Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May20_22-57-24_gpu4-119-5/events.out.tfevents.1716210021.gpu4-119-5.1054183.0 +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-v8-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-v8-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:aaf76a4f8002a9c20752fca19a7d6cff7cd9cc4517296c56710a0c0221ca3fbd
|
| 3 |
size 335579632
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.051660444591444865,
|
| 4 |
+
"train_runtime": 2852.4153,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 10.517,
|
| 7 |
+
"train_steps_per_second": 0.328
|
| 8 |
+
}
|
runs/May20_22-57-24_gpu4-119-5/events.out.tfevents.1716210021.gpu4-119-5.1054183.0
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 sha256:0184379cc52f952af0786fe0bf2627ddf660dde3f3b7c95529ebf5213f2cfb03
|
| 3 |
+
size 19845
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.051660444591444865,
|
| 4 |
+
"train_runtime": 2852.4153,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 10.517,
|
| 7 |
+
"train_steps_per_second": 0.328
|
| 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": 0.34782999753952026,
|
| 15 |
+
"logits/rejected": 0.3427616059780121,
|
| 16 |
+
"logps/chosen": -325.28106689453125,
|
| 17 |
+
"logps/rejected": -307.72515869140625,
|
| 18 |
+
"loss": 0.1853,
|
| 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": 0.30850738286972046,
|
| 29 |
+
"logits/rejected": 0.3003820478916168,
|
| 30 |
+
"logps/chosen": -350.7467956542969,
|
| 31 |
+
"logps/rejected": -376.2046203613281,
|
| 32 |
+
"loss": 0.2147,
|
| 33 |
+
"rewards/accuracies": 0.2291666716337204,
|
| 34 |
+
"rewards/chosen": -4.5030174078419805e-05,
|
| 35 |
+
"rewards/margins": 1.3379417396208737e-05,
|
| 36 |
+
"rewards/rejected": -5.840959056513384e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.2997807562351227,
|
| 43 |
+
"logits/rejected": 0.3171563148498535,
|
| 44 |
+
"logps/chosen": -282.0256652832031,
|
| 45 |
+
"logps/rejected": -303.3882751464844,
|
| 46 |
+
"loss": 0.2119,
|
| 47 |
+
"rewards/accuracies": 0.21875,
|
| 48 |
+
"rewards/chosen": -0.0002205806813435629,
|
| 49 |
+
"rewards/margins": -0.00011417151836212724,
|
| 50 |
+
"rewards/rejected": -0.00010640917753335088,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.31989020109176636,
|
| 57 |
+
"logits/rejected": 0.3349720537662506,
|
| 58 |
+
"logps/chosen": -293.8145751953125,
|
| 59 |
+
"logps/rejected": -287.182373046875,
|
| 60 |
+
"loss": 0.2235,
|
| 61 |
+
"rewards/accuracies": 0.22499999403953552,
|
| 62 |
+
"rewards/chosen": -0.00011079121759394184,
|
| 63 |
+
"rewards/margins": -4.205655932310037e-05,
|
| 64 |
+
"rewards/rejected": -6.873465463286266e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.2753044068813324,
|
| 71 |
+
"logits/rejected": 0.28743210434913635,
|
| 72 |
+
"logps/chosen": -245.92648315429688,
|
| 73 |
+
"logps/rejected": -302.4917907714844,
|
| 74 |
+
"loss": 0.2106,
|
| 75 |
+
"rewards/accuracies": 0.24375000596046448,
|
| 76 |
+
"rewards/chosen": 4.66261881229002e-05,
|
| 77 |
+
"rewards/margins": 5.961294664302841e-05,
|
| 78 |
+
"rewards/rejected": -1.2986754882149398e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.2745297849178314,
|
| 85 |
+
"logits/rejected": 0.2960417866706848,
|
| 86 |
+
"logps/chosen": -269.48114013671875,
|
| 87 |
+
"logps/rejected": -282.2041015625,
|
| 88 |
+
"loss": 0.2124,
|
| 89 |
+
"rewards/accuracies": 0.28125,
|
| 90 |
+
"rewards/chosen": -0.00018958283180836588,
|
| 91 |
+
"rewards/margins": 0.00012250976578798145,
|
| 92 |
+
"rewards/rejected": -0.0003120926267001778,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.3166781961917877,
|
| 99 |
+
"logits/rejected": 0.28668132424354553,
|
| 100 |
+
"logps/chosen": -276.03466796875,
|
| 101 |
+
"logps/rejected": -298.3278503417969,
|
| 102 |
+
"loss": 0.2073,
|
| 103 |
+
"rewards/accuracies": 0.3125,
|
| 104 |
+
"rewards/chosen": -0.0009398458641953766,
|
| 105 |
+
"rewards/margins": 0.0002089624322252348,
|
| 106 |
+
"rewards/rejected": -0.001148808398284018,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.32457390427589417,
|
| 113 |
+
"logits/rejected": 0.3343047499656677,
|
| 114 |
+
"logps/chosen": -228.984130859375,
|
| 115 |
+
"logps/rejected": -267.0279235839844,
|
| 116 |
+
"loss": 0.2098,
|
| 117 |
+
"rewards/accuracies": 0.26875001192092896,
|
| 118 |
+
"rewards/chosen": -0.0025071091949939728,
|
| 119 |
+
"rewards/margins": 0.00024417496751993895,
|
| 120 |
+
"rewards/rejected": -0.0027512842789292336,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.3037349581718445,
|
| 127 |
+
"logits/rejected": 0.288893461227417,
|
| 128 |
+
"logps/chosen": -264.49493408203125,
|
| 129 |
+
"logps/rejected": -277.01397705078125,
|
| 130 |
+
"loss": 0.2049,
|
| 131 |
+
"rewards/accuracies": 0.26875001192092896,
|
| 132 |
+
"rewards/chosen": -0.0028123059310019016,
|
| 133 |
+
"rewards/margins": 3.8383899664040655e-05,
|
| 134 |
+
"rewards/rejected": -0.0028506899252533913,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.27338820695877075,
|
| 141 |
+
"logits/rejected": 0.2850671410560608,
|
| 142 |
+
"logps/chosen": -274.2656555175781,
|
| 143 |
+
"logps/rejected": -273.5088806152344,
|
| 144 |
+
"loss": 0.2097,
|
| 145 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 146 |
+
"rewards/chosen": -0.004053288139402866,
|
| 147 |
+
"rewards/margins": 0.00020987665629945695,
|
| 148 |
+
"rewards/rejected": -0.004263165406882763,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.2746526896953583,
|
| 155 |
+
"logits/rejected": 0.3108225464820862,
|
| 156 |
+
"logps/chosen": -305.6490478515625,
|
| 157 |
+
"logps/rejected": -320.5104675292969,
|
| 158 |
+
"loss": 0.2048,
|
| 159 |
+
"rewards/accuracies": 0.2874999940395355,
|
| 160 |
+
"rewards/chosen": -0.004907802678644657,
|
| 161 |
+
"rewards/margins": 0.00013219797983765602,
|
| 162 |
+
"rewards/rejected": -0.005040000192821026,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.25255969166755676,
|
| 169 |
+
"logits/rejected": 0.23279385268688202,
|
| 170 |
+
"logps/chosen": -310.1192932128906,
|
| 171 |
+
"logps/rejected": -333.32049560546875,
|
| 172 |
+
"loss": 0.21,
|
| 173 |
+
"rewards/accuracies": 0.34375,
|
| 174 |
+
"rewards/chosen": -0.00747376773506403,
|
| 175 |
+
"rewards/margins": 0.0008040575194172561,
|
| 176 |
+
"rewards/rejected": -0.008277825079858303,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.22498245537281036,
|
| 183 |
+
"logits/rejected": 0.2073470801115036,
|
| 184 |
+
"logps/chosen": -278.15087890625,
|
| 185 |
+
"logps/rejected": -290.3549499511719,
|
| 186 |
+
"loss": 0.2104,
|
| 187 |
+
"rewards/accuracies": 0.2562499940395355,
|
| 188 |
+
"rewards/chosen": -0.013078084215521812,
|
| 189 |
+
"rewards/margins": 0.0007778271683491766,
|
| 190 |
+
"rewards/rejected": -0.013855909928679466,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.20476844906806946,
|
| 197 |
+
"logits/rejected": 0.2006731778383255,
|
| 198 |
+
"logps/chosen": -339.86907958984375,
|
| 199 |
+
"logps/rejected": -366.39935302734375,
|
| 200 |
+
"loss": 0.2098,
|
| 201 |
+
"rewards/accuracies": 0.33125001192092896,
|
| 202 |
+
"rewards/chosen": -0.029517754912376404,
|
| 203 |
+
"rewards/margins": 0.0024804342538118362,
|
| 204 |
+
"rewards/rejected": -0.03199819102883339,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.16123342514038086,
|
| 211 |
+
"logits/rejected": 0.1650470793247223,
|
| 212 |
+
"logps/chosen": -336.85479736328125,
|
| 213 |
+
"logps/rejected": -380.90106201171875,
|
| 214 |
+
"loss": 0.2096,
|
| 215 |
+
"rewards/accuracies": 0.34375,
|
| 216 |
+
"rewards/chosen": -0.046556852757930756,
|
| 217 |
+
"rewards/margins": 0.00344092957675457,
|
| 218 |
+
"rewards/rejected": -0.049997784197330475,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.127132385969162,
|
| 225 |
+
"logits/rejected": 0.11233675479888916,
|
| 226 |
+
"logps/chosen": -363.3497009277344,
|
| 227 |
+
"logps/rejected": -395.849609375,
|
| 228 |
+
"loss": 0.2161,
|
| 229 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 230 |
+
"rewards/chosen": -0.06019137054681778,
|
| 231 |
+
"rewards/margins": 0.002497343812137842,
|
| 232 |
+
"rewards/rejected": -0.06268872320652008,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.05813015252351761,
|
| 239 |
+
"logits/rejected": 0.10442493855953217,
|
| 240 |
+
"logps/chosen": -364.0877990722656,
|
| 241 |
+
"logps/rejected": -407.98272705078125,
|
| 242 |
+
"loss": 0.2065,
|
| 243 |
+
"rewards/accuracies": 0.33125001192092896,
|
| 244 |
+
"rewards/chosen": -0.052812881767749786,
|
| 245 |
+
"rewards/margins": 0.005263908766210079,
|
| 246 |
+
"rewards/rejected": -0.05807679891586304,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": -0.020289132371544838,
|
| 253 |
+
"logits/rejected": 0.03128629922866821,
|
| 254 |
+
"logps/chosen": -377.3454895019531,
|
| 255 |
+
"logps/rejected": -375.7449951171875,
|
| 256 |
+
"loss": 0.2054,
|
| 257 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 258 |
+
"rewards/chosen": -0.061011601239442825,
|
| 259 |
+
"rewards/margins": 0.0011604861356317997,
|
| 260 |
+
"rewards/rejected": -0.06217208504676819,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.07980453968048096,
|
| 267 |
+
"logits/rejected": 0.026858001947402954,
|
| 268 |
+
"logps/chosen": -365.4123229980469,
|
| 269 |
+
"logps/rejected": -389.89556884765625,
|
| 270 |
+
"loss": 0.212,
|
| 271 |
+
"rewards/accuracies": 0.3125,
|
| 272 |
+
"rewards/chosen": -0.05129029601812363,
|
| 273 |
+
"rewards/margins": 0.0013983547687530518,
|
| 274 |
+
"rewards/rejected": -0.05268865078687668,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.06391559541225433,
|
| 281 |
+
"logits/rejected": 0.08089544624090195,
|
| 282 |
+
"logps/chosen": -294.32977294921875,
|
| 283 |
+
"logps/rejected": -301.67242431640625,
|
| 284 |
+
"loss": 0.2034,
|
| 285 |
+
"rewards/accuracies": 0.2874999940395355,
|
| 286 |
+
"rewards/chosen": -0.028584271669387817,
|
| 287 |
+
"rewards/margins": 0.0021569356322288513,
|
| 288 |
+
"rewards/rejected": -0.03074120543897152,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": -0.007983528077602386,
|
| 295 |
+
"logits/rejected": -0.02395419403910637,
|
| 296 |
+
"logps/chosen": -364.5057373046875,
|
| 297 |
+
"logps/rejected": -398.78265380859375,
|
| 298 |
+
"loss": 0.2026,
|
| 299 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 300 |
+
"rewards/chosen": -0.03608248755335808,
|
| 301 |
+
"rewards/margins": 0.007917111739516258,
|
| 302 |
+
"rewards/rejected": -0.043999604880809784,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.052110157907009125,
|
| 309 |
+
"logits/rejected": 0.04244590550661087,
|
| 310 |
+
"logps/chosen": -333.72998046875,
|
| 311 |
+
"logps/rejected": -362.7451171875,
|
| 312 |
+
"loss": 0.212,
|
| 313 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 314 |
+
"rewards/chosen": -0.05566523224115372,
|
| 315 |
+
"rewards/margins": 0.008566088043153286,
|
| 316 |
+
"rewards/rejected": -0.06423132121562958,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.014940446242690086,
|
| 323 |
+
"logits/rejected": -0.00022823139443062246,
|
| 324 |
+
"logps/chosen": -349.548095703125,
|
| 325 |
+
"logps/rejected": -389.1466369628906,
|
| 326 |
+
"loss": 0.2003,
|
| 327 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 328 |
+
"rewards/chosen": -0.06377661973237991,
|
| 329 |
+
"rewards/margins": 0.007529625203460455,
|
| 330 |
+
"rewards/rejected": -0.0713062435388565,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": -0.05766149237751961,
|
| 337 |
+
"logits/rejected": -0.04082841798663139,
|
| 338 |
+
"logps/chosen": -325.00189208984375,
|
| 339 |
+
"logps/rejected": -329.35302734375,
|
| 340 |
+
"loss": 0.2027,
|
| 341 |
+
"rewards/accuracies": 0.23125000298023224,
|
| 342 |
+
"rewards/chosen": -0.04092506319284439,
|
| 343 |
+
"rewards/margins": -0.0009445661562494934,
|
| 344 |
+
"rewards/rejected": -0.03998050093650818,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.05024053901433945,
|
| 351 |
+
"logits/rejected": 0.0004725128528662026,
|
| 352 |
+
"logps/chosen": -322.26275634765625,
|
| 353 |
+
"logps/rejected": -347.1831970214844,
|
| 354 |
+
"loss": 0.207,
|
| 355 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 356 |
+
"rewards/chosen": -0.019810866564512253,
|
| 357 |
+
"rewards/margins": 0.003949201200157404,
|
| 358 |
+
"rewards/rejected": -0.02376006543636322,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": -0.025025557726621628,
|
| 365 |
+
"logits/rejected": -0.011019307188689709,
|
| 366 |
+
"logps/chosen": -288.26739501953125,
|
| 367 |
+
"logps/rejected": -308.3834533691406,
|
| 368 |
+
"loss": 0.1995,
|
| 369 |
+
"rewards/accuracies": 0.32499998807907104,
|
| 370 |
+
"rewards/chosen": -0.008453729562461376,
|
| 371 |
+
"rewards/margins": 0.004683175124228001,
|
| 372 |
+
"rewards/rejected": -0.013136905618011951,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.044585295021533966,
|
| 379 |
+
"logits/rejected": -0.011349612846970558,
|
| 380 |
+
"logps/chosen": -275.3843078613281,
|
| 381 |
+
"logps/rejected": -290.2745666503906,
|
| 382 |
+
"loss": 0.2048,
|
| 383 |
+
"rewards/accuracies": 0.3125,
|
| 384 |
+
"rewards/chosen": -0.005228747613728046,
|
| 385 |
+
"rewards/margins": 0.004847136326134205,
|
| 386 |
+
"rewards/rejected": -0.010075883939862251,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": -0.010054832324385643,
|
| 393 |
+
"logits/rejected": 0.022083023563027382,
|
| 394 |
+
"logps/chosen": -286.2877502441406,
|
| 395 |
+
"logps/rejected": -314.843017578125,
|
| 396 |
+
"loss": 0.2042,
|
| 397 |
+
"rewards/accuracies": 0.28125,
|
| 398 |
+
"rewards/chosen": -0.009463262744247913,
|
| 399 |
+
"rewards/margins": 0.0016764893662184477,
|
| 400 |
+
"rewards/rejected": -0.011139752343297005,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.06939663738012314,
|
| 407 |
+
"logits/rejected": -0.06833665817975998,
|
| 408 |
+
"logps/chosen": -292.0230407714844,
|
| 409 |
+
"logps/rejected": -319.52374267578125,
|
| 410 |
+
"loss": 0.2046,
|
| 411 |
+
"rewards/accuracies": 0.2874999940395355,
|
| 412 |
+
"rewards/chosen": -0.01107553206384182,
|
| 413 |
+
"rewards/margins": 0.002820921130478382,
|
| 414 |
+
"rewards/rejected": -0.013896455056965351,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.09846196323633194,
|
| 421 |
+
"logits/rejected": -0.05906381085515022,
|
| 422 |
+
"logps/chosen": -302.30340576171875,
|
| 423 |
+
"logps/rejected": -341.5763244628906,
|
| 424 |
+
"loss": 0.2079,
|
| 425 |
+
"rewards/accuracies": 0.34375,
|
| 426 |
+
"rewards/chosen": -0.01659044623374939,
|
| 427 |
+
"rewards/margins": 0.010817909613251686,
|
| 428 |
+
"rewards/rejected": -0.027408352121710777,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": -0.15265251696109772,
|
| 435 |
+
"logits/rejected": -0.09610708057880402,
|
| 436 |
+
"logps/chosen": -327.8166198730469,
|
| 437 |
+
"logps/rejected": -369.8201904296875,
|
| 438 |
+
"loss": 0.209,
|
| 439 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 440 |
+
"rewards/chosen": -0.02352728322148323,
|
| 441 |
+
"rewards/margins": 0.007946287281811237,
|
| 442 |
+
"rewards/rejected": -0.03147356957197189,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.1901048719882965,
|
| 449 |
+
"logits/rejected": -0.16242368519306183,
|
| 450 |
+
"logps/chosen": -332.37945556640625,
|
| 451 |
+
"logps/rejected": -352.0182800292969,
|
| 452 |
+
"loss": 0.2023,
|
| 453 |
+
"rewards/accuracies": 0.3125,
|
| 454 |
+
"rewards/chosen": -0.03192076459527016,
|
| 455 |
+
"rewards/margins": 0.005780586041510105,
|
| 456 |
+
"rewards/rejected": -0.03770134598016739,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.14182882010936737,
|
| 463 |
+
"logits/rejected": -0.18550843000411987,
|
| 464 |
+
"logps/chosen": -321.2982177734375,
|
| 465 |
+
"logps/rejected": -333.14837646484375,
|
| 466 |
+
"loss": 0.2061,
|
| 467 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 468 |
+
"rewards/chosen": -0.020713280886411667,
|
| 469 |
+
"rewards/margins": 0.004291003569960594,
|
| 470 |
+
"rewards/rejected": -0.025004282593727112,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.2318871021270752,
|
| 477 |
+
"logits/rejected": -0.12970159947872162,
|
| 478 |
+
"logps/chosen": -304.32928466796875,
|
| 479 |
+
"logps/rejected": -300.49517822265625,
|
| 480 |
+
"loss": 0.2098,
|
| 481 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 482 |
+
"rewards/chosen": -0.016532720997929573,
|
| 483 |
+
"rewards/margins": 0.005365257151424885,
|
| 484 |
+
"rewards/rejected": -0.021897977218031883,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": -0.10503053665161133,
|
| 491 |
+
"logits/rejected": -0.14621496200561523,
|
| 492 |
+
"logps/chosen": -288.16839599609375,
|
| 493 |
+
"logps/rejected": -330.89935302734375,
|
| 494 |
+
"loss": 0.2076,
|
| 495 |
+
"rewards/accuracies": 0.34375,
|
| 496 |
+
"rewards/chosen": -0.011596577242016792,
|
| 497 |
+
"rewards/margins": 0.006266799755394459,
|
| 498 |
+
"rewards/rejected": -0.017863376066088676,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": -0.16021689772605896,
|
| 505 |
+
"logits/rejected": -0.14831289649009705,
|
| 506 |
+
"logps/chosen": -317.23468017578125,
|
| 507 |
+
"logps/rejected": -378.10650634765625,
|
| 508 |
+
"loss": 0.199,
|
| 509 |
+
"rewards/accuracies": 0.375,
|
| 510 |
+
"rewards/chosen": -0.0146575216203928,
|
| 511 |
+
"rewards/margins": 0.006193594075739384,
|
| 512 |
+
"rewards/rejected": -0.020851116627454758,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.21353450417518616,
|
| 519 |
+
"logits/rejected": -0.2229534387588501,
|
| 520 |
+
"logps/chosen": -297.26434326171875,
|
| 521 |
+
"logps/rejected": -286.7055358886719,
|
| 522 |
+
"loss": 0.2086,
|
| 523 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 524 |
+
"rewards/chosen": -0.013432545587420464,
|
| 525 |
+
"rewards/margins": 0.001908454461954534,
|
| 526 |
+
"rewards/rejected": -0.015341001562774181,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.23490211367607117,
|
| 533 |
+
"logits/rejected": -0.19254347681999207,
|
| 534 |
+
"logps/chosen": -299.3580627441406,
|
| 535 |
+
"logps/rejected": -300.2660827636719,
|
| 536 |
+
"loss": 0.2118,
|
| 537 |
+
"rewards/accuracies": 0.3125,
|
| 538 |
+
"rewards/chosen": -0.01381734199821949,
|
| 539 |
+
"rewards/margins": 0.004050114192068577,
|
| 540 |
+
"rewards/rejected": -0.017867455258965492,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.20214135944843292,
|
| 547 |
+
"logits/rejected": -0.26244884729385376,
|
| 548 |
+
"logps/chosen": -289.81390380859375,
|
| 549 |
+
"logps/rejected": -331.31158447265625,
|
| 550 |
+
"loss": 0.2078,
|
| 551 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 552 |
+
"rewards/chosen": -0.009037318639457226,
|
| 553 |
+
"rewards/margins": 0.0066641224548220634,
|
| 554 |
+
"rewards/rejected": -0.01570144109427929,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.2581767439842224,
|
| 561 |
+
"logits/rejected": -0.26762059330940247,
|
| 562 |
+
"logps/chosen": -286.0437316894531,
|
| 563 |
+
"logps/rejected": -320.72772216796875,
|
| 564 |
+
"loss": 0.2007,
|
| 565 |
+
"rewards/accuracies": 0.34375,
|
| 566 |
+
"rewards/chosen": -0.012503271922469139,
|
| 567 |
+
"rewards/margins": 0.00960660632699728,
|
| 568 |
+
"rewards/rejected": -0.022109879180788994,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": -0.3141801357269287,
|
| 575 |
+
"logits/rejected": -0.3110749125480652,
|
| 576 |
+
"logps/chosen": -358.1673278808594,
|
| 577 |
+
"logps/rejected": -395.6116943359375,
|
| 578 |
+
"loss": 0.2151,
|
| 579 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 580 |
+
"rewards/chosen": -0.02111610770225525,
|
| 581 |
+
"rewards/margins": 0.008691903203725815,
|
| 582 |
+
"rewards/rejected": -0.029808010905981064,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.3446267545223236,
|
| 589 |
+
"logits/rejected": -0.33043938875198364,
|
| 590 |
+
"logps/chosen": -289.3715515136719,
|
| 591 |
+
"logps/rejected": -327.91790771484375,
|
| 592 |
+
"loss": 0.2074,
|
| 593 |
+
"rewards/accuracies": 0.3187499940395355,
|
| 594 |
+
"rewards/chosen": -0.015166997909545898,
|
| 595 |
+
"rewards/margins": 0.009188723750412464,
|
| 596 |
+
"rewards/rejected": -0.024355720728635788,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.36505457758903503,
|
| 603 |
+
"logits/rejected": -0.29573512077331543,
|
| 604 |
+
"logps/chosen": -290.6937255859375,
|
| 605 |
+
"logps/rejected": -299.7286071777344,
|
| 606 |
+
"loss": 0.209,
|
| 607 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 608 |
+
"rewards/chosen": -0.02466105856001377,
|
| 609 |
+
"rewards/margins": 0.00368274818174541,
|
| 610 |
+
"rewards/rejected": -0.02834380604326725,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.37998563051223755,
|
| 617 |
+
"logits/rejected": -0.3379359841346741,
|
| 618 |
+
"logps/chosen": -385.1395568847656,
|
| 619 |
+
"logps/rejected": -406.07147216796875,
|
| 620 |
+
"loss": 0.2147,
|
| 621 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 622 |
+
"rewards/chosen": -0.032053716480731964,
|
| 623 |
+
"rewards/margins": 0.007807403802871704,
|
| 624 |
+
"rewards/rejected": -0.03986112028360367,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.36350712180137634,
|
| 631 |
+
"logits/rejected": -0.35324662923812866,
|
| 632 |
+
"logps/chosen": -289.75543212890625,
|
| 633 |
+
"logps/rejected": -322.47930908203125,
|
| 634 |
+
"loss": 0.1993,
|
| 635 |
+
"rewards/accuracies": 0.3125,
|
| 636 |
+
"rewards/chosen": -0.0282241590321064,
|
| 637 |
+
"rewards/margins": 0.012596110813319683,
|
| 638 |
+
"rewards/rejected": -0.04082026332616806,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": -0.3876686990261078,
|
| 645 |
+
"logits/rejected": -0.3610993027687073,
|
| 646 |
+
"logps/chosen": -339.6667175292969,
|
| 647 |
+
"logps/rejected": -349.5023193359375,
|
| 648 |
+
"loss": 0.2046,
|
| 649 |
+
"rewards/accuracies": 0.2874999940395355,
|
| 650 |
+
"rewards/chosen": -0.035824716091156006,
|
| 651 |
+
"rewards/margins": 0.0051012164913117886,
|
| 652 |
+
"rewards/rejected": -0.04092593118548393,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": -0.42761000990867615,
|
| 659 |
+
"logits/rejected": -0.4186409115791321,
|
| 660 |
+
"logps/chosen": -332.4256896972656,
|
| 661 |
+
"logps/rejected": -350.052490234375,
|
| 662 |
+
"loss": 0.2216,
|
| 663 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 664 |
+
"rewards/chosen": -0.03896978124976158,
|
| 665 |
+
"rewards/margins": 0.004214274697005749,
|
| 666 |
+
"rewards/rejected": -0.0431840606033802,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.36252036690711975,
|
| 673 |
+
"logits/rejected": -0.36035069823265076,
|
| 674 |
+
"logps/chosen": -379.29962158203125,
|
| 675 |
+
"logps/rejected": -386.194091796875,
|
| 676 |
+
"loss": 0.2114,
|
| 677 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 678 |
+
"rewards/chosen": -0.03572685644030571,
|
| 679 |
+
"rewards/margins": 0.0034367397893220186,
|
| 680 |
+
"rewards/rejected": -0.03916360065340996,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.3759670555591583,
|
| 687 |
+
"logits/rejected": -0.35854417085647583,
|
| 688 |
+
"logps/chosen": -289.8544006347656,
|
| 689 |
+
"logps/rejected": -321.8282775878906,
|
| 690 |
+
"loss": 0.2106,
|
| 691 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 692 |
+
"rewards/chosen": -0.02995840646326542,
|
| 693 |
+
"rewards/margins": 0.007169515825808048,
|
| 694 |
+
"rewards/rejected": -0.03712791949510574,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.3935397267341614,
|
| 701 |
+
"logits/rejected": -0.41043296456336975,
|
| 702 |
+
"logps/chosen": -355.903076171875,
|
| 703 |
+
"logps/rejected": -344.1985778808594,
|
| 704 |
+
"loss": 0.2127,
|
| 705 |
+
"rewards/accuracies": 0.28125,
|
| 706 |
+
"rewards/chosen": -0.0340442880988121,
|
| 707 |
+
"rewards/margins": -0.001989628653973341,
|
| 708 |
+
"rewards/rejected": -0.032054655253887177,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.30559736490249634,
|
| 715 |
+
"logits/rejected": -0.33492517471313477,
|
| 716 |
+
"logps/chosen": -292.39227294921875,
|
| 717 |
+
"logps/rejected": -308.4276123046875,
|
| 718 |
+
"loss": 0.2084,
|
| 719 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 720 |
+
"rewards/chosen": -0.028410837054252625,
|
| 721 |
+
"rewards/margins": 0.004543141461908817,
|
| 722 |
+
"rewards/rejected": -0.03295397758483887,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.35250839591026306,
|
| 729 |
+
"logits/rejected": -0.34054213762283325,
|
| 730 |
+
"logps/chosen": -332.04315185546875,
|
| 731 |
+
"logps/rejected": -336.251220703125,
|
| 732 |
+
"loss": 0.2055,
|
| 733 |
+
"rewards/accuracies": 0.28125,
|
| 734 |
+
"rewards/chosen": -0.024514295160770416,
|
| 735 |
+
"rewards/margins": 0.002826205687597394,
|
| 736 |
+
"rewards/rejected": -0.02734050154685974,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.38282984495162964,
|
| 743 |
+
"logits/rejected": -0.30817848443984985,
|
| 744 |
+
"logps/chosen": -332.67364501953125,
|
| 745 |
+
"logps/rejected": -353.9303894042969,
|
| 746 |
+
"loss": 0.2045,
|
| 747 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 748 |
+
"rewards/chosen": -0.02591048739850521,
|
| 749 |
+
"rewards/margins": 0.006938849575817585,
|
| 750 |
+
"rewards/rejected": -0.03284933418035507,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.40525302290916443,
|
| 757 |
+
"logits/rejected": -0.36453166604042053,
|
| 758 |
+
"logps/chosen": -304.2394714355469,
|
| 759 |
+
"logps/rejected": -326.7181701660156,
|
| 760 |
+
"loss": 0.203,
|
| 761 |
+
"rewards/accuracies": 0.3125,
|
| 762 |
+
"rewards/chosen": -0.0233243890106678,
|
| 763 |
+
"rewards/margins": 0.00685765128582716,
|
| 764 |
+
"rewards/rejected": -0.030182043090462685,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.3453354239463806,
|
| 771 |
+
"logits/rejected": -0.4035136103630066,
|
| 772 |
+
"logps/chosen": -356.69140625,
|
| 773 |
+
"logps/rejected": -386.82281494140625,
|
| 774 |
+
"loss": 0.2075,
|
| 775 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 776 |
+
"rewards/chosen": -0.025404874235391617,
|
| 777 |
+
"rewards/margins": 0.011574333533644676,
|
| 778 |
+
"rewards/rejected": -0.036979205906391144,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.37287113070487976,
|
| 785 |
+
"logits/rejected": -0.38295817375183105,
|
| 786 |
+
"logps/chosen": -306.1138610839844,
|
| 787 |
+
"logps/rejected": -333.82958984375,
|
| 788 |
+
"loss": 0.2105,
|
| 789 |
+
"rewards/accuracies": 0.3125,
|
| 790 |
+
"rewards/chosen": -0.028054391965270042,
|
| 791 |
+
"rewards/margins": 0.006188055966049433,
|
| 792 |
+
"rewards/rejected": -0.034242451190948486,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": -0.36476778984069824,
|
| 799 |
+
"logits/rejected": -0.34431588649749756,
|
| 800 |
+
"logps/chosen": -295.88592529296875,
|
| 801 |
+
"logps/rejected": -300.2727355957031,
|
| 802 |
+
"loss": 0.2048,
|
| 803 |
+
"rewards/accuracies": 0.23125000298023224,
|
| 804 |
+
"rewards/chosen": -0.03209972754120827,
|
| 805 |
+
"rewards/margins": -0.0022686964366585016,
|
| 806 |
+
"rewards/rejected": -0.02983103133738041,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.3742281496524811,
|
| 813 |
+
"logits/rejected": -0.37335073947906494,
|
| 814 |
+
"logps/chosen": -328.6231994628906,
|
| 815 |
+
"logps/rejected": -348.46990966796875,
|
| 816 |
+
"loss": 0.2049,
|
| 817 |
+
"rewards/accuracies": 0.3187499940395355,
|
| 818 |
+
"rewards/chosen": -0.028273243457078934,
|
| 819 |
+
"rewards/margins": 0.00650573056191206,
|
| 820 |
+
"rewards/rejected": -0.03477897495031357,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.36765938997268677,
|
| 827 |
+
"logits/rejected": -0.36060625314712524,
|
| 828 |
+
"logps/chosen": -323.7262268066406,
|
| 829 |
+
"logps/rejected": -357.27813720703125,
|
| 830 |
+
"loss": 0.2111,
|
| 831 |
+
"rewards/accuracies": 0.3125,
|
| 832 |
+
"rewards/chosen": -0.036755647510290146,
|
| 833 |
+
"rewards/margins": 0.00827108509838581,
|
| 834 |
+
"rewards/rejected": -0.04502673074603081,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": -0.3832349181175232,
|
| 841 |
+
"logits/rejected": -0.40613269805908203,
|
| 842 |
+
"logps/chosen": -313.4564208984375,
|
| 843 |
+
"logps/rejected": -355.4290771484375,
|
| 844 |
+
"loss": 0.2075,
|
| 845 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 846 |
+
"rewards/chosen": -0.03660092502832413,
|
| 847 |
+
"rewards/margins": 0.008231913670897484,
|
| 848 |
+
"rewards/rejected": -0.04483283683657646,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.3985538184642792,
|
| 855 |
+
"logits/rejected": -0.44028186798095703,
|
| 856 |
+
"logps/chosen": -342.6407470703125,
|
| 857 |
+
"logps/rejected": -393.0326843261719,
|
| 858 |
+
"loss": 0.2026,
|
| 859 |
+
"rewards/accuracies": 0.36250001192092896,
|
| 860 |
+
"rewards/chosen": -0.03912167251110077,
|
| 861 |
+
"rewards/margins": 0.012444810010492802,
|
| 862 |
+
"rewards/rejected": -0.051566481590270996,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.3522663712501526,
|
| 869 |
+
"logits/rejected": -0.3656110167503357,
|
| 870 |
+
"logps/chosen": -300.55059814453125,
|
| 871 |
+
"logps/rejected": -309.12005615234375,
|
| 872 |
+
"loss": 0.1985,
|
| 873 |
+
"rewards/accuracies": 0.25,
|
| 874 |
+
"rewards/chosen": -0.043480511754751205,
|
| 875 |
+
"rewards/margins": 0.0020387214608490467,
|
| 876 |
+
"rewards/rejected": -0.045519232749938965,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.3727906346321106,
|
| 883 |
+
"logits/rejected": -0.42088228464126587,
|
| 884 |
+
"logps/chosen": -303.08184814453125,
|
| 885 |
+
"logps/rejected": -355.48114013671875,
|
| 886 |
+
"loss": 0.2027,
|
| 887 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 888 |
+
"rewards/chosen": -0.041418589651584625,
|
| 889 |
+
"rewards/margins": 0.010809944942593575,
|
| 890 |
+
"rewards/rejected": -0.05222853273153305,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.4294905662536621,
|
| 897 |
+
"logits/rejected": -0.35463112592697144,
|
| 898 |
+
"logps/chosen": -374.58221435546875,
|
| 899 |
+
"logps/rejected": -413.10626220703125,
|
| 900 |
+
"loss": 0.1983,
|
| 901 |
+
"rewards/accuracies": 0.3812499940395355,
|
| 902 |
+
"rewards/chosen": -0.04309406504034996,
|
| 903 |
+
"rewards/margins": 0.013471859507262707,
|
| 904 |
+
"rewards/rejected": -0.05656592175364494,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.38254573941230774,
|
| 911 |
+
"logits/rejected": -0.3926312029361725,
|
| 912 |
+
"logps/chosen": -307.92071533203125,
|
| 913 |
+
"logps/rejected": -331.7400817871094,
|
| 914 |
+
"loss": 0.1995,
|
| 915 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 916 |
+
"rewards/chosen": -0.03662495315074921,
|
| 917 |
+
"rewards/margins": 0.004892958328127861,
|
| 918 |
+
"rewards/rejected": -0.04151790589094162,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.41799673438072205,
|
| 925 |
+
"logits/rejected": -0.423776239156723,
|
| 926 |
+
"logps/chosen": -352.4769592285156,
|
| 927 |
+
"logps/rejected": -392.0356750488281,
|
| 928 |
+
"loss": 0.2013,
|
| 929 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 930 |
+
"rewards/chosen": -0.039123691618442535,
|
| 931 |
+
"rewards/margins": 0.012257387861609459,
|
| 932 |
+
"rewards/rejected": -0.05138107389211655,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.4221061170101166,
|
| 939 |
+
"logits/rejected": -0.3426254093647003,
|
| 940 |
+
"logps/chosen": -371.6142883300781,
|
| 941 |
+
"logps/rejected": -368.6783752441406,
|
| 942 |
+
"loss": 0.2131,
|
| 943 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 944 |
+
"rewards/chosen": -0.03723513334989548,
|
| 945 |
+
"rewards/margins": 0.001372279948554933,
|
| 946 |
+
"rewards/rejected": -0.038607411086559296,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.43726977705955505,
|
| 953 |
+
"logits/rejected": -0.433055579662323,
|
| 954 |
+
"logps/chosen": -349.0133056640625,
|
| 955 |
+
"logps/rejected": -424.606689453125,
|
| 956 |
+
"loss": 0.197,
|
| 957 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 958 |
+
"rewards/chosen": -0.02950415015220642,
|
| 959 |
+
"rewards/margins": 0.016581665724515915,
|
| 960 |
+
"rewards/rejected": -0.04608581215143204,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": -0.41025829315185547,
|
| 967 |
+
"logits/rejected": -0.39352136850357056,
|
| 968 |
+
"logps/chosen": -351.42724609375,
|
| 969 |
+
"logps/rejected": -362.4097900390625,
|
| 970 |
+
"loss": 0.2084,
|
| 971 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 972 |
+
"rewards/chosen": -0.04146607965230942,
|
| 973 |
+
"rewards/margins": 0.003974739462137222,
|
| 974 |
+
"rewards/rejected": -0.04544081538915634,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.3846993148326874,
|
| 981 |
+
"logits/rejected": -0.36020296812057495,
|
| 982 |
+
"logps/chosen": -345.7566833496094,
|
| 983 |
+
"logps/rejected": -369.3031311035156,
|
| 984 |
+
"loss": 0.2145,
|
| 985 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 986 |
+
"rewards/chosen": -0.0327707901597023,
|
| 987 |
+
"rewards/margins": 0.007174340076744556,
|
| 988 |
+
"rewards/rejected": -0.03994513303041458,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.4323287010192871,
|
| 995 |
+
"logits/rejected": -0.46247753500938416,
|
| 996 |
+
"logps/chosen": -310.33221435546875,
|
| 997 |
+
"logps/rejected": -337.3047790527344,
|
| 998 |
+
"loss": 0.196,
|
| 999 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 1000 |
+
"rewards/chosen": -0.02941690944135189,
|
| 1001 |
+
"rewards/margins": 0.008200698532164097,
|
| 1002 |
+
"rewards/rejected": -0.03761760890483856,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.44240742921829224,
|
| 1009 |
+
"logits/rejected": -0.4352414011955261,
|
| 1010 |
+
"logps/chosen": -350.82220458984375,
|
| 1011 |
+
"logps/rejected": -371.5367431640625,
|
| 1012 |
+
"loss": 0.2113,
|
| 1013 |
+
"rewards/accuracies": 0.34375,
|
| 1014 |
+
"rewards/chosen": -0.03298790752887726,
|
| 1015 |
+
"rewards/margins": 0.009050843305885792,
|
| 1016 |
+
"rewards/rejected": -0.042038749903440475,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.4660700857639313,
|
| 1023 |
+
"logits/rejected": -0.40507060289382935,
|
| 1024 |
+
"logps/chosen": -363.92041015625,
|
| 1025 |
+
"logps/rejected": -369.3705139160156,
|
| 1026 |
+
"loss": 0.2011,
|
| 1027 |
+
"rewards/accuracies": 0.33125001192092896,
|
| 1028 |
+
"rewards/chosen": -0.03945212811231613,
|
| 1029 |
+
"rewards/margins": 0.004098129458725452,
|
| 1030 |
+
"rewards/rejected": -0.04355026036500931,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.44686412811279297,
|
| 1037 |
+
"logits/rejected": -0.4067825376987457,
|
| 1038 |
+
"logps/chosen": -303.0172424316406,
|
| 1039 |
+
"logps/rejected": -316.5196838378906,
|
| 1040 |
+
"loss": 0.2008,
|
| 1041 |
+
"rewards/accuracies": 0.26875001192092896,
|
| 1042 |
+
"rewards/chosen": -0.028305992484092712,
|
| 1043 |
+
"rewards/margins": 0.0041877999901771545,
|
| 1044 |
+
"rewards/rejected": -0.03249379247426987,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.4332183003425598,
|
| 1051 |
+
"logits/rejected": -0.4446489214897156,
|
| 1052 |
+
"logps/chosen": -340.51263427734375,
|
| 1053 |
+
"logps/rejected": -362.9837341308594,
|
| 1054 |
+
"loss": 0.2079,
|
| 1055 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 1056 |
+
"rewards/chosen": -0.034973934292793274,
|
| 1057 |
+
"rewards/margins": 0.0031310406047850847,
|
| 1058 |
+
"rewards/rejected": -0.03810497373342514,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.3977935314178467,
|
| 1065 |
+
"logits/rejected": -0.36564216017723083,
|
| 1066 |
+
"logps/chosen": -354.89202880859375,
|
| 1067 |
+
"logps/rejected": -352.7674560546875,
|
| 1068 |
+
"loss": 0.2085,
|
| 1069 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 1070 |
+
"rewards/chosen": -0.03232111781835556,
|
| 1071 |
+
"rewards/margins": 0.001277880510315299,
|
| 1072 |
+
"rewards/rejected": -0.033598996698856354,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.4228762090206146,
|
| 1079 |
+
"logits/rejected": -0.4223594665527344,
|
| 1080 |
+
"logps/chosen": -291.3377990722656,
|
| 1081 |
+
"logps/rejected": -305.91143798828125,
|
| 1082 |
+
"loss": 0.2033,
|
| 1083 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 1084 |
+
"rewards/chosen": -0.026238340884447098,
|
| 1085 |
+
"rewards/margins": 0.004590832162648439,
|
| 1086 |
+
"rewards/rejected": -0.03082917258143425,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.37430620193481445,
|
| 1093 |
+
"logits/rejected": -0.37224718928337097,
|
| 1094 |
+
"logps/chosen": -271.09088134765625,
|
| 1095 |
+
"logps/rejected": -290.9538879394531,
|
| 1096 |
+
"loss": 0.2111,
|
| 1097 |
+
"rewards/accuracies": 0.2562499940395355,
|
| 1098 |
+
"rewards/chosen": -0.02569451928138733,
|
| 1099 |
+
"rewards/margins": 0.008396224118769169,
|
| 1100 |
+
"rewards/rejected": -0.03409074246883392,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.44756025075912476,
|
| 1107 |
+
"logits/rejected": -0.3608166575431824,
|
| 1108 |
+
"logps/chosen": -325.45709228515625,
|
| 1109 |
+
"logps/rejected": -369.91351318359375,
|
| 1110 |
+
"loss": 0.1955,
|
| 1111 |
+
"rewards/accuracies": 0.3062500059604645,
|
| 1112 |
+
"rewards/chosen": -0.03604112192988396,
|
| 1113 |
+
"rewards/margins": 0.004559466149657965,
|
| 1114 |
+
"rewards/rejected": -0.04060059040784836,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.3722971975803375,
|
| 1121 |
+
"logits/rejected": -0.34547311067581177,
|
| 1122 |
+
"logps/chosen": -340.4040832519531,
|
| 1123 |
+
"logps/rejected": -355.20404052734375,
|
| 1124 |
+
"loss": 0.2012,
|
| 1125 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 1126 |
+
"rewards/chosen": -0.03479091823101044,
|
| 1127 |
+
"rewards/margins": 0.0040581924840807915,
|
| 1128 |
+
"rewards/rejected": -0.038849107921123505,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.4394063949584961,
|
| 1135 |
+
"logits/rejected": -0.44897159934043884,
|
| 1136 |
+
"logps/chosen": -325.93255615234375,
|
| 1137 |
+
"logps/rejected": -360.37713623046875,
|
| 1138 |
+
"loss": 0.2055,
|
| 1139 |
+
"rewards/accuracies": 0.32499998807907104,
|
| 1140 |
+
"rewards/chosen": -0.034493155777454376,
|
| 1141 |
+
"rewards/margins": 0.005803712643682957,
|
| 1142 |
+
"rewards/rejected": -0.04029686748981476,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.3761179447174072,
|
| 1149 |
+
"logits/rejected": -0.4133715033531189,
|
| 1150 |
+
"logps/chosen": -341.07574462890625,
|
| 1151 |
+
"logps/rejected": -353.9838562011719,
|
| 1152 |
+
"loss": 0.2004,
|
| 1153 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 1154 |
+
"rewards/chosen": -0.037453822791576385,
|
| 1155 |
+
"rewards/margins": 0.0007335458067245781,
|
| 1156 |
+
"rewards/rejected": -0.03818737342953682,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.40443721413612366,
|
| 1163 |
+
"logits/rejected": -0.40503472089767456,
|
| 1164 |
+
"logps/chosen": -257.16357421875,
|
| 1165 |
+
"logps/rejected": -296.4949035644531,
|
| 1166 |
+
"loss": 0.2101,
|
| 1167 |
+
"rewards/accuracies": 0.2874999940395355,
|
| 1168 |
+
"rewards/chosen": -0.025397296994924545,
|
| 1169 |
+
"rewards/margins": 0.011320685967803001,
|
| 1170 |
+
"rewards/rejected": -0.036717988550662994,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.42295295000076294,
|
| 1177 |
+
"logits/rejected": -0.4149630069732666,
|
| 1178 |
+
"logps/chosen": -346.1056823730469,
|
| 1179 |
+
"logps/rejected": -367.1171569824219,
|
| 1180 |
+
"loss": 0.2066,
|
| 1181 |
+
"rewards/accuracies": 0.2750000059604645,
|
| 1182 |
+
"rewards/chosen": -0.03263362497091293,
|
| 1183 |
+
"rewards/margins": 0.007565206382423639,
|
| 1184 |
+
"rewards/rejected": -0.04019883647561073,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.4583490490913391,
|
| 1191 |
+
"logits/rejected": -0.432847797870636,
|
| 1192 |
+
"logps/chosen": -328.78582763671875,
|
| 1193 |
+
"logps/rejected": -337.87445068359375,
|
| 1194 |
+
"loss": 0.2024,
|
| 1195 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 1196 |
+
"rewards/chosen": -0.031004447489976883,
|
| 1197 |
+
"rewards/margins": 0.005912850610911846,
|
| 1198 |
+
"rewards/rejected": -0.03691729158163071,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.4011611044406891,
|
| 1205 |
+
"logits/rejected": -0.4167350232601166,
|
| 1206 |
+
"logps/chosen": -345.6464538574219,
|
| 1207 |
+
"logps/rejected": -370.5746154785156,
|
| 1208 |
+
"loss": 0.205,
|
| 1209 |
+
"rewards/accuracies": 0.35624998807907104,
|
| 1210 |
+
"rewards/chosen": -0.03289477154612541,
|
| 1211 |
+
"rewards/margins": 0.008914651349186897,
|
| 1212 |
+
"rewards/rejected": -0.041809432208538055,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.4343733787536621,
|
| 1219 |
+
"logits/rejected": -0.43256425857543945,
|
| 1220 |
+
"logps/chosen": -310.9982604980469,
|
| 1221 |
+
"logps/rejected": -327.97802734375,
|
| 1222 |
+
"loss": 0.199,
|
| 1223 |
+
"rewards/accuracies": 0.2562499940395355,
|
| 1224 |
+
"rewards/chosen": -0.025628242641687393,
|
| 1225 |
+
"rewards/margins": 0.006485571153461933,
|
| 1226 |
+
"rewards/rejected": -0.03211381286382675,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.4601428508758545,
|
| 1233 |
+
"logits/rejected": -0.4454170763492584,
|
| 1234 |
+
"logps/chosen": -326.32415771484375,
|
| 1235 |
+
"logps/rejected": -367.8747253417969,
|
| 1236 |
+
"loss": 0.21,
|
| 1237 |
+
"rewards/accuracies": 0.3375000059604645,
|
| 1238 |
+
"rewards/chosen": -0.02655145525932312,
|
| 1239 |
+
"rewards/margins": 0.01180974580347538,
|
| 1240 |
+
"rewards/rejected": -0.03836119920015335,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.41596898436546326,
|
| 1247 |
+
"logits/rejected": -0.4292394518852234,
|
| 1248 |
+
"logps/chosen": -312.1533203125,
|
| 1249 |
+
"logps/rejected": -325.45599365234375,
|
| 1250 |
+
"loss": 0.1936,
|
| 1251 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 1252 |
+
"rewards/chosen": -0.03066674806177616,
|
| 1253 |
+
"rewards/margins": 0.004992074333131313,
|
| 1254 |
+
"rewards/rejected": -0.0356588289141655,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.41111326217651367,
|
| 1261 |
+
"logits/rejected": -0.4396681785583496,
|
| 1262 |
+
"logps/chosen": -300.7364807128906,
|
| 1263 |
+
"logps/rejected": -301.65289306640625,
|
| 1264 |
+
"loss": 0.207,
|
| 1265 |
+
"rewards/accuracies": 0.26875001192092896,
|
| 1266 |
+
"rewards/chosen": -0.026606258004903793,
|
| 1267 |
+
"rewards/margins": 0.0029051213059574366,
|
| 1268 |
+
"rewards/rejected": -0.029511380940675735,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.4996066689491272,
|
| 1275 |
+
"logits/rejected": -0.43205633759498596,
|
| 1276 |
+
"logps/chosen": -359.67010498046875,
|
| 1277 |
+
"logps/rejected": -420.83026123046875,
|
| 1278 |
+
"loss": 0.199,
|
| 1279 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 1280 |
+
"rewards/chosen": -0.030006730929017067,
|
| 1281 |
+
"rewards/margins": 0.015778595581650734,
|
| 1282 |
+
"rewards/rejected": -0.0457853302359581,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.42298024892807007,
|
| 1289 |
+
"logits/rejected": -0.40388956665992737,
|
| 1290 |
+
"logps/chosen": -319.5880432128906,
|
| 1291 |
+
"logps/rejected": -326.4891662597656,
|
| 1292 |
+
"loss": 0.201,
|
| 1293 |
+
"rewards/accuracies": 0.29374998807907104,
|
| 1294 |
+
"rewards/chosen": -0.0287660863250494,
|
| 1295 |
+
"rewards/margins": 0.004919327795505524,
|
| 1296 |
+
"rewards/rejected": -0.033685412257909775,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.38126152753829956,
|
| 1303 |
+
"logits/rejected": -0.43538981676101685,
|
| 1304 |
+
"logps/chosen": -315.6664123535156,
|
| 1305 |
+
"logps/rejected": -353.7925720214844,
|
| 1306 |
+
"loss": 0.2054,
|
| 1307 |
+
"rewards/accuracies": 0.3125,
|
| 1308 |
+
"rewards/chosen": -0.028091344982385635,
|
| 1309 |
+
"rewards/margins": 0.011006112210452557,
|
| 1310 |
+
"rewards/rejected": -0.03909745439887047,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": -0.403546005487442,
|
| 1317 |
+
"logits/rejected": -0.42747077345848083,
|
| 1318 |
+
"logps/chosen": -312.3913879394531,
|
| 1319 |
+
"logps/rejected": -342.631103515625,
|
| 1320 |
+
"loss": 0.2149,
|
| 1321 |
+
"rewards/accuracies": 0.30000001192092896,
|
| 1322 |
+
"rewards/chosen": -0.029346201568841934,
|
| 1323 |
+
"rewards/margins": 0.008023385889828205,
|
| 1324 |
+
"rewards/rejected": -0.037369586527347565,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.051660444591444865,
|
| 1332 |
+
"train_runtime": 2852.4153,
|
| 1333 |
+
"train_samples_per_second": 10.517,
|
| 1334 |
+
"train_steps_per_second": 0.328
|
| 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 |
+
}
|