End of training

README.md

@@ -0,0 +1,249 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- axolotl
+- dpo
+- trl
+- dpo
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-7b-base-dpo-run
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: mistralai/Mistral-7B-v0.1
+base_model_ignore_patterns: []
+base_model_config: mistralai/Mistral-7B-v0.1
+model_revision:
+tokenizer_config:
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+tokenizer_use_fast: true
+tokenizer_legacy: true
+resize_token_embeddings_to_32x: false
+
+is_falcon_derived_model: false
+is_llama_derived_model: false
+is_mistral_derived_model: true
+is_qwen_derived_model: false
+
+model_config:
+  rope_scaling:
+
+bnb_config_kwargs:
+
+gptq: false
+gptq_groupsize:
+gptq_model_v1: false
+
+load_in_8bit: false
+load_in_4bit: true
+
+fp16: true
+
+lora_on_cpu: false
+
+rl: dpo
+datasets:
+  - path: NobodyExistsOnTheInternet/Fixed-gutenberg-dpo-v0.1
+    split: train
+    type: chatml.intel
+  - path: NobodyExistsOnTheInternet/Fixed-Distilabel-intel-orca-dpo-pairs
+    split: train
+    type: chatml.intel
+  - path: NobodyExistsOnTheInternet/ToxicDPOqa
+    split: train
+    type: chatml.intel
+  - path: NobodyExistsOnTheInternet/system-message-DPO
+    split: train
+    type: chatml.intel
+  - path: NobodyExistsOnTheInternet/alpaca-intel-data-dpo
+    split: train
+    type: chatml.intel
+  - path: NobodyExistsOnTheInternet/ToxicDPOqa
+    split: train
+    type: chatml.intel
+
+
+chat_template: chatml
+default_system_message: Generate a preferable answer.
+dataset_prepared_path: data/last_run_prepared
+push_dataset_to_hub:
+dataset_processes:
+dataset_keep_in_memory:
+hub_model_id: NobodyExistsOnTheInternet/mistral-7b-base-dpo-run
+hub_strategy: every_save
+hf_use_auth_token: true
+val_set_size: 0
+dataset_shard_num:
+dataset_shard_idx:
+
+sequence_len: 1024
+sample_packing: false
+eval_sample_packing:
+sample_packing_eff_est:
+total_num_tokens:
+
+device_map:
+max_memory:
+
+adapter: qlora
+lora_model_dir:
+
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_module:
+
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+lora_fan_in_fan_out:
+
+wandb_project: dpo-hermes-2.5
+wandb_entity:
+wandb_watch:
+wandb_name: 
+wandb_run_id:
+wandb_log_model:
+
+mlflow_tracking_uri:
+mlflow_experiment_name:
+
+output_dir: ./completed-model
+
+torch_compile: true
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+eval_batch_size:
+num_epochs: 2
+warmup_steps: 100
+warmup_ratio:
+learning_rate: 0.000001
+lr_quadratic_warmup:
+logging_steps:
+eval_steps:
+evals_per_epoch:
+save_strategy: steps
+save_steps: 1000
+saves_per_epoch: 
+save_total_limit:
+eval_table_size:
+eval_max_new_tokens:
+eval_causal_lm_metrics:
+
+loss_watchdog_threshold:
+loss_watchwatchdog_patience:
+
+train_on_inputs: false
+group_by_length: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+   use_reentrant: false
+
+lr_scheduler:
+
+optimizer: paged_adamw_8bit
+weight_decay: 0.01
+adam_beta1: 0.95
+adam_beta2: 0.999
+adam_epsilon: 0.0000001
+
+neftune_noise_alpha: 5
+
+flash_optimum:
+xformers_attention:
+flash_attention: true
+flash_attn_cross_entropy:
+flash_attn_rms_norm:
+flash_attn_fuse_qkv:
+flash_attn_fuse_mlp:
+sdp_attention:
+s2_attention:
+resume_from_checkpoint:
+auto_resume_from_checkpoints: false
+
+local_rank:
+
+tokens:
+
+fsdp:
+fsdp_config:
+
+deepspeed:
+
+ddp_timeout:
+ddp_bucket_cap_mb:
+ddp_broadcast_buffers:
+
+torchdistx_path:
+
+pretraining_dataset:
+
+debug:
+
+seed:
+
+```
+
+</details><br>
+
+# mistral-7b-base-dpo-run
+
+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.
+
+## 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: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.95,0.999) and epsilon=1e-07
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- training_steps: 15031
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bbea3a9f47522b8d9d6ad81b886e9e307ef855c26eeb9bf12205bfd8c6b264
+oid sha256:d73df302ad2980a1dc5078e34787075785e5b639f2909ec0e1490a4e69f4a6a3
 size 1384182104

config.json

@@ -34,7 +34,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.0",
   "use_cache": false,
   "vocab_size": 32000

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3ebfe135a69b54abaf5d30f63310a98312b7b2de0f849ad1895ab499789c60
+size 4986578982

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ec967a5d5093595fdd83d143b93a20830bade33e2d8505358fe40f6f635e58
+size 1048577750

runs/Mar10_11-25-20_05c27c174db0/events.out.tfevents.1710069924.05c27c174db0.832.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04cf8639924fe5849e3c8bf7eee9537e0ef92ddce99b9068bbcca8746c9e402e
-size 10323609
+oid sha256:48eb65c80c8852641bc29d68b0d669ff26d74458a7b77fc51df50baf1cce2c4d
+size 10345291