Upload 9 files

Dora-Smol.yml

@@ -0,0 +1,91 @@
+base_model: /media/renfroe/llms/SmolLM-360M/
+
+model_type: LlamaForCausalLM
+tokenizer_type: GPT2Tokenizer
+seed: 122887 
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+max_steps: 0
+resume_from_checkpoint: 
+datasets:
+  - path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/Dynamic_Optimization_Methods_with_Applications_sqa_answers_only.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path: /home/renfroe/Dev/tinyllama-models/dataset/open_hermes_top_tech.json
+    type: sharegpt
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/or-farm_sharegpt.json
+    type: sharegpt
+  
+
+
+dataset_prepared_path:
+val_set_size: 0.2
+output_dir: ./SmolLM-Ora
+auto_resume_from_checkpoints: false
+
+sequence_len: 2048
+sample_packing: true
+chat_template: chatml
+
+wandb_project: SmolLM-Ora
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 10
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: linear
+weight_decay: 0.0000001
+learning_rate: 0.0001
+lr_scheduler_kwargs:
+  #  num_cycles: 3 
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+eval_sample_packing: False
+
+warmup_steps: 50
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 4
+debug:
+deepspeed:
+
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  pad_token: "<|endoftext|>"

README.md

@@ -1,3 +1,172 @@
----
-license: apache-2.0
----
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: SmolLM-Ora
+  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: `0.4.0`
+```yaml
+base_model: /media/renfroe/llms/SmolLM-360M/
+
+model_type: LlamaForCausalLM
+tokenizer_type: GPT2Tokenizer
+seed: 122887 
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+max_steps: 0
+resume_from_checkpoint: 
+datasets:
+  - path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/Dynamic_Optimization_Methods_with_Applications_sqa_answers_only.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path: /home/renfroe/Dev/tinyllama-models/dataset/open_hermes_top_tech.json
+    type: sharegpt
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json
+    type:
+      field_instruction: question
+      field_output: answer
+      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+  - path:  /home/renfroe/Desktop/sqa_tiny-llama_dataset/or-farm_sharegpt.json
+    type: sharegpt
+  
+
+
+dataset_prepared_path:
+val_set_size: 0.2
+output_dir: ./SmolLM-Ora
+auto_resume_from_checkpoints: false
+
+sequence_len: 2048
+sample_packing: true
+chat_template: chatml
+
+wandb_project: SmolLM-Ora
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 10
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: linear
+weight_decay: 0.0000001
+learning_rate: 0.0001
+lr_scheduler_kwargs:
+  #  num_cycles: 3 
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+eval_sample_packing: False
+
+warmup_steps: 50
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 4
+debug:
+deepspeed:
+
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  pad_token: "<|endoftext|>"
+```
+
+</details><br>
+
+# SmolLM-Ora
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8298
+
+## 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: 10
+- eval_batch_size: 10
+- seed: 122887
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0131        | 0.01  | 1    | 1.0419          |
+| 0.9727        | 0.25  | 27   | 0.9962          |
+| 0.953         | 0.5   | 54   | 0.9076          |
+| 0.8494        | 0.75  | 81   | 0.8792          |
+| 0.9297        | 1.0   | 108  | 0.8632          |
+| 0.8801        | 1.22  | 135  | 0.8527          |
+| 0.8133        | 1.47  | 162  | 0.8459          |
+| 0.8342        | 1.72  | 189  | 0.8410          |
+| 0.8973        | 1.97  | 216  | 0.8376          |
+| 0.7731        | 2.19  | 243  | 0.8350          |
+| 0.8207        | 2.44  | 270  | 0.8332          |
+| 0.7963        | 2.69  | 297  | 0.8318          |
+| 0.81          | 2.94  | 324  | 0.8309          |
+| 0.8351        | 3.18  | 351  | 0.8302          |
+| 0.8104        | 3.43  | 378  | 0.8299          |
+| 0.9019        | 3.68  | 405  | 0.8298          |
+| 0.7828        | 3.93  | 432  | 0.8298          |
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/media/renfroe/llms/SmolLM-360M/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4c4e27aed572f746ea9e5165537830a1a34172b0e806809671ed800938fd4a
+size 723739989

special_tokens_map.json

@@ -0,0 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,172 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_fast": true,
+  "vocab_size": 49152
+}