Upload folder using huggingface_hub

README.md

@@ -0,0 +1,88 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: lora-out
+  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)
+# lora-out
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2973
+
+## 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: 0.00065
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5404        | 0.03  | 20   | 1.2764          |
+| 1.4523        | 0.06  | 40   | 1.2571          |
+| 1.5608        | 0.09  | 60   | 1.2465          |
+| 1.5921        | 0.12  | 80   | 1.2575          |
+| 1.6043        | 0.15  | 100  | 1.2432          |
+| 1.5496        | 0.18  | 120  | 1.2504          |
+| 1.348         | 0.21  | 140  | 1.2452          |
+| 1.4638        | 0.24  | 160  | 1.2661          |
+| 1.5733        | 0.27  | 180  | 1.2548          |
+| 1.5397        | 0.3   | 200  | 1.2674          |
+| 1.6154        | 0.33  | 220  | 1.2626          |
+| 1.5058        | 0.36  | 240  | 1.2672          |
+| 1.3974        | 0.4   | 260  | 1.2659          |
+| 1.6654        | 0.43  | 280  | 1.2648          |
+| 1.8051        | 0.46  | 300  | 1.2585          |
+| 1.7487        | 0.49  | 320  | 1.2736          |
+| 1.3612        | 0.52  | 340  | 1.2717          |
+| 1.5048        | 0.55  | 360  | 1.2809          |
+| 1.7134        | 0.58  | 380  | 1.2885          |
+| 1.5524        | 0.61  | 400  | 1.2805          |
+| 1.3705        | 0.64  | 420  | 1.2860          |
+| 1.4335        | 0.67  | 440  | 1.2896          |
+| 1.3642        | 0.7   | 460  | 1.2911          |
+| 1.6546        | 0.73  | 480  | 1.2888          |
+| 1.5345        | 0.76  | 500  | 1.2973          |
+| 1.5968        | 0.79  | 520  | 1.2885          |
+| 1.5694        | 0.82  | 540  | 1.2939          |
+| 1.5474        | 0.85  | 560  | 1.2892          |
+| 1.6981        | 0.88  | 580  | 1.2949          |
+| 1.5451        | 0.91  | 600  | 1.2886          |
+| 1.5845        | 0.94  | 620  | 1.2941          |
+| 1.5143        | 0.97  | 640  | 1.2973          |
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda1086566badda7ec0876d5d8d9d016416fca1ca16e9d778397fc619aa9282e
+size 2684516749

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "./mistralai_Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": "./mistralai_Mistral-7B-v0.1/tokenizer.json",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}