Evan-Lin/dpo-llama-chat

README.md

@@ -0,0 +1,83 @@
+---
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-chat-hf
+model-index:
+- name: dpo-llama-chat-without-none
+  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-llama-chat-without-none
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0177
+- Rewards/chosen: -5.0689
+- Rewards/rejected: -14.1911
+- Rewards/accuracies: 0.9933
+- Rewards/margins: 9.1223
+- Logps/rejected: -230.9264
+- Logps/chosen: -147.4190
+- Logits/rejected: -0.6518
+- Logits/chosen: -0.6273
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 256
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.2627        | 1.92  | 100  | 0.2451          | -1.0090        | -3.0456          | 0.9240             | 2.0366          | -119.4711      | -106.8200    | -0.8708         | -0.8600       |
+| 0.0386        | 3.84  | 200  | 0.0708          | -2.3491        | -7.1127          | 0.9813             | 4.7636          | -160.1419      | -120.2212    | -0.8381         | -0.8197       |
+| 0.0147        | 5.76  | 300  | 0.0424          | -2.9584        | -8.9699          | 0.9840             | 6.0115          | -178.7142      | -126.3143    | -0.7736         | -0.7537       |
+| 0.005         | 7.69  | 400  | 0.0294          | -3.7997        | -11.1138         | 0.9907             | 7.3141          | -200.1534      | -134.7274    | -0.7233         | -0.6967       |
+| 0.002         | 9.61  | 500  | 0.0186          | -4.4609        | -12.4831         | 0.9947             | 8.0222          | -213.8460      | -141.3395    | -0.6848         | -0.6600       |
+| 0.0008        | 11.53 | 600  | 0.0193          | -4.8300        | -13.5310         | 0.9947             | 8.7010          | -224.3250      | -145.0307    | -0.6646         | -0.6397       |
+| 0.0006        | 13.45 | 700  | 0.0166          | -4.8968        | -13.8306         | 0.9947             | 8.9338          | -227.3210      | -145.6982    | -0.6552         | -0.6304       |
+| 0.0005        | 15.37 | 800  | 0.0179          | -4.9970        | -14.0354         | 0.9933             | 9.0383          | -229.3687      | -146.7007    | -0.6498         | -0.6253       |
+| 0.0005        | 17.29 | 900  | 0.0156          | -5.0417        | -14.1518         | 0.9947             | 9.1101          | -230.5333      | -147.1470    | -0.6492         | -0.6245       |
+| 0.0005        | 19.21 | 1000 | 0.0177          | -5.0689        | -14.1911         | 0.9933             | 9.1223          | -230.9264      | -147.4190    | -0.6518         | -0.6273       |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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": [
+    "v_proj",
+    "out_proj",
+    "wte",
+    "k_proj",
+    "fc_out",
+    "q_proj",
+    "fc_in"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141dd4ed5d7add238576f244954362a8b9fdbb6e8f8f2bbb1bbfcb8157e84cff
+size 25191360

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 +1,42 @@
+{
+  "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>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "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:bf62c053ab3ff182f15262d4beb891b4d1ce3a524d83c6987386d6d7a82fd48c
+size 4728