Model save

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-dpo-lora
+  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. -->
+
+# zephyr-7b-dpo-lora
+
+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: 0.5381
+- Rewards/chosen: -0.0977
+- Rewards/rejected: -0.7746
+- Rewards/accuracies: 0.7183
+- Rewards/margins: 0.6768
+- Logps/rejected: -237.3503
+- Logps/chosen: -283.6626
+- Logits/rejected: -1.8216
+- Logits/chosen: -1.9102
+
+## 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: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5546        | 1.0   | 968  | 0.5678          | -0.0091        | -0.4982          | 0.7054             | 0.4891          | -234.5862      | -282.7758    | -1.8508         | -1.9394       |
+| 0.5491        | 2.0   | 1936 | 0.5438          | -0.0836        | -0.7251          | 0.7192             | 0.6414          | -236.8553      | -283.5217    | -1.8279         | -1.9162       |
+| 0.5463        | 3.0   | 2904 | 0.5381          | -0.0977        | -0.7746          | 0.7183             | 0.6768          | -237.3503      | -283.6626    | -1.8216         | -1.9102       |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97eb9f5f7cb370cc0712f6a221c0b6e5419730fb4ce136ac1650af60196294c0
+size 109086672

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -1.9102067947387695,
+    "eval_logits/rejected": -1.8216071128845215,
+    "eval_logps/chosen": -283.6626281738281,
+    "eval_logps/rejected": -237.35032653808594,
+    "eval_loss": 0.5380748510360718,
+    "eval_rewards/accuracies": 0.7182539701461792,
+    "eval_rewards/chosen": -0.09773208945989609,
+    "eval_rewards/margins": 0.6768320798873901,
+    "eval_rewards/rejected": -0.7745641469955444,
+    "eval_runtime": 873.0984,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.291,
+    "eval_steps_per_second": 0.072,
+    "train_loss": 0.5707186016333662,
+    "train_runtime": 142661.7128,
+    "train_samples": 61966,
+    "train_samples_per_second": 1.303,
+    "train_steps_per_second": 0.02
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -1.9102067947387695,
+    "eval_logits/rejected": -1.8216071128845215,
+    "eval_logps/chosen": -283.6626281738281,
+    "eval_logps/rejected": -237.35032653808594,
+    "eval_loss": 0.5380748510360718,
+    "eval_rewards/accuracies": 0.7182539701461792,
+    "eval_rewards/chosen": -0.09773208945989609,
+    "eval_rewards/margins": 0.6768320798873901,
+    "eval_rewards/rejected": -0.7745641469955444,
+    "eval_runtime": 873.0984,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.291,
+    "eval_steps_per_second": 0.072
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "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_config.json

@@ -0,0 +1,41 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5707186016333662,
+    "train_runtime": 142661.7128,
+    "train_samples": 61966,
+    "train_samples_per_second": 1.303,
+    "train_steps_per_second": 0.02
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f94ab8ccf8c1dbd06bf388d60a57e79e65e4f581d6b68b2149a42d01e6ef3a
+size 5496