Upload folder using huggingface_hub

README.md

@@ -0,0 +1,186 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B
+tags:
+- generated_from_trainer
+model-index:
+- name: qwen-2.9.3-qwen2-0.5b
+  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: `0.4.1`
+```yaml
+base_model: Qwen/Qwen2-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# load_in_4bit: true
+
+chat_template: chatml
+datasets:
+  - path: /workspace/datasets/dolphin201-sharegpt2.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/SystemChat_filtered_sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/SystemChat_multilingual_sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  # - path: /workspace/datasets/SystemChat-2.0-Arabic/SystemChatArabic_sharegpt.jsonl
+  #   type: sharegpt
+  #   conversation: chatml
+  # - path: /workspace/datasets/dolphin-coder-translate-sharegpt2.jsonl
+  #   type: sharegpt
+  #   conversation: chatml
+  # - path: /workspace/datasets/dolphin-coder-codegen-sharegpt2.jsonl
+  #   type: sharegpt
+  #   conversation: chatml
+  # - path: /workspace/datasets/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
+  #   type: sharegpt
+  #   conversation: chatml
+  # - path: /workspace/datasets/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
+  #   type: sharegpt
+  #   conversation: chatml
+  - path: /workspace/datasets/not_samantha_norefusals.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/Orca-Math-resort-unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/agent_instruct_react_unfiltered.jsonl
+    type: sharegpt  
+    conversation: chatml
+  - path: /workspace/datasets/toolbench_instruct_j1s1_3k_unfiltered.jsonl
+    type: sharegpt  
+    conversation: chatml
+  - path: /workspace/datasets/toolbench_negative_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/toolbench_react_10p_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/toolbench_tflan_cot_30p_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/openhermes200k_unfiltered.jsonl
+    type: sharegpt 
+    conversation: chatml
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.03
+output_dir: ./qwen-2.9.3-qwen2-0.5b
+
+sequence_len: 16384
+sample_packing: true
+pad_to_sequence_len: true
+
+# adapter: qlora
+# lora_r: 16
+# lora_alpha: 32
+# lora_dropout: 0.05
+# lora_target_modules:
+#   - q_proj
+#   - k_proj
+#   - v_proj
+#   - o_proj
+#   - gate_proj
+#   - up_proj
+#   - down_proj
+
+wandb_project: 2.9.3-qwen-2.9.3-qwen2-0.5b
+# wandb_entity: oaaic
+# wandb_watch:
+# wandb_name:
+# wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_8bit
+lr_scheduler: cosine
+learning_rate: 1e-4
+# max_grad_norm: 1.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+logging_steps: 1
+flash_attention: true
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
+warmup_steps: 10
+# evals_per_epoch: 2
+saves_per_epoch: 2
+save_total_limit: 2
+weight_decay: 0.1
+special_tokens:
+  eos_token: <|im_end|>
+
+
+```
+
+</details><br>
+
+# qwen-2.9.3-qwen2-0.5b
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9401
+
+## 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: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0495        | 1.0147 | 1453 | 1.0261          |
+| 0.9052        | 2.0161 | 2908 | 0.9491          |
+| 0.8097        | 2.9693 | 4296 | 0.9401          |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.41.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9adccc59fd39ac70af1c269702fa727fc14840d6c6ddc60668e95b9478947294
+size 988097824

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "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": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}