Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May16_23-27-05_gpu4-119-5/events.out.tfevents.1715866164.gpu4-119-5.702446.0 +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-v35-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-v35-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:afea87b6311e587ea4e1153fa522c44d07f13ca35caab548c4e5bf282f31f315
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.08644322651809155,
|
| 4 |
+
"train_runtime": 5283.9744,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 5.678,
|
| 7 |
+
"train_steps_per_second": 0.177
|
| 8 |
+
}
|
runs/May16_23-27-05_gpu4-119-5/events.out.tfevents.1715866164.gpu4-119-5.702446.0
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 sha256:36de2e70ca0692165cd4f348b0a3bd529950bed00bb1e59131db6a5667b79a6f
|
| 3 |
+
size 32451
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.08644322651809155,
|
| 4 |
+
"train_runtime": 5283.9744,
|
| 5 |
+
"train_samples": 30000,
|
| 6 |
+
"train_samples_per_second": 5.678,
|
| 7 |
+
"train_steps_per_second": 0.177
|
| 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": 0.1184067577123642,
|
| 15 |
+
"logits/rejected": 0.3525714576244354,
|
| 16 |
+
"logps/chosen": -429.5767822265625,
|
| 17 |
+
"logps/rejected": -514.7810668945312,
|
| 18 |
+
"loss": 0.3025,
|
| 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": 0.05111883208155632,
|
| 29 |
+
"logits/rejected": 0.23624171316623688,
|
| 30 |
+
"logps/chosen": -363.744140625,
|
| 31 |
+
"logps/rejected": -491.4056091308594,
|
| 32 |
+
"loss": 0.3259,
|
| 33 |
+
"rewards/accuracies": 0.3819444477558136,
|
| 34 |
+
"rewards/chosen": 2.125546416209545e-05,
|
| 35 |
+
"rewards/margins": -4.7190667828544974e-05,
|
| 36 |
+
"rewards/rejected": 6.844610470579937e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 42 |
+
"logits/chosen": 0.0970318466424942,
|
| 43 |
+
"logits/rejected": 0.21818876266479492,
|
| 44 |
+
"logps/chosen": -342.73223876953125,
|
| 45 |
+
"logps/rejected": -533.9749755859375,
|
| 46 |
+
"loss": 0.3389,
|
| 47 |
+
"rewards/accuracies": 0.5062500238418579,
|
| 48 |
+
"rewards/chosen": -0.00010573499457677826,
|
| 49 |
+
"rewards/margins": 0.00035456178011372685,
|
| 50 |
+
"rewards/rejected": -0.00046029678196646273,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 1.595744680851064e-06,
|
| 56 |
+
"logits/chosen": 0.08977697044610977,
|
| 57 |
+
"logits/rejected": 0.20492060482501984,
|
| 58 |
+
"logps/chosen": -356.282958984375,
|
| 59 |
+
"logps/rejected": -506.893798828125,
|
| 60 |
+
"loss": 0.3282,
|
| 61 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 62 |
+
"rewards/chosen": -0.0007758208666928113,
|
| 63 |
+
"rewards/margins": 0.0015017592813819647,
|
| 64 |
+
"rewards/rejected": -0.0022775803226977587,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 70 |
+
"logits/chosen": 0.14597493410110474,
|
| 71 |
+
"logits/rejected": 0.2742587625980377,
|
| 72 |
+
"logps/chosen": -373.9236755371094,
|
| 73 |
+
"logps/rejected": -478.6368103027344,
|
| 74 |
+
"loss": 0.3329,
|
| 75 |
+
"rewards/accuracies": 0.699999988079071,
|
| 76 |
+
"rewards/chosen": -0.0021772016771137714,
|
| 77 |
+
"rewards/margins": 0.00360355107113719,
|
| 78 |
+
"rewards/rejected": -0.005780753213912249,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 84 |
+
"logits/chosen": 0.06719115376472473,
|
| 85 |
+
"logits/rejected": 0.20441851019859314,
|
| 86 |
+
"logps/chosen": -339.3710021972656,
|
| 87 |
+
"logps/rejected": -437.3455505371094,
|
| 88 |
+
"loss": 0.3465,
|
| 89 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 90 |
+
"rewards/chosen": -0.00426669092848897,
|
| 91 |
+
"rewards/margins": 0.009421268478035927,
|
| 92 |
+
"rewards/rejected": -0.01368795894086361,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 3.191489361702128e-06,
|
| 98 |
+
"logits/chosen": -0.008065430447459221,
|
| 99 |
+
"logits/rejected": 0.08582984656095505,
|
| 100 |
+
"logps/chosen": -321.49005126953125,
|
| 101 |
+
"logps/rejected": -471.43896484375,
|
| 102 |
+
"loss": 0.3231,
|
| 103 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 104 |
+
"rewards/chosen": -0.008598757907748222,
|
| 105 |
+
"rewards/margins": 0.023485153913497925,
|
| 106 |
+
"rewards/rejected": -0.032083909958601,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 3.723404255319149e-06,
|
| 112 |
+
"logits/chosen": 0.06349015235900879,
|
| 113 |
+
"logits/rejected": 0.1338900625705719,
|
| 114 |
+
"logps/chosen": -400.74725341796875,
|
| 115 |
+
"logps/rejected": -535.9130859375,
|
| 116 |
+
"loss": 0.3199,
|
| 117 |
+
"rewards/accuracies": 0.768750011920929,
|
| 118 |
+
"rewards/chosen": -0.02710326947271824,
|
| 119 |
+
"rewards/margins": 0.03926965966820717,
|
| 120 |
+
"rewards/rejected": -0.06637293100357056,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"learning_rate": 4.255319148936171e-06,
|
| 126 |
+
"logits/chosen": -0.012521197088062763,
|
| 127 |
+
"logits/rejected": 0.05875171348452568,
|
| 128 |
+
"logps/chosen": -416.5260314941406,
|
| 129 |
+
"logps/rejected": -619.4620971679688,
|
| 130 |
+
"loss": 0.2653,
|
| 131 |
+
"rewards/accuracies": 0.762499988079071,
|
| 132 |
+
"rewards/chosen": -0.04513772577047348,
|
| 133 |
+
"rewards/margins": 0.09761229157447815,
|
| 134 |
+
"rewards/rejected": -0.14275000989437103,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.787234042553192e-06,
|
| 140 |
+
"logits/chosen": -0.06508742272853851,
|
| 141 |
+
"logits/rejected": -0.025008535012602806,
|
| 142 |
+
"logps/chosen": -398.4359436035156,
|
| 143 |
+
"logps/rejected": -709.9359130859375,
|
| 144 |
+
"loss": 0.2408,
|
| 145 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 146 |
+
"rewards/chosen": -0.06391867995262146,
|
| 147 |
+
"rewards/margins": 0.18030937016010284,
|
| 148 |
+
"rewards/rejected": -0.2442280501127243,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"learning_rate": 4.999375059004058e-06,
|
| 154 |
+
"logits/chosen": -0.11634773015975952,
|
| 155 |
+
"logits/rejected": -0.04804380610585213,
|
| 156 |
+
"logps/chosen": -461.4971618652344,
|
| 157 |
+
"logps/rejected": -726.8289794921875,
|
| 158 |
+
"loss": 0.2717,
|
| 159 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 160 |
+
"rewards/chosen": -0.0884505957365036,
|
| 161 |
+
"rewards/margins": 0.17610163986682892,
|
| 162 |
+
"rewards/rejected": -0.2645522356033325,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"learning_rate": 4.9955571065548795e-06,
|
| 168 |
+
"logits/chosen": -0.07285631448030472,
|
| 169 |
+
"logits/rejected": -0.07443198561668396,
|
| 170 |
+
"logps/chosen": -428.96588134765625,
|
| 171 |
+
"logps/rejected": -709.934326171875,
|
| 172 |
+
"loss": 0.2447,
|
| 173 |
+
"rewards/accuracies": 0.762499988079071,
|
| 174 |
+
"rewards/chosen": -0.06827546656131744,
|
| 175 |
+
"rewards/margins": 0.1353142112493515,
|
| 176 |
+
"rewards/rejected": -0.20358964800834656,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9882736864879e-06,
|
| 182 |
+
"logits/chosen": -0.176306813955307,
|
| 183 |
+
"logits/rejected": -0.049706846475601196,
|
| 184 |
+
"logps/chosen": -430.32562255859375,
|
| 185 |
+
"logps/rejected": -693.2147216796875,
|
| 186 |
+
"loss": 0.2456,
|
| 187 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 188 |
+
"rewards/chosen": -0.08173463493585587,
|
| 189 |
+
"rewards/margins": 0.13715550303459167,
|
| 190 |
+
"rewards/rejected": -0.21889011561870575,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"learning_rate": 4.977534912960124e-06,
|
| 196 |
+
"logits/chosen": -0.15699656307697296,
|
| 197 |
+
"logits/rejected": -0.0577981173992157,
|
| 198 |
+
"logps/chosen": -445.72894287109375,
|
| 199 |
+
"logps/rejected": -769.3819580078125,
|
| 200 |
+
"loss": 0.2081,
|
| 201 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 202 |
+
"rewards/chosen": -0.07942022383213043,
|
| 203 |
+
"rewards/margins": 0.19334132969379425,
|
| 204 |
+
"rewards/rejected": -0.2727615237236023,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"learning_rate": 4.963355698422092e-06,
|
| 210 |
+
"logits/chosen": -0.18548890948295593,
|
| 211 |
+
"logits/rejected": -0.12828989326953888,
|
| 212 |
+
"logps/chosen": -451.9037170410156,
|
| 213 |
+
"logps/rejected": -739.3684692382812,
|
| 214 |
+
"loss": 0.2257,
|
| 215 |
+
"rewards/accuracies": 0.78125,
|
| 216 |
+
"rewards/chosen": -0.0921342521905899,
|
| 217 |
+
"rewards/margins": 0.16765089333057404,
|
| 218 |
+
"rewards/rejected": -0.25978511571884155,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.945755732909625e-06,
|
| 224 |
+
"logits/chosen": -0.15024694800376892,
|
| 225 |
+
"logits/rejected": -0.06675387918949127,
|
| 226 |
+
"logps/chosen": -537.3986206054688,
|
| 227 |
+
"logps/rejected": -775.892578125,
|
| 228 |
+
"loss": 0.2479,
|
| 229 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 230 |
+
"rewards/chosen": -0.10632505267858505,
|
| 231 |
+
"rewards/margins": 0.16134649515151978,
|
| 232 |
+
"rewards/rejected": -0.2676715552806854,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"learning_rate": 4.924759456701167e-06,
|
| 238 |
+
"logits/chosen": -0.20865170657634735,
|
| 239 |
+
"logits/rejected": -0.10186436027288437,
|
| 240 |
+
"logps/chosen": -483.97760009765625,
|
| 241 |
+
"logps/rejected": -849.4505004882812,
|
| 242 |
+
"loss": 0.2265,
|
| 243 |
+
"rewards/accuracies": 0.824999988079071,
|
| 244 |
+
"rewards/chosen": -0.09985359013080597,
|
| 245 |
+
"rewards/margins": 0.2456916868686676,
|
| 246 |
+
"rewards/rejected": -0.34554529190063477,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18,
|
| 251 |
+
"learning_rate": 4.900396026378671e-06,
|
| 252 |
+
"logits/chosen": -0.23064300417900085,
|
| 253 |
+
"logits/rejected": -0.12898269295692444,
|
| 254 |
+
"logps/chosen": -494.6697692871094,
|
| 255 |
+
"logps/rejected": -781.0926513671875,
|
| 256 |
+
"loss": 0.2324,
|
| 257 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 258 |
+
"rewards/chosen": -0.11788048595190048,
|
| 259 |
+
"rewards/margins": 0.17606906592845917,
|
| 260 |
+
"rewards/rejected": -0.29394954442977905,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.872699274339169e-06,
|
| 266 |
+
"logits/chosen": -0.22916531562805176,
|
| 267 |
+
"logits/rejected": -0.14095698297023773,
|
| 268 |
+
"logps/chosen": -458.0244140625,
|
| 269 |
+
"logps/rejected": -759.4512939453125,
|
| 270 |
+
"loss": 0.2393,
|
| 271 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 272 |
+
"rewards/chosen": -0.12103551626205444,
|
| 273 |
+
"rewards/margins": 0.17601092159748077,
|
| 274 |
+
"rewards/rejected": -0.29704639315605164,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2,
|
| 279 |
+
"learning_rate": 4.8417076618132434e-06,
|
| 280 |
+
"logits/chosen": -0.19613122940063477,
|
| 281 |
+
"logits/rejected": -0.19725319743156433,
|
| 282 |
+
"logps/chosen": -477.3087463378906,
|
| 283 |
+
"logps/rejected": -782.9113159179688,
|
| 284 |
+
"loss": 0.2591,
|
| 285 |
+
"rewards/accuracies": 0.800000011920929,
|
| 286 |
+
"rewards/chosen": -0.12908069789409637,
|
| 287 |
+
"rewards/margins": 0.18730813264846802,
|
| 288 |
+
"rewards/rejected": -0.3163888156414032,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21,
|
| 293 |
+
"learning_rate": 4.807464225455655e-06,
|
| 294 |
+
"logits/chosen": -0.18979570269584656,
|
| 295 |
+
"logits/rejected": -0.12616662681102753,
|
| 296 |
+
"logps/chosen": -501.4048767089844,
|
| 297 |
+
"logps/rejected": -773.6704711914062,
|
| 298 |
+
"loss": 0.2318,
|
| 299 |
+
"rewards/accuracies": 0.71875,
|
| 300 |
+
"rewards/chosen": -0.126991406083107,
|
| 301 |
+
"rewards/margins": 0.16587643325328827,
|
| 302 |
+
"rewards/rejected": -0.29286783933639526,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.770016517582283e-06,
|
| 308 |
+
"logits/chosen": -0.19870837032794952,
|
| 309 |
+
"logits/rejected": -0.1376388520002365,
|
| 310 |
+
"logps/chosen": -476.4922790527344,
|
| 311 |
+
"logps/rejected": -797.6036376953125,
|
| 312 |
+
"loss": 0.2344,
|
| 313 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 314 |
+
"rewards/chosen": -0.12952814996242523,
|
| 315 |
+
"rewards/margins": 0.19133572280406952,
|
| 316 |
+
"rewards/rejected": -0.32086387276649475,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23,
|
| 321 |
+
"learning_rate": 4.7294165401363616e-06,
|
| 322 |
+
"logits/chosen": -0.18674388527870178,
|
| 323 |
+
"logits/rejected": -0.17149865627288818,
|
| 324 |
+
"logps/chosen": -476.748779296875,
|
| 325 |
+
"logps/rejected": -736.6768798828125,
|
| 326 |
+
"loss": 0.2225,
|
| 327 |
+
"rewards/accuracies": 0.768750011920929,
|
| 328 |
+
"rewards/chosen": -0.1292114555835724,
|
| 329 |
+
"rewards/margins": 0.17972734570503235,
|
| 330 |
+
"rewards/rejected": -0.30893880128860474,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"learning_rate": 4.68572067247573e-06,
|
| 336 |
+
"logits/chosen": -0.2134261131286621,
|
| 337 |
+
"logits/rejected": -0.17389492690563202,
|
| 338 |
+
"logps/chosen": -556.177490234375,
|
| 339 |
+
"logps/rejected": -932.4171752929688,
|
| 340 |
+
"loss": 0.2011,
|
| 341 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 342 |
+
"rewards/chosen": -0.17576465010643005,
|
| 343 |
+
"rewards/margins": 0.23368000984191895,
|
| 344 |
+
"rewards/rejected": -0.4094447195529938,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.638989593081364e-06,
|
| 350 |
+
"logits/chosen": -0.2312520444393158,
|
| 351 |
+
"logits/rejected": -0.17490056157112122,
|
| 352 |
+
"logps/chosen": -608.5135498046875,
|
| 353 |
+
"logps/rejected": -883.7859497070312,
|
| 354 |
+
"loss": 0.2251,
|
| 355 |
+
"rewards/accuracies": 0.78125,
|
| 356 |
+
"rewards/chosen": -0.19390198588371277,
|
| 357 |
+
"rewards/margins": 0.20176473259925842,
|
| 358 |
+
"rewards/rejected": -0.3956666886806488,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"learning_rate": 4.5892881952959015e-06,
|
| 364 |
+
"logits/chosen": -0.19589188694953918,
|
| 365 |
+
"logits/rejected": -0.16277478635311127,
|
| 366 |
+
"logps/chosen": -522.8567504882812,
|
| 367 |
+
"logps/rejected": -815.2623291015625,
|
| 368 |
+
"loss": 0.2215,
|
| 369 |
+
"rewards/accuracies": 0.793749988079071,
|
| 370 |
+
"rewards/chosen": -0.15903013944625854,
|
| 371 |
+
"rewards/margins": 0.19178643822669983,
|
| 372 |
+
"rewards/rejected": -0.3508165776729584,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"learning_rate": 4.536685497209182e-06,
|
| 378 |
+
"logits/chosen": -0.25143852829933167,
|
| 379 |
+
"logits/rejected": -0.15717722475528717,
|
| 380 |
+
"logps/chosen": -533.4439697265625,
|
| 381 |
+
"logps/rejected": -940.82763671875,
|
| 382 |
+
"loss": 0.2056,
|
| 383 |
+
"rewards/accuracies": 0.862500011920929,
|
| 384 |
+
"rewards/chosen": -0.18470649421215057,
|
| 385 |
+
"rewards/margins": 0.22995992004871368,
|
| 386 |
+
"rewards/rejected": -0.41466641426086426,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"learning_rate": 4.481254545815943e-06,
|
| 392 |
+
"logits/chosen": -0.23728492856025696,
|
| 393 |
+
"logits/rejected": -0.22243991494178772,
|
| 394 |
+
"logps/chosen": -552.9218139648438,
|
| 395 |
+
"logps/rejected": -903.7254028320312,
|
| 396 |
+
"loss": 0.196,
|
| 397 |
+
"rewards/accuracies": 0.800000011920929,
|
| 398 |
+
"rewards/chosen": -0.20833177864551544,
|
| 399 |
+
"rewards/margins": 0.22902217507362366,
|
| 400 |
+
"rewards/rejected": -0.4373539388179779,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"learning_rate": 4.42307231557875e-06,
|
| 406 |
+
"logits/chosen": -0.27826839685440063,
|
| 407 |
+
"logits/rejected": -0.200110524892807,
|
| 408 |
+
"logps/chosen": -523.31787109375,
|
| 409 |
+
"logps/rejected": -899.9382934570312,
|
| 410 |
+
"loss": 0.1954,
|
| 411 |
+
"rewards/accuracies": 0.75,
|
| 412 |
+
"rewards/chosen": -0.20382864773273468,
|
| 413 |
+
"rewards/margins": 0.2211592197418213,
|
| 414 |
+
"rewards/rejected": -0.42498788237571716,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"learning_rate": 4.3622196015370305e-06,
|
| 420 |
+
"logits/chosen": -0.23895792663097382,
|
| 421 |
+
"logits/rejected": -0.14843276143074036,
|
| 422 |
+
"logps/chosen": -594.8115844726562,
|
| 423 |
+
"logps/rejected": -907.5458984375,
|
| 424 |
+
"loss": 0.2135,
|
| 425 |
+
"rewards/accuracies": 0.800000011920929,
|
| 426 |
+
"rewards/chosen": -0.19232866168022156,
|
| 427 |
+
"rewards/margins": 0.21376939117908478,
|
| 428 |
+
"rewards/rejected": -0.40609806776046753,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"learning_rate": 4.298780907110648e-06,
|
| 434 |
+
"logits/chosen": -0.24878796935081482,
|
| 435 |
+
"logits/rejected": -0.18727460503578186,
|
| 436 |
+
"logps/chosen": -580.38671875,
|
| 437 |
+
"logps/rejected": -878.1405029296875,
|
| 438 |
+
"loss": 0.1938,
|
| 439 |
+
"rewards/accuracies": 0.800000011920929,
|
| 440 |
+
"rewards/chosen": -0.2084374725818634,
|
| 441 |
+
"rewards/margins": 0.20776410400867462,
|
| 442 |
+
"rewards/rejected": -0.4162015914916992,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"learning_rate": 4.23284432675381e-06,
|
| 448 |
+
"logits/chosen": -0.3039627969264984,
|
| 449 |
+
"logits/rejected": -0.23918378353118896,
|
| 450 |
+
"logps/chosen": -601.3494873046875,
|
| 451 |
+
"logps/rejected": -868.8585815429688,
|
| 452 |
+
"loss": 0.2041,
|
| 453 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 454 |
+
"rewards/chosen": -0.23962783813476562,
|
| 455 |
+
"rewards/margins": 0.18101730942726135,
|
| 456 |
+
"rewards/rejected": -0.420645147562027,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"learning_rate": 4.164501423622277e-06,
|
| 462 |
+
"logits/chosen": -0.3026599884033203,
|
| 463 |
+
"logits/rejected": -0.22676105797290802,
|
| 464 |
+
"logps/chosen": -559.4996337890625,
|
| 465 |
+
"logps/rejected": -871.5550537109375,
|
| 466 |
+
"loss": 0.1855,
|
| 467 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 468 |
+
"rewards/chosen": -0.21141842007637024,
|
| 469 |
+
"rewards/margins": 0.21575455367565155,
|
| 470 |
+
"rewards/rejected": -0.427172988653183,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35,
|
| 475 |
+
"learning_rate": 4.0938471024237355e-06,
|
| 476 |
+
"logits/chosen": -0.24148467183113098,
|
| 477 |
+
"logits/rejected": -0.19344112277030945,
|
| 478 |
+
"logps/chosen": -570.2223510742188,
|
| 479 |
+
"logps/rejected": -958.9056396484375,
|
| 480 |
+
"loss": 0.1827,
|
| 481 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 482 |
+
"rewards/chosen": -0.22266192734241486,
|
| 483 |
+
"rewards/margins": 0.2378120869398117,
|
| 484 |
+
"rewards/rejected": -0.46047407388687134,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36,
|
| 489 |
+
"learning_rate": 4.020979477627907e-06,
|
| 490 |
+
"logits/chosen": -0.23564183712005615,
|
| 491 |
+
"logits/rejected": -0.23679451644420624,
|
| 492 |
+
"logps/chosen": -623.2242431640625,
|
| 493 |
+
"logps/rejected": -871.82568359375,
|
| 494 |
+
"loss": 0.2297,
|
| 495 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 496 |
+
"rewards/chosen": -0.2473243921995163,
|
| 497 |
+
"rewards/margins": 0.19464418292045593,
|
| 498 |
+
"rewards/rejected": -0.44196853041648865,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37,
|
| 503 |
+
"learning_rate": 3.9459997372194105e-06,
|
| 504 |
+
"logits/chosen": -0.22112271189689636,
|
| 505 |
+
"logits/rejected": -0.24255314469337463,
|
| 506 |
+
"logps/chosen": -654.8084716796875,
|
| 507 |
+
"logps/rejected": -992.0069580078125,
|
| 508 |
+
"loss": 0.2101,
|
| 509 |
+
"rewards/accuracies": 0.768750011920929,
|
| 510 |
+
"rewards/chosen": -0.2653377950191498,
|
| 511 |
+
"rewards/margins": 0.21331480145454407,
|
| 512 |
+
"rewards/rejected": -0.47865256667137146,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38,
|
| 517 |
+
"learning_rate": 3.869012002182573e-06,
|
| 518 |
+
"logits/chosen": -0.2565579116344452,
|
| 519 |
+
"logits/rejected": -0.23455138504505157,
|
| 520 |
+
"logps/chosen": -634.1543579101562,
|
| 521 |
+
"logps/rejected": -1048.505859375,
|
| 522 |
+
"loss": 0.1816,
|
| 523 |
+
"rewards/accuracies": 0.8687499761581421,
|
| 524 |
+
"rewards/chosen": -0.246078759431839,
|
| 525 |
+
"rewards/margins": 0.2945541739463806,
|
| 526 |
+
"rewards/rejected": -0.540632963180542,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39,
|
| 531 |
+
"learning_rate": 3.7901231819133104e-06,
|
| 532 |
+
"logits/chosen": -0.27797406911849976,
|
| 533 |
+
"logits/rejected": -0.24355745315551758,
|
| 534 |
+
"logps/chosen": -634.2208251953125,
|
| 535 |
+
"logps/rejected": -972.6463012695312,
|
| 536 |
+
"loss": 0.2072,
|
| 537 |
+
"rewards/accuracies": 0.8125,
|
| 538 |
+
"rewards/chosen": -0.2534112334251404,
|
| 539 |
+
"rewards/margins": 0.23360367119312286,
|
| 540 |
+
"rewards/rejected": -0.48701491951942444,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"learning_rate": 3.709442825758875e-06,
|
| 546 |
+
"logits/chosen": -0.2145443856716156,
|
| 547 |
+
"logits/rejected": -0.2447199821472168,
|
| 548 |
+
"logps/chosen": -630.0811157226562,
|
| 549 |
+
"logps/rejected": -895.8094482421875,
|
| 550 |
+
"loss": 0.2066,
|
| 551 |
+
"rewards/accuracies": 0.78125,
|
| 552 |
+
"rewards/chosen": -0.2521076202392578,
|
| 553 |
+
"rewards/margins": 0.2124219834804535,
|
| 554 |
+
"rewards/rejected": -0.4645296037197113,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"learning_rate": 3.6270829708916113e-06,
|
| 560 |
+
"logits/chosen": -0.26773589849472046,
|
| 561 |
+
"logits/rejected": -0.1856563836336136,
|
| 562 |
+
"logps/chosen": -635.20703125,
|
| 563 |
+
"logps/rejected": -1008.9361572265625,
|
| 564 |
+
"loss": 0.1878,
|
| 565 |
+
"rewards/accuracies": 0.8125,
|
| 566 |
+
"rewards/chosen": -0.2653789818286896,
|
| 567 |
+
"rewards/margins": 0.2648240625858307,
|
| 568 |
+
"rewards/rejected": -0.5302029848098755,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"learning_rate": 3.543157986727991e-06,
|
| 574 |
+
"logits/chosen": -0.24474501609802246,
|
| 575 |
+
"logits/rejected": -0.21170318126678467,
|
| 576 |
+
"logps/chosen": -730.6715087890625,
|
| 577 |
+
"logps/rejected": -1069.3619384765625,
|
| 578 |
+
"loss": 0.2077,
|
| 579 |
+
"rewards/accuracies": 0.800000011920929,
|
| 580 |
+
"rewards/chosen": -0.2803260385990143,
|
| 581 |
+
"rewards/margins": 0.2544651925563812,
|
| 582 |
+
"rewards/rejected": -0.5347911715507507,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"learning_rate": 3.4577844161089614e-06,
|
| 588 |
+
"logits/chosen": -0.1851538121700287,
|
| 589 |
+
"logits/rejected": -0.24047665297985077,
|
| 590 |
+
"logps/chosen": -616.1502685546875,
|
| 591 |
+
"logps/rejected": -903.6608276367188,
|
| 592 |
+
"loss": 0.2123,
|
| 593 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 594 |
+
"rewards/chosen": -0.24726176261901855,
|
| 595 |
+
"rewards/margins": 0.19664901494979858,
|
| 596 |
+
"rewards/rejected": -0.44391077756881714,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"learning_rate": 3.3710808134621577e-06,
|
| 602 |
+
"logits/chosen": -0.2203509360551834,
|
| 603 |
+
"logits/rejected": -0.2040051519870758,
|
| 604 |
+
"logps/chosen": -636.1844482421875,
|
| 605 |
+
"logps/rejected": -1008.9363403320312,
|
| 606 |
+
"loss": 0.1868,
|
| 607 |
+
"rewards/accuracies": 0.856249988079071,
|
| 608 |
+
"rewards/chosen": -0.2344098538160324,
|
| 609 |
+
"rewards/margins": 0.2508249282836914,
|
| 610 |
+
"rewards/rejected": -0.485234797000885,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"learning_rate": 3.2831675801707126e-06,
|
| 616 |
+
"logits/chosen": -0.2882968783378601,
|
| 617 |
+
"logits/rejected": -0.28868910670280457,
|
| 618 |
+
"logps/chosen": -629.03662109375,
|
| 619 |
+
"logps/rejected": -997.5048828125,
|
| 620 |
+
"loss": 0.1877,
|
| 621 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 622 |
+
"rewards/chosen": -0.2724894881248474,
|
| 623 |
+
"rewards/margins": 0.2427108734846115,
|
| 624 |
+
"rewards/rejected": -0.5152003765106201,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"learning_rate": 3.194166797377289e-06,
|
| 630 |
+
"logits/chosen": -0.2842113971710205,
|
| 631 |
+
"logits/rejected": -0.2725662589073181,
|
| 632 |
+
"logps/chosen": -629.4954223632812,
|
| 633 |
+
"logps/rejected": -921.0350341796875,
|
| 634 |
+
"loss": 0.1871,
|
| 635 |
+
"rewards/accuracies": 0.824999988079071,
|
| 636 |
+
"rewards/chosen": -0.2583664059638977,
|
| 637 |
+
"rewards/margins": 0.23012156784534454,
|
| 638 |
+
"rewards/rejected": -0.48848801851272583,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"learning_rate": 3.104202056455501e-06,
|
| 644 |
+
"logits/chosen": -0.23092789947986603,
|
| 645 |
+
"logits/rejected": -0.2383890151977539,
|
| 646 |
+
"logps/chosen": -603.952392578125,
|
| 647 |
+
"logps/rejected": -931.93994140625,
|
| 648 |
+
"loss": 0.1852,
|
| 649 |
+
"rewards/accuracies": 0.768750011920929,
|
| 650 |
+
"rewards/chosen": -0.24851222336292267,
|
| 651 |
+
"rewards/margins": 0.2311173975467682,
|
| 652 |
+
"rewards/rejected": -0.4796296954154968,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"learning_rate": 3.013398287384144e-06,
|
| 658 |
+
"logits/chosen": -0.25257351994514465,
|
| 659 |
+
"logits/rejected": -0.20124118030071259,
|
| 660 |
+
"logps/chosen": -720.2821044921875,
|
| 661 |
+
"logps/rejected": -1016.345703125,
|
| 662 |
+
"loss": 0.2169,
|
| 663 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 664 |
+
"rewards/chosen": -0.291043221950531,
|
| 665 |
+
"rewards/margins": 0.23256464302539825,
|
| 666 |
+
"rewards/rejected": -0.5236078500747681,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"learning_rate": 2.9218815852625717e-06,
|
| 672 |
+
"logits/chosen": -0.280508816242218,
|
| 673 |
+
"logits/rejected": -0.27508029341697693,
|
| 674 |
+
"logps/chosen": -599.3237915039062,
|
| 675 |
+
"logps/rejected": -959.4754028320312,
|
| 676 |
+
"loss": 0.1873,
|
| 677 |
+
"rewards/accuracies": 0.8125,
|
| 678 |
+
"rewards/chosen": -0.266213595867157,
|
| 679 |
+
"rewards/margins": 0.23423174023628235,
|
| 680 |
+
"rewards/rejected": -0.5004453063011169,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"learning_rate": 2.829779035208113e-06,
|
| 686 |
+
"logits/chosen": -0.264869749546051,
|
| 687 |
+
"logits/rejected": -0.2316662073135376,
|
| 688 |
+
"logps/chosen": -632.74853515625,
|
| 689 |
+
"logps/rejected": -977.66845703125,
|
| 690 |
+
"loss": 0.1933,
|
| 691 |
+
"rewards/accuracies": 0.762499988079071,
|
| 692 |
+
"rewards/chosen": -0.2532680928707123,
|
| 693 |
+
"rewards/margins": 0.23631851375102997,
|
| 694 |
+
"rewards/rejected": -0.48958665132522583,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"learning_rate": 2.737218535878705e-06,
|
| 700 |
+
"logits/chosen": -0.26723513007164,
|
| 701 |
+
"logits/rejected": -0.2752009928226471,
|
| 702 |
+
"logps/chosen": -612.4442749023438,
|
| 703 |
+
"logps/rejected": -949.7120971679688,
|
| 704 |
+
"loss": 0.1789,
|
| 705 |
+
"rewards/accuracies": 0.793749988079071,
|
| 706 |
+
"rewards/chosen": -0.2443923056125641,
|
| 707 |
+
"rewards/margins": 0.23941712081432343,
|
| 708 |
+
"rewards/rejected": -0.4838094115257263,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.53,
|
| 713 |
+
"learning_rate": 2.64432862186579e-06,
|
| 714 |
+
"logits/chosen": -0.3223264515399933,
|
| 715 |
+
"logits/rejected": -0.29264402389526367,
|
| 716 |
+
"logps/chosen": -628.1448974609375,
|
| 717 |
+
"logps/rejected": -997.76123046875,
|
| 718 |
+
"loss": 0.1908,
|
| 719 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 720 |
+
"rewards/chosen": -0.26595020294189453,
|
| 721 |
+
"rewards/margins": 0.25043538212776184,
|
| 722 |
+
"rewards/rejected": -0.516385555267334,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.54,
|
| 727 |
+
"learning_rate": 2.551238285204126e-06,
|
| 728 |
+
"logits/chosen": -0.2382831573486328,
|
| 729 |
+
"logits/rejected": -0.2551121711730957,
|
| 730 |
+
"logps/chosen": -653.0089111328125,
|
| 731 |
+
"logps/rejected": -1023.2013549804688,
|
| 732 |
+
"loss": 0.2152,
|
| 733 |
+
"rewards/accuracies": 0.8125,
|
| 734 |
+
"rewards/chosen": -0.2814193367958069,
|
| 735 |
+
"rewards/margins": 0.2521519660949707,
|
| 736 |
+
"rewards/rejected": -0.5335713028907776,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.55,
|
| 741 |
+
"learning_rate": 2.4580767962463688e-06,
|
| 742 |
+
"logits/chosen": -0.25415441393852234,
|
| 743 |
+
"logits/rejected": -0.2852818965911865,
|
| 744 |
+
"logps/chosen": -588.615234375,
|
| 745 |
+
"logps/rejected": -990.0931396484375,
|
| 746 |
+
"loss": 0.1917,
|
| 747 |
+
"rewards/accuracies": 0.793749988079071,
|
| 748 |
+
"rewards/chosen": -0.2602744996547699,
|
| 749 |
+
"rewards/margins": 0.24789556860923767,
|
| 750 |
+
"rewards/rejected": -0.5081701278686523,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"learning_rate": 2.3649735241511546e-06,
|
| 756 |
+
"logits/chosen": -0.2810899317264557,
|
| 757 |
+
"logits/rejected": -0.24050931632518768,
|
| 758 |
+
"logps/chosen": -667.4718627929688,
|
| 759 |
+
"logps/rejected": -1030.656494140625,
|
| 760 |
+
"loss": 0.1788,
|
| 761 |
+
"rewards/accuracies": 0.793749988079071,
|
| 762 |
+
"rewards/chosen": -0.2851766049861908,
|
| 763 |
+
"rewards/margins": 0.2829527258872986,
|
| 764 |
+
"rewards/rejected": -0.5681293606758118,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"learning_rate": 2.2720577572339914e-06,
|
| 770 |
+
"logits/chosen": -0.29503872990608215,
|
| 771 |
+
"logits/rejected": -0.2738192677497864,
|
| 772 |
+
"logps/chosen": -669.0242309570312,
|
| 773 |
+
"logps/rejected": -1088.0225830078125,
|
| 774 |
+
"loss": 0.1644,
|
| 775 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 776 |
+
"rewards/chosen": -0.29529038071632385,
|
| 777 |
+
"rewards/margins": 0.3003653287887573,
|
| 778 |
+
"rewards/rejected": -0.5956557393074036,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"learning_rate": 2.1794585234303995e-06,
|
| 784 |
+
"logits/chosen": -0.2950688898563385,
|
| 785 |
+
"logits/rejected": -0.1541706621646881,
|
| 786 |
+
"logps/chosen": -705.3633422851562,
|
| 787 |
+
"logps/rejected": -1031.0267333984375,
|
| 788 |
+
"loss": 0.1825,
|
| 789 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 790 |
+
"rewards/chosen": -0.2902067303657532,
|
| 791 |
+
"rewards/margins": 0.284890741109848,
|
| 792 |
+
"rewards/rejected": -0.5750974416732788,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"learning_rate": 2.0873044111206407e-06,
|
| 798 |
+
"logits/chosen": -0.28339633345603943,
|
| 799 |
+
"logits/rejected": -0.22169962525367737,
|
| 800 |
+
"logps/chosen": -629.9029541015625,
|
| 801 |
+
"logps/rejected": -1066.449462890625,
|
| 802 |
+
"loss": 0.1942,
|
| 803 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 804 |
+
"rewards/chosen": -0.2589099705219269,
|
| 805 |
+
"rewards/margins": 0.2774832844734192,
|
| 806 |
+
"rewards/rejected": -0.5363932847976685,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"learning_rate": 1.9957233905648293e-06,
|
| 812 |
+
"logits/chosen": -0.24862179160118103,
|
| 813 |
+
"logits/rejected": -0.22971436381340027,
|
| 814 |
+
"logps/chosen": -636.7313232421875,
|
| 815 |
+
"logps/rejected": -972.0720825195312,
|
| 816 |
+
"loss": 0.1842,
|
| 817 |
+
"rewards/accuracies": 0.78125,
|
| 818 |
+
"rewards/chosen": -0.2589462399482727,
|
| 819 |
+
"rewards/margins": 0.2386230230331421,
|
| 820 |
+
"rewards/rejected": -0.4975692629814148,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"learning_rate": 1.904842636196402e-06,
|
| 826 |
+
"logits/chosen": -0.2794085443019867,
|
| 827 |
+
"logits/rejected": -0.25304803252220154,
|
| 828 |
+
"logps/chosen": -655.1509399414062,
|
| 829 |
+
"logps/rejected": -1037.134033203125,
|
| 830 |
+
"loss": 0.2004,
|
| 831 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 832 |
+
"rewards/chosen": -0.2735671103000641,
|
| 833 |
+
"rewards/margins": 0.27847912907600403,
|
| 834 |
+
"rewards/rejected": -0.5520461797714233,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"learning_rate": 1.814788350020726e-06,
|
| 840 |
+
"logits/chosen": -0.2863375246524811,
|
| 841 |
+
"logits/rejected": -0.2578074336051941,
|
| 842 |
+
"logps/chosen": -644.8294067382812,
|
| 843 |
+
"logps/rejected": -978.0472412109375,
|
| 844 |
+
"loss": 0.1852,
|
| 845 |
+
"rewards/accuracies": 0.8125,
|
| 846 |
+
"rewards/chosen": -0.27340829372406006,
|
| 847 |
+
"rewards/margins": 0.256661593914032,
|
| 848 |
+
"rewards/rejected": -0.5300698280334473,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"learning_rate": 1.725685586364051e-06,
|
| 854 |
+
"logits/chosen": -0.30925947427749634,
|
| 855 |
+
"logits/rejected": -0.26838865876197815,
|
| 856 |
+
"logps/chosen": -632.4716796875,
|
| 857 |
+
"logps/rejected": -994.3053588867188,
|
| 858 |
+
"loss": 0.2151,
|
| 859 |
+
"rewards/accuracies": 0.800000011920929,
|
| 860 |
+
"rewards/chosen": -0.27847468852996826,
|
| 861 |
+
"rewards/margins": 0.25020256638526917,
|
| 862 |
+
"rewards/rejected": -0.5286772847175598,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"learning_rate": 1.6376580782162172e-06,
|
| 868 |
+
"logits/chosen": -0.20261721312999725,
|
| 869 |
+
"logits/rejected": -0.221277117729187,
|
| 870 |
+
"logps/chosen": -634.4677124023438,
|
| 871 |
+
"logps/rejected": -994.3683471679688,
|
| 872 |
+
"loss": 0.1934,
|
| 873 |
+
"rewards/accuracies": 0.793749988079071,
|
| 874 |
+
"rewards/chosen": -0.25305241346359253,
|
| 875 |
+
"rewards/margins": 0.2600497603416443,
|
| 876 |
+
"rewards/rejected": -0.5131021738052368,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"learning_rate": 1.550828065408227e-06,
|
| 882 |
+
"logits/chosen": -0.293588250875473,
|
| 883 |
+
"logits/rejected": -0.250821977853775,
|
| 884 |
+
"logps/chosen": -588.5574951171875,
|
| 885 |
+
"logps/rejected": -976.6282348632812,
|
| 886 |
+
"loss": 0.1876,
|
| 887 |
+
"rewards/accuracies": 0.831250011920929,
|
| 888 |
+
"rewards/chosen": -0.26154106855392456,
|
| 889 |
+
"rewards/margins": 0.25152388215065,
|
| 890 |
+
"rewards/rejected": -0.5130649209022522,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"learning_rate": 1.4653161248633053e-06,
|
| 896 |
+
"logits/chosen": -0.25644367933273315,
|
| 897 |
+
"logits/rejected": -0.2529579699039459,
|
| 898 |
+
"logps/chosen": -637.1114501953125,
|
| 899 |
+
"logps/rejected": -1041.966064453125,
|
| 900 |
+
"loss": 0.177,
|
| 901 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 902 |
+
"rewards/chosen": -0.26990941166877747,
|
| 903 |
+
"rewards/margins": 0.2800416052341461,
|
| 904 |
+
"rewards/rejected": -0.5499509572982788,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"learning_rate": 1.381241003157162e-06,
|
| 910 |
+
"logits/chosen": -0.25759977102279663,
|
| 911 |
+
"logits/rejected": -0.22868645191192627,
|
| 912 |
+
"logps/chosen": -585.88671875,
|
| 913 |
+
"logps/rejected": -971.8045043945312,
|
| 914 |
+
"loss": 0.1695,
|
| 915 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 916 |
+
"rewards/chosen": -0.24511754512786865,
|
| 917 |
+
"rewards/margins": 0.2909080982208252,
|
| 918 |
+
"rewards/rejected": -0.5360256433486938,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"learning_rate": 1.298719451619979e-06,
|
| 924 |
+
"logits/chosen": -0.27405595779418945,
|
| 925 |
+
"logits/rejected": -0.25046929717063904,
|
| 926 |
+
"logps/chosen": -686.3485107421875,
|
| 927 |
+
"logps/rejected": -1069.6209716796875,
|
| 928 |
+
"loss": 0.1779,
|
| 929 |
+
"rewards/accuracies": 0.793749988079071,
|
| 930 |
+
"rewards/chosen": -0.29048749804496765,
|
| 931 |
+
"rewards/margins": 0.3021007776260376,
|
| 932 |
+
"rewards/rejected": -0.5925883054733276,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"learning_rate": 1.2178660642091036e-06,
|
| 938 |
+
"logits/chosen": -0.258391410112381,
|
| 939 |
+
"logits/rejected": -0.2719349265098572,
|
| 940 |
+
"logps/chosen": -642.6732177734375,
|
| 941 |
+
"logps/rejected": -1080.385498046875,
|
| 942 |
+
"loss": 0.1866,
|
| 943 |
+
"rewards/accuracies": 0.875,
|
| 944 |
+
"rewards/chosen": -0.2909965515136719,
|
| 945 |
+
"rewards/margins": 0.3018215596675873,
|
| 946 |
+
"rewards/rejected": -0.5928180813789368,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"learning_rate": 1.1387931183775821e-06,
|
| 952 |
+
"logits/chosen": -0.29932543635368347,
|
| 953 |
+
"logits/rejected": -0.2793118357658386,
|
| 954 |
+
"logps/chosen": -649.6714477539062,
|
| 955 |
+
"logps/rejected": -1090.2452392578125,
|
| 956 |
+
"loss": 0.1646,
|
| 957 |
+
"rewards/accuracies": 0.831250011920929,
|
| 958 |
+
"rewards/chosen": -0.2679978013038635,
|
| 959 |
+
"rewards/margins": 0.30532750487327576,
|
| 960 |
+
"rewards/rejected": -0.5733253359794617,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"learning_rate": 1.061610419159532e-06,
|
| 966 |
+
"logits/chosen": -0.27962726354599,
|
| 967 |
+
"logits/rejected": -0.21005702018737793,
|
| 968 |
+
"logps/chosen": -654.9832763671875,
|
| 969 |
+
"logps/rejected": -1042.5281982421875,
|
| 970 |
+
"loss": 0.195,
|
| 971 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 972 |
+
"rewards/chosen": -0.28967055678367615,
|
| 973 |
+
"rewards/margins": 0.28377145528793335,
|
| 974 |
+
"rewards/rejected": -0.5734419822692871,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"learning_rate": 9.864251466888364e-07,
|
| 980 |
+
"logits/chosen": -0.2319578379392624,
|
| 981 |
+
"logits/rejected": -0.22523808479309082,
|
| 982 |
+
"logps/chosen": -587.6854248046875,
|
| 983 |
+
"logps/rejected": -929.84716796875,
|
| 984 |
+
"loss": 0.1957,
|
| 985 |
+
"rewards/accuracies": 0.78125,
|
| 986 |
+
"rewards/chosen": -0.2619277834892273,
|
| 987 |
+
"rewards/margins": 0.24305231869220734,
|
| 988 |
+
"rewards/rejected": -0.5049800276756287,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"learning_rate": 9.133417073629288e-07,
|
| 994 |
+
"logits/chosen": -0.2581741213798523,
|
| 995 |
+
"logits/rejected": -0.22566178441047668,
|
| 996 |
+
"logps/chosen": -673.9590454101562,
|
| 997 |
+
"logps/rejected": -1043.8779296875,
|
| 998 |
+
"loss": 0.1946,
|
| 999 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1000 |
+
"rewards/chosen": -0.2741592526435852,
|
| 1001 |
+
"rewards/margins": 0.2668037712574005,
|
| 1002 |
+
"rewards/rejected": -0.5409630537033081,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"learning_rate": 8.424615888583332e-07,
|
| 1008 |
+
"logits/chosen": -0.24903810024261475,
|
| 1009 |
+
"logits/rejected": -0.19368259608745575,
|
| 1010 |
+
"logps/chosen": -702.1976318359375,
|
| 1011 |
+
"logps/rejected": -1104.967529296875,
|
| 1012 |
+
"loss": 0.1768,
|
| 1013 |
+
"rewards/accuracies": 0.78125,
|
| 1014 |
+
"rewards/chosen": -0.29275885224342346,
|
| 1015 |
+
"rewards/margins": 0.24981990456581116,
|
| 1016 |
+
"rewards/rejected": -0.5425786972045898,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"learning_rate": 7.738832191993092e-07,
|
| 1022 |
+
"logits/chosen": -0.2902497947216034,
|
| 1023 |
+
"logits/rejected": -0.27156323194503784,
|
| 1024 |
+
"logps/chosen": -642.2786865234375,
|
| 1025 |
+
"logps/rejected": -1030.1949462890625,
|
| 1026 |
+
"loss": 0.1896,
|
| 1027 |
+
"rewards/accuracies": 0.8125,
|
| 1028 |
+
"rewards/chosen": -0.296554833650589,
|
| 1029 |
+
"rewards/margins": 0.2522734999656677,
|
| 1030 |
+
"rewards/rejected": -0.5488283634185791,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"learning_rate": 7.077018300752917e-07,
|
| 1036 |
+
"logits/chosen": -0.25113141536712646,
|
| 1037 |
+
"logits/rejected": -0.27631789445877075,
|
| 1038 |
+
"logps/chosen": -658.340087890625,
|
| 1039 |
+
"logps/rejected": -1025.861328125,
|
| 1040 |
+
"loss": 0.1804,
|
| 1041 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1042 |
+
"rewards/chosen": -0.2932133376598358,
|
| 1043 |
+
"rewards/margins": 0.24299320578575134,
|
| 1044 |
+
"rewards/rejected": -0.5362066030502319,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"learning_rate": 6.440093245969342e-07,
|
| 1050 |
+
"logits/chosen": -0.2601129412651062,
|
| 1051 |
+
"logits/rejected": -0.23299941420555115,
|
| 1052 |
+
"logps/chosen": -661.2008056640625,
|
| 1053 |
+
"logps/rejected": -1049.9329833984375,
|
| 1054 |
+
"loss": 0.1731,
|
| 1055 |
+
"rewards/accuracies": 0.84375,
|
| 1056 |
+
"rewards/chosen": -0.28521472215652466,
|
| 1057 |
+
"rewards/margins": 0.2829175591468811,
|
| 1058 |
+
"rewards/rejected": -0.5681322813034058,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"learning_rate": 5.828941496744075e-07,
|
| 1064 |
+
"logits/chosen": -0.2920230031013489,
|
| 1065 |
+
"logits/rejected": -0.2706466317176819,
|
| 1066 |
+
"logps/chosen": -614.7430419921875,
|
| 1067 |
+
"logps/rejected": -1084.22802734375,
|
| 1068 |
+
"loss": 0.1975,
|
| 1069 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1070 |
+
"rewards/chosen": -0.26638248562812805,
|
| 1071 |
+
"rewards/margins": 0.29731154441833496,
|
| 1072 |
+
"rewards/rejected": -0.5636940598487854,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"learning_rate": 5.244411731951671e-07,
|
| 1078 |
+
"logits/chosen": -0.2530083954334259,
|
| 1079 |
+
"logits/rejected": -0.2159876525402069,
|
| 1080 |
+
"logps/chosen": -636.4935913085938,
|
| 1081 |
+
"logps/rejected": -965.4192504882812,
|
| 1082 |
+
"loss": 0.1974,
|
| 1083 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1084 |
+
"rewards/chosen": -0.27532270550727844,
|
| 1085 |
+
"rewards/margins": 0.23001885414123535,
|
| 1086 |
+
"rewards/rejected": -0.5053415298461914,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"learning_rate": 4.6873156617173594e-07,
|
| 1092 |
+
"logits/chosen": -0.2676984369754791,
|
| 1093 |
+
"logits/rejected": -0.2522314190864563,
|
| 1094 |
+
"logps/chosen": -619.7949829101562,
|
| 1095 |
+
"logps/rejected": -1006.8516845703125,
|
| 1096 |
+
"loss": 0.1934,
|
| 1097 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1098 |
+
"rewards/chosen": -0.25617390871047974,
|
| 1099 |
+
"rewards/margins": 0.25205108523368835,
|
| 1100 |
+
"rewards/rejected": -0.5082249641418457,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"learning_rate": 4.1584269002318653e-07,
|
| 1106 |
+
"logits/chosen": -0.276606023311615,
|
| 1107 |
+
"logits/rejected": -0.18771035969257355,
|
| 1108 |
+
"logps/chosen": -680.2154541015625,
|
| 1109 |
+
"logps/rejected": -1099.0855712890625,
|
| 1110 |
+
"loss": 0.1918,
|
| 1111 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 1112 |
+
"rewards/chosen": -0.2760952413082123,
|
| 1113 |
+
"rewards/margins": 0.2856435477733612,
|
| 1114 |
+
"rewards/rejected": -0.5617388486862183,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"learning_rate": 3.658479891468258e-07,
|
| 1120 |
+
"logits/chosen": -0.2671615183353424,
|
| 1121 |
+
"logits/rejected": -0.28831931948661804,
|
| 1122 |
+
"logps/chosen": -652.9794921875,
|
| 1123 |
+
"logps/rejected": -1049.533447265625,
|
| 1124 |
+
"loss": 0.1852,
|
| 1125 |
+
"rewards/accuracies": 0.8125,
|
| 1126 |
+
"rewards/chosen": -0.2673850953578949,
|
| 1127 |
+
"rewards/margins": 0.2847273647785187,
|
| 1128 |
+
"rewards/rejected": -0.5521124601364136,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"learning_rate": 3.18816888929272e-07,
|
| 1134 |
+
"logits/chosen": -0.2824237644672394,
|
| 1135 |
+
"logits/rejected": -0.2227623015642166,
|
| 1136 |
+
"logps/chosen": -643.0541381835938,
|
| 1137 |
+
"logps/rejected": -957.2637939453125,
|
| 1138 |
+
"loss": 0.207,
|
| 1139 |
+
"rewards/accuracies": 0.75,
|
| 1140 |
+
"rewards/chosen": -0.2690204679965973,
|
| 1141 |
+
"rewards/margins": 0.2505555748939514,
|
| 1142 |
+
"rewards/rejected": -0.5195759534835815,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"learning_rate": 2.748146993385484e-07,
|
| 1148 |
+
"logits/chosen": -0.3143889307975769,
|
| 1149 |
+
"logits/rejected": -0.2759067118167877,
|
| 1150 |
+
"logps/chosen": -651.569580078125,
|
| 1151 |
+
"logps/rejected": -1108.028076171875,
|
| 1152 |
+
"loss": 0.1587,
|
| 1153 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1154 |
+
"rewards/chosen": -0.2932509779930115,
|
| 1155 |
+
"rewards/margins": 0.2749115526676178,
|
| 1156 |
+
"rewards/rejected": -0.5681625604629517,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"learning_rate": 2.3390252423108077e-07,
|
| 1162 |
+
"logits/chosen": -0.26839888095855713,
|
| 1163 |
+
"logits/rejected": -0.23119351267814636,
|
| 1164 |
+
"logps/chosen": -665.0179443359375,
|
| 1165 |
+
"logps/rejected": -1112.646728515625,
|
| 1166 |
+
"loss": 0.1658,
|
| 1167 |
+
"rewards/accuracies": 0.8687499761581421,
|
| 1168 |
+
"rewards/chosen": -0.28339672088623047,
|
| 1169 |
+
"rewards/margins": 0.3101740777492523,
|
| 1170 |
+
"rewards/rejected": -0.5935708284378052,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"learning_rate": 1.961371764995243e-07,
|
| 1176 |
+
"logits/chosen": -0.2762928605079651,
|
| 1177 |
+
"logits/rejected": -0.28436392545700073,
|
| 1178 |
+
"logps/chosen": -631.9949951171875,
|
| 1179 |
+
"logps/rejected": -1104.309326171875,
|
| 1180 |
+
"loss": 0.1821,
|
| 1181 |
+
"rewards/accuracies": 0.862500011920929,
|
| 1182 |
+
"rewards/chosen": -0.2872810959815979,
|
| 1183 |
+
"rewards/margins": 0.303080290555954,
|
| 1184 |
+
"rewards/rejected": -0.5903614163398743,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"learning_rate": 1.61571099179261e-07,
|
| 1190 |
+
"logits/chosen": -0.2735849916934967,
|
| 1191 |
+
"logits/rejected": -0.2402714043855667,
|
| 1192 |
+
"logps/chosen": -652.4813842773438,
|
| 1193 |
+
"logps/rejected": -1141.485107421875,
|
| 1194 |
+
"loss": 0.1638,
|
| 1195 |
+
"rewards/accuracies": 0.8687499761581421,
|
| 1196 |
+
"rewards/chosen": -0.2600463032722473,
|
| 1197 |
+
"rewards/margins": 0.34138140082359314,
|
| 1198 |
+
"rewards/rejected": -0.6014277338981628,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"learning_rate": 1.3025229262312367e-07,
|
| 1204 |
+
"logits/chosen": -0.20563116669654846,
|
| 1205 |
+
"logits/rejected": -0.25282037258148193,
|
| 1206 |
+
"logps/chosen": -693.9833984375,
|
| 1207 |
+
"logps/rejected": -1084.752197265625,
|
| 1208 |
+
"loss": 0.183,
|
| 1209 |
+
"rewards/accuracies": 0.84375,
|
| 1210 |
+
"rewards/chosen": -0.2829940617084503,
|
| 1211 |
+
"rewards/margins": 0.27976807951927185,
|
| 1212 |
+
"rewards/rejected": -0.5627621412277222,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"learning_rate": 1.0222424784546853e-07,
|
| 1218 |
+
"logits/chosen": -0.22862930595874786,
|
| 1219 |
+
"logits/rejected": -0.21136240661144257,
|
| 1220 |
+
"logps/chosen": -638.4495239257812,
|
| 1221 |
+
"logps/rejected": -1061.037109375,
|
| 1222 |
+
"loss": 0.1807,
|
| 1223 |
+
"rewards/accuracies": 0.8062499761581421,
|
| 1224 |
+
"rewards/chosen": -0.2733309268951416,
|
| 1225 |
+
"rewards/margins": 0.28016480803489685,
|
| 1226 |
+
"rewards/rejected": -0.5534957647323608,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"learning_rate": 7.752588612816553e-08,
|
| 1232 |
+
"logits/chosen": -0.2907347083091736,
|
| 1233 |
+
"logits/rejected": -0.2525694966316223,
|
| 1234 |
+
"logps/chosen": -626.2022705078125,
|
| 1235 |
+
"logps/rejected": -999.1546630859375,
|
| 1236 |
+
"loss": 0.19,
|
| 1237 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1238 |
+
"rewards/chosen": -0.2700883746147156,
|
| 1239 |
+
"rewards/margins": 0.2750420868396759,
|
| 1240 |
+
"rewards/rejected": -0.5451304316520691,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"learning_rate": 5.619150497236991e-08,
|
| 1246 |
+
"logits/chosen": -0.2824448347091675,
|
| 1247 |
+
"logits/rejected": -0.21472208201885223,
|
| 1248 |
+
"logps/chosen": -694.7796630859375,
|
| 1249 |
+
"logps/rejected": -1101.357666015625,
|
| 1250 |
+
"loss": 0.1808,
|
| 1251 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1252 |
+
"rewards/chosen": -0.30949831008911133,
|
| 1253 |
+
"rewards/margins": 0.29203012585639954,
|
| 1254 |
+
"rewards/rejected": -0.601528525352478,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"learning_rate": 3.825073047112743e-08,
|
| 1260 |
+
"logits/chosen": -0.2339903563261032,
|
| 1261 |
+
"logits/rejected": -0.25414004921913147,
|
| 1262 |
+
"logps/chosen": -677.6926879882812,
|
| 1263 |
+
"logps/rejected": -1110.830810546875,
|
| 1264 |
+
"loss": 0.175,
|
| 1265 |
+
"rewards/accuracies": 0.8812500238418579,
|
| 1266 |
+
"rewards/chosen": -0.2908310890197754,
|
| 1267 |
+
"rewards/margins": 0.3078031539916992,
|
| 1268 |
+
"rewards/rejected": -0.5986341834068298,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"learning_rate": 2.372847616895685e-08,
|
| 1274 |
+
"logits/chosen": -0.2827141582965851,
|
| 1275 |
+
"logits/rejected": -0.24739205837249756,
|
| 1276 |
+
"logps/chosen": -659.048583984375,
|
| 1277 |
+
"logps/rejected": -1077.357177734375,
|
| 1278 |
+
"loss": 0.1941,
|
| 1279 |
+
"rewards/accuracies": 0.793749988079071,
|
| 1280 |
+
"rewards/chosen": -0.28590255975723267,
|
| 1281 |
+
"rewards/margins": 0.280953586101532,
|
| 1282 |
+
"rewards/rejected": -0.5668561458587646,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"learning_rate": 1.264490846553279e-08,
|
| 1288 |
+
"logits/chosen": -0.29719191789627075,
|
| 1289 |
+
"logits/rejected": -0.23341615498065948,
|
| 1290 |
+
"logps/chosen": -676.8151245117188,
|
| 1291 |
+
"logps/rejected": -1061.142822265625,
|
| 1292 |
+
"loss": 0.1835,
|
| 1293 |
+
"rewards/accuracies": 0.8187500238418579,
|
| 1294 |
+
"rewards/chosen": -0.2869683802127838,
|
| 1295 |
+
"rewards/margins": 0.2846153676509857,
|
| 1296 |
+
"rewards/rejected": -0.57158362865448,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"learning_rate": 5.015418611516165e-09,
|
| 1302 |
+
"logits/chosen": -0.22863967716693878,
|
| 1303 |
+
"logits/rejected": -0.20865638554096222,
|
| 1304 |
+
"logps/chosen": -656.0875854492188,
|
| 1305 |
+
"logps/rejected": -1003.3201904296875,
|
| 1306 |
+
"loss": 0.1869,
|
| 1307 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1308 |
+
"rewards/chosen": -0.2743567228317261,
|
| 1309 |
+
"rewards/margins": 0.260437935590744,
|
| 1310 |
+
"rewards/rejected": -0.5347946286201477,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"learning_rate": 8.506013354186993e-10,
|
| 1316 |
+
"logits/chosen": -0.22728657722473145,
|
| 1317 |
+
"logits/rejected": -0.21279653906822205,
|
| 1318 |
+
"logps/chosen": -687.8726806640625,
|
| 1319 |
+
"logps/rejected": -1077.039306640625,
|
| 1320 |
+
"loss": 0.1753,
|
| 1321 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1322 |
+
"rewards/chosen": -0.28496915102005005,
|
| 1323 |
+
"rewards/margins": 0.2890021502971649,
|
| 1324 |
+
"rewards/rejected": -0.5739713907241821,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 937,
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_loss": 0.08644322651809155,
|
| 1332 |
+
"train_runtime": 5283.9744,
|
| 1333 |
+
"train_samples_per_second": 5.678,
|
| 1334 |
+
"train_steps_per_second": 0.177
|
| 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 |
+
}
|