Commit
•
0329836
1
Parent(s):
45b3b22
Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May15_00-56-30_gpu4-119-5/events.out.tfevents.1715698744.gpu4-119-5.2140848.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +2662 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 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-renew-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-renew-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 sha256:71c670a5a3301ed8a0295eb00155c41fbf94150e6f50d6e0a58080e194de290f
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.579099040222168,
|
| 4 |
+
"train_runtime": 16673.7788,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.799,
|
| 7 |
+
"train_steps_per_second": 0.112
|
| 8 |
+
}
|
runs/May15_00-56-30_gpu4-119-5/events.out.tfevents.1715698744.gpu4-119-5.2140848.0
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 sha256:320ba22a86b0fbec61fa241a5923159f12add3b3966725eef0a4a0ac2b2a942e
|
| 3 |
+
size 117457
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.579099040222168,
|
| 4 |
+
"train_runtime": 16673.7788,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 1.799,
|
| 7 |
+
"train_steps_per_second": 0.112
|
| 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": 0.04955034703016281,
|
| 15 |
+
"logits/rejected": 0.2081322818994522,
|
| 16 |
+
"logps/chosen": -399.2755126953125,
|
| 17 |
+
"logps/rejected": -356.2502136230469,
|
| 18 |
+
"loss": 1.8388,
|
| 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": 0.12051750719547272,
|
| 29 |
+
"logits/rejected": 0.17576032876968384,
|
| 30 |
+
"logps/chosen": -352.8992919921875,
|
| 31 |
+
"logps/rejected": -348.6365966796875,
|
| 32 |
+
"loss": 2.1871,
|
| 33 |
+
"rewards/accuracies": 0.3888888955116272,
|
| 34 |
+
"rewards/chosen": 3.012115485034883e-05,
|
| 35 |
+
"rewards/margins": -1.0702900908654556e-05,
|
| 36 |
+
"rewards/rejected": 4.0824070310918614e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 5.319148936170213e-07,
|
| 42 |
+
"logits/chosen": 0.12970615923404694,
|
| 43 |
+
"logits/rejected": 0.25619959831237793,
|
| 44 |
+
"logps/chosen": -330.56390380859375,
|
| 45 |
+
"logps/rejected": -314.9967346191406,
|
| 46 |
+
"loss": 2.1076,
|
| 47 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 48 |
+
"rewards/chosen": -1.1562701729417313e-05,
|
| 49 |
+
"rewards/margins": 1.4026712960912846e-05,
|
| 50 |
+
"rewards/rejected": -2.558941559982486e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 7.97872340425532e-07,
|
| 56 |
+
"logits/chosen": 0.0827835202217102,
|
| 57 |
+
"logits/rejected": 0.23312167823314667,
|
| 58 |
+
"logps/chosen": -356.8667907714844,
|
| 59 |
+
"logps/rejected": -348.5129089355469,
|
| 60 |
+
"loss": 2.0534,
|
| 61 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 62 |
+
"rewards/chosen": 8.046765287872404e-05,
|
| 63 |
+
"rewards/margins": 0.00017265856149606407,
|
| 64 |
+
"rewards/rejected": -9.21908940654248e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 70 |
+
"logits/chosen": 0.15581126511096954,
|
| 71 |
+
"logits/rejected": 0.2709190249443054,
|
| 72 |
+
"logps/chosen": -379.3042907714844,
|
| 73 |
+
"logps/rejected": -344.07720947265625,
|
| 74 |
+
"loss": 2.1496,
|
| 75 |
+
"rewards/accuracies": 0.41874998807907104,
|
| 76 |
+
"rewards/chosen": -7.353671389864758e-05,
|
| 77 |
+
"rewards/margins": -1.741977030178532e-05,
|
| 78 |
+
"rewards/rejected": -5.6116947234841064e-05,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 84 |
+
"logits/chosen": 0.14546141028404236,
|
| 85 |
+
"logits/rejected": 0.1901441365480423,
|
| 86 |
+
"logps/chosen": -344.20733642578125,
|
| 87 |
+
"logps/rejected": -325.073974609375,
|
| 88 |
+
"loss": 2.2903,
|
| 89 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 90 |
+
"rewards/chosen": -2.2368712961906567e-05,
|
| 91 |
+
"rewards/margins": 4.947663546772674e-05,
|
| 92 |
+
"rewards/rejected": -7.184535206761211e-05,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 1.595744680851064e-06,
|
| 98 |
+
"logits/chosen": 0.09698285907506943,
|
| 99 |
+
"logits/rejected": 0.1907365322113037,
|
| 100 |
+
"logps/chosen": -347.95751953125,
|
| 101 |
+
"logps/rejected": -366.4272155761719,
|
| 102 |
+
"loss": 2.2621,
|
| 103 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 104 |
+
"rewards/chosen": -0.00013693059736397117,
|
| 105 |
+
"rewards/margins": 4.145975617575459e-05,
|
| 106 |
+
"rewards/rejected": -0.00017839032807387412,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 112 |
+
"logits/chosen": 0.09873981028795242,
|
| 113 |
+
"logits/rejected": 0.1650334745645523,
|
| 114 |
+
"logps/chosen": -343.1393127441406,
|
| 115 |
+
"logps/rejected": -323.4422912597656,
|
| 116 |
+
"loss": 1.9323,
|
| 117 |
+
"rewards/accuracies": 0.625,
|
| 118 |
+
"rewards/chosen": 0.00018913080566562712,
|
| 119 |
+
"rewards/margins": 0.0006557141896337271,
|
| 120 |
+
"rewards/rejected": -0.0004665833548642695,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 126 |
+
"logits/chosen": 0.04767695814371109,
|
| 127 |
+
"logits/rejected": 0.15447475016117096,
|
| 128 |
+
"logps/chosen": -330.0970764160156,
|
| 129 |
+
"logps/rejected": -345.8455810546875,
|
| 130 |
+
"loss": 2.2122,
|
| 131 |
+
"rewards/accuracies": 0.512499988079071,
|
| 132 |
+
"rewards/chosen": -0.00011976109817624092,
|
| 133 |
+
"rewards/margins": 0.00030935637187212706,
|
| 134 |
+
"rewards/rejected": -0.0004291174409445375,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 2.393617021276596e-06,
|
| 140 |
+
"logits/chosen": 0.07230930775403976,
|
| 141 |
+
"logits/rejected": 0.15430572628974915,
|
| 142 |
+
"logps/chosen": -316.2431335449219,
|
| 143 |
+
"logps/rejected": -347.070556640625,
|
| 144 |
+
"loss": 2.0968,
|
| 145 |
+
"rewards/accuracies": 0.612500011920929,
|
| 146 |
+
"rewards/chosen": 0.00011777224426623434,
|
| 147 |
+
"rewards/margins": 0.00068097427720204,
|
| 148 |
+
"rewards/rejected": -0.0005632020765915513,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 154 |
+
"logits/chosen": 0.16333770751953125,
|
| 155 |
+
"logits/rejected": 0.23844099044799805,
|
| 156 |
+
"logps/chosen": -365.7076110839844,
|
| 157 |
+
"logps/rejected": -356.7385559082031,
|
| 158 |
+
"loss": 2.0913,
|
| 159 |
+
"rewards/accuracies": 0.612500011920929,
|
| 160 |
+
"rewards/chosen": 0.00023379763297270983,
|
| 161 |
+
"rewards/margins": 0.001117090112529695,
|
| 162 |
+
"rewards/rejected": -0.0008832925814203918,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 168 |
+
"logits/chosen": 0.15442657470703125,
|
| 169 |
+
"logits/rejected": 0.2177698314189911,
|
| 170 |
+
"logps/chosen": -325.3774719238281,
|
| 171 |
+
"logps/rejected": -331.230224609375,
|
| 172 |
+
"loss": 2.194,
|
| 173 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 174 |
+
"rewards/chosen": 0.0007118202047422528,
|
| 175 |
+
"rewards/margins": 0.002311364747583866,
|
| 176 |
+
"rewards/rejected": -0.0015995446592569351,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 3.191489361702128e-06,
|
| 182 |
+
"logits/chosen": 0.1042538657784462,
|
| 183 |
+
"logits/rejected": 0.22217731177806854,
|
| 184 |
+
"logps/chosen": -385.71258544921875,
|
| 185 |
+
"logps/rejected": -346.8166198730469,
|
| 186 |
+
"loss": 2.1461,
|
| 187 |
+
"rewards/accuracies": 0.675000011920929,
|
| 188 |
+
"rewards/chosen": 0.00048388572758994997,
|
| 189 |
+
"rewards/margins": 0.0024064378812909126,
|
| 190 |
+
"rewards/rejected": -0.001922552241012454,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07,
|
| 195 |
+
"learning_rate": 3.457446808510639e-06,
|
| 196 |
+
"logits/chosen": 0.11709433794021606,
|
| 197 |
+
"logits/rejected": 0.1892680823802948,
|
| 198 |
+
"logps/chosen": -366.34527587890625,
|
| 199 |
+
"logps/rejected": -335.19305419921875,
|
| 200 |
+
"loss": 2.0647,
|
| 201 |
+
"rewards/accuracies": 0.643750011920929,
|
| 202 |
+
"rewards/chosen": 0.0013805570779368281,
|
| 203 |
+
"rewards/margins": 0.0054556322284042835,
|
| 204 |
+
"rewards/rejected": -0.004075074568390846,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07,
|
| 209 |
+
"learning_rate": 3.723404255319149e-06,
|
| 210 |
+
"logits/chosen": 0.08869902789592743,
|
| 211 |
+
"logits/rejected": 0.1678289771080017,
|
| 212 |
+
"logps/chosen": -340.19000244140625,
|
| 213 |
+
"logps/rejected": -347.8067932128906,
|
| 214 |
+
"loss": 2.1245,
|
| 215 |
+
"rewards/accuracies": 0.71875,
|
| 216 |
+
"rewards/chosen": 0.00034795800456777215,
|
| 217 |
+
"rewards/margins": 0.007005759980529547,
|
| 218 |
+
"rewards/rejected": -0.006657801568508148,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 3.98936170212766e-06,
|
| 224 |
+
"logits/chosen": 0.09667147696018219,
|
| 225 |
+
"logits/rejected": 0.17873503267765045,
|
| 226 |
+
"logps/chosen": -348.5378723144531,
|
| 227 |
+
"logps/rejected": -354.625732421875,
|
| 228 |
+
"loss": 2.0674,
|
| 229 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 230 |
+
"rewards/chosen": -0.002576244994997978,
|
| 231 |
+
"rewards/margins": 0.012314345687627792,
|
| 232 |
+
"rewards/rejected": -0.014890591613948345,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09,
|
| 237 |
+
"learning_rate": 4.255319148936171e-06,
|
| 238 |
+
"logits/chosen": 0.11646904796361923,
|
| 239 |
+
"logits/rejected": 0.19791707396507263,
|
| 240 |
+
"logps/chosen": -371.9278869628906,
|
| 241 |
+
"logps/rejected": -352.6597595214844,
|
| 242 |
+
"loss": 2.0031,
|
| 243 |
+
"rewards/accuracies": 0.675000011920929,
|
| 244 |
+
"rewards/chosen": -0.017293656244874,
|
| 245 |
+
"rewards/margins": 0.017039310187101364,
|
| 246 |
+
"rewards/rejected": -0.034332968294620514,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09,
|
| 251 |
+
"learning_rate": 4.521276595744681e-06,
|
| 252 |
+
"logits/chosen": 0.0863865464925766,
|
| 253 |
+
"logits/rejected": 0.13875712454319,
|
| 254 |
+
"logps/chosen": -359.6827697753906,
|
| 255 |
+
"logps/rejected": -397.03314208984375,
|
| 256 |
+
"loss": 2.0383,
|
| 257 |
+
"rewards/accuracies": 0.71875,
|
| 258 |
+
"rewards/chosen": -0.04616696387529373,
|
| 259 |
+
"rewards/margins": 0.033675678074359894,
|
| 260 |
+
"rewards/rejected": -0.07984264194965363,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 4.787234042553192e-06,
|
| 266 |
+
"logits/chosen": 0.1687321960926056,
|
| 267 |
+
"logits/rejected": 0.18632039427757263,
|
| 268 |
+
"logps/chosen": -518.4354248046875,
|
| 269 |
+
"logps/rejected": -581.8291625976562,
|
| 270 |
+
"loss": 1.965,
|
| 271 |
+
"rewards/accuracies": 0.637499988079071,
|
| 272 |
+
"rewards/chosen": -0.18014833331108093,
|
| 273 |
+
"rewards/margins": 0.08009239286184311,
|
| 274 |
+
"rewards/rejected": -0.26024070382118225,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1,
|
| 279 |
+
"learning_rate": 4.999982660399688e-06,
|
| 280 |
+
"logits/chosen": 0.1435881406068802,
|
| 281 |
+
"logits/rejected": 0.23430481553077698,
|
| 282 |
+
"logps/chosen": -702.39453125,
|
| 283 |
+
"logps/rejected": -783.1107177734375,
|
| 284 |
+
"loss": 1.9302,
|
| 285 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 286 |
+
"rewards/chosen": -0.3382980227470398,
|
| 287 |
+
"rewards/margins": 0.09362809360027313,
|
| 288 |
+
"rewards/rejected": -0.4319261610507965,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"learning_rate": 4.99937579964398e-06,
|
| 294 |
+
"logits/chosen": 0.208383709192276,
|
| 295 |
+
"logits/rejected": 0.2906993627548218,
|
| 296 |
+
"logps/chosen": -713.2571411132812,
|
| 297 |
+
"logps/rejected": -865.4801635742188,
|
| 298 |
+
"loss": 1.9144,
|
| 299 |
+
"rewards/accuracies": 0.643750011920929,
|
| 300 |
+
"rewards/chosen": -0.37990179657936096,
|
| 301 |
+
"rewards/margins": 0.1499054878950119,
|
| 302 |
+
"rewards/rejected": -0.5298072695732117,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 4.9979021993870645e-06,
|
| 308 |
+
"logits/chosen": 0.3532663583755493,
|
| 309 |
+
"logits/rejected": 0.40125733613967896,
|
| 310 |
+
"logps/chosen": -827.6688232421875,
|
| 311 |
+
"logps/rejected": -1008.0562744140625,
|
| 312 |
+
"loss": 1.9168,
|
| 313 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 314 |
+
"rewards/chosen": -0.48167118430137634,
|
| 315 |
+
"rewards/margins": 0.19706857204437256,
|
| 316 |
+
"rewards/rejected": -0.6787397861480713,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"learning_rate": 4.995562370647553e-06,
|
| 322 |
+
"logits/chosen": 0.26290273666381836,
|
| 323 |
+
"logits/rejected": 0.30596408247947693,
|
| 324 |
+
"logps/chosen": -668.184326171875,
|
| 325 |
+
"logps/rejected": -875.458984375,
|
| 326 |
+
"loss": 1.9675,
|
| 327 |
+
"rewards/accuracies": 0.65625,
|
| 328 |
+
"rewards/chosen": -0.3495655059814453,
|
| 329 |
+
"rewards/margins": 0.21041527390480042,
|
| 330 |
+
"rewards/rejected": -0.5599807500839233,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"learning_rate": 4.992357124836838e-06,
|
| 336 |
+
"logits/chosen": 0.20304854214191437,
|
| 337 |
+
"logits/rejected": 0.3136758804321289,
|
| 338 |
+
"logps/chosen": -769.69775390625,
|
| 339 |
+
"logps/rejected": -896.6029052734375,
|
| 340 |
+
"loss": 1.9428,
|
| 341 |
+
"rewards/accuracies": 0.699999988079071,
|
| 342 |
+
"rewards/chosen": -0.387773334980011,
|
| 343 |
+
"rewards/margins": 0.15167225897312164,
|
| 344 |
+
"rewards/rejected": -0.5394456386566162,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 4.9882875734777044e-06,
|
| 350 |
+
"logits/chosen": 0.1910410374403,
|
| 351 |
+
"logits/rejected": 0.2551349699497223,
|
| 352 |
+
"logps/chosen": -708.0855712890625,
|
| 353 |
+
"logps/rejected": -942.3931884765625,
|
| 354 |
+
"loss": 1.8036,
|
| 355 |
+
"rewards/accuracies": 0.637499988079071,
|
| 356 |
+
"rewards/chosen": -0.38504528999328613,
|
| 357 |
+
"rewards/margins": 0.18461327254772186,
|
| 358 |
+
"rewards/rejected": -0.5696585774421692,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13,
|
| 363 |
+
"learning_rate": 4.983355127818882e-06,
|
| 364 |
+
"logits/chosen": 0.21396322548389435,
|
| 365 |
+
"logits/rejected": 0.2892169654369354,
|
| 366 |
+
"logps/chosen": -857.2903442382812,
|
| 367 |
+
"logps/rejected": -1077.1361083984375,
|
| 368 |
+
"loss": 1.6775,
|
| 369 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 370 |
+
"rewards/chosen": -0.48091378808021545,
|
| 371 |
+
"rewards/margins": 0.24324023723602295,
|
| 372 |
+
"rewards/rejected": -0.7241540551185608,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.14,
|
| 377 |
+
"learning_rate": 4.977561498345639e-06,
|
| 378 |
+
"logits/chosen": 0.24105820059776306,
|
| 379 |
+
"logits/rejected": 0.32143664360046387,
|
| 380 |
+
"logps/chosen": -767.349365234375,
|
| 381 |
+
"logps/rejected": -1007.8854370117188,
|
| 382 |
+
"loss": 1.7354,
|
| 383 |
+
"rewards/accuracies": 0.6875,
|
| 384 |
+
"rewards/chosen": -0.4250938296318054,
|
| 385 |
+
"rewards/margins": 0.24705836176872253,
|
| 386 |
+
"rewards/rejected": -0.6721522212028503,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14,
|
| 391 |
+
"learning_rate": 4.970908694186624e-06,
|
| 392 |
+
"logits/chosen": 0.24902021884918213,
|
| 393 |
+
"logits/rejected": 0.2764545977115631,
|
| 394 |
+
"logps/chosen": -909.8703002929688,
|
| 395 |
+
"logps/rejected": -1201.24560546875,
|
| 396 |
+
"loss": 1.7645,
|
| 397 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 398 |
+
"rewards/chosen": -0.5648880004882812,
|
| 399 |
+
"rewards/margins": 0.3094554543495178,
|
| 400 |
+
"rewards/rejected": -0.8743433952331543,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15,
|
| 405 |
+
"learning_rate": 4.9633990224171305e-06,
|
| 406 |
+
"logits/chosen": 0.22477073967456818,
|
| 407 |
+
"logits/rejected": 0.32122597098350525,
|
| 408 |
+
"logps/chosen": -854.8441162109375,
|
| 409 |
+
"logps/rejected": -1083.2144775390625,
|
| 410 |
+
"loss": 1.9272,
|
| 411 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 412 |
+
"rewards/chosen": -0.492588609457016,
|
| 413 |
+
"rewards/margins": 0.24561519920825958,
|
| 414 |
+
"rewards/rejected": -0.7382038235664368,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15,
|
| 419 |
+
"learning_rate": 4.955035087259046e-06,
|
| 420 |
+
"logits/chosen": 0.24095304310321808,
|
| 421 |
+
"logits/rejected": 0.27735045552253723,
|
| 422 |
+
"logps/chosen": -786.0255737304688,
|
| 423 |
+
"logps/rejected": -907.18603515625,
|
| 424 |
+
"loss": 1.9192,
|
| 425 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 426 |
+
"rewards/chosen": -0.43741363286972046,
|
| 427 |
+
"rewards/margins": 0.15155784785747528,
|
| 428 |
+
"rewards/rejected": -0.5889714956283569,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 4.945819789177756e-06,
|
| 434 |
+
"logits/chosen": 0.28113454580307007,
|
| 435 |
+
"logits/rejected": 0.328742116689682,
|
| 436 |
+
"logps/chosen": -699.2544555664062,
|
| 437 |
+
"logps/rejected": -963.7498168945312,
|
| 438 |
+
"loss": 1.6742,
|
| 439 |
+
"rewards/accuracies": 0.71875,
|
| 440 |
+
"rewards/chosen": -0.35792165994644165,
|
| 441 |
+
"rewards/margins": 0.29106318950653076,
|
| 442 |
+
"rewards/rejected": -0.6489847898483276,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17,
|
| 447 |
+
"learning_rate": 4.935756323876306e-06,
|
| 448 |
+
"logits/chosen": 0.25907808542251587,
|
| 449 |
+
"logits/rejected": 0.32955312728881836,
|
| 450 |
+
"logps/chosen": -888.01416015625,
|
| 451 |
+
"logps/rejected": -1171.78369140625,
|
| 452 |
+
"loss": 1.6716,
|
| 453 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 454 |
+
"rewards/chosen": -0.4973801076412201,
|
| 455 |
+
"rewards/margins": 0.3079432547092438,
|
| 456 |
+
"rewards/rejected": -0.8053233027458191,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.17,
|
| 461 |
+
"learning_rate": 4.924848181187199e-06,
|
| 462 |
+
"logits/chosen": 0.2684496343135834,
|
| 463 |
+
"logits/rejected": 0.32716041803359985,
|
| 464 |
+
"logps/chosen": -976.4813232421875,
|
| 465 |
+
"logps/rejected": -1259.734619140625,
|
| 466 |
+
"loss": 1.7699,
|
| 467 |
+
"rewards/accuracies": 0.706250011920929,
|
| 468 |
+
"rewards/chosen": -0.6323069334030151,
|
| 469 |
+
"rewards/margins": 0.2792579233646393,
|
| 470 |
+
"rewards/rejected": -0.911564826965332,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 4.913099143862173e-06,
|
| 476 |
+
"logits/chosen": 0.23882272839546204,
|
| 477 |
+
"logits/rejected": 0.3363894820213318,
|
| 478 |
+
"logps/chosen": -949.0950927734375,
|
| 479 |
+
"logps/rejected": -1274.9371337890625,
|
| 480 |
+
"loss": 1.5789,
|
| 481 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 482 |
+
"rewards/chosen": -0.5801984667778015,
|
| 483 |
+
"rewards/margins": 0.33727020025253296,
|
| 484 |
+
"rewards/rejected": -0.9174687266349792,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"learning_rate": 4.900513286260416e-06,
|
| 490 |
+
"logits/chosen": 0.21043291687965393,
|
| 491 |
+
"logits/rejected": 0.2558518052101135,
|
| 492 |
+
"logps/chosen": -877.2346801757812,
|
| 493 |
+
"logps/rejected": -1073.109130859375,
|
| 494 |
+
"loss": 2.0442,
|
| 495 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 496 |
+
"rewards/chosen": -0.5416908860206604,
|
| 497 |
+
"rewards/margins": 0.2031005322933197,
|
| 498 |
+
"rewards/rejected": -0.7447915077209473,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19,
|
| 503 |
+
"learning_rate": 4.887094972935645e-06,
|
| 504 |
+
"logits/chosen": 0.16980823874473572,
|
| 505 |
+
"logits/rejected": 0.25876349210739136,
|
| 506 |
+
"logps/chosen": -807.2410888671875,
|
| 507 |
+
"logps/rejected": -1025.34619140625,
|
| 508 |
+
"loss": 1.7629,
|
| 509 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 510 |
+
"rewards/chosen": -0.47985905408859253,
|
| 511 |
+
"rewards/margins": 0.2095312625169754,
|
| 512 |
+
"rewards/rejected": -0.6893904209136963,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 4.87284885712256e-06,
|
| 518 |
+
"logits/chosen": 0.18493933975696564,
|
| 519 |
+
"logits/rejected": 0.2487083226442337,
|
| 520 |
+
"logps/chosen": -851.6658935546875,
|
| 521 |
+
"logps/rejected": -1111.9356689453125,
|
| 522 |
+
"loss": 1.6052,
|
| 523 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 524 |
+
"rewards/chosen": -0.5041731595993042,
|
| 525 |
+
"rewards/margins": 0.2590993344783783,
|
| 526 |
+
"rewards/rejected": -0.7632725834846497,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2,
|
| 531 |
+
"learning_rate": 4.857779879123181e-06,
|
| 532 |
+
"logits/chosen": 0.21949057281017303,
|
| 533 |
+
"logits/rejected": 0.2645294964313507,
|
| 534 |
+
"logps/chosen": -1002.091796875,
|
| 535 |
+
"logps/rejected": -1264.646240234375,
|
| 536 |
+
"loss": 1.8152,
|
| 537 |
+
"rewards/accuracies": 0.668749988079071,
|
| 538 |
+
"rewards/chosen": -0.6552623510360718,
|
| 539 |
+
"rewards/margins": 0.2699270248413086,
|
| 540 |
+
"rewards/rejected": -0.9251893758773804,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2,
|
| 545 |
+
"learning_rate": 4.841893264593643e-06,
|
| 546 |
+
"logits/chosen": 0.1550827920436859,
|
| 547 |
+
"logits/rejected": 0.21283721923828125,
|
| 548 |
+
"logps/chosen": -910.0081176757812,
|
| 549 |
+
"logps/rejected": -1235.340087890625,
|
| 550 |
+
"loss": 1.7966,
|
| 551 |
+
"rewards/accuracies": 0.643750011920929,
|
| 552 |
+
"rewards/chosen": -0.6146690249443054,
|
| 553 |
+
"rewards/margins": 0.31371524930000305,
|
| 554 |
+
"rewards/rejected": -0.9283843040466309,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 4.825194522732023e-06,
|
| 560 |
+
"logits/chosen": 0.16921932995319366,
|
| 561 |
+
"logits/rejected": 0.2049584686756134,
|
| 562 |
+
"logps/chosen": -959.2523193359375,
|
| 563 |
+
"logps/rejected": -1241.6702880859375,
|
| 564 |
+
"loss": 1.6467,
|
| 565 |
+
"rewards/accuracies": 0.699999988079071,
|
| 566 |
+
"rewards/chosen": -0.6084691286087036,
|
| 567 |
+
"rewards/margins": 0.2845255434513092,
|
| 568 |
+
"rewards/rejected": -0.8929947018623352,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21,
|
| 573 |
+
"learning_rate": 4.807689444367853e-06,
|
| 574 |
+
"logits/chosen": 0.11238515377044678,
|
| 575 |
+
"logits/rejected": 0.18375565111637115,
|
| 576 |
+
"logps/chosen": -928.6314697265625,
|
| 577 |
+
"logps/rejected": -1184.4490966796875,
|
| 578 |
+
"loss": 1.7385,
|
| 579 |
+
"rewards/accuracies": 0.637499988079071,
|
| 580 |
+
"rewards/chosen": -0.5591214895248413,
|
| 581 |
+
"rewards/margins": 0.2713908851146698,
|
| 582 |
+
"rewards/rejected": -0.8305123448371887,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.22,
|
| 587 |
+
"learning_rate": 4.78938409995396e-06,
|
| 588 |
+
"logits/chosen": 0.14083296060562134,
|
| 589 |
+
"logits/rejected": 0.22474069893360138,
|
| 590 |
+
"logps/chosen": -847.0357666015625,
|
| 591 |
+
"logps/rejected": -1209.1551513671875,
|
| 592 |
+
"loss": 1.5509,
|
| 593 |
+
"rewards/accuracies": 0.6875,
|
| 594 |
+
"rewards/chosen": -0.524152398109436,
|
| 595 |
+
"rewards/margins": 0.3589867353439331,
|
| 596 |
+
"rewards/rejected": -0.8831392526626587,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22,
|
| 601 |
+
"learning_rate": 4.770284837461342e-06,
|
| 602 |
+
"logits/chosen": 0.12362311035394669,
|
| 603 |
+
"logits/rejected": 0.2302417755126953,
|
| 604 |
+
"logps/chosen": -902.5638427734375,
|
| 605 |
+
"logps/rejected": -1300.2840576171875,
|
| 606 |
+
"loss": 1.5579,
|
| 607 |
+
"rewards/accuracies": 0.6875,
|
| 608 |
+
"rewards/chosen": -0.5615973472595215,
|
| 609 |
+
"rewards/margins": 0.3917149603366852,
|
| 610 |
+
"rewards/rejected": -0.9533122777938843,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23,
|
| 615 |
+
"learning_rate": 4.7503982801778015e-06,
|
| 616 |
+
"logits/chosen": 0.13658492267131805,
|
| 617 |
+
"logits/rejected": 0.2200813740491867,
|
| 618 |
+
"logps/chosen": -907.9083251953125,
|
| 619 |
+
"logps/rejected": -1213.299072265625,
|
| 620 |
+
"loss": 1.6695,
|
| 621 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 622 |
+
"rewards/chosen": -0.5479084253311157,
|
| 623 |
+
"rewards/margins": 0.3318006098270416,
|
| 624 |
+
"rewards/rejected": -0.8797089457511902,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23,
|
| 629 |
+
"learning_rate": 4.729731324411104e-06,
|
| 630 |
+
"logits/chosen": 0.13933658599853516,
|
| 631 |
+
"logits/rejected": 0.19316565990447998,
|
| 632 |
+
"logps/chosen": -839.1355590820312,
|
| 633 |
+
"logps/rejected": -1168.003173828125,
|
| 634 |
+
"loss": 1.6066,
|
| 635 |
+
"rewards/accuracies": 0.675000011920929,
|
| 636 |
+
"rewards/chosen": -0.5049761533737183,
|
| 637 |
+
"rewards/margins": 0.344684898853302,
|
| 638 |
+
"rewards/rejected": -0.8496610522270203,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"learning_rate": 4.7082911370974645e-06,
|
| 644 |
+
"logits/chosen": 0.22927124798297882,
|
| 645 |
+
"logits/rejected": 0.23591044545173645,
|
| 646 |
+
"logps/chosen": -970.3570556640625,
|
| 647 |
+
"logps/rejected": -1318.6837158203125,
|
| 648 |
+
"loss": 1.5185,
|
| 649 |
+
"rewards/accuracies": 0.699999988079071,
|
| 650 |
+
"rewards/chosen": -0.615644097328186,
|
| 651 |
+
"rewards/margins": 0.3570120334625244,
|
| 652 |
+
"rewards/rejected": -0.9726561307907104,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.25,
|
| 657 |
+
"learning_rate": 4.68608515331618e-06,
|
| 658 |
+
"logits/chosen": 0.17804929614067078,
|
| 659 |
+
"logits/rejected": 0.23750662803649902,
|
| 660 |
+
"logps/chosen": -1088.924560546875,
|
| 661 |
+
"logps/rejected": -1432.3790283203125,
|
| 662 |
+
"loss": 1.5923,
|
| 663 |
+
"rewards/accuracies": 0.65625,
|
| 664 |
+
"rewards/chosen": -0.7223563194274902,
|
| 665 |
+
"rewards/margins": 0.37143898010253906,
|
| 666 |
+
"rewards/rejected": -1.0937952995300293,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25,
|
| 671 |
+
"learning_rate": 4.663121073711269e-06,
|
| 672 |
+
"logits/chosen": 0.14603152871131897,
|
| 673 |
+
"logits/rejected": 0.23797519505023956,
|
| 674 |
+
"logps/chosen": -1071.876220703125,
|
| 675 |
+
"logps/rejected": -1489.7244873046875,
|
| 676 |
+
"loss": 1.7778,
|
| 677 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 678 |
+
"rewards/chosen": -0.7220622301101685,
|
| 679 |
+
"rewards/margins": 0.40577608346939087,
|
| 680 |
+
"rewards/rejected": -1.127838373184204,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.26,
|
| 685 |
+
"learning_rate": 4.63940686182103e-06,
|
| 686 |
+
"logits/chosen": 0.10619086027145386,
|
| 687 |
+
"logits/rejected": 0.14224204421043396,
|
| 688 |
+
"logps/chosen": -1099.4365234375,
|
| 689 |
+
"logps/rejected": -1425.9031982421875,
|
| 690 |
+
"loss": 1.7194,
|
| 691 |
+
"rewards/accuracies": 0.6875,
|
| 692 |
+
"rewards/chosen": -0.7509239912033081,
|
| 693 |
+
"rewards/margins": 0.32126182317733765,
|
| 694 |
+
"rewards/rejected": -1.072185754776001,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.26,
|
| 699 |
+
"learning_rate": 4.614950741316425e-06,
|
| 700 |
+
"logits/chosen": 0.10838212817907333,
|
| 701 |
+
"logits/rejected": 0.1664058417081833,
|
| 702 |
+
"logps/chosen": -1114.0084228515625,
|
| 703 |
+
"logps/rejected": -1451.7799072265625,
|
| 704 |
+
"loss": 1.6984,
|
| 705 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 706 |
+
"rewards/chosen": -0.7566073536872864,
|
| 707 |
+
"rewards/margins": 0.3575124740600586,
|
| 708 |
+
"rewards/rejected": -1.1141197681427002,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.27,
|
| 713 |
+
"learning_rate": 4.589761193149254e-06,
|
| 714 |
+
"logits/chosen": 0.09154035151004791,
|
| 715 |
+
"logits/rejected": 0.08705167472362518,
|
| 716 |
+
"logps/chosen": -1139.4503173828125,
|
| 717 |
+
"logps/rejected": -1456.401611328125,
|
| 718 |
+
"loss": 1.7525,
|
| 719 |
+
"rewards/accuracies": 0.668749988079071,
|
| 720 |
+
"rewards/chosen": -0.8078290820121765,
|
| 721 |
+
"rewards/margins": 0.33122915029525757,
|
| 722 |
+
"rewards/rejected": -1.139058232307434,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27,
|
| 727 |
+
"learning_rate": 4.563846952611112e-06,
|
| 728 |
+
"logits/chosen": 0.04763927310705185,
|
| 729 |
+
"logits/rejected": 0.160281240940094,
|
| 730 |
+
"logps/chosen": -1115.03369140625,
|
| 731 |
+
"logps/rejected": -1348.77880859375,
|
| 732 |
+
"loss": 1.7972,
|
| 733 |
+
"rewards/accuracies": 0.675000011920929,
|
| 734 |
+
"rewards/chosen": -0.7022587656974792,
|
| 735 |
+
"rewards/margins": 0.31208425760269165,
|
| 736 |
+
"rewards/rejected": -1.014343023300171,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.28,
|
| 741 |
+
"learning_rate": 4.537217006304141e-06,
|
| 742 |
+
"logits/chosen": 0.05074567720293999,
|
| 743 |
+
"logits/rejected": 0.1087862104177475,
|
| 744 |
+
"logps/chosen": -982.4554443359375,
|
| 745 |
+
"logps/rejected": -1275.624267578125,
|
| 746 |
+
"loss": 1.6134,
|
| 747 |
+
"rewards/accuracies": 0.737500011920929,
|
| 748 |
+
"rewards/chosen": -0.6048920750617981,
|
| 749 |
+
"rewards/margins": 0.3106018006801605,
|
| 750 |
+
"rewards/rejected": -0.9154938459396362,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.28,
|
| 755 |
+
"learning_rate": 4.50988058902464e-06,
|
| 756 |
+
"logits/chosen": 0.01388006191700697,
|
| 757 |
+
"logits/rejected": 0.0734701007604599,
|
| 758 |
+
"logps/chosen": -849.9498291015625,
|
| 759 |
+
"logps/rejected": -1094.3758544921875,
|
| 760 |
+
"loss": 1.8119,
|
| 761 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 762 |
+
"rewards/chosen": -0.5126731991767883,
|
| 763 |
+
"rewards/margins": 0.261741042137146,
|
| 764 |
+
"rewards/rejected": -0.7744141817092896,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29,
|
| 769 |
+
"learning_rate": 4.481847180560593e-06,
|
| 770 |
+
"logits/chosen": 0.02280263975262642,
|
| 771 |
+
"logits/rejected": 0.06258614361286163,
|
| 772 |
+
"logps/chosen": -819.1052856445312,
|
| 773 |
+
"logps/rejected": -1066.9857177734375,
|
| 774 |
+
"loss": 1.7565,
|
| 775 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 776 |
+
"rewards/chosen": -0.5206565856933594,
|
| 777 |
+
"rewards/margins": 0.2521199584007263,
|
| 778 |
+
"rewards/rejected": -0.7727766633033752,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"learning_rate": 4.453126502404253e-06,
|
| 784 |
+
"logits/chosen": 0.0006181815406307578,
|
| 785 |
+
"logits/rejected": 0.02327551506459713,
|
| 786 |
+
"logps/chosen": -941.8448486328125,
|
| 787 |
+
"logps/rejected": -1197.061767578125,
|
| 788 |
+
"loss": 1.7268,
|
| 789 |
+
"rewards/accuracies": 0.675000011920929,
|
| 790 |
+
"rewards/chosen": -0.5985831022262573,
|
| 791 |
+
"rewards/margins": 0.26690778136253357,
|
| 792 |
+
"rewards/rejected": -0.8654907941818237,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"learning_rate": 4.423728514380892e-06,
|
| 798 |
+
"logits/chosen": 0.00485605001449585,
|
| 799 |
+
"logits/rejected": 0.03726247698068619,
|
| 800 |
+
"logps/chosen": -1022.1149291992188,
|
| 801 |
+
"logps/rejected": -1314.630859375,
|
| 802 |
+
"loss": 1.8572,
|
| 803 |
+
"rewards/accuracies": 0.612500011920929,
|
| 804 |
+
"rewards/chosen": -0.6928538084030151,
|
| 805 |
+
"rewards/margins": 0.2553819417953491,
|
| 806 |
+
"rewards/rejected": -0.9482356905937195,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3,
|
| 811 |
+
"learning_rate": 4.393663411194918e-06,
|
| 812 |
+
"logits/chosen": 0.038806699216365814,
|
| 813 |
+
"logits/rejected": 0.05322469025850296,
|
| 814 |
+
"logps/chosen": -993.5315551757812,
|
| 815 |
+
"logps/rejected": -1312.275634765625,
|
| 816 |
+
"loss": 1.6143,
|
| 817 |
+
"rewards/accuracies": 0.668749988079071,
|
| 818 |
+
"rewards/chosen": -0.6640539765357971,
|
| 819 |
+
"rewards/margins": 0.3003658652305603,
|
| 820 |
+
"rewards/rejected": -0.9644198417663574,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.31,
|
| 825 |
+
"learning_rate": 4.362941618894523e-06,
|
| 826 |
+
"logits/chosen": 0.01965520530939102,
|
| 827 |
+
"logits/rejected": 0.033857885748147964,
|
| 828 |
+
"logps/chosen": -962.2711181640625,
|
| 829 |
+
"logps/rejected": -1249.142578125,
|
| 830 |
+
"loss": 1.767,
|
| 831 |
+
"rewards/accuracies": 0.65625,
|
| 832 |
+
"rewards/chosen": -0.6267088651657104,
|
| 833 |
+
"rewards/margins": 0.29039520025253296,
|
| 834 |
+
"rewards/rejected": -0.9171040654182434,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31,
|
| 839 |
+
"learning_rate": 4.331573791256116e-06,
|
| 840 |
+
"logits/chosen": -0.02834545448422432,
|
| 841 |
+
"logits/rejected": 0.037625543773174286,
|
| 842 |
+
"logps/chosen": -1008.5965576171875,
|
| 843 |
+
"logps/rejected": -1362.098876953125,
|
| 844 |
+
"loss": 1.5613,
|
| 845 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 846 |
+
"rewards/chosen": -0.6537022590637207,
|
| 847 |
+
"rewards/margins": 0.3879777789115906,
|
| 848 |
+
"rewards/rejected": -1.0416799783706665,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.32,
|
| 853 |
+
"learning_rate": 4.299570806089786e-06,
|
| 854 |
+
"logits/chosen": -0.03007788583636284,
|
| 855 |
+
"logits/rejected": 0.0712488442659378,
|
| 856 |
+
"logps/chosen": -982.5880737304688,
|
| 857 |
+
"logps/rejected": -1292.6614990234375,
|
| 858 |
+
"loss": 1.6944,
|
| 859 |
+
"rewards/accuracies": 0.675000011920929,
|
| 860 |
+
"rewards/chosen": -0.6564881801605225,
|
| 861 |
+
"rewards/margins": 0.3164929747581482,
|
| 862 |
+
"rewards/rejected": -0.9729811549186707,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.33,
|
| 867 |
+
"learning_rate": 4.266943761467057e-06,
|
| 868 |
+
"logits/chosen": 0.03833829611539841,
|
| 869 |
+
"logits/rejected": 0.06410752981901169,
|
| 870 |
+
"logps/chosen": -991.5280151367188,
|
| 871 |
+
"logps/rejected": -1269.9459228515625,
|
| 872 |
+
"loss": 1.6837,
|
| 873 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 874 |
+
"rewards/chosen": -0.6482813954353333,
|
| 875 |
+
"rewards/margins": 0.28088536858558655,
|
| 876 |
+
"rewards/rejected": -0.9291667938232422,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33,
|
| 881 |
+
"learning_rate": 4.233703971872287e-06,
|
| 882 |
+
"logits/chosen": 0.01419871486723423,
|
| 883 |
+
"logits/rejected": 0.041936878114938736,
|
| 884 |
+
"logps/chosen": -955.8319091796875,
|
| 885 |
+
"logps/rejected": -1251.8397216796875,
|
| 886 |
+
"loss": 1.6607,
|
| 887 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 888 |
+
"rewards/chosen": -0.6094011664390564,
|
| 889 |
+
"rewards/margins": 0.32103410363197327,
|
| 890 |
+
"rewards/rejected": -0.9304353594779968,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.34,
|
| 895 |
+
"learning_rate": 4.1998629642789925e-06,
|
| 896 |
+
"logits/chosen": 0.0568360760807991,
|
| 897 |
+
"logits/rejected": 0.1395053267478943,
|
| 898 |
+
"logps/chosen": -1048.60009765625,
|
| 899 |
+
"logps/rejected": -1351.2703857421875,
|
| 900 |
+
"loss": 1.7727,
|
| 901 |
+
"rewards/accuracies": 0.612500011920929,
|
| 902 |
+
"rewards/chosen": -0.6901832222938538,
|
| 903 |
+
"rewards/margins": 0.2976410686969757,
|
| 904 |
+
"rewards/rejected": -0.9878243207931519,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.34,
|
| 909 |
+
"learning_rate": 4.165432474152505e-06,
|
| 910 |
+
"logits/chosen": 0.032792214304208755,
|
| 911 |
+
"logits/rejected": 0.019641969352960587,
|
| 912 |
+
"logps/chosen": -961.2864990234375,
|
| 913 |
+
"logps/rejected": -1392.465576171875,
|
| 914 |
+
"loss": 1.4681,
|
| 915 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 916 |
+
"rewards/chosen": -0.6157466173171997,
|
| 917 |
+
"rewards/margins": 0.42596155405044556,
|
| 918 |
+
"rewards/rejected": -1.04170823097229,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35,
|
| 923 |
+
"learning_rate": 4.130424441380308e-06,
|
| 924 |
+
"logits/chosen": 0.0214821957051754,
|
| 925 |
+
"logits/rejected": 0.11312129348516464,
|
| 926 |
+
"logps/chosen": -1139.0208740234375,
|
| 927 |
+
"logps/rejected": -1529.8564453125,
|
| 928 |
+
"loss": 1.5676,
|
| 929 |
+
"rewards/accuracies": 0.731249988079071,
|
| 930 |
+
"rewards/chosen": -0.7614965438842773,
|
| 931 |
+
"rewards/margins": 0.40181460976600647,
|
| 932 |
+
"rewards/rejected": -1.163311243057251,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"learning_rate": 4.09485100613151e-06,
|
| 938 |
+
"logits/chosen": 0.03265173360705376,
|
| 939 |
+
"logits/rejected": 0.08288411051034927,
|
| 940 |
+
"logps/chosen": -1008.8547973632812,
|
| 941 |
+
"logps/rejected": -1373.1070556640625,
|
| 942 |
+
"loss": 1.6128,
|
| 943 |
+
"rewards/accuracies": 0.643750011920929,
|
| 944 |
+
"rewards/chosen": -0.6687760949134827,
|
| 945 |
+
"rewards/margins": 0.3712404668331146,
|
| 946 |
+
"rewards/rejected": -1.040016531944275,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"learning_rate": 4.058724504646834e-06,
|
| 952 |
+
"logits/chosen": 0.008680765517055988,
|
| 953 |
+
"logits/rejected": 0.03280487284064293,
|
| 954 |
+
"logps/chosen": -1010.1678466796875,
|
| 955 |
+
"logps/rejected": -1343.5008544921875,
|
| 956 |
+
"loss": 1.6108,
|
| 957 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 958 |
+
"rewards/chosen": -0.6555579304695129,
|
| 959 |
+
"rewards/margins": 0.34102123975753784,
|
| 960 |
+
"rewards/rejected": -0.9965791702270508,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36,
|
| 965 |
+
"learning_rate": 4.022057464960632e-06,
|
| 966 |
+
"logits/chosen": 0.051326651126146317,
|
| 967 |
+
"logits/rejected": 0.10143965482711792,
|
| 968 |
+
"logps/chosen": -1015.6981201171875,
|
| 969 |
+
"logps/rejected": -1286.204345703125,
|
| 970 |
+
"loss": 1.8244,
|
| 971 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 972 |
+
"rewards/chosen": -0.6295019388198853,
|
| 973 |
+
"rewards/margins": 0.3051254153251648,
|
| 974 |
+
"rewards/rejected": -0.93462735414505,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37,
|
| 979 |
+
"learning_rate": 3.984862602556383e-06,
|
| 980 |
+
"logits/chosen": 0.06714431941509247,
|
| 981 |
+
"logits/rejected": 0.14711423218250275,
|
| 982 |
+
"logps/chosen": -878.5494384765625,
|
| 983 |
+
"logps/rejected": -1243.7890625,
|
| 984 |
+
"loss": 1.5624,
|
| 985 |
+
"rewards/accuracies": 0.737500011920929,
|
| 986 |
+
"rewards/chosen": -0.5232223272323608,
|
| 987 |
+
"rewards/margins": 0.37018781900405884,
|
| 988 |
+
"rewards/rejected": -0.8934100866317749,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.37,
|
| 993 |
+
"learning_rate": 3.947152815957187e-06,
|
| 994 |
+
"logits/chosen": 0.024934569373726845,
|
| 995 |
+
"logits/rejected": 0.09314241260290146,
|
| 996 |
+
"logps/chosen": -954.0012817382812,
|
| 997 |
+
"logps/rejected": -1265.03564453125,
|
| 998 |
+
"loss": 1.6638,
|
| 999 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1000 |
+
"rewards/chosen": -0.6106816530227661,
|
| 1001 |
+
"rewards/margins": 0.3257291316986084,
|
| 1002 |
+
"rewards/rejected": -0.9364109039306641,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38,
|
| 1007 |
+
"learning_rate": 3.908941182252785e-06,
|
| 1008 |
+
"logits/chosen": 0.029830629006028175,
|
| 1009 |
+
"logits/rejected": 0.10770799964666367,
|
| 1010 |
+
"logps/chosen": -949.3072509765625,
|
| 1011 |
+
"logps/rejected": -1249.8748779296875,
|
| 1012 |
+
"loss": 1.7333,
|
| 1013 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1014 |
+
"rewards/chosen": -0.6108871102333069,
|
| 1015 |
+
"rewards/margins": 0.3122674822807312,
|
| 1016 |
+
"rewards/rejected": -0.9231545329093933,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.38,
|
| 1021 |
+
"learning_rate": 3.8702409525646535e-06,
|
| 1022 |
+
"logits/chosen": 0.060981638729572296,
|
| 1023 |
+
"logits/rejected": 0.06661652028560638,
|
| 1024 |
+
"logps/chosen": -897.6103515625,
|
| 1025 |
+
"logps/rejected": -1229.4617919921875,
|
| 1026 |
+
"loss": 1.6608,
|
| 1027 |
+
"rewards/accuracies": 0.65625,
|
| 1028 |
+
"rewards/chosen": -0.5749759674072266,
|
| 1029 |
+
"rewards/margins": 0.29930251836776733,
|
| 1030 |
+
"rewards/rejected": -0.8742784261703491,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.39,
|
| 1035 |
+
"learning_rate": 3.8310655474507495e-06,
|
| 1036 |
+
"logits/chosen": 0.03684331104159355,
|
| 1037 |
+
"logits/rejected": 0.14619871973991394,
|
| 1038 |
+
"logps/chosen": -923.5501098632812,
|
| 1039 |
+
"logps/rejected": -1209.08740234375,
|
| 1040 |
+
"loss": 1.6177,
|
| 1041 |
+
"rewards/accuracies": 0.65625,
|
| 1042 |
+
"rewards/chosen": -0.5860185623168945,
|
| 1043 |
+
"rewards/margins": 0.3128363788127899,
|
| 1044 |
+
"rewards/rejected": -0.8988549113273621,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39,
|
| 1049 |
+
"learning_rate": 3.7914285522515002e-06,
|
| 1050 |
+
"logits/chosen": 0.011234849691390991,
|
| 1051 |
+
"logits/rejected": 0.10097019374370575,
|
| 1052 |
+
"logps/chosen": -936.65234375,
|
| 1053 |
+
"logps/rejected": -1304.6485595703125,
|
| 1054 |
+
"loss": 1.5484,
|
| 1055 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1056 |
+
"rewards/chosen": -0.5933856964111328,
|
| 1057 |
+
"rewards/margins": 0.3895036578178406,
|
| 1058 |
+
"rewards/rejected": -0.9828893542289734,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4,
|
| 1063 |
+
"learning_rate": 3.751343712378639e-06,
|
| 1064 |
+
"logits/chosen": 0.05703802779316902,
|
| 1065 |
+
"logits/rejected": 0.13415174186229706,
|
| 1066 |
+
"logps/chosen": -1007.4900512695312,
|
| 1067 |
+
"logps/rejected": -1316.6981201171875,
|
| 1068 |
+
"loss": 1.5569,
|
| 1069 |
+
"rewards/accuracies": 0.6875,
|
| 1070 |
+
"rewards/chosen": -0.6273565888404846,
|
| 1071 |
+
"rewards/margins": 0.3487706184387207,
|
| 1072 |
+
"rewards/rejected": -0.9761272668838501,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.41,
|
| 1077 |
+
"learning_rate": 3.710824928548546e-06,
|
| 1078 |
+
"logits/chosen": 0.11401792615652084,
|
| 1079 |
+
"logits/rejected": 0.149090975522995,
|
| 1080 |
+
"logps/chosen": -1011.75634765625,
|
| 1081 |
+
"logps/rejected": -1267.4716796875,
|
| 1082 |
+
"loss": 1.991,
|
| 1083 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1084 |
+
"rewards/chosen": -0.662542462348938,
|
| 1085 |
+
"rewards/margins": 0.27919334173202515,
|
| 1086 |
+
"rewards/rejected": -0.9417358636856079,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"learning_rate": 3.6698862519617225e-06,
|
| 1092 |
+
"logits/chosen": 0.04727781563997269,
|
| 1093 |
+
"logits/rejected": 0.0998949259519577,
|
| 1094 |
+
"logps/chosen": -959.3302001953125,
|
| 1095 |
+
"logps/rejected": -1265.2984619140625,
|
| 1096 |
+
"loss": 1.6325,
|
| 1097 |
+
"rewards/accuracies": 0.65625,
|
| 1098 |
+
"rewards/chosen": -0.6212436556816101,
|
| 1099 |
+
"rewards/margins": 0.3175702691078186,
|
| 1100 |
+
"rewards/rejected": -0.9388139843940735,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.42,
|
| 1105 |
+
"learning_rate": 3.6285418794300793e-06,
|
| 1106 |
+
"logits/chosen": 0.08479107916355133,
|
| 1107 |
+
"logits/rejected": 0.1416613757610321,
|
| 1108 |
+
"logps/chosen": -1000.9298706054688,
|
| 1109 |
+
"logps/rejected": -1267.0145263671875,
|
| 1110 |
+
"loss": 1.7375,
|
| 1111 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1112 |
+
"rewards/chosen": -0.6357444524765015,
|
| 1113 |
+
"rewards/margins": 0.310316264629364,
|
| 1114 |
+
"rewards/rejected": -0.9460607767105103,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42,
|
| 1119 |
+
"learning_rate": 3.5868061484537365e-06,
|
| 1120 |
+
"logits/chosen": 0.02577986940741539,
|
| 1121 |
+
"logits/rejected": 0.08596567064523697,
|
| 1122 |
+
"logps/chosen": -1112.874755859375,
|
| 1123 |
+
"logps/rejected": -1473.1839599609375,
|
| 1124 |
+
"loss": 1.6638,
|
| 1125 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1126 |
+
"rewards/chosen": -0.7674813270568848,
|
| 1127 |
+
"rewards/margins": 0.35035058856010437,
|
| 1128 |
+
"rewards/rejected": -1.1178319454193115,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43,
|
| 1133 |
+
"learning_rate": 3.5446935322490285e-06,
|
| 1134 |
+
"logits/chosen": 0.03142818063497543,
|
| 1135 |
+
"logits/rejected": 0.0737256333231926,
|
| 1136 |
+
"logps/chosen": -1049.059326171875,
|
| 1137 |
+
"logps/rejected": -1381.332763671875,
|
| 1138 |
+
"loss": 1.6325,
|
| 1139 |
+
"rewards/accuracies": 0.71875,
|
| 1140 |
+
"rewards/chosen": -0.7112890481948853,
|
| 1141 |
+
"rewards/margins": 0.3419298231601715,
|
| 1142 |
+
"rewards/rejected": -1.0532188415527344,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.43,
|
| 1147 |
+
"learning_rate": 3.502218634729447e-06,
|
| 1148 |
+
"logits/chosen": 0.04486529529094696,
|
| 1149 |
+
"logits/rejected": 0.07387622445821762,
|
| 1150 |
+
"logps/chosen": -1063.0550537109375,
|
| 1151 |
+
"logps/rejected": -1385.9937744140625,
|
| 1152 |
+
"loss": 1.7277,
|
| 1153 |
+
"rewards/accuracies": 0.65625,
|
| 1154 |
+
"rewards/chosen": -0.7465726137161255,
|
| 1155 |
+
"rewards/margins": 0.30831706523895264,
|
| 1156 |
+
"rewards/rejected": -1.0548895597457886,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.44,
|
| 1161 |
+
"learning_rate": 3.459396185441265e-06,
|
| 1162 |
+
"logits/chosen": 0.042615022510290146,
|
| 1163 |
+
"logits/rejected": 0.08985388278961182,
|
| 1164 |
+
"logps/chosen": -1015.6598510742188,
|
| 1165 |
+
"logps/rejected": -1335.8912353515625,
|
| 1166 |
+
"loss": 1.5891,
|
| 1167 |
+
"rewards/accuracies": 0.71875,
|
| 1168 |
+
"rewards/chosen": -0.6490973234176636,
|
| 1169 |
+
"rewards/margins": 0.33889901638031006,
|
| 1170 |
+
"rewards/rejected": -0.9879962801933289,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44,
|
| 1175 |
+
"learning_rate": 3.4162410344555834e-06,
|
| 1176 |
+
"logits/chosen": 0.07760035991668701,
|
| 1177 |
+
"logits/rejected": 0.09005734324455261,
|
| 1178 |
+
"logps/chosen": -1110.9671630859375,
|
| 1179 |
+
"logps/rejected": -1389.163330078125,
|
| 1180 |
+
"loss": 1.7173,
|
| 1181 |
+
"rewards/accuracies": 0.6875,
|
| 1182 |
+
"rewards/chosen": -0.7506981492042542,
|
| 1183 |
+
"rewards/margins": 0.29421886801719666,
|
| 1184 |
+
"rewards/rejected": -1.0449169874191284,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.45,
|
| 1189 |
+
"learning_rate": 3.3727681472185937e-06,
|
| 1190 |
+
"logits/chosen": 0.052268415689468384,
|
| 1191 |
+
"logits/rejected": 0.10122676193714142,
|
| 1192 |
+
"logps/chosen": -903.8248901367188,
|
| 1193 |
+
"logps/rejected": -1204.15576171875,
|
| 1194 |
+
"loss": 1.5496,
|
| 1195 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1196 |
+
"rewards/chosen": -0.5848682522773743,
|
| 1197 |
+
"rewards/margins": 0.31761133670806885,
|
| 1198 |
+
"rewards/rejected": -0.9024796485900879,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.45,
|
| 1203 |
+
"learning_rate": 3.3289925993618217e-06,
|
| 1204 |
+
"logits/chosen": 0.06663919985294342,
|
| 1205 |
+
"logits/rejected": 0.1188969761133194,
|
| 1206 |
+
"logps/chosen": -1047.30029296875,
|
| 1207 |
+
"logps/rejected": -1304.7379150390625,
|
| 1208 |
+
"loss": 1.7105,
|
| 1209 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1210 |
+
"rewards/chosen": -0.671362578868866,
|
| 1211 |
+
"rewards/margins": 0.3004400134086609,
|
| 1212 |
+
"rewards/rejected": -0.9718025326728821,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46,
|
| 1217 |
+
"learning_rate": 3.2849295714741643e-06,
|
| 1218 |
+
"logits/chosen": 0.0677184984087944,
|
| 1219 |
+
"logits/rejected": 0.11335499584674835,
|
| 1220 |
+
"logps/chosen": -1036.0316162109375,
|
| 1221 |
+
"logps/rejected": -1401.0706787109375,
|
| 1222 |
+
"loss": 1.622,
|
| 1223 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1224 |
+
"rewards/chosen": -0.6989107131958008,
|
| 1225 |
+
"rewards/margins": 0.36011943221092224,
|
| 1226 |
+
"rewards/rejected": -1.0590301752090454,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46,
|
| 1231 |
+
"learning_rate": 3.2405943438375287e-06,
|
| 1232 |
+
"logits/chosen": 0.08610890805721283,
|
| 1233 |
+
"logits/rejected": 0.1343824565410614,
|
| 1234 |
+
"logps/chosen": -1109.2958984375,
|
| 1235 |
+
"logps/rejected": -1425.269287109375,
|
| 1236 |
+
"loss": 1.6286,
|
| 1237 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1238 |
+
"rewards/chosen": -0.753276526927948,
|
| 1239 |
+
"rewards/margins": 0.3505406975746155,
|
| 1240 |
+
"rewards/rejected": -1.1038172245025635,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"learning_rate": 3.1960022911279036e-06,
|
| 1246 |
+
"logits/chosen": 0.04142437130212784,
|
| 1247 |
+
"logits/rejected": 0.10113891214132309,
|
| 1248 |
+
"logps/chosen": -1057.3348388671875,
|
| 1249 |
+
"logps/rejected": -1386.047607421875,
|
| 1250 |
+
"loss": 1.754,
|
| 1251 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1252 |
+
"rewards/chosen": -0.7235895395278931,
|
| 1253 |
+
"rewards/margins": 0.334214448928833,
|
| 1254 |
+
"rewards/rejected": -1.0578038692474365,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"learning_rate": 3.1511688770836844e-06,
|
| 1260 |
+
"logits/chosen": 0.062126994132995605,
|
| 1261 |
+
"logits/rejected": 0.10421881824731827,
|
| 1262 |
+
"logps/chosen": -1068.828857421875,
|
| 1263 |
+
"logps/rejected": -1316.99951171875,
|
| 1264 |
+
"loss": 1.6456,
|
| 1265 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1266 |
+
"rewards/chosen": -0.732558012008667,
|
| 1267 |
+
"rewards/margins": 0.2871066927909851,
|
| 1268 |
+
"rewards/rejected": -1.0196647644042969,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.48,
|
| 1273 |
+
"learning_rate": 3.1061096491431307e-06,
|
| 1274 |
+
"logits/chosen": 0.062398504465818405,
|
| 1275 |
+
"logits/rejected": 0.14607712626457214,
|
| 1276 |
+
"logps/chosen": -1060.228271484375,
|
| 1277 |
+
"logps/rejected": -1450.5191650390625,
|
| 1278 |
+
"loss": 1.6495,
|
| 1279 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1280 |
+
"rewards/chosen": -0.7299556732177734,
|
| 1281 |
+
"rewards/margins": 0.3911103308200836,
|
| 1282 |
+
"rewards/rejected": -1.1210659742355347,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49,
|
| 1287 |
+
"learning_rate": 3.0608402330527796e-06,
|
| 1288 |
+
"logits/chosen": 0.10377037525177002,
|
| 1289 |
+
"logits/rejected": 0.1702093631029129,
|
| 1290 |
+
"logps/chosen": -1070.2183837890625,
|
| 1291 |
+
"logps/rejected": -1444.0865478515625,
|
| 1292 |
+
"loss": 1.4815,
|
| 1293 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 1294 |
+
"rewards/chosen": -0.6973433494567871,
|
| 1295 |
+
"rewards/margins": 0.40493422746658325,
|
| 1296 |
+
"rewards/rejected": -1.1022775173187256,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.49,
|
| 1301 |
+
"learning_rate": 3.0153763274487176e-06,
|
| 1302 |
+
"logits/chosen": 0.10599883645772934,
|
| 1303 |
+
"logits/rejected": 0.14606773853302002,
|
| 1304 |
+
"logps/chosen": -1007.1170043945312,
|
| 1305 |
+
"logps/rejected": -1397.21826171875,
|
| 1306 |
+
"loss": 1.7218,
|
| 1307 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1308 |
+
"rewards/chosen": -0.7144777178764343,
|
| 1309 |
+
"rewards/margins": 0.3858681619167328,
|
| 1310 |
+
"rewards/rejected": -1.1003458499908447,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5,
|
| 1315 |
+
"learning_rate": 2.9697336984125683e-06,
|
| 1316 |
+
"logits/chosen": 0.10908961296081543,
|
| 1317 |
+
"logits/rejected": 0.1530420482158661,
|
| 1318 |
+
"logps/chosen": -1157.73828125,
|
| 1319 |
+
"logps/rejected": -1576.6483154296875,
|
| 1320 |
+
"loss": 1.5431,
|
| 1321 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1322 |
+
"rewards/chosen": -0.8187190890312195,
|
| 1323 |
+
"rewards/margins": 0.3967840075492859,
|
| 1324 |
+
"rewards/rejected": -1.2155030965805054,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5,
|
| 1329 |
+
"learning_rate": 2.923928174004094e-06,
|
| 1330 |
+
"logits/chosen": 0.06097055599093437,
|
| 1331 |
+
"logits/rejected": 0.11391390860080719,
|
| 1332 |
+
"logps/chosen": -1108.5380859375,
|
| 1333 |
+
"logps/rejected": -1444.47607421875,
|
| 1334 |
+
"loss": 1.6738,
|
| 1335 |
+
"rewards/accuracies": 0.65625,
|
| 1336 |
+
"rewards/chosen": -0.7912001609802246,
|
| 1337 |
+
"rewards/margins": 0.3262966573238373,
|
| 1338 |
+
"rewards/rejected": -1.1174967288970947,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.51,
|
| 1343 |
+
"learning_rate": 2.8779756387723036e-06,
|
| 1344 |
+
"logits/chosen": 0.06467770040035248,
|
| 1345 |
+
"logits/rejected": 0.0973706915974617,
|
| 1346 |
+
"logps/chosen": -1154.4818115234375,
|
| 1347 |
+
"logps/rejected": -1414.0888671875,
|
| 1348 |
+
"loss": 1.4953,
|
| 1349 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1350 |
+
"rewards/chosen": -0.7806675434112549,
|
| 1351 |
+
"rewards/margins": 0.309781551361084,
|
| 1352 |
+
"rewards/rejected": -1.0904490947723389,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.51,
|
| 1357 |
+
"learning_rate": 2.831892028246968e-06,
|
| 1358 |
+
"logits/chosen": 0.07558836042881012,
|
| 1359 |
+
"logits/rejected": 0.13848301768302917,
|
| 1360 |
+
"logps/chosen": -1124.1239013671875,
|
| 1361 |
+
"logps/rejected": -1415.198486328125,
|
| 1362 |
+
"loss": 1.6304,
|
| 1363 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1364 |
+
"rewards/chosen": -0.7694803476333618,
|
| 1365 |
+
"rewards/margins": 0.3106168210506439,
|
| 1366 |
+
"rewards/rejected": -1.0800971984863281,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.52,
|
| 1371 |
+
"learning_rate": 2.7856933234124617e-06,
|
| 1372 |
+
"logits/chosen": 0.09707184135913849,
|
| 1373 |
+
"logits/rejected": 0.15487423539161682,
|
| 1374 |
+
"logps/chosen": -1033.051513671875,
|
| 1375 |
+
"logps/rejected": -1383.0096435546875,
|
| 1376 |
+
"loss": 1.5955,
|
| 1377 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1378 |
+
"rewards/chosen": -0.7070351243019104,
|
| 1379 |
+
"rewards/margins": 0.32586950063705444,
|
| 1380 |
+
"rewards/rejected": -1.0329046249389648,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.52,
|
| 1385 |
+
"learning_rate": 2.7393955451658387e-06,
|
| 1386 |
+
"logits/chosen": 0.17485928535461426,
|
| 1387 |
+
"logits/rejected": 0.20479004085063934,
|
| 1388 |
+
"logps/chosen": -1019.5245361328125,
|
| 1389 |
+
"logps/rejected": -1405.92578125,
|
| 1390 |
+
"loss": 1.5161,
|
| 1391 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1392 |
+
"rewards/chosen": -0.6749985814094543,
|
| 1393 |
+
"rewards/margins": 0.39169296622276306,
|
| 1394 |
+
"rewards/rejected": -1.066691517829895,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.53,
|
| 1399 |
+
"learning_rate": 2.6930147487610667e-06,
|
| 1400 |
+
"logits/chosen": 0.1469564139842987,
|
| 1401 |
+
"logits/rejected": 0.18740007281303406,
|
| 1402 |
+
"logps/chosen": -1112.45654296875,
|
| 1403 |
+
"logps/rejected": -1390.9603271484375,
|
| 1404 |
+
"loss": 1.8518,
|
| 1405 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1406 |
+
"rewards/chosen": -0.7527428269386292,
|
| 1407 |
+
"rewards/margins": 0.29854851961135864,
|
| 1408 |
+
"rewards/rejected": -1.0512912273406982,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"learning_rate": 2.6465670182413487e-06,
|
| 1414 |
+
"logits/chosen": 0.1311412751674652,
|
| 1415 |
+
"logits/rejected": 0.16103684902191162,
|
| 1416 |
+
"logps/chosen": -1034.7266845703125,
|
| 1417 |
+
"logps/rejected": -1487.0198974609375,
|
| 1418 |
+
"loss": 1.4757,
|
| 1419 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1420 |
+
"rewards/chosen": -0.6916247010231018,
|
| 1421 |
+
"rewards/margins": 0.43866676092147827,
|
| 1422 |
+
"rewards/rejected": -1.13029146194458,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.54,
|
| 1427 |
+
"learning_rate": 2.6000684608614594e-06,
|
| 1428 |
+
"logits/chosen": 0.1081945076584816,
|
| 1429 |
+
"logits/rejected": 0.2089473456144333,
|
| 1430 |
+
"logps/chosen": -1155.034423828125,
|
| 1431 |
+
"logps/rejected": -1513.755615234375,
|
| 1432 |
+
"loss": 1.6896,
|
| 1433 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 1434 |
+
"rewards/chosen": -0.815504252910614,
|
| 1435 |
+
"rewards/margins": 0.3612630367279053,
|
| 1436 |
+
"rewards/rejected": -1.1767674684524536,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.54,
|
| 1441 |
+
"learning_rate": 2.5535352015020338e-06,
|
| 1442 |
+
"logits/chosen": 0.1341986358165741,
|
| 1443 |
+
"logits/rejected": 0.18716619908809662,
|
| 1444 |
+
"logps/chosen": -1160.8070068359375,
|
| 1445 |
+
"logps/rejected": -1478.892333984375,
|
| 1446 |
+
"loss": 1.566,
|
| 1447 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1448 |
+
"rewards/chosen": -0.7914396524429321,
|
| 1449 |
+
"rewards/margins": 0.33516114950180054,
|
| 1450 |
+
"rewards/rejected": -1.126600742340088,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.55,
|
| 1455 |
+
"learning_rate": 2.506983377077741e-06,
|
| 1456 |
+
"logits/chosen": 0.11889129877090454,
|
| 1457 |
+
"logits/rejected": 0.172836571931839,
|
| 1458 |
+
"logps/chosen": -1112.3515625,
|
| 1459 |
+
"logps/rejected": -1390.6231689453125,
|
| 1460 |
+
"loss": 1.7204,
|
| 1461 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1462 |
+
"rewards/chosen": -0.7569676637649536,
|
| 1463 |
+
"rewards/margins": 0.2798970341682434,
|
| 1464 |
+
"rewards/rejected": -1.0368645191192627,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.55,
|
| 1469 |
+
"learning_rate": 2.460429130941289e-06,
|
| 1470 |
+
"logits/chosen": 0.1303168535232544,
|
| 1471 |
+
"logits/rejected": 0.23098449409008026,
|
| 1472 |
+
"logps/chosen": -1031.8233642578125,
|
| 1473 |
+
"logps/rejected": -1380.739013671875,
|
| 1474 |
+
"loss": 1.4098,
|
| 1475 |
+
"rewards/accuracies": 0.75,
|
| 1476 |
+
"rewards/chosen": -0.6430400609970093,
|
| 1477 |
+
"rewards/margins": 0.3773672878742218,
|
| 1478 |
+
"rewards/rejected": -1.0204073190689087,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.56,
|
| 1483 |
+
"learning_rate": 2.413888607285192e-06,
|
| 1484 |
+
"logits/chosen": 0.08564915508031845,
|
| 1485 |
+
"logits/rejected": 0.12453781068325043,
|
| 1486 |
+
"logps/chosen": -985.0271606445312,
|
| 1487 |
+
"logps/rejected": -1363.299072265625,
|
| 1488 |
+
"loss": 1.5626,
|
| 1489 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1490 |
+
"rewards/chosen": -0.6599403619766235,
|
| 1491 |
+
"rewards/margins": 0.3573141098022461,
|
| 1492 |
+
"rewards/rejected": -1.0172545909881592,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.57,
|
| 1497 |
+
"learning_rate": 2.367377945543249e-06,
|
| 1498 |
+
"logits/chosen": 0.12176636606454849,
|
| 1499 |
+
"logits/rejected": 0.2213442027568817,
|
| 1500 |
+
"logps/chosen": -1076.0185546875,
|
| 1501 |
+
"logps/rejected": -1498.5506591796875,
|
| 1502 |
+
"loss": 1.5116,
|
| 1503 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1504 |
+
"rewards/chosen": -0.7448247671127319,
|
| 1505 |
+
"rewards/margins": 0.4244067668914795,
|
| 1506 |
+
"rewards/rejected": -1.169231653213501,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.57,
|
| 1511 |
+
"learning_rate": 2.320913274793676e-06,
|
| 1512 |
+
"logits/chosen": 0.1362072080373764,
|
| 1513 |
+
"logits/rejected": 0.1790778636932373,
|
| 1514 |
+
"logps/chosen": -1171.556396484375,
|
| 1515 |
+
"logps/rejected": -1544.1282958984375,
|
| 1516 |
+
"loss": 1.6752,
|
| 1517 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1518 |
+
"rewards/chosen": -0.8081449270248413,
|
| 1519 |
+
"rewards/margins": 0.386355459690094,
|
| 1520 |
+
"rewards/rejected": -1.1945003271102905,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.58,
|
| 1525 |
+
"learning_rate": 2.27451070816582e-06,
|
| 1526 |
+
"logits/chosen": 0.13579389452934265,
|
| 1527 |
+
"logits/rejected": 0.1608073115348816,
|
| 1528 |
+
"logps/chosen": -1076.015380859375,
|
| 1529 |
+
"logps/rejected": -1350.9400634765625,
|
| 1530 |
+
"loss": 1.7586,
|
| 1531 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 1532 |
+
"rewards/chosen": -0.7380760312080383,
|
| 1533 |
+
"rewards/margins": 0.29431313276290894,
|
| 1534 |
+
"rewards/rejected": -1.0323892831802368,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.58,
|
| 1539 |
+
"learning_rate": 2.228186337252414e-06,
|
| 1540 |
+
"logits/chosen": 0.09430348873138428,
|
| 1541 |
+
"logits/rejected": 0.20111441612243652,
|
| 1542 |
+
"logps/chosen": -1102.0145263671875,
|
| 1543 |
+
"logps/rejected": -1460.5335693359375,
|
| 1544 |
+
"loss": 1.6547,
|
| 1545 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1546 |
+
"rewards/chosen": -0.7317436337471008,
|
| 1547 |
+
"rewards/margins": 0.37700966000556946,
|
| 1548 |
+
"rewards/rejected": -1.1087532043457031,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.59,
|
| 1553 |
+
"learning_rate": 2.1819562265292946e-06,
|
| 1554 |
+
"logits/chosen": 0.16240547597408295,
|
| 1555 |
+
"logits/rejected": 0.1689942628145218,
|
| 1556 |
+
"logps/chosen": -983.9060668945312,
|
| 1557 |
+
"logps/rejected": -1212.6190185546875,
|
| 1558 |
+
"loss": 1.6005,
|
| 1559 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1560 |
+
"rewards/chosen": -0.6035498380661011,
|
| 1561 |
+
"rewards/margins": 0.29034045338630676,
|
| 1562 |
+
"rewards/rejected": -0.8938902616500854,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"learning_rate": 2.1358364077845236e-06,
|
| 1568 |
+
"logits/chosen": 0.13844513893127441,
|
| 1569 |
+
"logits/rejected": 0.2087705433368683,
|
| 1570 |
+
"logps/chosen": -1064.875732421875,
|
| 1571 |
+
"logps/rejected": -1291.0726318359375,
|
| 1572 |
+
"loss": 1.7957,
|
| 1573 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1574 |
+
"rewards/chosen": -0.6955076456069946,
|
| 1575 |
+
"rewards/margins": 0.26428431272506714,
|
| 1576 |
+
"rewards/rejected": -0.9597919583320618,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6,
|
| 1581 |
+
"learning_rate": 2.089842874558849e-06,
|
| 1582 |
+
"logits/chosen": 0.15783284604549408,
|
| 1583 |
+
"logits/rejected": 0.22821958363056183,
|
| 1584 |
+
"logps/chosen": -973.8444213867188,
|
| 1585 |
+
"logps/rejected": -1261.2291259765625,
|
| 1586 |
+
"loss": 1.5954,
|
| 1587 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1588 |
+
"rewards/chosen": -0.6483608484268188,
|
| 1589 |
+
"rewards/margins": 0.29802364110946655,
|
| 1590 |
+
"rewards/rejected": -0.946384608745575,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6,
|
| 1595 |
+
"learning_rate": 2.0439915765994242e-06,
|
| 1596 |
+
"logits/chosen": 0.13555693626403809,
|
| 1597 |
+
"logits/rejected": 0.15965650975704193,
|
| 1598 |
+
"logps/chosen": -1126.0108642578125,
|
| 1599 |
+
"logps/rejected": -1440.069580078125,
|
| 1600 |
+
"loss": 1.5556,
|
| 1601 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1602 |
+
"rewards/chosen": -0.7768179774284363,
|
| 1603 |
+
"rewards/margins": 0.32900911569595337,
|
| 1604 |
+
"rewards/rejected": -1.1058270931243896,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.61,
|
| 1609 |
+
"learning_rate": 1.9982984143287186e-06,
|
| 1610 |
+
"logits/chosen": 0.15475307404994965,
|
| 1611 |
+
"logits/rejected": 0.1996763050556183,
|
| 1612 |
+
"logps/chosen": -1288.257568359375,
|
| 1613 |
+
"logps/rejected": -1648.780517578125,
|
| 1614 |
+
"loss": 1.4784,
|
| 1615 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1616 |
+
"rewards/chosen": -0.8938125371932983,
|
| 1617 |
+
"rewards/margins": 0.37623515725135803,
|
| 1618 |
+
"rewards/rejected": -1.270047903060913,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.61,
|
| 1623 |
+
"learning_rate": 1.95277923333053e-06,
|
| 1624 |
+
"logits/chosen": 0.07992354780435562,
|
| 1625 |
+
"logits/rejected": 0.14772897958755493,
|
| 1626 |
+
"logps/chosen": -1287.0286865234375,
|
| 1627 |
+
"logps/rejected": -1581.1400146484375,
|
| 1628 |
+
"loss": 1.759,
|
| 1629 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1630 |
+
"rewards/chosen": -0.8965250849723816,
|
| 1631 |
+
"rewards/margins": 0.3494908809661865,
|
| 1632 |
+
"rewards/rejected": -1.2460159063339233,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.62,
|
| 1637 |
+
"learning_rate": 1.9074498188550156e-06,
|
| 1638 |
+
"logits/chosen": 0.09774446487426758,
|
| 1639 |
+
"logits/rejected": 0.14773234724998474,
|
| 1640 |
+
"logps/chosen": -1122.9798583984375,
|
| 1641 |
+
"logps/rejected": -1415.415283203125,
|
| 1642 |
+
"loss": 1.7595,
|
| 1643 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1644 |
+
"rewards/chosen": -0.7342059016227722,
|
| 1645 |
+
"rewards/margins": 0.3350808918476105,
|
| 1646 |
+
"rewards/rejected": -1.069286823272705,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.62,
|
| 1651 |
+
"learning_rate": 1.862325890344643e-06,
|
| 1652 |
+
"logits/chosen": 0.08668424934148788,
|
| 1653 |
+
"logits/rejected": 0.1557636559009552,
|
| 1654 |
+
"logps/chosen": -1046.437744140625,
|
| 1655 |
+
"logps/rejected": -1386.939208984375,
|
| 1656 |
+
"loss": 1.5183,
|
| 1657 |
+
"rewards/accuracies": 0.6875,
|
| 1658 |
+
"rewards/chosen": -0.7016348242759705,
|
| 1659 |
+
"rewards/margins": 0.36825114488601685,
|
| 1660 |
+
"rewards/rejected": -1.0698859691619873,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.63,
|
| 1665 |
+
"learning_rate": 1.817423095982972e-06,
|
| 1666 |
+
"logits/chosen": 0.12340223789215088,
|
| 1667 |
+
"logits/rejected": 0.14640815556049347,
|
| 1668 |
+
"logps/chosen": -974.4490966796875,
|
| 1669 |
+
"logps/rejected": -1238.3133544921875,
|
| 1670 |
+
"loss": 1.6995,
|
| 1671 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1672 |
+
"rewards/chosen": -0.6591961979866028,
|
| 1673 |
+
"rewards/margins": 0.2718682587146759,
|
| 1674 |
+
"rewards/rejected": -0.9310644268989563,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.63,
|
| 1679 |
+
"learning_rate": 1.7727570072681293e-06,
|
| 1680 |
+
"logits/chosen": 0.14854778349399567,
|
| 1681 |
+
"logits/rejected": 0.17698471248149872,
|
| 1682 |
+
"logps/chosen": -1057.446533203125,
|
| 1683 |
+
"logps/rejected": -1373.8194580078125,
|
| 1684 |
+
"loss": 1.6968,
|
| 1685 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1686 |
+
"rewards/chosen": -0.7261327505111694,
|
| 1687 |
+
"rewards/margins": 0.3126031458377838,
|
| 1688 |
+
"rewards/rejected": -1.0387358665466309,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.64,
|
| 1693 |
+
"learning_rate": 1.7283431136128961e-06,
|
| 1694 |
+
"logits/chosen": 0.14250560104846954,
|
| 1695 |
+
"logits/rejected": 0.17423418164253235,
|
| 1696 |
+
"logps/chosen": -1109.4017333984375,
|
| 1697 |
+
"logps/rejected": -1430.1903076171875,
|
| 1698 |
+
"loss": 1.5583,
|
| 1699 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1700 |
+
"rewards/chosen": -0.7613256573677063,
|
| 1701 |
+
"rewards/margins": 0.3207666873931885,
|
| 1702 |
+
"rewards/rejected": -1.08209228515625,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.65,
|
| 1707 |
+
"learning_rate": 1.6841968169732478e-06,
|
| 1708 |
+
"logits/chosen": 0.10577497631311417,
|
| 1709 |
+
"logits/rejected": 0.17070509493350983,
|
| 1710 |
+
"logps/chosen": -1129.2164306640625,
|
| 1711 |
+
"logps/rejected": -1423.0538330078125,
|
| 1712 |
+
"loss": 1.7291,
|
| 1713 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1714 |
+
"rewards/chosen": -0.7770806550979614,
|
| 1715 |
+
"rewards/margins": 0.32531023025512695,
|
| 1716 |
+
"rewards/rejected": -1.1023907661437988,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.65,
|
| 1721 |
+
"learning_rate": 1.6403334265072284e-06,
|
| 1722 |
+
"logits/chosen": 0.1173873171210289,
|
| 1723 |
+
"logits/rejected": 0.18929217755794525,
|
| 1724 |
+
"logps/chosen": -1162.355224609375,
|
| 1725 |
+
"logps/rejected": -1572.89306640625,
|
| 1726 |
+
"loss": 1.5668,
|
| 1727 |
+
"rewards/accuracies": 0.71875,
|
| 1728 |
+
"rewards/chosen": -0.8342976570129395,
|
| 1729 |
+
"rewards/margins": 0.41481128334999084,
|
| 1730 |
+
"rewards/rejected": -1.2491087913513184,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.66,
|
| 1735 |
+
"learning_rate": 1.5967681532660066e-06,
|
| 1736 |
+
"logits/chosen": 0.08649718761444092,
|
| 1737 |
+
"logits/rejected": 0.12614522874355316,
|
| 1738 |
+
"logps/chosen": -1182.95361328125,
|
| 1739 |
+
"logps/rejected": -1542.8983154296875,
|
| 1740 |
+
"loss": 1.552,
|
| 1741 |
+
"rewards/accuracies": 0.71875,
|
| 1742 |
+
"rewards/chosen": -0.8389142751693726,
|
| 1743 |
+
"rewards/margins": 0.3838485777378082,
|
| 1744 |
+
"rewards/rejected": -1.2227627038955688,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.66,
|
| 1749 |
+
"learning_rate": 1.5535161049189463e-06,
|
| 1750 |
+
"logits/chosen": 0.048624537885189056,
|
| 1751 |
+
"logits/rejected": 0.12681320309638977,
|
| 1752 |
+
"logps/chosen": -1181.8487548828125,
|
| 1753 |
+
"logps/rejected": -1500.6976318359375,
|
| 1754 |
+
"loss": 1.6678,
|
| 1755 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1756 |
+
"rewards/chosen": -0.8252663612365723,
|
| 1757 |
+
"rewards/margins": 0.32674065232276917,
|
| 1758 |
+
"rewards/rejected": -1.1520068645477295,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.67,
|
| 1763 |
+
"learning_rate": 1.5105922805145356e-06,
|
| 1764 |
+
"logits/chosen": 0.0684380978345871,
|
| 1765 |
+
"logits/rejected": 0.12469562143087387,
|
| 1766 |
+
"logps/chosen": -1170.2078857421875,
|
| 1767 |
+
"logps/rejected": -1520.978759765625,
|
| 1768 |
+
"loss": 1.6999,
|
| 1769 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1770 |
+
"rewards/chosen": -0.77997887134552,
|
| 1771 |
+
"rewards/margins": 0.3841548562049866,
|
| 1772 |
+
"rewards/rejected": -1.1641336679458618,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.67,
|
| 1777 |
+
"learning_rate": 1.4680115652789823e-06,
|
| 1778 |
+
"logits/chosen": 0.08953334391117096,
|
| 1779 |
+
"logits/rejected": 0.12195037305355072,
|
| 1780 |
+
"logps/chosen": -1053.8450927734375,
|
| 1781 |
+
"logps/rejected": -1404.131591796875,
|
| 1782 |
+
"loss": 1.5207,
|
| 1783 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1784 |
+
"rewards/chosen": -0.7199850082397461,
|
| 1785 |
+
"rewards/margins": 0.3669469952583313,
|
| 1786 |
+
"rewards/rejected": -1.0869319438934326,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.68,
|
| 1791 |
+
"learning_rate": 1.4257887254542767e-06,
|
| 1792 |
+
"logits/chosen": 0.06104928255081177,
|
| 1793 |
+
"logits/rejected": 0.09251236915588379,
|
| 1794 |
+
"logps/chosen": -1130.771728515625,
|
| 1795 |
+
"logps/rejected": -1455.777587890625,
|
| 1796 |
+
"loss": 1.7221,
|
| 1797 |
+
"rewards/accuracies": 0.6875,
|
| 1798 |
+
"rewards/chosen": -0.7961911559104919,
|
| 1799 |
+
"rewards/margins": 0.32651156187057495,
|
| 1800 |
+
"rewards/rejected": -1.122702717781067,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.68,
|
| 1805 |
+
"learning_rate": 1.3839384031775227e-06,
|
| 1806 |
+
"logits/chosen": 0.09284323453903198,
|
| 1807 |
+
"logits/rejected": 0.12470339238643646,
|
| 1808 |
+
"logps/chosen": -1184.2957763671875,
|
| 1809 |
+
"logps/rejected": -1491.9906005859375,
|
| 1810 |
+
"loss": 1.7259,
|
| 1811 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1812 |
+
"rewards/chosen": -0.876724362373352,
|
| 1813 |
+
"rewards/margins": 0.3096561133861542,
|
| 1814 |
+
"rewards/rejected": -1.186380386352539,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.69,
|
| 1819 |
+
"learning_rate": 1.342475111403298e-06,
|
| 1820 |
+
"logits/chosen": 0.07502352446317673,
|
| 1821 |
+
"logits/rejected": 0.16246311366558075,
|
| 1822 |
+
"logps/chosen": -1262.9688720703125,
|
| 1823 |
+
"logps/rejected": -1597.161376953125,
|
| 1824 |
+
"loss": 1.6929,
|
| 1825 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1826 |
+
"rewards/chosen": -0.899106502532959,
|
| 1827 |
+
"rewards/margins": 0.3475545048713684,
|
| 1828 |
+
"rewards/rejected": -1.2466610670089722,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.69,
|
| 1833 |
+
"learning_rate": 1.3014132288708209e-06,
|
| 1834 |
+
"logits/chosen": 0.12563182413578033,
|
| 1835 |
+
"logits/rejected": 0.18176163733005524,
|
| 1836 |
+
"logps/chosen": -1079.9150390625,
|
| 1837 |
+
"logps/rejected": -1426.569580078125,
|
| 1838 |
+
"loss": 1.5658,
|
| 1839 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1840 |
+
"rewards/chosen": -0.7534309029579163,
|
| 1841 |
+
"rewards/margins": 0.33269041776657104,
|
| 1842 |
+
"rewards/rejected": -1.0861213207244873,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7,
|
| 1847 |
+
"learning_rate": 1.2607669951176549e-06,
|
| 1848 |
+
"logits/chosen": 0.09636719524860382,
|
| 1849 |
+
"logits/rejected": 0.12595590949058533,
|
| 1850 |
+
"logps/chosen": -1216.9656982421875,
|
| 1851 |
+
"logps/rejected": -1592.846923828125,
|
| 1852 |
+
"loss": 1.5262,
|
| 1853 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1854 |
+
"rewards/chosen": -0.8419526219367981,
|
| 1855 |
+
"rewards/margins": 0.4114845395088196,
|
| 1856 |
+
"rewards/rejected": -1.2534370422363281,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"learning_rate": 1.2205505055416891e-06,
|
| 1862 |
+
"logits/chosen": 0.0674719512462616,
|
| 1863 |
+
"logits/rejected": 0.13288016617298126,
|
| 1864 |
+
"logps/chosen": -1207.83203125,
|
| 1865 |
+
"logps/rejected": -1462.1517333984375,
|
| 1866 |
+
"loss": 1.7114,
|
| 1867 |
+
"rewards/accuracies": 0.637499988079071,
|
| 1868 |
+
"rewards/chosen": -0.864331841468811,
|
| 1869 |
+
"rewards/margins": 0.288027286529541,
|
| 1870 |
+
"rewards/rejected": -1.1523590087890625,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.71,
|
| 1875 |
+
"learning_rate": 1.1807777065131002e-06,
|
| 1876 |
+
"logits/chosen": 0.07271184772253036,
|
| 1877 |
+
"logits/rejected": 0.13265785574913025,
|
| 1878 |
+
"logps/chosen": -1237.49267578125,
|
| 1879 |
+
"logps/rejected": -1638.8544921875,
|
| 1880 |
+
"loss": 1.5222,
|
| 1881 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1882 |
+
"rewards/chosen": -0.8673235774040222,
|
| 1883 |
+
"rewards/margins": 0.3971632122993469,
|
| 1884 |
+
"rewards/rejected": -1.2644867897033691,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.71,
|
| 1889 |
+
"learning_rate": 1.1414623905380012e-06,
|
| 1890 |
+
"logits/chosen": 0.07448406517505646,
|
| 1891 |
+
"logits/rejected": 0.14864052832126617,
|
| 1892 |
+
"logps/chosen": -1119.6168212890625,
|
| 1893 |
+
"logps/rejected": -1548.5118408203125,
|
| 1894 |
+
"loss": 1.4952,
|
| 1895 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1896 |
+
"rewards/chosen": -0.7575954794883728,
|
| 1897 |
+
"rewards/margins": 0.4239155352115631,
|
| 1898 |
+
"rewards/rejected": -1.1815111637115479,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.72,
|
| 1903 |
+
"learning_rate": 1.1026181914754388e-06,
|
| 1904 |
+
"logits/chosen": 0.09954806417226791,
|
| 1905 |
+
"logits/rejected": 0.16613879799842834,
|
| 1906 |
+
"logps/chosen": -1136.9033203125,
|
| 1907 |
+
"logps/rejected": -1430.72900390625,
|
| 1908 |
+
"loss": 1.6896,
|
| 1909 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1910 |
+
"rewards/chosen": -0.7874740362167358,
|
| 1911 |
+
"rewards/margins": 0.2991321086883545,
|
| 1912 |
+
"rewards/rejected": -1.0866060256958008,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.73,
|
| 1917 |
+
"learning_rate": 1.0642585798094136e-06,
|
| 1918 |
+
"logits/chosen": 0.07558660209178925,
|
| 1919 |
+
"logits/rejected": 0.1294403225183487,
|
| 1920 |
+
"logps/chosen": -1061.685302734375,
|
| 1921 |
+
"logps/rejected": -1429.032470703125,
|
| 1922 |
+
"loss": 1.5992,
|
| 1923 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1924 |
+
"rewards/chosen": -0.7224678993225098,
|
| 1925 |
+
"rewards/margins": 0.3703506588935852,
|
| 1926 |
+
"rewards/rejected": -1.0928184986114502,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.73,
|
| 1931 |
+
"learning_rate": 1.0263968579775522e-06,
|
| 1932 |
+
"logits/chosen": 0.06903640925884247,
|
| 1933 |
+
"logits/rejected": 0.14249339699745178,
|
| 1934 |
+
"logps/chosen": -1082.8212890625,
|
| 1935 |
+
"logps/rejected": -1504.9525146484375,
|
| 1936 |
+
"loss": 1.2627,
|
| 1937 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1938 |
+
"rewards/chosen": -0.7245824337005615,
|
| 1939 |
+
"rewards/margins": 0.4476887583732605,
|
| 1940 |
+
"rewards/rejected": -1.1722711324691772,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.74,
|
| 1945 |
+
"learning_rate": 9.89046155758058e-07,
|
| 1946 |
+
"logits/chosen": 0.08827939629554749,
|
| 1947 |
+
"logits/rejected": 0.15384915471076965,
|
| 1948 |
+
"logps/chosen": -1257.3944091796875,
|
| 1949 |
+
"logps/rejected": -1638.11083984375,
|
| 1950 |
+
"loss": 1.6438,
|
| 1951 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1952 |
+
"rewards/chosen": -0.8749507665634155,
|
| 1953 |
+
"rewards/margins": 0.39814838767051697,
|
| 1954 |
+
"rewards/rejected": -1.2730991840362549,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.74,
|
| 1959 |
+
"learning_rate": 9.52219425716534e-07,
|
| 1960 |
+
"logits/chosen": 0.07912211120128632,
|
| 1961 |
+
"logits/rejected": 0.10791107267141342,
|
| 1962 |
+
"logps/chosen": -1195.5802001953125,
|
| 1963 |
+
"logps/rejected": -1549.964111328125,
|
| 1964 |
+
"loss": 1.6688,
|
| 1965 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1966 |
+
"rewards/chosen": -0.8793632388114929,
|
| 1967 |
+
"rewards/margins": 0.35304269194602966,
|
| 1968 |
+
"rewards/rejected": -1.2324059009552002,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.75,
|
| 1973 |
+
"learning_rate": 9.15929438714262e-07,
|
| 1974 |
+
"logits/chosen": 0.10573384910821915,
|
| 1975 |
+
"logits/rejected": 0.1559595763683319,
|
| 1976 |
+
"logps/chosen": -1081.0791015625,
|
| 1977 |
+
"logps/rejected": -1481.296142578125,
|
| 1978 |
+
"loss": 1.4667,
|
| 1979 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1980 |
+
"rewards/chosen": -0.7587048411369324,
|
| 1981 |
+
"rewards/margins": 0.4136192798614502,
|
| 1982 |
+
"rewards/rejected": -1.1723239421844482,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.75,
|
| 1987 |
+
"learning_rate": 8.801887794794911e-07,
|
| 1988 |
+
"logits/chosen": 0.05759074538946152,
|
| 1989 |
+
"logits/rejected": 0.13223622739315033,
|
| 1990 |
+
"logps/chosen": -1182.5169677734375,
|
| 1991 |
+
"logps/rejected": -1658.713134765625,
|
| 1992 |
+
"loss": 1.3708,
|
| 1993 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1994 |
+
"rewards/chosen": -0.8255613446235657,
|
| 1995 |
+
"rewards/margins": 0.4847756028175354,
|
| 1996 |
+
"rewards/rejected": -1.3103368282318115,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.76,
|
| 2001 |
+
"learning_rate": 8.450098422432787e-07,
|
| 2002 |
+
"logits/chosen": 0.08058818429708481,
|
| 2003 |
+
"logits/rejected": 0.17761366069316864,
|
| 2004 |
+
"logps/chosen": -1177.451416015625,
|
| 2005 |
+
"logps/rejected": -1569.4161376953125,
|
| 2006 |
+
"loss": 1.7648,
|
| 2007 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2008 |
+
"rewards/chosen": -0.8251779675483704,
|
| 2009 |
+
"rewards/margins": 0.39350980520248413,
|
| 2010 |
+
"rewards/rejected": -1.218687653541565,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"learning_rate": 8.104048264413858e-07,
|
| 2016 |
+
"logits/chosen": 0.08303747326135635,
|
| 2017 |
+
"logits/rejected": 0.157932847738266,
|
| 2018 |
+
"logps/chosen": -1107.2733154296875,
|
| 2019 |
+
"logps/rejected": -1565.2877197265625,
|
| 2020 |
+
"loss": 1.3706,
|
| 2021 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2022 |
+
"rewards/chosen": -0.769390881061554,
|
| 2023 |
+
"rewards/margins": 0.4508587419986725,
|
| 2024 |
+
"rewards/rejected": -1.2202496528625488,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.77,
|
| 2029 |
+
"learning_rate": 7.763857324837321e-07,
|
| 2030 |
+
"logits/chosen": 0.0844537764787674,
|
| 2031 |
+
"logits/rejected": 0.13607878983020782,
|
| 2032 |
+
"logps/chosen": -1097.9794921875,
|
| 2033 |
+
"logps/rejected": -1437.67138671875,
|
| 2034 |
+
"loss": 1.6685,
|
| 2035 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 2036 |
+
"rewards/chosen": -0.7822902798652649,
|
| 2037 |
+
"rewards/margins": 0.364152729511261,
|
| 2038 |
+
"rewards/rejected": -1.1464428901672363,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.77,
|
| 2043 |
+
"learning_rate": 7.429643575928605e-07,
|
| 2044 |
+
"logits/chosen": 0.057485781610012054,
|
| 2045 |
+
"logits/rejected": 0.14504484832286835,
|
| 2046 |
+
"logps/chosen": -1145.53515625,
|
| 2047 |
+
"logps/rejected": -1544.49462890625,
|
| 2048 |
+
"loss": 1.6211,
|
| 2049 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2050 |
+
"rewards/chosen": -0.7827796936035156,
|
| 2051 |
+
"rewards/margins": 0.4238261580467224,
|
| 2052 |
+
"rewards/rejected": -1.2066057920455933,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.78,
|
| 2057 |
+
"learning_rate": 7.101522917128709e-07,
|
| 2058 |
+
"logits/chosen": 0.09009334444999695,
|
| 2059 |
+
"logits/rejected": 0.12808983027935028,
|
| 2060 |
+
"logps/chosen": -1061.626708984375,
|
| 2061 |
+
"logps/rejected": -1464.641357421875,
|
| 2062 |
+
"loss": 1.4222,
|
| 2063 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2064 |
+
"rewards/chosen": -0.7373768091201782,
|
| 2065 |
+
"rewards/margins": 0.39346086978912354,
|
| 2066 |
+
"rewards/rejected": -1.1308376789093018,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.78,
|
| 2071 |
+
"learning_rate": 6.779609134902312e-07,
|
| 2072 |
+
"logits/chosen": 0.11229290068149567,
|
| 2073 |
+
"logits/rejected": 0.16109147667884827,
|
| 2074 |
+
"logps/chosen": -1014.5134887695312,
|
| 2075 |
+
"logps/rejected": -1326.9337158203125,
|
| 2076 |
+
"loss": 1.724,
|
| 2077 |
+
"rewards/accuracies": 0.643750011920929,
|
| 2078 |
+
"rewards/chosen": -0.6920040845870972,
|
| 2079 |
+
"rewards/margins": 0.3285384774208069,
|
| 2080 |
+
"rewards/rejected": -1.0205425024032593,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.79,
|
| 2085 |
+
"learning_rate": 6.464013863278629e-07,
|
| 2086 |
+
"logits/chosen": 0.12503568828105927,
|
| 2087 |
+
"logits/rejected": 0.19441263377666473,
|
| 2088 |
+
"logps/chosen": -1199.6285400390625,
|
| 2089 |
+
"logps/rejected": -1496.771240234375,
|
| 2090 |
+
"loss": 1.7378,
|
| 2091 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 2092 |
+
"rewards/chosen": -0.8214676976203918,
|
| 2093 |
+
"rewards/margins": 0.3142891228199005,
|
| 2094 |
+
"rewards/rejected": -1.1357567310333252,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.79,
|
| 2099 |
+
"learning_rate": 6.154846545138696e-07,
|
| 2100 |
+
"logits/chosen": 0.09698246419429779,
|
| 2101 |
+
"logits/rejected": 0.17293763160705566,
|
| 2102 |
+
"logps/chosen": -1231.1141357421875,
|
| 2103 |
+
"logps/rejected": -1501.1031494140625,
|
| 2104 |
+
"loss": 1.9488,
|
| 2105 |
+
"rewards/accuracies": 0.625,
|
| 2106 |
+
"rewards/chosen": -0.8393710851669312,
|
| 2107 |
+
"rewards/margins": 0.2999555170536041,
|
| 2108 |
+
"rewards/rejected": -1.1393266916275024,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8,
|
| 2113 |
+
"learning_rate": 5.852214394262515e-07,
|
| 2114 |
+
"logits/chosen": 0.09356184303760529,
|
| 2115 |
+
"logits/rejected": 0.12046798318624496,
|
| 2116 |
+
"logps/chosen": -1084.208740234375,
|
| 2117 |
+
"logps/rejected": -1468.5865478515625,
|
| 2118 |
+
"loss": 1.6395,
|
| 2119 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 2120 |
+
"rewards/chosen": -0.7786747217178345,
|
| 2121 |
+
"rewards/margins": 0.34865671396255493,
|
| 2122 |
+
"rewards/rejected": -1.1273314952850342,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.81,
|
| 2127 |
+
"learning_rate": 5.556222358149191e-07,
|
| 2128 |
+
"logits/chosen": 0.06989214569330215,
|
| 2129 |
+
"logits/rejected": 0.12371733039617538,
|
| 2130 |
+
"logps/chosen": -1111.44775390625,
|
| 2131 |
+
"logps/rejected": -1397.4815673828125,
|
| 2132 |
+
"loss": 1.6382,
|
| 2133 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 2134 |
+
"rewards/chosen": -0.7657614946365356,
|
| 2135 |
+
"rewards/margins": 0.3277229070663452,
|
| 2136 |
+
"rewards/rejected": -1.0934845209121704,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.81,
|
| 2141 |
+
"learning_rate": 5.266973081622992e-07,
|
| 2142 |
+
"logits/chosen": 0.09623502939939499,
|
| 2143 |
+
"logits/rejected": 0.12523935735225677,
|
| 2144 |
+
"logps/chosen": -1027.00634765625,
|
| 2145 |
+
"logps/rejected": -1464.6611328125,
|
| 2146 |
+
"loss": 1.5786,
|
| 2147 |
+
"rewards/accuracies": 0.6875,
|
| 2148 |
+
"rewards/chosen": -0.7143763899803162,
|
| 2149 |
+
"rewards/margins": 0.40375128388404846,
|
| 2150 |
+
"rewards/rejected": -1.118127703666687,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.82,
|
| 2155 |
+
"learning_rate": 4.984566871237942e-07,
|
| 2156 |
+
"logits/chosen": 0.12962420284748077,
|
| 2157 |
+
"logits/rejected": 0.18393470346927643,
|
| 2158 |
+
"logps/chosen": -1017.5735473632812,
|
| 2159 |
+
"logps/rejected": -1400.67138671875,
|
| 2160 |
+
"loss": 1.5976,
|
| 2161 |
+
"rewards/accuracies": 0.668749988079071,
|
| 2162 |
+
"rewards/chosen": -0.7108270525932312,
|
| 2163 |
+
"rewards/margins": 0.38168221712112427,
|
| 2164 |
+
"rewards/rejected": -1.092509150505066,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.82,
|
| 2169 |
+
"learning_rate": 4.709101660493251e-07,
|
| 2170 |
+
"logits/chosen": 0.11588941514492035,
|
| 2171 |
+
"logits/rejected": 0.199117973446846,
|
| 2172 |
+
"logps/chosen": -1026.5185546875,
|
| 2173 |
+
"logps/rejected": -1404.314208984375,
|
| 2174 |
+
"loss": 1.5534,
|
| 2175 |
+
"rewards/accuracies": 0.71875,
|
| 2176 |
+
"rewards/chosen": -0.6769729852676392,
|
| 2177 |
+
"rewards/margins": 0.3804163932800293,
|
| 2178 |
+
"rewards/rejected": -1.0573893785476685,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.83,
|
| 2183 |
+
"learning_rate": 4.440672975871743e-07,
|
| 2184 |
+
"logits/chosen": 0.08243189007043839,
|
| 2185 |
+
"logits/rejected": 0.17241016030311584,
|
| 2186 |
+
"logps/chosen": -1097.091552734375,
|
| 2187 |
+
"logps/rejected": -1497.203857421875,
|
| 2188 |
+
"loss": 1.362,
|
| 2189 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 2190 |
+
"rewards/chosen": -0.722274661064148,
|
| 2191 |
+
"rewards/margins": 0.4388486444950104,
|
| 2192 |
+
"rewards/rejected": -1.1611233949661255,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.83,
|
| 2197 |
+
"learning_rate": 4.1793739037129134e-07,
|
| 2198 |
+
"logits/chosen": 0.08427461236715317,
|
| 2199 |
+
"logits/rejected": 0.15939496457576752,
|
| 2200 |
+
"logps/chosen": -1080.250732421875,
|
| 2201 |
+
"logps/rejected": -1431.294677734375,
|
| 2202 |
+
"loss": 1.5649,
|
| 2203 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 2204 |
+
"rewards/chosen": -0.7504817247390747,
|
| 2205 |
+
"rewards/margins": 0.3592514097690582,
|
| 2206 |
+
"rewards/rejected": -1.1097332239151,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.84,
|
| 2211 |
+
"learning_rate": 3.9252950579322405e-07,
|
| 2212 |
+
"logits/chosen": 0.09509806334972382,
|
| 2213 |
+
"logits/rejected": 0.14530691504478455,
|
| 2214 |
+
"logps/chosen": -1005.5162353515625,
|
| 2215 |
+
"logps/rejected": -1375.9266357421875,
|
| 2216 |
+
"loss": 1.5294,
|
| 2217 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2218 |
+
"rewards/chosen": -0.6889379620552063,
|
| 2219 |
+
"rewards/margins": 0.3749217092990875,
|
| 2220 |
+
"rewards/rejected": -1.0638595819473267,
|
| 2221 |
+
"step": 1570
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.84,
|
| 2225 |
+
"learning_rate": 3.6785245485978864e-07,
|
| 2226 |
+
"logits/chosen": 0.13486482203006744,
|
| 2227 |
+
"logits/rejected": 0.12031221389770508,
|
| 2228 |
+
"logps/chosen": -1113.1337890625,
|
| 2229 |
+
"logps/rejected": -1436.71337890625,
|
| 2230 |
+
"loss": 1.7315,
|
| 2231 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 2232 |
+
"rewards/chosen": -0.7942808866500854,
|
| 2233 |
+
"rewards/margins": 0.31816208362579346,
|
| 2234 |
+
"rewards/rejected": -1.112442970275879,
|
| 2235 |
+
"step": 1580
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.85,
|
| 2239 |
+
"learning_rate": 3.43914795137566e-07,
|
| 2240 |
+
"logits/chosen": 0.12698054313659668,
|
| 2241 |
+
"logits/rejected": 0.20286865532398224,
|
| 2242 |
+
"logps/chosen": -1038.547607421875,
|
| 2243 |
+
"logps/rejected": -1364.681396484375,
|
| 2244 |
+
"loss": 1.6174,
|
| 2245 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 2246 |
+
"rewards/chosen": -0.7222835421562195,
|
| 2247 |
+
"rewards/margins": 0.33720117807388306,
|
| 2248 |
+
"rewards/rejected": -1.0594847202301025,
|
| 2249 |
+
"step": 1590
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.85,
|
| 2253 |
+
"learning_rate": 3.207248277852901e-07,
|
| 2254 |
+
"logits/chosen": 0.11406983435153961,
|
| 2255 |
+
"logits/rejected": 0.19401147961616516,
|
| 2256 |
+
"logps/chosen": -1013.9378051757812,
|
| 2257 |
+
"logps/rejected": -1410.285888671875,
|
| 2258 |
+
"loss": 1.5172,
|
| 2259 |
+
"rewards/accuracies": 0.606249988079071,
|
| 2260 |
+
"rewards/chosen": -0.6757684946060181,
|
| 2261 |
+
"rewards/margins": 0.38184699416160583,
|
| 2262 |
+
"rewards/rejected": -1.0576155185699463,
|
| 2263 |
+
"step": 1600
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.86,
|
| 2267 |
+
"learning_rate": 2.9829059467515074e-07,
|
| 2268 |
+
"logits/chosen": 0.11214902251958847,
|
| 2269 |
+
"logits/rejected": 0.13649222254753113,
|
| 2270 |
+
"logps/chosen": -1164.2906494140625,
|
| 2271 |
+
"logps/rejected": -1486.5689697265625,
|
| 2272 |
+
"loss": 1.6461,
|
| 2273 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 2274 |
+
"rewards/chosen": -0.8062076568603516,
|
| 2275 |
+
"rewards/margins": 0.3245384097099304,
|
| 2276 |
+
"rewards/rejected": -1.1307461261749268,
|
| 2277 |
+
"step": 1610
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.86,
|
| 2281 |
+
"learning_rate": 2.766198756040153e-07,
|
| 2282 |
+
"logits/chosen": 0.11051913350820541,
|
| 2283 |
+
"logits/rejected": 0.1855718195438385,
|
| 2284 |
+
"logps/chosen": -1100.14501953125,
|
| 2285 |
+
"logps/rejected": -1472.6260986328125,
|
| 2286 |
+
"loss": 1.5808,
|
| 2287 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2288 |
+
"rewards/chosen": -0.7349221706390381,
|
| 2289 |
+
"rewards/margins": 0.3916444778442383,
|
| 2290 |
+
"rewards/rejected": -1.1265666484832764,
|
| 2291 |
+
"step": 1620
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.87,
|
| 2295 |
+
"learning_rate": 2.5572018559553155e-07,
|
| 2296 |
+
"logits/chosen": 0.1027497872710228,
|
| 2297 |
+
"logits/rejected": 0.13441568613052368,
|
| 2298 |
+
"logps/chosen": -1062.0927734375,
|
| 2299 |
+
"logps/rejected": -1416.841064453125,
|
| 2300 |
+
"loss": 1.5722,
|
| 2301 |
+
"rewards/accuracies": 0.675000011920929,
|
| 2302 |
+
"rewards/chosen": -0.7326242327690125,
|
| 2303 |
+
"rewards/margins": 0.36529573798179626,
|
| 2304 |
+
"rewards/rejected": -1.0979200601577759,
|
| 2305 |
+
"step": 1630
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.87,
|
| 2309 |
+
"learning_rate": 2.3559877229404864e-07,
|
| 2310 |
+
"logits/chosen": 0.0654052123427391,
|
| 2311 |
+
"logits/rejected": 0.14604170620441437,
|
| 2312 |
+
"logps/chosen": -1041.9859619140625,
|
| 2313 |
+
"logps/rejected": -1462.3514404296875,
|
| 2314 |
+
"loss": 1.3094,
|
| 2315 |
+
"rewards/accuracies": 0.737500011920929,
|
| 2316 |
+
"rewards/chosen": -0.6855828166007996,
|
| 2317 |
+
"rewards/margins": 0.435748428106308,
|
| 2318 |
+
"rewards/rejected": -1.1213312149047852,
|
| 2319 |
+
"step": 1640
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.88,
|
| 2323 |
+
"learning_rate": 2.1626261345126576e-07,
|
| 2324 |
+
"logits/chosen": 0.10176499933004379,
|
| 2325 |
+
"logits/rejected": 0.12414362281560898,
|
| 2326 |
+
"logps/chosen": -1152.2626953125,
|
| 2327 |
+
"logps/rejected": -1480.9588623046875,
|
| 2328 |
+
"loss": 1.5617,
|
| 2329 |
+
"rewards/accuracies": 0.6875,
|
| 2330 |
+
"rewards/chosen": -0.779994547367096,
|
| 2331 |
+
"rewards/margins": 0.3541329503059387,
|
| 2332 |
+
"rewards/rejected": -1.1341274976730347,
|
| 2333 |
+
"step": 1650
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.89,
|
| 2337 |
+
"learning_rate": 1.9771841450646505e-07,
|
| 2338 |
+
"logits/chosen": 0.09231498837471008,
|
| 2339 |
+
"logits/rejected": 0.15306654572486877,
|
| 2340 |
+
"logps/chosen": -1075.6600341796875,
|
| 2341 |
+
"logps/rejected": -1482.9368896484375,
|
| 2342 |
+
"loss": 1.4986,
|
| 2343 |
+
"rewards/accuracies": 0.75,
|
| 2344 |
+
"rewards/chosen": -0.7160147428512573,
|
| 2345 |
+
"rewards/margins": 0.4125767648220062,
|
| 2346 |
+
"rewards/rejected": -1.1285914182662964,
|
| 2347 |
+
"step": 1660
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.89,
|
| 2351 |
+
"learning_rate": 1.7997260626118758e-07,
|
| 2352 |
+
"logits/chosen": 0.07871339470148087,
|
| 2353 |
+
"logits/rejected": 0.1630566418170929,
|
| 2354 |
+
"logps/chosen": -1022.990234375,
|
| 2355 |
+
"logps/rejected": -1364.323974609375,
|
| 2356 |
+
"loss": 1.532,
|
| 2357 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2358 |
+
"rewards/chosen": -0.6643663048744202,
|
| 2359 |
+
"rewards/margins": 0.3671983480453491,
|
| 2360 |
+
"rewards/rejected": -1.031564474105835,
|
| 2361 |
+
"step": 1670
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9,
|
| 2365 |
+
"learning_rate": 1.6303134264914365e-07,
|
| 2366 |
+
"logits/chosen": 0.05614648386836052,
|
| 2367 |
+
"logits/rejected": 0.13106751441955566,
|
| 2368 |
+
"logps/chosen": -1096.6705322265625,
|
| 2369 |
+
"logps/rejected": -1407.255615234375,
|
| 2370 |
+
"loss": 1.5868,
|
| 2371 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 2372 |
+
"rewards/chosen": -0.7051296234130859,
|
| 2373 |
+
"rewards/margins": 0.3592469096183777,
|
| 2374 |
+
"rewards/rejected": -1.0643765926361084,
|
| 2375 |
+
"step": 1680
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9,
|
| 2379 |
+
"learning_rate": 1.469004986021355e-07,
|
| 2380 |
+
"logits/chosen": 0.08326787501573563,
|
| 2381 |
+
"logits/rejected": 0.14079895615577698,
|
| 2382 |
+
"logps/chosen": -1091.39697265625,
|
| 2383 |
+
"logps/rejected": -1426.65283203125,
|
| 2384 |
+
"loss": 1.7203,
|
| 2385 |
+
"rewards/accuracies": 0.668749988079071,
|
| 2386 |
+
"rewards/chosen": -0.73790043592453,
|
| 2387 |
+
"rewards/margins": 0.3496142029762268,
|
| 2388 |
+
"rewards/rejected": -1.0875146389007568,
|
| 2389 |
+
"step": 1690
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.91,
|
| 2393 |
+
"learning_rate": 1.315856680127367e-07,
|
| 2394 |
+
"logits/chosen": 0.07813490927219391,
|
| 2395 |
+
"logits/rejected": 0.18866008520126343,
|
| 2396 |
+
"logps/chosen": -1085.9488525390625,
|
| 2397 |
+
"logps/rejected": -1426.083251953125,
|
| 2398 |
+
"loss": 1.7138,
|
| 2399 |
+
"rewards/accuracies": 0.637499988079071,
|
| 2400 |
+
"rewards/chosen": -0.743714451789856,
|
| 2401 |
+
"rewards/margins": 0.342837393283844,
|
| 2402 |
+
"rewards/rejected": -1.0865519046783447,
|
| 2403 |
+
"step": 1700
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.91,
|
| 2407 |
+
"learning_rate": 1.1709216179442817e-07,
|
| 2408 |
+
"logits/chosen": 0.07439470291137695,
|
| 2409 |
+
"logits/rejected": 0.14408041536808014,
|
| 2410 |
+
"logps/chosen": -1104.112548828125,
|
| 2411 |
+
"logps/rejected": -1494.4288330078125,
|
| 2412 |
+
"loss": 1.3662,
|
| 2413 |
+
"rewards/accuracies": 0.75,
|
| 2414 |
+
"rewards/chosen": -0.7067037224769592,
|
| 2415 |
+
"rewards/margins": 0.4223453104496002,
|
| 2416 |
+
"rewards/rejected": -1.1290490627288818,
|
| 2417 |
+
"step": 1710
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.92,
|
| 2421 |
+
"learning_rate": 1.0342500603986421e-07,
|
| 2422 |
+
"logits/chosen": 0.06722331047058105,
|
| 2423 |
+
"logits/rejected": 0.10560252517461777,
|
| 2424 |
+
"logps/chosen": -989.7840576171875,
|
| 2425 |
+
"logps/rejected": -1307.6107177734375,
|
| 2426 |
+
"loss": 1.7934,
|
| 2427 |
+
"rewards/accuracies": 0.699999988079071,
|
| 2428 |
+
"rewards/chosen": -0.6622638702392578,
|
| 2429 |
+
"rewards/margins": 0.3219539523124695,
|
| 2430 |
+
"rewards/rejected": -0.9842178225517273,
|
| 2431 |
+
"step": 1720
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.92,
|
| 2435 |
+
"learning_rate": 9.058894027791643e-08,
|
| 2436 |
+
"logits/chosen": 0.08770893514156342,
|
| 2437 |
+
"logits/rejected": 0.15539699792861938,
|
| 2438 |
+
"logps/chosen": -1029.530517578125,
|
| 2439 |
+
"logps/rejected": -1314.664306640625,
|
| 2440 |
+
"loss": 1.8332,
|
| 2441 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 2442 |
+
"rewards/chosen": -0.6983517408370972,
|
| 2443 |
+
"rewards/margins": 0.2923336625099182,
|
| 2444 |
+
"rewards/rejected": -0.9906853437423706,
|
| 2445 |
+
"step": 1730
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.93,
|
| 2449 |
+
"learning_rate": 7.858841583008592e-08,
|
| 2450 |
+
"logits/chosen": 0.1337372064590454,
|
| 2451 |
+
"logits/rejected": 0.17292381823062897,
|
| 2452 |
+
"logps/chosen": -989.8046875,
|
| 2453 |
+
"logps/rejected": -1368.048095703125,
|
| 2454 |
+
"loss": 1.5287,
|
| 2455 |
+
"rewards/accuracies": 0.6875,
|
| 2456 |
+
"rewards/chosen": -0.6523457765579224,
|
| 2457 |
+
"rewards/margins": 0.3857383131980896,
|
| 2458 |
+
"rewards/rejected": -1.0380841493606567,
|
| 2459 |
+
"step": 1740
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.93,
|
| 2463 |
+
"learning_rate": 6.742759426686313e-08,
|
| 2464 |
+
"logits/chosen": 0.12590888142585754,
|
| 2465 |
+
"logits/rejected": 0.17510025203227997,
|
| 2466 |
+
"logps/chosen": -1068.725830078125,
|
| 2467 |
+
"logps/rejected": -1355.000244140625,
|
| 2468 |
+
"loss": 1.5962,
|
| 2469 |
+
"rewards/accuracies": 0.706250011920929,
|
| 2470 |
+
"rewards/chosen": -0.6910558938980103,
|
| 2471 |
+
"rewards/margins": 0.33794966340065,
|
| 2472 |
+
"rewards/rejected": -1.029005527496338,
|
| 2473 |
+
"step": 1750
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.94,
|
| 2477 |
+
"learning_rate": 5.7110345964571104e-08,
|
| 2478 |
+
"logits/chosen": 0.09558887034654617,
|
| 2479 |
+
"logits/rejected": 0.15812750160694122,
|
| 2480 |
+
"logps/chosen": -1157.002685546875,
|
| 2481 |
+
"logps/rejected": -1459.370849609375,
|
| 2482 |
+
"loss": 1.5588,
|
| 2483 |
+
"rewards/accuracies": 0.699999988079071,
|
| 2484 |
+
"rewards/chosen": -0.7800796627998352,
|
| 2485 |
+
"rewards/margins": 0.33304229378700256,
|
| 2486 |
+
"rewards/rejected": -1.1131219863891602,
|
| 2487 |
+
"step": 1760
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.94,
|
| 2491 |
+
"learning_rate": 4.764024876318357e-08,
|
| 2492 |
+
"logits/chosen": 0.08710858970880508,
|
| 2493 |
+
"logits/rejected": 0.16179919242858887,
|
| 2494 |
+
"logps/chosen": -1023.4801025390625,
|
| 2495 |
+
"logps/rejected": -1355.501953125,
|
| 2496 |
+
"loss": 1.711,
|
| 2497 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 2498 |
+
"rewards/chosen": -0.7188773155212402,
|
| 2499 |
+
"rewards/margins": 0.3240003287792206,
|
| 2500 |
+
"rewards/rejected": -1.0428775548934937,
|
| 2501 |
+
"step": 1770
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.95,
|
| 2505 |
+
"learning_rate": 3.902058672559633e-08,
|
| 2506 |
+
"logits/chosen": 0.13087372481822968,
|
| 2507 |
+
"logits/rejected": 0.18574543297290802,
|
| 2508 |
+
"logps/chosen": -1036.978759765625,
|
| 2509 |
+
"logps/rejected": -1390.5789794921875,
|
| 2510 |
+
"loss": 1.5651,
|
| 2511 |
+
"rewards/accuracies": 0.6875,
|
| 2512 |
+
"rewards/chosen": -0.6995924711227417,
|
| 2513 |
+
"rewards/margins": 0.35320958495140076,
|
| 2514 |
+
"rewards/rejected": -1.0528020858764648,
|
| 2515 |
+
"step": 1780
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.95,
|
| 2519 |
+
"learning_rate": 3.125434899876933e-08,
|
| 2520 |
+
"logits/chosen": 0.09127840399742126,
|
| 2521 |
+
"logits/rejected": 0.18651551008224487,
|
| 2522 |
+
"logps/chosen": -1081.856201171875,
|
| 2523 |
+
"logps/rejected": -1476.410888671875,
|
| 2524 |
+
"loss": 1.5536,
|
| 2525 |
+
"rewards/accuracies": 0.6875,
|
| 2526 |
+
"rewards/chosen": -0.7147141098976135,
|
| 2527 |
+
"rewards/margins": 0.4145401120185852,
|
| 2528 |
+
"rewards/rejected": -1.1292542219161987,
|
| 2529 |
+
"step": 1790
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.96,
|
| 2533 |
+
"learning_rate": 2.4344228777145873e-08,
|
| 2534 |
+
"logits/chosen": 0.0788322165608406,
|
| 2535 |
+
"logits/rejected": 0.1238178238272667,
|
| 2536 |
+
"logps/chosen": -986.0138549804688,
|
| 2537 |
+
"logps/rejected": -1424.9691162109375,
|
| 2538 |
+
"loss": 1.6491,
|
| 2539 |
+
"rewards/accuracies": 0.6875,
|
| 2540 |
+
"rewards/chosen": -0.6681248545646667,
|
| 2541 |
+
"rewards/margins": 0.41846686601638794,
|
| 2542 |
+
"rewards/rejected": -1.0865918397903442,
|
| 2543 |
+
"step": 1800
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.97,
|
| 2547 |
+
"learning_rate": 1.829262236869772e-08,
|
| 2548 |
+
"logits/chosen": 0.11619732528924942,
|
| 2549 |
+
"logits/rejected": 0.17705723643302917,
|
| 2550 |
+
"logps/chosen": -1101.0535888671875,
|
| 2551 |
+
"logps/rejected": -1451.33544921875,
|
| 2552 |
+
"loss": 1.5375,
|
| 2553 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2554 |
+
"rewards/chosen": -0.7447971105575562,
|
| 2555 |
+
"rewards/margins": 0.3711633086204529,
|
| 2556 |
+
"rewards/rejected": -1.1159603595733643,
|
| 2557 |
+
"step": 1810
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.97,
|
| 2561 |
+
"learning_rate": 1.3101628363929586e-08,
|
| 2562 |
+
"logits/chosen": 0.07590712606906891,
|
| 2563 |
+
"logits/rejected": 0.10692886263132095,
|
| 2564 |
+
"logps/chosen": -1034.286376953125,
|
| 2565 |
+
"logps/rejected": -1416.898681640625,
|
| 2566 |
+
"loss": 1.4333,
|
| 2567 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 2568 |
+
"rewards/chosen": -0.6867724657058716,
|
| 2569 |
+
"rewards/margins": 0.39223819971084595,
|
| 2570 |
+
"rewards/rejected": -1.0790107250213623,
|
| 2571 |
+
"step": 1820
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.98,
|
| 2575 |
+
"learning_rate": 8.773046908123195e-09,
|
| 2576 |
+
"logits/chosen": 0.11580286175012589,
|
| 2577 |
+
"logits/rejected": 0.17976327240467072,
|
| 2578 |
+
"logps/chosen": -1056.7957763671875,
|
| 2579 |
+
"logps/rejected": -1410.120361328125,
|
| 2580 |
+
"loss": 1.5549,
|
| 2581 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 2582 |
+
"rewards/chosen": -0.6937663555145264,
|
| 2583 |
+
"rewards/margins": 0.37733033299446106,
|
| 2584 |
+
"rewards/rejected": -1.071096658706665,
|
| 2585 |
+
"step": 1830
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.98,
|
| 2589 |
+
"learning_rate": 5.308379077080817e-09,
|
| 2590 |
+
"logits/chosen": 0.08766238391399384,
|
| 2591 |
+
"logits/rejected": 0.15721826255321503,
|
| 2592 |
+
"logps/chosen": -1196.5023193359375,
|
| 2593 |
+
"logps/rejected": -1440.4573974609375,
|
| 2594 |
+
"loss": 1.7298,
|
| 2595 |
+
"rewards/accuracies": 0.668749988079071,
|
| 2596 |
+
"rewards/chosen": -0.7777877449989319,
|
| 2597 |
+
"rewards/margins": 0.31406041979789734,
|
| 2598 |
+
"rewards/rejected": -1.0918481349945068,
|
| 2599 |
+
"step": 1840
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.99,
|
| 2603 |
+
"learning_rate": 2.7088263565760996e-09,
|
| 2604 |
+
"logits/chosen": 0.05079632252454758,
|
| 2605 |
+
"logits/rejected": 0.1428813636302948,
|
| 2606 |
+
"logps/chosen": -1076.935302734375,
|
| 2607 |
+
"logps/rejected": -1446.3316650390625,
|
| 2608 |
+
"loss": 1.482,
|
| 2609 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 2610 |
+
"rewards/chosen": -0.7342230081558228,
|
| 2611 |
+
"rewards/margins": 0.37562787532806396,
|
| 2612 |
+
"rewards/rejected": -1.1098508834838867,
|
| 2613 |
+
"step": 1850
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.99,
|
| 2617 |
+
"learning_rate": 9.752902257023633e-10,
|
| 2618 |
+
"logits/chosen": 0.07703147828578949,
|
| 2619 |
+
"logits/rejected": 0.13958509266376495,
|
| 2620 |
+
"logps/chosen": -1000.0032348632812,
|
| 2621 |
+
"logps/rejected": -1295.458984375,
|
| 2622 |
+
"loss": 1.8327,
|
| 2623 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 2624 |
+
"rewards/chosen": -0.6804636716842651,
|
| 2625 |
+
"rewards/margins": 0.2884565591812134,
|
| 2626 |
+
"rewards/rejected": -0.9689203500747681,
|
| 2627 |
+
"step": 1860
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.0,
|
| 2631 |
+
"learning_rate": 1.083718442532189e-10,
|
| 2632 |
+
"logits/chosen": 0.09295358508825302,
|
| 2633 |
+
"logits/rejected": 0.16223040223121643,
|
| 2634 |
+
"logps/chosen": -1160.269287109375,
|
| 2635 |
+
"logps/rejected": -1494.4976806640625,
|
| 2636 |
+
"loss": 1.5841,
|
| 2637 |
+
"rewards/accuracies": 0.643750011920929,
|
| 2638 |
+
"rewards/chosen": -0.7781329154968262,
|
| 2639 |
+
"rewards/margins": 0.3674696981906891,
|
| 2640 |
+
"rewards/rejected": -1.1456025838851929,
|
| 2641 |
+
"step": 1870
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.0,
|
| 2645 |
+
"step": 1875,
|
| 2646 |
+
"total_flos": 0.0,
|
| 2647 |
+
"train_loss": 1.579099040222168,
|
| 2648 |
+
"train_runtime": 16673.7788,
|
| 2649 |
+
"train_samples_per_second": 1.799,
|
| 2650 |
+
"train_steps_per_second": 0.112
|
| 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 |
+
}
|