Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May20_03-01-21_gpu4-119-5/events.out.tfevents.1716138241.gpu4-119-5.70660.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- dpo
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-i0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: phi-2-irepo-chatml-v2-i1
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# phi-2-irepo-chatml-v2-i1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-i0](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-i0) on the None dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 8
|
| 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 |
+
- PEFT 0.7.1
|
| 58 |
+
- Transformers 4.36.2
|
| 59 |
+
- Pytorch 2.1.2+cu121
|
| 60 |
+
- Datasets 2.14.6
|
| 61 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335579632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ba2b2a320bda09405479d568db5d1bd603ef8757cc9736167f1a5c32a4c397
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.3301706374836579,
|
| 4 |
+
"train_runtime": 6917.8099,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.337,
|
| 7 |
+
"train_steps_per_second": 0.135
|
| 8 |
+
}
|
runs/May20_03-01-21_gpu4-119-5/events.out.tfevents.1716138241.gpu4-119-5.70660.0
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 sha256:7c6532c33b27e26c71743e3603e96acce876b55a8635a3f9795a48ea6a9f8e5b
|
| 3 |
+
size 64716
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.3301706374836579,
|
| 4 |
+
"train_runtime": 6917.8099,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 4.337,
|
| 7 |
+
"train_steps_per_second": 0.135
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994666666666666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 937,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.319148936170213e-08,
|
| 14 |
+
"logits/chosen": 0.03003755956888199,
|
| 15 |
+
"logits/rejected": 0.14685480296611786,
|
| 16 |
+
"logps/chosen": -314.14739990234375,
|
| 17 |
+
"logps/rejected": -285.09228515625,
|
| 18 |
+
"loss": 0.379,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": 0.24652427434921265,
|
| 29 |
+
"logits/rejected": 0.310183584690094,
|
| 30 |
+
"logps/chosen": -415.2710876464844,
|
| 31 |
+
"logps/rejected": -420.6697692871094,
|
| 32 |
+
"loss": 0.3666,
|
| 33 |
+
"rewards/accuracies": 0.3055555522441864,
|
| 34 |
+
"rewards/chosen": -0.0005877503426745534,
|
| 35 |
+
"rewards/margins": -1.95145039469935e-05,
|
| 36 |
+
"rewards/rejected": -0.000568235875107348,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.2645895481109619,
|
| 43 |
+
"logits/rejected": 0.19589334726333618,
|
| 44 |
+
"logps/chosen": -365.053466796875,
|
| 45 |
+
"logps/rejected": -364.3542785644531,
|
| 46 |
+
"loss": 0.3639,
|
| 47 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 48 |
+
"rewards/chosen": -0.0009052521781995893,
|
| 49 |
+
"rewards/margins": 2.238732122350484e-05,
|
| 50 |
+
"rewards/rejected": -0.000927639368455857,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.20655973255634308,
|
| 57 |
+
"logits/rejected": 0.2799147963523865,
|
| 58 |
+
"logps/chosen": -425.14288330078125,
|
| 59 |
+
"logps/rejected": -414.9308166503906,
|
| 60 |
+
"loss": 0.3657,
|
| 61 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 62 |
+
"rewards/chosen": -0.0010341120650991797,
|
| 63 |
+
"rewards/margins": 0.00020249195222277194,
|
| 64 |
+
"rewards/rejected": -0.0012366041773930192,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.1586448699235916,
|
| 71 |
+
"logits/rejected": 0.3028702735900879,
|
| 72 |
+
"logps/chosen": -435.25311279296875,
|
| 73 |
+
"logps/rejected": -412.69769287109375,
|
| 74 |
+
"loss": 0.3732,
|
| 75 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 76 |
+
"rewards/chosen": -0.000818841508589685,
|
| 77 |
+
"rewards/margins": 0.0002176587877329439,
|
| 78 |
+
"rewards/rejected": -0.0010365003254264593,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.30979618430137634,
|
| 85 |
+
"logits/rejected": 0.18890634179115295,
|
| 86 |
+
"logps/chosen": -376.4929504394531,
|
| 87 |
+
"logps/rejected": -388.2627868652344,
|
| 88 |
+
"loss": 0.3709,
|
| 89 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 90 |
+
"rewards/chosen": -0.0009732651524245739,
|
| 91 |
+
"rewards/margins": 0.00020587551989592612,
|
| 92 |
+
"rewards/rejected": -0.0011791407596319914,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.25725987553596497,
|
| 99 |
+
"logits/rejected": 0.27524492144584656,
|
| 100 |
+
"logps/chosen": -435.30682373046875,
|
| 101 |
+
"logps/rejected": -389.1386413574219,
|
| 102 |
+
"loss": 0.38,
|
| 103 |
+
"rewards/accuracies": 0.4375,
|
| 104 |
+
"rewards/chosen": 0.0007843401399441063,
|
| 105 |
+
"rewards/margins": 0.0004105453845113516,
|
| 106 |
+
"rewards/rejected": 0.00037379475543275476,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.19644694030284882,
|
| 113 |
+
"logits/rejected": 0.2764621675014496,
|
| 114 |
+
"logps/chosen": -445.50042724609375,
|
| 115 |
+
"logps/rejected": -425.63714599609375,
|
| 116 |
+
"loss": 0.3673,
|
| 117 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 118 |
+
"rewards/chosen": 0.004284649156033993,
|
| 119 |
+
"rewards/margins": 0.0006289929151535034,
|
| 120 |
+
"rewards/rejected": 0.003655656473711133,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.17820295691490173,
|
| 127 |
+
"logits/rejected": 0.14415612816810608,
|
| 128 |
+
"logps/chosen": -420.62811279296875,
|
| 129 |
+
"logps/rejected": -431.13250732421875,
|
| 130 |
+
"loss": 0.3782,
|
| 131 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 132 |
+
"rewards/chosen": 0.011514987796545029,
|
| 133 |
+
"rewards/margins": 0.0015228450065478683,
|
| 134 |
+
"rewards/rejected": 0.009992143139243126,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.1115020141005516,
|
| 141 |
+
"logits/rejected": 0.2590204179286957,
|
| 142 |
+
"logps/chosen": -431.19622802734375,
|
| 143 |
+
"logps/rejected": -393.2071228027344,
|
| 144 |
+
"loss": 0.3752,
|
| 145 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 146 |
+
"rewards/chosen": 0.013366015627980232,
|
| 147 |
+
"rewards/margins": 0.0019467566162347794,
|
| 148 |
+
"rewards/rejected": 0.011419258080422878,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.17629960179328918,
|
| 155 |
+
"logits/rejected": 0.18853217363357544,
|
| 156 |
+
"logps/chosen": -391.21258544921875,
|
| 157 |
+
"logps/rejected": -405.5911560058594,
|
| 158 |
+
"loss": 0.3634,
|
| 159 |
+
"rewards/accuracies": 0.45625001192092896,
|
| 160 |
+
"rewards/chosen": 0.006202789954841137,
|
| 161 |
+
"rewards/margins": 0.0038450881838798523,
|
| 162 |
+
"rewards/rejected": 0.0023577010724693537,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.19157476723194122,
|
| 169 |
+
"logits/rejected": 0.2552744746208191,
|
| 170 |
+
"logps/chosen": -388.6427001953125,
|
| 171 |
+
"logps/rejected": -401.7698974609375,
|
| 172 |
+
"loss": 0.371,
|
| 173 |
+
"rewards/accuracies": 0.4375,
|
| 174 |
+
"rewards/chosen": -0.011058819480240345,
|
| 175 |
+
"rewards/margins": 0.004346723668277264,
|
| 176 |
+
"rewards/rejected": -0.015405543148517609,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.1481851041316986,
|
| 183 |
+
"logits/rejected": 0.15830105543136597,
|
| 184 |
+
"logps/chosen": -485.09942626953125,
|
| 185 |
+
"logps/rejected": -512.1583251953125,
|
| 186 |
+
"loss": 0.3596,
|
| 187 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 188 |
+
"rewards/chosen": -0.04192991554737091,
|
| 189 |
+
"rewards/margins": 0.01182691939175129,
|
| 190 |
+
"rewards/rejected": -0.05375684052705765,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.06818593293428421,
|
| 197 |
+
"logits/rejected": 0.1832435131072998,
|
| 198 |
+
"logps/chosen": -470.56787109375,
|
| 199 |
+
"logps/rejected": -495.54296875,
|
| 200 |
+
"loss": 0.3416,
|
| 201 |
+
"rewards/accuracies": 0.46875,
|
| 202 |
+
"rewards/chosen": -0.07512780278921127,
|
| 203 |
+
"rewards/margins": 0.020879648625850677,
|
| 204 |
+
"rewards/rejected": -0.09600745886564255,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.1163097396492958,
|
| 211 |
+
"logits/rejected": 0.10711435973644257,
|
| 212 |
+
"logps/chosen": -498.22589111328125,
|
| 213 |
+
"logps/rejected": -498.1195373535156,
|
| 214 |
+
"loss": 0.3582,
|
| 215 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 216 |
+
"rewards/chosen": -0.10014933347702026,
|
| 217 |
+
"rewards/margins": 0.015763022005558014,
|
| 218 |
+
"rewards/rejected": -0.11591235548257828,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.019728729501366615,
|
| 225 |
+
"logits/rejected": 0.078994520008564,
|
| 226 |
+
"logps/chosen": -495.50775146484375,
|
| 227 |
+
"logps/rejected": -522.085693359375,
|
| 228 |
+
"loss": 0.3351,
|
| 229 |
+
"rewards/accuracies": 0.46875,
|
| 230 |
+
"rewards/chosen": -0.10014746338129044,
|
| 231 |
+
"rewards/margins": 0.027558928355574608,
|
| 232 |
+
"rewards/rejected": -0.1277063935995102,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.03191109746694565,
|
| 239 |
+
"logits/rejected": 0.026030873879790306,
|
| 240 |
+
"logps/chosen": -531.992919921875,
|
| 241 |
+
"logps/rejected": -575.7620239257812,
|
| 242 |
+
"loss": 0.3317,
|
| 243 |
+
"rewards/accuracies": 0.5,
|
| 244 |
+
"rewards/chosen": -0.12353821098804474,
|
| 245 |
+
"rewards/margins": 0.04307270795106888,
|
| 246 |
+
"rewards/rejected": -0.16661091148853302,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.045843735337257385,
|
| 253 |
+
"logits/rejected": -0.08834481984376907,
|
| 254 |
+
"logps/chosen": -522.8604736328125,
|
| 255 |
+
"logps/rejected": -612.8219604492188,
|
| 256 |
+
"loss": 0.3325,
|
| 257 |
+
"rewards/accuracies": 0.512499988079071,
|
| 258 |
+
"rewards/chosen": -0.12141416221857071,
|
| 259 |
+
"rewards/margins": 0.06917469203472137,
|
| 260 |
+
"rewards/rejected": -0.1905888319015503,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.002990189241245389,
|
| 267 |
+
"logits/rejected": 0.019473141059279442,
|
| 268 |
+
"logps/chosen": -489.2099609375,
|
| 269 |
+
"logps/rejected": -574.8321533203125,
|
| 270 |
+
"loss": 0.3276,
|
| 271 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 272 |
+
"rewards/chosen": -0.1273360550403595,
|
| 273 |
+
"rewards/margins": 0.07243254780769348,
|
| 274 |
+
"rewards/rejected": -0.19976858794689178,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": -0.11638545989990234,
|
| 281 |
+
"logits/rejected": -0.009681841358542442,
|
| 282 |
+
"logps/chosen": -484.964111328125,
|
| 283 |
+
"logps/rejected": -536.099609375,
|
| 284 |
+
"loss": 0.3322,
|
| 285 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 286 |
+
"rewards/chosen": -0.12863071262836456,
|
| 287 |
+
"rewards/margins": 0.03380769491195679,
|
| 288 |
+
"rewards/rejected": -0.16243840754032135,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.027831071987748146,
|
| 295 |
+
"logits/rejected": -0.09354544430971146,
|
| 296 |
+
"logps/chosen": -500.5443420410156,
|
| 297 |
+
"logps/rejected": -592.7569580078125,
|
| 298 |
+
"loss": 0.3133,
|
| 299 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 300 |
+
"rewards/chosen": -0.13087543845176697,
|
| 301 |
+
"rewards/margins": 0.05950712040066719,
|
| 302 |
+
"rewards/rejected": -0.19038255512714386,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": -0.0018000513082370162,
|
| 309 |
+
"logits/rejected": -0.0076873586513102055,
|
| 310 |
+
"logps/chosen": -555.552734375,
|
| 311 |
+
"logps/rejected": -638.7350463867188,
|
| 312 |
+
"loss": 0.3334,
|
| 313 |
+
"rewards/accuracies": 0.550000011920929,
|
| 314 |
+
"rewards/chosen": -0.15001370012760162,
|
| 315 |
+
"rewards/margins": 0.07444901764392853,
|
| 316 |
+
"rewards/rejected": -0.22446270287036896,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": -0.06452230364084244,
|
| 323 |
+
"logits/rejected": -0.07058578729629517,
|
| 324 |
+
"logps/chosen": -568.3099365234375,
|
| 325 |
+
"logps/rejected": -612.906005859375,
|
| 326 |
+
"loss": 0.3192,
|
| 327 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 328 |
+
"rewards/chosen": -0.16391663253307343,
|
| 329 |
+
"rewards/margins": 0.06138613820075989,
|
| 330 |
+
"rewards/rejected": -0.22530274093151093,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": -0.08687802404165268,
|
| 337 |
+
"logits/rejected": -0.076780766248703,
|
| 338 |
+
"logps/chosen": -612.529296875,
|
| 339 |
+
"logps/rejected": -664.7831420898438,
|
| 340 |
+
"loss": 0.3315,
|
| 341 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 342 |
+
"rewards/chosen": -0.188650444149971,
|
| 343 |
+
"rewards/margins": 0.07060692459344864,
|
| 344 |
+
"rewards/rejected": -0.25925734639167786,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.1167052760720253,
|
| 351 |
+
"logits/rejected": -0.08061762899160385,
|
| 352 |
+
"logps/chosen": -604.2794189453125,
|
| 353 |
+
"logps/rejected": -630.2823486328125,
|
| 354 |
+
"loss": 0.329,
|
| 355 |
+
"rewards/accuracies": 0.5,
|
| 356 |
+
"rewards/chosen": -0.16320253908634186,
|
| 357 |
+
"rewards/margins": 0.0545579195022583,
|
| 358 |
+
"rewards/rejected": -0.21776047348976135,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": -0.16316112875938416,
|
| 365 |
+
"logits/rejected": -0.14865779876708984,
|
| 366 |
+
"logps/chosen": -552.4512939453125,
|
| 367 |
+
"logps/rejected": -629.3975830078125,
|
| 368 |
+
"loss": 0.3366,
|
| 369 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 370 |
+
"rewards/chosen": -0.14637981355190277,
|
| 371 |
+
"rewards/margins": 0.06526754051446915,
|
| 372 |
+
"rewards/rejected": -0.21164734661579132,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.030054206028580666,
|
| 379 |
+
"logits/rejected": -0.08666323125362396,
|
| 380 |
+
"logps/chosen": -507.67291259765625,
|
| 381 |
+
"logps/rejected": -623.1397094726562,
|
| 382 |
+
"loss": 0.3152,
|
| 383 |
+
"rewards/accuracies": 0.543749988079071,
|
| 384 |
+
"rewards/chosen": -0.12688292562961578,
|
| 385 |
+
"rewards/margins": 0.09281791746616364,
|
| 386 |
+
"rewards/rejected": -0.21970084309577942,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": -0.16756266355514526,
|
| 393 |
+
"logits/rejected": -0.08279438316822052,
|
| 394 |
+
"logps/chosen": -546.107666015625,
|
| 395 |
+
"logps/rejected": -583.4124755859375,
|
| 396 |
+
"loss": 0.3663,
|
| 397 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 398 |
+
"rewards/chosen": -0.14095798134803772,
|
| 399 |
+
"rewards/margins": 0.05275345966219902,
|
| 400 |
+
"rewards/rejected": -0.19371144473552704,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.07078931480646133,
|
| 407 |
+
"logits/rejected": -0.024411968886852264,
|
| 408 |
+
"logps/chosen": -521.5887451171875,
|
| 409 |
+
"logps/rejected": -594.6179809570312,
|
| 410 |
+
"loss": 0.3399,
|
| 411 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 412 |
+
"rewards/chosen": -0.12093210220336914,
|
| 413 |
+
"rewards/margins": 0.07108847051858902,
|
| 414 |
+
"rewards/rejected": -0.19202056527137756,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.11468502134084702,
|
| 421 |
+
"logits/rejected": -0.13895608484745026,
|
| 422 |
+
"logps/chosen": -504.01617431640625,
|
| 423 |
+
"logps/rejected": -566.6771240234375,
|
| 424 |
+
"loss": 0.3359,
|
| 425 |
+
"rewards/accuracies": 0.46875,
|
| 426 |
+
"rewards/chosen": -0.09359009563922882,
|
| 427 |
+
"rewards/margins": 0.06398390233516693,
|
| 428 |
+
"rewards/rejected": -0.15757399797439575,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": -0.15202876925468445,
|
| 435 |
+
"logits/rejected": -0.06361649930477142,
|
| 436 |
+
"logps/chosen": -508.5723571777344,
|
| 437 |
+
"logps/rejected": -572.959716796875,
|
| 438 |
+
"loss": 0.3201,
|
| 439 |
+
"rewards/accuracies": 0.512499988079071,
|
| 440 |
+
"rewards/chosen": -0.10353565216064453,
|
| 441 |
+
"rewards/margins": 0.06490160524845123,
|
| 442 |
+
"rewards/rejected": -0.16843725740909576,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.13953888416290283,
|
| 449 |
+
"logits/rejected": -0.08700491487979889,
|
| 450 |
+
"logps/chosen": -540.6795654296875,
|
| 451 |
+
"logps/rejected": -607.9012451171875,
|
| 452 |
+
"loss": 0.3162,
|
| 453 |
+
"rewards/accuracies": 0.512499988079071,
|
| 454 |
+
"rewards/chosen": -0.12709401547908783,
|
| 455 |
+
"rewards/margins": 0.06415100395679474,
|
| 456 |
+
"rewards/rejected": -0.19124500453472137,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.16462412476539612,
|
| 463 |
+
"logits/rejected": -0.05515863746404648,
|
| 464 |
+
"logps/chosen": -506.59637451171875,
|
| 465 |
+
"logps/rejected": -600.5057373046875,
|
| 466 |
+
"loss": 0.314,
|
| 467 |
+
"rewards/accuracies": 0.46875,
|
| 468 |
+
"rewards/chosen": -0.12504397332668304,
|
| 469 |
+
"rewards/margins": 0.0829906165599823,
|
| 470 |
+
"rewards/rejected": -0.20803460478782654,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.08193415403366089,
|
| 477 |
+
"logits/rejected": -0.05177025869488716,
|
| 478 |
+
"logps/chosen": -479.7059631347656,
|
| 479 |
+
"logps/rejected": -517.7894287109375,
|
| 480 |
+
"loss": 0.3372,
|
| 481 |
+
"rewards/accuracies": 0.46875,
|
| 482 |
+
"rewards/chosen": -0.10423684120178223,
|
| 483 |
+
"rewards/margins": 0.046939365565776825,
|
| 484 |
+
"rewards/rejected": -0.15117622911930084,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": -0.15444053709506989,
|
| 491 |
+
"logits/rejected": -0.02473391965031624,
|
| 492 |
+
"logps/chosen": -556.2892456054688,
|
| 493 |
+
"logps/rejected": -601.0501708984375,
|
| 494 |
+
"loss": 0.3136,
|
| 495 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 496 |
+
"rewards/chosen": -0.0967629998922348,
|
| 497 |
+
"rewards/margins": 0.06504927575588226,
|
| 498 |
+
"rewards/rejected": -0.16181227564811707,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.011976124718785286,
|
| 505 |
+
"logits/rejected": 0.010825025849044323,
|
| 506 |
+
"logps/chosen": -520.3416137695312,
|
| 507 |
+
"logps/rejected": -617.6292114257812,
|
| 508 |
+
"loss": 0.3083,
|
| 509 |
+
"rewards/accuracies": 0.612500011920929,
|
| 510 |
+
"rewards/chosen": -0.09249953180551529,
|
| 511 |
+
"rewards/margins": 0.09974247217178345,
|
| 512 |
+
"rewards/rejected": -0.19224199652671814,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.0032506571151316166,
|
| 519 |
+
"logits/rejected": -0.05111609026789665,
|
| 520 |
+
"logps/chosen": -534.9469604492188,
|
| 521 |
+
"logps/rejected": -627.3300170898438,
|
| 522 |
+
"loss": 0.3096,
|
| 523 |
+
"rewards/accuracies": 0.518750011920929,
|
| 524 |
+
"rewards/chosen": -0.11961764097213745,
|
| 525 |
+
"rewards/margins": 0.09712241590023041,
|
| 526 |
+
"rewards/rejected": -0.21674005687236786,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.04654575139284134,
|
| 533 |
+
"logits/rejected": 0.02392629161477089,
|
| 534 |
+
"logps/chosen": -564.7318115234375,
|
| 535 |
+
"logps/rejected": -613.5872802734375,
|
| 536 |
+
"loss": 0.326,
|
| 537 |
+
"rewards/accuracies": 0.5,
|
| 538 |
+
"rewards/chosen": -0.13059517741203308,
|
| 539 |
+
"rewards/margins": 0.08819568157196045,
|
| 540 |
+
"rewards/rejected": -0.21879085898399353,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.061980921775102615,
|
| 547 |
+
"logits/rejected": 0.08209049701690674,
|
| 548 |
+
"logps/chosen": -578.1087646484375,
|
| 549 |
+
"logps/rejected": -638.3121948242188,
|
| 550 |
+
"loss": 0.3223,
|
| 551 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 552 |
+
"rewards/chosen": -0.13412974774837494,
|
| 553 |
+
"rewards/margins": 0.07588179409503937,
|
| 554 |
+
"rewards/rejected": -0.2100115567445755,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.05568457394838333,
|
| 561 |
+
"logits/rejected": -0.08035759627819061,
|
| 562 |
+
"logps/chosen": -512.9743041992188,
|
| 563 |
+
"logps/rejected": -560.0599365234375,
|
| 564 |
+
"loss": 0.346,
|
| 565 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 566 |
+
"rewards/chosen": -0.1260611116886139,
|
| 567 |
+
"rewards/margins": 0.04897795990109444,
|
| 568 |
+
"rewards/rejected": -0.17503906786441803,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": -0.05415787175297737,
|
| 575 |
+
"logits/rejected": 0.043633949011564255,
|
| 576 |
+
"logps/chosen": -507.5973205566406,
|
| 577 |
+
"logps/rejected": -553.030517578125,
|
| 578 |
+
"loss": 0.326,
|
| 579 |
+
"rewards/accuracies": 0.550000011920929,
|
| 580 |
+
"rewards/chosen": -0.10723169893026352,
|
| 581 |
+
"rewards/margins": 0.06125740334391594,
|
| 582 |
+
"rewards/rejected": -0.16848909854888916,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.07862399518489838,
|
| 589 |
+
"logits/rejected": -0.04382779076695442,
|
| 590 |
+
"logps/chosen": -506.9168395996094,
|
| 591 |
+
"logps/rejected": -584.4060668945312,
|
| 592 |
+
"loss": 0.3222,
|
| 593 |
+
"rewards/accuracies": 0.550000011920929,
|
| 594 |
+
"rewards/chosen": -0.09048938751220703,
|
| 595 |
+
"rewards/margins": 0.07321049273014069,
|
| 596 |
+
"rewards/rejected": -0.16369988024234772,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.046413786709308624,
|
| 603 |
+
"logits/rejected": -0.0055254013277590275,
|
| 604 |
+
"logps/chosen": -521.91259765625,
|
| 605 |
+
"logps/rejected": -581.7081298828125,
|
| 606 |
+
"loss": 0.3205,
|
| 607 |
+
"rewards/accuracies": 0.5,
|
| 608 |
+
"rewards/chosen": -0.10815830528736115,
|
| 609 |
+
"rewards/margins": 0.06724079698324203,
|
| 610 |
+
"rewards/rejected": -0.1753990799188614,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.06368018686771393,
|
| 617 |
+
"logits/rejected": -0.005307002458721399,
|
| 618 |
+
"logps/chosen": -505.17950439453125,
|
| 619 |
+
"logps/rejected": -562.3865966796875,
|
| 620 |
+
"loss": 0.3294,
|
| 621 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 622 |
+
"rewards/chosen": -0.11235632002353668,
|
| 623 |
+
"rewards/margins": 0.0673181563615799,
|
| 624 |
+
"rewards/rejected": -0.17967447638511658,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.12101604044437408,
|
| 631 |
+
"logits/rejected": -0.049035437405109406,
|
| 632 |
+
"logps/chosen": -559.6871337890625,
|
| 633 |
+
"logps/rejected": -634.565673828125,
|
| 634 |
+
"loss": 0.3143,
|
| 635 |
+
"rewards/accuracies": 0.46875,
|
| 636 |
+
"rewards/chosen": -0.14436963200569153,
|
| 637 |
+
"rewards/margins": 0.07392090559005737,
|
| 638 |
+
"rewards/rejected": -0.2182905375957489,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.005751132965087891,
|
| 645 |
+
"logits/rejected": 0.00010851323895622045,
|
| 646 |
+
"logps/chosen": -529.8284301757812,
|
| 647 |
+
"logps/rejected": -600.77783203125,
|
| 648 |
+
"loss": 0.332,
|
| 649 |
+
"rewards/accuracies": 0.512499988079071,
|
| 650 |
+
"rewards/chosen": -0.12567661702632904,
|
| 651 |
+
"rewards/margins": 0.07157091796398163,
|
| 652 |
+
"rewards/rejected": -0.19724753499031067,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.012865634635090828,
|
| 659 |
+
"logits/rejected": -0.07809716463088989,
|
| 660 |
+
"logps/chosen": -546.5116577148438,
|
| 661 |
+
"logps/rejected": -665.4036865234375,
|
| 662 |
+
"loss": 0.3226,
|
| 663 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 664 |
+
"rewards/chosen": -0.14242392778396606,
|
| 665 |
+
"rewards/margins": 0.08929804712533951,
|
| 666 |
+
"rewards/rejected": -0.23172196745872498,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.08698035031557083,
|
| 673 |
+
"logits/rejected": 0.01734771579504013,
|
| 674 |
+
"logps/chosen": -509.57977294921875,
|
| 675 |
+
"logps/rejected": -574.0706176757812,
|
| 676 |
+
"loss": 0.3039,
|
| 677 |
+
"rewards/accuracies": 0.543749988079071,
|
| 678 |
+
"rewards/chosen": -0.13136714696884155,
|
| 679 |
+
"rewards/margins": 0.09488403052091599,
|
| 680 |
+
"rewards/rejected": -0.22625115513801575,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.11155049502849579,
|
| 687 |
+
"logits/rejected": -0.028806675225496292,
|
| 688 |
+
"logps/chosen": -595.2827758789062,
|
| 689 |
+
"logps/rejected": -679.2177734375,
|
| 690 |
+
"loss": 0.3197,
|
| 691 |
+
"rewards/accuracies": 0.518750011920929,
|
| 692 |
+
"rewards/chosen": -0.16865819692611694,
|
| 693 |
+
"rewards/margins": 0.08433203399181366,
|
| 694 |
+
"rewards/rejected": -0.2529902160167694,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.09512178599834442,
|
| 701 |
+
"logits/rejected": 0.04600674659013748,
|
| 702 |
+
"logps/chosen": -571.9730224609375,
|
| 703 |
+
"logps/rejected": -646.7930297851562,
|
| 704 |
+
"loss": 0.3138,
|
| 705 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 706 |
+
"rewards/chosen": -0.17400047183036804,
|
| 707 |
+
"rewards/margins": 0.07587233185768127,
|
| 708 |
+
"rewards/rejected": -0.24987280368804932,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.04382805526256561,
|
| 715 |
+
"logits/rejected": -0.0209367536008358,
|
| 716 |
+
"logps/chosen": -529.54931640625,
|
| 717 |
+
"logps/rejected": -601.68701171875,
|
| 718 |
+
"loss": 0.332,
|
| 719 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 720 |
+
"rewards/chosen": -0.15199477970600128,
|
| 721 |
+
"rewards/margins": 0.06770177185535431,
|
| 722 |
+
"rewards/rejected": -0.2196965217590332,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.06805320829153061,
|
| 729 |
+
"logits/rejected": -0.0435967817902565,
|
| 730 |
+
"logps/chosen": -574.57568359375,
|
| 731 |
+
"logps/rejected": -631.7911987304688,
|
| 732 |
+
"loss": 0.3189,
|
| 733 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 734 |
+
"rewards/chosen": -0.13725146651268005,
|
| 735 |
+
"rewards/margins": 0.07907568663358688,
|
| 736 |
+
"rewards/rejected": -0.21632714569568634,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.053729694336652756,
|
| 743 |
+
"logits/rejected": -0.009868663735687733,
|
| 744 |
+
"logps/chosen": -575.8187866210938,
|
| 745 |
+
"logps/rejected": -617.7347412109375,
|
| 746 |
+
"loss": 0.3371,
|
| 747 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 748 |
+
"rewards/chosen": -0.14825518429279327,
|
| 749 |
+
"rewards/margins": 0.07731777429580688,
|
| 750 |
+
"rewards/rejected": -0.22557297348976135,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.1181708350777626,
|
| 757 |
+
"logits/rejected": -0.051215410232543945,
|
| 758 |
+
"logps/chosen": -563.2030639648438,
|
| 759 |
+
"logps/rejected": -628.1510009765625,
|
| 760 |
+
"loss": 0.3196,
|
| 761 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 762 |
+
"rewards/chosen": -0.1552611142396927,
|
| 763 |
+
"rewards/margins": 0.07067932933568954,
|
| 764 |
+
"rewards/rejected": -0.22594043612480164,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.0351797491312027,
|
| 771 |
+
"logits/rejected": -0.09967297315597534,
|
| 772 |
+
"logps/chosen": -557.1263427734375,
|
| 773 |
+
"logps/rejected": -605.281982421875,
|
| 774 |
+
"loss": 0.3204,
|
| 775 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 776 |
+
"rewards/chosen": -0.14646664261817932,
|
| 777 |
+
"rewards/margins": 0.07007946074008942,
|
| 778 |
+
"rewards/rejected": -0.21654610335826874,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.1466439813375473,
|
| 785 |
+
"logits/rejected": -0.06507374346256256,
|
| 786 |
+
"logps/chosen": -511.141845703125,
|
| 787 |
+
"logps/rejected": -615.8265380859375,
|
| 788 |
+
"loss": 0.3076,
|
| 789 |
+
"rewards/accuracies": 0.5,
|
| 790 |
+
"rewards/chosen": -0.15620598196983337,
|
| 791 |
+
"rewards/margins": 0.08635568618774414,
|
| 792 |
+
"rewards/rejected": -0.24256166815757751,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": -0.01115155965089798,
|
| 799 |
+
"logits/rejected": -0.14947594702243805,
|
| 800 |
+
"logps/chosen": -603.1889038085938,
|
| 801 |
+
"logps/rejected": -690.7286376953125,
|
| 802 |
+
"loss": 0.3239,
|
| 803 |
+
"rewards/accuracies": 0.543749988079071,
|
| 804 |
+
"rewards/chosen": -0.17474761605262756,
|
| 805 |
+
"rewards/margins": 0.09008537232875824,
|
| 806 |
+
"rewards/rejected": -0.2648329734802246,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.05594000220298767,
|
| 813 |
+
"logits/rejected": 0.006943766959011555,
|
| 814 |
+
"logps/chosen": -565.42724609375,
|
| 815 |
+
"logps/rejected": -629.1002197265625,
|
| 816 |
+
"loss": 0.3094,
|
| 817 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 818 |
+
"rewards/chosen": -0.15515407919883728,
|
| 819 |
+
"rewards/margins": 0.07448241859674454,
|
| 820 |
+
"rewards/rejected": -0.22963650524616241,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.13735847175121307,
|
| 827 |
+
"logits/rejected": 0.04537354037165642,
|
| 828 |
+
"logps/chosen": -552.429931640625,
|
| 829 |
+
"logps/rejected": -570.6002807617188,
|
| 830 |
+
"loss": 0.3396,
|
| 831 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 832 |
+
"rewards/chosen": -0.15960142016410828,
|
| 833 |
+
"rewards/margins": 0.04359527677297592,
|
| 834 |
+
"rewards/rejected": -0.2031966894865036,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": -0.07736693322658539,
|
| 841 |
+
"logits/rejected": -0.05264727398753166,
|
| 842 |
+
"logps/chosen": -544.4369506835938,
|
| 843 |
+
"logps/rejected": -598.355712890625,
|
| 844 |
+
"loss": 0.3445,
|
| 845 |
+
"rewards/accuracies": 0.4375,
|
| 846 |
+
"rewards/chosen": -0.15497347712516785,
|
| 847 |
+
"rewards/margins": 0.06363853067159653,
|
| 848 |
+
"rewards/rejected": -0.21861203014850616,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.07268525660037994,
|
| 855 |
+
"logits/rejected": -0.053814847022295,
|
| 856 |
+
"logps/chosen": -544.3436279296875,
|
| 857 |
+
"logps/rejected": -624.2950439453125,
|
| 858 |
+
"loss": 0.3343,
|
| 859 |
+
"rewards/accuracies": 0.53125,
|
| 860 |
+
"rewards/chosen": -0.146144837141037,
|
| 861 |
+
"rewards/margins": 0.07093065977096558,
|
| 862 |
+
"rewards/rejected": -0.21707551181316376,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.07499315589666367,
|
| 869 |
+
"logits/rejected": -0.029876768589019775,
|
| 870 |
+
"logps/chosen": -565.154296875,
|
| 871 |
+
"logps/rejected": -655.4544067382812,
|
| 872 |
+
"loss": 0.2842,
|
| 873 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 874 |
+
"rewards/chosen": -0.13710975646972656,
|
| 875 |
+
"rewards/margins": 0.07628355920314789,
|
| 876 |
+
"rewards/rejected": -0.21339330077171326,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.10578916221857071,
|
| 883 |
+
"logits/rejected": 0.04064566642045975,
|
| 884 |
+
"logps/chosen": -581.9578247070312,
|
| 885 |
+
"logps/rejected": -640.3221435546875,
|
| 886 |
+
"loss": 0.3135,
|
| 887 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 888 |
+
"rewards/chosen": -0.13465943932533264,
|
| 889 |
+
"rewards/margins": 0.0698099285364151,
|
| 890 |
+
"rewards/rejected": -0.20446936786174774,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.08297138661146164,
|
| 897 |
+
"logits/rejected": -0.07259473949670792,
|
| 898 |
+
"logps/chosen": -585.0145263671875,
|
| 899 |
+
"logps/rejected": -616.9873657226562,
|
| 900 |
+
"loss": 0.3218,
|
| 901 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 902 |
+
"rewards/chosen": -0.1459634006023407,
|
| 903 |
+
"rewards/margins": 0.07179699838161469,
|
| 904 |
+
"rewards/rejected": -0.21776041388511658,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.0852777510881424,
|
| 911 |
+
"logits/rejected": -0.1009194403886795,
|
| 912 |
+
"logps/chosen": -514.9520263671875,
|
| 913 |
+
"logps/rejected": -590.4235229492188,
|
| 914 |
+
"loss": 0.3253,
|
| 915 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 916 |
+
"rewards/chosen": -0.12546613812446594,
|
| 917 |
+
"rewards/margins": 0.07676034420728683,
|
| 918 |
+
"rewards/rejected": -0.20222647488117218,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.05136794596910477,
|
| 925 |
+
"logits/rejected": -0.047903820872306824,
|
| 926 |
+
"logps/chosen": -556.219970703125,
|
| 927 |
+
"logps/rejected": -654.3678588867188,
|
| 928 |
+
"loss": 0.3159,
|
| 929 |
+
"rewards/accuracies": 0.5625,
|
| 930 |
+
"rewards/chosen": -0.1294935643672943,
|
| 931 |
+
"rewards/margins": 0.09803324192762375,
|
| 932 |
+
"rewards/rejected": -0.22752681374549866,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.09225879609584808,
|
| 939 |
+
"logits/rejected": -0.1522790640592575,
|
| 940 |
+
"logps/chosen": -538.4688110351562,
|
| 941 |
+
"logps/rejected": -610.7028198242188,
|
| 942 |
+
"loss": 0.3291,
|
| 943 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 944 |
+
"rewards/chosen": -0.1511029750108719,
|
| 945 |
+
"rewards/margins": 0.06751099228858948,
|
| 946 |
+
"rewards/rejected": -0.21861395239830017,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.07817684859037399,
|
| 953 |
+
"logits/rejected": -0.11500729620456696,
|
| 954 |
+
"logps/chosen": -518.6499633789062,
|
| 955 |
+
"logps/rejected": -615.0601806640625,
|
| 956 |
+
"loss": 0.3069,
|
| 957 |
+
"rewards/accuracies": 0.518750011920929,
|
| 958 |
+
"rewards/chosen": -0.1302158087491989,
|
| 959 |
+
"rewards/margins": 0.09146422147750854,
|
| 960 |
+
"rewards/rejected": -0.22168001532554626,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": -0.04123290255665779,
|
| 967 |
+
"logits/rejected": -0.0999784916639328,
|
| 968 |
+
"logps/chosen": -584.451171875,
|
| 969 |
+
"logps/rejected": -703.47998046875,
|
| 970 |
+
"loss": 0.3058,
|
| 971 |
+
"rewards/accuracies": 0.512499988079071,
|
| 972 |
+
"rewards/chosen": -0.15831688046455383,
|
| 973 |
+
"rewards/margins": 0.11426403373479843,
|
| 974 |
+
"rewards/rejected": -0.27258092164993286,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.07548685371875763,
|
| 981 |
+
"logits/rejected": -0.11166922748088837,
|
| 982 |
+
"logps/chosen": -550.4864501953125,
|
| 983 |
+
"logps/rejected": -603.9669189453125,
|
| 984 |
+
"loss": 0.3336,
|
| 985 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 986 |
+
"rewards/chosen": -0.15913598239421844,
|
| 987 |
+
"rewards/margins": 0.06622796505689621,
|
| 988 |
+
"rewards/rejected": -0.22536394000053406,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.07478149980306625,
|
| 995 |
+
"logits/rejected": -0.011451124213635921,
|
| 996 |
+
"logps/chosen": -555.3692626953125,
|
| 997 |
+
"logps/rejected": -622.7389526367188,
|
| 998 |
+
"loss": 0.3177,
|
| 999 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1000 |
+
"rewards/chosen": -0.14817936718463898,
|
| 1001 |
+
"rewards/margins": 0.07494769245386124,
|
| 1002 |
+
"rewards/rejected": -0.22312703728675842,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.15149171650409698,
|
| 1009 |
+
"logits/rejected": -0.008707734756171703,
|
| 1010 |
+
"logps/chosen": -537.5607299804688,
|
| 1011 |
+
"logps/rejected": -632.0250244140625,
|
| 1012 |
+
"loss": 0.3153,
|
| 1013 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1014 |
+
"rewards/chosen": -0.14303314685821533,
|
| 1015 |
+
"rewards/margins": 0.1020839661359787,
|
| 1016 |
+
"rewards/rejected": -0.24511709809303284,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.08291809260845184,
|
| 1023 |
+
"logits/rejected": -0.06536273658275604,
|
| 1024 |
+
"logps/chosen": -605.5488891601562,
|
| 1025 |
+
"logps/rejected": -701.1112060546875,
|
| 1026 |
+
"loss": 0.3347,
|
| 1027 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1028 |
+
"rewards/chosen": -0.16533637046813965,
|
| 1029 |
+
"rewards/margins": 0.09125199168920517,
|
| 1030 |
+
"rewards/rejected": -0.2565883696079254,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.13041993975639343,
|
| 1037 |
+
"logits/rejected": -0.04777718335390091,
|
| 1038 |
+
"logps/chosen": -541.6893310546875,
|
| 1039 |
+
"logps/rejected": -630.17138671875,
|
| 1040 |
+
"loss": 0.3055,
|
| 1041 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 1042 |
+
"rewards/chosen": -0.14917008578777313,
|
| 1043 |
+
"rewards/margins": 0.09115210920572281,
|
| 1044 |
+
"rewards/rejected": -0.24032218754291534,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.09324527531862259,
|
| 1051 |
+
"logits/rejected": -0.11122927814722061,
|
| 1052 |
+
"logps/chosen": -541.8341064453125,
|
| 1053 |
+
"logps/rejected": -629.8985595703125,
|
| 1054 |
+
"loss": 0.3379,
|
| 1055 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1056 |
+
"rewards/chosen": -0.16076061129570007,
|
| 1057 |
+
"rewards/margins": 0.07641086727380753,
|
| 1058 |
+
"rewards/rejected": -0.2371714562177658,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.1291544884443283,
|
| 1065 |
+
"logits/rejected": -0.02545195445418358,
|
| 1066 |
+
"logps/chosen": -582.502197265625,
|
| 1067 |
+
"logps/rejected": -676.6446533203125,
|
| 1068 |
+
"loss": 0.3138,
|
| 1069 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1070 |
+
"rewards/chosen": -0.15107361972332,
|
| 1071 |
+
"rewards/margins": 0.09025880694389343,
|
| 1072 |
+
"rewards/rejected": -0.24133244156837463,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.1935300976037979,
|
| 1079 |
+
"logits/rejected": -0.0874740406870842,
|
| 1080 |
+
"logps/chosen": -634.2234497070312,
|
| 1081 |
+
"logps/rejected": -651.4421997070312,
|
| 1082 |
+
"loss": 0.3293,
|
| 1083 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1084 |
+
"rewards/chosen": -0.17711934447288513,
|
| 1085 |
+
"rewards/margins": 0.060172189027071,
|
| 1086 |
+
"rewards/rejected": -0.23729152977466583,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.09884585440158844,
|
| 1093 |
+
"logits/rejected": -0.052547551691532135,
|
| 1094 |
+
"logps/chosen": -597.0643310546875,
|
| 1095 |
+
"logps/rejected": -668.3179931640625,
|
| 1096 |
+
"loss": 0.3121,
|
| 1097 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1098 |
+
"rewards/chosen": -0.15433833003044128,
|
| 1099 |
+
"rewards/margins": 0.07509264349937439,
|
| 1100 |
+
"rewards/rejected": -0.22943095862865448,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.17812196910381317,
|
| 1107 |
+
"logits/rejected": -0.04409525915980339,
|
| 1108 |
+
"logps/chosen": -529.5570068359375,
|
| 1109 |
+
"logps/rejected": -592.1903076171875,
|
| 1110 |
+
"loss": 0.3069,
|
| 1111 |
+
"rewards/accuracies": 0.5,
|
| 1112 |
+
"rewards/chosen": -0.12470044940710068,
|
| 1113 |
+
"rewards/margins": 0.08706951141357422,
|
| 1114 |
+
"rewards/rejected": -0.2117699682712555,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.17632423341274261,
|
| 1121 |
+
"logits/rejected": 0.020423654466867447,
|
| 1122 |
+
"logps/chosen": -539.355224609375,
|
| 1123 |
+
"logps/rejected": -550.2349853515625,
|
| 1124 |
+
"loss": 0.3477,
|
| 1125 |
+
"rewards/accuracies": 0.4375,
|
| 1126 |
+
"rewards/chosen": -0.14735418558120728,
|
| 1127 |
+
"rewards/margins": 0.04963860288262367,
|
| 1128 |
+
"rewards/rejected": -0.19699278473854065,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.11399457603693008,
|
| 1135 |
+
"logits/rejected": -0.008361217565834522,
|
| 1136 |
+
"logps/chosen": -550.0650634765625,
|
| 1137 |
+
"logps/rejected": -629.9093017578125,
|
| 1138 |
+
"loss": 0.342,
|
| 1139 |
+
"rewards/accuracies": 0.543749988079071,
|
| 1140 |
+
"rewards/chosen": -0.14632944762706757,
|
| 1141 |
+
"rewards/margins": 0.09393130242824554,
|
| 1142 |
+
"rewards/rejected": -0.2402607500553131,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.1393519937992096,
|
| 1149 |
+
"logits/rejected": -0.07454421371221542,
|
| 1150 |
+
"logps/chosen": -484.50213623046875,
|
| 1151 |
+
"logps/rejected": -572.2808837890625,
|
| 1152 |
+
"loss": 0.3571,
|
| 1153 |
+
"rewards/accuracies": 0.46875,
|
| 1154 |
+
"rewards/chosen": -0.12875160574913025,
|
| 1155 |
+
"rewards/margins": 0.08377497643232346,
|
| 1156 |
+
"rewards/rejected": -0.21252655982971191,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.0922452062368393,
|
| 1163 |
+
"logits/rejected": -0.11933571100234985,
|
| 1164 |
+
"logps/chosen": -504.70806884765625,
|
| 1165 |
+
"logps/rejected": -641.5916748046875,
|
| 1166 |
+
"loss": 0.3064,
|
| 1167 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1168 |
+
"rewards/chosen": -0.13076017796993256,
|
| 1169 |
+
"rewards/margins": 0.10374923050403595,
|
| 1170 |
+
"rewards/rejected": -0.2345094233751297,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.08234205842018127,
|
| 1177 |
+
"logits/rejected": 0.009737101383507252,
|
| 1178 |
+
"logps/chosen": -560.4942016601562,
|
| 1179 |
+
"logps/rejected": -647.23095703125,
|
| 1180 |
+
"loss": 0.3171,
|
| 1181 |
+
"rewards/accuracies": 0.5625,
|
| 1182 |
+
"rewards/chosen": -0.1362009346485138,
|
| 1183 |
+
"rewards/margins": 0.08297161757946014,
|
| 1184 |
+
"rewards/rejected": -0.21917252242565155,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.010607835836708546,
|
| 1191 |
+
"logits/rejected": -0.1094130128622055,
|
| 1192 |
+
"logps/chosen": -571.977783203125,
|
| 1193 |
+
"logps/rejected": -655.345703125,
|
| 1194 |
+
"loss": 0.3039,
|
| 1195 |
+
"rewards/accuracies": 0.5,
|
| 1196 |
+
"rewards/chosen": -0.1528376042842865,
|
| 1197 |
+
"rewards/margins": 0.06883414089679718,
|
| 1198 |
+
"rewards/rejected": -0.22167173027992249,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.10850746929645538,
|
| 1205 |
+
"logits/rejected": -0.10889410972595215,
|
| 1206 |
+
"logps/chosen": -419.2569885253906,
|
| 1207 |
+
"logps/rejected": -512.2922973632812,
|
| 1208 |
+
"loss": 0.3312,
|
| 1209 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1210 |
+
"rewards/chosen": -0.11631663888692856,
|
| 1211 |
+
"rewards/margins": 0.07554365694522858,
|
| 1212 |
+
"rewards/rejected": -0.19186028838157654,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.16420094668865204,
|
| 1219 |
+
"logits/rejected": -0.08157550543546677,
|
| 1220 |
+
"logps/chosen": -544.343994140625,
|
| 1221 |
+
"logps/rejected": -583.8645629882812,
|
| 1222 |
+
"loss": 0.318,
|
| 1223 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 1224 |
+
"rewards/chosen": -0.1383691132068634,
|
| 1225 |
+
"rewards/margins": 0.07660222053527832,
|
| 1226 |
+
"rewards/rejected": -0.21497133374214172,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.13259460031986237,
|
| 1233 |
+
"logits/rejected": -0.15146221220493317,
|
| 1234 |
+
"logps/chosen": -514.0303955078125,
|
| 1235 |
+
"logps/rejected": -571.2809448242188,
|
| 1236 |
+
"loss": 0.3349,
|
| 1237 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 1238 |
+
"rewards/chosen": -0.13906028866767883,
|
| 1239 |
+
"rewards/margins": 0.06452740728855133,
|
| 1240 |
+
"rewards/rejected": -0.20358769595623016,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.0921165943145752,
|
| 1247 |
+
"logits/rejected": -0.084059938788414,
|
| 1248 |
+
"logps/chosen": -513.1318969726562,
|
| 1249 |
+
"logps/rejected": -630.0098876953125,
|
| 1250 |
+
"loss": 0.309,
|
| 1251 |
+
"rewards/accuracies": 0.581250011920929,
|
| 1252 |
+
"rewards/chosen": -0.13389384746551514,
|
| 1253 |
+
"rewards/margins": 0.10617604106664658,
|
| 1254 |
+
"rewards/rejected": -0.24006986618041992,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.1827644407749176,
|
| 1261 |
+
"logits/rejected": -0.017491687089204788,
|
| 1262 |
+
"logps/chosen": -513.20703125,
|
| 1263 |
+
"logps/rejected": -602.4353637695312,
|
| 1264 |
+
"loss": 0.3324,
|
| 1265 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1266 |
+
"rewards/chosen": -0.12371834367513657,
|
| 1267 |
+
"rewards/margins": 0.09411574900150299,
|
| 1268 |
+
"rewards/rejected": -0.21783408522605896,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.10702376067638397,
|
| 1275 |
+
"logits/rejected": -0.09792954474687576,
|
| 1276 |
+
"logps/chosen": -554.7036743164062,
|
| 1277 |
+
"logps/rejected": -612.7283935546875,
|
| 1278 |
+
"loss": 0.3209,
|
| 1279 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 1280 |
+
"rewards/chosen": -0.1507497876882553,
|
| 1281 |
+
"rewards/margins": 0.05762406066060066,
|
| 1282 |
+
"rewards/rejected": -0.20837385952472687,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.14019733667373657,
|
| 1289 |
+
"logits/rejected": -0.11023645102977753,
|
| 1290 |
+
"logps/chosen": -621.0760498046875,
|
| 1291 |
+
"logps/rejected": -737.30078125,
|
| 1292 |
+
"loss": 0.3071,
|
| 1293 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1294 |
+
"rewards/chosen": -0.15968570113182068,
|
| 1295 |
+
"rewards/margins": 0.11614030599594116,
|
| 1296 |
+
"rewards/rejected": -0.27582600712776184,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.09468534588813782,
|
| 1303 |
+
"logits/rejected": -0.021795030683279037,
|
| 1304 |
+
"logps/chosen": -583.4420166015625,
|
| 1305 |
+
"logps/rejected": -647.2615356445312,
|
| 1306 |
+
"loss": 0.3225,
|
| 1307 |
+
"rewards/accuracies": 0.53125,
|
| 1308 |
+
"rewards/chosen": -0.14064806699752808,
|
| 1309 |
+
"rewards/margins": 0.08540509641170502,
|
| 1310 |
+
"rewards/rejected": -0.22605319321155548,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": -0.09509189426898956,
|
| 1317 |
+
"logits/rejected": -0.08425020426511765,
|
| 1318 |
+
"logps/chosen": -551.0325317382812,
|
| 1319 |
+
"logps/rejected": -589.43017578125,
|
| 1320 |
+
"loss": 0.3333,
|
| 1321 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1322 |
+
"rewards/chosen": -0.1517583280801773,
|
| 1323 |
+
"rewards/margins": 0.05821775645017624,
|
| 1324 |
+
"rewards/rejected": -0.20997610688209534,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.3301706374836579,
|
| 1332 |
+
"train_runtime": 6917.8099,
|
| 1333 |
+
"train_samples_per_second": 4.337,
|
| 1334 |
+
"train_steps_per_second": 0.135
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 10,
|
| 1338 |
+
"max_steps": 937,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 100,
|
| 1342 |
+
"total_flos": 0.0,
|
| 1343 |
+
"train_batch_size": 4,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|