End of training

DPO/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

DPO/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1988ff685aa8332b3ec4734a07d432d7bd15873457b60514ef53f33acdc28fc2
+size 167832240

README.md

@@ -0,0 +1,76 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: mistral_dpo2
+  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. -->
+
+# mistral_dpo2
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6594
+- Rewards/chosen: -0.0073
+- Rewards/rejected: -0.0880
+- Rewards/accuracies: 0.6532
+- Rewards/margins: 0.0807
+- Logps/rejected: -47.9164
+- Logps/chosen: -70.6164
+- Logits/rejected: -0.6606
+- Logits/chosen: -0.8711
+
+## 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-07
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 40
+- training_steps: 200
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6886        | 0.1251 | 40   | 0.6857          | 0.0161         | 0.0006           | 0.6532             | 0.0154          | -47.0302       | -70.3825     | -0.6637         | -0.8738       |
+| 0.6729        | 0.2502 | 80   | 0.6731          | 0.0155         | -0.0284          | 0.6587             | 0.0438          | -47.3201       | -70.3884     | -0.6620         | -0.8723       |
+| 0.6661        | 0.3753 | 120  | 0.6656          | 0.0214         | -0.0413          | 0.6532             | 0.0627          | -47.4494       | -70.3287     | -0.6616         | -0.8720       |
+| 0.6495        | 0.5004 | 160  | 0.6611          | -0.0187        | -0.0942          | 0.6532             | 0.0756          | -47.9787       | -70.7297     | -0.6609         | -0.8713       |
+| 0.6525        | 0.6255 | 200  | 0.6594          | -0.0073        | -0.0880          | 0.6532             | 0.0807          | -47.9164       | -70.6164     | -0.6606         | -0.8711       |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

reference/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

reference/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2977cb9ab288ae038de82de4eb67a55f06454dfb98a57bcb943096d0b3b52373
+size 167832240

runs/Jul26_06-17-55_192-9-148-18/events.out.tfevents.1721974701.192-9-148-18.325764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50e5423d60134c098b34fb240946a359781feeda2b2566d86758faa51ddbb9f
+size 16997

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0a3ebf050ae0dd8f678ab6236ff7be643f81d7dae85ffd927963956e2472e8
+size 5944