End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,212 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: unsloth/Qwen2-0.5B
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 0a09ee27-b445-4cd3-9165-f21d11b7aed2
+  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
+adapter: lora
+base_model: unsloth/Qwen2-0.5B
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 40527198fd7180da_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/40527198fd7180da_train_data.json
+  type:
+    field_input: bodies
+    field_instruction: decl
+    field_output: desc
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 3
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 500
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: true
+hub_model_id: kk-aivio/0a09ee27-b445-4cd3-9165-f21d11b7aed2
+hub_strategy: end
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 50
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: constant
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 26961
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/40527198fd7180da_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 10
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 500
+saves_per_epoch: null
+sequence_len: 512
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: a88f056a-2840-48ca-ada7-c0aa6accc543
+wandb_project: SN56-11
+wandb_run: your_name
+wandb_runid: a88f056a-2840-48ca-ada7-c0aa6accc543
+warmup_steps: 50
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 0a09ee27-b445-4cd3-9165-f21d11b7aed2
+
+This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7987
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 50
+- training_steps: 26961
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| No log        | 0.0000 | 1     | 3.3424          |
+| 2.1995        | 0.0155 | 500   | 2.2708          |
+| 2.2108        | 0.0309 | 1000  | 2.2152          |
+| 2.1032        | 0.0464 | 1500  | 2.1619          |
+| 2.0713        | 0.0618 | 2000  | 2.1323          |
+| 2.0045        | 0.0773 | 2500  | 2.1248          |
+| 2.0501        | 0.0927 | 3000  | 2.0747          |
+| 2.0731        | 0.1082 | 3500  | 2.0585          |
+| 1.9948        | 0.1237 | 4000  | 2.0393          |
+| 2.0056        | 0.1391 | 4500  | 2.0268          |
+| 1.9357        | 0.1546 | 5000  | 2.0100          |
+| 1.9762        | 0.1700 | 5500  | 2.0064          |
+| 1.9652        | 0.1855 | 6000  | 2.0130          |
+| 1.9825        | 0.2009 | 6500  | 1.9832          |
+| 1.9862        | 0.2164 | 7000  | 1.9895          |
+| 1.9041        | 0.2318 | 7500  | 1.9636          |
+| 1.9515        | 0.2473 | 8000  | 1.9703          |
+| 1.9021        | 0.2628 | 8500  | 1.9595          |
+| 1.9045        | 0.2782 | 9000  | 1.9328          |
+| 1.9421        | 0.2937 | 9500  | 1.9335          |
+| 1.9514        | 0.3091 | 10000 | 1.9253          |
+| 1.9284        | 0.3246 | 10500 | 1.9102          |
+| 1.8786        | 0.3400 | 11000 | 1.9036          |
+| 1.9155        | 0.3555 | 11500 | 1.9042          |
+| 1.9281        | 0.3710 | 12000 | 1.8976          |
+| 1.9146        | 0.3864 | 12500 | 1.8951          |
+| 1.8653        | 0.4019 | 13000 | 1.8863          |
+| 1.8602        | 0.4173 | 13500 | 1.8874          |
+| 1.9072        | 0.4328 | 14000 | 1.8690          |
+| 1.9027        | 0.4482 | 14500 | 1.8718          |
+| 1.8846        | 0.4637 | 15000 | 1.8672          |
+| 1.867         | 0.4791 | 15500 | 1.8722          |
+| 1.8286        | 0.4946 | 16000 | 1.8667          |
+| 1.8683        | 0.5101 | 16500 | 1.8528          |
+| 1.888         | 0.5255 | 17000 | 1.8587          |
+| 1.9014        | 0.5410 | 17500 | 1.8616          |
+| 1.8694        | 0.5564 | 18000 | 1.8491          |
+| 1.8908        | 0.5719 | 18500 | 1.8610          |
+| 1.8868        | 0.5873 | 19000 | 1.8386          |
+| 1.8248        | 0.6028 | 19500 | 1.8407          |
+| 1.8243        | 0.6183 | 20000 | 1.8341          |
+| 1.8059        | 0.6337 | 20500 | 1.8354          |
+| 1.8845        | 0.6492 | 21000 | 1.8283          |
+| 1.8418        | 0.6646 | 21500 | 1.8234          |
+| 1.7949        | 0.6801 | 22000 | 1.8303          |
+| 1.7507        | 0.6955 | 22500 | 1.8166          |
+| 1.8184        | 0.7110 | 23000 | 1.8156          |
+| 1.7994        | 0.7265 | 23500 | 1.8180          |
+| 1.8035        | 0.7419 | 24000 | 1.8161          |
+| 1.7769        | 0.7574 | 24500 | 1.8010          |
+| 1.8879        | 0.7728 | 25000 | 1.8103          |
+| 1.7857        | 0.7883 | 25500 | 1.8180          |
+| 1.7394        | 0.8037 | 26000 | 1.8006          |
+| 1.8255        | 0.8192 | 26500 | 1.7987          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-0.5B",
+  "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": 64,
+  "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": [
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_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 sha256:1f9cbe7cb7219a4b3c3406a3d325538904ce8dda3e23fda4a11b050689dcadce
+size 70506570

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6f436cc37d003670fef6904bd65ea547a9fdd6d895250ee10fa498ffee7313
+size 70430032

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "unsloth/Qwen2-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "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,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
+size 11418456

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "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
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "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 %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c562f910816a21524ee327c96011bff951fee379a51abe9b9dba95a5831078
+size 6776