Duplicate from mrcuddle/Tiny-Darkllama3.2-1B-Instruct

Co-authored-by: T.Ph <mrcuddle@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,142 @@
+---
+library_name: transformers
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- ChaoticNeutrals/Luminous_Opus
+- ChaoticNeutrals/Synthetic-Dark-RP
+- ChaoticNeutrals/Synthetic-RP
+model-index:
+- name: Tiny-Darkllama3.2-1B-Instruct
+  results: []
+base_model:
+- unsloth/Llama-3.2-1B
+---
+
+<!-- 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: `0.6.0`
+```yaml
+base_model: unsloth/Llama-3.2-1B
+bf16: false
+dataset_prepared_path: last_run_prepared
+datasets:
+- chat_template: alpaca
+  field_messages: conversations
+  message_field_content: value
+  message_field_role: from
+  path: ChaoticNeutrals/Luminous_Opus
+  split: train
+  type: chat_template
+debug: null
+deepspeed: null
+early_stopping_patience: null
+evals_per_epoch: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: mrcuddle/Tiny-Darkllama3.2-1B-Instruct
+is_llama_derived_model: true
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lr_scheduler: linear
+max_steps: 20
+micro_batch_size: 1
+mlflow_experiment_name: colab-example
+model_type: LlamaForCausalLM
+num_epochs: 4
+optimizer: adamw_torch
+output_dir: ./llama2
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+sample_packing: true
+saves_per_epoch: null
+sequence_len: 1096
+special_tokens: null
+strict: false
+tf32: false
+tokenizer_type: LlamaTokenizer
+train_on_inputs: false
+wandb_entity: null
+wandb_log_model: null
+wandb_name: null
+wandb_project: null
+wandb_watch: null
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# Tiny-Darkllama3.2-1B-Instruct
+
+This model was trained from unsloth/Llama-3.2-1B on the ChaoticNeutrals/Luminous_Opus, Synthetic-Dark-RP, Synthetic-RP datasets.
+
+
+
+
+## Training and evaluation data
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 20
+
+### Training results
+[2025-02-11 13:09:27,300] [INFO] [axolotl.train.train:173] [PID:7240] [RANK:0] Starting trainer...
+[2025-02-11 13:09:27,706] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:203] [PID:7240] [RANK:0] gather_len_batches: [35]
+[2025-02-11 13:09:27,761] [INFO] [axolotl.callbacks.on_train_begin:39] [PID:7240] [RANK:0] The Axolotl config has been saved to the MLflow artifacts.
+{'loss': 3.4922, 'grad_norm': 9.877531051635742, 'learning_rate': 2e-05, 'epoch': 0.03}
+  5% 1/20 [00:02<00:37,  1.98s/it][2025-02-11 13:09:31,221] [INFO] [axolotl.callbacks.on_step_end:127] [PID:7240] [RANK:0] cuda memory usage while training: 12.320GB (+8.604GB cache, +0.565GB misc)
+{'loss': 3.3057, 'grad_norm': 11.661816596984863, 'learning_rate': 4e-05, 'epoch': 0.06}
+{'loss': 2.4733, 'grad_norm': 8.751928329467773, 'learning_rate': 6e-05, 'epoch': 0.09}
+{'loss': 2.9842, 'grad_norm': 10.503549575805664, 'learning_rate': 8e-05, 'epoch': 0.11}
+{'loss': 2.6624, 'grad_norm': 12.645892143249512, 'learning_rate': 0.0001, 'epoch': 0.14}
+{'loss': 2.7616, 'grad_norm': 10.691230773925781, 'learning_rate': 0.00012, 'epoch': 0.17}
+{'loss': 2.9891, 'grad_norm': 10.076760292053223, 'learning_rate': 0.00014, 'epoch': 0.2}
+{'loss': 2.3745, 'grad_norm': 10.034379959106445, 'learning_rate': 0.00016, 'epoch': 0.23}
+{'loss': 2.4965, 'grad_norm': 9.778562545776367, 'learning_rate': 0.00018, 'epoch': 0.26}
+{'loss': 2.3811, 'grad_norm': 19.146963119506836, 'learning_rate': 0.0002, 'epoch': 0.29}
+{'loss': 3.3611, 'grad_norm': 14.556534767150879, 'learning_rate': 0.00018, 'epoch': 0.31}
+{'loss': 2.9619, 'grad_norm': 16.88424301147461, 'learning_rate': 0.00016, 'epoch': 0.34}
+{'loss': 2.121, 'grad_norm': 9.94941520690918, 'learning_rate': 0.00014, 'epoch': 0.37}
+{'loss': 2.1042, 'grad_norm': 23.178285598754883, 'learning_rate': 0.00012, 'epoch': 0.4}
+{'loss': 2.4722, 'grad_norm': 10.403461456298828, 'learning_rate': 0.0001, 'epoch': 0.43}
+{'loss': 2.7434, 'grad_norm': 11.339975357055664, 'learning_rate': 8e-05, 'epoch': 0.46}
+{'loss': 2.2349, 'grad_norm': 202.98793029785156, 'learning_rate': 6e-05, 'epoch': 0.49}
+{'loss': 2.3479, 'grad_norm': 10.250885009765625, 'learning_rate': 4e-05, 'epoch': 0.51}
+{'loss': 2.4169, 'grad_norm': 14.021651268005371, 'learning_rate': 2e-05, 'epoch': 0.54}
+{'loss': 3.4686, 'grad_norm': 10.988056182861328, 'learning_rate': 0.0, 'epoch': 0.57}
+{'train_runtime': 172.0118, 'train_samples_per_second': 0.116, 'train_steps_per_second': 0.116, 'train_loss': 2.707640600204468, 'epoch': 0.57}
+100% 20/20 [02:52<00:00,  8.65s/it]
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/content/llama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d120c445cb612d9e4cc306e08393ba4a66b2c9acaa4fc13dd39646d36ad365
+size 4400216536

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5334bfecc5b1bc05f0b6cb6a33df6952dc00c2aeea3f7ead036553759a4a1b0
+size 6520