Upload folder using huggingface_hub

README.md

@@ -0,0 +1,93 @@
+---
+license: wtfpl
+base_model: CausalLM/7B
+tags:
+- generated_from_trainer
+model-index:
+- name: workspace/causal-dolphin-v0.1
+  results: []
+---
+
+[<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)
+# Causal-Dolphin-Agent-v0.1
+
+This model is a LoRA fine-tune of [CausalLM/7B](https://huggingface.co/CausalLM/7B) on Eric's wonderful [Dolphin](https://huggingface.co/datasets/ehartford/dolphin) dataset, with [THUDM/AgentInstruct](https://huggingface.co/datasets/THUDM/AgentInstruct) mixed in both training runs.
+
+Causal-Dolphin-Agent was trained for 3 epochs on 5 million GPT3.5 augmented FLAN instructions & AgentInstruct dataset in ChatML format. It was then trained a further 3 epochs on 1 million GPT4 augmented FLAN instructions with AgentInstruct shuffled in as well. 
+
+It achieves the following results on the evaluation set:
+- Loss: 2.8435
+
+## Prompt Format
+
+Causal-Dolphin-Agent uses ChatML as the prompt format:
+```<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+If Danny owns a bike, then Edward owns a bike. If Edward owns a bike, then Freddy owns a bike. If Danny owns a bike, which of the following statements must be true? Let's think step by step.
+
+I. Edward owns a bike.
+II. Freddy owns a bike.
+III. Freddy does not own a bike.
+
+Choose one answer:
+I only
+II only
+III only
+I and II only
+I and III only
+<|im_end|>
+<|im_start|>assistant```
+
+## Training and evaluation data
+
+[ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin)
+[THUDM/AgentInstruct](https://huggingface.co/datasets/THUDM/AgentInstruct)
+
+## Training procedure
+Causal-Dolphin-Agent was trained for 3 epochs on 5 million GPT3.5 augmented FLAN instructions & AgentInstruct dataset in ChatML format. It was then trained a further 3 epochs on 1 million GPT4 augmented FLAN instructions with AgentInstruct shuffled in as well. 
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.7774        | 0.0   | 1    | 5.1009          |
+| 3.2798        | 0.15  | 46   | 5.1010          |
+| 2.0722        | 0.3   | 92   | 5.0489          |
+| 2.5919        | 0.45  | 138  | 4.8834          |
+| 2.0011        | 0.6   | 184  | 4.6678          |
+| 1.3733        | 0.75  | 230  | 4.4628          |
+| 1.7321        | 0.9   | 276  | 4.2757          |
+| 1.3994        | 1.05  | 322  | 4.1029          |
+| 1.2308        | 1.2   | 368  | 3.8916          |
+| 0.8229        | 1.35  | 414  | 3.6451          |
+| 0.9592        | 1.5   | 460  | 3.4106          |
+| 0.8528        | 1.65  | 506  | 3.2250          |
+| 0.7362        | 1.8   | 552  | 3.0852          |
+| 0.8077        | 1.95  | 598  | 2.9881          |
+| 0.6912        | 2.1   | 644  | 2.9315          |
+| 0.7776        | 2.25  | 690  | 2.8911          |
+| 0.6916        | 2.41  | 736  | 2.8678          |
+| 0.8674        | 2.56  | 782  | 2.8534          |
+| 0.7797        | 2.71  | 828  | 2.8545          |
+| 0.6838        | 2.86  | 874  | 2.8435          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CausalLM/7B",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22980146de9b7323bc4ca16384b2dc25e239d966273a317a7d06c564fdacbae9
+size 67155338

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "CausalLM/7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 151936
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "128244": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<unk>"
+}