aritrasen/mistral-dpo

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: mistral-dpo
+  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-dpo
+
+This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7175
+- Rewards/chosen: 0.5987
+- Rewards/rejected: 0.4947
+- Rewards/accuracies: 0.5769
+- Rewards/margins: 0.1040
+- Logps/rejected: -155.3645
+- Logps/chosen: -178.6683
+- Logits/rejected: -2.3247
+- Logits/chosen: -2.3598
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.7039        | 0.0   | 10   | 0.6929          | 0.0710         | 0.0692           | 0.5                | 0.0018          | -159.6188      | -183.9449    | -2.2886         | -2.3271       |
+| 0.68          | 0.0   | 20   | 0.7113          | -0.0478        | -0.0188          | 0.4519             | -0.0290         | -160.4993      | -185.1333    | -2.2979         | -2.3361       |
+| 0.8777        | 0.0   | 30   | 0.7367          | -0.3027        | -0.2538          | 0.4904             | -0.0489         | -162.8490      | -187.6822    | -2.3132         | -2.3525       |
+| 0.8501        | 0.0   | 40   | 0.7407          | -0.2893        | -0.2458          | 0.4327             | -0.0435         | -162.7690      | -187.5477    | -2.3173         | -2.3556       |
+| 0.7253        | 0.0   | 50   | 0.7207          | -0.0228        | -0.0265          | 0.4904             | 0.0037          | -160.5759      | -184.8833    | -2.3167         | -2.3538       |
+| 0.7293        | 0.0   | 60   | 0.7066          | 0.1787         | 0.1240           | 0.5673             | 0.0547          | -159.0715      | -182.8687    | -2.3194         | -2.3553       |
+| 0.6057        | 0.01  | 70   | 0.6851          | 0.4039         | 0.2915           | 0.5769             | 0.1125          | -157.3963      | -180.6157    | -2.3192         | -2.3543       |
+| 0.7169        | 0.01  | 80   | 0.6853          | 0.5467         | 0.4175           | 0.5769             | 0.1291          | -156.1357      | -179.1884    | -2.3219         | -2.3564       |
+| 0.6324        | 0.01  | 90   | 0.7046          | 0.5751         | 0.4602           | 0.5769             | 0.1149          | -155.7090      | -178.9038    | -2.3232         | -2.3580       |
+| 0.5915        | 0.01  | 100  | 0.7175          | 0.5987         | 0.4947           | 0.5769             | 0.1040          | -155.3645      | -178.6683    | -2.3247         | -2.3598       |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/OpenHermes-2-Mistral-7B-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 6,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e96ed6d91792e6d66f1b1fc0d1ba395d6a5171279143a3b0f51db663cbb7541
+size 6832600

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Jan11_16-40-25_a61afaa5d79f/events.out.tfevents.1704991365.a61afaa5d79f.2583.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652a208172d14b014be828058c50cbddd8da3d5ae6a6cbd2d3b12760b781401f
+size 19310

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8efc565e9efbe13a27d53ed4c0f1f7be7176ab57b0a5714db4d07e43212821
+size 4091