Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,194 @@
+---
+base_model: unsloth/Mistral-Nemo-Base-2407
+library_name: peft
+license: apache-2.0
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: mn-inf-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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+# Set up for use on 2x24gb cards 
+# huggingface-cli login --token $hf_key && wandb login $wandb_key
+# python -m axolotl.cli.preprocess mn-inf-lora.yml
+# accelerate launch -m axolotl.cli.train mn-inf-lora.yml
+# python -m axolotl.cli.merge_lora ms-adventure-s.yml
+# huggingface-cli upload ToastyPigeon/ms-type1-adventure-s adventure-workspace/merged . --private
+
+base_model: unsloth/Mistral-Nemo-Base-2407
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+sequence_len: 8192 # 99% vram
+min_sample_len: 128
+bf16: true
+fp16:
+tf32: false
+flash_attention: true
+special_tokens:
+
+# Data
+dataset_prepared_path: last_run_prepared
+datasets:
+  - path: botmall/bodinforg-completions
+    type: completion
+warmup_steps: 20
+shuffle_merged_datasets: true
+
+save_safetensors: true
+
+# WandB
+wandb_project: Mistral-Nemo-Inflation
+wandb_entity:
+
+# Iterations
+num_epochs: 1
+
+# Output
+output_dir: ./adventure-workspace
+hub_model_id: botmall/mn-inf-qlora
+hub_strategy: "checkpoint"
+
+# Sampling
+sample_packing: true
+pad_to_sequence_len: true
+
+# Batching
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+eval_batch_size: 1
+gradient_checkpointing: 'unsloth'
+gradient_checkpointing_kwargs:
+   use_reentrant: true
+
+unsloth_cross_entropy_loss: true
+#unsloth_lora_mlp: true
+#unsloth_lora_qkv: true
+#unsloth_lora_o: true
+
+# Evaluation
+val_set_size: 40
+evals_per_epoch: 5
+eval_table_size:
+eval_max_new_tokens: 256
+eval_sample_packing: false
+
+# LoRA
+adapter: qlora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.1
+lora_target_linear: 
+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:
+
+# Optimizer
+optimizer: paged_adamw_8bit # adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0001
+cosine_min_lr_ratio: 0.1
+weight_decay: 0.01
+max_grad_norm: 10.0
+
+# Misc
+train_on_inputs: false
+group_by_length: false
+early_stopping_patience:
+local_rank:
+logging_steps: 1
+xformers_attention:
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3.json # previously blank
+fsdp:
+fsdp_config:
+
+# Checkpoints
+resume_from_checkpoint:
+saves_per_epoch: 1
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+```
+
+</details><br>
+
+# mn-inf-qlora
+
+This model is a fine-tuned version of [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2226
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.2853        | 0.0057 | 1    | 2.3231          |
+| 2.2576        | 0.2102 | 37   | 2.2478          |
+| 2.1671        | 0.4205 | 74   | 2.2352          |
+| 2.2319        | 0.6307 | 111  | 2.2259          |
+| 2.174         | 0.8409 | 148  | 2.2226          |
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "inflatebot/MN-12B-Mag-Mell-R1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01cbf065547f2ab6915a565e816f5afcf4b7ea7de7675676becd6ec768b42f0
+size 228141160

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "inflatebot/MN-12B-Mag-Mell-R1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 15,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4c8fcd33487a449c07f423d47adb035bba8347ccf13eb074b4d1fef8acf919
+size 17078288

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c44a0f2c9d2ec98f44eb784396ebb6d033f0108a4702e31b64f27d55e6df44d
+size 8184