Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Aug09_15-36-07_COE-CS-sv003/events.out.tfevents.1723218067.COE-CS-sv003.3438867.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1359 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: prometheus-7b-direct
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# prometheus-7b-direct
|
| 19 |
+
|
| 20 |
+
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 generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3430
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 4
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 1
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 59 |
+
| 0.3481 | 0.9992 | 931 | 0.3430 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.43.4
|
| 65 |
+
- Pytorch 2.3.1+cu121
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9991950630533941,
|
| 3 |
+
"total_flos": 194880114524160.0,
|
| 4 |
+
"train_loss": 0.5082111883624412,
|
| 5 |
+
"train_runtime": 20913.2373,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.425,
|
| 8 |
+
"train_steps_per_second": 0.045
|
| 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": "4.43.4"
|
| 6 |
+
}
|
runs/Aug09_15-36-07_COE-CS-sv003/events.out.tfevents.1723218067.COE-CS-sv003.3438867.0
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:b91a8580798d303c07e0a99ddc0a9d9f48c380ef6cda182dfcb81b9d35c27300
|
| 3 |
+
size 45150
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9991950630533941,
|
| 3 |
+
"total_flos": 194880114524160.0,
|
| 4 |
+
"train_loss": 0.5082111883624412,
|
| 5 |
+
"train_runtime": 20913.2373,
|
| 6 |
+
"train_samples": 98952,
|
| 7 |
+
"train_samples_per_second": 1.425,
|
| 8 |
+
"train_steps_per_second": 0.045
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9991950630533941,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 931,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0010732492621411322,
|
| 13 |
+
"grad_norm": 22.296275963984172,
|
| 14 |
+
"learning_rate": 1.0638297872340426e-07,
|
| 15 |
+
"loss": 1.3042,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005366246310705662,
|
| 20 |
+
"grad_norm": 20.47367655843234,
|
| 21 |
+
"learning_rate": 5.319148936170213e-07,
|
| 22 |
+
"loss": 1.3018,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010732492621411323,
|
| 27 |
+
"grad_norm": 8.599621080094153,
|
| 28 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 29 |
+
"loss": 1.1903,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.016098738932116986,
|
| 34 |
+
"grad_norm": 8.578183948965831,
|
| 35 |
+
"learning_rate": 1.595744680851064e-06,
|
| 36 |
+
"loss": 1.0319,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.021464985242822646,
|
| 41 |
+
"grad_norm": 3.3186946669144883,
|
| 42 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 43 |
+
"loss": 0.9077,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.026831231553528307,
|
| 48 |
+
"grad_norm": 2.4208456794965487,
|
| 49 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 50 |
+
"loss": 0.8688,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03219747786423397,
|
| 55 |
+
"grad_norm": 2.3084720872118303,
|
| 56 |
+
"learning_rate": 3.191489361702128e-06,
|
| 57 |
+
"loss": 0.8445,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03756372417493963,
|
| 62 |
+
"grad_norm": 2.47946578003686,
|
| 63 |
+
"learning_rate": 3.723404255319149e-06,
|
| 64 |
+
"loss": 0.8252,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04292997048564529,
|
| 69 |
+
"grad_norm": 2.3070118168825586,
|
| 70 |
+
"learning_rate": 4.255319148936171e-06,
|
| 71 |
+
"loss": 0.8045,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04829621679635095,
|
| 76 |
+
"grad_norm": 2.347470725755473,
|
| 77 |
+
"learning_rate": 4.787234042553192e-06,
|
| 78 |
+
"loss": 0.784,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.053662463107056614,
|
| 83 |
+
"grad_norm": 2.399247076216005,
|
| 84 |
+
"learning_rate": 5.319148936170213e-06,
|
| 85 |
+
"loss": 0.782,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.059028709417762275,
|
| 90 |
+
"grad_norm": 2.3895963062252057,
|
| 91 |
+
"learning_rate": 5.851063829787235e-06,
|
| 92 |
+
"loss": 0.7509,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06439495572846794,
|
| 97 |
+
"grad_norm": 2.3434507391593926,
|
| 98 |
+
"learning_rate": 6.382978723404256e-06,
|
| 99 |
+
"loss": 0.7477,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0697612020391736,
|
| 104 |
+
"grad_norm": 2.23138891237801,
|
| 105 |
+
"learning_rate": 6.914893617021278e-06,
|
| 106 |
+
"loss": 0.7313,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07512744834987926,
|
| 111 |
+
"grad_norm": 2.3748774018346874,
|
| 112 |
+
"learning_rate": 7.446808510638298e-06,
|
| 113 |
+
"loss": 0.7191,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08049369466058492,
|
| 118 |
+
"grad_norm": 2.336896984412136,
|
| 119 |
+
"learning_rate": 7.97872340425532e-06,
|
| 120 |
+
"loss": 0.7153,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08585994097129059,
|
| 125 |
+
"grad_norm": 2.169053338540135,
|
| 126 |
+
"learning_rate": 8.510638297872341e-06,
|
| 127 |
+
"loss": 0.7155,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.09122618728199625,
|
| 132 |
+
"grad_norm": 2.265230463284654,
|
| 133 |
+
"learning_rate": 9.042553191489362e-06,
|
| 134 |
+
"loss": 0.6957,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0965924335927019,
|
| 139 |
+
"grad_norm": 2.3476311708110935,
|
| 140 |
+
"learning_rate": 9.574468085106385e-06,
|
| 141 |
+
"loss": 0.6938,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.10195867990340757,
|
| 146 |
+
"grad_norm": 2.284843693991532,
|
| 147 |
+
"learning_rate": 9.999964780082996e-06,
|
| 148 |
+
"loss": 0.6955,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.10732492621411323,
|
| 153 |
+
"grad_norm": 2.18921254485461,
|
| 154 |
+
"learning_rate": 9.998732135085665e-06,
|
| 155 |
+
"loss": 0.6834,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.11269117252481889,
|
| 160 |
+
"grad_norm": 2.1101783381393417,
|
| 161 |
+
"learning_rate": 9.995738990383743e-06,
|
| 162 |
+
"loss": 0.6806,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11805741883552455,
|
| 167 |
+
"grad_norm": 2.370512013174141,
|
| 168 |
+
"learning_rate": 9.990986400130607e-06,
|
| 169 |
+
"loss": 0.6769,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12342366514623021,
|
| 174 |
+
"grad_norm": 2.1335004655744396,
|
| 175 |
+
"learning_rate": 9.984476038137437e-06,
|
| 176 |
+
"loss": 0.686,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12878991145693588,
|
| 181 |
+
"grad_norm": 2.1669988426080673,
|
| 182 |
+
"learning_rate": 9.97621019728372e-06,
|
| 183 |
+
"loss": 0.6861,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.13415615776764153,
|
| 188 |
+
"grad_norm": 2.382311101815907,
|
| 189 |
+
"learning_rate": 9.966191788709716e-06,
|
| 190 |
+
"loss": 0.667,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1395224040783472,
|
| 195 |
+
"grad_norm": 2.0401210704281905,
|
| 196 |
+
"learning_rate": 9.954424340791195e-06,
|
| 197 |
+
"loss": 0.6661,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.14488865038905285,
|
| 202 |
+
"grad_norm": 1.997533760617226,
|
| 203 |
+
"learning_rate": 9.940911997896774e-06,
|
| 204 |
+
"loss": 0.6649,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15025489669975853,
|
| 209 |
+
"grad_norm": 2.195901881231756,
|
| 210 |
+
"learning_rate": 9.925659518928316e-06,
|
| 211 |
+
"loss": 0.6616,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.15562114301046417,
|
| 216 |
+
"grad_norm": 2.0610833935176553,
|
| 217 |
+
"learning_rate": 9.908672275644898e-06,
|
| 218 |
+
"loss": 0.6618,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16098738932116985,
|
| 223 |
+
"grad_norm": 1.9308969816226162,
|
| 224 |
+
"learning_rate": 9.889956250770933e-06,
|
| 225 |
+
"loss": 0.6573,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1663536356318755,
|
| 230 |
+
"grad_norm": 2.2067283334504384,
|
| 231 |
+
"learning_rate": 9.86951803588912e-06,
|
| 232 |
+
"loss": 0.6505,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17171988194258117,
|
| 237 |
+
"grad_norm": 2.163844105631547,
|
| 238 |
+
"learning_rate": 9.847364829118963e-06,
|
| 239 |
+
"loss": 0.6352,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.17708612825328682,
|
| 244 |
+
"grad_norm": 2.514522017128904,
|
| 245 |
+
"learning_rate": 9.82350443258166e-06,
|
| 246 |
+
"loss": 0.644,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1824523745639925,
|
| 251 |
+
"grad_norm": 2.3092372737846016,
|
| 252 |
+
"learning_rate": 9.797945249652295e-06,
|
| 253 |
+
"loss": 0.6401,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.18781862087469814,
|
| 258 |
+
"grad_norm": 2.086913451295013,
|
| 259 |
+
"learning_rate": 9.770696282000245e-06,
|
| 260 |
+
"loss": 0.6317,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1931848671854038,
|
| 265 |
+
"grad_norm": 4.263008656041996,
|
| 266 |
+
"learning_rate": 9.741767126418898e-06,
|
| 267 |
+
"loss": 0.6352,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.19855111349610946,
|
| 272 |
+
"grad_norm": 6.669287827969328,
|
| 273 |
+
"learning_rate": 9.711167971445766e-06,
|
| 274 |
+
"loss": 0.6245,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.20391735980681513,
|
| 279 |
+
"grad_norm": 2.418998473641885,
|
| 280 |
+
"learning_rate": 9.67890959377418e-06,
|
| 281 |
+
"loss": 0.6382,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.20928360611752078,
|
| 286 |
+
"grad_norm": 1.9261419429094924,
|
| 287 |
+
"learning_rate": 9.645003354457872e-06,
|
| 288 |
+
"loss": 0.6215,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21464985242822646,
|
| 293 |
+
"grad_norm": 2.414448676465819,
|
| 294 |
+
"learning_rate": 9.60946119490972e-06,
|
| 295 |
+
"loss": 0.6146,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2200160987389321,
|
| 300 |
+
"grad_norm": 1.885911480793101,
|
| 301 |
+
"learning_rate": 9.57229563269612e-06,
|
| 302 |
+
"loss": 0.6162,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22538234504963778,
|
| 307 |
+
"grad_norm": 2.008464028829634,
|
| 308 |
+
"learning_rate": 9.533519757128426e-06,
|
| 309 |
+
"loss": 0.6156,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.23074859136034345,
|
| 314 |
+
"grad_norm": 2.16331315927476,
|
| 315 |
+
"learning_rate": 9.49314722465304e-06,
|
| 316 |
+
"loss": 0.6069,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2361148376710491,
|
| 321 |
+
"grad_norm": 1.973961982068933,
|
| 322 |
+
"learning_rate": 9.451192254041759e-06,
|
| 323 |
+
"loss": 0.606,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24148108398175477,
|
| 328 |
+
"grad_norm": 2.0087656849792186,
|
| 329 |
+
"learning_rate": 9.407669621384073e-06,
|
| 330 |
+
"loss": 0.6094,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.24684733029246042,
|
| 335 |
+
"grad_norm": 1.954551142386887,
|
| 336 |
+
"learning_rate": 9.362594654883185e-06,
|
| 337 |
+
"loss": 0.6041,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.25221357660316607,
|
| 342 |
+
"grad_norm": 1.929191512896689,
|
| 343 |
+
"learning_rate": 9.31598322945759e-06,
|
| 344 |
+
"loss": 0.6079,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.25757982291387177,
|
| 349 |
+
"grad_norm": 1.9441153007960759,
|
| 350 |
+
"learning_rate": 9.267851761150092e-06,
|
| 351 |
+
"loss": 0.6047,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2629460692245774,
|
| 356 |
+
"grad_norm": 1.9607729270332375,
|
| 357 |
+
"learning_rate": 9.218217201346251e-06,
|
| 358 |
+
"loss": 0.5979,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.26831231553528306,
|
| 363 |
+
"grad_norm": 2.0964944576432205,
|
| 364 |
+
"learning_rate": 9.167097030804289e-06,
|
| 365 |
+
"loss": 0.5974,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2736785618459887,
|
| 370 |
+
"grad_norm": 2.064418571453017,
|
| 371 |
+
"learning_rate": 9.114509253498554e-06,
|
| 372 |
+
"loss": 0.5911,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.2790448081566944,
|
| 377 |
+
"grad_norm": 1.9882015589578523,
|
| 378 |
+
"learning_rate": 9.060472390278717e-06,
|
| 379 |
+
"loss": 0.5852,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.28441105446740006,
|
| 384 |
+
"grad_norm": 1.8956409406412695,
|
| 385 |
+
"learning_rate": 9.005005472346923e-06,
|
| 386 |
+
"loss": 0.5893,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2897773007781057,
|
| 391 |
+
"grad_norm": 2.420717269019028,
|
| 392 |
+
"learning_rate": 8.948128034555212e-06,
|
| 393 |
+
"loss": 0.5852,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.29514354708881135,
|
| 398 |
+
"grad_norm": 2.0430945196466825,
|
| 399 |
+
"learning_rate": 8.889860108525544e-06,
|
| 400 |
+
"loss": 0.5776,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.30050979339951706,
|
| 405 |
+
"grad_norm": 2.131587227034572,
|
| 406 |
+
"learning_rate": 8.83022221559489e-06,
|
| 407 |
+
"loss": 0.5783,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3058760397102227,
|
| 412 |
+
"grad_norm": 2.012144077782948,
|
| 413 |
+
"learning_rate": 8.76923535958783e-06,
|
| 414 |
+
"loss": 0.5739,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31124228602092835,
|
| 419 |
+
"grad_norm": 1.9798793555936918,
|
| 420 |
+
"learning_rate": 8.706921019419237e-06,
|
| 421 |
+
"loss": 0.5743,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.316608532331634,
|
| 426 |
+
"grad_norm": 2.1981871661379784,
|
| 427 |
+
"learning_rate": 8.643301141529619e-06,
|
| 428 |
+
"loss": 0.5537,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3219747786423397,
|
| 433 |
+
"grad_norm": 1.9783993595823293,
|
| 434 |
+
"learning_rate": 8.578398132155846e-06,
|
| 435 |
+
"loss": 0.5736,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.32734102495304535,
|
| 440 |
+
"grad_norm": 2.266646671924457,
|
| 441 |
+
"learning_rate": 8.512234849439887e-06,
|
| 442 |
+
"loss": 0.5605,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.332707271263751,
|
| 447 |
+
"grad_norm": 2.0388062627147003,
|
| 448 |
+
"learning_rate": 8.444834595378434e-06,
|
| 449 |
+
"loss": 0.5541,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3380735175744567,
|
| 454 |
+
"grad_norm": 1.8746273235590827,
|
| 455 |
+
"learning_rate": 8.376221107616187e-06,
|
| 456 |
+
"loss": 0.5493,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34343976388516234,
|
| 461 |
+
"grad_norm": 1.9641687714089828,
|
| 462 |
+
"learning_rate": 8.306418551085707e-06,
|
| 463 |
+
"loss": 0.5473,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.348806010195868,
|
| 468 |
+
"grad_norm": 2.0231873134828047,
|
| 469 |
+
"learning_rate": 8.23545150949679e-06,
|
| 470 |
+
"loss": 0.5382,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35417225650657364,
|
| 475 |
+
"grad_norm": 1.9081132594420114,
|
| 476 |
+
"learning_rate": 8.163344976678342e-06,
|
| 477 |
+
"loss": 0.5415,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.35953850281727934,
|
| 482 |
+
"grad_norm": 1.8808578978116353,
|
| 483 |
+
"learning_rate": 8.090124347775837e-06,
|
| 484 |
+
"loss": 0.5413,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.364904749127985,
|
| 489 |
+
"grad_norm": 2.069476839747095,
|
| 490 |
+
"learning_rate": 8.0158154103074e-06,
|
| 491 |
+
"loss": 0.5378,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.37027099543869063,
|
| 496 |
+
"grad_norm": 2.1043362965325105,
|
| 497 |
+
"learning_rate": 7.940444335081733e-06,
|
| 498 |
+
"loss": 0.5553,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3756372417493963,
|
| 503 |
+
"grad_norm": 2.0354788880153682,
|
| 504 |
+
"learning_rate": 7.864037666981037e-06,
|
| 505 |
+
"loss": 0.541,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.381003488060102,
|
| 510 |
+
"grad_norm": 2.064254592161078,
|
| 511 |
+
"learning_rate": 7.786622315612182e-06,
|
| 512 |
+
"loss": 0.5329,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3863697343708076,
|
| 517 |
+
"grad_norm": 1.9234108182391954,
|
| 518 |
+
"learning_rate": 7.708225545829446e-06,
|
| 519 |
+
"loss": 0.5226,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3917359806815133,
|
| 524 |
+
"grad_norm": 1.9515453224494816,
|
| 525 |
+
"learning_rate": 7.6288749681321115e-06,
|
| 526 |
+
"loss": 0.5277,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3971022269922189,
|
| 531 |
+
"grad_norm": 1.9085592553037638,
|
| 532 |
+
"learning_rate": 7.548598528940354e-06,
|
| 533 |
+
"loss": 0.5285,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4024684733029246,
|
| 538 |
+
"grad_norm": 1.870687980940359,
|
| 539 |
+
"learning_rate": 7.4674245007528135e-06,
|
| 540 |
+
"loss": 0.5247,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.40783471961363027,
|
| 545 |
+
"grad_norm": 2.077267366579556,
|
| 546 |
+
"learning_rate": 7.385381472189321e-06,
|
| 547 |
+
"loss": 0.5116,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4132009659243359,
|
| 552 |
+
"grad_norm": 1.9454145271664978,
|
| 553 |
+
"learning_rate": 7.302498337922293e-06,
|
| 554 |
+
"loss": 0.5213,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.41856721223504156,
|
| 559 |
+
"grad_norm": 1.9119626674890595,
|
| 560 |
+
"learning_rate": 7.218804288500343e-06,
|
| 561 |
+
"loss": 0.5264,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.42393345854574727,
|
| 566 |
+
"grad_norm": 2.022414838693354,
|
| 567 |
+
"learning_rate": 7.134328800067684e-06,
|
| 568 |
+
"loss": 0.5194,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4292997048564529,
|
| 573 |
+
"grad_norm": 2.092163320659975,
|
| 574 |
+
"learning_rate": 7.049101623982938e-06,
|
| 575 |
+
"loss": 0.5131,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.43466595116715856,
|
| 580 |
+
"grad_norm": 2.0021479768579558,
|
| 581 |
+
"learning_rate": 6.963152776341044e-06,
|
| 582 |
+
"loss": 0.5041,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4400321974778642,
|
| 587 |
+
"grad_norm": 2.0327320697895814,
|
| 588 |
+
"learning_rate": 6.876512527401897e-06,
|
| 589 |
+
"loss": 0.5052,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4453984437885699,
|
| 594 |
+
"grad_norm": 2.2412216150911832,
|
| 595 |
+
"learning_rate": 6.789211390929497e-06,
|
| 596 |
+
"loss": 0.5054,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45076469009927556,
|
| 601 |
+
"grad_norm": 2.115153656464059,
|
| 602 |
+
"learning_rate": 6.701280113445324e-06,
|
| 603 |
+
"loss": 0.5061,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4561309364099812,
|
| 608 |
+
"grad_norm": 1.9249370789560831,
|
| 609 |
+
"learning_rate": 6.6127496633997475e-06,
|
| 610 |
+
"loss": 0.4842,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4614971827206869,
|
| 615 |
+
"grad_norm": 1.953527868661831,
|
| 616 |
+
"learning_rate": 6.523651220265269e-06,
|
| 617 |
+
"loss": 0.4949,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.46686342903139255,
|
| 622 |
+
"grad_norm": 1.8982198151481615,
|
| 623 |
+
"learning_rate": 6.434016163555452e-06,
|
| 624 |
+
"loss": 0.491,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4722296753420982,
|
| 629 |
+
"grad_norm": 1.841890965273987,
|
| 630 |
+
"learning_rate": 6.343876061773385e-06,
|
| 631 |
+
"loss": 0.487,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.47759592165280385,
|
| 636 |
+
"grad_norm": 1.9387691599261847,
|
| 637 |
+
"learning_rate": 6.2532626612936035e-06,
|
| 638 |
+
"loss": 0.4736,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48296216796350955,
|
| 643 |
+
"grad_norm": 1.861661855956454,
|
| 644 |
+
"learning_rate": 6.162207875181354e-06,
|
| 645 |
+
"loss": 0.4787,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4883284142742152,
|
| 650 |
+
"grad_norm": 1.866771313626566,
|
| 651 |
+
"learning_rate": 6.070743771953157e-06,
|
| 652 |
+
"loss": 0.4707,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49369466058492084,
|
| 657 |
+
"grad_norm": 1.8847305365601024,
|
| 658 |
+
"learning_rate": 5.978902564282616e-06,
|
| 659 |
+
"loss": 0.4764,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4990609068956265,
|
| 664 |
+
"grad_norm": 2.0081377194420384,
|
| 665 |
+
"learning_rate": 5.886716597655472e-06,
|
| 666 |
+
"loss": 0.4728,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5044271532063321,
|
| 671 |
+
"grad_norm": 2.040321737831785,
|
| 672 |
+
"learning_rate": 5.7942183389778536e-06,
|
| 673 |
+
"loss": 0.4702,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5097933995170378,
|
| 678 |
+
"grad_norm": 2.121711837077905,
|
| 679 |
+
"learning_rate": 5.701440365141799e-06,
|
| 680 |
+
"loss": 0.4629,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5151596458277435,
|
| 685 |
+
"grad_norm": 1.8953898552423818,
|
| 686 |
+
"learning_rate": 5.608415351552014e-06,
|
| 687 |
+
"loss": 0.4618,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5205258921384491,
|
| 692 |
+
"grad_norm": 1.9319156687040069,
|
| 693 |
+
"learning_rate": 5.515176060617945e-06,
|
| 694 |
+
"loss": 0.4645,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5258921384491548,
|
| 699 |
+
"grad_norm": 2.0580844567420753,
|
| 700 |
+
"learning_rate": 5.421755330215223e-06,
|
| 701 |
+
"loss": 0.4513,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5312583847598604,
|
| 706 |
+
"grad_norm": 1.9986754618051978,
|
| 707 |
+
"learning_rate": 5.328186062120509e-06,
|
| 708 |
+
"loss": 0.4667,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5366246310705661,
|
| 713 |
+
"grad_norm": 1.8960453690474102,
|
| 714 |
+
"learning_rate": 5.23450121042383e-06,
|
| 715 |
+
"loss": 0.4673,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5419908773812718,
|
| 720 |
+
"grad_norm": 1.905017636620808,
|
| 721 |
+
"learning_rate": 5.140733769922525e-06,
|
| 722 |
+
"loss": 0.4537,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5473571236919774,
|
| 727 |
+
"grad_norm": 1.955396324000518,
|
| 728 |
+
"learning_rate": 5.0469167645008245e-06,
|
| 729 |
+
"loss": 0.4478,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5527233700026831,
|
| 734 |
+
"grad_norm": 1.9184357161762489,
|
| 735 |
+
"learning_rate": 4.953083235499177e-06,
|
| 736 |
+
"loss": 0.4455,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.5580896163133888,
|
| 741 |
+
"grad_norm": 1.8626012702880614,
|
| 742 |
+
"learning_rate": 4.859266230077474e-06,
|
| 743 |
+
"loss": 0.4435,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5634558626240944,
|
| 748 |
+
"grad_norm": 1.8866714654623984,
|
| 749 |
+
"learning_rate": 4.7654987895761705e-06,
|
| 750 |
+
"loss": 0.4492,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5688221089348001,
|
| 755 |
+
"grad_norm": 1.9997800662285936,
|
| 756 |
+
"learning_rate": 4.671813937879494e-06,
|
| 757 |
+
"loss": 0.4552,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5741883552455058,
|
| 762 |
+
"grad_norm": 2.008542669530135,
|
| 763 |
+
"learning_rate": 4.5782446697847775e-06,
|
| 764 |
+
"loss": 0.4329,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5795546015562114,
|
| 769 |
+
"grad_norm": 1.9257375981696094,
|
| 770 |
+
"learning_rate": 4.484823939382056e-06,
|
| 771 |
+
"loss": 0.4433,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5849208478669171,
|
| 776 |
+
"grad_norm": 2.018856467121276,
|
| 777 |
+
"learning_rate": 4.391584648447989e-06,
|
| 778 |
+
"loss": 0.4352,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5902870941776227,
|
| 783 |
+
"grad_norm": 1.8446623655945045,
|
| 784 |
+
"learning_rate": 4.298559634858202e-06,
|
| 785 |
+
"loss": 0.4338,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5956533404883284,
|
| 790 |
+
"grad_norm": 1.9846432448897824,
|
| 791 |
+
"learning_rate": 4.205781661022146e-06,
|
| 792 |
+
"loss": 0.4228,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6010195867990341,
|
| 797 |
+
"grad_norm": 1.9065968436703373,
|
| 798 |
+
"learning_rate": 4.1132834023445304e-06,
|
| 799 |
+
"loss": 0.4259,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6063858331097397,
|
| 804 |
+
"grad_norm": 1.972887566791961,
|
| 805 |
+
"learning_rate": 4.021097435717386e-06,
|
| 806 |
+
"loss": 0.4179,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6117520794204454,
|
| 811 |
+
"grad_norm": 2.085630898921528,
|
| 812 |
+
"learning_rate": 3.929256228046845e-06,
|
| 813 |
+
"loss": 0.4205,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6171183257311511,
|
| 818 |
+
"grad_norm": 1.9369874318383387,
|
| 819 |
+
"learning_rate": 3.837792124818647e-06,
|
| 820 |
+
"loss": 0.4247,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6224845720418567,
|
| 825 |
+
"grad_norm": 1.8597647904112595,
|
| 826 |
+
"learning_rate": 3.7467373387063973e-06,
|
| 827 |
+
"loss": 0.4205,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6278508183525624,
|
| 832 |
+
"grad_norm": 1.7821892594233963,
|
| 833 |
+
"learning_rate": 3.656123938226618e-06,
|
| 834 |
+
"loss": 0.4046,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.633217064663268,
|
| 839 |
+
"grad_norm": 1.9833859795715034,
|
| 840 |
+
"learning_rate": 3.5659838364445505e-06,
|
| 841 |
+
"loss": 0.4111,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6385833109739737,
|
| 846 |
+
"grad_norm": 1.944780902162987,
|
| 847 |
+
"learning_rate": 3.476348779734732e-06,
|
| 848 |
+
"loss": 0.415,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6439495572846794,
|
| 853 |
+
"grad_norm": 1.9550245947033087,
|
| 854 |
+
"learning_rate": 3.387250336600254e-06,
|
| 855 |
+
"loss": 0.4191,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.649315803595385,
|
| 860 |
+
"grad_norm": 1.8117200718403572,
|
| 861 |
+
"learning_rate": 3.298719886554677e-06,
|
| 862 |
+
"loss": 0.3993,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6546820499060907,
|
| 867 |
+
"grad_norm": 1.940882592630498,
|
| 868 |
+
"learning_rate": 3.2107886090705035e-06,
|
| 869 |
+
"loss": 0.4081,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6600482962167964,
|
| 874 |
+
"grad_norm": 1.8525749922673174,
|
| 875 |
+
"learning_rate": 3.1234874725981045e-06,
|
| 876 |
+
"loss": 0.4076,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.665414542527502,
|
| 881 |
+
"grad_norm": 1.9210849233799236,
|
| 882 |
+
"learning_rate": 3.036847223658958e-06,
|
| 883 |
+
"loss": 0.4108,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6707807888382077,
|
| 888 |
+
"grad_norm": 1.9000639666031305,
|
| 889 |
+
"learning_rate": 2.950898376017064e-06,
|
| 890 |
+
"loss": 0.4034,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.6761470351489134,
|
| 895 |
+
"grad_norm": 2.003614087267324,
|
| 896 |
+
"learning_rate": 2.865671199932318e-06,
|
| 897 |
+
"loss": 0.4132,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.681513281459619,
|
| 902 |
+
"grad_norm": 1.9763936407420173,
|
| 903 |
+
"learning_rate": 2.781195711499658e-06,
|
| 904 |
+
"loss": 0.4016,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6868795277703247,
|
| 909 |
+
"grad_norm": 1.9016795114295642,
|
| 910 |
+
"learning_rate": 2.697501662077707e-06,
|
| 911 |
+
"loss": 0.401,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6922457740810303,
|
| 916 |
+
"grad_norm": 1.9624570132442953,
|
| 917 |
+
"learning_rate": 2.6146185278106807e-06,
|
| 918 |
+
"loss": 0.3933,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.697612020391736,
|
| 923 |
+
"grad_norm": 1.8275718245227606,
|
| 924 |
+
"learning_rate": 2.5325754992471886e-06,
|
| 925 |
+
"loss": 0.393,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7029782667024417,
|
| 930 |
+
"grad_norm": 1.8709439923940803,
|
| 931 |
+
"learning_rate": 2.4514014710596467e-06,
|
| 932 |
+
"loss": 0.388,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7083445130131473,
|
| 937 |
+
"grad_norm": 1.911631586090792,
|
| 938 |
+
"learning_rate": 2.3711250318678906e-06,
|
| 939 |
+
"loss": 0.3941,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.713710759323853,
|
| 944 |
+
"grad_norm": 1.7745399065562626,
|
| 945 |
+
"learning_rate": 2.2917744541705544e-06,
|
| 946 |
+
"loss": 0.3865,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7190770056345587,
|
| 951 |
+
"grad_norm": 1.998234024876106,
|
| 952 |
+
"learning_rate": 2.2133776843878185e-06,
|
| 953 |
+
"loss": 0.3866,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7244432519452643,
|
| 958 |
+
"grad_norm": 1.808681557692019,
|
| 959 |
+
"learning_rate": 2.1359623330189655e-06,
|
| 960 |
+
"loss": 0.3856,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.72980949825597,
|
| 965 |
+
"grad_norm": 1.8088686581817492,
|
| 966 |
+
"learning_rate": 2.059555664918268e-06,
|
| 967 |
+
"loss": 0.3901,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7351757445666756,
|
| 972 |
+
"grad_norm": 1.8039745722281364,
|
| 973 |
+
"learning_rate": 1.9841845896926022e-06,
|
| 974 |
+
"loss": 0.3829,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7405419908773813,
|
| 979 |
+
"grad_norm": 1.8674727402680937,
|
| 980 |
+
"learning_rate": 1.9098756522241634e-06,
|
| 981 |
+
"loss": 0.3768,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.745908237188087,
|
| 986 |
+
"grad_norm": 1.9068171536750957,
|
| 987 |
+
"learning_rate": 1.8366550233216584e-06,
|
| 988 |
+
"loss": 0.3812,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.7512744834987926,
|
| 993 |
+
"grad_norm": 1.9765087911769241,
|
| 994 |
+
"learning_rate": 1.7645484905032129e-06,
|
| 995 |
+
"loss": 0.3764,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7566407298094983,
|
| 1000 |
+
"grad_norm": 1.775516730227496,
|
| 1001 |
+
"learning_rate": 1.6935814489142937e-06,
|
| 1002 |
+
"loss": 0.3797,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.762006976120204,
|
| 1007 |
+
"grad_norm": 1.7646714298996984,
|
| 1008 |
+
"learning_rate": 1.6237788923838149e-06,
|
| 1009 |
+
"loss": 0.371,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7673732224309096,
|
| 1014 |
+
"grad_norm": 1.8315846638175772,
|
| 1015 |
+
"learning_rate": 1.555165404621567e-06,
|
| 1016 |
+
"loss": 0.3835,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7727394687416153,
|
| 1021 |
+
"grad_norm": 1.8505733173378243,
|
| 1022 |
+
"learning_rate": 1.487765150560116e-06,
|
| 1023 |
+
"loss": 0.3687,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.778105715052321,
|
| 1028 |
+
"grad_norm": 1.7848924875740815,
|
| 1029 |
+
"learning_rate": 1.4216018678441558e-06,
|
| 1030 |
+
"loss": 0.3724,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7834719613630265,
|
| 1035 |
+
"grad_norm": 1.7527547920489353,
|
| 1036 |
+
"learning_rate": 1.3566988584703817e-06,
|
| 1037 |
+
"loss": 0.3676,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7888382076737323,
|
| 1042 |
+
"grad_norm": 2.017475663507191,
|
| 1043 |
+
"learning_rate": 1.293078980580766e-06,
|
| 1044 |
+
"loss": 0.3624,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7942044539844378,
|
| 1049 |
+
"grad_norm": 1.932581243094435,
|
| 1050 |
+
"learning_rate": 1.2307646404121692e-06,
|
| 1051 |
+
"loss": 0.3701,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.7995707002951435,
|
| 1056 |
+
"grad_norm": 1.8424247641839024,
|
| 1057 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 1058 |
+
"loss": 0.3711,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8049369466058492,
|
| 1063 |
+
"grad_norm": 1.8159029145907732,
|
| 1064 |
+
"learning_rate": 1.1101398914744565e-06,
|
| 1065 |
+
"loss": 0.3633,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.8103031929165548,
|
| 1070 |
+
"grad_norm": 2.055480043240695,
|
| 1071 |
+
"learning_rate": 1.0518719654447896e-06,
|
| 1072 |
+
"loss": 0.3623,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8156694392272605,
|
| 1077 |
+
"grad_norm": 1.7975799838896245,
|
| 1078 |
+
"learning_rate": 9.949945276530782e-07,
|
| 1079 |
+
"loss": 0.3606,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8210356855379662,
|
| 1084 |
+
"grad_norm": 1.7631852825296395,
|
| 1085 |
+
"learning_rate": 9.395276097212841e-07,
|
| 1086 |
+
"loss": 0.3592,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8264019318486718,
|
| 1091 |
+
"grad_norm": 1.7910286892268594,
|
| 1092 |
+
"learning_rate": 8.854907465014479e-07,
|
| 1093 |
+
"loss": 0.3551,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8317681781593775,
|
| 1098 |
+
"grad_norm": 1.8158143036353944,
|
| 1099 |
+
"learning_rate": 8.329029691957124e-07,
|
| 1100 |
+
"loss": 0.364,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8371344244700831,
|
| 1105 |
+
"grad_norm": 1.9191566287165054,
|
| 1106 |
+
"learning_rate": 7.817827986537508e-07,
|
| 1107 |
+
"loss": 0.3553,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8425006707807888,
|
| 1112 |
+
"grad_norm": 1.9001999154855205,
|
| 1113 |
+
"learning_rate": 7.321482388499096e-07,
|
| 1114 |
+
"loss": 0.3599,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8478669170914945,
|
| 1119 |
+
"grad_norm": 1.8486152336637562,
|
| 1120 |
+
"learning_rate": 6.840167705424106e-07,
|
| 1121 |
+
"loss": 0.3601,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8532331634022001,
|
| 1126 |
+
"grad_norm": 1.7749346973416724,
|
| 1127 |
+
"learning_rate": 6.374053451168166e-07,
|
| 1128 |
+
"loss": 0.3549,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8585994097129058,
|
| 1133 |
+
"grad_norm": 1.8218491540968815,
|
| 1134 |
+
"learning_rate": 5.92330378615929e-07,
|
| 1135 |
+
"loss": 0.3645,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.8639656560236115,
|
| 1140 |
+
"grad_norm": 1.783717297938072,
|
| 1141 |
+
"learning_rate": 5.488077459582425e-07,
|
| 1142 |
+
"loss": 0.3583,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8693319023343171,
|
| 1147 |
+
"grad_norm": 1.7473164870091953,
|
| 1148 |
+
"learning_rate": 5.068527753469604e-07,
|
| 1149 |
+
"loss": 0.353,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8746981486450228,
|
| 1154 |
+
"grad_norm": 1.6866190577833358,
|
| 1155 |
+
"learning_rate": 4.664802428715753e-07,
|
| 1156 |
+
"loss": 0.3569,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8800643949557284,
|
| 1161 |
+
"grad_norm": 1.7605022217720974,
|
| 1162 |
+
"learning_rate": 4.2770436730388166e-07,
|
| 1163 |
+
"loss": 0.3427,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8854306412664341,
|
| 1168 |
+
"grad_norm": 1.748026700381262,
|
| 1169 |
+
"learning_rate": 3.9053880509028086e-07,
|
| 1170 |
+
"loss": 0.3556,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8907968875771398,
|
| 1175 |
+
"grad_norm": 1.82694857458379,
|
| 1176 |
+
"learning_rate": 3.549966455421305e-07,
|
| 1177 |
+
"loss": 0.3569,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8961631338878454,
|
| 1182 |
+
"grad_norm": 1.7449903357160679,
|
| 1183 |
+
"learning_rate": 3.2109040622582186e-07,
|
| 1184 |
+
"loss": 0.3567,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9015293801985511,
|
| 1189 |
+
"grad_norm": 1.765178738808068,
|
| 1190 |
+
"learning_rate": 2.8883202855423676e-07,
|
| 1191 |
+
"loss": 0.3464,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9068956265092568,
|
| 1196 |
+
"grad_norm": 1.8646790389554087,
|
| 1197 |
+
"learning_rate": 2.582328735811029e-07,
|
| 1198 |
+
"loss": 0.3485,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9122618728199624,
|
| 1203 |
+
"grad_norm": 1.7327234524732287,
|
| 1204 |
+
"learning_rate": 2.2930371799975593e-07,
|
| 1205 |
+
"loss": 0.3548,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9176281191306681,
|
| 1210 |
+
"grad_norm": 1.7873784801521655,
|
| 1211 |
+
"learning_rate": 2.0205475034770606e-07,
|
| 1212 |
+
"loss": 0.3529,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9229943654413738,
|
| 1217 |
+
"grad_norm": 1.8492213076499473,
|
| 1218 |
+
"learning_rate": 1.7649556741833995e-07,
|
| 1219 |
+
"loss": 0.3473,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9283606117520794,
|
| 1224 |
+
"grad_norm": 1.8273172776853641,
|
| 1225 |
+
"learning_rate": 1.5263517088103862e-07,
|
| 1226 |
+
"loss": 0.351,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.9337268580627851,
|
| 1231 |
+
"grad_norm": 1.9136908811797346,
|
| 1232 |
+
"learning_rate": 1.304819641108801e-07,
|
| 1233 |
+
"loss": 0.3471,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9390931043734907,
|
| 1238 |
+
"grad_norm": 1.7762316103832752,
|
| 1239 |
+
"learning_rate": 1.1004374922906846e-07,
|
| 1240 |
+
"loss": 0.3412,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9444593506841964,
|
| 1245 |
+
"grad_norm": 1.9275493541172453,
|
| 1246 |
+
"learning_rate": 9.132772435510362e-08,
|
| 1247 |
+
"loss": 0.3566,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9498255969949021,
|
| 1252 |
+
"grad_norm": 1.714257495081281,
|
| 1253 |
+
"learning_rate": 7.434048107168523e-08,
|
| 1254 |
+
"loss": 0.3426,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9551918433056077,
|
| 1259 |
+
"grad_norm": 1.7853244835501505,
|
| 1260 |
+
"learning_rate": 5.908800210322696e-08,
|
| 1261 |
+
"loss": 0.3455,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.9605580896163134,
|
| 1266 |
+
"grad_norm": 1.7339077062506096,
|
| 1267 |
+
"learning_rate": 4.55756592088058e-08,
|
| 1268 |
+
"loss": 0.3456,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.9659243359270191,
|
| 1273 |
+
"grad_norm": 1.8108202681226637,
|
| 1274 |
+
"learning_rate": 3.3808211290284886e-08,
|
| 1275 |
+
"loss": 0.3475,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9712905822377247,
|
| 1280 |
+
"grad_norm": 1.7215289002872909,
|
| 1281 |
+
"learning_rate": 2.378980271628195e-08,
|
| 1282 |
+
"loss": 0.3417,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9766568285484304,
|
| 1287 |
+
"grad_norm": 1.7249368209329086,
|
| 1288 |
+
"learning_rate": 1.552396186256411e-08,
|
| 1289 |
+
"loss": 0.3469,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.982023074859136,
|
| 1294 |
+
"grad_norm": 1.7553769156007077,
|
| 1295 |
+
"learning_rate": 9.013599869394096e-09,
|
| 1296 |
+
"loss": 0.3512,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.9873893211698417,
|
| 1301 |
+
"grad_norm": 1.734616112736488,
|
| 1302 |
+
"learning_rate": 4.261009616257638e-09,
|
| 1303 |
+
"loss": 0.3459,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.9927555674805474,
|
| 1308 |
+
"grad_norm": 1.7507232934356496,
|
| 1309 |
+
"learning_rate": 1.2678649143349485e-09,
|
| 1310 |
+
"loss": 0.3454,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.998121813791253,
|
| 1315 |
+
"grad_norm": 1.8191481247099934,
|
| 1316 |
+
"learning_rate": 3.5219917003948003e-11,
|
| 1317 |
+
"loss": 0.3481,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.9991950630533941,
|
| 1322 |
+
"eval_loss": 0.3430202901363373,
|
| 1323 |
+
"eval_runtime": 96.876,
|
| 1324 |
+
"eval_samples_per_second": 3.117,
|
| 1325 |
+
"eval_steps_per_second": 0.785,
|
| 1326 |
+
"step": 931
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9991950630533941,
|
| 1330 |
+
"step": 931,
|
| 1331 |
+
"total_flos": 194880114524160.0,
|
| 1332 |
+
"train_loss": 0.5082111883624412,
|
| 1333 |
+
"train_runtime": 20913.2373,
|
| 1334 |
+
"train_samples_per_second": 1.425,
|
| 1335 |
+
"train_steps_per_second": 0.045
|
| 1336 |
+
}
|
| 1337 |
+
],
|
| 1338 |
+
"logging_steps": 5,
|
| 1339 |
+
"max_steps": 931,
|
| 1340 |
+
"num_input_tokens_seen": 0,
|
| 1341 |
+
"num_train_epochs": 1,
|
| 1342 |
+
"save_steps": 100,
|
| 1343 |
+
"stateful_callbacks": {
|
| 1344 |
+
"TrainerControl": {
|
| 1345 |
+
"args": {
|
| 1346 |
+
"should_epoch_stop": false,
|
| 1347 |
+
"should_evaluate": false,
|
| 1348 |
+
"should_log": false,
|
| 1349 |
+
"should_save": true,
|
| 1350 |
+
"should_training_stop": true
|
| 1351 |
+
},
|
| 1352 |
+
"attributes": {}
|
| 1353 |
+
}
|
| 1354 |
+
},
|
| 1355 |
+
"total_flos": 194880114524160.0,
|
| 1356 |
+
"train_batch_size": 2,
|
| 1357 |
+
"trial_name": null,
|
| 1358 |
+
"trial_params": null
|
| 1359 |
+
}
|