End of training

README.md

@@ -0,0 +1,190 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: manishiitg/open-aditi-hi-v1
+model-index:
+- name: open-aditi-hi-v1-dpo
+  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: `0.3.0`
+```yaml
+base_model: manishiitg/open-aditi-hi-v1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+rl: true
+datasets:
+  - path: manishiitg/argilla-ultrafeedback-binarized-preferences-cleaned
+    split: train
+    type: ultra_apply_chatml
+  - path: manishiitg/unalignment-toxic-dpo-v0.1
+    split: train
+    type: apply_chatml
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+output_dir: /sky-notebook/manishiitg/open-aditi-hi-v1-dpo
+
+hub_model_id: manishiitg/open-aditi-hi-v1-dpo
+hf_use_auth_token: true
+
+wandb_project: open-aditi-hi-v1-dpo
+
+save_safetensors: true
+
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: false
+
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+lora_modules_to_save:
+ - embed_tokens
+ - lm_head
+
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 3
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true ## manage check point resume from here
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 10
+eval_steps: 0
+evals_per_epoch: 0
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps: 100 ## increase based on your dataset
+save_strategy: steps
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+tokens: # these are delimiters
+  - "<|im_start|>"
+  - "<|im_end|>"
+```
+
+</details><br>
+
+# open-aditi-hi-v1-dpo
+
+This model is a fine-tuned version of [manishiitg/open-aditi-hi-v1](https://huggingface.co/manishiitg/open-aditi-hi-v1) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 12
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 6964
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.1+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "manishiitg/open-aditi-hi-v1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47347ad8b6b44c9ca85d4e517d3d6e0d350959b2d8462d9e8416e8f46780012
+size 692153240

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "manishiitg/open-aditi-hi-v1",
+  "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,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

runs/Jan14_09-44-40_1c54d1981a2c/events.out.tfevents.1705225948.1c54d1981a2c.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba70bca6ebd74c8e42cbc613fcf2f54531e11a57251c7075416a02c9674a1d81
+size 1013436

runs/Jan15_10-06-37_e7646ab1305c/events.out.tfevents.1705313656.e7646ab1305c.38.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1695f3c93dfdf4526c3f579d0ebac71a1be94e431cb69664a1dd805d1616517a
+size 1176982

runs/Jan16_10-01-10_fe5fe188cf5a/events.out.tfevents.1705399979.fe5fe188cf5a.38.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8305883f3012b7c105c340dfc1b682bbe9affc9f21a58efaf1b2ba3c2869df5a
+size 1184124

runs/Jan17_09-59-09_9a35389951a8/events.out.tfevents.1705486313.9a35389951a8.38.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab106d00c782a1a1f4c23f7f77735744b14b1caf165d339afed22b4a495625f
+size 1171160

runs/Jan18_10-00-02_6605e1600ed0/events.out.tfevents.1705572757.6605e1600ed0.38.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4784296f8083c2cd1aa876431a115964bb0d01ce32881e4f6b9e0b5f2e0f80ad
+size 45814

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e6d6fda4c62bb59f12ca84a901913fba26d57766a9463b0001c3b875d80b89
+size 4792