Upload folder using huggingface_hub

README.md

@@ -0,0 +1,178 @@
+---
+base_model: mistralai/Mistral-Nemo-Base-2407
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora_outputs
+  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
+base_model: mistralai/Mistral-Nemo-Base-2407
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+adapter: qlora
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+datasets:
+  - path: /home/austin/disk1/summaries_fixed.jsonl
+    type: sharegpt
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: ./qlora_outputs
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+wandb_project: summarization-qlora
+wandb_entity:
+wandb_watch:
+wandb_name: actual_run1
+wandb_log_model:
+ 
+ #unsloth_cross_entropy_loss: true
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention: false
+flash_attention: true
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 25
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 4
+debug:
+deepspeed: ./deepspeed_configs/zero2.json
+weight_decay: 0.0
+fsdp:
+  #  - full_shard
+  #  - auto_wrap
+fsdp_config:
+  #  fsdp_limit_all_gathers: true
+  #  fsdp_activation_checkpointing: true
+  #  fsdp_sync_module_states: true
+  #  fsdp_offload_params: false
+  #  fsdp_use_orig_params: false
+  #  fsdp_cpu_ram_efficient_loading: false
+  #  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
+  #  fsdp_state_dict_type: FULL_STATE_DICT
+  #  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+special_tokens:
+  pad_token: </s>
+
+```
+
+</details><br>
+
+# qlora_outputs
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5617
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 25
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.0177        | 0.0014 | 1    | 1.6514          |
+| 1.6259        | 0.2507 | 177  | 1.2032          |
+| 1.4232        | 0.5014 | 354  | 1.1897          |
+| 1.6835        | 0.7521 | 531  | 1.1985          |
+| 1.6514        | 1.0028 | 708  | 1.1874          |
+| 1.4538        | 1.2365 | 885  | 1.2166          |
+| 1.2421        | 1.4873 | 1062 | 1.2224          |
+| 1.2844        | 1.7380 | 1239 | 1.2330          |
+| 1.4152        | 1.9887 | 1416 | 1.2345          |
+| 1.1668        | 2.2252 | 1593 | 1.3476          |
+| 1.1249        | 2.4759 | 1770 | 1.3608          |
+| 0.921         | 2.7266 | 1947 | 1.3793          |
+| 0.7824        | 2.9773 | 2124 | 1.3906          |
+| 1.1759        | 3.2040 | 2301 | 1.5438          |
+| 0.6625        | 3.4547 | 2478 | 1.5644          |
+| 0.8959        | 3.7054 | 2655 | 1.5617          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6842a215f1e38f0301c0cee03ee41d3f80d8be8936c1527138a56b9c1e06e1d1
+size 228153978

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": "4.44.0",
+  "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": "</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
+  }
+}