End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: AI-Sweden-Models/gpt-sw3-1.3b
+model-index:
+- name: gpt1B_DPO_model
+  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. -->
+
+# gpt1B_DPO_model
+
+This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-1.3b](https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -217.1661
+- Logps/chosen: -114.3195
+- Logits/rejected: -3.2643
+- Logits/chosen: -3.4174
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6931        | 0.79  | 200  | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+| 0.6931        | 1.59  | 400  | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+| 0.6931        | 2.38  | 600  | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+| 0.6931        | 3.18  | 800  | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+| 0.6931        | 3.97  | 1000 | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+| 0.6931        | 4.77  | 1200 | 0.6931          | 0.0            | 0.0              | 0.0                | 0.0             | -217.1661      | -114.3195    | -3.2643         | -3.4174       |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.1
+- Pytorch 2.2.0+cu118
+- Datasets 2.17.1
+- Tokenizers 0.15.2

dpo/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "AI-Sweden-Models/gpt-sw3-1.3b",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

dpo/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51a70c74db410dae453be3f9b74269b51853ec8b706bb85e69e15c27b27f153
+size 100669688

reference/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "AI-Sweden-Models/gpt-sw3-1.3b",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

reference/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51a70c74db410dae453be3f9b74269b51853ec8b706bb85e69e15c27b27f153
+size 100669688