End of training

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 94bee815-bb95-47e6-835f-ad38135a2860
+  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: samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306
+bf16: auto
+chat_template: llama3
+dataloader_num_workers: 8
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 4b98334ce710802c_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/
+  type:
+    field_input: input
+    field_instruction: instruct
+    field_output: output
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: cimol/94bee815-bb95-47e6-835f-ad38135a2860
+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: 1
+lora_alpha: 32
+lora_dropout: 0.15
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+loraplus_lr_embedding: 1.0e-06
+loraplus_lr_ratio: 16
+lr_scheduler: cosine
+max_grad_norm: 1
+max_steps: 100
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/4b98334ce710802c_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 20
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.999
+  adam_epsilon: 1e-8
+optimizer: adamw_torch_fused
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+saves_per_epoch: 5
+sequence_len: 1024
+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: 859088c3-5caa-40f5-84fd-490d89cece7b
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 859088c3-5caa-40f5-84fd-490d89cece7b
+warmup_steps: 150
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 94bee815-bb95-47e6-835f-ad38135a2860
+
+This model is a fine-tuned version of [samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306](https://huggingface.co/samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9920
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 150
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7732        | 0.0001 | 1    | 0.9834          |
+| 1.1379        | 0.0002 | 2    | 0.9834          |
+| 0.9396        | 0.0004 | 4    | 0.9834          |
+| 0.9896        | 0.0005 | 6    | 0.9834          |
+| 0.8178        | 0.0007 | 8    | 0.9834          |
+| 0.9894        | 0.0009 | 10   | 0.9834          |
+| 1.9155        | 0.0011 | 12   | 0.9834          |
+| 1.0269        | 0.0012 | 14   | 0.9835          |
+| 0.7556        | 0.0014 | 16   | 0.9836          |
+| 0.8767        | 0.0016 | 18   | 0.9838          |
+| 1.1682        | 0.0018 | 20   | 0.9840          |
+| 0.764         | 0.0020 | 22   | 0.9842          |
+| 1.1331        | 0.0021 | 24   | 0.9845          |
+| 0.868         | 0.0023 | 26   | 0.9848          |
+| 0.7687        | 0.0025 | 28   | 0.9851          |
+| 0.9999        | 0.0027 | 30   | 0.9855          |
+| 0.649         | 0.0029 | 32   | 0.9861          |
+| 1.2312        | 0.0030 | 34   | 0.9865          |
+| 0.6942        | 0.0032 | 36   | 0.9870          |
+| 0.8366        | 0.0034 | 38   | 0.9875          |
+| 0.7883        | 0.0036 | 40   | 0.9879          |
+| 0.7254        | 0.0037 | 42   | 0.9882          |
+| 0.9824        | 0.0039 | 44   | 0.9882          |
+| 0.692         | 0.0041 | 46   | 0.9884          |
+| 0.7093        | 0.0043 | 48   | 0.9886          |
+| 0.897         | 0.0045 | 50   | 0.9885          |
+| 0.549         | 0.0046 | 52   | 0.9886          |
+| 0.7148        | 0.0048 | 54   | 0.9887          |
+| 1.327         | 0.0050 | 56   | 0.9888          |
+| 1.0484        | 0.0052 | 58   | 0.9890          |
+| 1.1284        | 0.0053 | 60   | 0.9892          |
+| 0.653         | 0.0055 | 62   | 0.9894          |
+| 0.8266        | 0.0057 | 64   | 0.9896          |
+| 0.835         | 0.0059 | 66   | 0.9900          |
+| 0.7215        | 0.0061 | 68   | 0.9902          |
+| 0.9994        | 0.0062 | 70   | 0.9904          |
+| 1.0789        | 0.0064 | 72   | 0.9904          |
+| 0.7381        | 0.0066 | 74   | 0.9903          |
+| 0.8917        | 0.0068 | 76   | 0.9903          |
+| 0.9863        | 0.0070 | 78   | 0.9901          |
+| 0.8527        | 0.0071 | 80   | 0.9903          |
+| 0.878         | 0.0073 | 82   | 0.9903          |
+| 1.2412        | 0.0075 | 84   | 0.9904          |
+| 1.0756        | 0.0077 | 86   | 0.9904          |
+| 0.8945        | 0.0078 | 88   | 0.9905          |
+| 0.6819        | 0.0080 | 90   | 0.9902          |
+| 0.7676        | 0.0082 | 92   | 0.9901          |
+| 0.8783        | 0.0084 | 94   | 0.9904          |
+| 1.0132        | 0.0086 | 96   | 0.9907          |
+| 0.8469        | 0.0087 | 98   | 0.9913          |
+| 0.9485        | 0.0089 | 100  | 0.9920          |
+
+
+### 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": "samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306",
+  "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": 32,
+  "lora_dropout": 0.15,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "down_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 sha256:508235ea6da5e1da923b1ffdebc2af45fcd0e684e8552770d8fa9da41d1c9ae3
+size 96549898

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555ae280381a3ba2670ab4b7262b50dbef62ac87ac5b42b64b1ab4c078e5ed11
+size 96498736

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "samoline/5cf4792e-00af-4d5f-b922-4c7d5237f306",
+  "activation_function": "swiGLU",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "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": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "verbose": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1608a5321241e9a40a6e63304730324b0105623d214842c5fdc4e8c0efbc6b
+size 6840