Update README.md

README.md

@@ -8,242 +8,4 @@ model-index:
 - name: marigold-fft
   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: `0.8.0.dev0`
-```yaml
-base_model: Qwen/Qwen2.5-32B
-model_type: AutoModelForCausalLM
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-chat_template: jinja
-chat_template_jinja: "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- if messages[0]['role'] == 'system' %}{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}{%- elif message.role == \"assistant\" %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}"
-datasets:
-  # Continued pretrain: novels, short stories
-  - path: datasets/Sugarquill10k_Clean.jsonl
-    type: completion
-  - path: datasets/Mixed-Novels-Completions.jsonl
-    type: completion
-  - path: datasets/Mixed-Novels-Completions-2.jsonl
-    type: completion
-  - path: datasets/recursal-scp-8k-filtered-4k.jsonl
-    type: completion
-  # overfitting on disco elysium
-  - path: datasets/disco.jsonl
-    type: completion
-  - path: datasets/disco-chat.json
-    type: completion
-
-  # Instruct datasets (local)
-  - path: datasets/competition-math-sharegpt.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/systemchat-1k-sharegpt.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/opencai_rp_sharegpt.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/floyd-instruct-8k.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/woke-identity.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/Claude-Sonnet35-Charcard-Unslop-v2.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/kalo-opus-22k-unslop.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/gryphe-4o-WP-sharegpt-cleaned.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/discord-logs-cleaned-sharegpt.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/creative-writing-multiturn-16k.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/limo-sharegpt.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/tot-bio-2k-subset-sharegpt.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/gpqa-benchmaxxing.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/UBW_Tapestries.json
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-  - path: datasets/medical-o1-reasoning-default-sys.jsonl
-    type: chat_template
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-
-shuffle_merged_datasets: true
-
-special_tokens:
-  eos_token: "<|im_end|>"
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.02
-output_dir: ./marigold-fft
-
-sequence_len: 10240 # could try 10240 too?
-sample_packing: true
-eval_sample_packing: false
-pad_to_sequence_len: true
-
-gradient_accumulation_steps: 8
-micro_batch_size: 1
-num_epochs: 3
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 5e-5
-
-weight_decay: 0.1
-max_grad_norm: 3
-
-train_on_inputs: false
-group_by_length: false
-bf16: auto
-fp16:
-tf32: false
-
-gradient_checkpointing: unsloth
-gradient_checkpointing_kwargs:
-  use_reentrant: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_ratio: 0.05
-evals_per_epoch: 4
-eval_table_size:
-
-saves_per_epoch: 4
-save_total_limit: 5
-
-debug:
-
-plugins:
-  - axolotl.integrations.liger.LigerPlugin
-liger_rope: true
-liger_rms_norm: true
-liger_glu_activation: true
-liger_layer_norm: true
-liger_fused_linear_cross_entropy: true
-
-deepspeed: deepspeed_configs/zero3_bf16.json # multigpu only, maybe zero3_bf16_cpuoffload_params if OOM
-
-wandb_project: Qwen2.5-32B-Marigold-v0
-wandb_entity:
-wandb_name: Marigold-v0-fft
-
-```
-
-</details><br>
-
-# marigold-fft
-
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the (insert datasets here) datasets.
-It achieves the following results on the evaluation set:
-- Loss: 2.2256
-
-## 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: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 8
-- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 27
-- num_epochs: 3.0
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 2.0226        | 0.0054 | 1    | 3.5764          |
-| 1.8588        | 0.2522 | 47   | 2.2616          |
-| 1.7952        | 0.5044 | 94   | 2.1989          |
-| 1.8266        | 0.7565 | 141  | 2.1619          |
-| 1.5997        | 1.0107 | 188  | 2.1603          |
-| 1.5134        | 1.2629 | 235  | 2.1552          |
-| 1.4614        | 1.5151 | 282  | 2.1373          |
-| 1.6362        | 1.7673 | 329  | 2.1242          |
-| 1.1374        | 2.0215 | 376  | 2.2327          |
-| 1.2301        | 2.2736 | 423  | 2.2244          |
-| 1.1773        | 2.5258 | 470  | 2.2257          |
-| 1.1864        | 2.7780 | 517  | 2.2256          |
-
-
-### Framework versions
-
-- Transformers 4.49.0
-- Pytorch 2.5.1+cu124
-- Datasets 3.2.0
-- Tokenizers 0.21.0
+# Qwen2.5-32B-Marigold-v1-ep3