Model save
Browse files- README.md +60 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- runs/May15_02-45-37_gpu4-119-5/events.out.tfevents.1715705213.gpu4-119-5.2308029.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +926 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: DUAL-GPO/phi-2-gpo-new-i0
|
| 9 |
+
model-index:
|
| 10 |
+
- name: phi-2-gpo-v23-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-v23-i1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.7.1
|
| 57 |
+
- Transformers 4.36.2
|
| 58 |
+
- Pytorch 2.1.2+cu121
|
| 59 |
+
- Datasets 2.14.6
|
| 60 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167807296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e50648c5364f6838f44348a2ac013294ad2010141837118bbe4f7a8553f66df5
|
| 3 |
size 167807296
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.31719773806619866,
|
| 4 |
+
"train_runtime": 5988.5761,
|
| 5 |
+
"train_samples": 10200,
|
| 6 |
+
"train_samples_per_second": 1.703,
|
| 7 |
+
"train_steps_per_second": 0.106
|
| 8 |
+
}
|
runs/May15_02-45-37_gpu4-119-5/events.out.tfevents.1715705213.gpu4-119-5.2308029.0
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:fb481d1daf1a351169f5aab7380478fa1f414096076a715911929911f6c18ba1
|
| 3 |
+
size 45614
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.31719773806619866,
|
| 4 |
+
"train_runtime": 5988.5761,
|
| 5 |
+
"train_samples": 10200,
|
| 6 |
+
"train_samples_per_second": 1.703,
|
| 7 |
+
"train_steps_per_second": 0.106
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,926 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9992156862745099,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 637,
|
| 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": 7.8125e-08,
|
| 14 |
+
"logits/chosen": 0.0918828696012497,
|
| 15 |
+
"logits/rejected": 0.26330235600471497,
|
| 16 |
+
"logps/chosen": -458.63958740234375,
|
| 17 |
+
"logps/rejected": -388.8646240234375,
|
| 18 |
+
"loss": 0.4001,
|
| 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": 0.02,
|
| 27 |
+
"learning_rate": 7.8125e-07,
|
| 28 |
+
"logits/chosen": 0.07364361733198166,
|
| 29 |
+
"logits/rejected": 0.15213775634765625,
|
| 30 |
+
"logps/chosen": -318.695556640625,
|
| 31 |
+
"logps/rejected": -323.5196533203125,
|
| 32 |
+
"loss": 0.3624,
|
| 33 |
+
"rewards/accuracies": 0.4166666567325592,
|
| 34 |
+
"rewards/chosen": 5.298387259244919e-05,
|
| 35 |
+
"rewards/margins": -6.156884046504274e-05,
|
| 36 |
+
"rewards/rejected": 0.00011455271305749193,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03,
|
| 41 |
+
"learning_rate": 1.5625e-06,
|
| 42 |
+
"logits/chosen": 0.10303022712469101,
|
| 43 |
+
"logits/rejected": 0.1733068823814392,
|
| 44 |
+
"logps/chosen": -370.1763916015625,
|
| 45 |
+
"logps/rejected": -344.3110046386719,
|
| 46 |
+
"loss": 0.3763,
|
| 47 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 48 |
+
"rewards/chosen": -9.297926590079442e-05,
|
| 49 |
+
"rewards/margins": -0.00011266962246736512,
|
| 50 |
+
"rewards/rejected": 1.9690334738697857e-05,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 2.3437500000000002e-06,
|
| 56 |
+
"logits/chosen": 0.10951884090900421,
|
| 57 |
+
"logits/rejected": 0.171161487698555,
|
| 58 |
+
"logps/chosen": -374.95770263671875,
|
| 59 |
+
"logps/rejected": -342.6380615234375,
|
| 60 |
+
"loss": 0.3916,
|
| 61 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 62 |
+
"rewards/chosen": -2.8160246074548922e-05,
|
| 63 |
+
"rewards/margins": 1.7810778444982134e-05,
|
| 64 |
+
"rewards/rejected": -4.5971013605594635e-05,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 3.125e-06,
|
| 70 |
+
"logits/chosen": 0.1174466460943222,
|
| 71 |
+
"logits/rejected": 0.18849265575408936,
|
| 72 |
+
"logps/chosen": -321.7309875488281,
|
| 73 |
+
"logps/rejected": -292.35772705078125,
|
| 74 |
+
"loss": 0.363,
|
| 75 |
+
"rewards/accuracies": 0.53125,
|
| 76 |
+
"rewards/chosen": 0.00019040452025365084,
|
| 77 |
+
"rewards/margins": 0.00019320171850267798,
|
| 78 |
+
"rewards/rejected": -2.797205524984747e-06,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 3.90625e-06,
|
| 84 |
+
"logits/chosen": 0.19317670166492462,
|
| 85 |
+
"logits/rejected": 0.24143847823143005,
|
| 86 |
+
"logps/chosen": -354.2140808105469,
|
| 87 |
+
"logps/rejected": -362.29583740234375,
|
| 88 |
+
"loss": 0.3632,
|
| 89 |
+
"rewards/accuracies": 0.53125,
|
| 90 |
+
"rewards/chosen": 0.00048213909030891955,
|
| 91 |
+
"rewards/margins": 0.00036385521525517106,
|
| 92 |
+
"rewards/rejected": 0.00011828396236523986,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 98 |
+
"logits/chosen": 0.18060320615768433,
|
| 99 |
+
"logits/rejected": 0.22344954311847687,
|
| 100 |
+
"logps/chosen": -357.6122131347656,
|
| 101 |
+
"logps/rejected": -364.1398620605469,
|
| 102 |
+
"loss": 0.3805,
|
| 103 |
+
"rewards/accuracies": 0.637499988079071,
|
| 104 |
+
"rewards/chosen": 0.0008422869141213596,
|
| 105 |
+
"rewards/margins": 0.001053076470270753,
|
| 106 |
+
"rewards/rejected": -0.00021078942518215626,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11,
|
| 111 |
+
"learning_rate": 4.998647417232375e-06,
|
| 112 |
+
"logits/chosen": 0.08928748220205307,
|
| 113 |
+
"logits/rejected": 0.15246489644050598,
|
| 114 |
+
"logps/chosen": -318.8173522949219,
|
| 115 |
+
"logps/rejected": -304.9363708496094,
|
| 116 |
+
"loss": 0.356,
|
| 117 |
+
"rewards/accuracies": 0.612500011920929,
|
| 118 |
+
"rewards/chosen": 0.0005034763598814607,
|
| 119 |
+
"rewards/margins": 0.0022861119359731674,
|
| 120 |
+
"rewards/rejected": -0.0017826355760917068,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13,
|
| 125 |
+
"learning_rate": 4.990386933279973e-06,
|
| 126 |
+
"logits/chosen": 0.12598779797554016,
|
| 127 |
+
"logits/rejected": 0.20218820869922638,
|
| 128 |
+
"logps/chosen": -341.4804382324219,
|
| 129 |
+
"logps/rejected": -344.4537048339844,
|
| 130 |
+
"loss": 0.3596,
|
| 131 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 132 |
+
"rewards/chosen": -0.00020067775039933622,
|
| 133 |
+
"rewards/margins": 0.0030791102908551693,
|
| 134 |
+
"rewards/rejected": -0.003279787953943014,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"learning_rate": 4.974642195009681e-06,
|
| 140 |
+
"logits/chosen": 0.17095333337783813,
|
| 141 |
+
"logits/rejected": 0.2281300127506256,
|
| 142 |
+
"logps/chosen": -314.36920166015625,
|
| 143 |
+
"logps/rejected": -312.678466796875,
|
| 144 |
+
"loss": 0.369,
|
| 145 |
+
"rewards/accuracies": 0.625,
|
| 146 |
+
"rewards/chosen": -0.002451724372804165,
|
| 147 |
+
"rewards/margins": 0.004382356069982052,
|
| 148 |
+
"rewards/rejected": -0.006834079977124929,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.16,
|
| 153 |
+
"learning_rate": 4.951460519416228e-06,
|
| 154 |
+
"logits/chosen": 0.14624568819999695,
|
| 155 |
+
"logits/rejected": 0.19171926379203796,
|
| 156 |
+
"logps/chosen": -362.2412414550781,
|
| 157 |
+
"logps/rejected": -357.18170166015625,
|
| 158 |
+
"loss": 0.3748,
|
| 159 |
+
"rewards/accuracies": 0.625,
|
| 160 |
+
"rewards/chosen": -0.004997233394533396,
|
| 161 |
+
"rewards/margins": 0.008778322488069534,
|
| 162 |
+
"rewards/rejected": -0.013775557279586792,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.17,
|
| 167 |
+
"learning_rate": 4.920911573406925e-06,
|
| 168 |
+
"logits/chosen": 0.0949273556470871,
|
| 169 |
+
"logits/rejected": 0.15069428086280823,
|
| 170 |
+
"logps/chosen": -337.5642395019531,
|
| 171 |
+
"logps/rejected": -346.2424621582031,
|
| 172 |
+
"loss": 0.3603,
|
| 173 |
+
"rewards/accuracies": 0.668749988079071,
|
| 174 |
+
"rewards/chosen": -0.006651742849498987,
|
| 175 |
+
"rewards/margins": 0.01205554511398077,
|
| 176 |
+
"rewards/rejected": -0.018707286566495895,
|
| 177 |
+
"step": 110
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19,
|
| 181 |
+
"learning_rate": 4.883087164434672e-06,
|
| 182 |
+
"logits/chosen": 0.08049245178699493,
|
| 183 |
+
"logits/rejected": 0.17421886324882507,
|
| 184 |
+
"logps/chosen": -359.105224609375,
|
| 185 |
+
"logps/rejected": -364.32904052734375,
|
| 186 |
+
"loss": 0.358,
|
| 187 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 188 |
+
"rewards/chosen": -0.013828782364726067,
|
| 189 |
+
"rewards/margins": 0.016524765640497208,
|
| 190 |
+
"rewards/rejected": -0.030353549867868423,
|
| 191 |
+
"step": 120
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2,
|
| 195 |
+
"learning_rate": 4.8381009645929044e-06,
|
| 196 |
+
"logits/chosen": 0.117076575756073,
|
| 197 |
+
"logits/rejected": 0.1626085489988327,
|
| 198 |
+
"logps/chosen": -359.46728515625,
|
| 199 |
+
"logps/rejected": -418.33868408203125,
|
| 200 |
+
"loss": 0.3424,
|
| 201 |
+
"rewards/accuracies": 0.625,
|
| 202 |
+
"rewards/chosen": -0.03268348425626755,
|
| 203 |
+
"rewards/margins": 0.038762401789426804,
|
| 204 |
+
"rewards/rejected": -0.07144588232040405,
|
| 205 |
+
"step": 130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.22,
|
| 209 |
+
"learning_rate": 4.786088169001671e-06,
|
| 210 |
+
"logits/chosen": 0.12248921394348145,
|
| 211 |
+
"logits/rejected": 0.203883558511734,
|
| 212 |
+
"logps/chosen": -427.392333984375,
|
| 213 |
+
"logps/rejected": -504.49908447265625,
|
| 214 |
+
"loss": 0.3317,
|
| 215 |
+
"rewards/accuracies": 0.65625,
|
| 216 |
+
"rewards/chosen": -0.11223888397216797,
|
| 217 |
+
"rewards/margins": 0.05915551260113716,
|
| 218 |
+
"rewards/rejected": -0.17139439284801483,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.24,
|
| 223 |
+
"learning_rate": 4.727205089511466e-06,
|
| 224 |
+
"logits/chosen": 0.08418472111225128,
|
| 225 |
+
"logits/rejected": 0.21436505019664764,
|
| 226 |
+
"logps/chosen": -579.9471435546875,
|
| 227 |
+
"logps/rejected": -638.8032836914062,
|
| 228 |
+
"loss": 0.3334,
|
| 229 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 230 |
+
"rewards/chosen": -0.20061063766479492,
|
| 231 |
+
"rewards/margins": 0.07825453579425812,
|
| 232 |
+
"rewards/rejected": -0.27886515855789185,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.25,
|
| 237 |
+
"learning_rate": 4.661628684945851e-06,
|
| 238 |
+
"logits/chosen": 0.13719815015792847,
|
| 239 |
+
"logits/rejected": 0.22896163165569305,
|
| 240 |
+
"logps/chosen": -483.87744140625,
|
| 241 |
+
"logps/rejected": -555.54931640625,
|
| 242 |
+
"loss": 0.3506,
|
| 243 |
+
"rewards/accuracies": 0.574999988079071,
|
| 244 |
+
"rewards/chosen": -0.1468028724193573,
|
| 245 |
+
"rewards/margins": 0.06705925613641739,
|
| 246 |
+
"rewards/rejected": -0.21386213600635529,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.27,
|
| 251 |
+
"learning_rate": 4.5895560292946e-06,
|
| 252 |
+
"logits/chosen": 0.15668627619743347,
|
| 253 |
+
"logits/rejected": 0.24040012061595917,
|
| 254 |
+
"logps/chosen": -489.44195556640625,
|
| 255 |
+
"logps/rejected": -503.8895568847656,
|
| 256 |
+
"loss": 0.3035,
|
| 257 |
+
"rewards/accuracies": 0.643750011920929,
|
| 258 |
+
"rewards/chosen": -0.11202345043420792,
|
| 259 |
+
"rewards/margins": 0.060164742171764374,
|
| 260 |
+
"rewards/rejected": -0.1721881926059723,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.28,
|
| 265 |
+
"learning_rate": 4.511203719455588e-06,
|
| 266 |
+
"logits/chosen": 0.1728764772415161,
|
| 267 |
+
"logits/rejected": 0.21227356791496277,
|
| 268 |
+
"logps/chosen": -434.38555908203125,
|
| 269 |
+
"logps/rejected": -474.145263671875,
|
| 270 |
+
"loss": 0.3136,
|
| 271 |
+
"rewards/accuracies": 0.637499988079071,
|
| 272 |
+
"rewards/chosen": -0.10123687982559204,
|
| 273 |
+
"rewards/margins": 0.06594525277614594,
|
| 274 |
+
"rewards/rejected": -0.16718213260173798,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3,
|
| 279 |
+
"learning_rate": 4.426807224305315e-06,
|
| 280 |
+
"logits/chosen": 0.1319476068019867,
|
| 281 |
+
"logits/rejected": 0.2203722447156906,
|
| 282 |
+
"logps/chosen": -476.09088134765625,
|
| 283 |
+
"logps/rejected": -508.6603088378906,
|
| 284 |
+
"loss": 0.3452,
|
| 285 |
+
"rewards/accuracies": 0.643750011920929,
|
| 286 |
+
"rewards/chosen": -0.1248413696885109,
|
| 287 |
+
"rewards/margins": 0.052263855934143066,
|
| 288 |
+
"rewards/rejected": -0.17710521817207336,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.31,
|
| 293 |
+
"learning_rate": 4.336620177054269e-06,
|
| 294 |
+
"logits/chosen": 0.1470222920179367,
|
| 295 |
+
"logits/rejected": 0.2037900686264038,
|
| 296 |
+
"logps/chosen": -433.387939453125,
|
| 297 |
+
"logps/rejected": -526.0863037109375,
|
| 298 |
+
"loss": 0.3211,
|
| 299 |
+
"rewards/accuracies": 0.65625,
|
| 300 |
+
"rewards/chosen": -0.10074210166931152,
|
| 301 |
+
"rewards/margins": 0.07372565567493439,
|
| 302 |
+
"rewards/rejected": -0.1744677573442459,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.33,
|
| 307 |
+
"learning_rate": 4.240913613013785e-06,
|
| 308 |
+
"logits/chosen": 0.13598838448524475,
|
| 309 |
+
"logits/rejected": 0.24791710078716278,
|
| 310 |
+
"logps/chosen": -504.983642578125,
|
| 311 |
+
"logps/rejected": -547.6514282226562,
|
| 312 |
+
"loss": 0.3223,
|
| 313 |
+
"rewards/accuracies": 0.59375,
|
| 314 |
+
"rewards/chosen": -0.13141490519046783,
|
| 315 |
+
"rewards/margins": 0.06105287745594978,
|
| 316 |
+
"rewards/rejected": -0.19246776401996613,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.35,
|
| 321 |
+
"learning_rate": 4.139975155065109e-06,
|
| 322 |
+
"logits/chosen": 0.10929516702890396,
|
| 323 |
+
"logits/rejected": 0.2205590009689331,
|
| 324 |
+
"logps/chosen": -466.38543701171875,
|
| 325 |
+
"logps/rejected": -554.4016723632812,
|
| 326 |
+
"loss": 0.3052,
|
| 327 |
+
"rewards/accuracies": 0.637499988079071,
|
| 328 |
+
"rewards/chosen": -0.1270093470811844,
|
| 329 |
+
"rewards/margins": 0.08514191210269928,
|
| 330 |
+
"rewards/rejected": -0.21215125918388367,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.36,
|
| 335 |
+
"learning_rate": 4.034108149278544e-06,
|
| 336 |
+
"logits/chosen": 0.12504920363426208,
|
| 337 |
+
"logits/rejected": 0.20017783343791962,
|
| 338 |
+
"logps/chosen": -500.18218994140625,
|
| 339 |
+
"logps/rejected": -552.7307739257812,
|
| 340 |
+
"loss": 0.2987,
|
| 341 |
+
"rewards/accuracies": 0.675000011920929,
|
| 342 |
+
"rewards/chosen": -0.13430464267730713,
|
| 343 |
+
"rewards/margins": 0.07368321716785431,
|
| 344 |
+
"rewards/rejected": -0.20798785984516144,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.38,
|
| 349 |
+
"learning_rate": 3.923630753280358e-06,
|
| 350 |
+
"logits/chosen": 0.14272692799568176,
|
| 351 |
+
"logits/rejected": 0.20935645699501038,
|
| 352 |
+
"logps/chosen": -516.2708740234375,
|
| 353 |
+
"logps/rejected": -599.9803466796875,
|
| 354 |
+
"loss": 0.2931,
|
| 355 |
+
"rewards/accuracies": 0.675000011920929,
|
| 356 |
+
"rewards/chosen": -0.138849675655365,
|
| 357 |
+
"rewards/margins": 0.1058221235871315,
|
| 358 |
+
"rewards/rejected": -0.2446717917919159,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.39,
|
| 363 |
+
"learning_rate": 3.80887498010715e-06,
|
| 364 |
+
"logits/chosen": 0.20914337038993835,
|
| 365 |
+
"logits/rejected": 0.22870346903800964,
|
| 366 |
+
"logps/chosen": -463.67340087890625,
|
| 367 |
+
"logps/rejected": -534.5090942382812,
|
| 368 |
+
"loss": 0.3168,
|
| 369 |
+
"rewards/accuracies": 0.612500011920929,
|
| 370 |
+
"rewards/chosen": -0.1403440535068512,
|
| 371 |
+
"rewards/margins": 0.06889508664608002,
|
| 372 |
+
"rewards/rejected": -0.20923912525177002,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.41,
|
| 377 |
+
"learning_rate": 3.690185700421145e-06,
|
| 378 |
+
"logits/chosen": 0.17314383387565613,
|
| 379 |
+
"logits/rejected": 0.2541898787021637,
|
| 380 |
+
"logps/chosen": -500.0283203125,
|
| 381 |
+
"logps/rejected": -567.5086059570312,
|
| 382 |
+
"loss": 0.3046,
|
| 383 |
+
"rewards/accuracies": 0.706250011920929,
|
| 384 |
+
"rewards/chosen": -0.12471531331539154,
|
| 385 |
+
"rewards/margins": 0.11497502028942108,
|
| 386 |
+
"rewards/rejected": -0.23969034850597382,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.42,
|
| 391 |
+
"learning_rate": 3.567919606085004e-06,
|
| 392 |
+
"logits/chosen": 0.18270955979824066,
|
| 393 |
+
"logits/rejected": 0.24541044235229492,
|
| 394 |
+
"logps/chosen": -524.0221557617188,
|
| 395 |
+
"logps/rejected": -606.4444580078125,
|
| 396 |
+
"loss": 0.3055,
|
| 397 |
+
"rewards/accuracies": 0.668749988079071,
|
| 398 |
+
"rewards/chosen": -0.13682256639003754,
|
| 399 |
+
"rewards/margins": 0.10733524709939957,
|
| 400 |
+
"rewards/rejected": -0.2441578209400177,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.44,
|
| 405 |
+
"learning_rate": 3.442444138210883e-06,
|
| 406 |
+
"logits/chosen": 0.19482332468032837,
|
| 407 |
+
"logits/rejected": 0.29221558570861816,
|
| 408 |
+
"logps/chosen": -545.2671508789062,
|
| 409 |
+
"logps/rejected": -661.770263671875,
|
| 410 |
+
"loss": 0.2962,
|
| 411 |
+
"rewards/accuracies": 0.706250011920929,
|
| 412 |
+
"rewards/chosen": -0.15382714569568634,
|
| 413 |
+
"rewards/margins": 0.1256464123725891,
|
| 414 |
+
"rewards/rejected": -0.27947354316711426,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.45,
|
| 419 |
+
"learning_rate": 3.314136382905234e-06,
|
| 420 |
+
"logits/chosen": 0.2596381902694702,
|
| 421 |
+
"logits/rejected": 0.29522743821144104,
|
| 422 |
+
"logps/chosen": -531.8798217773438,
|
| 423 |
+
"logps/rejected": -688.622802734375,
|
| 424 |
+
"loss": 0.2707,
|
| 425 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 426 |
+
"rewards/chosen": -0.17996947467327118,
|
| 427 |
+
"rewards/margins": 0.1445850431919098,
|
| 428 |
+
"rewards/rejected": -0.3245545029640198,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.47,
|
| 433 |
+
"learning_rate": 3.1833819380279028e-06,
|
| 434 |
+
"logits/chosen": 0.30931779742240906,
|
| 435 |
+
"logits/rejected": 0.2789193391799927,
|
| 436 |
+
"logps/chosen": -576.7262573242188,
|
| 437 |
+
"logps/rejected": -676.7431640625,
|
| 438 |
+
"loss": 0.3178,
|
| 439 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 440 |
+
"rewards/chosen": -0.2274230420589447,
|
| 441 |
+
"rewards/margins": 0.11135544627904892,
|
| 442 |
+
"rewards/rejected": -0.3387784957885742,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.49,
|
| 447 |
+
"learning_rate": 3.050573754371228e-06,
|
| 448 |
+
"logits/chosen": 0.20585477352142334,
|
| 449 |
+
"logits/rejected": 0.25459426641464233,
|
| 450 |
+
"logps/chosen": -536.5878295898438,
|
| 451 |
+
"logps/rejected": -603.1542358398438,
|
| 452 |
+
"loss": 0.3075,
|
| 453 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 454 |
+
"rewards/chosen": -0.21307428181171417,
|
| 455 |
+
"rewards/margins": 0.07962417602539062,
|
| 456 |
+
"rewards/rejected": -0.2926984429359436,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5,
|
| 461 |
+
"learning_rate": 2.916110954741667e-06,
|
| 462 |
+
"logits/chosen": 0.19497337937355042,
|
| 463 |
+
"logits/rejected": 0.39090901613235474,
|
| 464 |
+
"logps/chosen": -572.049560546875,
|
| 465 |
+
"logps/rejected": -697.1812133789062,
|
| 466 |
+
"loss": 0.2871,
|
| 467 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 468 |
+
"rewards/chosen": -0.2017597258090973,
|
| 469 |
+
"rewards/margins": 0.134249746799469,
|
| 470 |
+
"rewards/rejected": -0.3360094726085663,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.52,
|
| 475 |
+
"learning_rate": 2.7803976344929497e-06,
|
| 476 |
+
"logits/chosen": 0.16042862832546234,
|
| 477 |
+
"logits/rejected": 0.262906551361084,
|
| 478 |
+
"logps/chosen": -574.7508544921875,
|
| 479 |
+
"logps/rejected": -686.5535888671875,
|
| 480 |
+
"loss": 0.3012,
|
| 481 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 482 |
+
"rewards/chosen": -0.20231370627880096,
|
| 483 |
+
"rewards/margins": 0.13932286202907562,
|
| 484 |
+
"rewards/rejected": -0.3416365683078766,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.53,
|
| 489 |
+
"learning_rate": 2.6438416471154277e-06,
|
| 490 |
+
"logits/chosen": 0.23894529044628143,
|
| 491 |
+
"logits/rejected": 0.24849145114421844,
|
| 492 |
+
"logps/chosen": -529.4860229492188,
|
| 493 |
+
"logps/rejected": -650.188232421875,
|
| 494 |
+
"loss": 0.2966,
|
| 495 |
+
"rewards/accuracies": 0.643750011920929,
|
| 496 |
+
"rewards/chosen": -0.20321831107139587,
|
| 497 |
+
"rewards/margins": 0.11060591042041779,
|
| 498 |
+
"rewards/rejected": -0.31382423639297485,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.55,
|
| 503 |
+
"learning_rate": 2.5068533785312673e-06,
|
| 504 |
+
"logits/chosen": 0.16733770072460175,
|
| 505 |
+
"logits/rejected": 0.24236424267292023,
|
| 506 |
+
"logps/chosen": -526.2505493164062,
|
| 507 |
+
"logps/rejected": -613.4932861328125,
|
| 508 |
+
"loss": 0.2909,
|
| 509 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 510 |
+
"rewards/chosen": -0.2088821828365326,
|
| 511 |
+
"rewards/margins": 0.10516791045665741,
|
| 512 |
+
"rewards/rejected": -0.3140501081943512,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.56,
|
| 517 |
+
"learning_rate": 2.369844513779026e-06,
|
| 518 |
+
"logits/chosen": 0.16742342710494995,
|
| 519 |
+
"logits/rejected": 0.2210749387741089,
|
| 520 |
+
"logps/chosen": -558.5418701171875,
|
| 521 |
+
"logps/rejected": -629.0260620117188,
|
| 522 |
+
"loss": 0.3169,
|
| 523 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 524 |
+
"rewards/chosen": -0.20471343398094177,
|
| 525 |
+
"rewards/margins": 0.09914077073335648,
|
| 526 |
+
"rewards/rejected": -0.30385422706604004,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.58,
|
| 531 |
+
"learning_rate": 2.2332267997940514e-06,
|
| 532 |
+
"logits/chosen": 0.2225278615951538,
|
| 533 |
+
"logits/rejected": 0.25043898820877075,
|
| 534 |
+
"logps/chosen": -623.16748046875,
|
| 535 |
+
"logps/rejected": -674.67724609375,
|
| 536 |
+
"loss": 0.3545,
|
| 537 |
+
"rewards/accuracies": 0.643750011920929,
|
| 538 |
+
"rewards/chosen": -0.24807922542095184,
|
| 539 |
+
"rewards/margins": 0.08578108996152878,
|
| 540 |
+
"rewards/rejected": -0.3338603377342224,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6,
|
| 545 |
+
"learning_rate": 2.097410808002869e-06,
|
| 546 |
+
"logits/chosen": 0.17123399674892426,
|
| 547 |
+
"logits/rejected": 0.24292032420635223,
|
| 548 |
+
"logps/chosen": -598.9353637695312,
|
| 549 |
+
"logps/rejected": -703.7257080078125,
|
| 550 |
+
"loss": 0.2788,
|
| 551 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 552 |
+
"rewards/chosen": -0.20804348587989807,
|
| 553 |
+
"rewards/margins": 0.1404215544462204,
|
| 554 |
+
"rewards/rejected": -0.3484650254249573,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.61,
|
| 559 |
+
"learning_rate": 1.962804700450265e-06,
|
| 560 |
+
"logits/chosen": 0.13856971263885498,
|
| 561 |
+
"logits/rejected": 0.204025536775589,
|
| 562 |
+
"logps/chosen": -580.52197265625,
|
| 563 |
+
"logps/rejected": -670.6529541015625,
|
| 564 |
+
"loss": 0.2891,
|
| 565 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 566 |
+
"rewards/chosen": -0.22241008281707764,
|
| 567 |
+
"rewards/margins": 0.10534980148077011,
|
| 568 |
+
"rewards/rejected": -0.32775989174842834,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.63,
|
| 573 |
+
"learning_rate": 1.8298130031671974e-06,
|
| 574 |
+
"logits/chosen": 0.15039893984794617,
|
| 575 |
+
"logits/rejected": 0.18419519066810608,
|
| 576 |
+
"logps/chosen": -529.6956787109375,
|
| 577 |
+
"logps/rejected": -624.8928833007812,
|
| 578 |
+
"loss": 0.2796,
|
| 579 |
+
"rewards/accuracies": 0.675000011920929,
|
| 580 |
+
"rewards/chosen": -0.1940956562757492,
|
| 581 |
+
"rewards/margins": 0.1203426718711853,
|
| 582 |
+
"rewards/rejected": -0.3144383430480957,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.64,
|
| 587 |
+
"learning_rate": 1.6988353904658495e-06,
|
| 588 |
+
"logits/chosen": 0.17148879170417786,
|
| 589 |
+
"logits/rejected": 0.24635398387908936,
|
| 590 |
+
"logps/chosen": -560.6425170898438,
|
| 591 |
+
"logps/rejected": -683.8626098632812,
|
| 592 |
+
"loss": 0.2732,
|
| 593 |
+
"rewards/accuracies": 0.6875,
|
| 594 |
+
"rewards/chosen": -0.2084239274263382,
|
| 595 |
+
"rewards/margins": 0.1307951807975769,
|
| 596 |
+
"rewards/rejected": -0.33921903371810913,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.66,
|
| 601 |
+
"learning_rate": 1.5702654838153641e-06,
|
| 602 |
+
"logits/chosen": 0.13374552130699158,
|
| 603 |
+
"logits/rejected": 0.21898336708545685,
|
| 604 |
+
"logps/chosen": -533.1779174804688,
|
| 605 |
+
"logps/rejected": -647.463134765625,
|
| 606 |
+
"loss": 0.2948,
|
| 607 |
+
"rewards/accuracies": 0.668749988079071,
|
| 608 |
+
"rewards/chosen": -0.1993607133626938,
|
| 609 |
+
"rewards/margins": 0.10736644268035889,
|
| 610 |
+
"rewards/rejected": -0.30672717094421387,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.67,
|
| 615 |
+
"learning_rate": 1.4444896689079142e-06,
|
| 616 |
+
"logits/chosen": 0.2023026943206787,
|
| 617 |
+
"logits/rejected": 0.2337256669998169,
|
| 618 |
+
"logps/chosen": -578.2020874023438,
|
| 619 |
+
"logps/rejected": -652.1826171875,
|
| 620 |
+
"loss": 0.3217,
|
| 621 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 622 |
+
"rewards/chosen": -0.21291308104991913,
|
| 623 |
+
"rewards/margins": 0.093999482691288,
|
| 624 |
+
"rewards/rejected": -0.30691254138946533,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.69,
|
| 629 |
+
"learning_rate": 1.3218859344701634e-06,
|
| 630 |
+
"logits/chosen": 0.10349559783935547,
|
| 631 |
+
"logits/rejected": 0.16690309345722198,
|
| 632 |
+
"logps/chosen": -569.8800048828125,
|
| 633 |
+
"logps/rejected": -680.734619140625,
|
| 634 |
+
"loss": 0.2608,
|
| 635 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 636 |
+
"rewards/chosen": -0.20618288218975067,
|
| 637 |
+
"rewards/margins": 0.1448386162519455,
|
| 638 |
+
"rewards/rejected": -0.3510214686393738,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.71,
|
| 643 |
+
"learning_rate": 1.2028227363097583e-06,
|
| 644 |
+
"logits/chosen": 0.13843318819999695,
|
| 645 |
+
"logits/rejected": 0.18968960642814636,
|
| 646 |
+
"logps/chosen": -550.9771728515625,
|
| 647 |
+
"logps/rejected": -633.4754638671875,
|
| 648 |
+
"loss": 0.3117,
|
| 649 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 650 |
+
"rewards/chosen": -0.21659895777702332,
|
| 651 |
+
"rewards/margins": 0.11474967002868652,
|
| 652 |
+
"rewards/rejected": -0.33134859800338745,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.72,
|
| 657 |
+
"learning_rate": 1.0876578900107053e-06,
|
| 658 |
+
"logits/chosen": 0.17231318354606628,
|
| 659 |
+
"logits/rejected": 0.17545001208782196,
|
| 660 |
+
"logps/chosen": -558.6343994140625,
|
| 661 |
+
"logps/rejected": -641.2686767578125,
|
| 662 |
+
"loss": 0.2869,
|
| 663 |
+
"rewards/accuracies": 0.606249988079071,
|
| 664 |
+
"rewards/chosen": -0.21609997749328613,
|
| 665 |
+
"rewards/margins": 0.10281254351139069,
|
| 666 |
+
"rewards/rejected": -0.3189125061035156,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.74,
|
| 671 |
+
"learning_rate": 9.767374956053584e-07,
|
| 672 |
+
"logits/chosen": 0.20297455787658691,
|
| 673 |
+
"logits/rejected": 0.27692240476608276,
|
| 674 |
+
"logps/chosen": -603.3773803710938,
|
| 675 |
+
"logps/rejected": -657.2963256835938,
|
| 676 |
+
"loss": 0.3629,
|
| 677 |
+
"rewards/accuracies": 0.59375,
|
| 678 |
+
"rewards/chosen": -0.24698205292224884,
|
| 679 |
+
"rewards/margins": 0.058980755507946014,
|
| 680 |
+
"rewards/rejected": -0.30596280097961426,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.75,
|
| 685 |
+
"learning_rate": 8.703948974546592e-07,
|
| 686 |
+
"logits/chosen": 0.17270350456237793,
|
| 687 |
+
"logits/rejected": 0.20394925773143768,
|
| 688 |
+
"logps/chosen": -522.0367431640625,
|
| 689 |
+
"logps/rejected": -605.554443359375,
|
| 690 |
+
"loss": 0.3139,
|
| 691 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 692 |
+
"rewards/chosen": -0.20573575794696808,
|
| 693 |
+
"rewards/margins": 0.10728572309017181,
|
| 694 |
+
"rewards/rejected": -0.3130214810371399,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.77,
|
| 699 |
+
"learning_rate": 7.689496824624526e-07,
|
| 700 |
+
"logits/chosen": 0.13458377122879028,
|
| 701 |
+
"logits/rejected": 0.19917598366737366,
|
| 702 |
+
"logps/chosen": -544.7473754882812,
|
| 703 |
+
"logps/rejected": -663.064208984375,
|
| 704 |
+
"loss": 0.2822,
|
| 705 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 706 |
+
"rewards/chosen": -0.21486207842826843,
|
| 707 |
+
"rewards/margins": 0.11823858320713043,
|
| 708 |
+
"rewards/rejected": -0.3331006169319153,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.78,
|
| 713 |
+
"learning_rate": 6.7270671963451e-07,
|
| 714 |
+
"logits/chosen": 0.11218737065792084,
|
| 715 |
+
"logits/rejected": 0.21531948447227478,
|
| 716 |
+
"logps/chosen": -529.8823852539062,
|
| 717 |
+
"logps/rejected": -646.2406005859375,
|
| 718 |
+
"loss": 0.2889,
|
| 719 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 720 |
+
"rewards/chosen": -0.202474907040596,
|
| 721 |
+
"rewards/margins": 0.11822378635406494,
|
| 722 |
+
"rewards/rejected": -0.32069867849349976,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.8,
|
| 727 |
+
"learning_rate": 5.819552438686238e-07,
|
| 728 |
+
"logits/chosen": 0.14948822557926178,
|
| 729 |
+
"logits/rejected": 0.17894427478313446,
|
| 730 |
+
"logps/chosen": -545.9841918945312,
|
| 731 |
+
"logps/rejected": -637.9070434570312,
|
| 732 |
+
"loss": 0.3393,
|
| 733 |
+
"rewards/accuracies": 0.643750011920929,
|
| 734 |
+
"rewards/chosen": -0.2308504283428192,
|
| 735 |
+
"rewards/margins": 0.08178289234638214,
|
| 736 |
+
"rewards/rejected": -0.31263333559036255,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.82,
|
| 741 |
+
"learning_rate": 4.969679867292276e-07,
|
| 742 |
+
"logits/chosen": 0.15977367758750916,
|
| 743 |
+
"logits/rejected": 0.14595797657966614,
|
| 744 |
+
"logps/chosen": -558.384521484375,
|
| 745 |
+
"logps/rejected": -640.0645751953125,
|
| 746 |
+
"loss": 0.3019,
|
| 747 |
+
"rewards/accuracies": 0.65625,
|
| 748 |
+
"rewards/chosen": -0.23137719929218292,
|
| 749 |
+
"rewards/margins": 0.09733609855175018,
|
| 750 |
+
"rewards/rejected": -0.3287132680416107,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.83,
|
| 755 |
+
"learning_rate": 4.1800035681877765e-07,
|
| 756 |
+
"logits/chosen": 0.1737111657857895,
|
| 757 |
+
"logits/rejected": 0.2044694423675537,
|
| 758 |
+
"logps/chosen": -557.0775146484375,
|
| 759 |
+
"logps/rejected": -703.0406494140625,
|
| 760 |
+
"loss": 0.2799,
|
| 761 |
+
"rewards/accuracies": 0.699999988079071,
|
| 762 |
+
"rewards/chosen": -0.21399672329425812,
|
| 763 |
+
"rewards/margins": 0.1301182061433792,
|
| 764 |
+
"rewards/rejected": -0.34411489963531494,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.85,
|
| 769 |
+
"learning_rate": 3.4528967220911287e-07,
|
| 770 |
+
"logits/chosen": 0.11454256623983383,
|
| 771 |
+
"logits/rejected": 0.22100505232810974,
|
| 772 |
+
"logps/chosen": -569.0726318359375,
|
| 773 |
+
"logps/rejected": -655.3294677734375,
|
| 774 |
+
"loss": 0.3021,
|
| 775 |
+
"rewards/accuracies": 0.706250011920929,
|
| 776 |
+
"rewards/chosen": -0.21696233749389648,
|
| 777 |
+
"rewards/margins": 0.10485026985406876,
|
| 778 |
+
"rewards/rejected": -0.32181257009506226,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.86,
|
| 783 |
+
"learning_rate": 2.7905444723949765e-07,
|
| 784 |
+
"logits/chosen": 0.08618897199630737,
|
| 785 |
+
"logits/rejected": 0.19658343493938446,
|
| 786 |
+
"logps/chosen": -588.386962890625,
|
| 787 |
+
"logps/rejected": -682.5491333007812,
|
| 788 |
+
"loss": 0.2921,
|
| 789 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 790 |
+
"rewards/chosen": -0.22489456832408905,
|
| 791 |
+
"rewards/margins": 0.09568282216787338,
|
| 792 |
+
"rewards/rejected": -0.3205774426460266,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.88,
|
| 797 |
+
"learning_rate": 2.1949373582475065e-07,
|
| 798 |
+
"logits/chosen": 0.17197827994823456,
|
| 799 |
+
"logits/rejected": 0.24235980212688446,
|
| 800 |
+
"logps/chosen": -550.1292724609375,
|
| 801 |
+
"logps/rejected": -628.2039794921875,
|
| 802 |
+
"loss": 0.3376,
|
| 803 |
+
"rewards/accuracies": 0.625,
|
| 804 |
+
"rewards/chosen": -0.22096483409404755,
|
| 805 |
+
"rewards/margins": 0.08723219484090805,
|
| 806 |
+
"rewards/rejected": -0.3081970512866974,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.89,
|
| 811 |
+
"learning_rate": 1.667865332469379e-07,
|
| 812 |
+
"logits/chosen": 0.1541893035173416,
|
| 813 |
+
"logits/rejected": 0.2220904380083084,
|
| 814 |
+
"logps/chosen": -562.9713745117188,
|
| 815 |
+
"logps/rejected": -657.7110595703125,
|
| 816 |
+
"loss": 0.2415,
|
| 817 |
+
"rewards/accuracies": 0.75,
|
| 818 |
+
"rewards/chosen": -0.1808656007051468,
|
| 819 |
+
"rewards/margins": 0.13864107429981232,
|
| 820 |
+
"rewards/rejected": -0.3195067048072815,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.91,
|
| 825 |
+
"learning_rate": 1.2109123822844653e-07,
|
| 826 |
+
"logits/chosen": 0.16481325030326843,
|
| 827 |
+
"logits/rejected": 0.20911450684070587,
|
| 828 |
+
"logps/chosen": -529.6812744140625,
|
| 829 |
+
"logps/rejected": -672.5157470703125,
|
| 830 |
+
"loss": 0.3085,
|
| 831 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 832 |
+
"rewards/chosen": -0.21774494647979736,
|
| 833 |
+
"rewards/margins": 0.11994588375091553,
|
| 834 |
+
"rewards/rejected": -0.3376908600330353,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.93,
|
| 839 |
+
"learning_rate": 8.254517690300946e-08,
|
| 840 |
+
"logits/chosen": 0.12228590250015259,
|
| 841 |
+
"logits/rejected": 0.19594553112983704,
|
| 842 |
+
"logps/chosen": -565.060546875,
|
| 843 |
+
"logps/rejected": -686.70947265625,
|
| 844 |
+
"loss": 0.2775,
|
| 845 |
+
"rewards/accuracies": 0.71875,
|
| 846 |
+
"rewards/chosen": -0.20458519458770752,
|
| 847 |
+
"rewards/margins": 0.12763497233390808,
|
| 848 |
+
"rewards/rejected": -0.3322201371192932,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.94,
|
| 853 |
+
"learning_rate": 5.126419011529993e-08,
|
| 854 |
+
"logits/chosen": 0.1007891520857811,
|
| 855 |
+
"logits/rejected": 0.23624570667743683,
|
| 856 |
+
"logps/chosen": -578.2725830078125,
|
| 857 |
+
"logps/rejected": -646.430908203125,
|
| 858 |
+
"loss": 0.2885,
|
| 859 |
+
"rewards/accuracies": 0.675000011920929,
|
| 860 |
+
"rewards/chosen": -0.20723719894886017,
|
| 861 |
+
"rewards/margins": 0.1008644700050354,
|
| 862 |
+
"rewards/rejected": -0.3081016540527344,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.96,
|
| 867 |
+
"learning_rate": 2.734228528934679e-08,
|
| 868 |
+
"logits/chosen": 0.1077275276184082,
|
| 869 |
+
"logits/rejected": 0.18885311484336853,
|
| 870 |
+
"logps/chosen": -591.439208984375,
|
| 871 |
+
"logps/rejected": -687.6322021484375,
|
| 872 |
+
"loss": 0.2913,
|
| 873 |
+
"rewards/accuracies": 0.706250011920929,
|
| 874 |
+
"rewards/chosen": -0.23343046009540558,
|
| 875 |
+
"rewards/margins": 0.11967509984970093,
|
| 876 |
+
"rewards/rejected": -0.3531055748462677,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.97,
|
| 881 |
+
"learning_rate": 1.0851353912008644e-08,
|
| 882 |
+
"logits/chosen": 0.1404169648885727,
|
| 883 |
+
"logits/rejected": 0.17623500525951385,
|
| 884 |
+
"logps/chosen": -562.1318969726562,
|
| 885 |
+
"logps/rejected": -675.3463134765625,
|
| 886 |
+
"loss": 0.3244,
|
| 887 |
+
"rewards/accuracies": 0.668749988079071,
|
| 888 |
+
"rewards/chosen": -0.22516414523124695,
|
| 889 |
+
"rewards/margins": 0.1208973079919815,
|
| 890 |
+
"rewards/rejected": -0.3460614085197449,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.99,
|
| 895 |
+
"learning_rate": 1.8409554805329243e-09,
|
| 896 |
+
"logits/chosen": 0.18373514711856842,
|
| 897 |
+
"logits/rejected": 0.21246370673179626,
|
| 898 |
+
"logps/chosen": -578.3257446289062,
|
| 899 |
+
"logps/rejected": -651.350830078125,
|
| 900 |
+
"loss": 0.3169,
|
| 901 |
+
"rewards/accuracies": 0.643750011920929,
|
| 902 |
+
"rewards/chosen": -0.22300894558429718,
|
| 903 |
+
"rewards/margins": 0.09293990582227707,
|
| 904 |
+
"rewards/rejected": -0.31594881415367126,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.0,
|
| 909 |
+
"step": 637,
|
| 910 |
+
"total_flos": 0.0,
|
| 911 |
+
"train_loss": 0.31719773806619866,
|
| 912 |
+
"train_runtime": 5988.5761,
|
| 913 |
+
"train_samples_per_second": 1.703,
|
| 914 |
+
"train_steps_per_second": 0.106
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"logging_steps": 10,
|
| 918 |
+
"max_steps": 637,
|
| 919 |
+
"num_input_tokens_seen": 0,
|
| 920 |
+
"num_train_epochs": 1,
|
| 921 |
+
"save_steps": 100,
|
| 922 |
+
"total_flos": 0.0,
|
| 923 |
+
"train_batch_size": 4,
|
| 924 |
+
"trial_name": null,
|
| 925 |
+
"trial_params": null
|
| 926 |
+
}
|