Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: alignment-handbook/zephyr-7b-sft-full
+model-index:
+- name: nash_dpo_rank4_iter_plus_3
+  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. -->
+
+# nash_dpo_rank4_iter_plus_3
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- 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+cu121
+- 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": "alignment-handbook/zephyr-7b-sft-full",
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0dfd31abdf83e940590c6fffa89efd594477774be9e85083a1811c4db27d5c0
+size 335605144

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.9072314500808716,
+    "eval_logits/rejected": -1.686521053314209,
+    "eval_logps/chosen": -320.5736083984375,
+    "eval_logps/rejected": -328.9005126953125,
+    "eval_loss": 0.604966402053833,
+    "eval_rewards/accuracies": 0.6899999976158142,
+    "eval_rewards/chosen": -0.04819466918706894,
+    "eval_rewards/margins": 0.26583459973335266,
+    "eval_rewards/rejected": -0.3140292465686798,
+    "eval_runtime": 384.0617,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.207,
+    "eval_steps_per_second": 0.651,
+    "train_loss": 0.0,
+    "train_runtime": 0.0096,
+    "train_samples": 5000,
+    "train_samples_per_second": 521173.985,
+    "train_steps_per_second": 4065.157
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.9072314500808716,
+    "eval_logits/rejected": -1.686521053314209,
+    "eval_logps/chosen": -320.5736083984375,
+    "eval_logps/rejected": -328.9005126953125,
+    "eval_loss": 0.604966402053833,
+    "eval_rewards/accuracies": 0.6899999976158142,
+    "eval_rewards/chosen": -0.04819466918706894,
+    "eval_rewards/margins": 0.26583459973335266,
+    "eval_rewards/rejected": -0.3140292465686798,
+    "eval_runtime": 384.0617,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.207,
+    "eval_steps_per_second": 0.651
+}

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": 1.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0096,
+    "train_samples": 5000,
+    "train_samples_per_second": 521173.985,
+    "train_steps_per_second": 4065.157
+}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 100,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.25e-06,
+      "logits/chosen": -2.5433855056762695,
+      "logits/rejected": -2.521193504333496,
+      "logps/chosen": -335.29010009765625,
+      "logps/rejected": -420.1910400390625,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.646121984004666e-06,
+      "logits/chosen": -2.4242465496063232,
+      "logits/rejected": -2.3739523887634277,
+      "logps/chosen": -283.9295349121094,
+      "logps/rejected": -356.6905517578125,
+      "loss": 0.6732,
+      "rewards/accuracies": 0.6354166865348816,
+      "rewards/chosen": 0.0827573761343956,
+      "rewards/margins": 0.037400420755147934,
+      "rewards/rejected": 0.045356955379247665,
+      "step": 10
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.835583164544139e-06,
+      "logits/chosen": -2.1755757331848145,
+      "logits/rejected": -2.069685935974121,
+      "logps/chosen": -307.59771728515625,
+      "logps/rejected": -366.8892517089844,
+      "loss": 0.6079,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 0.02839103899896145,
+      "rewards/margins": 0.22918327152729034,
+      "rewards/rejected": -0.20079222321510315,
+      "step": 20
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.723433775328385e-07,
+      "logits/chosen": -1.9671818017959595,
+      "logits/rejected": -1.8299922943115234,
+      "logps/chosen": -337.34051513671875,
+      "logps/rejected": -414.0975646972656,
+      "loss": 0.5677,
+      "rewards/accuracies": 0.746874988079071,
+      "rewards/chosen": -0.01181054301559925,
+      "rewards/margins": 0.3342409133911133,
+      "rewards/rejected": -0.34605151414871216,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "step": 39,
+      "total_flos": 0.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.0096,
+      "train_samples_per_second": 521173.985,
+      "train_steps_per_second": 4065.157
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f660d5bb72f5c540d92587c414b14213c0edb9f7c8d2e1b978c6a22886ea8f5b
+size 4920