Model save

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: zephyr-7b-dpo-qlora
+  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-qlora
+
+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: 0.6656
+- Rewards/chosen: 0.0388
+- Rewards/rejected: -0.0264
+- Rewards/accuracies: 0.6900
+- Rewards/margins: 0.0652
+- Logps/rejected: -237.8513
+- Logps/chosen: -255.6933
+- Logits/rejected: -2.8702
+- Logits/chosen: -2.8928
+
+## 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-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 1024
+- total_train_batch_size: 4096
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "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,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4dbbff2539f5a8cc2b73edc88b63b9ab06ac92e3ac29db5f235026806303ab
+size 671150064

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 0.94,
+    "eval_logits/chosen": -2.892765760421753,
+    "eval_logits/rejected": -2.870206356048584,
+    "eval_logps/chosen": -255.6932830810547,
+    "eval_logps/rejected": -237.85133361816406,
+    "eval_loss": 0.6655747294425964,
+    "eval_rewards/accuracies": 0.6899999976158142,
+    "eval_rewards/chosen": 0.03882095217704773,
+    "eval_rewards/margins": 0.06518173217773438,
+    "eval_rewards/rejected": -0.026360776275396347,
+    "eval_runtime": 905.2491,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.209,
+    "eval_steps_per_second": 0.552,
+    "train_loss": 0.6761519227709089,
+    "train_runtime": 40312.7822,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.517,
+    "train_steps_per_second": 0.0
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.94,
+    "eval_logits/chosen": -2.892765760421753,
+    "eval_logits/rejected": -2.870206356048584,
+    "eval_logps/chosen": -255.6932830810547,
+    "eval_logps/rejected": -237.85133361816406,
+    "eval_loss": 0.6655747294425964,
+    "eval_rewards/accuracies": 0.6899999976158142,
+    "eval_rewards/chosen": 0.03882095217704773,
+    "eval_rewards/margins": 0.06518173217773438,
+    "eval_rewards/rejected": -0.026360776275396347,
+    "eval_runtime": 905.2491,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.209,
+    "eval_steps_per_second": 0.552
+}

runs/Feb13_23-01-20_ip-172-31-12-179/events.out.tfevents.1707865729.ip-172-31-12-179.1495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16be397c167a4213b9b1a6db0c517a873f8d2d5b7a5f592edcc1c4ac12dbd0e6
+size 6526

runs/Feb13_23-01-20_ip-172-31-12-179/events.out.tfevents.1707906946.ip-172-31-12-179.1495.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40daae194d0202bc3e6f9b09b54b6a4c7a7c04e53ce87c066fbf7c2edb3d2d52
+size 815

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 +1,43 @@
+{
+  "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
+    }
+  },
+  "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": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.94,
+    "train_loss": 0.6761519227709089,
+    "train_runtime": 40312.7822,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.517,
+    "train_steps_per_second": 0.0
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9379743522638053,
+  "eval_steps": 100,
+  "global_step": 14,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.9041404724121094,
+      "logits/rejected": -2.8873558044433594,
+      "logps/chosen": -256.58734130859375,
+      "logps/rejected": -238.80397033691406,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2500000000000007e-06,
+      "logits/chosen": -2.9109790325164795,
+      "logits/rejected": -2.8924036026000977,
+      "logps/chosen": -258.4911193847656,
+      "logps/rejected": -244.30831909179688,
+      "loss": 0.6793,
+      "rewards/accuracies": 0.5908203125,
+      "rewards/chosen": 0.04758377745747566,
+      "rewards/margins": 0.029919220134615898,
+      "rewards/rejected": 0.017664561048150063,
+      "step": 10
+    },
+    {
+      "epoch": 0.94,
+      "step": 14,
+      "total_flos": 0.0,
+      "train_loss": 0.6761519227709089,
+      "train_runtime": 40312.7822,
+      "train_samples_per_second": 1.517,
+      "train_steps_per_second": 0.0
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09ff2637c91d42e638be06b03259cb3c36c437d9752ac79ab9f5b2b83c3a6bc
+size 4856