Commit
•
617551b
1
Parent(s):
025aa93
Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May12_03-20-42_gpu4-119-5/events.out.tfevents.1715448183.gpu4-119-5.1641529.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-gpo-newSFT-b0.001-30k-i1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# phi-2-gpo-newSFT-b0.001-30k-i1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.7.1
|
| 57 |
+
- Transformers 4.36.2
|
| 58 |
+
- Pytorch 2.1.2
|
| 59 |
+
- Datasets 2.14.6
|
| 60 |
+
- 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 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3639f19fcaf8c9ea821f590e46b563e7498267023e798d8c46c86e0cf91b482
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2330256977081299,
|
| 4 |
+
"train_runtime": 17175.1012,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.747,
|
| 7 |
+
"train_steps_per_second": 0.109
|
| 8 |
+
}
|
runs/May12_03-20-42_gpu4-119-5/events.out.tfevents.1715448183.gpu4-119-5.1641529.0
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 sha256:2751db31768005e08deae87328f4c4a7f925b87a300f5d2107b0e54197f0d137
|
| 3 |
+
size 124286
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2330256977081299,
|
| 4 |
+
"train_runtime": 17175.1012,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.747,
|
| 7 |
+
"train_steps_per_second": 0.109
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2662 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1875,
|
| 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": 2.6595744680851065e-08,
|
| 14 |
+
"logits/chosen": 0.08248457312583923,
|
| 15 |
+
"logits/rejected": 0.20234191417694092,
|
| 16 |
+
"logps/chosen": -342.9681091308594,
|
| 17 |
+
"logps/rejected": -279.68194580078125,
|
| 18 |
+
"loss": 0.2964,
|
| 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": 2.6595744680851066e-07,
|
| 28 |
+
"logits/chosen": 0.12211620807647705,
|
| 29 |
+
"logits/rejected": 0.22816644608974457,
|
| 30 |
+
"logps/chosen": -387.83782958984375,
|
| 31 |
+
"logps/rejected": -299.0201721191406,
|
| 32 |
+
"loss": 0.334,
|
| 33 |
+
"rewards/accuracies": 0.3958333432674408,
|
| 34 |
+
"rewards/chosen": 2.3156941097113304e-05,
|
| 35 |
+
"rewards/margins": 5.933707143412903e-05,
|
| 36 |
+
"rewards/rejected": -3.618013215600513e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.061443157494068146,
|
| 43 |
+
"logits/rejected": 0.2900610864162445,
|
| 44 |
+
"logps/chosen": -387.94866943359375,
|
| 45 |
+
"logps/rejected": -344.0950927734375,
|
| 46 |
+
"loss": 0.3514,
|
| 47 |
+
"rewards/accuracies": 0.4437499940395355,
|
| 48 |
+
"rewards/chosen": -6.4797219238244e-05,
|
| 49 |
+
"rewards/margins": -0.0001574750494910404,
|
| 50 |
+
"rewards/rejected": 9.267783752875403e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.07704450935125351,
|
| 57 |
+
"logits/rejected": 0.24550946056842804,
|
| 58 |
+
"logps/chosen": -327.02447509765625,
|
| 59 |
+
"logps/rejected": -287.892822265625,
|
| 60 |
+
"loss": 0.3212,
|
| 61 |
+
"rewards/accuracies": 0.39375001192092896,
|
| 62 |
+
"rewards/chosen": -0.00013851793482899666,
|
| 63 |
+
"rewards/margins": -0.00014858768554404378,
|
| 64 |
+
"rewards/rejected": 1.0069748896057718e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.15527553856372833,
|
| 71 |
+
"logits/rejected": 0.2848062217235565,
|
| 72 |
+
"logps/chosen": -380.29180908203125,
|
| 73 |
+
"logps/rejected": -296.22418212890625,
|
| 74 |
+
"loss": 0.3505,
|
| 75 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 76 |
+
"rewards/chosen": 0.00010127278801519424,
|
| 77 |
+
"rewards/margins": 7.252545765368268e-05,
|
| 78 |
+
"rewards/rejected": 2.8747313990606926e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.061357248574495316,
|
| 85 |
+
"logits/rejected": 0.2838377356529236,
|
| 86 |
+
"logps/chosen": -341.8178405761719,
|
| 87 |
+
"logps/rejected": -285.6352233886719,
|
| 88 |
+
"loss": 0.3228,
|
| 89 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 90 |
+
"rewards/chosen": 0.00010316881525795907,
|
| 91 |
+
"rewards/margins": 4.464336234377697e-05,
|
| 92 |
+
"rewards/rejected": 5.852547474205494e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.10541439056396484,
|
| 99 |
+
"logits/rejected": 0.28058919310569763,
|
| 100 |
+
"logps/chosen": -343.18572998046875,
|
| 101 |
+
"logps/rejected": -294.2557373046875,
|
| 102 |
+
"loss": 0.3285,
|
| 103 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 104 |
+
"rewards/chosen": 0.00032235862454399467,
|
| 105 |
+
"rewards/margins": 0.0005498815444298089,
|
| 106 |
+
"rewards/rejected": -0.00022752289078198373,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.08224678784608841,
|
| 113 |
+
"logits/rejected": 0.2537159323692322,
|
| 114 |
+
"logps/chosen": -377.56622314453125,
|
| 115 |
+
"logps/rejected": -302.76885986328125,
|
| 116 |
+
"loss": 0.3673,
|
| 117 |
+
"rewards/accuracies": 0.625,
|
| 118 |
+
"rewards/chosen": 0.0004772460088133812,
|
| 119 |
+
"rewards/margins": 0.0005696729640476406,
|
| 120 |
+
"rewards/rejected": -9.242700616596267e-05,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.08698181807994843,
|
| 127 |
+
"logits/rejected": 0.28228509426116943,
|
| 128 |
+
"logps/chosen": -353.9815979003906,
|
| 129 |
+
"logps/rejected": -302.00439453125,
|
| 130 |
+
"loss": 0.3803,
|
| 131 |
+
"rewards/accuracies": 0.6875,
|
| 132 |
+
"rewards/chosen": 0.0008322820067405701,
|
| 133 |
+
"rewards/margins": 0.0010860636830329895,
|
| 134 |
+
"rewards/rejected": -0.0002537816180847585,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.13658957183361053,
|
| 141 |
+
"logits/rejected": 0.2813904583454132,
|
| 142 |
+
"logps/chosen": -331.66705322265625,
|
| 143 |
+
"logps/rejected": -290.46148681640625,
|
| 144 |
+
"loss": 0.3316,
|
| 145 |
+
"rewards/accuracies": 0.675000011920929,
|
| 146 |
+
"rewards/chosen": 0.0012246040860190988,
|
| 147 |
+
"rewards/margins": 0.0016386559000238776,
|
| 148 |
+
"rewards/rejected": -0.00041405190131627023,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.14109408855438232,
|
| 155 |
+
"logits/rejected": 0.28268519043922424,
|
| 156 |
+
"logps/chosen": -337.4228210449219,
|
| 157 |
+
"logps/rejected": -265.25091552734375,
|
| 158 |
+
"loss": 0.3472,
|
| 159 |
+
"rewards/accuracies": 0.706250011920929,
|
| 160 |
+
"rewards/chosen": 0.0017904158448800445,
|
| 161 |
+
"rewards/margins": 0.0025100118946284056,
|
| 162 |
+
"rewards/rejected": -0.0007195962825790048,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.0813894122838974,
|
| 169 |
+
"logits/rejected": 0.19894129037857056,
|
| 170 |
+
"logps/chosen": -331.2377014160156,
|
| 171 |
+
"logps/rejected": -252.0073699951172,
|
| 172 |
+
"loss": 0.336,
|
| 173 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 174 |
+
"rewards/chosen": 0.002608851296827197,
|
| 175 |
+
"rewards/margins": 0.0032108586747199297,
|
| 176 |
+
"rewards/rejected": -0.0006020068540237844,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.05477667599916458,
|
| 183 |
+
"logits/rejected": 0.2091325968503952,
|
| 184 |
+
"logps/chosen": -345.79229736328125,
|
| 185 |
+
"logps/rejected": -283.46649169921875,
|
| 186 |
+
"loss": 0.3315,
|
| 187 |
+
"rewards/accuracies": 0.699999988079071,
|
| 188 |
+
"rewards/chosen": 0.005583181511610746,
|
| 189 |
+
"rewards/margins": 0.006550823338329792,
|
| 190 |
+
"rewards/rejected": -0.0009676421177573502,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.10417729616165161,
|
| 197 |
+
"logits/rejected": 0.28965848684310913,
|
| 198 |
+
"logps/chosen": -355.0021057128906,
|
| 199 |
+
"logps/rejected": -291.60302734375,
|
| 200 |
+
"loss": 0.3406,
|
| 201 |
+
"rewards/accuracies": 0.71875,
|
| 202 |
+
"rewards/chosen": 0.007259941194206476,
|
| 203 |
+
"rewards/margins": 0.008403105661273003,
|
| 204 |
+
"rewards/rejected": -0.001143165398389101,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.1521492302417755,
|
| 211 |
+
"logits/rejected": 0.25287285447120667,
|
| 212 |
+
"logps/chosen": -362.653564453125,
|
| 213 |
+
"logps/rejected": -299.1832580566406,
|
| 214 |
+
"loss": 0.3305,
|
| 215 |
+
"rewards/accuracies": 0.75,
|
| 216 |
+
"rewards/chosen": 0.00862643402069807,
|
| 217 |
+
"rewards/margins": 0.016447611153125763,
|
| 218 |
+
"rewards/rejected": -0.007821176201105118,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.1634024679660797,
|
| 225 |
+
"logits/rejected": 0.32300662994384766,
|
| 226 |
+
"logps/chosen": -331.88592529296875,
|
| 227 |
+
"logps/rejected": -299.06195068359375,
|
| 228 |
+
"loss": 0.3256,
|
| 229 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 230 |
+
"rewards/chosen": 0.003903627395629883,
|
| 231 |
+
"rewards/margins": 0.019702786579728127,
|
| 232 |
+
"rewards/rejected": -0.015799159184098244,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.17028017342090607,
|
| 239 |
+
"logits/rejected": 0.3108305335044861,
|
| 240 |
+
"logps/chosen": -379.0628662109375,
|
| 241 |
+
"logps/rejected": -322.420166015625,
|
| 242 |
+
"loss": 0.2893,
|
| 243 |
+
"rewards/accuracies": 0.793749988079071,
|
| 244 |
+
"rewards/chosen": -0.008702902123332024,
|
| 245 |
+
"rewards/margins": 0.03689227253198624,
|
| 246 |
+
"rewards/rejected": -0.04559517279267311,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.17017154395580292,
|
| 253 |
+
"logits/rejected": 0.31650176644325256,
|
| 254 |
+
"logps/chosen": -397.65875244140625,
|
| 255 |
+
"logps/rejected": -400.8711242675781,
|
| 256 |
+
"loss": 0.2877,
|
| 257 |
+
"rewards/accuracies": 0.737500011920929,
|
| 258 |
+
"rewards/chosen": -0.037718433886766434,
|
| 259 |
+
"rewards/margins": 0.06432106345891953,
|
| 260 |
+
"rewards/rejected": -0.10203950107097626,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.18481381237506866,
|
| 267 |
+
"logits/rejected": 0.33424076437950134,
|
| 268 |
+
"logps/chosen": -473.28680419921875,
|
| 269 |
+
"logps/rejected": -518.6297607421875,
|
| 270 |
+
"loss": 0.2869,
|
| 271 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 272 |
+
"rewards/chosen": -0.12800003588199615,
|
| 273 |
+
"rewards/margins": 0.0953989028930664,
|
| 274 |
+
"rewards/rejected": -0.22339896857738495,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.227821946144104,
|
| 281 |
+
"logits/rejected": 0.3258199989795685,
|
| 282 |
+
"logps/chosen": -561.3455200195312,
|
| 283 |
+
"logps/rejected": -633.8394165039062,
|
| 284 |
+
"loss": 0.2913,
|
| 285 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 286 |
+
"rewards/chosen": -0.2103206217288971,
|
| 287 |
+
"rewards/margins": 0.13042964041233063,
|
| 288 |
+
"rewards/rejected": -0.3407502770423889,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.2324659377336502,
|
| 295 |
+
"logits/rejected": 0.3176039457321167,
|
| 296 |
+
"logps/chosen": -520.3052368164062,
|
| 297 |
+
"logps/rejected": -595.4998168945312,
|
| 298 |
+
"loss": 0.2482,
|
| 299 |
+
"rewards/accuracies": 0.762499988079071,
|
| 300 |
+
"rewards/chosen": -0.16411438584327698,
|
| 301 |
+
"rewards/margins": 0.14954686164855957,
|
| 302 |
+
"rewards/rejected": -0.31366124749183655,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.27860119938850403,
|
| 309 |
+
"logits/rejected": 0.3871223032474518,
|
| 310 |
+
"logps/chosen": -527.0191650390625,
|
| 311 |
+
"logps/rejected": -620.4132080078125,
|
| 312 |
+
"loss": 0.2693,
|
| 313 |
+
"rewards/accuracies": 0.668749988079071,
|
| 314 |
+
"rewards/chosen": -0.2112080156803131,
|
| 315 |
+
"rewards/margins": 0.1339053362607956,
|
| 316 |
+
"rewards/rejected": -0.3451133370399475,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.2107020914554596,
|
| 323 |
+
"logits/rejected": 0.3118240237236023,
|
| 324 |
+
"logps/chosen": -586.7862548828125,
|
| 325 |
+
"logps/rejected": -676.7178955078125,
|
| 326 |
+
"loss": 0.2707,
|
| 327 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 328 |
+
"rewards/chosen": -0.2537532448768616,
|
| 329 |
+
"rewards/margins": 0.12398215383291245,
|
| 330 |
+
"rewards/rejected": -0.37773534655570984,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.22325322031974792,
|
| 337 |
+
"logits/rejected": 0.3859561085700989,
|
| 338 |
+
"logps/chosen": -596.8721923828125,
|
| 339 |
+
"logps/rejected": -648.3790893554688,
|
| 340 |
+
"loss": 0.2911,
|
| 341 |
+
"rewards/accuracies": 0.668749988079071,
|
| 342 |
+
"rewards/chosen": -0.24456577003002167,
|
| 343 |
+
"rewards/margins": 0.12123928964138031,
|
| 344 |
+
"rewards/rejected": -0.36580508947372437,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.24928610026836395,
|
| 351 |
+
"logits/rejected": 0.3123549818992615,
|
| 352 |
+
"logps/chosen": -526.9947509765625,
|
| 353 |
+
"logps/rejected": -622.6949462890625,
|
| 354 |
+
"loss": 0.2858,
|
| 355 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 356 |
+
"rewards/chosen": -0.1741228997707367,
|
| 357 |
+
"rewards/margins": 0.15204958617687225,
|
| 358 |
+
"rewards/rejected": -0.32617247104644775,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.2413512021303177,
|
| 365 |
+
"logits/rejected": 0.3579440712928772,
|
| 366 |
+
"logps/chosen": -527.4100341796875,
|
| 367 |
+
"logps/rejected": -615.1137084960938,
|
| 368 |
+
"loss": 0.2276,
|
| 369 |
+
"rewards/accuracies": 0.706250011920929,
|
| 370 |
+
"rewards/chosen": -0.18759354948997498,
|
| 371 |
+
"rewards/margins": 0.15318110585212708,
|
| 372 |
+
"rewards/rejected": -0.34077465534210205,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.22231824696063995,
|
| 379 |
+
"logits/rejected": 0.3377223610877991,
|
| 380 |
+
"logps/chosen": -557.3218994140625,
|
| 381 |
+
"logps/rejected": -656.0249633789062,
|
| 382 |
+
"loss": 0.2409,
|
| 383 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 384 |
+
"rewards/chosen": -0.21337445080280304,
|
| 385 |
+
"rewards/margins": 0.14147409796714783,
|
| 386 |
+
"rewards/rejected": -0.35484856367111206,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.20074252784252167,
|
| 393 |
+
"logits/rejected": 0.31892186403274536,
|
| 394 |
+
"logps/chosen": -619.4715576171875,
|
| 395 |
+
"logps/rejected": -680.501708984375,
|
| 396 |
+
"loss": 0.2752,
|
| 397 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 398 |
+
"rewards/chosen": -0.27192774415016174,
|
| 399 |
+
"rewards/margins": 0.13113710284233093,
|
| 400 |
+
"rewards/rejected": -0.4030648171901703,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.21738846600055695,
|
| 407 |
+
"logits/rejected": 0.36280277371406555,
|
| 408 |
+
"logps/chosen": -641.8638916015625,
|
| 409 |
+
"logps/rejected": -719.9840087890625,
|
| 410 |
+
"loss": 0.2682,
|
| 411 |
+
"rewards/accuracies": 0.675000011920929,
|
| 412 |
+
"rewards/chosen": -0.2767099142074585,
|
| 413 |
+
"rewards/margins": 0.1477716863155365,
|
| 414 |
+
"rewards/rejected": -0.4244815707206726,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": 0.25205639004707336,
|
| 421 |
+
"logits/rejected": 0.3571772873401642,
|
| 422 |
+
"logps/chosen": -596.9175415039062,
|
| 423 |
+
"logps/rejected": -665.6470947265625,
|
| 424 |
+
"loss": 0.2488,
|
| 425 |
+
"rewards/accuracies": 0.699999988079071,
|
| 426 |
+
"rewards/chosen": -0.23527784645557404,
|
| 427 |
+
"rewards/margins": 0.1494690328836441,
|
| 428 |
+
"rewards/rejected": -0.38474684953689575,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.2460106611251831,
|
| 435 |
+
"logits/rejected": 0.340692400932312,
|
| 436 |
+
"logps/chosen": -576.7429809570312,
|
| 437 |
+
"logps/rejected": -725.2931518554688,
|
| 438 |
+
"loss": 0.1927,
|
| 439 |
+
"rewards/accuracies": 0.78125,
|
| 440 |
+
"rewards/chosen": -0.23355364799499512,
|
| 441 |
+
"rewards/margins": 0.19731679558753967,
|
| 442 |
+
"rewards/rejected": -0.4308704435825348,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.27840182185173035,
|
| 449 |
+
"logits/rejected": 0.3699595034122467,
|
| 450 |
+
"logps/chosen": -655.7606201171875,
|
| 451 |
+
"logps/rejected": -755.6095581054688,
|
| 452 |
+
"loss": 0.2432,
|
| 453 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 454 |
+
"rewards/chosen": -0.2706039547920227,
|
| 455 |
+
"rewards/margins": 0.1736321747303009,
|
| 456 |
+
"rewards/rejected": -0.4442361295223236,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.25754767656326294,
|
| 463 |
+
"logits/rejected": 0.38638874888420105,
|
| 464 |
+
"logps/chosen": -657.5533447265625,
|
| 465 |
+
"logps/rejected": -750.8352661132812,
|
| 466 |
+
"loss": 0.2622,
|
| 467 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 468 |
+
"rewards/chosen": -0.2994315028190613,
|
| 469 |
+
"rewards/margins": 0.16641752421855927,
|
| 470 |
+
"rewards/rejected": -0.46584898233413696,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.25059616565704346,
|
| 477 |
+
"logits/rejected": 0.36868372559547424,
|
| 478 |
+
"logps/chosen": -672.0949096679688,
|
| 479 |
+
"logps/rejected": -803.8678588867188,
|
| 480 |
+
"loss": 0.241,
|
| 481 |
+
"rewards/accuracies": 0.75,
|
| 482 |
+
"rewards/chosen": -0.3017386496067047,
|
| 483 |
+
"rewards/margins": 0.20527306199073792,
|
| 484 |
+
"rewards/rejected": -0.5070117115974426,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.2503548264503479,
|
| 491 |
+
"logits/rejected": 0.29262545704841614,
|
| 492 |
+
"logps/chosen": -637.6034545898438,
|
| 493 |
+
"logps/rejected": -689.4666748046875,
|
| 494 |
+
"loss": 0.2409,
|
| 495 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 496 |
+
"rewards/chosen": -0.28344589471817017,
|
| 497 |
+
"rewards/margins": 0.14148998260498047,
|
| 498 |
+
"rewards/rejected": -0.424935907125473,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.21581009030342102,
|
| 505 |
+
"logits/rejected": 0.38255298137664795,
|
| 506 |
+
"logps/chosen": -662.43212890625,
|
| 507 |
+
"logps/rejected": -777.831787109375,
|
| 508 |
+
"loss": 0.2152,
|
| 509 |
+
"rewards/accuracies": 0.762499988079071,
|
| 510 |
+
"rewards/chosen": -0.28980588912963867,
|
| 511 |
+
"rewards/margins": 0.18855467438697815,
|
| 512 |
+
"rewards/rejected": -0.4783605635166168,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.2862156331539154,
|
| 519 |
+
"logits/rejected": 0.3305504024028778,
|
| 520 |
+
"logps/chosen": -632.4459228515625,
|
| 521 |
+
"logps/rejected": -718.5078125,
|
| 522 |
+
"loss": 0.2728,
|
| 523 |
+
"rewards/accuracies": 0.65625,
|
| 524 |
+
"rewards/chosen": -0.294480562210083,
|
| 525 |
+
"rewards/margins": 0.14050373435020447,
|
| 526 |
+
"rewards/rejected": -0.43498435616493225,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.2614066004753113,
|
| 533 |
+
"logits/rejected": 0.2966289818286896,
|
| 534 |
+
"logps/chosen": -622.0609130859375,
|
| 535 |
+
"logps/rejected": -742.937744140625,
|
| 536 |
+
"loss": 0.2505,
|
| 537 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 538 |
+
"rewards/chosen": -0.2878873348236084,
|
| 539 |
+
"rewards/margins": 0.15637485682964325,
|
| 540 |
+
"rewards/rejected": -0.4442622661590576,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": 0.1658310443162918,
|
| 547 |
+
"logits/rejected": 0.25932207703590393,
|
| 548 |
+
"logps/chosen": -574.1139526367188,
|
| 549 |
+
"logps/rejected": -716.8287353515625,
|
| 550 |
+
"loss": 0.2169,
|
| 551 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 552 |
+
"rewards/chosen": -0.25041764974594116,
|
| 553 |
+
"rewards/margins": 0.1778055727481842,
|
| 554 |
+
"rewards/rejected": -0.428223192691803,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": 0.2032794952392578,
|
| 561 |
+
"logits/rejected": 0.2511264681816101,
|
| 562 |
+
"logps/chosen": -652.1287841796875,
|
| 563 |
+
"logps/rejected": -765.1002807617188,
|
| 564 |
+
"loss": 0.2461,
|
| 565 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 566 |
+
"rewards/chosen": -0.31416720151901245,
|
| 567 |
+
"rewards/margins": 0.15508690476417542,
|
| 568 |
+
"rewards/rejected": -0.4692540764808655,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.17228561639785767,
|
| 575 |
+
"logits/rejected": 0.28850919008255005,
|
| 576 |
+
"logps/chosen": -621.0162963867188,
|
| 577 |
+
"logps/rejected": -751.5133666992188,
|
| 578 |
+
"loss": 0.2474,
|
| 579 |
+
"rewards/accuracies": 0.699999988079071,
|
| 580 |
+
"rewards/chosen": -0.28327521681785583,
|
| 581 |
+
"rewards/margins": 0.1886013299226761,
|
| 582 |
+
"rewards/rejected": -0.4718765616416931,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": 0.15390515327453613,
|
| 589 |
+
"logits/rejected": 0.23650500178337097,
|
| 590 |
+
"logps/chosen": -579.6705322265625,
|
| 591 |
+
"logps/rejected": -705.4219970703125,
|
| 592 |
+
"loss": 0.2203,
|
| 593 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 594 |
+
"rewards/chosen": -0.2634733319282532,
|
| 595 |
+
"rewards/margins": 0.17486760020256042,
|
| 596 |
+
"rewards/rejected": -0.4383409917354584,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": 0.15774960815906525,
|
| 603 |
+
"logits/rejected": 0.25373905897140503,
|
| 604 |
+
"logps/chosen": -635.8734130859375,
|
| 605 |
+
"logps/rejected": -759.529052734375,
|
| 606 |
+
"loss": 0.2478,
|
| 607 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 608 |
+
"rewards/chosen": -0.2786625921726227,
|
| 609 |
+
"rewards/margins": 0.18710032105445862,
|
| 610 |
+
"rewards/rejected": -0.4657629132270813,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.17501457035541534,
|
| 617 |
+
"logits/rejected": 0.25947824120521545,
|
| 618 |
+
"logps/chosen": -635.3245849609375,
|
| 619 |
+
"logps/rejected": -745.48095703125,
|
| 620 |
+
"loss": 0.2544,
|
| 621 |
+
"rewards/accuracies": 0.6875,
|
| 622 |
+
"rewards/chosen": -0.2973678708076477,
|
| 623 |
+
"rewards/margins": 0.17151114344596863,
|
| 624 |
+
"rewards/rejected": -0.4688790440559387,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": 0.17305608093738556,
|
| 631 |
+
"logits/rejected": 0.23529882729053497,
|
| 632 |
+
"logps/chosen": -642.1393432617188,
|
| 633 |
+
"logps/rejected": -720.1858520507812,
|
| 634 |
+
"loss": 0.2465,
|
| 635 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 636 |
+
"rewards/chosen": -0.28984335064888,
|
| 637 |
+
"rewards/margins": 0.16753990948200226,
|
| 638 |
+
"rewards/rejected": -0.4573832154273987,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": 0.20705783367156982,
|
| 645 |
+
"logits/rejected": 0.22554746270179749,
|
| 646 |
+
"logps/chosen": -680.9107055664062,
|
| 647 |
+
"logps/rejected": -766.1033325195312,
|
| 648 |
+
"loss": 0.2615,
|
| 649 |
+
"rewards/accuracies": 0.675000011920929,
|
| 650 |
+
"rewards/chosen": -0.32083216309547424,
|
| 651 |
+
"rewards/margins": 0.16086088120937347,
|
| 652 |
+
"rewards/rejected": -0.4816930890083313,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": 0.1991531401872635,
|
| 659 |
+
"logits/rejected": 0.230634406208992,
|
| 660 |
+
"logps/chosen": -618.709716796875,
|
| 661 |
+
"logps/rejected": -745.50537109375,
|
| 662 |
+
"loss": 0.2224,
|
| 663 |
+
"rewards/accuracies": 0.731249988079071,
|
| 664 |
+
"rewards/chosen": -0.3031608760356903,
|
| 665 |
+
"rewards/margins": 0.1703597754240036,
|
| 666 |
+
"rewards/rejected": -0.4735206663608551,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.1910509616136551,
|
| 673 |
+
"logits/rejected": 0.2898029685020447,
|
| 674 |
+
"logps/chosen": -711.2774047851562,
|
| 675 |
+
"logps/rejected": -782.086181640625,
|
| 676 |
+
"loss": 0.2611,
|
| 677 |
+
"rewards/accuracies": 0.737500011920929,
|
| 678 |
+
"rewards/chosen": -0.3283078670501709,
|
| 679 |
+
"rewards/margins": 0.1573607474565506,
|
| 680 |
+
"rewards/rejected": -0.4856685996055603,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.1314457505941391,
|
| 687 |
+
"logits/rejected": 0.21780280768871307,
|
| 688 |
+
"logps/chosen": -586.25439453125,
|
| 689 |
+
"logps/rejected": -682.1627197265625,
|
| 690 |
+
"loss": 0.2774,
|
| 691 |
+
"rewards/accuracies": 0.75,
|
| 692 |
+
"rewards/chosen": -0.2654445469379425,
|
| 693 |
+
"rewards/margins": 0.14997784793376923,
|
| 694 |
+
"rewards/rejected": -0.4154224395751953,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": 0.16227178275585175,
|
| 701 |
+
"logits/rejected": 0.2971927225589752,
|
| 702 |
+
"logps/chosen": -620.1968994140625,
|
| 703 |
+
"logps/rejected": -727.1217651367188,
|
| 704 |
+
"loss": 0.2396,
|
| 705 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 706 |
+
"rewards/chosen": -0.25877463817596436,
|
| 707 |
+
"rewards/margins": 0.17255476117134094,
|
| 708 |
+
"rewards/rejected": -0.4313293397426605,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": 0.17410214245319366,
|
| 715 |
+
"logits/rejected": 0.2344098538160324,
|
| 716 |
+
"logps/chosen": -601.7906494140625,
|
| 717 |
+
"logps/rejected": -691.7999267578125,
|
| 718 |
+
"loss": 0.2486,
|
| 719 |
+
"rewards/accuracies": 0.706250011920929,
|
| 720 |
+
"rewards/chosen": -0.2862247824668884,
|
| 721 |
+
"rewards/margins": 0.1431434452533722,
|
| 722 |
+
"rewards/rejected": -0.429368257522583,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": 0.21162112057209015,
|
| 729 |
+
"logits/rejected": 0.2572205662727356,
|
| 730 |
+
"logps/chosen": -637.9953002929688,
|
| 731 |
+
"logps/rejected": -775.0775756835938,
|
| 732 |
+
"loss": 0.2253,
|
| 733 |
+
"rewards/accuracies": 0.731249988079071,
|
| 734 |
+
"rewards/chosen": -0.2933396100997925,
|
| 735 |
+
"rewards/margins": 0.17365200817584991,
|
| 736 |
+
"rewards/rejected": -0.4669916033744812,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": 0.20230130851268768,
|
| 743 |
+
"logits/rejected": 0.2933056056499481,
|
| 744 |
+
"logps/chosen": -694.6912231445312,
|
| 745 |
+
"logps/rejected": -818.5560913085938,
|
| 746 |
+
"loss": 0.2893,
|
| 747 |
+
"rewards/accuracies": 0.71875,
|
| 748 |
+
"rewards/chosen": -0.35351866483688354,
|
| 749 |
+
"rewards/margins": 0.16594737768173218,
|
| 750 |
+
"rewards/rejected": -0.5194661021232605,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": 0.18275514245033264,
|
| 757 |
+
"logits/rejected": 0.280184805393219,
|
| 758 |
+
"logps/chosen": -717.5177001953125,
|
| 759 |
+
"logps/rejected": -888.8621215820312,
|
| 760 |
+
"loss": 0.1868,
|
| 761 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 762 |
+
"rewards/chosen": -0.3565286695957184,
|
| 763 |
+
"rewards/margins": 0.23444192111492157,
|
| 764 |
+
"rewards/rejected": -0.5909705758094788,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": 0.1679656207561493,
|
| 771 |
+
"logits/rejected": 0.26842325925827026,
|
| 772 |
+
"logps/chosen": -630.0240478515625,
|
| 773 |
+
"logps/rejected": -751.3941650390625,
|
| 774 |
+
"loss": 0.2507,
|
| 775 |
+
"rewards/accuracies": 0.668749988079071,
|
| 776 |
+
"rewards/chosen": -0.32289132475852966,
|
| 777 |
+
"rewards/margins": 0.16883692145347595,
|
| 778 |
+
"rewards/rejected": -0.4917283058166504,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": 0.14577992260456085,
|
| 785 |
+
"logits/rejected": 0.2916201949119568,
|
| 786 |
+
"logps/chosen": -620.7379150390625,
|
| 787 |
+
"logps/rejected": -734.3123168945312,
|
| 788 |
+
"loss": 0.2375,
|
| 789 |
+
"rewards/accuracies": 0.699999988079071,
|
| 790 |
+
"rewards/chosen": -0.26863834261894226,
|
| 791 |
+
"rewards/margins": 0.1942332684993744,
|
| 792 |
+
"rewards/rejected": -0.46287161111831665,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": 0.20810751616954803,
|
| 799 |
+
"logits/rejected": 0.2806350886821747,
|
| 800 |
+
"logps/chosen": -641.7298583984375,
|
| 801 |
+
"logps/rejected": -756.7706909179688,
|
| 802 |
+
"loss": 0.2485,
|
| 803 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 804 |
+
"rewards/chosen": -0.3129487931728363,
|
| 805 |
+
"rewards/margins": 0.16476401686668396,
|
| 806 |
+
"rewards/rejected": -0.47771281003952026,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": 0.17864790558815002,
|
| 813 |
+
"logits/rejected": 0.28502240777015686,
|
| 814 |
+
"logps/chosen": -667.49365234375,
|
| 815 |
+
"logps/rejected": -784.1561279296875,
|
| 816 |
+
"loss": 0.2486,
|
| 817 |
+
"rewards/accuracies": 0.75,
|
| 818 |
+
"rewards/chosen": -0.29371771216392517,
|
| 819 |
+
"rewards/margins": 0.18731026351451874,
|
| 820 |
+
"rewards/rejected": -0.4810279905796051,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": 0.18069639801979065,
|
| 827 |
+
"logits/rejected": 0.26032230257987976,
|
| 828 |
+
"logps/chosen": -668.4435424804688,
|
| 829 |
+
"logps/rejected": -794.9130859375,
|
| 830 |
+
"loss": 0.2149,
|
| 831 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 832 |
+
"rewards/chosen": -0.29407259821891785,
|
| 833 |
+
"rewards/margins": 0.2029459923505783,
|
| 834 |
+
"rewards/rejected": -0.49701857566833496,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": 0.14592161774635315,
|
| 841 |
+
"logits/rejected": 0.21640054881572723,
|
| 842 |
+
"logps/chosen": -656.1441650390625,
|
| 843 |
+
"logps/rejected": -773.119140625,
|
| 844 |
+
"loss": 0.2124,
|
| 845 |
+
"rewards/accuracies": 0.768750011920929,
|
| 846 |
+
"rewards/chosen": -0.30144789814949036,
|
| 847 |
+
"rewards/margins": 0.19570669531822205,
|
| 848 |
+
"rewards/rejected": -0.49715456366539,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": 0.13483521342277527,
|
| 855 |
+
"logits/rejected": 0.26808056235313416,
|
| 856 |
+
"logps/chosen": -663.4806518554688,
|
| 857 |
+
"logps/rejected": -814.9881591796875,
|
| 858 |
+
"loss": 0.2158,
|
| 859 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 860 |
+
"rewards/chosen": -0.33338984847068787,
|
| 861 |
+
"rewards/margins": 0.21311593055725098,
|
| 862 |
+
"rewards/rejected": -0.5465058088302612,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": 0.17011983692646027,
|
| 869 |
+
"logits/rejected": 0.30834323167800903,
|
| 870 |
+
"logps/chosen": -687.5603637695312,
|
| 871 |
+
"logps/rejected": -845.2774658203125,
|
| 872 |
+
"loss": 0.2322,
|
| 873 |
+
"rewards/accuracies": 0.731249988079071,
|
| 874 |
+
"rewards/chosen": -0.3399781286716461,
|
| 875 |
+
"rewards/margins": 0.20812830328941345,
|
| 876 |
+
"rewards/rejected": -0.5481064319610596,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": 0.2005978524684906,
|
| 883 |
+
"logits/rejected": 0.2786727845668793,
|
| 884 |
+
"logps/chosen": -676.8416748046875,
|
| 885 |
+
"logps/rejected": -822.3328247070312,
|
| 886 |
+
"loss": 0.2327,
|
| 887 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 888 |
+
"rewards/chosen": -0.32490307092666626,
|
| 889 |
+
"rewards/margins": 0.2102217972278595,
|
| 890 |
+
"rewards/rejected": -0.5351248979568481,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": 0.2299545705318451,
|
| 897 |
+
"logits/rejected": 0.3201584815979004,
|
| 898 |
+
"logps/chosen": -677.6417236328125,
|
| 899 |
+
"logps/rejected": -811.4082641601562,
|
| 900 |
+
"loss": 0.2091,
|
| 901 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 902 |
+
"rewards/chosen": -0.3028990626335144,
|
| 903 |
+
"rewards/margins": 0.2108876258134842,
|
| 904 |
+
"rewards/rejected": -0.5137866735458374,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": 0.18550391495227814,
|
| 911 |
+
"logits/rejected": 0.3030850887298584,
|
| 912 |
+
"logps/chosen": -693.2557373046875,
|
| 913 |
+
"logps/rejected": -851.9300537109375,
|
| 914 |
+
"loss": 0.2046,
|
| 915 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 916 |
+
"rewards/chosen": -0.32129475474357605,
|
| 917 |
+
"rewards/margins": 0.23609153926372528,
|
| 918 |
+
"rewards/rejected": -0.5573862791061401,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": 0.21198038756847382,
|
| 925 |
+
"logits/rejected": 0.353886216878891,
|
| 926 |
+
"logps/chosen": -680.061767578125,
|
| 927 |
+
"logps/rejected": -838.3746337890625,
|
| 928 |
+
"loss": 0.2152,
|
| 929 |
+
"rewards/accuracies": 0.762499988079071,
|
| 930 |
+
"rewards/chosen": -0.3215908408164978,
|
| 931 |
+
"rewards/margins": 0.2143673449754715,
|
| 932 |
+
"rewards/rejected": -0.5359582304954529,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": 0.1963845193386078,
|
| 939 |
+
"logits/rejected": 0.32071763277053833,
|
| 940 |
+
"logps/chosen": -664.4266357421875,
|
| 941 |
+
"logps/rejected": -800.628662109375,
|
| 942 |
+
"loss": 0.2326,
|
| 943 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 944 |
+
"rewards/chosen": -0.323551207780838,
|
| 945 |
+
"rewards/margins": 0.20758795738220215,
|
| 946 |
+
"rewards/rejected": -0.5311391949653625,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": 0.2653447985649109,
|
| 953 |
+
"logits/rejected": 0.32281583547592163,
|
| 954 |
+
"logps/chosen": -645.7322998046875,
|
| 955 |
+
"logps/rejected": -818.6993408203125,
|
| 956 |
+
"loss": 0.2088,
|
| 957 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 958 |
+
"rewards/chosen": -0.30575788021087646,
|
| 959 |
+
"rewards/margins": 0.20940056443214417,
|
| 960 |
+
"rewards/rejected": -0.5151584148406982,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": 0.22752830386161804,
|
| 967 |
+
"logits/rejected": 0.29400375485420227,
|
| 968 |
+
"logps/chosen": -668.3670654296875,
|
| 969 |
+
"logps/rejected": -773.338623046875,
|
| 970 |
+
"loss": 0.2668,
|
| 971 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 972 |
+
"rewards/chosen": -0.3347984850406647,
|
| 973 |
+
"rewards/margins": 0.1586008071899414,
|
| 974 |
+
"rewards/rejected": -0.4933992922306061,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": 0.22624416649341583,
|
| 981 |
+
"logits/rejected": 0.3623146116733551,
|
| 982 |
+
"logps/chosen": -635.141357421875,
|
| 983 |
+
"logps/rejected": -833.0682373046875,
|
| 984 |
+
"loss": 0.2039,
|
| 985 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 986 |
+
"rewards/chosen": -0.32188528776168823,
|
| 987 |
+
"rewards/margins": 0.22867591679096222,
|
| 988 |
+
"rewards/rejected": -0.5505611896514893,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": 0.24318163096904755,
|
| 995 |
+
"logits/rejected": 0.31874382495880127,
|
| 996 |
+
"logps/chosen": -668.0684814453125,
|
| 997 |
+
"logps/rejected": -803.7855224609375,
|
| 998 |
+
"loss": 0.2405,
|
| 999 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1000 |
+
"rewards/chosen": -0.33614617586135864,
|
| 1001 |
+
"rewards/margins": 0.18720091879367828,
|
| 1002 |
+
"rewards/rejected": -0.5233470797538757,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": 0.2103017121553421,
|
| 1009 |
+
"logits/rejected": 0.30453357100486755,
|
| 1010 |
+
"logps/chosen": -750.6541748046875,
|
| 1011 |
+
"logps/rejected": -890.9783325195312,
|
| 1012 |
+
"loss": 0.2479,
|
| 1013 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1014 |
+
"rewards/chosen": -0.3959191143512726,
|
| 1015 |
+
"rewards/margins": 0.2101031243801117,
|
| 1016 |
+
"rewards/rejected": -0.6060222387313843,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": 0.18374183773994446,
|
| 1023 |
+
"logits/rejected": 0.2802325189113617,
|
| 1024 |
+
"logps/chosen": -704.2998046875,
|
| 1025 |
+
"logps/rejected": -872.6188354492188,
|
| 1026 |
+
"loss": 0.2378,
|
| 1027 |
+
"rewards/accuracies": 0.6875,
|
| 1028 |
+
"rewards/chosen": -0.3979497253894806,
|
| 1029 |
+
"rewards/margins": 0.18762901425361633,
|
| 1030 |
+
"rewards/rejected": -0.5855787396430969,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": 0.2030530869960785,
|
| 1037 |
+
"logits/rejected": 0.2757278084754944,
|
| 1038 |
+
"logps/chosen": -781.7509155273438,
|
| 1039 |
+
"logps/rejected": -940.8536376953125,
|
| 1040 |
+
"loss": 0.1757,
|
| 1041 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1042 |
+
"rewards/chosen": -0.4106892943382263,
|
| 1043 |
+
"rewards/margins": 0.23548904061317444,
|
| 1044 |
+
"rewards/rejected": -0.6461783647537231,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": 0.1338091641664505,
|
| 1051 |
+
"logits/rejected": 0.2605449855327606,
|
| 1052 |
+
"logps/chosen": -802.19091796875,
|
| 1053 |
+
"logps/rejected": -937.0023193359375,
|
| 1054 |
+
"loss": 0.226,
|
| 1055 |
+
"rewards/accuracies": 0.75,
|
| 1056 |
+
"rewards/chosen": -0.42191141843795776,
|
| 1057 |
+
"rewards/margins": 0.2278059720993042,
|
| 1058 |
+
"rewards/rejected": -0.649717390537262,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": 0.2370164394378662,
|
| 1065 |
+
"logits/rejected": 0.2781811058521271,
|
| 1066 |
+
"logps/chosen": -754.5617065429688,
|
| 1067 |
+
"logps/rejected": -908.2735595703125,
|
| 1068 |
+
"loss": 0.2125,
|
| 1069 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1070 |
+
"rewards/chosen": -0.3990176320075989,
|
| 1071 |
+
"rewards/margins": 0.20696358382701874,
|
| 1072 |
+
"rewards/rejected": -0.6059812307357788,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": 0.169587641954422,
|
| 1079 |
+
"logits/rejected": 0.3024446368217468,
|
| 1080 |
+
"logps/chosen": -662.3217163085938,
|
| 1081 |
+
"logps/rejected": -817.04638671875,
|
| 1082 |
+
"loss": 0.2308,
|
| 1083 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1084 |
+
"rewards/chosen": -0.35774677991867065,
|
| 1085 |
+
"rewards/margins": 0.19141057133674622,
|
| 1086 |
+
"rewards/rejected": -0.5491573214530945,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": 0.18283501267433167,
|
| 1093 |
+
"logits/rejected": 0.27203458547592163,
|
| 1094 |
+
"logps/chosen": -694.4537353515625,
|
| 1095 |
+
"logps/rejected": -874.41162109375,
|
| 1096 |
+
"loss": 0.1928,
|
| 1097 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1098 |
+
"rewards/chosen": -0.3298128545284271,
|
| 1099 |
+
"rewards/margins": 0.236416295170784,
|
| 1100 |
+
"rewards/rejected": -0.5662291646003723,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": 0.23415608704090118,
|
| 1107 |
+
"logits/rejected": 0.27542707324028015,
|
| 1108 |
+
"logps/chosen": -682.388671875,
|
| 1109 |
+
"logps/rejected": -793.8580932617188,
|
| 1110 |
+
"loss": 0.1776,
|
| 1111 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1112 |
+
"rewards/chosen": -0.29099172353744507,
|
| 1113 |
+
"rewards/margins": 0.22200138866901398,
|
| 1114 |
+
"rewards/rejected": -0.5129930973052979,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": 0.14799238741397858,
|
| 1121 |
+
"logits/rejected": 0.28972503542900085,
|
| 1122 |
+
"logps/chosen": -674.9385375976562,
|
| 1123 |
+
"logps/rejected": -882.7672729492188,
|
| 1124 |
+
"loss": 0.1758,
|
| 1125 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1126 |
+
"rewards/chosen": -0.32894080877304077,
|
| 1127 |
+
"rewards/margins": 0.24991688132286072,
|
| 1128 |
+
"rewards/rejected": -0.5788577198982239,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": 0.1383066177368164,
|
| 1135 |
+
"logits/rejected": 0.24791190028190613,
|
| 1136 |
+
"logps/chosen": -707.7462158203125,
|
| 1137 |
+
"logps/rejected": -852.08984375,
|
| 1138 |
+
"loss": 0.223,
|
| 1139 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1140 |
+
"rewards/chosen": -0.36430221796035767,
|
| 1141 |
+
"rewards/margins": 0.1998947560787201,
|
| 1142 |
+
"rewards/rejected": -0.5641970038414001,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": 0.1664973497390747,
|
| 1149 |
+
"logits/rejected": 0.2503690719604492,
|
| 1150 |
+
"logps/chosen": -671.7937622070312,
|
| 1151 |
+
"logps/rejected": -855.0314331054688,
|
| 1152 |
+
"loss": 0.2005,
|
| 1153 |
+
"rewards/accuracies": 0.78125,
|
| 1154 |
+
"rewards/chosen": -0.32940590381622314,
|
| 1155 |
+
"rewards/margins": 0.23283663392066956,
|
| 1156 |
+
"rewards/rejected": -0.5622425079345703,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": 0.13743051886558533,
|
| 1163 |
+
"logits/rejected": 0.2722577452659607,
|
| 1164 |
+
"logps/chosen": -701.9246826171875,
|
| 1165 |
+
"logps/rejected": -850.3126220703125,
|
| 1166 |
+
"loss": 0.2512,
|
| 1167 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1168 |
+
"rewards/chosen": -0.365190327167511,
|
| 1169 |
+
"rewards/margins": 0.20733347535133362,
|
| 1170 |
+
"rewards/rejected": -0.5725237727165222,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": 0.14434996247291565,
|
| 1177 |
+
"logits/rejected": 0.24066290259361267,
|
| 1178 |
+
"logps/chosen": -690.765380859375,
|
| 1179 |
+
"logps/rejected": -829.47802734375,
|
| 1180 |
+
"loss": 0.2331,
|
| 1181 |
+
"rewards/accuracies": 0.75,
|
| 1182 |
+
"rewards/chosen": -0.3407720923423767,
|
| 1183 |
+
"rewards/margins": 0.19598500430583954,
|
| 1184 |
+
"rewards/rejected": -0.5367571115493774,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": 0.17098698019981384,
|
| 1191 |
+
"logits/rejected": 0.24693337082862854,
|
| 1192 |
+
"logps/chosen": -667.8488159179688,
|
| 1193 |
+
"logps/rejected": -805.3338012695312,
|
| 1194 |
+
"loss": 0.2299,
|
| 1195 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1196 |
+
"rewards/chosen": -0.3178989291191101,
|
| 1197 |
+
"rewards/margins": 0.19422563910484314,
|
| 1198 |
+
"rewards/rejected": -0.5121246576309204,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": 0.14288540184497833,
|
| 1205 |
+
"logits/rejected": 0.34719187021255493,
|
| 1206 |
+
"logps/chosen": -716.6546020507812,
|
| 1207 |
+
"logps/rejected": -865.6365356445312,
|
| 1208 |
+
"loss": 0.1918,
|
| 1209 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1210 |
+
"rewards/chosen": -0.3239936828613281,
|
| 1211 |
+
"rewards/margins": 0.23718833923339844,
|
| 1212 |
+
"rewards/rejected": -0.5611820220947266,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": 0.16771307587623596,
|
| 1219 |
+
"logits/rejected": 0.30368170142173767,
|
| 1220 |
+
"logps/chosen": -685.092529296875,
|
| 1221 |
+
"logps/rejected": -844.0833740234375,
|
| 1222 |
+
"loss": 0.2314,
|
| 1223 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1224 |
+
"rewards/chosen": -0.3250967860221863,
|
| 1225 |
+
"rewards/margins": 0.22138158977031708,
|
| 1226 |
+
"rewards/rejected": -0.5464783906936646,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": 0.184052973985672,
|
| 1233 |
+
"logits/rejected": 0.25310075283050537,
|
| 1234 |
+
"logps/chosen": -602.6265869140625,
|
| 1235 |
+
"logps/rejected": -813.6980590820312,
|
| 1236 |
+
"loss": 0.2004,
|
| 1237 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1238 |
+
"rewards/chosen": -0.30271750688552856,
|
| 1239 |
+
"rewards/margins": 0.22967958450317383,
|
| 1240 |
+
"rewards/rejected": -0.5323971509933472,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": 0.16844046115875244,
|
| 1247 |
+
"logits/rejected": 0.29345783591270447,
|
| 1248 |
+
"logps/chosen": -665.3712768554688,
|
| 1249 |
+
"logps/rejected": -814.3455200195312,
|
| 1250 |
+
"loss": 0.2311,
|
| 1251 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1252 |
+
"rewards/chosen": -0.3122372329235077,
|
| 1253 |
+
"rewards/margins": 0.22387078404426575,
|
| 1254 |
+
"rewards/rejected": -0.5361080169677734,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": 0.13841773569583893,
|
| 1261 |
+
"logits/rejected": 0.2724143862724304,
|
| 1262 |
+
"logps/chosen": -630.0308837890625,
|
| 1263 |
+
"logps/rejected": -790.6541748046875,
|
| 1264 |
+
"loss": 0.2211,
|
| 1265 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1266 |
+
"rewards/chosen": -0.3019189238548279,
|
| 1267 |
+
"rewards/margins": 0.20678682625293732,
|
| 1268 |
+
"rewards/rejected": -0.508705735206604,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": 0.1345725655555725,
|
| 1275 |
+
"logits/rejected": 0.23907344043254852,
|
| 1276 |
+
"logps/chosen": -637.2769775390625,
|
| 1277 |
+
"logps/rejected": -765.0687255859375,
|
| 1278 |
+
"loss": 0.2417,
|
| 1279 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1280 |
+
"rewards/chosen": -0.3158628046512604,
|
| 1281 |
+
"rewards/margins": 0.18091067671775818,
|
| 1282 |
+
"rewards/rejected": -0.49677348136901855,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": 0.17173132300376892,
|
| 1289 |
+
"logits/rejected": 0.27450239658355713,
|
| 1290 |
+
"logps/chosen": -654.5206909179688,
|
| 1291 |
+
"logps/rejected": -773.1864624023438,
|
| 1292 |
+
"loss": 0.2347,
|
| 1293 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1294 |
+
"rewards/chosen": -0.29153797030448914,
|
| 1295 |
+
"rewards/margins": 0.18850579857826233,
|
| 1296 |
+
"rewards/rejected": -0.48004379868507385,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": 0.09793679416179657,
|
| 1303 |
+
"logits/rejected": 0.21310484409332275,
|
| 1304 |
+
"logps/chosen": -548.7819213867188,
|
| 1305 |
+
"logps/rejected": -664.791748046875,
|
| 1306 |
+
"loss": 0.2495,
|
| 1307 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1308 |
+
"rewards/chosen": -0.27799323201179504,
|
| 1309 |
+
"rewards/margins": 0.1372607797384262,
|
| 1310 |
+
"rewards/rejected": -0.41525402665138245,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": 0.1282065361738205,
|
| 1317 |
+
"logits/rejected": 0.24735228717327118,
|
| 1318 |
+
"logps/chosen": -664.9998779296875,
|
| 1319 |
+
"logps/rejected": -803.4345092773438,
|
| 1320 |
+
"loss": 0.2076,
|
| 1321 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1322 |
+
"rewards/chosen": -0.2840580344200134,
|
| 1323 |
+
"rewards/margins": 0.20879141986370087,
|
| 1324 |
+
"rewards/rejected": -0.4928494393825531,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": 0.16821298003196716,
|
| 1331 |
+
"logits/rejected": 0.27364301681518555,
|
| 1332 |
+
"logps/chosen": -605.760009765625,
|
| 1333 |
+
"logps/rejected": -756.7783203125,
|
| 1334 |
+
"loss": 0.1963,
|
| 1335 |
+
"rewards/accuracies": 0.75,
|
| 1336 |
+
"rewards/chosen": -0.2758532166481018,
|
| 1337 |
+
"rewards/margins": 0.2066863477230072,
|
| 1338 |
+
"rewards/rejected": -0.48253950476646423,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": 0.17568457126617432,
|
| 1345 |
+
"logits/rejected": 0.29186689853668213,
|
| 1346 |
+
"logps/chosen": -685.6893310546875,
|
| 1347 |
+
"logps/rejected": -801.7379760742188,
|
| 1348 |
+
"loss": 0.2097,
|
| 1349 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1350 |
+
"rewards/chosen": -0.310352623462677,
|
| 1351 |
+
"rewards/margins": 0.21010994911193848,
|
| 1352 |
+
"rewards/rejected": -0.5204626321792603,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": 0.13978341221809387,
|
| 1359 |
+
"logits/rejected": 0.301819771528244,
|
| 1360 |
+
"logps/chosen": -684.533447265625,
|
| 1361 |
+
"logps/rejected": -834.8068237304688,
|
| 1362 |
+
"loss": 0.1966,
|
| 1363 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1364 |
+
"rewards/chosen": -0.32525286078453064,
|
| 1365 |
+
"rewards/margins": 0.2377183884382248,
|
| 1366 |
+
"rewards/rejected": -0.5629712343215942,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": 0.09446505457162857,
|
| 1373 |
+
"logits/rejected": 0.23469948768615723,
|
| 1374 |
+
"logps/chosen": -680.0986938476562,
|
| 1375 |
+
"logps/rejected": -874.7296752929688,
|
| 1376 |
+
"loss": 0.2222,
|
| 1377 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1378 |
+
"rewards/chosen": -0.37397751212120056,
|
| 1379 |
+
"rewards/margins": 0.21345043182373047,
|
| 1380 |
+
"rewards/rejected": -0.5874279141426086,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": 0.14745548367500305,
|
| 1387 |
+
"logits/rejected": 0.24975991249084473,
|
| 1388 |
+
"logps/chosen": -698.392333984375,
|
| 1389 |
+
"logps/rejected": -879.1796875,
|
| 1390 |
+
"loss": 0.2214,
|
| 1391 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1392 |
+
"rewards/chosen": -0.3602352738380432,
|
| 1393 |
+
"rewards/margins": 0.23033419251441956,
|
| 1394 |
+
"rewards/rejected": -0.5905694365501404,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": 0.2092140018939972,
|
| 1401 |
+
"logits/rejected": 0.27887001633644104,
|
| 1402 |
+
"logps/chosen": -710.7349853515625,
|
| 1403 |
+
"logps/rejected": -857.5948486328125,
|
| 1404 |
+
"loss": 0.2073,
|
| 1405 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1406 |
+
"rewards/chosen": -0.3808177411556244,
|
| 1407 |
+
"rewards/margins": 0.20695774257183075,
|
| 1408 |
+
"rewards/rejected": -0.5877754092216492,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": 0.1725001335144043,
|
| 1415 |
+
"logits/rejected": 0.29407089948654175,
|
| 1416 |
+
"logps/chosen": -729.5244750976562,
|
| 1417 |
+
"logps/rejected": -877.9232177734375,
|
| 1418 |
+
"loss": 0.2245,
|
| 1419 |
+
"rewards/accuracies": 0.75,
|
| 1420 |
+
"rewards/chosen": -0.3700968027114868,
|
| 1421 |
+
"rewards/margins": 0.21660438179969788,
|
| 1422 |
+
"rewards/rejected": -0.5867011547088623,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": 0.2023136168718338,
|
| 1429 |
+
"logits/rejected": 0.34080618619918823,
|
| 1430 |
+
"logps/chosen": -720.8736572265625,
|
| 1431 |
+
"logps/rejected": -897.9036254882812,
|
| 1432 |
+
"loss": 0.1841,
|
| 1433 |
+
"rewards/accuracies": 0.78125,
|
| 1434 |
+
"rewards/chosen": -0.35647687315940857,
|
| 1435 |
+
"rewards/margins": 0.2519916296005249,
|
| 1436 |
+
"rewards/rejected": -0.6084684133529663,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": 0.19418708980083466,
|
| 1443 |
+
"logits/rejected": 0.2382660210132599,
|
| 1444 |
+
"logps/chosen": -742.7463989257812,
|
| 1445 |
+
"logps/rejected": -869.5545654296875,
|
| 1446 |
+
"loss": 0.2384,
|
| 1447 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1448 |
+
"rewards/chosen": -0.38469210267066956,
|
| 1449 |
+
"rewards/margins": 0.19250501692295074,
|
| 1450 |
+
"rewards/rejected": -0.5771971344947815,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": 0.14089372754096985,
|
| 1457 |
+
"logits/rejected": 0.31221604347229004,
|
| 1458 |
+
"logps/chosen": -706.3193359375,
|
| 1459 |
+
"logps/rejected": -869.9044799804688,
|
| 1460 |
+
"loss": 0.2098,
|
| 1461 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1462 |
+
"rewards/chosen": -0.37956079840660095,
|
| 1463 |
+
"rewards/margins": 0.2095469981431961,
|
| 1464 |
+
"rewards/rejected": -0.5891078114509583,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": 0.17403286695480347,
|
| 1471 |
+
"logits/rejected": 0.26741212606430054,
|
| 1472 |
+
"logps/chosen": -721.5260620117188,
|
| 1473 |
+
"logps/rejected": -841.1495971679688,
|
| 1474 |
+
"loss": 0.2229,
|
| 1475 |
+
"rewards/accuracies": 0.75,
|
| 1476 |
+
"rewards/chosen": -0.3337891697883606,
|
| 1477 |
+
"rewards/margins": 0.21049503982067108,
|
| 1478 |
+
"rewards/rejected": -0.5442842245101929,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": 0.08936522901058197,
|
| 1485 |
+
"logits/rejected": 0.208079531788826,
|
| 1486 |
+
"logps/chosen": -630.3549194335938,
|
| 1487 |
+
"logps/rejected": -773.2559204101562,
|
| 1488 |
+
"loss": 0.2153,
|
| 1489 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1490 |
+
"rewards/chosen": -0.31285005807876587,
|
| 1491 |
+
"rewards/margins": 0.19155475497245789,
|
| 1492 |
+
"rewards/rejected": -0.5044047832489014,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": 0.13943253457546234,
|
| 1499 |
+
"logits/rejected": 0.25722983479499817,
|
| 1500 |
+
"logps/chosen": -671.1966552734375,
|
| 1501 |
+
"logps/rejected": -789.2672729492188,
|
| 1502 |
+
"loss": 0.2079,
|
| 1503 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1504 |
+
"rewards/chosen": -0.32751041650772095,
|
| 1505 |
+
"rewards/margins": 0.2003813236951828,
|
| 1506 |
+
"rewards/rejected": -0.5278916358947754,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": 0.1597217619419098,
|
| 1513 |
+
"logits/rejected": 0.1886836737394333,
|
| 1514 |
+
"logps/chosen": -683.5093994140625,
|
| 1515 |
+
"logps/rejected": -836.6939697265625,
|
| 1516 |
+
"loss": 0.1907,
|
| 1517 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1518 |
+
"rewards/chosen": -0.3347502648830414,
|
| 1519 |
+
"rewards/margins": 0.21815776824951172,
|
| 1520 |
+
"rewards/rejected": -0.5529080629348755,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": 0.11823856830596924,
|
| 1527 |
+
"logits/rejected": 0.22079403698444366,
|
| 1528 |
+
"logps/chosen": -722.5678100585938,
|
| 1529 |
+
"logps/rejected": -888.1004028320312,
|
| 1530 |
+
"loss": 0.2454,
|
| 1531 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1532 |
+
"rewards/chosen": -0.3936742842197418,
|
| 1533 |
+
"rewards/margins": 0.19485920667648315,
|
| 1534 |
+
"rewards/rejected": -0.5885335206985474,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": 0.12982912361621857,
|
| 1541 |
+
"logits/rejected": 0.2598816454410553,
|
| 1542 |
+
"logps/chosen": -726.23291015625,
|
| 1543 |
+
"logps/rejected": -867.5569458007812,
|
| 1544 |
+
"loss": 0.2153,
|
| 1545 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1546 |
+
"rewards/chosen": -0.3581377863883972,
|
| 1547 |
+
"rewards/margins": 0.21532902121543884,
|
| 1548 |
+
"rewards/rejected": -0.5734668970108032,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": 0.12636715173721313,
|
| 1555 |
+
"logits/rejected": 0.23508496582508087,
|
| 1556 |
+
"logps/chosen": -683.2789306640625,
|
| 1557 |
+
"logps/rejected": -821.7802734375,
|
| 1558 |
+
"loss": 0.2059,
|
| 1559 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1560 |
+
"rewards/chosen": -0.32184451818466187,
|
| 1561 |
+
"rewards/margins": 0.22134391963481903,
|
| 1562 |
+
"rewards/rejected": -0.5431884527206421,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": 0.11493659019470215,
|
| 1569 |
+
"logits/rejected": 0.25907325744628906,
|
| 1570 |
+
"logps/chosen": -688.8036499023438,
|
| 1571 |
+
"logps/rejected": -853.0017700195312,
|
| 1572 |
+
"loss": 0.1887,
|
| 1573 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1574 |
+
"rewards/chosen": -0.3468135893344879,
|
| 1575 |
+
"rewards/margins": 0.22318044304847717,
|
| 1576 |
+
"rewards/rejected": -0.5699939727783203,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": 0.15250439941883087,
|
| 1583 |
+
"logits/rejected": 0.25078490376472473,
|
| 1584 |
+
"logps/chosen": -663.3401489257812,
|
| 1585 |
+
"logps/rejected": -840.7469482421875,
|
| 1586 |
+
"loss": 0.2285,
|
| 1587 |
+
"rewards/accuracies": 0.78125,
|
| 1588 |
+
"rewards/chosen": -0.36832159757614136,
|
| 1589 |
+
"rewards/margins": 0.2164924144744873,
|
| 1590 |
+
"rewards/rejected": -0.5848139524459839,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": 0.15975138545036316,
|
| 1597 |
+
"logits/rejected": 0.2446996420621872,
|
| 1598 |
+
"logps/chosen": -686.4671020507812,
|
| 1599 |
+
"logps/rejected": -884.5764770507812,
|
| 1600 |
+
"loss": 0.1993,
|
| 1601 |
+
"rewards/accuracies": 0.6875,
|
| 1602 |
+
"rewards/chosen": -0.357178658246994,
|
| 1603 |
+
"rewards/margins": 0.2013837844133377,
|
| 1604 |
+
"rewards/rejected": -0.5585624575614929,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": 0.1569955199956894,
|
| 1611 |
+
"logits/rejected": 0.2909889817237854,
|
| 1612 |
+
"logps/chosen": -670.5752563476562,
|
| 1613 |
+
"logps/rejected": -830.7100830078125,
|
| 1614 |
+
"loss": 0.2121,
|
| 1615 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1616 |
+
"rewards/chosen": -0.3219209909439087,
|
| 1617 |
+
"rewards/margins": 0.2229768931865692,
|
| 1618 |
+
"rewards/rejected": -0.5448979139328003,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": 0.16851790249347687,
|
| 1625 |
+
"logits/rejected": 0.27851399779319763,
|
| 1626 |
+
"logps/chosen": -673.5487060546875,
|
| 1627 |
+
"logps/rejected": -770.0308837890625,
|
| 1628 |
+
"loss": 0.2135,
|
| 1629 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1630 |
+
"rewards/chosen": -0.2954522967338562,
|
| 1631 |
+
"rewards/margins": 0.1889936327934265,
|
| 1632 |
+
"rewards/rejected": -0.4844458997249603,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": 0.12967072427272797,
|
| 1639 |
+
"logits/rejected": 0.20891770720481873,
|
| 1640 |
+
"logps/chosen": -606.8577880859375,
|
| 1641 |
+
"logps/rejected": -735.3054809570312,
|
| 1642 |
+
"loss": 0.2069,
|
| 1643 |
+
"rewards/accuracies": 0.75,
|
| 1644 |
+
"rewards/chosen": -0.26535481214523315,
|
| 1645 |
+
"rewards/margins": 0.20063455402851105,
|
| 1646 |
+
"rewards/rejected": -0.465989351272583,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": 0.1516229659318924,
|
| 1653 |
+
"logits/rejected": 0.2716851532459259,
|
| 1654 |
+
"logps/chosen": -612.8181762695312,
|
| 1655 |
+
"logps/rejected": -756.4715576171875,
|
| 1656 |
+
"loss": 0.2025,
|
| 1657 |
+
"rewards/accuracies": 0.75,
|
| 1658 |
+
"rewards/chosen": -0.28186386823654175,
|
| 1659 |
+
"rewards/margins": 0.21003735065460205,
|
| 1660 |
+
"rewards/rejected": -0.4919012188911438,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": 0.1507120281457901,
|
| 1667 |
+
"logits/rejected": 0.29278236627578735,
|
| 1668 |
+
"logps/chosen": -704.4903564453125,
|
| 1669 |
+
"logps/rejected": -869.5260009765625,
|
| 1670 |
+
"loss": 0.2119,
|
| 1671 |
+
"rewards/accuracies": 0.78125,
|
| 1672 |
+
"rewards/chosen": -0.3547202944755554,
|
| 1673 |
+
"rewards/margins": 0.2284606695175171,
|
| 1674 |
+
"rewards/rejected": -0.5831810235977173,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": 0.2021058052778244,
|
| 1681 |
+
"logits/rejected": 0.2638623118400574,
|
| 1682 |
+
"logps/chosen": -692.8404541015625,
|
| 1683 |
+
"logps/rejected": -797.3179321289062,
|
| 1684 |
+
"loss": 0.2564,
|
| 1685 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1686 |
+
"rewards/chosen": -0.354163259267807,
|
| 1687 |
+
"rewards/margins": 0.18512588739395142,
|
| 1688 |
+
"rewards/rejected": -0.5392891764640808,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": 0.1298045814037323,
|
| 1695 |
+
"logits/rejected": 0.24017031490802765,
|
| 1696 |
+
"logps/chosen": -702.1468505859375,
|
| 1697 |
+
"logps/rejected": -854.5265502929688,
|
| 1698 |
+
"loss": 0.2064,
|
| 1699 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1700 |
+
"rewards/chosen": -0.3338576555252075,
|
| 1701 |
+
"rewards/margins": 0.22743964195251465,
|
| 1702 |
+
"rewards/rejected": -0.5612972974777222,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": 0.20339742302894592,
|
| 1709 |
+
"logits/rejected": 0.24962684512138367,
|
| 1710 |
+
"logps/chosen": -729.5333862304688,
|
| 1711 |
+
"logps/rejected": -869.4794921875,
|
| 1712 |
+
"loss": 0.2122,
|
| 1713 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1714 |
+
"rewards/chosen": -0.34650754928588867,
|
| 1715 |
+
"rewards/margins": 0.223586767911911,
|
| 1716 |
+
"rewards/rejected": -0.5700943470001221,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": 0.1773589849472046,
|
| 1723 |
+
"logits/rejected": 0.29130274057388306,
|
| 1724 |
+
"logps/chosen": -689.1021728515625,
|
| 1725 |
+
"logps/rejected": -871.9329223632812,
|
| 1726 |
+
"loss": 0.1625,
|
| 1727 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1728 |
+
"rewards/chosen": -0.32862764596939087,
|
| 1729 |
+
"rewards/margins": 0.2522730827331543,
|
| 1730 |
+
"rewards/rejected": -0.5809007287025452,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": 0.08677888661623001,
|
| 1737 |
+
"logits/rejected": 0.2043531835079193,
|
| 1738 |
+
"logps/chosen": -683.0452270507812,
|
| 1739 |
+
"logps/rejected": -853.3363037109375,
|
| 1740 |
+
"loss": 0.1967,
|
| 1741 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1742 |
+
"rewards/chosen": -0.3488999605178833,
|
| 1743 |
+
"rewards/margins": 0.2315068542957306,
|
| 1744 |
+
"rewards/rejected": -0.5804067850112915,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": 0.12979058921337128,
|
| 1751 |
+
"logits/rejected": 0.24603179097175598,
|
| 1752 |
+
"logps/chosen": -737.0632934570312,
|
| 1753 |
+
"logps/rejected": -886.8776245117188,
|
| 1754 |
+
"loss": 0.2403,
|
| 1755 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1756 |
+
"rewards/chosen": -0.39016053080558777,
|
| 1757 |
+
"rewards/margins": 0.20638911426067352,
|
| 1758 |
+
"rewards/rejected": -0.5965496301651001,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": 0.15358899533748627,
|
| 1765 |
+
"logits/rejected": 0.32385343313217163,
|
| 1766 |
+
"logps/chosen": -662.0921630859375,
|
| 1767 |
+
"logps/rejected": -823.0596923828125,
|
| 1768 |
+
"loss": 0.2037,
|
| 1769 |
+
"rewards/accuracies": 0.75,
|
| 1770 |
+
"rewards/chosen": -0.31596821546554565,
|
| 1771 |
+
"rewards/margins": 0.2252482920885086,
|
| 1772 |
+
"rewards/rejected": -0.5412164926528931,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": 0.14214789867401123,
|
| 1779 |
+
"logits/rejected": 0.25008469820022583,
|
| 1780 |
+
"logps/chosen": -613.7877197265625,
|
| 1781 |
+
"logps/rejected": -783.76025390625,
|
| 1782 |
+
"loss": 0.2255,
|
| 1783 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1784 |
+
"rewards/chosen": -0.3245735764503479,
|
| 1785 |
+
"rewards/margins": 0.18011733889579773,
|
| 1786 |
+
"rewards/rejected": -0.504690945148468,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": 0.14355778694152832,
|
| 1793 |
+
"logits/rejected": 0.24925288558006287,
|
| 1794 |
+
"logps/chosen": -668.3030395507812,
|
| 1795 |
+
"logps/rejected": -847.2467041015625,
|
| 1796 |
+
"loss": 0.1859,
|
| 1797 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1798 |
+
"rewards/chosen": -0.30989786982536316,
|
| 1799 |
+
"rewards/margins": 0.23173482716083527,
|
| 1800 |
+
"rewards/rejected": -0.5416327118873596,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": 0.16522178053855896,
|
| 1807 |
+
"logits/rejected": 0.24320781230926514,
|
| 1808 |
+
"logps/chosen": -641.2236938476562,
|
| 1809 |
+
"logps/rejected": -764.9053344726562,
|
| 1810 |
+
"loss": 0.2218,
|
| 1811 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1812 |
+
"rewards/chosen": -0.3104414641857147,
|
| 1813 |
+
"rewards/margins": 0.18151786923408508,
|
| 1814 |
+
"rewards/rejected": -0.4919593334197998,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": 0.10045696794986725,
|
| 1821 |
+
"logits/rejected": 0.22447367012500763,
|
| 1822 |
+
"logps/chosen": -676.05419921875,
|
| 1823 |
+
"logps/rejected": -803.32763671875,
|
| 1824 |
+
"loss": 0.2208,
|
| 1825 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1826 |
+
"rewards/chosen": -0.3212507665157318,
|
| 1827 |
+
"rewards/margins": 0.21263284981250763,
|
| 1828 |
+
"rewards/rejected": -0.5338836312294006,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": 0.158107191324234,
|
| 1835 |
+
"logits/rejected": 0.19983355700969696,
|
| 1836 |
+
"logps/chosen": -619.661865234375,
|
| 1837 |
+
"logps/rejected": -794.2459106445312,
|
| 1838 |
+
"loss": 0.2081,
|
| 1839 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1840 |
+
"rewards/chosen": -0.30042386054992676,
|
| 1841 |
+
"rewards/margins": 0.20652098953723907,
|
| 1842 |
+
"rewards/rejected": -0.5069448947906494,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": 0.13469955325126648,
|
| 1849 |
+
"logits/rejected": 0.26009881496429443,
|
| 1850 |
+
"logps/chosen": -700.5491943359375,
|
| 1851 |
+
"logps/rejected": -826.0719604492188,
|
| 1852 |
+
"loss": 0.208,
|
| 1853 |
+
"rewards/accuracies": 0.75,
|
| 1854 |
+
"rewards/chosen": -0.3267166316509247,
|
| 1855 |
+
"rewards/margins": 0.2262444794178009,
|
| 1856 |
+
"rewards/rejected": -0.5529611706733704,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": 0.12177290767431259,
|
| 1863 |
+
"logits/rejected": 0.23323854804039001,
|
| 1864 |
+
"logps/chosen": -655.70849609375,
|
| 1865 |
+
"logps/rejected": -841.9342041015625,
|
| 1866 |
+
"loss": 0.1949,
|
| 1867 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1868 |
+
"rewards/chosen": -0.3228956162929535,
|
| 1869 |
+
"rewards/margins": 0.23238658905029297,
|
| 1870 |
+
"rewards/rejected": -0.5552822947502136,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": 0.13625140488147736,
|
| 1877 |
+
"logits/rejected": 0.2116333544254303,
|
| 1878 |
+
"logps/chosen": -680.4044799804688,
|
| 1879 |
+
"logps/rejected": -844.9688720703125,
|
| 1880 |
+
"loss": 0.2145,
|
| 1881 |
+
"rewards/accuracies": 0.75,
|
| 1882 |
+
"rewards/chosen": -0.3188444972038269,
|
| 1883 |
+
"rewards/margins": 0.22850990295410156,
|
| 1884 |
+
"rewards/rejected": -0.5473544001579285,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": 0.10103823244571686,
|
| 1891 |
+
"logits/rejected": 0.19432368874549866,
|
| 1892 |
+
"logps/chosen": -624.4705810546875,
|
| 1893 |
+
"logps/rejected": -799.0113525390625,
|
| 1894 |
+
"loss": 0.2225,
|
| 1895 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1896 |
+
"rewards/chosen": -0.2993714213371277,
|
| 1897 |
+
"rewards/margins": 0.21414069831371307,
|
| 1898 |
+
"rewards/rejected": -0.513512134552002,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": 0.16599547863006592,
|
| 1905 |
+
"logits/rejected": 0.23224572837352753,
|
| 1906 |
+
"logps/chosen": -686.8082275390625,
|
| 1907 |
+
"logps/rejected": -823.6770629882812,
|
| 1908 |
+
"loss": 0.2035,
|
| 1909 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1910 |
+
"rewards/chosen": -0.30449575185775757,
|
| 1911 |
+
"rewards/margins": 0.21346712112426758,
|
| 1912 |
+
"rewards/rejected": -0.5179629325866699,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": 0.11574041843414307,
|
| 1919 |
+
"logits/rejected": 0.1864078789949417,
|
| 1920 |
+
"logps/chosen": -661.083984375,
|
| 1921 |
+
"logps/rejected": -803.5848999023438,
|
| 1922 |
+
"loss": 0.2521,
|
| 1923 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1924 |
+
"rewards/chosen": -0.3295978903770447,
|
| 1925 |
+
"rewards/margins": 0.16920098662376404,
|
| 1926 |
+
"rewards/rejected": -0.4987989068031311,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": 0.1372244954109192,
|
| 1933 |
+
"logits/rejected": 0.2742239534854889,
|
| 1934 |
+
"logps/chosen": -652.0556640625,
|
| 1935 |
+
"logps/rejected": -803.6484375,
|
| 1936 |
+
"loss": 0.2306,
|
| 1937 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1938 |
+
"rewards/chosen": -0.30462098121643066,
|
| 1939 |
+
"rewards/margins": 0.20189952850341797,
|
| 1940 |
+
"rewards/rejected": -0.5065204501152039,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": 0.18852971494197845,
|
| 1947 |
+
"logits/rejected": 0.26183754205703735,
|
| 1948 |
+
"logps/chosen": -696.4068603515625,
|
| 1949 |
+
"logps/rejected": -802.4880981445312,
|
| 1950 |
+
"loss": 0.2703,
|
| 1951 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1952 |
+
"rewards/chosen": -0.32309865951538086,
|
| 1953 |
+
"rewards/margins": 0.1942833513021469,
|
| 1954 |
+
"rewards/rejected": -0.517382025718689,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": 0.18374116718769073,
|
| 1961 |
+
"logits/rejected": 0.23104730248451233,
|
| 1962 |
+
"logps/chosen": -661.356201171875,
|
| 1963 |
+
"logps/rejected": -787.6057739257812,
|
| 1964 |
+
"loss": 0.224,
|
| 1965 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1966 |
+
"rewards/chosen": -0.30247530341148376,
|
| 1967 |
+
"rewards/margins": 0.20218057930469513,
|
| 1968 |
+
"rewards/rejected": -0.5046559572219849,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": 0.18678037822246552,
|
| 1975 |
+
"logits/rejected": 0.3186245560646057,
|
| 1976 |
+
"logps/chosen": -632.1265869140625,
|
| 1977 |
+
"logps/rejected": -761.0514526367188,
|
| 1978 |
+
"loss": 0.2275,
|
| 1979 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1980 |
+
"rewards/chosen": -0.2909912168979645,
|
| 1981 |
+
"rewards/margins": 0.19340907037258148,
|
| 1982 |
+
"rewards/rejected": -0.48440033197402954,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": 0.14555346965789795,
|
| 1989 |
+
"logits/rejected": 0.2179187834262848,
|
| 1990 |
+
"logps/chosen": -666.7107543945312,
|
| 1991 |
+
"logps/rejected": -776.0972900390625,
|
| 1992 |
+
"loss": 0.2247,
|
| 1993 |
+
"rewards/accuracies": 0.75,
|
| 1994 |
+
"rewards/chosen": -0.3142651319503784,
|
| 1995 |
+
"rewards/margins": 0.18122203648090363,
|
| 1996 |
+
"rewards/rejected": -0.4954872131347656,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": 0.10284000635147095,
|
| 2003 |
+
"logits/rejected": 0.24823495745658875,
|
| 2004 |
+
"logps/chosen": -654.6766357421875,
|
| 2005 |
+
"logps/rejected": -778.5437622070312,
|
| 2006 |
+
"loss": 0.2153,
|
| 2007 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2008 |
+
"rewards/chosen": -0.289842426776886,
|
| 2009 |
+
"rewards/margins": 0.20343871414661407,
|
| 2010 |
+
"rewards/rejected": -0.49328118562698364,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": 0.16312912106513977,
|
| 2017 |
+
"logits/rejected": 0.21963107585906982,
|
| 2018 |
+
"logps/chosen": -632.3480834960938,
|
| 2019 |
+
"logps/rejected": -775.2318115234375,
|
| 2020 |
+
"loss": 0.2299,
|
| 2021 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2022 |
+
"rewards/chosen": -0.30911892652511597,
|
| 2023 |
+
"rewards/margins": 0.1682128757238388,
|
| 2024 |
+
"rewards/rejected": -0.4773317873477936,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": 0.14603514969348907,
|
| 2031 |
+
"logits/rejected": 0.25196802616119385,
|
| 2032 |
+
"logps/chosen": -642.275390625,
|
| 2033 |
+
"logps/rejected": -800.051513671875,
|
| 2034 |
+
"loss": 0.234,
|
| 2035 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2036 |
+
"rewards/chosen": -0.3225029408931732,
|
| 2037 |
+
"rewards/margins": 0.20271165668964386,
|
| 2038 |
+
"rewards/rejected": -0.5252145528793335,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": 0.1552133560180664,
|
| 2045 |
+
"logits/rejected": 0.2241334468126297,
|
| 2046 |
+
"logps/chosen": -628.1038818359375,
|
| 2047 |
+
"logps/rejected": -822.3765869140625,
|
| 2048 |
+
"loss": 0.1891,
|
| 2049 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2050 |
+
"rewards/chosen": -0.3023911118507385,
|
| 2051 |
+
"rewards/margins": 0.23453156650066376,
|
| 2052 |
+
"rewards/rejected": -0.5369226932525635,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": 0.15086951851844788,
|
| 2059 |
+
"logits/rejected": 0.25160127878189087,
|
| 2060 |
+
"logps/chosen": -729.95947265625,
|
| 2061 |
+
"logps/rejected": -846.2911987304688,
|
| 2062 |
+
"loss": 0.1995,
|
| 2063 |
+
"rewards/accuracies": 0.78125,
|
| 2064 |
+
"rewards/chosen": -0.3416779637336731,
|
| 2065 |
+
"rewards/margins": 0.20796218514442444,
|
| 2066 |
+
"rewards/rejected": -0.5496400594711304,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": 0.13389447331428528,
|
| 2073 |
+
"logits/rejected": 0.1718115508556366,
|
| 2074 |
+
"logps/chosen": -662.325927734375,
|
| 2075 |
+
"logps/rejected": -822.61181640625,
|
| 2076 |
+
"loss": 0.2358,
|
| 2077 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2078 |
+
"rewards/chosen": -0.3139615058898926,
|
| 2079 |
+
"rewards/margins": 0.21937116980552673,
|
| 2080 |
+
"rewards/rejected": -0.5333326458930969,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": 0.13355755805969238,
|
| 2087 |
+
"logits/rejected": 0.24505715072155,
|
| 2088 |
+
"logps/chosen": -674.4129638671875,
|
| 2089 |
+
"logps/rejected": -807.907470703125,
|
| 2090 |
+
"loss": 0.2259,
|
| 2091 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2092 |
+
"rewards/chosen": -0.3266414999961853,
|
| 2093 |
+
"rewards/margins": 0.20114055275917053,
|
| 2094 |
+
"rewards/rejected": -0.5277820825576782,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": 0.17101332545280457,
|
| 2101 |
+
"logits/rejected": 0.24388432502746582,
|
| 2102 |
+
"logps/chosen": -667.0880126953125,
|
| 2103 |
+
"logps/rejected": -843.1787109375,
|
| 2104 |
+
"loss": 0.2001,
|
| 2105 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2106 |
+
"rewards/chosen": -0.31553584337234497,
|
| 2107 |
+
"rewards/margins": 0.22510071098804474,
|
| 2108 |
+
"rewards/rejected": -0.5406365394592285,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": 0.1403154879808426,
|
| 2115 |
+
"logits/rejected": 0.1944664716720581,
|
| 2116 |
+
"logps/chosen": -611.7420654296875,
|
| 2117 |
+
"logps/rejected": -802.8869018554688,
|
| 2118 |
+
"loss": 0.1929,
|
| 2119 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2120 |
+
"rewards/chosen": -0.3096386790275574,
|
| 2121 |
+
"rewards/margins": 0.22140173614025116,
|
| 2122 |
+
"rewards/rejected": -0.531040370464325,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": 0.13102367520332336,
|
| 2129 |
+
"logits/rejected": 0.20809051394462585,
|
| 2130 |
+
"logps/chosen": -669.8289794921875,
|
| 2131 |
+
"logps/rejected": -821.7249145507812,
|
| 2132 |
+
"loss": 0.2066,
|
| 2133 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2134 |
+
"rewards/chosen": -0.2995157837867737,
|
| 2135 |
+
"rewards/margins": 0.2382737696170807,
|
| 2136 |
+
"rewards/rejected": -0.5377895832061768,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": 0.16256758570671082,
|
| 2143 |
+
"logits/rejected": 0.2884465157985687,
|
| 2144 |
+
"logps/chosen": -657.072021484375,
|
| 2145 |
+
"logps/rejected": -821.6876220703125,
|
| 2146 |
+
"loss": 0.2189,
|
| 2147 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2148 |
+
"rewards/chosen": -0.30884090065956116,
|
| 2149 |
+
"rewards/margins": 0.22088280320167542,
|
| 2150 |
+
"rewards/rejected": -0.5297237634658813,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": 0.1519722193479538,
|
| 2157 |
+
"logits/rejected": 0.2986641526222229,
|
| 2158 |
+
"logps/chosen": -695.6591796875,
|
| 2159 |
+
"logps/rejected": -865.2161865234375,
|
| 2160 |
+
"loss": 0.2069,
|
| 2161 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2162 |
+
"rewards/chosen": -0.33254241943359375,
|
| 2163 |
+
"rewards/margins": 0.23650801181793213,
|
| 2164 |
+
"rewards/rejected": -0.5690504312515259,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": 0.1198592409491539,
|
| 2171 |
+
"logits/rejected": 0.24108009040355682,
|
| 2172 |
+
"logps/chosen": -657.8306274414062,
|
| 2173 |
+
"logps/rejected": -859.29833984375,
|
| 2174 |
+
"loss": 0.2173,
|
| 2175 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2176 |
+
"rewards/chosen": -0.31234902143478394,
|
| 2177 |
+
"rewards/margins": 0.2416820079088211,
|
| 2178 |
+
"rewards/rejected": -0.5540310740470886,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": 0.15342529118061066,
|
| 2185 |
+
"logits/rejected": 0.21858489513397217,
|
| 2186 |
+
"logps/chosen": -640.5154418945312,
|
| 2187 |
+
"logps/rejected": -774.4490966796875,
|
| 2188 |
+
"loss": 0.2209,
|
| 2189 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2190 |
+
"rewards/chosen": -0.3267766833305359,
|
| 2191 |
+
"rewards/margins": 0.19230851531028748,
|
| 2192 |
+
"rewards/rejected": -0.519085168838501,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": 0.18993167579174042,
|
| 2199 |
+
"logits/rejected": 0.26399049162864685,
|
| 2200 |
+
"logps/chosen": -640.939453125,
|
| 2201 |
+
"logps/rejected": -825.0241088867188,
|
| 2202 |
+
"loss": 0.2353,
|
| 2203 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 2204 |
+
"rewards/chosen": -0.3261680603027344,
|
| 2205 |
+
"rewards/margins": 0.19224853813648224,
|
| 2206 |
+
"rewards/rejected": -0.5184165835380554,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": 0.148400217294693,
|
| 2213 |
+
"logits/rejected": 0.22420552372932434,
|
| 2214 |
+
"logps/chosen": -638.9559936523438,
|
| 2215 |
+
"logps/rejected": -800.7708129882812,
|
| 2216 |
+
"loss": 0.1952,
|
| 2217 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2218 |
+
"rewards/chosen": -0.30330848693847656,
|
| 2219 |
+
"rewards/margins": 0.22106847167015076,
|
| 2220 |
+
"rewards/rejected": -0.5243769884109497,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": 0.18423089385032654,
|
| 2227 |
+
"logits/rejected": 0.2459380328655243,
|
| 2228 |
+
"logps/chosen": -680.0947875976562,
|
| 2229 |
+
"logps/rejected": -856.1446533203125,
|
| 2230 |
+
"loss": 0.2004,
|
| 2231 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2232 |
+
"rewards/chosen": -0.3225480914115906,
|
| 2233 |
+
"rewards/margins": 0.2401798963546753,
|
| 2234 |
+
"rewards/rejected": -0.5627279281616211,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": 0.1533311903476715,
|
| 2241 |
+
"logits/rejected": 0.20948585867881775,
|
| 2242 |
+
"logps/chosen": -651.2598876953125,
|
| 2243 |
+
"logps/rejected": -795.5108032226562,
|
| 2244 |
+
"loss": 0.2182,
|
| 2245 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2246 |
+
"rewards/chosen": -0.3288353979587555,
|
| 2247 |
+
"rewards/margins": 0.18383339047431946,
|
| 2248 |
+
"rewards/rejected": -0.512668788433075,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": 0.1523989737033844,
|
| 2255 |
+
"logits/rejected": 0.24100735783576965,
|
| 2256 |
+
"logps/chosen": -618.7085571289062,
|
| 2257 |
+
"logps/rejected": -805.9244995117188,
|
| 2258 |
+
"loss": 0.1826,
|
| 2259 |
+
"rewards/accuracies": 0.75,
|
| 2260 |
+
"rewards/chosen": -0.29542338848114014,
|
| 2261 |
+
"rewards/margins": 0.22522738575935364,
|
| 2262 |
+
"rewards/rejected": -0.5206507444381714,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": 0.1278158277273178,
|
| 2269 |
+
"logits/rejected": 0.22139263153076172,
|
| 2270 |
+
"logps/chosen": -732.3717041015625,
|
| 2271 |
+
"logps/rejected": -855.8250732421875,
|
| 2272 |
+
"loss": 0.2259,
|
| 2273 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2274 |
+
"rewards/chosen": -0.3528819680213928,
|
| 2275 |
+
"rewards/margins": 0.20918047428131104,
|
| 2276 |
+
"rewards/rejected": -0.5620623826980591,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": 0.14292459189891815,
|
| 2283 |
+
"logits/rejected": 0.30465906858444214,
|
| 2284 |
+
"logps/chosen": -667.1749267578125,
|
| 2285 |
+
"logps/rejected": -841.5711669921875,
|
| 2286 |
+
"loss": 0.1826,
|
| 2287 |
+
"rewards/accuracies": 0.78125,
|
| 2288 |
+
"rewards/chosen": -0.3154456317424774,
|
| 2289 |
+
"rewards/margins": 0.2273203581571579,
|
| 2290 |
+
"rewards/rejected": -0.5427660346031189,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": 0.16036184132099152,
|
| 2297 |
+
"logits/rejected": 0.2627103924751282,
|
| 2298 |
+
"logps/chosen": -683.5515747070312,
|
| 2299 |
+
"logps/rejected": -796.56787109375,
|
| 2300 |
+
"loss": 0.2053,
|
| 2301 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2302 |
+
"rewards/chosen": -0.32863935828208923,
|
| 2303 |
+
"rewards/margins": 0.201740100979805,
|
| 2304 |
+
"rewards/rejected": -0.5303794741630554,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": 0.10556507110595703,
|
| 2311 |
+
"logits/rejected": 0.19262662529945374,
|
| 2312 |
+
"logps/chosen": -708.3388671875,
|
| 2313 |
+
"logps/rejected": -892.02197265625,
|
| 2314 |
+
"loss": 0.2239,
|
| 2315 |
+
"rewards/accuracies": 0.78125,
|
| 2316 |
+
"rewards/chosen": -0.34648841619491577,
|
| 2317 |
+
"rewards/margins": 0.2360268384218216,
|
| 2318 |
+
"rewards/rejected": -0.582515299320221,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": 0.13623256981372833,
|
| 2325 |
+
"logits/rejected": 0.2520672678947449,
|
| 2326 |
+
"logps/chosen": -698.7113037109375,
|
| 2327 |
+
"logps/rejected": -843.6485595703125,
|
| 2328 |
+
"loss": 0.2044,
|
| 2329 |
+
"rewards/accuracies": 0.731249988079071,
|
| 2330 |
+
"rewards/chosen": -0.350619375705719,
|
| 2331 |
+
"rewards/margins": 0.2033306360244751,
|
| 2332 |
+
"rewards/rejected": -0.5539500117301941,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": 0.12394211441278458,
|
| 2339 |
+
"logits/rejected": 0.255685418844223,
|
| 2340 |
+
"logps/chosen": -701.68017578125,
|
| 2341 |
+
"logps/rejected": -891.2081909179688,
|
| 2342 |
+
"loss": 0.2145,
|
| 2343 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2344 |
+
"rewards/chosen": -0.3482310175895691,
|
| 2345 |
+
"rewards/margins": 0.23429682850837708,
|
| 2346 |
+
"rewards/rejected": -0.5825279355049133,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": 0.1238374263048172,
|
| 2353 |
+
"logits/rejected": 0.23963268101215363,
|
| 2354 |
+
"logps/chosen": -683.5324096679688,
|
| 2355 |
+
"logps/rejected": -842.0015869140625,
|
| 2356 |
+
"loss": 0.2257,
|
| 2357 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 2358 |
+
"rewards/chosen": -0.31508007645606995,
|
| 2359 |
+
"rewards/margins": 0.2424265444278717,
|
| 2360 |
+
"rewards/rejected": -0.5575065612792969,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": 0.1542249619960785,
|
| 2367 |
+
"logits/rejected": 0.26766401529312134,
|
| 2368 |
+
"logps/chosen": -751.26171875,
|
| 2369 |
+
"logps/rejected": -901.7872924804688,
|
| 2370 |
+
"loss": 0.1951,
|
| 2371 |
+
"rewards/accuracies": 0.75,
|
| 2372 |
+
"rewards/chosen": -0.35173672437667847,
|
| 2373 |
+
"rewards/margins": 0.22757640480995178,
|
| 2374 |
+
"rewards/rejected": -0.5793130993843079,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": 0.12692458927631378,
|
| 2381 |
+
"logits/rejected": 0.2118302285671234,
|
| 2382 |
+
"logps/chosen": -675.017578125,
|
| 2383 |
+
"logps/rejected": -829.9061279296875,
|
| 2384 |
+
"loss": 0.2303,
|
| 2385 |
+
"rewards/accuracies": 0.699999988079071,
|
| 2386 |
+
"rewards/chosen": -0.33988887071609497,
|
| 2387 |
+
"rewards/margins": 0.19631198048591614,
|
| 2388 |
+
"rewards/rejected": -0.5362008810043335,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": 0.11164776980876923,
|
| 2395 |
+
"logits/rejected": 0.21648769080638885,
|
| 2396 |
+
"logps/chosen": -657.6282958984375,
|
| 2397 |
+
"logps/rejected": -799.0164794921875,
|
| 2398 |
+
"loss": 0.192,
|
| 2399 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2400 |
+
"rewards/chosen": -0.32347801327705383,
|
| 2401 |
+
"rewards/margins": 0.21190226078033447,
|
| 2402 |
+
"rewards/rejected": -0.5353802442550659,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": 0.0844898596405983,
|
| 2409 |
+
"logits/rejected": 0.2031726837158203,
|
| 2410 |
+
"logps/chosen": -725.109619140625,
|
| 2411 |
+
"logps/rejected": -869.9738159179688,
|
| 2412 |
+
"loss": 0.2053,
|
| 2413 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2414 |
+
"rewards/chosen": -0.35323506593704224,
|
| 2415 |
+
"rewards/margins": 0.2272004634141922,
|
| 2416 |
+
"rewards/rejected": -0.5804354548454285,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": 0.16333475708961487,
|
| 2423 |
+
"logits/rejected": 0.22125931084156036,
|
| 2424 |
+
"logps/chosen": -669.9171752929688,
|
| 2425 |
+
"logps/rejected": -802.5113525390625,
|
| 2426 |
+
"loss": 0.232,
|
| 2427 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2428 |
+
"rewards/chosen": -0.3276098072528839,
|
| 2429 |
+
"rewards/margins": 0.21911415457725525,
|
| 2430 |
+
"rewards/rejected": -0.5467239618301392,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": 0.15154321491718292,
|
| 2437 |
+
"logits/rejected": 0.252513587474823,
|
| 2438 |
+
"logps/chosen": -668.7503662109375,
|
| 2439 |
+
"logps/rejected": -801.6619262695312,
|
| 2440 |
+
"loss": 0.2252,
|
| 2441 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2442 |
+
"rewards/chosen": -0.33079949021339417,
|
| 2443 |
+
"rewards/margins": 0.20475859940052032,
|
| 2444 |
+
"rewards/rejected": -0.5355581045150757,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": 0.1299131065607071,
|
| 2451 |
+
"logits/rejected": 0.2569180130958557,
|
| 2452 |
+
"logps/chosen": -691.34228515625,
|
| 2453 |
+
"logps/rejected": -851.5472412109375,
|
| 2454 |
+
"loss": 0.1733,
|
| 2455 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2456 |
+
"rewards/chosen": -0.3316085636615753,
|
| 2457 |
+
"rewards/margins": 0.2289518564939499,
|
| 2458 |
+
"rewards/rejected": -0.5605604648590088,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": 0.15428964793682098,
|
| 2465 |
+
"logits/rejected": 0.30156534910202026,
|
| 2466 |
+
"logps/chosen": -670.6358642578125,
|
| 2467 |
+
"logps/rejected": -829.8116455078125,
|
| 2468 |
+
"loss": 0.2113,
|
| 2469 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2470 |
+
"rewards/chosen": -0.33194589614868164,
|
| 2471 |
+
"rewards/margins": 0.22803179919719696,
|
| 2472 |
+
"rewards/rejected": -0.5599777102470398,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": 0.1505686342716217,
|
| 2479 |
+
"logits/rejected": 0.26538941264152527,
|
| 2480 |
+
"logps/chosen": -700.7206420898438,
|
| 2481 |
+
"logps/rejected": -845.8724365234375,
|
| 2482 |
+
"loss": 0.2174,
|
| 2483 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2484 |
+
"rewards/chosen": -0.33285072445869446,
|
| 2485 |
+
"rewards/margins": 0.22789886593818665,
|
| 2486 |
+
"rewards/rejected": -0.5607496500015259,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": 0.14582636952400208,
|
| 2493 |
+
"logits/rejected": 0.210880845785141,
|
| 2494 |
+
"logps/chosen": -675.3494262695312,
|
| 2495 |
+
"logps/rejected": -822.8538818359375,
|
| 2496 |
+
"loss": 0.1898,
|
| 2497 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 2498 |
+
"rewards/chosen": -0.3319861888885498,
|
| 2499 |
+
"rewards/margins": 0.21374984085559845,
|
| 2500 |
+
"rewards/rejected": -0.5457359552383423,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": 0.09690573811531067,
|
| 2507 |
+
"logits/rejected": 0.21973006427288055,
|
| 2508 |
+
"logps/chosen": -667.906005859375,
|
| 2509 |
+
"logps/rejected": -875.2356567382812,
|
| 2510 |
+
"loss": 0.1945,
|
| 2511 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 2512 |
+
"rewards/chosen": -0.3273436725139618,
|
| 2513 |
+
"rewards/margins": 0.24747705459594727,
|
| 2514 |
+
"rewards/rejected": -0.5748206377029419,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": 0.08470339328050613,
|
| 2521 |
+
"logits/rejected": 0.23671475052833557,
|
| 2522 |
+
"logps/chosen": -656.4951171875,
|
| 2523 |
+
"logps/rejected": -821.2351684570312,
|
| 2524 |
+
"loss": 0.2145,
|
| 2525 |
+
"rewards/accuracies": 0.75,
|
| 2526 |
+
"rewards/chosen": -0.32644474506378174,
|
| 2527 |
+
"rewards/margins": 0.212808296084404,
|
| 2528 |
+
"rewards/rejected": -0.5392531156539917,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": 0.09538368880748749,
|
| 2535 |
+
"logits/rejected": 0.21011042594909668,
|
| 2536 |
+
"logps/chosen": -703.3250732421875,
|
| 2537 |
+
"logps/rejected": -883.3131713867188,
|
| 2538 |
+
"loss": 0.1995,
|
| 2539 |
+
"rewards/accuracies": 0.768750011920929,
|
| 2540 |
+
"rewards/chosen": -0.33553892374038696,
|
| 2541 |
+
"rewards/margins": 0.2493852823972702,
|
| 2542 |
+
"rewards/rejected": -0.5849242210388184,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": 0.1573551446199417,
|
| 2549 |
+
"logits/rejected": 0.2588816285133362,
|
| 2550 |
+
"logps/chosen": -683.0828247070312,
|
| 2551 |
+
"logps/rejected": -843.8508911132812,
|
| 2552 |
+
"loss": 0.2083,
|
| 2553 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2554 |
+
"rewards/chosen": -0.30922335386276245,
|
| 2555 |
+
"rewards/margins": 0.24052074551582336,
|
| 2556 |
+
"rewards/rejected": -0.5497440695762634,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": 0.09812667965888977,
|
| 2563 |
+
"logits/rejected": 0.21138449013233185,
|
| 2564 |
+
"logps/chosen": -694.7268676757812,
|
| 2565 |
+
"logps/rejected": -886.9791870117188,
|
| 2566 |
+
"loss": 0.2094,
|
| 2567 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2568 |
+
"rewards/chosen": -0.34521687030792236,
|
| 2569 |
+
"rewards/margins": 0.23157024383544922,
|
| 2570 |
+
"rewards/rejected": -0.5767871141433716,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": 0.1276710033416748,
|
| 2577 |
+
"logits/rejected": 0.21167734265327454,
|
| 2578 |
+
"logps/chosen": -673.7769775390625,
|
| 2579 |
+
"logps/rejected": -854.2696533203125,
|
| 2580 |
+
"loss": 0.1992,
|
| 2581 |
+
"rewards/accuracies": 0.78125,
|
| 2582 |
+
"rewards/chosen": -0.3254976272583008,
|
| 2583 |
+
"rewards/margins": 0.2494417428970337,
|
| 2584 |
+
"rewards/rejected": -0.5749393701553345,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": 0.11343555152416229,
|
| 2591 |
+
"logits/rejected": 0.25598517060279846,
|
| 2592 |
+
"logps/chosen": -700.44921875,
|
| 2593 |
+
"logps/rejected": -852.5792846679688,
|
| 2594 |
+
"loss": 0.2213,
|
| 2595 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 2596 |
+
"rewards/chosen": -0.3366733491420746,
|
| 2597 |
+
"rewards/margins": 0.21852286159992218,
|
| 2598 |
+
"rewards/rejected": -0.555196225643158,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": 0.15132495760917664,
|
| 2605 |
+
"logits/rejected": 0.24779316782951355,
|
| 2606 |
+
"logps/chosen": -710.2337646484375,
|
| 2607 |
+
"logps/rejected": -898.6566162109375,
|
| 2608 |
+
"loss": 0.2162,
|
| 2609 |
+
"rewards/accuracies": 0.762499988079071,
|
| 2610 |
+
"rewards/chosen": -0.3569861650466919,
|
| 2611 |
+
"rewards/margins": 0.23351311683654785,
|
| 2612 |
+
"rewards/rejected": -0.5904992818832397,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": 0.1191195398569107,
|
| 2619 |
+
"logits/rejected": 0.2252669632434845,
|
| 2620 |
+
"logps/chosen": -693.7659912109375,
|
| 2621 |
+
"logps/rejected": -813.2882690429688,
|
| 2622 |
+
"loss": 0.239,
|
| 2623 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2624 |
+
"rewards/chosen": -0.34295856952667236,
|
| 2625 |
+
"rewards/margins": 0.19307160377502441,
|
| 2626 |
+
"rewards/rejected": -0.5360301733016968,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": 0.10991505533456802,
|
| 2633 |
+
"logits/rejected": 0.2280399352312088,
|
| 2634 |
+
"logps/chosen": -677.8359985351562,
|
| 2635 |
+
"logps/rejected": -832.2960815429688,
|
| 2636 |
+
"loss": 0.234,
|
| 2637 |
+
"rewards/accuracies": 0.675000011920929,
|
| 2638 |
+
"rewards/chosen": -0.34933480620384216,
|
| 2639 |
+
"rewards/margins": 0.19008032977581024,
|
| 2640 |
+
"rewards/rejected": -0.539415180683136,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 0.2330256977081299,
|
| 2648 |
+
"train_runtime": 17175.1012,
|
| 2649 |
+
"train_samples_per_second": 1.747,
|
| 2650 |
+
"train_steps_per_second": 0.109
|
| 2651 |
+
}
|
| 2652 |
+
],
|
| 2653 |
+
"logging_steps": 10,
|
| 2654 |
+
"max_steps": 1875,
|
| 2655 |
+
"num_input_tokens_seen": 0,
|
| 2656 |
+
"num_train_epochs": 1,
|
| 2657 |
+
"save_steps": 100,
|
| 2658 |
+
"total_flos": 0.0,
|
| 2659 |
+
"train_batch_size": 4,
|
| 2660 |
+
"trial_name": null,
|
| 2661 |
+
"trial_params": null
|
| 2662 |
+
}
|