Model save

README.md

@@ -0,0 +1,184 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: Mistral-7B-v0.1-q-sparse-fineweb-edu-table2-re
+  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: `0.5.2`
+```yaml
+base_model: mistralai/Mistral-7B-v0.1
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+tokenizer_use_fast: false
+resize_token_embeddings_to_32x: false
+
+flash_attention: true
+xformers_attention:
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: skymizer/Mistral-7B-v0.1-base-tokenized-fineweb-edu-45B-4096
+    train_on_split: train
+    type: completion
+
+test_datasets:
+  - path: skymizer/Mistral-7B-v0.1-base-tokenized-fineweb-edu-test-4K
+    split: test
+    type: completion
+
+is_preprocess: true
+skip_prepare_dataset: true
+
+dataset_prepared_path:
+
+hf_use_auth_token: true
+output_dir: /mnt/home/model-team/models/Mistral-7B-v0.1-q-sparse-fineweb-edu-table2-re
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true
+
+sequence_len: 4096
+sample_packing: true
+sample_packing_group_size: 100000
+sample_packing_bin_size: 200
+pad_to_sequence_len: true
+
+eval_sample_packing: false
+# eval_causal_lm_metrics: ["perplexity"]
+
+wandb_project: "sparse-tuning-cpt"
+wandb_entity:
+wandb_watch:
+wandb_name: "Mistral-7B-v0.1-q-sparse-fineweb-edu-table2-re"
+wandb_log_model:
+
+# global batch size = 2 * 8 * 8 GPUs * 8 Nodes * 4096 = 4M
+gradient_accumulation_steps: 2
+micro_batch_size: 8
+eval_batch_size: 1
+max_steps: 10000
+optimizer: adamw_torch
+learning_rate: 0.00005
+lr_scheduler: cosine
+cosine_min_lr_ratio: 0.2 
+weight_decay: 0.01
+adam_beta1: 0.9
+adam_beta2: 0.95
+adam_eps: 0.000001
+max_grad_norm: 2.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: false
+
+hub_model_id: "skymizer/Mistral-7B-v0.1-q-sparse-fineweb-edu-table2-re"
+
+save_strategy: "steps"
+save_steps: 500
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+local_rank:
+logging_steps: 1
+
+warmup_steps: 375
+eval_steps: 500
+eval_table_size:
+debug:
+deepspeed: /root/train/axolotl/deepspeed_configs/zero3_bf16.json
+fsdp:
+fsdp_config:
+seed: 42
+
+```
+
+</details><br>
+
+# Mistral-7B-v0.1-q-sparse-fineweb-edu-table2-re
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9784
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 1024
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 375
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 11.1526       | 0.0001 | 1     | 11.1178         |
+| 3.9513        | 0.0408 | 500   | 3.7699          |
+| 3.4469        | 0.0817 | 1000  | 3.2772          |
+| 3.1993        | 0.1225 | 1500  | 3.0024          |
+| 2.8081        | 0.1633 | 2000  | 2.7218          |
+| 2.5217        | 0.2042 | 2500  | 2.4860          |
+| 2.3993        | 0.2450 | 3000  | 2.3570          |
+| 2.2919        | 0.2858 | 3500  | 2.2761          |
+| 2.2379        | 0.3267 | 4000  | 2.2180          |
+| 2.2047        | 0.3675 | 4500  | 2.1721          |
+| 2.1553        | 0.4083 | 5000  | 2.1367          |
+| 2.1279        | 0.4491 | 5500  | 2.1066          |
+| 2.0689        | 0.4900 | 6000  | 2.0822          |
+| 2.0702        | 0.5308 | 6500  | 2.0608          |
+| 2.0611        | 0.5716 | 7000  | 2.0425          |
+| 2.0242        | 0.6125 | 7500  | 2.0264          |
+| 2.0449        | 0.6533 | 8000  | 2.0140          |
+| 2.0245        | 0.6941 | 8500  | 2.0025          |
+| 2.0107        | 0.7350 | 9000  | 1.9933          |
+| 1.9995        | 0.7758 | 9500  | 1.9851          |
+| 1.9995        | 0.8166 | 10000 | 1.9784          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}