Model save

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: TomGrc/FusionNet_7Bx2_MoE_v0.1
+model-index:
+- name: stealth-finance-v2-dpo-adapter
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# stealth-finance-v2-dpo-adapter
+
+This model is a fine-tuned version of [TomGrc/FusionNet_7Bx2_MoE_v0.1](https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1290
+- Rewards/chosen: -0.1799
+- Rewards/rejected: -6.0696
+- Rewards/accuracies: 0.8597
+- Rewards/margins: 5.8897
+- Logps/rejected: -324.0384
+- Logps/chosen: -275.3572
+- Logits/rejected: -0.7749
+- Logits/chosen: -0.7773
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.3593        | 1.0   | 3280 | 0.1290          | -0.1799        | -6.0696          | 0.8597             | 5.8897          | -324.0384      | -275.3572    | -0.7749         | -0.7773       |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.7773212790489197,
+    "eval_logits/rejected": -0.7749085426330566,
+    "eval_logps/chosen": -275.3572082519531,
+    "eval_logps/rejected": -324.0383605957031,
+    "eval_loss": 0.12900209426879883,
+    "eval_rewards/accuracies": 0.8596742749214172,
+    "eval_rewards/chosen": -0.17991267144680023,
+    "eval_rewards/margins": 5.889674186706543,
+    "eval_rewards/rejected": -6.069586277008057,
+    "eval_runtime": 76159.9506,
+    "eval_samples": 197968,
+    "eval_samples_per_second": 2.599,
+    "eval_steps_per_second": 1.3,
+    "train_loss": 0.3931771684165408,
+    "train_runtime": 248473.0607,
+    "train_samples": 209976,
+    "train_samples_per_second": 0.845,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.7773212790489197,
+    "eval_logits/rejected": -0.7749085426330566,
+    "eval_logps/chosen": -275.3572082519531,
+    "eval_logps/rejected": -324.0383605957031,
+    "eval_loss": 0.12900209426879883,
+    "eval_rewards/accuracies": 0.8596742749214172,
+    "eval_rewards/chosen": -0.17991267144680023,
+    "eval_rewards/margins": 5.889674186706543,
+    "eval_rewards/rejected": -6.069586277008057,
+    "eval_runtime": 76159.9506,
+    "eval_samples": 197968,
+    "eval_samples_per_second": 2.599,
+    "eval_steps_per_second": 1.3
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.3931771684165408,
+    "train_runtime": 248473.0607,
+    "train_samples": 209976,
+    "train_samples_per_second": 0.845,
+    "train_steps_per_second": 0.013
+}