Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May17_08-41-46_gpu4-119-5/events.out.tfevents.1715899457.gpu4-119-5.1248913.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +1346 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-v37-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-v37-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 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.7.1
|
| 59 |
+
- Transformers 4.36.2
|
| 60 |
+
- Pytorch 2.1.2+cu121
|
| 61 |
+
- Datasets 2.14.6
|
| 62 |
+
- 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 sha256:82ddaad12b3df537ff0a2bc9d84260aecdda8c34fe49e0605878ed9f07eb5d18
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.24207222728871738,
|
| 4 |
+
"train_runtime": 8784.9129,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.415,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
runs/May17_08-41-46_gpu4-119-5/events.out.tfevents.1715899457.gpu4-119-5.1248913.0
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 sha256:6c3624b3ee1bda30329335296478ea4e9edc1f0958866a6759598c4cafc3d8cd
|
| 3 |
+
size 51471
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.24207222728871738,
|
| 4 |
+
"train_runtime": 8784.9129,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 3.415,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994666666666666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 937,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.319148936170213e-08,
|
| 14 |
+
"logits/chosen": 0.22503182291984558,
|
| 15 |
+
"logits/rejected": 0.20745767652988434,
|
| 16 |
+
"logps/chosen": -503.960205078125,
|
| 17 |
+
"logps/rejected": -393.79901123046875,
|
| 18 |
+
"loss": 0.3545,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 5.319148936170213e-07,
|
| 28 |
+
"logits/chosen": 0.13639158010482788,
|
| 29 |
+
"logits/rejected": 0.23417764902114868,
|
| 30 |
+
"logps/chosen": -312.29608154296875,
|
| 31 |
+
"logps/rejected": -286.0322265625,
|
| 32 |
+
"loss": 0.3609,
|
| 33 |
+
"rewards/accuracies": 0.4305555522441864,
|
| 34 |
+
"rewards/chosen": 9.671921725384891e-05,
|
| 35 |
+
"rewards/margins": 8.819119102554396e-05,
|
| 36 |
+
"rewards/rejected": 8.528020771336742e-06,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.1057649701833725,
|
| 43 |
+
"logits/rejected": 0.17593668401241302,
|
| 44 |
+
"logps/chosen": -372.1605529785156,
|
| 45 |
+
"logps/rejected": -358.22869873046875,
|
| 46 |
+
"loss": 0.3704,
|
| 47 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 48 |
+
"rewards/chosen": 7.727816409897059e-05,
|
| 49 |
+
"rewards/margins": 0.00010253030632156879,
|
| 50 |
+
"rewards/rejected": -2.5252131308661774e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.11514975130558014,
|
| 57 |
+
"logits/rejected": 0.20654134452342987,
|
| 58 |
+
"logps/chosen": -371.88287353515625,
|
| 59 |
+
"logps/rejected": -313.6852722167969,
|
| 60 |
+
"loss": 0.3724,
|
| 61 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 62 |
+
"rewards/chosen": 5.6704669987084344e-05,
|
| 63 |
+
"rewards/margins": 4.732383786176797e-06,
|
| 64 |
+
"rewards/rejected": 5.197228165343404e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.08795060217380524,
|
| 71 |
+
"logits/rejected": 0.2017325907945633,
|
| 72 |
+
"logps/chosen": -372.4765930175781,
|
| 73 |
+
"logps/rejected": -345.6024475097656,
|
| 74 |
+
"loss": 0.3779,
|
| 75 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 76 |
+
"rewards/chosen": 0.00011807264672825113,
|
| 77 |
+
"rewards/margins": -1.2403141226968728e-05,
|
| 78 |
+
"rewards/rejected": 0.00013047578977420926,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.12501904368400574,
|
| 85 |
+
"logits/rejected": 0.1548817902803421,
|
| 86 |
+
"logps/chosen": -319.83941650390625,
|
| 87 |
+
"logps/rejected": -304.3211975097656,
|
| 88 |
+
"loss": 0.3743,
|
| 89 |
+
"rewards/accuracies": 0.550000011920929,
|
| 90 |
+
"rewards/chosen": 0.000266839109826833,
|
| 91 |
+
"rewards/margins": 0.0005234330310486257,
|
| 92 |
+
"rewards/rejected": -0.00025659389211796224,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": 0.056398905813694,
|
| 99 |
+
"logits/rejected": 0.16611042618751526,
|
| 100 |
+
"logps/chosen": -342.92767333984375,
|
| 101 |
+
"logps/rejected": -301.9825744628906,
|
| 102 |
+
"loss": 0.3686,
|
| 103 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 104 |
+
"rewards/chosen": 0.0005045770085416734,
|
| 105 |
+
"rewards/margins": 0.0005726306699216366,
|
| 106 |
+
"rewards/rejected": -6.805359589634463e-05,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.1134648472070694,
|
| 113 |
+
"logits/rejected": 0.15889659523963928,
|
| 114 |
+
"logps/chosen": -367.37451171875,
|
| 115 |
+
"logps/rejected": -299.69818115234375,
|
| 116 |
+
"loss": 0.3747,
|
| 117 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 118 |
+
"rewards/chosen": 0.0005155171384103596,
|
| 119 |
+
"rewards/margins": 0.0006443473394028842,
|
| 120 |
+
"rewards/rejected": -0.0001288302446482703,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": 0.14280062913894653,
|
| 127 |
+
"logits/rejected": 0.17763297259807587,
|
| 128 |
+
"logps/chosen": -384.6070251464844,
|
| 129 |
+
"logps/rejected": -323.2566223144531,
|
| 130 |
+
"loss": 0.3719,
|
| 131 |
+
"rewards/accuracies": 0.574999988079071,
|
| 132 |
+
"rewards/chosen": 0.0013791865203529596,
|
| 133 |
+
"rewards/margins": 0.001650324440561235,
|
| 134 |
+
"rewards/rejected": -0.00027113803662359715,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": 0.11830653250217438,
|
| 141 |
+
"logits/rejected": 0.18050488829612732,
|
| 142 |
+
"logps/chosen": -299.129638671875,
|
| 143 |
+
"logps/rejected": -308.74737548828125,
|
| 144 |
+
"loss": 0.3591,
|
| 145 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 146 |
+
"rewards/chosen": 0.0019053416326642036,
|
| 147 |
+
"rewards/margins": 0.0032806836534291506,
|
| 148 |
+
"rewards/rejected": -0.001375342020764947,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": 0.099853515625,
|
| 155 |
+
"logits/rejected": 0.20920684933662415,
|
| 156 |
+
"logps/chosen": -351.15936279296875,
|
| 157 |
+
"logps/rejected": -335.2391662597656,
|
| 158 |
+
"loss": 0.3606,
|
| 159 |
+
"rewards/accuracies": 0.606249988079071,
|
| 160 |
+
"rewards/chosen": 0.0006141302874311805,
|
| 161 |
+
"rewards/margins": 0.005217243917286396,
|
| 162 |
+
"rewards/rejected": -0.004603113513439894,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": 0.07743649184703827,
|
| 169 |
+
"logits/rejected": 0.1303156465291977,
|
| 170 |
+
"logps/chosen": -312.6484375,
|
| 171 |
+
"logps/rejected": -312.4829406738281,
|
| 172 |
+
"loss": 0.3599,
|
| 173 |
+
"rewards/accuracies": 0.59375,
|
| 174 |
+
"rewards/chosen": -0.004017535597085953,
|
| 175 |
+
"rewards/margins": 0.00877195131033659,
|
| 176 |
+
"rewards/rejected": -0.012789485976099968,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": 0.05438951402902603,
|
| 183 |
+
"logits/rejected": 0.15021613240242004,
|
| 184 |
+
"logps/chosen": -383.91510009765625,
|
| 185 |
+
"logps/rejected": -360.8976745605469,
|
| 186 |
+
"loss": 0.3608,
|
| 187 |
+
"rewards/accuracies": 0.625,
|
| 188 |
+
"rewards/chosen": -0.020418299362063408,
|
| 189 |
+
"rewards/margins": 0.013604333624243736,
|
| 190 |
+
"rewards/rejected": -0.034022632986307144,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": 0.06449095904827118,
|
| 197 |
+
"logits/rejected": 0.11669395118951797,
|
| 198 |
+
"logps/chosen": -372.52386474609375,
|
| 199 |
+
"logps/rejected": -411.42388916015625,
|
| 200 |
+
"loss": 0.343,
|
| 201 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 202 |
+
"rewards/chosen": -0.03320731967687607,
|
| 203 |
+
"rewards/margins": 0.03409535437822342,
|
| 204 |
+
"rewards/rejected": -0.06730266660451889,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": 0.04302512854337692,
|
| 211 |
+
"logits/rejected": 0.050311993807554245,
|
| 212 |
+
"logps/chosen": -413.1893005371094,
|
| 213 |
+
"logps/rejected": -404.35516357421875,
|
| 214 |
+
"loss": 0.351,
|
| 215 |
+
"rewards/accuracies": 0.574999988079071,
|
| 216 |
+
"rewards/chosen": -0.06032940745353699,
|
| 217 |
+
"rewards/margins": 0.03157948702573776,
|
| 218 |
+
"rewards/rejected": -0.09190888702869415,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": 0.03025934100151062,
|
| 225 |
+
"logits/rejected": 0.11820876598358154,
|
| 226 |
+
"logps/chosen": -419.5621643066406,
|
| 227 |
+
"logps/rejected": -454.58148193359375,
|
| 228 |
+
"loss": 0.3325,
|
| 229 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 230 |
+
"rewards/chosen": -0.07952941954135895,
|
| 231 |
+
"rewards/margins": 0.04821295291185379,
|
| 232 |
+
"rewards/rejected": -0.12774237990379333,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": 0.09332932531833649,
|
| 239 |
+
"logits/rejected": 0.1296716332435608,
|
| 240 |
+
"logps/chosen": -410.50634765625,
|
| 241 |
+
"logps/rejected": -435.3250427246094,
|
| 242 |
+
"loss": 0.3517,
|
| 243 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 244 |
+
"rewards/chosen": -0.09774389117956161,
|
| 245 |
+
"rewards/margins": 0.045623380690813065,
|
| 246 |
+
"rewards/rejected": -0.14336727559566498,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": 0.035608045756816864,
|
| 253 |
+
"logits/rejected": 0.18676114082336426,
|
| 254 |
+
"logps/chosen": -455.2527770996094,
|
| 255 |
+
"logps/rejected": -499.14886474609375,
|
| 256 |
+
"loss": 0.3275,
|
| 257 |
+
"rewards/accuracies": 0.574999988079071,
|
| 258 |
+
"rewards/chosen": -0.12179211527109146,
|
| 259 |
+
"rewards/margins": 0.055649809539318085,
|
| 260 |
+
"rewards/rejected": -0.17744192481040955,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": 0.04756158962845802,
|
| 267 |
+
"logits/rejected": 0.11594130843877792,
|
| 268 |
+
"logps/chosen": -468.597900390625,
|
| 269 |
+
"logps/rejected": -482.14190673828125,
|
| 270 |
+
"loss": 0.3563,
|
| 271 |
+
"rewards/accuracies": 0.574999988079071,
|
| 272 |
+
"rewards/chosen": -0.1254795491695404,
|
| 273 |
+
"rewards/margins": 0.041418299078941345,
|
| 274 |
+
"rewards/rejected": -0.16689783334732056,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": 0.11988376080989838,
|
| 281 |
+
"logits/rejected": 0.22085747122764587,
|
| 282 |
+
"logps/chosen": -452.22052001953125,
|
| 283 |
+
"logps/rejected": -387.4115905761719,
|
| 284 |
+
"loss": 0.3779,
|
| 285 |
+
"rewards/accuracies": 0.612500011920929,
|
| 286 |
+
"rewards/chosen": -0.07290507853031158,
|
| 287 |
+
"rewards/margins": 0.016655491665005684,
|
| 288 |
+
"rewards/rejected": -0.08956055343151093,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": 0.11956377327442169,
|
| 295 |
+
"logits/rejected": 0.19818153977394104,
|
| 296 |
+
"logps/chosen": -401.03387451171875,
|
| 297 |
+
"logps/rejected": -415.95123291015625,
|
| 298 |
+
"loss": 0.3403,
|
| 299 |
+
"rewards/accuracies": 0.637499988079071,
|
| 300 |
+
"rewards/chosen": -0.06231163814663887,
|
| 301 |
+
"rewards/margins": 0.0385347381234169,
|
| 302 |
+
"rewards/rejected": -0.10084638744592667,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": 0.12819179892539978,
|
| 309 |
+
"logits/rejected": 0.11948923766613007,
|
| 310 |
+
"logps/chosen": -411.1438903808594,
|
| 311 |
+
"logps/rejected": -455.16455078125,
|
| 312 |
+
"loss": 0.3232,
|
| 313 |
+
"rewards/accuracies": 0.643750011920929,
|
| 314 |
+
"rewards/chosen": -0.08700522780418396,
|
| 315 |
+
"rewards/margins": 0.0522175133228302,
|
| 316 |
+
"rewards/rejected": -0.13922274112701416,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": 0.15324261784553528,
|
| 323 |
+
"logits/rejected": 0.20623254776000977,
|
| 324 |
+
"logps/chosen": -480.10888671875,
|
| 325 |
+
"logps/rejected": -499.2796936035156,
|
| 326 |
+
"loss": 0.3304,
|
| 327 |
+
"rewards/accuracies": 0.643750011920929,
|
| 328 |
+
"rewards/chosen": -0.10702191293239594,
|
| 329 |
+
"rewards/margins": 0.05671936273574829,
|
| 330 |
+
"rewards/rejected": -0.16374126076698303,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": 0.18569575250148773,
|
| 337 |
+
"logits/rejected": 0.17661599814891815,
|
| 338 |
+
"logps/chosen": -443.75848388671875,
|
| 339 |
+
"logps/rejected": -451.41143798828125,
|
| 340 |
+
"loss": 0.342,
|
| 341 |
+
"rewards/accuracies": 0.612500011920929,
|
| 342 |
+
"rewards/chosen": -0.1080365926027298,
|
| 343 |
+
"rewards/margins": 0.036346640437841415,
|
| 344 |
+
"rewards/rejected": -0.14438322186470032,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": 0.08591008186340332,
|
| 351 |
+
"logits/rejected": 0.18295328319072723,
|
| 352 |
+
"logps/chosen": -431.0286560058594,
|
| 353 |
+
"logps/rejected": -486.2010803222656,
|
| 354 |
+
"loss": 0.3212,
|
| 355 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 356 |
+
"rewards/chosen": -0.12310918420553207,
|
| 357 |
+
"rewards/margins": 0.055181778967380524,
|
| 358 |
+
"rewards/rejected": -0.1782909631729126,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": 0.11142314970493317,
|
| 365 |
+
"logits/rejected": 0.17328810691833496,
|
| 366 |
+
"logps/chosen": -461.910400390625,
|
| 367 |
+
"logps/rejected": -543.1893920898438,
|
| 368 |
+
"loss": 0.3188,
|
| 369 |
+
"rewards/accuracies": 0.706250011920929,
|
| 370 |
+
"rewards/chosen": -0.1216365322470665,
|
| 371 |
+
"rewards/margins": 0.08850517868995667,
|
| 372 |
+
"rewards/rejected": -0.21014170348644257,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": 0.13197702169418335,
|
| 379 |
+
"logits/rejected": 0.14432582259178162,
|
| 380 |
+
"logps/chosen": -482.305908203125,
|
| 381 |
+
"logps/rejected": -524.9083862304688,
|
| 382 |
+
"loss": 0.3151,
|
| 383 |
+
"rewards/accuracies": 0.5625,
|
| 384 |
+
"rewards/chosen": -0.1686619073152542,
|
| 385 |
+
"rewards/margins": 0.057187020778656006,
|
| 386 |
+
"rewards/rejected": -0.2258489429950714,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": 0.1734444499015808,
|
| 393 |
+
"logits/rejected": 0.21249273419380188,
|
| 394 |
+
"logps/chosen": -479.7071838378906,
|
| 395 |
+
"logps/rejected": -537.2325439453125,
|
| 396 |
+
"loss": 0.327,
|
| 397 |
+
"rewards/accuracies": 0.59375,
|
| 398 |
+
"rewards/chosen": -0.16160346567630768,
|
| 399 |
+
"rewards/margins": 0.06107072904706001,
|
| 400 |
+
"rewards/rejected": -0.2226742058992386,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": 0.15867115557193756,
|
| 407 |
+
"logits/rejected": 0.19647037982940674,
|
| 408 |
+
"logps/chosen": -458.0674743652344,
|
| 409 |
+
"logps/rejected": -501.34722900390625,
|
| 410 |
+
"loss": 0.3286,
|
| 411 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 412 |
+
"rewards/chosen": -0.1390560269355774,
|
| 413 |
+
"rewards/margins": 0.062171000987291336,
|
| 414 |
+
"rewards/rejected": -0.20122702419757843,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": 0.13150140643119812,
|
| 421 |
+
"logits/rejected": 0.22199960052967072,
|
| 422 |
+
"logps/chosen": -450.36669921875,
|
| 423 |
+
"logps/rejected": -506.1780700683594,
|
| 424 |
+
"loss": 0.3315,
|
| 425 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 426 |
+
"rewards/chosen": -0.12922145426273346,
|
| 427 |
+
"rewards/margins": 0.06099293380975723,
|
| 428 |
+
"rewards/rejected": -0.1902143657207489,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": 0.19327369332313538,
|
| 435 |
+
"logits/rejected": 0.24881592392921448,
|
| 436 |
+
"logps/chosen": -497.6783142089844,
|
| 437 |
+
"logps/rejected": -505.5125427246094,
|
| 438 |
+
"loss": 0.3363,
|
| 439 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 440 |
+
"rewards/chosen": -0.12306072562932968,
|
| 441 |
+
"rewards/margins": 0.05413200706243515,
|
| 442 |
+
"rewards/rejected": -0.17719274759292603,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": 0.18834055960178375,
|
| 449 |
+
"logits/rejected": 0.23213116824626923,
|
| 450 |
+
"logps/chosen": -515.0231323242188,
|
| 451 |
+
"logps/rejected": -483.41217041015625,
|
| 452 |
+
"loss": 0.3318,
|
| 453 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 454 |
+
"rewards/chosen": -0.12383429706096649,
|
| 455 |
+
"rewards/margins": 0.042060453444719315,
|
| 456 |
+
"rewards/rejected": -0.1658947467803955,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": 0.17896682024002075,
|
| 463 |
+
"logits/rejected": 0.2394729107618332,
|
| 464 |
+
"logps/chosen": -463.9024353027344,
|
| 465 |
+
"logps/rejected": -537.2124633789062,
|
| 466 |
+
"loss": 0.3272,
|
| 467 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 468 |
+
"rewards/chosen": -0.13291411101818085,
|
| 469 |
+
"rewards/margins": 0.0873040109872818,
|
| 470 |
+
"rewards/rejected": -0.22021810710430145,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": 0.17872880399227142,
|
| 477 |
+
"logits/rejected": 0.24048776924610138,
|
| 478 |
+
"logps/chosen": -512.0220947265625,
|
| 479 |
+
"logps/rejected": -550.4924926757812,
|
| 480 |
+
"loss": 0.3286,
|
| 481 |
+
"rewards/accuracies": 0.637499988079071,
|
| 482 |
+
"rewards/chosen": -0.15976758301258087,
|
| 483 |
+
"rewards/margins": 0.06323219835758209,
|
| 484 |
+
"rewards/rejected": -0.22299976646900177,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": 0.17755231261253357,
|
| 491 |
+
"logits/rejected": 0.21120838820934296,
|
| 492 |
+
"logps/chosen": -548.46728515625,
|
| 493 |
+
"logps/rejected": -568.703369140625,
|
| 494 |
+
"loss": 0.3282,
|
| 495 |
+
"rewards/accuracies": 0.637499988079071,
|
| 496 |
+
"rewards/chosen": -0.17922678589820862,
|
| 497 |
+
"rewards/margins": 0.060503531247377396,
|
| 498 |
+
"rewards/rejected": -0.23973031342029572,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": 0.16182249784469604,
|
| 505 |
+
"logits/rejected": 0.26147884130477905,
|
| 506 |
+
"logps/chosen": -495.8375549316406,
|
| 507 |
+
"logps/rejected": -622.0607299804688,
|
| 508 |
+
"loss": 0.3019,
|
| 509 |
+
"rewards/accuracies": 0.668749988079071,
|
| 510 |
+
"rewards/chosen": -0.16881313920021057,
|
| 511 |
+
"rewards/margins": 0.08940894901752472,
|
| 512 |
+
"rewards/rejected": -0.2582220435142517,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": 0.18107028305530548,
|
| 519 |
+
"logits/rejected": 0.2131391018629074,
|
| 520 |
+
"logps/chosen": -508.89654541015625,
|
| 521 |
+
"logps/rejected": -552.6736450195312,
|
| 522 |
+
"loss": 0.3104,
|
| 523 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 524 |
+
"rewards/chosen": -0.1358935385942459,
|
| 525 |
+
"rewards/margins": 0.08370544016361237,
|
| 526 |
+
"rewards/rejected": -0.21959897875785828,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": 0.1739516258239746,
|
| 533 |
+
"logits/rejected": 0.2705302834510803,
|
| 534 |
+
"logps/chosen": -560.09912109375,
|
| 535 |
+
"logps/rejected": -567.2365112304688,
|
| 536 |
+
"loss": 0.3328,
|
| 537 |
+
"rewards/accuracies": 0.65625,
|
| 538 |
+
"rewards/chosen": -0.13778193295001984,
|
| 539 |
+
"rewards/margins": 0.07480571419000626,
|
| 540 |
+
"rewards/rejected": -0.2125876396894455,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": 0.22400352358818054,
|
| 547 |
+
"logits/rejected": 0.29006537795066833,
|
| 548 |
+
"logps/chosen": -505.47930908203125,
|
| 549 |
+
"logps/rejected": -527.4620361328125,
|
| 550 |
+
"loss": 0.3112,
|
| 551 |
+
"rewards/accuracies": 0.675000011920929,
|
| 552 |
+
"rewards/chosen": -0.1362600326538086,
|
| 553 |
+
"rewards/margins": 0.07366020977497101,
|
| 554 |
+
"rewards/rejected": -0.2099202424287796,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": 0.18031330406665802,
|
| 561 |
+
"logits/rejected": 0.2229474037885666,
|
| 562 |
+
"logps/chosen": -452.552734375,
|
| 563 |
+
"logps/rejected": -508.63262939453125,
|
| 564 |
+
"loss": 0.3029,
|
| 565 |
+
"rewards/accuracies": 0.643750011920929,
|
| 566 |
+
"rewards/chosen": -0.14223061501979828,
|
| 567 |
+
"rewards/margins": 0.06927666813135147,
|
| 568 |
+
"rewards/rejected": -0.21150727570056915,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": 0.15998587012290955,
|
| 575 |
+
"logits/rejected": 0.21808397769927979,
|
| 576 |
+
"logps/chosen": -500.90606689453125,
|
| 577 |
+
"logps/rejected": -549.7945556640625,
|
| 578 |
+
"loss": 0.3176,
|
| 579 |
+
"rewards/accuracies": 0.59375,
|
| 580 |
+
"rewards/chosen": -0.1795472800731659,
|
| 581 |
+
"rewards/margins": 0.06672011315822601,
|
| 582 |
+
"rewards/rejected": -0.24626736342906952,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": 0.2227793037891388,
|
| 589 |
+
"logits/rejected": 0.2791008949279785,
|
| 590 |
+
"logps/chosen": -547.274658203125,
|
| 591 |
+
"logps/rejected": -587.1893310546875,
|
| 592 |
+
"loss": 0.3266,
|
| 593 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 594 |
+
"rewards/chosen": -0.17155751585960388,
|
| 595 |
+
"rewards/margins": 0.09018336981534958,
|
| 596 |
+
"rewards/rejected": -0.26174092292785645,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": 0.1325720101594925,
|
| 603 |
+
"logits/rejected": 0.252084881067276,
|
| 604 |
+
"logps/chosen": -493.5597229003906,
|
| 605 |
+
"logps/rejected": -546.8651733398438,
|
| 606 |
+
"loss": 0.3289,
|
| 607 |
+
"rewards/accuracies": 0.668749988079071,
|
| 608 |
+
"rewards/chosen": -0.16804993152618408,
|
| 609 |
+
"rewards/margins": 0.0734732523560524,
|
| 610 |
+
"rewards/rejected": -0.2415231466293335,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": 0.18316540122032166,
|
| 617 |
+
"logits/rejected": 0.2671397030353546,
|
| 618 |
+
"logps/chosen": -492.28607177734375,
|
| 619 |
+
"logps/rejected": -566.4286499023438,
|
| 620 |
+
"loss": 0.3285,
|
| 621 |
+
"rewards/accuracies": 0.65625,
|
| 622 |
+
"rewards/chosen": -0.13893112540245056,
|
| 623 |
+
"rewards/margins": 0.09025856852531433,
|
| 624 |
+
"rewards/rejected": -0.2291897088289261,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": 0.21058030426502228,
|
| 631 |
+
"logits/rejected": 0.24718663096427917,
|
| 632 |
+
"logps/chosen": -539.2806396484375,
|
| 633 |
+
"logps/rejected": -528.8162841796875,
|
| 634 |
+
"loss": 0.3355,
|
| 635 |
+
"rewards/accuracies": 0.643750011920929,
|
| 636 |
+
"rewards/chosen": -0.14369945228099823,
|
| 637 |
+
"rewards/margins": 0.05218692496418953,
|
| 638 |
+
"rewards/rejected": -0.19588637351989746,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": 0.21172599494457245,
|
| 645 |
+
"logits/rejected": 0.2746911644935608,
|
| 646 |
+
"logps/chosen": -477.0757751464844,
|
| 647 |
+
"logps/rejected": -474.86749267578125,
|
| 648 |
+
"loss": 0.3319,
|
| 649 |
+
"rewards/accuracies": 0.550000011920929,
|
| 650 |
+
"rewards/chosen": -0.14388036727905273,
|
| 651 |
+
"rewards/margins": 0.03479112684726715,
|
| 652 |
+
"rewards/rejected": -0.17867149412631989,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": 0.20078706741333008,
|
| 659 |
+
"logits/rejected": 0.26265597343444824,
|
| 660 |
+
"logps/chosen": -446.60693359375,
|
| 661 |
+
"logps/rejected": -523.1649169921875,
|
| 662 |
+
"loss": 0.3179,
|
| 663 |
+
"rewards/accuracies": 0.706250011920929,
|
| 664 |
+
"rewards/chosen": -0.1348758488893509,
|
| 665 |
+
"rewards/margins": 0.07731764018535614,
|
| 666 |
+
"rewards/rejected": -0.21219351887702942,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": 0.22624699771404266,
|
| 673 |
+
"logits/rejected": 0.278435081243515,
|
| 674 |
+
"logps/chosen": -513.7930297851562,
|
| 675 |
+
"logps/rejected": -577.3609619140625,
|
| 676 |
+
"loss": 0.2867,
|
| 677 |
+
"rewards/accuracies": 0.731249988079071,
|
| 678 |
+
"rewards/chosen": -0.15286709368228912,
|
| 679 |
+
"rewards/margins": 0.09449265152215958,
|
| 680 |
+
"rewards/rejected": -0.2473597526550293,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": 0.16784998774528503,
|
| 687 |
+
"logits/rejected": 0.18377156555652618,
|
| 688 |
+
"logps/chosen": -516.9537353515625,
|
| 689 |
+
"logps/rejected": -570.5045776367188,
|
| 690 |
+
"loss": 0.3264,
|
| 691 |
+
"rewards/accuracies": 0.675000011920929,
|
| 692 |
+
"rewards/chosen": -0.18329444527626038,
|
| 693 |
+
"rewards/margins": 0.06330955028533936,
|
| 694 |
+
"rewards/rejected": -0.24660399556159973,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": 0.2142370045185089,
|
| 701 |
+
"logits/rejected": 0.2654828131198883,
|
| 702 |
+
"logps/chosen": -513.2080078125,
|
| 703 |
+
"logps/rejected": -633.4437866210938,
|
| 704 |
+
"loss": 0.2835,
|
| 705 |
+
"rewards/accuracies": 0.706250011920929,
|
| 706 |
+
"rewards/chosen": -0.1864250749349594,
|
| 707 |
+
"rewards/margins": 0.12554675340652466,
|
| 708 |
+
"rewards/rejected": -0.3119718134403229,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": 0.2339199036359787,
|
| 715 |
+
"logits/rejected": 0.3211553394794464,
|
| 716 |
+
"logps/chosen": -538.3214111328125,
|
| 717 |
+
"logps/rejected": -600.5282592773438,
|
| 718 |
+
"loss": 0.2922,
|
| 719 |
+
"rewards/accuracies": 0.668749988079071,
|
| 720 |
+
"rewards/chosen": -0.1798117458820343,
|
| 721 |
+
"rewards/margins": 0.09368885308504105,
|
| 722 |
+
"rewards/rejected": -0.27350059151649475,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": 0.20931610465049744,
|
| 729 |
+
"logits/rejected": 0.29080599546432495,
|
| 730 |
+
"logps/chosen": -553.5645751953125,
|
| 731 |
+
"logps/rejected": -621.51513671875,
|
| 732 |
+
"loss": 0.315,
|
| 733 |
+
"rewards/accuracies": 0.65625,
|
| 734 |
+
"rewards/chosen": -0.2022249698638916,
|
| 735 |
+
"rewards/margins": 0.09137126803398132,
|
| 736 |
+
"rewards/rejected": -0.29359620809555054,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": 0.2311556041240692,
|
| 743 |
+
"logits/rejected": 0.2898443639278412,
|
| 744 |
+
"logps/chosen": -564.0858764648438,
|
| 745 |
+
"logps/rejected": -701.887939453125,
|
| 746 |
+
"loss": 0.2773,
|
| 747 |
+
"rewards/accuracies": 0.75,
|
| 748 |
+
"rewards/chosen": -0.22962744534015656,
|
| 749 |
+
"rewards/margins": 0.13914015889167786,
|
| 750 |
+
"rewards/rejected": -0.3687676191329956,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": 0.21098744869232178,
|
| 757 |
+
"logits/rejected": 0.3181845545768738,
|
| 758 |
+
"logps/chosen": -588.2892456054688,
|
| 759 |
+
"logps/rejected": -676.7548828125,
|
| 760 |
+
"loss": 0.2998,
|
| 761 |
+
"rewards/accuracies": 0.643750011920929,
|
| 762 |
+
"rewards/chosen": -0.21903486549854279,
|
| 763 |
+
"rewards/margins": 0.09523408114910126,
|
| 764 |
+
"rewards/rejected": -0.31426894664764404,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": 0.2154814451932907,
|
| 771 |
+
"logits/rejected": 0.3008938431739807,
|
| 772 |
+
"logps/chosen": -563.6261596679688,
|
| 773 |
+
"logps/rejected": -657.9494018554688,
|
| 774 |
+
"loss": 0.2899,
|
| 775 |
+
"rewards/accuracies": 0.6875,
|
| 776 |
+
"rewards/chosen": -0.19673727452754974,
|
| 777 |
+
"rewards/margins": 0.12186020612716675,
|
| 778 |
+
"rewards/rejected": -0.3185974657535553,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": 0.22583889961242676,
|
| 785 |
+
"logits/rejected": 0.30130234360694885,
|
| 786 |
+
"logps/chosen": -559.0008544921875,
|
| 787 |
+
"logps/rejected": -666.7113037109375,
|
| 788 |
+
"loss": 0.2739,
|
| 789 |
+
"rewards/accuracies": 0.737500011920929,
|
| 790 |
+
"rewards/chosen": -0.18335992097854614,
|
| 791 |
+
"rewards/margins": 0.129757359623909,
|
| 792 |
+
"rewards/rejected": -0.31311726570129395,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": 0.2066396176815033,
|
| 799 |
+
"logits/rejected": 0.23956134915351868,
|
| 800 |
+
"logps/chosen": -514.6549072265625,
|
| 801 |
+
"logps/rejected": -633.8093872070312,
|
| 802 |
+
"loss": 0.3114,
|
| 803 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 804 |
+
"rewards/chosen": -0.21198049187660217,
|
| 805 |
+
"rewards/margins": 0.11119239032268524,
|
| 806 |
+
"rewards/rejected": -0.3231728672981262,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": 0.25394177436828613,
|
| 813 |
+
"logits/rejected": 0.3233291804790497,
|
| 814 |
+
"logps/chosen": -516.4053955078125,
|
| 815 |
+
"logps/rejected": -631.0079345703125,
|
| 816 |
+
"loss": 0.2863,
|
| 817 |
+
"rewards/accuracies": 0.6875,
|
| 818 |
+
"rewards/chosen": -0.18605783581733704,
|
| 819 |
+
"rewards/margins": 0.12697571516036987,
|
| 820 |
+
"rewards/rejected": -0.3130335807800293,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": 0.23206424713134766,
|
| 827 |
+
"logits/rejected": 0.24580395221710205,
|
| 828 |
+
"logps/chosen": -533.16650390625,
|
| 829 |
+
"logps/rejected": -624.2952880859375,
|
| 830 |
+
"loss": 0.2859,
|
| 831 |
+
"rewards/accuracies": 0.699999988079071,
|
| 832 |
+
"rewards/chosen": -0.19318199157714844,
|
| 833 |
+
"rewards/margins": 0.11356300115585327,
|
| 834 |
+
"rewards/rejected": -0.3067449927330017,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": 0.2015029937028885,
|
| 841 |
+
"logits/rejected": 0.27999237179756165,
|
| 842 |
+
"logps/chosen": -526.4388427734375,
|
| 843 |
+
"logps/rejected": -610.4771728515625,
|
| 844 |
+
"loss": 0.2962,
|
| 845 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 846 |
+
"rewards/chosen": -0.1759098321199417,
|
| 847 |
+
"rewards/margins": 0.12597855925559998,
|
| 848 |
+
"rewards/rejected": -0.3018884062767029,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": 0.22685325145721436,
|
| 855 |
+
"logits/rejected": 0.2123553305864334,
|
| 856 |
+
"logps/chosen": -530.7593383789062,
|
| 857 |
+
"logps/rejected": -596.7511596679688,
|
| 858 |
+
"loss": 0.2988,
|
| 859 |
+
"rewards/accuracies": 0.65625,
|
| 860 |
+
"rewards/chosen": -0.20077498257160187,
|
| 861 |
+
"rewards/margins": 0.10626114904880524,
|
| 862 |
+
"rewards/rejected": -0.3070361018180847,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": 0.2265332043170929,
|
| 869 |
+
"logits/rejected": 0.25227993726730347,
|
| 870 |
+
"logps/chosen": -548.7151489257812,
|
| 871 |
+
"logps/rejected": -657.1322631835938,
|
| 872 |
+
"loss": 0.2881,
|
| 873 |
+
"rewards/accuracies": 0.75,
|
| 874 |
+
"rewards/chosen": -0.2090146541595459,
|
| 875 |
+
"rewards/margins": 0.12534213066101074,
|
| 876 |
+
"rewards/rejected": -0.33435681462287903,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": 0.18398644030094147,
|
| 883 |
+
"logits/rejected": 0.2708356976509094,
|
| 884 |
+
"logps/chosen": -577.2225952148438,
|
| 885 |
+
"logps/rejected": -658.6173095703125,
|
| 886 |
+
"loss": 0.2699,
|
| 887 |
+
"rewards/accuracies": 0.737500011920929,
|
| 888 |
+
"rewards/chosen": -0.20767459273338318,
|
| 889 |
+
"rewards/margins": 0.11812429130077362,
|
| 890 |
+
"rewards/rejected": -0.325798898935318,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": 0.2091066539287567,
|
| 897 |
+
"logits/rejected": 0.273884117603302,
|
| 898 |
+
"logps/chosen": -563.6356201171875,
|
| 899 |
+
"logps/rejected": -645.4375,
|
| 900 |
+
"loss": 0.3124,
|
| 901 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 902 |
+
"rewards/chosen": -0.20846951007843018,
|
| 903 |
+
"rewards/margins": 0.09923194348812103,
|
| 904 |
+
"rewards/rejected": -0.3077014088630676,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": 0.2188616544008255,
|
| 911 |
+
"logits/rejected": 0.2746090292930603,
|
| 912 |
+
"logps/chosen": -567.142578125,
|
| 913 |
+
"logps/rejected": -631.2537841796875,
|
| 914 |
+
"loss": 0.2965,
|
| 915 |
+
"rewards/accuracies": 0.706250011920929,
|
| 916 |
+
"rewards/chosen": -0.19390718638896942,
|
| 917 |
+
"rewards/margins": 0.11340739578008652,
|
| 918 |
+
"rewards/rejected": -0.30731460452079773,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": 0.242666095495224,
|
| 925 |
+
"logits/rejected": 0.2608735263347626,
|
| 926 |
+
"logps/chosen": -517.3770751953125,
|
| 927 |
+
"logps/rejected": -616.4417724609375,
|
| 928 |
+
"loss": 0.2942,
|
| 929 |
+
"rewards/accuracies": 0.71875,
|
| 930 |
+
"rewards/chosen": -0.1942964643239975,
|
| 931 |
+
"rewards/margins": 0.11079655587673187,
|
| 932 |
+
"rewards/rejected": -0.30509302020072937,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": 0.16175343096256256,
|
| 939 |
+
"logits/rejected": 0.2701238989830017,
|
| 940 |
+
"logps/chosen": -573.2815551757812,
|
| 941 |
+
"logps/rejected": -654.2884521484375,
|
| 942 |
+
"loss": 0.3025,
|
| 943 |
+
"rewards/accuracies": 0.675000011920929,
|
| 944 |
+
"rewards/chosen": -0.22864040732383728,
|
| 945 |
+
"rewards/margins": 0.119266077876091,
|
| 946 |
+
"rewards/rejected": -0.34790652990341187,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": 0.23474529385566711,
|
| 953 |
+
"logits/rejected": 0.29773998260498047,
|
| 954 |
+
"logps/chosen": -530.2286376953125,
|
| 955 |
+
"logps/rejected": -627.4801025390625,
|
| 956 |
+
"loss": 0.3166,
|
| 957 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 958 |
+
"rewards/chosen": -0.20864705741405487,
|
| 959 |
+
"rewards/margins": 0.10489342361688614,
|
| 960 |
+
"rewards/rejected": -0.3135404884815216,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": 0.23635394871234894,
|
| 967 |
+
"logits/rejected": 0.27978676557540894,
|
| 968 |
+
"logps/chosen": -528.3208618164062,
|
| 969 |
+
"logps/rejected": -589.3389892578125,
|
| 970 |
+
"loss": 0.309,
|
| 971 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 972 |
+
"rewards/chosen": -0.19641873240470886,
|
| 973 |
+
"rewards/margins": 0.07995133101940155,
|
| 974 |
+
"rewards/rejected": -0.276370108127594,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": 0.22646358609199524,
|
| 981 |
+
"logits/rejected": 0.31415465474128723,
|
| 982 |
+
"logps/chosen": -522.7443237304688,
|
| 983 |
+
"logps/rejected": -638.9615478515625,
|
| 984 |
+
"loss": 0.2545,
|
| 985 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 986 |
+
"rewards/chosen": -0.17692828178405762,
|
| 987 |
+
"rewards/margins": 0.13757161796092987,
|
| 988 |
+
"rewards/rejected": -0.3144999146461487,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": 0.25629907846450806,
|
| 995 |
+
"logits/rejected": 0.32496970891952515,
|
| 996 |
+
"logps/chosen": -573.7655029296875,
|
| 997 |
+
"logps/rejected": -639.9420166015625,
|
| 998 |
+
"loss": 0.3064,
|
| 999 |
+
"rewards/accuracies": 0.606249988079071,
|
| 1000 |
+
"rewards/chosen": -0.22299213707447052,
|
| 1001 |
+
"rewards/margins": 0.0986771434545517,
|
| 1002 |
+
"rewards/rejected": -0.3216692805290222,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": 0.23862013220787048,
|
| 1009 |
+
"logits/rejected": 0.29511600732803345,
|
| 1010 |
+
"logps/chosen": -586.1082153320312,
|
| 1011 |
+
"logps/rejected": -664.5083618164062,
|
| 1012 |
+
"loss": 0.318,
|
| 1013 |
+
"rewards/accuracies": 0.65625,
|
| 1014 |
+
"rewards/chosen": -0.2209562063217163,
|
| 1015 |
+
"rewards/margins": 0.10732462257146835,
|
| 1016 |
+
"rewards/rejected": -0.32828083634376526,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": 0.20532169938087463,
|
| 1023 |
+
"logits/rejected": 0.27353784441947937,
|
| 1024 |
+
"logps/chosen": -541.2822265625,
|
| 1025 |
+
"logps/rejected": -623.6652221679688,
|
| 1026 |
+
"loss": 0.3026,
|
| 1027 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1028 |
+
"rewards/chosen": -0.2209356278181076,
|
| 1029 |
+
"rewards/margins": 0.08726519346237183,
|
| 1030 |
+
"rewards/rejected": -0.30820080637931824,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": 0.2527928650379181,
|
| 1037 |
+
"logits/rejected": 0.28749826550483704,
|
| 1038 |
+
"logps/chosen": -536.0897216796875,
|
| 1039 |
+
"logps/rejected": -644.0540161132812,
|
| 1040 |
+
"loss": 0.3051,
|
| 1041 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1042 |
+
"rewards/chosen": -0.21758422255516052,
|
| 1043 |
+
"rewards/margins": 0.10065360367298126,
|
| 1044 |
+
"rewards/rejected": -0.3182377815246582,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": 0.2695181965827942,
|
| 1051 |
+
"logits/rejected": 0.2740219235420227,
|
| 1052 |
+
"logps/chosen": -605.3865966796875,
|
| 1053 |
+
"logps/rejected": -638.5525512695312,
|
| 1054 |
+
"loss": 0.3171,
|
| 1055 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1056 |
+
"rewards/chosen": -0.21937242150306702,
|
| 1057 |
+
"rewards/margins": 0.09414593875408173,
|
| 1058 |
+
"rewards/rejected": -0.31351834535598755,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": 0.19430357217788696,
|
| 1065 |
+
"logits/rejected": 0.26386886835098267,
|
| 1066 |
+
"logps/chosen": -525.9102783203125,
|
| 1067 |
+
"logps/rejected": -589.8792724609375,
|
| 1068 |
+
"loss": 0.3099,
|
| 1069 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1070 |
+
"rewards/chosen": -0.19337861239910126,
|
| 1071 |
+
"rewards/margins": 0.10214637219905853,
|
| 1072 |
+
"rewards/rejected": -0.2955249845981598,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": 0.22553198039531708,
|
| 1079 |
+
"logits/rejected": 0.30115246772766113,
|
| 1080 |
+
"logps/chosen": -566.0553588867188,
|
| 1081 |
+
"logps/rejected": -673.5691528320312,
|
| 1082 |
+
"loss": 0.3187,
|
| 1083 |
+
"rewards/accuracies": 0.65625,
|
| 1084 |
+
"rewards/chosen": -0.23551130294799805,
|
| 1085 |
+
"rewards/margins": 0.09716212749481201,
|
| 1086 |
+
"rewards/rejected": -0.33267340064048767,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": 0.22058384120464325,
|
| 1093 |
+
"logits/rejected": 0.2929172217845917,
|
| 1094 |
+
"logps/chosen": -517.9133911132812,
|
| 1095 |
+
"logps/rejected": -579.1270141601562,
|
| 1096 |
+
"loss": 0.3049,
|
| 1097 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1098 |
+
"rewards/chosen": -0.18619771301746368,
|
| 1099 |
+
"rewards/margins": 0.10236430168151855,
|
| 1100 |
+
"rewards/rejected": -0.28856199979782104,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": 0.2658401131629944,
|
| 1107 |
+
"logits/rejected": 0.2887721657752991,
|
| 1108 |
+
"logps/chosen": -540.28125,
|
| 1109 |
+
"logps/rejected": -608.2423095703125,
|
| 1110 |
+
"loss": 0.304,
|
| 1111 |
+
"rewards/accuracies": 0.668749988079071,
|
| 1112 |
+
"rewards/chosen": -0.19344370067119598,
|
| 1113 |
+
"rewards/margins": 0.10303628444671631,
|
| 1114 |
+
"rewards/rejected": -0.2964799702167511,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": 0.17139685153961182,
|
| 1121 |
+
"logits/rejected": 0.25828295946121216,
|
| 1122 |
+
"logps/chosen": -554.6468505859375,
|
| 1123 |
+
"logps/rejected": -640.1256103515625,
|
| 1124 |
+
"loss": 0.282,
|
| 1125 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1126 |
+
"rewards/chosen": -0.20378851890563965,
|
| 1127 |
+
"rewards/margins": 0.1270802915096283,
|
| 1128 |
+
"rewards/rejected": -0.33086878061294556,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": 0.2666166126728058,
|
| 1135 |
+
"logits/rejected": 0.34795981645584106,
|
| 1136 |
+
"logps/chosen": -539.4295654296875,
|
| 1137 |
+
"logps/rejected": -628.8125,
|
| 1138 |
+
"loss": 0.2971,
|
| 1139 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1140 |
+
"rewards/chosen": -0.2073674499988556,
|
| 1141 |
+
"rewards/margins": 0.1060541421175003,
|
| 1142 |
+
"rewards/rejected": -0.3134215772151947,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": 0.21775129437446594,
|
| 1149 |
+
"logits/rejected": 0.293344110250473,
|
| 1150 |
+
"logps/chosen": -570.99658203125,
|
| 1151 |
+
"logps/rejected": -677.3284301757812,
|
| 1152 |
+
"loss": 0.2876,
|
| 1153 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1154 |
+
"rewards/chosen": -0.20963303744792938,
|
| 1155 |
+
"rewards/margins": 0.11293938010931015,
|
| 1156 |
+
"rewards/rejected": -0.32257241010665894,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": 0.24225249886512756,
|
| 1163 |
+
"logits/rejected": 0.24781346321105957,
|
| 1164 |
+
"logps/chosen": -576.57666015625,
|
| 1165 |
+
"logps/rejected": -700.5311279296875,
|
| 1166 |
+
"loss": 0.2831,
|
| 1167 |
+
"rewards/accuracies": 0.699999988079071,
|
| 1168 |
+
"rewards/chosen": -0.21174940466880798,
|
| 1169 |
+
"rewards/margins": 0.13153058290481567,
|
| 1170 |
+
"rewards/rejected": -0.34328001737594604,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": 0.24054893851280212,
|
| 1177 |
+
"logits/rejected": 0.26931822299957275,
|
| 1178 |
+
"logps/chosen": -555.5228881835938,
|
| 1179 |
+
"logps/rejected": -626.7105712890625,
|
| 1180 |
+
"loss": 0.3005,
|
| 1181 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1182 |
+
"rewards/chosen": -0.21045789122581482,
|
| 1183 |
+
"rewards/margins": 0.11446176469326019,
|
| 1184 |
+
"rewards/rejected": -0.3249196708202362,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": 0.2166041135787964,
|
| 1191 |
+
"logits/rejected": 0.3280956745147705,
|
| 1192 |
+
"logps/chosen": -568.7992553710938,
|
| 1193 |
+
"logps/rejected": -648.0155029296875,
|
| 1194 |
+
"loss": 0.2852,
|
| 1195 |
+
"rewards/accuracies": 0.625,
|
| 1196 |
+
"rewards/chosen": -0.21820878982543945,
|
| 1197 |
+
"rewards/margins": 0.10663551092147827,
|
| 1198 |
+
"rewards/rejected": -0.32484427094459534,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": 0.239153191447258,
|
| 1205 |
+
"logits/rejected": 0.2556217610836029,
|
| 1206 |
+
"logps/chosen": -576.3333740234375,
|
| 1207 |
+
"logps/rejected": -648.7257080078125,
|
| 1208 |
+
"loss": 0.3209,
|
| 1209 |
+
"rewards/accuracies": 0.706250011920929,
|
| 1210 |
+
"rewards/chosen": -0.23230747878551483,
|
| 1211 |
+
"rewards/margins": 0.08656927943229675,
|
| 1212 |
+
"rewards/rejected": -0.31887680292129517,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": 0.18877582252025604,
|
| 1219 |
+
"logits/rejected": 0.29884201288223267,
|
| 1220 |
+
"logps/chosen": -558.5150146484375,
|
| 1221 |
+
"logps/rejected": -645.3088989257812,
|
| 1222 |
+
"loss": 0.2991,
|
| 1223 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 1224 |
+
"rewards/chosen": -0.21622328460216522,
|
| 1225 |
+
"rewards/margins": 0.11353172361850739,
|
| 1226 |
+
"rewards/rejected": -0.3297550082206726,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": 0.21539130806922913,
|
| 1233 |
+
"logits/rejected": 0.27139174938201904,
|
| 1234 |
+
"logps/chosen": -597.243408203125,
|
| 1235 |
+
"logps/rejected": -675.239501953125,
|
| 1236 |
+
"loss": 0.3016,
|
| 1237 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1238 |
+
"rewards/chosen": -0.2269672453403473,
|
| 1239 |
+
"rewards/margins": 0.10424689948558807,
|
| 1240 |
+
"rewards/rejected": -0.33121412992477417,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": 0.23871974647045135,
|
| 1247 |
+
"logits/rejected": 0.27142205834388733,
|
| 1248 |
+
"logps/chosen": -519.5438232421875,
|
| 1249 |
+
"logps/rejected": -582.7971801757812,
|
| 1250 |
+
"loss": 0.3158,
|
| 1251 |
+
"rewards/accuracies": 0.65625,
|
| 1252 |
+
"rewards/chosen": -0.19175615906715393,
|
| 1253 |
+
"rewards/margins": 0.08461669087409973,
|
| 1254 |
+
"rewards/rejected": -0.27637284994125366,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": 0.2282760590314865,
|
| 1261 |
+
"logits/rejected": 0.3373679518699646,
|
| 1262 |
+
"logps/chosen": -577.5682373046875,
|
| 1263 |
+
"logps/rejected": -626.8815307617188,
|
| 1264 |
+
"loss": 0.3167,
|
| 1265 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1266 |
+
"rewards/chosen": -0.22001275420188904,
|
| 1267 |
+
"rewards/margins": 0.07437258958816528,
|
| 1268 |
+
"rewards/rejected": -0.2943853735923767,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": 0.20522919297218323,
|
| 1275 |
+
"logits/rejected": 0.24701757729053497,
|
| 1276 |
+
"logps/chosen": -569.3855590820312,
|
| 1277 |
+
"logps/rejected": -645.0745849609375,
|
| 1278 |
+
"loss": 0.3067,
|
| 1279 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1280 |
+
"rewards/chosen": -0.22419647872447968,
|
| 1281 |
+
"rewards/margins": 0.0874943733215332,
|
| 1282 |
+
"rewards/rejected": -0.3116908669471741,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": 0.22225090861320496,
|
| 1289 |
+
"logits/rejected": 0.26438599824905396,
|
| 1290 |
+
"logps/chosen": -567.0126953125,
|
| 1291 |
+
"logps/rejected": -654.3960571289062,
|
| 1292 |
+
"loss": 0.2847,
|
| 1293 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1294 |
+
"rewards/chosen": -0.20670703053474426,
|
| 1295 |
+
"rewards/margins": 0.11432477086782455,
|
| 1296 |
+
"rewards/rejected": -0.32103174924850464,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": 0.24451366066932678,
|
| 1303 |
+
"logits/rejected": 0.3054306209087372,
|
| 1304 |
+
"logps/chosen": -528.2220458984375,
|
| 1305 |
+
"logps/rejected": -643.4144287109375,
|
| 1306 |
+
"loss": 0.2967,
|
| 1307 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 1308 |
+
"rewards/chosen": -0.19906611740589142,
|
| 1309 |
+
"rewards/margins": 0.1229342445731163,
|
| 1310 |
+
"rewards/rejected": -0.32200032472610474,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": 0.2621709704399109,
|
| 1317 |
+
"logits/rejected": 0.3254636228084564,
|
| 1318 |
+
"logps/chosen": -604.9237060546875,
|
| 1319 |
+
"logps/rejected": -632.830322265625,
|
| 1320 |
+
"loss": 0.3013,
|
| 1321 |
+
"rewards/accuracies": 0.643750011920929,
|
| 1322 |
+
"rewards/chosen": -0.22578959167003632,
|
| 1323 |
+
"rewards/margins": 0.09746529161930084,
|
| 1324 |
+
"rewards/rejected": -0.32325488328933716,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.24207222728871738,
|
| 1332 |
+
"train_runtime": 8784.9129,
|
| 1333 |
+
"train_samples_per_second": 3.415,
|
| 1334 |
+
"train_steps_per_second": 0.107
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 10,
|
| 1338 |
+
"max_steps": 937,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 100,
|
| 1342 |
+
"total_flos": 0.0,
|
| 1343 |
+
"train_batch_size": 4,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|