Upload folder using huggingface_hub

README.md

@@ -0,0 +1,205 @@
+---
+license: apache-2.0
+base_model: h2oai/h2o-danube3-500m-base
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: clite7-500m-test-ckpts
+  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
+# Weights and Biases logging config
+wandb_project: clite
+wandb_entity:
+wandb_watch:
+wandb_name: v7
+wandb_log_model:
+
+# Model architecture config
+base_model: h2oai/h2o-danube3-500m-base
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: anthropic
+
+# Hugging Face saving config
+hub_model_id:
+hub_strategy:
+push_dataset_to_hub:
+hf_use_auth_token:
+
+# Model checkpointing config
+output_dir: ./lora-out
+resume_from_checkpoint:
+save_steps:
+saves_per_epoch: 5
+save_safetensors: true
+save_total_limit: 2
+
+# Mixed precision training config
+bf16: true
+fp16: false
+tf32: false
+
+# Model loading config
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+# Sequence config
+sequence_len: 8192
+s2_attention: false
+sample_packing: true
+eval_sample_packing: true
+pad_to_sequence_len: true
+train_on_inputs: true
+group_by_length: false
+
+# Dataset config
+datasets:
+    - path: kalomaze/Opus_Instruct_3k
+      type: chat_template
+val_set_size: 0.1
+evaluation_strategy:
+eval_steps:
+evals_per_epoch: 10
+test_datasets:
+dataset_prepared_path: ./last-preped-dataset
+shuffle_merged_datasets: true
+
+# Training hyperparameters
+num_epochs: 3
+gradient_accumulation_steps: 2
+micro_batch_size: 8
+eval_batch_size: 8
+warmup_steps: 10
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.00004
+cosine_min_lr_ratio: 0.1
+weight_decay: 0.1
+max_grad_norm: 1
+logging_steps: 1
+
+# Model optimization
+gradient_checkpointing: unsloth
+xformers_attention: false
+flash_attention: true
+sdp_attention: false
+unsloth_cross_entropy_loss: false
+unsloth_lora_mlp: false
+unsloth_lora_qkv: false
+unsloth_lora_o: false
+
+# Loss monitoring config
+early_stopping_patience: false
+loss_watchdog_threshold: 100.0
+loss_watchdog_patience: 3
+
+# Debug config
+debug: true
+seed: 02496
+
+# DeepSpeed and FSDP config
+deepspeed:
+fsdp:
+fsdp_config:
+
+# Token config
+special_tokens:
+tokens: # these are delimiters
+  - "<EOT>"
+
+# Checkpoint backing up
+hub_model_id: Fizzarolli/clite7-500m-test-ckpts
+hub_strategy: all_checkpoints
+
+```
+
+</details><br>
+
+[<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/ruthenic/clite/runs/diil6zl9)
+# clite7-500m-test-ckpts
+
+This model is a fine-tuned version of [h2oai/h2o-danube3-500m-base](https://huggingface.co/h2oai/h2o-danube3-500m-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3765
+
+## 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: 4e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 2496
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.9517        | 0.0952 | 1    | 3.7616          |
+| 2.9796        | 0.1905 | 2    | 3.6462          |
+| 2.9632        | 0.2857 | 3    | 3.3357          |
+| 2.6639        | 0.3810 | 4    | 3.0408          |
+| 2.5048        | 0.4762 | 5    | 2.7322          |
+| 2.4911        | 0.5714 | 6    | 2.5094          |
+| 2.1291        | 0.6667 | 7    | 2.3554          |
+| 4.8452        | 0.7619 | 8    | 1.6418          |
+| 1.6902        | 0.8571 | 9    | 1.6067          |
+| 1.6166        | 0.9524 | 10   | 1.5581          |
+| 1.5985        | 1.0476 | 11   | 1.5162          |
+| 1.5001        | 1.0476 | 12   | 1.4847          |
+| 1.4679        | 1.1429 | 13   | 1.4601          |
+| 1.4981        | 1.2381 | 14   | 1.4440          |
+| 1.4864        | 1.3333 | 15   | 1.4293          |
+| 1.4895        | 1.4286 | 16   | 1.4174          |
+| 1.4653        | 1.5238 | 17   | 1.4061          |
+| 1.4447        | 1.6190 | 18   | 1.3988          |
+| 1.4492        | 1.7143 | 19   | 1.3937          |
+| 1.4244        | 1.8095 | 20   | 1.3896          |
+| 1.4319        | 1.9048 | 21   | 1.3858          |
+| 1.4238        | 2.0    | 22   | 1.3830          |
+| 1.4725        | 2.0952 | 23   | 1.3810          |
+| 1.3862        | 2.0952 | 24   | 1.3794          |
+| 1.3526        | 2.1905 | 25   | 1.3783          |
+| 1.4134        | 2.2857 | 26   | 1.3776          |
+| 1.3909        | 2.3810 | 27   | 1.3771          |
+| 1.4016        | 2.4762 | 28   | 1.3769          |
+| 1.3494        | 2.5714 | 29   | 1.3766          |
+| 1.3783        | 2.6667 | 30   | 1.3765          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<EOT>": 32000
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "h2oai/h2o-danube3-500m-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f9c1a0f0665bbb5658e21b8d90c114539fc5169afe3150f1150eeed36ba44b
+size 1027204400

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '\n\nHuman: ' + message['content'].strip() + '\n\nAssistant: '}}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() + '<EOT>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853c07866dba1e272478b1e6ffec8ed072f5273d861bb651dea6f6a946625a88
+size 6072