Model save

.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 +1,196 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 3a48d94d-6406-4b11-a8fb-f42d50273305
+  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: Qwen/Qwen2-0.5B
+bf16: true
+chat_template: llama3
+data_processes: 54
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - b973d55f42cfe085_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/b973d55f42cfe085_train_data.json
+  type:
+    field_input: prediction_agent
+    field_instruction: id
+    field_output: text
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+distributed_training:
+  backend: nccl
+  multi_gpu: true
+  num_gpus: 2
+do_eval: true
+early_stopping_patience: 4
+eval_batch_size: 16
+eval_max_new_tokens: 128
+eval_steps: 150
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp:
+- full_shard
+fsdp_config:
+  backward_prefetch: BACKWARD_PRE
+  cpu_offload: false
+  forward_prefetch: false
+  mixed_precision: bf16
+  sharding_strategy: FULL_SHARD
+  use_orig_params: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+group_by_length: true
+hub_ignore_patterns:
+- README.md
+- config.json
+hub_model_id: cimol/3a48d94d-6406-4b11-a8fb-f42d50273305
+hub_repo: null
+hub_strategy: end
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 10
+lora_alpha: 128
+lora_dropout: 0.1
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 64
+lora_target_linear: true
+lr_scheduler: polynomial
+lr_scheduler_warmup_steps: 75
+max_grad_norm: 0.5
+max_memory:
+  0: 75GB
+  1: 75GB
+max_steps: 1950
+micro_batch_size: 16
+mlflow_experiment_name: /tmp/b973d55f42cfe085_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 4
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-8
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 300
+saves_per_epoch: null
+seed: 17333
+sequence_len: 1024
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+total_train_batch_size: 32
+train_batch_size: 32
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 0a4e6580-4386-4e34-a04e-7f6adebdf9f1
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 0a4e6580-4386-4e34-a04e-7f6adebdf9f1
+warmup_steps: 150
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 3a48d94d-6406-4b11-a8fb-f42d50273305
+
+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: 2.2988
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 17333
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-8
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_steps: 150
+- training_steps: 1950
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0016 | 1    | 2.6957          |
+| 2.2442        | 0.2381 | 150  | 2.4509          |
+| 2.2058        | 0.4762 | 300  | 2.3882          |
+| 2.1434        | 0.7143 | 450  | 2.3595          |
+| 2.0915        | 0.9524 | 600  | 2.3382          |
+| 2.2356        | 1.1905 | 750  | 2.3310          |
+| 2.2304        | 1.4286 | 900  | 2.3187          |
+| 2.167         | 1.6667 | 1050 | 2.3100          |
+| 2.1963        | 1.9048 | 1200 | 2.2987          |
+| 2.1883        | 2.1429 | 1350 | 2.3045          |
+| 2.2211        | 2.3810 | 1500 | 2.3047          |
+| 2.217         | 2.6190 | 1650 | 2.2979          |
+| 2.2194        | 2.8571 | 1800 | 2.2953          |
+| 2.2695        | 3.0952 | 1950 | 2.2988          |
+
+
+### 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": "Qwen/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": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061eb2227e17fdcbaedaaa4e8d2643da7775abcd7828d0490bc9b74de8270ed9
+size 140815952

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/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,
+  "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",
+  "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": "<|endoftext|>",
+    "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:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

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 %}{% 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": "<|endoftext|>",
+  "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:b1fdec8aff630bba200672586e9292b7988673140f4c784d0c8f42f4b173d53b
+size 7032