Evan-Lin/dpo-llama-chat

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dpo-dataset.json filter=lfs diff=lfs merge=lfs -text
+gigaspeech_prompt_xs_large_v3_wer.json filter=lfs diff=lfs merge=lfs -text
+sft-dataset.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0483
+- Rewards/chosen: 0.8443
+- Rewards/rejected: -4.9894
+- Rewards/accuracies: 0.9864
+- Rewards/margins: 5.8337
+- Logps/rejected: -163.0178
+- Logps/chosen: -85.8088
+- Logits/rejected: -1.0144
+- Logits/chosen: -0.8703
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5635        | 0.24  | 100  | 0.5460          | 0.2168         | -0.4663          | 0.7367             | 0.6831          | -117.7869      | -92.0844     | -1.3150         | -1.2411       |
+| 0.3836        | 0.47  | 200  | 0.3582          | 0.1507         | -1.4599          | 0.8494             | 1.6106          | -127.7231      | -92.7453     | -0.6842         | -0.5917       |
+| 0.2525        | 0.71  | 300  | 0.2509          | 0.6325         | -1.7217          | 0.9095             | 2.3542          | -130.3404      | -87.9269     | -0.7855         | -0.6860       |
+| 0.1625        | 0.94  | 400  | 0.1711          | 0.6613         | -2.8054          | 0.9357             | 3.4667          | -141.1781      | -87.6390     | -0.7853         | -0.6836       |
+| 0.0695        | 1.18  | 500  | 0.1215          | 0.6443         | -3.7903          | 0.9589             | 4.4347          | -151.0267      | -87.8085     | -0.8915         | -0.7635       |
+| 0.0448        | 1.42  | 600  | 0.0905          | 1.0284         | -4.1415          | 0.9698             | 5.1699          | -154.5387      | -83.9677     | -0.9632         | -0.8182       |
+| 0.0515        | 1.65  | 700  | 0.0760          | 1.1233         | -3.6423          | 0.9758             | 4.7656          | -149.5469      | -83.0189     | -0.9748         | -0.8504       |
+| 0.0396        | 1.89  | 800  | 0.0542          | 0.7363         | -4.9101          | 0.9864             | 5.6464          | -162.2247      | -86.8886     | -1.0377         | -0.8963       |
+| 0.0099        | 2.13  | 900  | 0.0486          | 0.8344         | -4.9605          | 0.9864             | 5.7949          | -162.7287      | -85.9078     | -1.0199         | -0.8760       |
+| 0.0107        | 2.36  | 1000 | 0.0483          | 0.8443         | -4.9894          | 0.9864             | 5.8337          | -163.0178      | -85.8088     | -1.0144         | -0.8703       |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc_in",
+    "out_proj",
+    "q_proj",
+    "v_proj",
+    "wte",
+    "fc_out"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88de8b810a4a78a446194be966750655c96d5449e79ef950203c3c92f85b2ed5
+size 25191360

dpo-dataset.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a6d6f23c6bcbca11a5cef1a4970fc5012796582fd08457532e1db66980e9df
+size 18308271

gigaspeech_prompt_xs_large_v3_wer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a75d9ee3250fa61c36e2211203a7c31dbb14e18eeeb0647b7f6a8b9341d5e9
+size 26504717

merge_json.py

@@ -0,0 +1,14 @@
+import os
+import json 
+
+files = ["gigaspeech_no-previous_test_0-5000.json", "gigaspeech_no-previous_test_5000-10000.json", "gigaspeech_no-previous_test_10000-15000.json", "gigaspeech_no-previous_test_15000-20000.json"]
+output_file = "gigaspeech_no-previous_test.json"
+
+final_output = {}
+for file in files: 
+	with open(file) as f:
+		data = json.load(f)
+	final_output.update(data)
+
+with open(output_file, "w") as f: 
+	json.dump(final_output, f)

merge_list.py

@@ -0,0 +1,13 @@
+import os
+import json 
+
+files = ["gigaspeech_prompt_xs_large_v3_wer_0-20000.json", "gigaspeech_prompt_xs_large_v3_wer_20000-99999999.json"]
+output_file = "gigaspeech_prompt_xs_large_v3_wer.json"
+final_output = []
+for file in files: 
+	with open(file) as f:
+		data = json.load(f)
+	final_output.extend(data)
+
+with open(output_file, "w") as f: 
+	json.dump(final_output, f)

sft-dataset.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a6d6f23c6bcbca11a5cef1a4970fc5012796582fd08457532e1db66980e9df
+size 18308271

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "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 sha256:949e32986ef53e33661e230b0aa8cd28cec4469b31448b29ebb37de8b6c6651f
+size 4664