2.637755494092567,
|
| 539 |
+
"learning_rate": 9.692011337503212e-06,
|
| 540 |
+
"loss": 0.6421,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.20419129500268673,
|
| 545 |
+
"grad_norm": 2.520737872507786,
|
| 546 |
+
"learning_rate": 9.675592931118293e-06,
|
| 547 |
+
"loss": 0.6358,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.20687802256851157,
|
| 552 |
+
"grad_norm": 2.3907603747141675,
|
| 553 |
+
"learning_rate": 9.658762842283343e-06,
|
| 554 |
+
"loss": 0.6285,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.20956475013433637,
|
| 559 |
+
"grad_norm": 2.3651549722988023,
|
| 560 |
+
"learning_rate": 9.641522552875055e-06,
|
| 561 |
+
"loss": 0.6119,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2122514777001612,
|
| 566 |
+
"grad_norm": 2.5208115737245604,
|
| 567 |
+
"learning_rate": 9.62387358088798e-06,
|
| 568 |
+
"loss": 0.6333,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21493820526598603,
|
| 573 |
+
"grad_norm": 2.6819070319357037,
|
| 574 |
+
"learning_rate": 9.605817480300863e-06,
|
| 575 |
+
"loss": 0.6205,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.21762493283181086,
|
| 580 |
+
"grad_norm": 2.356493009815594,
|
| 581 |
+
"learning_rate": 9.587355840939813e-06,
|
| 582 |
+
"loss": 0.64,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22031166039763567,
|
| 587 |
+
"grad_norm": 2.405371194871644,
|
| 588 |
+
"learning_rate": 9.568490288338324e-06,
|
| 589 |
+
"loss": 0.6245,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2229983879634605,
|
| 594 |
+
"grad_norm": 2.6012482105829706,
|
| 595 |
+
"learning_rate": 9.549222483594154e-06,
|
| 596 |
+
"loss": 0.6451,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22568511552928533,
|
| 601 |
+
"grad_norm": 2.3956259391703196,
|
| 602 |
+
"learning_rate": 9.529554123223053e-06,
|
| 603 |
+
"loss": 0.6223,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.22837184309511016,
|
| 608 |
+
"grad_norm": 2.398583860789219,
|
| 609 |
+
"learning_rate": 9.5094869390094e-06,
|
| 610 |
+
"loss": 0.6427,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.231058570660935,
|
| 615 |
+
"grad_norm": 2.5232663534614863,
|
| 616 |
+
"learning_rate": 9.48902269785371e-06,
|
| 617 |
+
"loss": 0.6264,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2337452982267598,
|
| 622 |
+
"grad_norm": 2.4227785562286033,
|
| 623 |
+
"learning_rate": 9.468163201617063e-06,
|
| 624 |
+
"loss": 0.6172,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23643202579258463,
|
| 629 |
+
"grad_norm": 2.4898638907719586,
|
| 630 |
+
"learning_rate": 9.446910286962453e-06,
|
| 631 |
+
"loss": 0.6186,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.23911875335840946,
|
| 636 |
+
"grad_norm": 2.3600937624812524,
|
| 637 |
+
"learning_rate": 9.425265825193077e-06,
|
| 638 |
+
"loss": 0.6009,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2418054809242343,
|
| 643 |
+
"grad_norm": 2.479426617963906,
|
| 644 |
+
"learning_rate": 9.403231722087554e-06,
|
| 645 |
+
"loss": 0.6373,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.24449220849005912,
|
| 650 |
+
"grad_norm": 2.4357419818938117,
|
| 651 |
+
"learning_rate": 9.380809917732132e-06,
|
| 652 |
+
"loss": 0.6076,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.24717893605588392,
|
| 657 |
+
"grad_norm": 2.47734706096724,
|
| 658 |
+
"learning_rate": 9.358002386349862e-06,
|
| 659 |
+
"loss": 0.6052,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.24986566362170876,
|
| 664 |
+
"grad_norm": 2.545179042557431,
|
| 665 |
+
"learning_rate": 9.334811136126778e-06,
|
| 666 |
+
"loss": 0.6067,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.2525523911875336,
|
| 671 |
+
"grad_norm": 2.576572600102202,
|
| 672 |
+
"learning_rate": 9.31123820903506e-06,
|
| 673 |
+
"loss": 0.6035,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.2552391187533584,
|
| 678 |
+
"grad_norm": 2.4612256004699145,
|
| 679 |
+
"learning_rate": 9.287285680653254e-06,
|
| 680 |
+
"loss": 0.606,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.25792584631918325,
|
| 685 |
+
"grad_norm": 2.495237864289767,
|
| 686 |
+
"learning_rate": 9.262955659983522e-06,
|
| 687 |
+
"loss": 0.5942,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.2606125738850081,
|
| 692 |
+
"grad_norm": 2.65866167773882,
|
| 693 |
+
"learning_rate": 9.238250289265921e-06,
|
| 694 |
+
"loss": 0.599,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.2632993014508329,
|
| 699 |
+
"grad_norm": 2.473870495050297,
|
| 700 |
+
"learning_rate": 9.21317174378982e-06,
|
| 701 |
+
"loss": 0.612,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.2659860290166577,
|
| 706 |
+
"grad_norm": 2.3022323203953,
|
| 707 |
+
"learning_rate": 9.187722231702326e-06,
|
| 708 |
+
"loss": 0.5794,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2686727565824825,
|
| 713 |
+
"grad_norm": 2.3360448253147643,
|
| 714 |
+
"learning_rate": 9.161903993813892e-06,
|
| 715 |
+
"loss": 0.5821,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.27135948414830735,
|
| 720 |
+
"grad_norm": 2.4400501057412454,
|
| 721 |
+
"learning_rate": 9.135719303400995e-06,
|
| 722 |
+
"loss": 0.5969,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.2740462117141322,
|
| 727 |
+
"grad_norm": 2.324402047254847,
|
| 728 |
+
"learning_rate": 9.10917046600598e-06,
|
| 729 |
+
"loss": 0.5914,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.276732939279957,
|
| 734 |
+
"grad_norm": 2.4328149953899296,
|
| 735 |
+
"learning_rate": 9.082259819234063e-06,
|
| 736 |
+
"loss": 0.5871,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.27941966684578184,
|
| 741 |
+
"grad_norm": 2.326659710915374,
|
| 742 |
+
"learning_rate": 9.054989732547507e-06,
|
| 743 |
+
"loss": 0.5874,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.2821063944116067,
|
| 748 |
+
"grad_norm": 2.4409777215420942,
|
| 749 |
+
"learning_rate": 9.027362607056986e-06,
|
| 750 |
+
"loss": 0.5964,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2847931219774315,
|
| 755 |
+
"grad_norm": 2.412955363836415,
|
| 756 |
+
"learning_rate": 8.999380875310176e-06,
|
| 757 |
+
"loss": 0.5877,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.28747984954325634,
|
| 762 |
+
"grad_norm": 2.8194077899428516,
|
| 763 |
+
"learning_rate": 8.971047001077561e-06,
|
| 764 |
+
"loss": 0.5883,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.2901665771090811,
|
| 769 |
+
"grad_norm": 2.469304660089161,
|
| 770 |
+
"learning_rate": 8.942363479135516e-06,
|
| 771 |
+
"loss": 0.5801,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.29285330467490595,
|
| 776 |
+
"grad_norm": 2.3564533376477192,
|
| 777 |
+
"learning_rate": 8.913332835046629e-06,
|
| 778 |
+
"loss": 0.576,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.2955400322407308,
|
| 783 |
+
"grad_norm": 2.4491464187209067,
|
| 784 |
+
"learning_rate": 8.883957624937333e-06,
|
| 785 |
+
"loss": 0.5792,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2982267598065556,
|
| 790 |
+
"grad_norm": 2.3159629602291276,
|
| 791 |
+
"learning_rate": 8.854240435272842e-06,
|
| 792 |
+
"loss": 0.5617,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.30091348737238044,
|
| 797 |
+
"grad_norm": 2.5317785480271584,
|
| 798 |
+
"learning_rate": 8.824183882629411e-06,
|
| 799 |
+
"loss": 0.5669,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.30360021493820527,
|
| 804 |
+
"grad_norm": 2.3852078136194135,
|
| 805 |
+
"learning_rate": 8.793790613463956e-06,
|
| 806 |
+
"loss": 0.5697,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3062869425040301,
|
| 811 |
+
"grad_norm": 2.4921927583022168,
|
| 812 |
+
"learning_rate": 8.763063303881021e-06,
|
| 813 |
+
"loss": 0.5796,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.30897367006985493,
|
| 818 |
+
"grad_norm": 9.308745310175,
|
| 819 |
+
"learning_rate": 8.73200465939717e-06,
|
| 820 |
+
"loss": 0.5735,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31166039763567976,
|
| 825 |
+
"grad_norm": 2.4517036683344458,
|
| 826 |
+
"learning_rate": 8.700617414702746e-06,
|
| 827 |
+
"loss": 0.5671,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.31434712520150454,
|
| 832 |
+
"grad_norm": 2.2949061651822635,
|
| 833 |
+
"learning_rate": 8.668904333421098e-06,
|
| 834 |
+
"loss": 0.5696,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31703385276732937,
|
| 839 |
+
"grad_norm": 2.2916177476898096,
|
| 840 |
+
"learning_rate": 8.636868207865244e-06,
|
| 841 |
+
"loss": 0.5756,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.3197205803331542,
|
| 846 |
+
"grad_norm": 2.5518854172821297,
|
| 847 |
+
"learning_rate": 8.604511858792006e-06,
|
| 848 |
+
"loss": 0.5622,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32240730789897903,
|
| 853 |
+
"grad_norm": 2.4475160043733797,
|
| 854 |
+
"learning_rate": 8.571838135153645e-06,
|
| 855 |
+
"loss": 0.5525,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.32509403546480387,
|
| 860 |
+
"grad_norm": 2.3488225651794497,
|
| 861 |
+
"learning_rate": 8.538849913847019e-06,
|
| 862 |
+
"loss": 0.569,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3277807630306287,
|
| 867 |
+
"grad_norm": 2.353785375547004,
|
| 868 |
+
"learning_rate": 8.505550099460264e-06,
|
| 869 |
+
"loss": 0.5575,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.33046749059645353,
|
| 874 |
+
"grad_norm": 2.5058455114214166,
|
| 875 |
+
"learning_rate": 8.471941624017058e-06,
|
| 876 |
+
"loss": 0.5497,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33315421816227836,
|
| 881 |
+
"grad_norm": 2.4037582668437674,
|
| 882 |
+
"learning_rate": 8.43802744671845e-06,
|
| 883 |
+
"loss": 0.5592,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.3358409457281032,
|
| 888 |
+
"grad_norm": 2.3703138788584206,
|
| 889 |
+
"learning_rate": 8.403810553682307e-06,
|
| 890 |
+
"loss": 0.55,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.338527673293928,
|
| 895 |
+
"grad_norm": 2.4422133082637605,
|
| 896 |
+
"learning_rate": 8.369293957680397e-06,
|
| 897 |
+
"loss": 0.5451,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.3412144008597528,
|
| 902 |
+
"grad_norm": 2.372256863029062,
|
| 903 |
+
"learning_rate": 8.334480697873101e-06,
|
| 904 |
+
"loss": 0.5616,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34390112842557763,
|
| 909 |
+
"grad_norm": 2.30267735280899,
|
| 910 |
+
"learning_rate": 8.299373839541829e-06,
|
| 911 |
+
"loss": 0.547,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.34658785599140246,
|
| 916 |
+
"grad_norm": 2.312324577995851,
|
| 917 |
+
"learning_rate": 8.26397647381912e-06,
|
| 918 |
+
"loss": 0.5406,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3492745835572273,
|
| 923 |
+
"grad_norm": 2.4374915255270175,
|
| 924 |
+
"learning_rate": 8.228291717416472e-06,
|
| 925 |
+
"loss": 0.5388,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3519613111230521,
|
| 930 |
+
"grad_norm": 2.3871133470130674,
|
| 931 |
+
"learning_rate": 8.192322712349917e-06,
|
| 932 |
+
"loss": 0.5432,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35464803868887695,
|
| 937 |
+
"grad_norm": 2.519969391683205,
|
| 938 |
+
"learning_rate": 8.15607262566337e-06,
|
| 939 |
+
"loss": 0.5348,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.3573347662547018,
|
| 944 |
+
"grad_norm": 2.4866718815954623,
|
| 945 |
+
"learning_rate": 8.119544649149762e-06,
|
| 946 |
+
"loss": 0.5567,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3600214938205266,
|
| 951 |
+
"grad_norm": 2.401099368264956,
|
| 952 |
+
"learning_rate": 8.08274199907003e-06,
|
| 953 |
+
"loss": 0.5409,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.36270822138635145,
|
| 958 |
+
"grad_norm": 2.320605485178993,
|
| 959 |
+
"learning_rate": 8.0456679158699e-06,
|
| 960 |
+
"loss": 0.5283,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.3653949489521762,
|
| 965 |
+
"grad_norm": 2.3005736041616642,
|
| 966 |
+
"learning_rate": 8.008325663894586e-06,
|
| 967 |
+
"loss": 0.5368,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.36808167651800106,
|
| 972 |
+
"grad_norm": 2.305647834819274,
|
| 973 |
+
"learning_rate": 7.970718531101365e-06,
|
| 974 |
+
"loss": 0.5398,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.3707684040838259,
|
| 979 |
+
"grad_norm": 2.3268228923372263,
|
| 980 |
+
"learning_rate": 7.932849828770062e-06,
|
| 981 |
+
"loss": 0.5348,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.3734551316496507,
|
| 986 |
+
"grad_norm": 2.2813438553059053,
|
| 987 |
+
"learning_rate": 7.89472289121151e-06,
|
| 988 |
+
"loss": 0.5602,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37614185921547555,
|
| 993 |
+
"grad_norm": 2.2064861994852816,
|
| 994 |
+
"learning_rate": 7.856341075473963e-06,
|
| 995 |
+
"loss": 0.5227,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.3788285867813004,
|
| 1000 |
+
"grad_norm": 2.385886752618868,
|
| 1001 |
+
"learning_rate": 7.817707761047498e-06,
|
| 1002 |
+
"loss": 0.5292,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.3815153143471252,
|
| 1007 |
+
"grad_norm": 2.3717077533920867,
|
| 1008 |
+
"learning_rate": 7.77882634956647e-06,
|
| 1009 |
+
"loss": 0.5332,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.38420204191295004,
|
| 1014 |
+
"grad_norm": 2.389159454524817,
|
| 1015 |
+
"learning_rate": 7.739700264509993e-06,
|
| 1016 |
+
"loss": 0.5236,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.3868887694787749,
|
| 1021 |
+
"grad_norm": 2.314814719990629,
|
| 1022 |
+
"learning_rate": 7.700332950900504e-06,
|
| 1023 |
+
"loss": 0.5217,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.38957549704459965,
|
| 1028 |
+
"grad_norm": 2.207891685389126,
|
| 1029 |
+
"learning_rate": 7.660727875000432e-06,
|
| 1030 |
+
"loss": 0.5078,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3922622246104245,
|
| 1035 |
+
"grad_norm": 2.3264819673930432,
|
| 1036 |
+
"learning_rate": 7.6208885240069995e-06,
|
| 1037 |
+
"loss": 0.5267,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.3949489521762493,
|
| 1042 |
+
"grad_norm": 2.288819911752258,
|
| 1043 |
+
"learning_rate": 7.5808184057451765e-06,
|
| 1044 |
+
"loss": 0.5067,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39763567974207414,
|
| 1049 |
+
"grad_norm": 2.3653593555899857,
|
| 1050 |
+
"learning_rate": 7.540521048358814e-06,
|
| 1051 |
+
"loss": 0.5344,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.400322407307899,
|
| 1056 |
+
"grad_norm": 2.4648359924535743,
|
| 1057 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1058 |
+
"loss": 0.5227,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4030091348737238,
|
| 1063 |
+
"grad_norm": 2.409473996165666,
|
| 1064 |
+
"learning_rate": 7.459258828516645e-06,
|
| 1065 |
+
"loss": 0.5096,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.40569586243954864,
|
| 1070 |
+
"grad_norm": 2.3668323179746236,
|
| 1071 |
+
"learning_rate": 7.418301121138335e-06,
|
| 1072 |
+
"loss": 0.5171,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.40838259000537347,
|
| 1077 |
+
"grad_norm": 2.4782926067309825,
|
| 1078 |
+
"learning_rate": 7.3771304841604764e-06,
|
| 1079 |
+
"loss": 0.51,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.4110693175711983,
|
| 1084 |
+
"grad_norm": 2.267794928141394,
|
| 1085 |
+
"learning_rate": 7.335750542626772e-06,
|
| 1086 |
+
"loss": 0.5245,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41375604513702313,
|
| 1091 |
+
"grad_norm": 2.318079683575523,
|
| 1092 |
+
"learning_rate": 7.294164940010031e-06,
|
| 1093 |
+
"loss": 0.5124,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.4164427727028479,
|
| 1098 |
+
"grad_norm": 2.1909268149999988,
|
| 1099 |
+
"learning_rate": 7.2523773378913655e-06,
|
| 1100 |
+
"loss": 0.5168,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.41912950026867274,
|
| 1105 |
+
"grad_norm": 2.2456539972858773,
|
| 1106 |
+
"learning_rate": 7.210391415637797e-06,
|
| 1107 |
+
"loss": 0.4946,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.42181622783449757,
|
| 1112 |
+
"grad_norm": 2.4974603199079133,
|
| 1113 |
+
"learning_rate": 7.168210870078277e-06,
|
| 1114 |
+
"loss": 0.5064,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.4245029554003224,
|
| 1119 |
+
"grad_norm": 2.334444583921718,
|
| 1120 |
+
"learning_rate": 7.125839415178204e-06,
|
| 1121 |
+
"loss": 0.5116,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.42718968296614723,
|
| 1126 |
+
"grad_norm": 2.397330148256394,
|
| 1127 |
+
"learning_rate": 7.083280781712394e-06,
|
| 1128 |
+
"loss": 0.5081,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.42987641053197206,
|
| 1133 |
+
"grad_norm": 2.5416270893996273,
|
| 1134 |
+
"learning_rate": 7.0405387169365965e-06,
|
| 1135 |
+
"loss": 0.499,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.4325631380977969,
|
| 1140 |
+
"grad_norm": 2.3363347223952657,
|
| 1141 |
+
"learning_rate": 6.9976169842575526e-06,
|
| 1142 |
+
"loss": 0.5049,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4352498656636217,
|
| 1147 |
+
"grad_norm": 2.296216857638828,
|
| 1148 |
+
"learning_rate": 6.9545193629016215e-06,
|
| 1149 |
+
"loss": 0.5168,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.43793659322944656,
|
| 1154 |
+
"grad_norm": 2.4900891751826237,
|
| 1155 |
+
"learning_rate": 6.911249647582036e-06,
|
| 1156 |
+
"loss": 0.4939,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44062332079527133,
|
| 1161 |
+
"grad_norm": 2.3708479871646797,
|
| 1162 |
+
"learning_rate": 6.867811648164769e-06,
|
| 1163 |
+
"loss": 0.4968,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.44331004836109617,
|
| 1168 |
+
"grad_norm": 2.2942739105778007,
|
| 1169 |
+
"learning_rate": 6.824209189333082e-06,
|
| 1170 |
+
"loss": 0.4892,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.445996775926921,
|
| 1175 |
+
"grad_norm": 2.298491349290504,
|
| 1176 |
+
"learning_rate": 6.780446110250766e-06,
|
| 1177 |
+
"loss": 0.5064,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.4486835034927458,
|
| 1182 |
+
"grad_norm": 2.3571392373027624,
|
| 1183 |
+
"learning_rate": 6.736526264224101e-06,
|
| 1184 |
+
"loss": 0.5005,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45137023105857066,
|
| 1189 |
+
"grad_norm": 2.459885767558715,
|
| 1190 |
+
"learning_rate": 6.692453518362587e-06,
|
| 1191 |
+
"loss": 0.4951,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.4540569586243955,
|
| 1196 |
+
"grad_norm": 2.411449421942393,
|
| 1197 |
+
"learning_rate": 6.648231753238431e-06,
|
| 1198 |
+
"loss": 0.4828,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.4567436861902203,
|
| 1203 |
+
"grad_norm": 2.404363576863236,
|
| 1204 |
+
"learning_rate": 6.603864862544879e-06,
|
| 1205 |
+
"loss": 0.493,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.45943041375604515,
|
| 1210 |
+
"grad_norm": 2.2737487815721478,
|
| 1211 |
+
"learning_rate": 6.5593567527533715e-06,
|
| 1212 |
+
"loss": 0.4744,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46211714132187,
|
| 1217 |
+
"grad_norm": 2.3678978985955186,
|
| 1218 |
+
"learning_rate": 6.514711342769588e-06,
|
| 1219 |
+
"loss": 0.5012,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.4648038688876948,
|
| 1224 |
+
"grad_norm": 2.356303245264604,
|
| 1225 |
+
"learning_rate": 6.469932563588386e-06,
|
| 1226 |
+
"loss": 0.4973,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.4674905964535196,
|
| 1231 |
+
"grad_norm": 2.7020262831984527,
|
| 1232 |
+
"learning_rate": 6.425024357947677e-06,
|
| 1233 |
+
"loss": 0.4918,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.4701773240193444,
|
| 1238 |
+
"grad_norm": 2.3340485214143745,
|
| 1239 |
+
"learning_rate": 6.3799906799812805e-06,
|
| 1240 |
+
"loss": 0.4982,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47286405158516925,
|
| 1245 |
+
"grad_norm": 2.4191389152178373,
|
| 1246 |
+
"learning_rate": 6.334835494870759e-06,
|
| 1247 |
+
"loss": 0.4751,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.4755507791509941,
|
| 1252 |
+
"grad_norm": 2.272119239990629,
|
| 1253 |
+
"learning_rate": 6.289562778496285e-06,
|
| 1254 |
+
"loss": 0.4872,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.4782375067168189,
|
| 1259 |
+
"grad_norm": 2.300477262266863,
|
| 1260 |
+
"learning_rate": 6.244176517086573e-06,
|
| 1261 |
+
"loss": 0.4821,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.48092423428264375,
|
| 1266 |
+
"grad_norm": 2.446204046472319,
|
| 1267 |
+
"learning_rate": 6.1986807068678926e-06,
|
| 1268 |
+
"loss": 0.4823,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.4836109618484686,
|
| 1273 |
+
"grad_norm": 2.290872783259082,
|
| 1274 |
+
"learning_rate": 6.153079353712201e-06,
|
| 1275 |
+
"loss": 0.4683,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.4862976894142934,
|
| 1280 |
+
"grad_norm": 2.311264668993125,
|
| 1281 |
+
"learning_rate": 6.107376472784438e-06,
|
| 1282 |
+
"loss": 0.4759,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.48898441698011824,
|
| 1287 |
+
"grad_norm": 2.1766053144740805,
|
| 1288 |
+
"learning_rate": 6.061576088188981e-06,
|
| 1289 |
+
"loss": 0.4541,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.491671144545943,
|
| 1294 |
+
"grad_norm": 2.2863598186899563,
|
| 1295 |
+
"learning_rate": 6.015682232615336e-06,
|
| 1296 |
+
"loss": 0.4751,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49435787211176785,
|
| 1301 |
+
"grad_norm": 2.3157344313618453,
|
| 1302 |
+
"learning_rate": 5.969698946983055e-06,
|
| 1303 |
+
"loss": 0.4579,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.4970445996775927,
|
| 1308 |
+
"grad_norm": 2.4556667211388308,
|
| 1309 |
+
"learning_rate": 5.923630280085948e-06,
|
| 1310 |
+
"loss": 0.4667,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.4997313272434175,
|
| 1315 |
+
"grad_norm": 2.2693647056660575,
|
| 1316 |
+
"learning_rate": 5.877480288235569e-06,
|
| 1317 |
+
"loss": 0.4642,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5024180548092424,
|
| 1322 |
+
"grad_norm": 2.299235513307737,
|
| 1323 |
+
"learning_rate": 5.831253034904083e-06,
|
| 1324 |
+
"loss": 0.4625,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5051047823750672,
|
| 1329 |
+
"grad_norm": 2.2594758653976603,
|
| 1330 |
+
"learning_rate": 5.7849525903664636e-06,
|
| 1331 |
+
"loss": 0.4741,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.507791509940892,
|
| 1336 |
+
"grad_norm": 2.346200404836091,
|
| 1337 |
+
"learning_rate": 5.738583031342123e-06,
|
| 1338 |
+
"loss": 0.4533,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5104782375067168,
|
| 1343 |
+
"grad_norm": 2.198398726512657,
|
| 1344 |
+
"learning_rate": 5.692148440635946e-06,
|
| 1345 |
+
"loss": 0.4561,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.5131649650725416,
|
| 1350 |
+
"grad_norm": 2.3681691462263466,
|
| 1351 |
+
"learning_rate": 5.645652906778808e-06,
|
| 1352 |
+
"loss": 0.4621,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5158516926383665,
|
| 1357 |
+
"grad_norm": 2.344944047074419,
|
| 1358 |
+
"learning_rate": 5.599100523667586e-06,
|
| 1359 |
+
"loss": 0.4599,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.5185384202041913,
|
| 1364 |
+
"grad_norm": 2.2092289217419085,
|
| 1365 |
+
"learning_rate": 5.552495390204691e-06,
|
| 1366 |
+
"loss": 0.4722,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.5212251477700162,
|
| 1371 |
+
"grad_norm": 2.3297576895231606,
|
| 1372 |
+
"learning_rate": 5.505841609937162e-06,
|
| 1373 |
+
"loss": 0.4532,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.5239118753358409,
|
| 1378 |
+
"grad_norm": 2.267324308428592,
|
| 1379 |
+
"learning_rate": 5.4591432906953515e-06,
|
| 1380 |
+
"loss": 0.4527,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.5265986029016658,
|
| 1385 |
+
"grad_norm": 2.4550058840280884,
|
| 1386 |
+
"learning_rate": 5.412404544231235e-06,
|
| 1387 |
+
"loss": 0.4562,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.5292853304674906,
|
| 1392 |
+
"grad_norm": 2.268535616599798,
|
| 1393 |
+
"learning_rate": 5.365629485856381e-06,
|
| 1394 |
+
"loss": 0.4454,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5319720580333154,
|
| 1399 |
+
"grad_norm": 2.598323262451839,
|
| 1400 |
+
"learning_rate": 5.318822234079584e-06,
|
| 1401 |
+
"loss": 0.4614,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5346587855991403,
|
| 1406 |
+
"grad_norm": 6.381482924500483,
|
| 1407 |
+
"learning_rate": 5.271986910244254e-06,
|
| 1408 |
+
"loss": 0.4366,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.537345513164965,
|
| 1413 |
+
"grad_norm": 2.359236695134924,
|
| 1414 |
+
"learning_rate": 5.225127638165514e-06,
|
| 1415 |
+
"loss": 0.4535,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5400322407307899,
|
| 1420 |
+
"grad_norm": 2.268448533208311,
|
| 1421 |
+
"learning_rate": 5.178248543767122e-06,
|
| 1422 |
+
"loss": 0.4342,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.5427189682966147,
|
| 1427 |
+
"grad_norm": 2.358403761646346,
|
| 1428 |
+
"learning_rate": 5.1313537547181716e-06,
|
| 1429 |
+
"loss": 0.4405,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.5454056958624396,
|
| 1434 |
+
"grad_norm": 2.2710106949262805,
|
| 1435 |
+
"learning_rate": 5.084447400069656e-06,
|
| 1436 |
+
"loss": 0.4419,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.5480924234282644,
|
| 1441 |
+
"grad_norm": 2.368278941060436,
|
| 1442 |
+
"learning_rate": 5.037533609890917e-06,
|
| 1443 |
+
"loss": 0.4364,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.5507791509940893,
|
| 1448 |
+
"grad_norm": 2.284175829190933,
|
| 1449 |
+
"learning_rate": 4.990616514905982e-06,
|
| 1450 |
+
"loss": 0.4452,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.553465878559914,
|
| 1455 |
+
"grad_norm": 2.41532321709073,
|
| 1456 |
+
"learning_rate": 4.943700246129871e-06,
|
| 1457 |
+
"loss": 0.436,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5561526061257388,
|
| 1462 |
+
"grad_norm": 2.3211025544242787,
|
| 1463 |
+
"learning_rate": 4.896788934504853e-06,
|
| 1464 |
+
"loss": 0.4467,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.5588393336915637,
|
| 1469 |
+
"grad_norm": 2.347444291429596,
|
| 1470 |
+
"learning_rate": 4.849886710536725e-06,
|
| 1471 |
+
"loss": 0.4288,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5615260612573885,
|
| 1476 |
+
"grad_norm": 2.4127644606277014,
|
| 1477 |
+
"learning_rate": 4.802997703931124e-06,
|
| 1478 |
+
"loss": 0.4355,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.5642127888232134,
|
| 1483 |
+
"grad_norm": 2.4325621488004776,
|
| 1484 |
+
"learning_rate": 4.7561260432299015e-06,
|
| 1485 |
+
"loss": 0.4551,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.5668995163890381,
|
| 1490 |
+
"grad_norm": 2.242665015732091,
|
| 1491 |
+
"learning_rate": 4.7092758554476215e-06,
|
| 1492 |
+
"loss": 0.4364,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.569586243954863,
|
| 1497 |
+
"grad_norm": 2.4289606347980692,
|
| 1498 |
+
"learning_rate": 4.662451265708174e-06,
|
| 1499 |
+
"loss": 0.4316,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5722729715206878,
|
| 1504 |
+
"grad_norm": 2.2828904861500257,
|
| 1505 |
+
"learning_rate": 4.6156563968815575e-06,
|
| 1506 |
+
"loss": 0.4298,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.5749596990865127,
|
| 1511 |
+
"grad_norm": 2.320278023559682,
|
| 1512 |
+
"learning_rate": 4.568895369220868e-06,
|
| 1513 |
+
"loss": 0.4332,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.5776464266523375,
|
| 1518 |
+
"grad_norm": 2.228672536344676,
|
| 1519 |
+
"learning_rate": 4.52217229999951e-06,
|
| 1520 |
+
"loss": 0.4291,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.5803331542181622,
|
| 1525 |
+
"grad_norm": 2.2818442860821664,
|
| 1526 |
+
"learning_rate": 4.47549130314868e-06,
|
| 1527 |
+
"loss": 0.4254,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.5830198817839871,
|
| 1532 |
+
"grad_norm": 2.218722467460458,
|
| 1533 |
+
"learning_rate": 4.428856488895128e-06,
|
| 1534 |
+
"loss": 0.441,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5857066093498119,
|
| 1539 |
+
"grad_norm": 2.2852430401184907,
|
| 1540 |
+
"learning_rate": 4.382271963399268e-06,
|
| 1541 |
+
"loss": 0.4201,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.5883933369156368,
|
| 1546 |
+
"grad_norm": 2.2551743568535416,
|
| 1547 |
+
"learning_rate": 4.33574182839362e-06,
|
| 1548 |
+
"loss": 0.4284,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.5910800644814616,
|
| 1553 |
+
"grad_norm": 2.161938070818427,
|
| 1554 |
+
"learning_rate": 4.28927018082167e-06,
|
| 1555 |
+
"loss": 0.4274,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.5937667920472864,
|
| 1560 |
+
"grad_norm": 2.4061344797719753,
|
| 1561 |
+
"learning_rate": 4.2428611124771184e-06,
|
| 1562 |
+
"loss": 0.4141,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.5964535196131112,
|
| 1567 |
+
"grad_norm": 2.325443484824538,
|
| 1568 |
+
"learning_rate": 4.19651870964362e-06,
|
| 1569 |
+
"loss": 0.4286,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5991402471789361,
|
| 1574 |
+
"grad_norm": 2.3440359985504133,
|
| 1575 |
+
"learning_rate": 4.150247052734979e-06,
|
| 1576 |
+
"loss": 0.4302,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6018269747447609,
|
| 1581 |
+
"grad_norm": 2.4615226071875567,
|
| 1582 |
+
"learning_rate": 4.104050215935875e-06,
|
| 1583 |
+
"loss": 0.4111,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.6045137023105857,
|
| 1588 |
+
"grad_norm": 2.4429242324006983,
|
| 1589 |
+
"learning_rate": 4.0579322668431295e-06,
|
| 1590 |
+
"loss": 0.4193,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6072004298764105,
|
| 1595 |
+
"grad_norm": 2.3015769237979677,
|
| 1596 |
+
"learning_rate": 4.011897266107567e-06,
|
| 1597 |
+
"loss": 0.42,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6098871574422353,
|
| 1602 |
+
"grad_norm": 2.1719410742796,
|
| 1603 |
+
"learning_rate": 3.965949267076465e-06,
|
| 1604 |
+
"loss": 0.4027,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6125738850080602,
|
| 1609 |
+
"grad_norm": 2.192156669745234,
|
| 1610 |
+
"learning_rate": 3.9200923154366685e-06,
|
| 1611 |
+
"loss": 0.423,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.615260612573885,
|
| 1616 |
+
"grad_norm": 2.2811472307718414,
|
| 1617 |
+
"learning_rate": 3.874330448858369e-06,
|
| 1618 |
+
"loss": 0.4142,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6179473401397099,
|
| 1623 |
+
"grad_norm": 2.116499798174077,
|
| 1624 |
+
"learning_rate": 3.8286676966395895e-06,
|
| 1625 |
+
"loss": 0.4107,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6206340677055346,
|
| 1630 |
+
"grad_norm": 2.244666553521093,
|
| 1631 |
+
"learning_rate": 3.7831080793514065e-06,
|
| 1632 |
+
"loss": 0.4017,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.6233207952713595,
|
| 1637 |
+
"grad_norm": 2.4675679743826295,
|
| 1638 |
+
"learning_rate": 3.7376556084839465e-06,
|
| 1639 |
+
"loss": 0.4059,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.6260075228371843,
|
| 1644 |
+
"grad_norm": 2.443117409755618,
|
| 1645 |
+
"learning_rate": 3.692314286093167e-06,
|
| 1646 |
+
"loss": 0.4162,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.6286942504030091,
|
| 1651 |
+
"grad_norm": 2.2029356738105363,
|
| 1652 |
+
"learning_rate": 3.647088104448494e-06,
|
| 1653 |
+
"loss": 0.4045,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.631380977968834,
|
| 1658 |
+
"grad_norm": 2.2250689532361045,
|
| 1659 |
+
"learning_rate": 3.601981045681292e-06,
|
| 1660 |
+
"loss": 0.4035,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.6340677055346587,
|
| 1665 |
+
"grad_norm": 2.3017262536884395,
|
| 1666 |
+
"learning_rate": 3.556997081434248e-06,
|
| 1667 |
+
"loss": 0.4043,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.6367544331004836,
|
| 1672 |
+
"grad_norm": 2.242688700397434,
|
| 1673 |
+
"learning_rate": 3.5121401725116653e-06,
|
| 1674 |
+
"loss": 0.405,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6394411606663084,
|
| 1679 |
+
"grad_norm": 2.0746209840311747,
|
| 1680 |
+
"learning_rate": 3.4674142685307264e-06,
|
| 1681 |
+
"loss": 0.4086,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6421278882321333,
|
| 1686 |
+
"grad_norm": 2.2459358965322993,
|
| 1687 |
+
"learning_rate": 3.4228233075737225e-06,
|
| 1688 |
+
"loss": 0.4121,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.6448146157979581,
|
| 1693 |
+
"grad_norm": 2.1930816457650235,
|
| 1694 |
+
"learning_rate": 3.3783712158413163e-06,
|
| 1695 |
+
"loss": 0.395,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.647501343363783,
|
| 1700 |
+
"grad_norm": 2.0405182523892145,
|
| 1701 |
+
"learning_rate": 3.3340619073068347e-06,
|
| 1702 |
+
"loss": 0.3865,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.6501880709296077,
|
| 1707 |
+
"grad_norm": 2.280921131796164,
|
| 1708 |
+
"learning_rate": 3.289899283371657e-06,
|
| 1709 |
+
"loss": 0.3905,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.6528747984954326,
|
| 1714 |
+
"grad_norm": 2.297801391720408,
|
| 1715 |
+
"learning_rate": 3.2458872325216893e-06,
|
| 1716 |
+
"loss": 0.3992,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.6555615260612574,
|
| 1721 |
+
"grad_norm": 2.2255966269222363,
|
| 1722 |
+
"learning_rate": 3.202029629984991e-06,
|
| 1723 |
+
"loss": 0.4012,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.6582482536270822,
|
| 1728 |
+
"grad_norm": 2.159969955127635,
|
| 1729 |
+
"learning_rate": 3.158330337390565e-06,
|
| 1730 |
+
"loss": 0.4008,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.6609349811929071,
|
| 1735 |
+
"grad_norm": 2.2717513219011636,
|
| 1736 |
+
"learning_rate": 3.1147932024283424e-06,
|
| 1737 |
+
"loss": 0.3915,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.6636217087587318,
|
| 1742 |
+
"grad_norm": 2.2223909448906247,
|
| 1743 |
+
"learning_rate": 3.071422058510394e-06,
|
| 1744 |
+
"loss": 0.3918,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.6663084363245567,
|
| 1749 |
+
"grad_norm": 2.3054337829096294,
|
| 1750 |
+
"learning_rate": 3.0282207244334084e-06,
|
| 1751 |
+
"loss": 0.4009,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.6689951638903815,
|
| 1756 |
+
"grad_norm": 2.2290900583766677,
|
| 1757 |
+
"learning_rate": 2.9851930040424383e-06,
|
| 1758 |
+
"loss": 0.4068,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.6716818914562064,
|
| 1763 |
+
"grad_norm": 2.1757281052534303,
|
| 1764 |
+
"learning_rate": 2.9423426858959892e-06,
|
| 1765 |
+
"loss": 0.3882,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.6743686190220312,
|
| 1770 |
+
"grad_norm": 2.1885464432673314,
|
| 1771 |
+
"learning_rate": 2.8996735429324256e-06,
|
| 1772 |
+
"loss": 0.389,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.677055346587856,
|
| 1777 |
+
"grad_norm": 2.0896855258083464,
|
| 1778 |
+
"learning_rate": 2.8571893321377773e-06,
|
| 1779 |
+
"loss": 0.3856,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.6797420741536808,
|
| 1784 |
+
"grad_norm": 2.313353541234272,
|
| 1785 |
+
"learning_rate": 2.8148937942149347e-06,
|
| 1786 |
+
"loss": 0.392,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.6824288017195056,
|
| 1791 |
+
"grad_norm": 2.3338524034127346,
|
| 1792 |
+
"learning_rate": 2.7727906532542783e-06,
|
| 1793 |
+
"loss": 0.3869,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.6851155292853305,
|
| 1798 |
+
"grad_norm": 2.084691037407018,
|
| 1799 |
+
"learning_rate": 2.7308836164057913e-06,
|
| 1800 |
+
"loss": 0.3826,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.6878022568511553,
|
| 1805 |
+
"grad_norm": 2.324796342452183,
|
| 1806 |
+
"learning_rate": 2.6891763735526223e-06,
|
| 1807 |
+
"loss": 0.3871,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.6904889844169801,
|
| 1812 |
+
"grad_norm": 2.160101574703143,
|
| 1813 |
+
"learning_rate": 2.6476725969862227e-06,
|
| 1814 |
+
"loss": 0.3728,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.6931757119828049,
|
| 1819 |
+
"grad_norm": 2.067721186262042,
|
| 1820 |
+
"learning_rate": 2.6063759410829813e-06,
|
| 1821 |
+
"loss": 0.3811,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.6958624395486298,
|
| 1826 |
+
"grad_norm": 2.4251135654528646,
|
| 1827 |
+
"learning_rate": 2.565290041982471e-06,
|
| 1828 |
+
"loss": 0.3884,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.6985491671144546,
|
| 1833 |
+
"grad_norm": 2.1893196908992123,
|
| 1834 |
+
"learning_rate": 2.524418517267283e-06,
|
| 1835 |
+
"loss": 0.3915,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.7012358946802795,
|
| 1840 |
+
"grad_norm": 2.1923809598940602,
|
| 1841 |
+
"learning_rate": 2.4837649656445117e-06,
|
| 1842 |
+
"loss": 0.3853,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7039226222461042,
|
| 1847 |
+
"grad_norm": 2.2626797878823712,
|
| 1848 |
+
"learning_rate": 2.4433329666288774e-06,
|
| 1849 |
+
"loss": 0.3771,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.706609349811929,
|
| 1854 |
+
"grad_norm": 2.208206845682125,
|
| 1855 |
+
"learning_rate": 2.4031260802275623e-06,
|
| 1856 |
+
"loss": 0.3689,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7092960773777539,
|
| 1861 |
+
"grad_norm": 2.18574695336372,
|
| 1862 |
+
"learning_rate": 2.3631478466267498e-06,
|
| 1863 |
+
"loss": 0.3728,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7119828049435787,
|
| 1868 |
+
"grad_norm": 2.207451564888781,
|
| 1869 |
+
"learning_rate": 2.323401785879921e-06,
|
| 1870 |
+
"loss": 0.3758,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7146695325094036,
|
| 1875 |
+
"grad_norm": 2.168655924857549,
|
| 1876 |
+
"learning_rate": 2.283891397597908e-06,
|
| 1877 |
+
"loss": 0.3672,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.7173562600752283,
|
| 1882 |
+
"grad_norm": 2.255193862061058,
|
| 1883 |
+
"learning_rate": 2.2446201606407537e-06,
|
| 1884 |
+
"loss": 0.3794,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.7200429876410532,
|
| 1889 |
+
"grad_norm": 2.2636128693117166,
|
| 1890 |
+
"learning_rate": 2.205591532811416e-06,
|
| 1891 |
+
"loss": 0.3742,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.722729715206878,
|
| 1896 |
+
"grad_norm": 2.1328893959069117,
|
| 1897 |
+
"learning_rate": 2.166808950551296e-06,
|
| 1898 |
+
"loss": 0.3778,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.7254164427727029,
|
| 1903 |
+
"grad_norm": 2.1602209025177705,
|
| 1904 |
+
"learning_rate": 2.128275828637664e-06,
|
| 1905 |
+
"loss": 0.3788,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.7281031703385277,
|
| 1910 |
+
"grad_norm": 2.28424029482692,
|
| 1911 |
+
"learning_rate": 2.089995559883004e-06,
|
| 1912 |
+
"loss": 0.371,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.7307898979043524,
|
| 1917 |
+
"grad_norm": 2.15439710916817,
|
| 1918 |
+
"learning_rate": 2.0519715148362585e-06,
|
| 1919 |
+
"loss": 0.3724,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.7334766254701773,
|
| 1924 |
+
"grad_norm": 2.1370354226282355,
|
| 1925 |
+
"learning_rate": 2.0142070414860704e-06,
|
| 1926 |
+
"loss": 0.3551,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.7361633530360021,
|
| 1931 |
+
"grad_norm": 2.1423156686501836,
|
| 1932 |
+
"learning_rate": 1.976705464965985e-06,
|
| 1933 |
+
"loss": 0.3817,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.738850080601827,
|
| 1938 |
+
"grad_norm": 2.1767372641376976,
|
| 1939 |
+
"learning_rate": 1.9394700872616856e-06,
|
| 1940 |
+
"loss": 0.3692,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.7415368081676518,
|
| 1945 |
+
"grad_norm": 2.1148705992310552,
|
| 1946 |
+
"learning_rate": 1.902504186920245e-06,
|
| 1947 |
+
"loss": 0.3701,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.7442235357334767,
|
| 1952 |
+
"grad_norm": 2.127192293566224,
|
| 1953 |
+
"learning_rate": 1.8658110187614538e-06,
|
| 1954 |
+
"loss": 0.3716,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.7469102632993014,
|
| 1959 |
+
"grad_norm": 2.1527774862898394,
|
| 1960 |
+
"learning_rate": 1.8293938135912475e-06,
|
| 1961 |
+
"loss": 0.3663,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7495969908651263,
|
| 1966 |
+
"grad_norm": 2.3762653649020553,
|
| 1967 |
+
"learning_rate": 1.793255777917217e-06,
|
| 1968 |
+
"loss": 0.356,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.7522837184309511,
|
| 1973 |
+
"grad_norm": 2.0672220526784444,
|
| 1974 |
+
"learning_rate": 1.7574000936662928e-06,
|
| 1975 |
+
"loss": 0.3666,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.7549704459967759,
|
| 1980 |
+
"grad_norm": 2.131662760991029,
|
| 1981 |
+
"learning_rate": 1.7218299179045789e-06,
|
| 1982 |
+
"loss": 0.3777,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.7576571735626008,
|
| 1987 |
+
"grad_norm": 2.3447659932151423,
|
| 1988 |
+
"learning_rate": 1.6865483825593643e-06,
|
| 1989 |
+
"loss": 0.3718,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.7603439011284255,
|
| 1994 |
+
"grad_norm": 2.393514042224357,
|
| 1995 |
+
"learning_rate": 1.6515585941433694e-06,
|
| 1996 |
+
"loss": 0.3642,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.7630306286942504,
|
| 2001 |
+
"grad_norm": 2.3166220749115194,
|
| 2002 |
+
"learning_rate": 1.6168636334812126e-06,
|
| 2003 |
+
"loss": 0.3712,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.7657173562600752,
|
| 2008 |
+
"grad_norm": 2.1832693900107745,
|
| 2009 |
+
"learning_rate": 1.5824665554381579e-06,
|
| 2010 |
+
"loss": 0.3658,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.7684040838259001,
|
| 2015 |
+
"grad_norm": 2.0779160960958594,
|
| 2016 |
+
"learning_rate": 1.5483703886511191e-06,
|
| 2017 |
+
"loss": 0.3615,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.7710908113917249,
|
| 2022 |
+
"grad_norm": 2.098593414629146,
|
| 2023 |
+
"learning_rate": 1.5145781352620054e-06,
|
| 2024 |
+
"loss": 0.353,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.7737775389575497,
|
| 2029 |
+
"grad_norm": 2.1861074294439224,
|
| 2030 |
+
"learning_rate": 1.481092770653374e-06,
|
| 2031 |
+
"loss": 0.3599,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.7764642665233745,
|
| 2036 |
+
"grad_norm": 2.2448007733369923,
|
| 2037 |
+
"learning_rate": 1.4479172431864647e-06,
|
| 2038 |
+
"loss": 0.3548,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.7791509940891993,
|
| 2043 |
+
"grad_norm": 2.307957775652367,
|
| 2044 |
+
"learning_rate": 1.4150544739415755e-06,
|
| 2045 |
+
"loss": 0.3549,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.7818377216550242,
|
| 2050 |
+
"grad_norm": 2.1872047936836903,
|
| 2051 |
+
"learning_rate": 1.382507356460891e-06,
|
| 2052 |
+
"loss": 0.3533,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.784524449220849,
|
| 2057 |
+
"grad_norm": 2.1557683435766304,
|
| 2058 |
+
"learning_rate": 1.3502787564936875e-06,
|
| 2059 |
+
"loss": 0.3678,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.7872111767866738,
|
| 2064 |
+
"grad_norm": 2.088183401090359,
|
| 2065 |
+
"learning_rate": 1.3183715117440143e-06,
|
| 2066 |
+
"loss": 0.3452,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.7898979043524986,
|
| 2071 |
+
"grad_norm": 2.1559096637691195,
|
| 2072 |
+
"learning_rate": 1.2867884316208345e-06,
|
| 2073 |
+
"loss": 0.3605,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.7925846319183235,
|
| 2078 |
+
"grad_norm": 1.8737663503332451,
|
| 2079 |
+
"learning_rate": 1.255532296990662e-06,
|
| 2080 |
+
"loss": 0.3514,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.7952713594841483,
|
| 2085 |
+
"grad_norm": 2.196223751578153,
|
| 2086 |
+
"learning_rate": 1.2246058599327021e-06,
|
| 2087 |
+
"loss": 0.3511,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.7979580870499732,
|
| 2092 |
+
"grad_norm": 2.0822224737026294,
|
| 2093 |
+
"learning_rate": 1.194011843496537e-06,
|
| 2094 |
+
"loss": 0.3653,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.800644814615798,
|
| 2099 |
+
"grad_norm": 2.2216664507383457,
|
| 2100 |
+
"learning_rate": 1.163752941462362e-06,
|
| 2101 |
+
"loss": 0.3491,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.8033315421816228,
|
| 2106 |
+
"grad_norm": 2.259893004106475,
|
| 2107 |
+
"learning_rate": 1.1338318181038037e-06,
|
| 2108 |
+
"loss": 0.3495,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8060182697474476,
|
| 2113 |
+
"grad_norm": 2.1666650973142687,
|
| 2114 |
+
"learning_rate": 1.1042511079533275e-06,
|
| 2115 |
+
"loss": 0.3611,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.8087049973132724,
|
| 2120 |
+
"grad_norm": 2.2659364719554898,
|
| 2121 |
+
"learning_rate": 1.0750134155702674e-06,
|
| 2122 |
+
"loss": 0.3626,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8113917248790973,
|
| 2127 |
+
"grad_norm": 2.108890981344199,
|
| 2128 |
+
"learning_rate": 1.046121315311508e-06,
|
| 2129 |
+
"loss": 0.3522,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.814078452444922,
|
| 2134 |
+
"grad_norm": 1.9553754507307322,
|
| 2135 |
+
"learning_rate": 1.017577351104801e-06,
|
| 2136 |
+
"loss": 0.3491,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.8167651800107469,
|
| 2141 |
+
"grad_norm": 2.042354110902273,
|
| 2142 |
+
"learning_rate": 9.893840362247809e-07,
|
| 2143 |
+
"loss": 0.3489,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.8194519075765717,
|
| 2148 |
+
"grad_norm": 2.1701934651234613,
|
| 2149 |
+
"learning_rate": 9.615438530716753e-07,
|
| 2150 |
+
"loss": 0.3556,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.8221386351423966,
|
| 2155 |
+
"grad_norm": 2.298551493046633,
|
| 2156 |
+
"learning_rate": 9.340592529527237e-07,
|
| 2157 |
+
"loss": 0.3533,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.8248253627082214,
|
| 2162 |
+
"grad_norm": 2.0661919944679656,
|
| 2163 |
+
"learning_rate": 9.069326558663488e-07,
|
| 2164 |
+
"loss": 0.3504,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8275120902740463,
|
| 2169 |
+
"grad_norm": 2.238182054477219,
|
| 2170 |
+
"learning_rate": 8.801664502890722e-07,
|
| 2171 |
+
"loss": 0.3583,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.830198817839871,
|
| 2176 |
+
"grad_norm": 2.206073109503085,
|
| 2177 |
+
"learning_rate": 8.537629929652186e-07,
|
| 2178 |
+
"loss": 0.3493,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8328855454056958,
|
| 2183 |
+
"grad_norm": 2.112920269926838,
|
| 2184 |
+
"learning_rate": 8.277246086993962e-07,
|
| 2185 |
+
"loss": 0.3485,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.8355722729715207,
|
| 2190 |
+
"grad_norm": 2.1091946693423824,
|
| 2191 |
+
"learning_rate": 8.02053590151805e-07,
|
| 2192 |
+
"loss": 0.3602,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.8382590005373455,
|
| 2197 |
+
"grad_norm": 2.0674911667909592,
|
| 2198 |
+
"learning_rate": 7.767521976363735e-07,
|
| 2199 |
+
"loss": 0.344,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.8409457281031704,
|
| 2204 |
+
"grad_norm": 2.094630956022192,
|
| 2205 |
+
"learning_rate": 7.518226589217286e-07,
|
| 2206 |
+
"loss": 0.3555,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.8436324556689951,
|
| 2211 |
+
"grad_norm": 1.9871731688863412,
|
| 2212 |
+
"learning_rate": 7.27267169035053e-07,
|
| 2213 |
+
"loss": 0.3446,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.84631918323482,
|
| 2218 |
+
"grad_norm": 1.9968082439337067,
|
| 2219 |
+
"learning_rate": 7.030878900688115e-07,
|
| 2220 |
+
"loss": 0.3453,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8490059108006448,
|
| 2225 |
+
"grad_norm": 2.0534061294688435,
|
| 2226 |
+
"learning_rate": 6.792869509903777e-07,
|
| 2227 |
+
"loss": 0.3471,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8516926383664697,
|
| 2232 |
+
"grad_norm": 2.06210125589499,
|
| 2233 |
+
"learning_rate": 6.558664474545817e-07,
|
| 2234 |
+
"loss": 0.3395,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8543793659322945,
|
| 2239 |
+
"grad_norm": 1.9567313896707874,
|
| 2240 |
+
"learning_rate": 6.328284416191893e-07,
|
| 2241 |
+
"loss": 0.3401,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.8570660934981192,
|
| 2246 |
+
"grad_norm": 2.060413092979503,
|
| 2247 |
+
"learning_rate": 6.101749619633346e-07,
|
| 2248 |
+
"loss": 0.3394,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.8597528210639441,
|
| 2253 |
+
"grad_norm": 2.1887059434963603,
|
| 2254 |
+
"learning_rate": 5.879080031089047e-07,
|
| 2255 |
+
"loss": 0.3543,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.8624395486297689,
|
| 2260 |
+
"grad_norm": 1.9845082909122282,
|
| 2261 |
+
"learning_rate": 5.660295256449233e-07,
|
| 2262 |
+
"loss": 0.3389,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.8651262761955938,
|
| 2267 |
+
"grad_norm": 2.3356240543268414,
|
| 2268 |
+
"learning_rate": 5.445414559549167e-07,
|
| 2269 |
+
"loss": 0.3403,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.8678130037614186,
|
| 2274 |
+
"grad_norm": 2.2880237510434123,
|
| 2275 |
+
"learning_rate": 5.234456860473042e-07,
|
| 2276 |
+
"loss": 0.333,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.8704997313272435,
|
| 2281 |
+
"grad_norm": 1.987792837037979,
|
| 2282 |
+
"learning_rate": 5.027440733887973e-07,
|
| 2283 |
+
"loss": 0.3413,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.8731864588930682,
|
| 2288 |
+
"grad_norm": 2.145351742840335,
|
| 2289 |
+
"learning_rate": 4.824384407408622e-07,
|
| 2290 |
+
"loss": 0.3419,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.8758731864588931,
|
| 2295 |
+
"grad_norm": 2.0454741447896034,
|
| 2296 |
+
"learning_rate": 4.625305759992205e-07,
|
| 2297 |
+
"loss": 0.3446,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.8785599140247179,
|
| 2302 |
+
"grad_norm": 2.3653559873352754,
|
| 2303 |
+
"learning_rate": 4.4302223203642803e-07,
|
| 2304 |
+
"loss": 0.3456,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.8812466415905427,
|
| 2309 |
+
"grad_norm": 1.9465586799987966,
|
| 2310 |
+
"learning_rate": 4.2391512654753443e-07,
|
| 2311 |
+
"loss": 0.3401,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.8839333691563676,
|
| 2316 |
+
"grad_norm": 2.0641483788200166,
|
| 2317 |
+
"learning_rate": 4.05210941898847e-07,
|
| 2318 |
+
"loss": 0.3444,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.8866200967221923,
|
| 2323 |
+
"grad_norm": 1.9634013461126347,
|
| 2324 |
+
"learning_rate": 3.8691132497979064e-07,
|
| 2325 |
+
"loss": 0.3262,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.8893068242880172,
|
| 2330 |
+
"grad_norm": 1.9771681166485953,
|
| 2331 |
+
"learning_rate": 3.6901788705790753e-07,
|
| 2332 |
+
"loss": 0.3339,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.891993551853842,
|
| 2337 |
+
"grad_norm": 2.0517920199325363,
|
| 2338 |
+
"learning_rate": 3.5153220363698225e-07,
|
| 2339 |
+
"loss": 0.3505,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.8946802794196669,
|
| 2344 |
+
"grad_norm": 1.9243621922759124,
|
| 2345 |
+
"learning_rate": 3.344558143183246e-07,
|
| 2346 |
+
"loss": 0.342,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.8973670069854917,
|
| 2351 |
+
"grad_norm": 1.9232396735880564,
|
| 2352 |
+
"learning_rate": 3.1779022266520245e-07,
|
| 2353 |
+
"loss": 0.347,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9000537345513165,
|
| 2358 |
+
"grad_norm": 2.0661817058830305,
|
| 2359 |
+
"learning_rate": 3.015368960704584e-07,
|
| 2360 |
+
"loss": 0.3293,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9027404621171413,
|
| 2365 |
+
"grad_norm": 2.1100704132509094,
|
| 2366 |
+
"learning_rate": 2.856972656273066e-07,
|
| 2367 |
+
"loss": 0.3331,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.9054271896829661,
|
| 2372 |
+
"grad_norm": 2.0718216201058444,
|
| 2373 |
+
"learning_rate": 2.7027272600332443e-07,
|
| 2374 |
+
"loss": 0.3422,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.908113917248791,
|
| 2379 |
+
"grad_norm": 2.1084735618419246,
|
| 2380 |
+
"learning_rate": 2.5526463531765467e-07,
|
| 2381 |
+
"loss": 0.3453,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.9108006448146158,
|
| 2386 |
+
"grad_norm": 1.8503057057006569,
|
| 2387 |
+
"learning_rate": 2.4067431502142414e-07,
|
| 2388 |
+
"loss": 0.3369,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.9134873723804406,
|
| 2393 |
+
"grad_norm": 2.2410702930225437,
|
| 2394 |
+
"learning_rate": 2.2650304978138916e-07,
|
| 2395 |
+
"loss": 0.3422,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.9161740999462654,
|
| 2400 |
+
"grad_norm": 1.988010259435427,
|
| 2401 |
+
"learning_rate": 2.1275208736682262e-07,
|
| 2402 |
+
"loss": 0.3273,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.9188608275120903,
|
| 2407 |
+
"grad_norm": 2.162508541847929,
|
| 2408 |
+
"learning_rate": 1.9942263853964917e-07,
|
| 2409 |
+
"loss": 0.348,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9215475550779151,
|
| 2414 |
+
"grad_norm": 2.173499113968412,
|
| 2415 |
+
"learning_rate": 1.8651587694783924e-07,
|
| 2416 |
+
"loss": 0.3366,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92423428264374,
|
| 2421 |
+
"grad_norm": 1.9783121068716565,
|
| 2422 |
+
"learning_rate": 1.7403293902206851e-07,
|
| 2423 |
+
"loss": 0.3282,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.9269210102095647,
|
| 2428 |
+
"grad_norm": 1.8953184142427286,
|
| 2429 |
+
"learning_rate": 1.6197492387565629e-07,
|
| 2430 |
+
"loss": 0.3346,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.9296077377753896,
|
| 2435 |
+
"grad_norm": 2.0149463904024474,
|
| 2436 |
+
"learning_rate": 1.503428932077916e-07,
|
| 2437 |
+
"loss": 0.3457,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.9322944653412144,
|
| 2442 |
+
"grad_norm": 2.0287919597007447,
|
| 2443 |
+
"learning_rate": 1.3913787121004717e-07,
|
| 2444 |
+
"loss": 0.3301,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.9349811929070392,
|
| 2449 |
+
"grad_norm": 2.049509308073804,
|
| 2450 |
+
"learning_rate": 1.2836084447620466e-07,
|
| 2451 |
+
"loss": 0.3483,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.9376679204728641,
|
| 2456 |
+
"grad_norm": 2.0687381489986714,
|
| 2457 |
+
"learning_rate": 1.180127619153837e-07,
|
| 2458 |
+
"loss": 0.3296,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.9403546480386888,
|
| 2463 |
+
"grad_norm": 2.129632171046833,
|
| 2464 |
+
"learning_rate": 1.0809453466849029e-07,
|
| 2465 |
+
"loss": 0.3416,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.9430413756045137,
|
| 2470 |
+
"grad_norm": 1.940321140330739,
|
| 2471 |
+
"learning_rate": 9.860703602799281e-08,
|
| 2472 |
+
"loss": 0.344,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.9457281031703385,
|
| 2477 |
+
"grad_norm": 2.2300828043810434,
|
| 2478 |
+
"learning_rate": 8.955110136102952e-08,
|
| 2479 |
+
"loss": 0.3332,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.9484148307361634,
|
| 2484 |
+
"grad_norm": 2.039077625849431,
|
| 2485 |
+
"learning_rate": 8.092752803585513e-08,
|
| 2486 |
+
"loss": 0.3398,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9511015583019882,
|
| 2491 |
+
"grad_norm": 1.9309466845356567,
|
| 2492 |
+
"learning_rate": 7.273707535162988e-08,
|
| 2493 |
+
"loss": 0.3345,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9537882858678131,
|
| 2498 |
+
"grad_norm": 2.085038229808163,
|
| 2499 |
+
"learning_rate": 6.498046447156958e-08,
|
| 2500 |
+
"loss": 0.3413,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.9564750134336378,
|
| 2505 |
+
"grad_norm": 2.073268982177981,
|
| 2506 |
+
"learning_rate": 5.7658378359443104e-08,
|
| 2507 |
+
"loss": 0.3389,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.9591617409994626,
|
| 2512 |
+
"grad_norm": 2.1191914780783185,
|
| 2513 |
+
"learning_rate": 5.077146171943936e-08,
|
| 2514 |
+
"loss": 0.3301,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.9618484685652875,
|
| 2519 |
+
"grad_norm": 2.0695293690655494,
|
| 2520 |
+
"learning_rate": 4.432032093940219e-08,
|
| 2521 |
+
"loss": 0.3387,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.9645351961311123,
|
| 2526 |
+
"grad_norm": 2.181866235925443,
|
| 2527 |
+
"learning_rate": 3.8305524037438035e-08,
|
| 2528 |
+
"loss": 0.3327,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.9672219236969372,
|
| 2533 |
+
"grad_norm": 2.0829327323896742,
|
| 2534 |
+
"learning_rate": 3.27276006119015e-08,
|
| 2535 |
+
"loss": 0.3269,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.9699086512627619,
|
| 2540 |
+
"grad_norm": 2.0402878486865084,
|
| 2541 |
+
"learning_rate": 2.7587041794766012e-08,
|
| 2542 |
+
"loss": 0.3428,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.9725953788285868,
|
| 2547 |
+
"grad_norm": 2.1613154681131386,
|
| 2548 |
+
"learning_rate": 2.2884300208378395e-08,
|
| 2549 |
+
"loss": 0.3389,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.9752821063944116,
|
| 2554 |
+
"grad_norm": 2.190787226227149,
|
| 2555 |
+
"learning_rate": 1.8619789925608534e-08,
|
| 2556 |
+
"loss": 0.3487,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.9779688339602365,
|
| 2561 |
+
"grad_norm": 1.9274721887684194,
|
| 2562 |
+
"learning_rate": 1.4793886433387417e-08,
|
| 2563 |
+
"loss": 0.3248,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.9806555615260613,
|
| 2568 |
+
"grad_norm": 2.0401602016541296,
|
| 2569 |
+
"learning_rate": 1.1406926599646373e-08,
|
| 2570 |
+
"loss": 0.3378,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.983342289091886,
|
| 2575 |
+
"grad_norm": 1.9245890826575305,
|
| 2576 |
+
"learning_rate": 8.459208643659122e-09,
|
| 2577 |
+
"loss": 0.3301,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.9860290166577109,
|
| 2582 |
+
"grad_norm": 2.145271841454969,
|
| 2583 |
+
"learning_rate": 5.950992109779452e-09,
|
| 2584 |
+
"loss": 0.3337,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.9887157442235357,
|
| 2589 |
+
"grad_norm": 2.102840117283832,
|
| 2590 |
+
"learning_rate": 3.88249784459227e-09,
|
| 2591 |
+
"loss": 0.3436,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.9914024717893606,
|
| 2596 |
+
"grad_norm": 1.8642178563070946,
|
| 2597 |
+
"learning_rate": 2.2539079774658303e-09,
|
| 2598 |
+
"loss": 0.3346,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.9940891993551854,
|
| 2603 |
+
"grad_norm": 2.0754130978586462,
|
| 2604 |
+
"learning_rate": 1.0653659045156695e-09,
|
| 2605 |
+
"loss": 0.323,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.9967759269210102,
|
| 2610 |
+
"grad_norm": 2.1177194452551293,
|
| 2611 |
+
"learning_rate": 3.1697627597970794e-10,
|
| 2612 |
+
"loss": 0.3273,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.999462654486835,
|
| 2617 |
+
"grad_norm": 2.036609175873343,
|
| 2618 |
+
"learning_rate": 8.804987003951937e-12,
|
| 2619 |
+
"loss": 0.3344,
|
| 2620 |
+
"step": 1860
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 1.0,
|
| 2624 |
+
"eval_runtime": 3.3729,
|
| 2625 |
+
"eval_samples_per_second": 2.965,
|
| 2626 |
+
"eval_steps_per_second": 0.889,
|
| 2627 |
+
"step": 1861
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"step": 1861,
|
| 2632 |
+
"total_flos": 194827769610240.0,
|
| 2633 |
+
"train_loss": 0.5009698675307838,
|
| 2634 |
+
"train_runtime": 16706.09,
|
| 2635 |
+
"train_samples_per_second": 1.782,
|
| 2636 |
+
"train_steps_per_second": 0.111
|
| 2637 |
+
}
|
| 2638 |
+
],
|
| 2639 |
+
"logging_steps": 5,
|
| 2640 |
+
"max_steps": 1861,
|
| 2641 |
+
"num_input_tokens_seen": 0,
|
| 2642 |
+
"num_train_epochs": 1,
|
| 2643 |
+
"save_steps": 100,
|
| 2644 |
+
"stateful_callbacks": {
|
| 2645 |
+
"TrainerControl": {
|
| 2646 |
+
"args": {
|
| 2647 |
+
"should_epoch_stop": false,
|
| 2648 |
+
"should_evaluate": false,
|
| 2649 |
+
"should_log": false,
|
| 2650 |
+
"should_save": true,
|
| 2651 |
+
"should_training_stop": true
|
| 2652 |
+
},
|
| 2653 |
+
"attributes": {}
|
| 2654 |
+
}
|
| 2655 |
+
},
|
| 2656 |
+
"total_flos": 194827769610240.0,
|
| 2657 |
+
"train_batch_size": 4,
|
| 2658 |
+
"trial_name": null,
|
| 2659 |
+
"trial_params": null
|
| 2660 |
+
}
|