TrevorJS/mtg-code-llama-7b-dpo

README.md

@@ -0,0 +1,77 @@
+---
+license: llama2
+base_model: codellama/CodeLlama-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: 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. -->
+
+# dpo
+
+This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0010
+- Rewards/chosen: -5.5160
+- Rewards/rejected: -16.3854
+- Rewards/accuracies: 0.9991
+- Rewards/margins: 10.8694
+- Logps/rejected: -189.5804
+- Logps/chosen: -75.4962
+- Logits/rejected: -1.9168
+- Logits/chosen: -2.2651
+
+## 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: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.0937        | 0.07  | 100  | 0.1058          | -5.7722        | -13.1291         | 0.9515             | 7.3569          | -157.0180      | -78.0587     | -1.5497         | -1.7945       |
+| 0.0442        | 0.15  | 200  | 0.0392          | -4.5353        | -13.5199         | 0.9835             | 8.9845          | -160.9253      | -65.6901     | -2.3349         | -2.6709       |
+| 0.0165        | 0.22  | 300  | 0.0186          | -5.9014        | -14.9526         | 0.9939             | 9.0511          | -175.2523      | -79.3511     | -2.1283         | -2.4222       |
+| 0.0016        | 0.29  | 400  | 0.0239          | -7.2028        | -18.5000         | 0.9922             | 11.2973         | -210.7271      | -92.3644     | -1.9903         | -2.3400       |
+| 0.0014        | 0.36  | 500  | 0.0065          | -5.1522        | -15.5259         | 0.9983             | 10.3737         | -180.9857      | -71.8588     | -1.6803         | -2.0312       |
+| 0.0006        | 0.44  | 600  | 0.0038          | -5.0346        | -14.9248         | 0.9991             | 9.8902          | -174.9747      | -70.6829     | -2.1480         | -2.4897       |
+| 0.0003        | 0.51  | 700  | 0.0018          | -5.2732        | -16.3551         | 0.9991             | 11.0819         | -189.2777      | -73.0690     | -1.9657         | -2.3112       |
+| 0.0002        | 0.58  | 800  | 0.0016          | -5.5844        | -16.3258         | 1.0                | 10.7414         | -188.9845      | -76.1804     | -1.9284         | -2.2717       |
+| 0.0004        | 0.66  | 900  | 0.0011          | -5.5422        | -16.3921         | 0.9991             | 10.8499         | -189.6474      | -75.7582     | -1.9152         | -2.2631       |
+| 0.0008        | 0.73  | 1000 | 0.0010          | -5.5160        | -16.3854         | 0.9991             | 10.8694         | -189.5804      | -75.4962     | -1.9168         | -2.2651       |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ea7e6e6940a3bffa6ba4ec1c1a45920c5cee96163f0ebf2df01b1b3bc9a6ab
+size 80122381

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0789fb5cf14abad8e57dc19f2dafc11a51d431e860bcf6d1215e733113e8c29
+size 4027