24/08/16 Initial Commit

README.md

@@ -1,3 +1,79 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: keeeeenw/MicroLlama
+tags:
+- generated_from_trainer
+model-index:
+- name: MicroLlama_305M_stage1
+  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)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/momorami-kaist/medusa_test/runs/3ou8zlhf)
+# MicroLlama_305M_stage1
+
+This model is a fine-tuned version of [keeeeenw/MicroLlama](https://huggingface.co/keeeeenw/MicroLlama) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9645
+
+## 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: 0.0005
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.0309        | 0.0242 | 40   | 3.0794          |
+| 3.0295        | 0.0483 | 80   | 2.9479          |
+| 2.8731        | 0.0725 | 120  | 2.9168          |
+| 2.8009        | 0.0966 | 160  | 2.9328          |
+| 2.9132        | 0.1208 | 200  | 2.9119          |
+| 2.7718        | 0.1449 | 240  | 2.8891          |
+| 2.884         | 0.1691 | 280  | 2.8912          |
+| 2.7161        | 0.1932 | 320  | 2.8810          |
+| 2.6438        | 0.2174 | 360  | 2.8815          |
+| 2.6152        | 0.2415 | 400  | 2.8896          |
+| 2.7979        | 0.2657 | 440  | 2.8809          |
+| 2.7002        | 0.2899 | 480  | 2.8611          |
+| 2.6969        | 0.3140 | 520  | 2.8598          |
+| 2.8914        | 0.3382 | 560  | 2.8694          |
+| 2.7377        | 0.3623 | 600  | 2.8479          |
+| 2.7575        | 0.3865 | 640  | 2.8544          |
+| 2.8079        | 0.4106 | 680  | 2.8756          |
+| 3.2421        | 0.4348 | 720  | 2.9645          |
+
+
+### Framework versions
+
+- Transformers 4.43.0
+- Pytorch 2.3.1
+- Datasets 2.15.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "keeeeenw/MicroLlama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "medusa_num_heads": 4,
+  "medusa_num_layers": 1,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "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": "bfloat16",
+  "transformers_version": "4.43.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05bd9032388dd9907eb54ae31488e88ebee115128bedc7b086671d1991323aa
+size 879828432

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caae61e64640d554cf284b55ffaac33450b791b06cec745ff52ed3de666a0ecf
+size 271108660

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3edaa40748ca2f1db06ce3d4081be5b7f0f7caf22c32d24b9ed70cfa1efdb77
+size 879855990

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29706500f8fe69aa61a62e9f1c542da177090efb816b613770204adcd5cc04b0
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,43 @@
+{
+  "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>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "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 sha256:62c5aaac84a29e9b64e2a8c76ee66b8c53b521633219d795aed9292df981e6d1
+size 5560