Upload folder using huggingface_hub

README.md

@@ -0,0 +1,53 @@
+---
+library_name: peft
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+license: apache-2.0
+tags:
+  - lora
+  - qwen2.5
+  - avito
+  - validation
+  - classification
+language:
+  - ru
+---
+
+# Avito Validation LoRA Adapter
+
+LoRA адаптер для валидации объявлений Avito, обученный на базе Qwen2.5-1.5B-Instruct.
+
+## Model Details
+
+- **Base Model:** [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
+- **LoRA Rank (r):** 16
+- **LoRA Alpha:** 32
+- **LoRA Dropout:** 0.05
+- **Target Modules:** q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+- **Task Type:** CAUSAL_LM
+- **Training:** Fine-tuned on Fireworks.ai (December 2024)
+
+## Training Stats
+
+- **Epochs:** 2
+- **Steps:** 3,333
+- **Training Sequences:** 34,672
+- **Training Tokens:** ~101M
+- **Final Loss:** 0.125
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "Stepan222/avito-validation-lora")
+```
+
+## License
+
+Apache 2.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ae41b9645c1b209e5c472dba01a6f60eba0f8746488e5ce44a76c86dcbb8a7
+size 36981856

stats.json

@@ -0,0 +1 @@
+{"world_size": 1, "epochs": 2, "steps": 3333, "seqs": 34672, "tokens": 101258180, "last_epoch_steps": 0, "last_epoch_seqs": 0, "last_epoch_tokens": 0, "total_seqs": 17336, "nan_in_loss_seqs": 0, "experiment_tracking_run_id": null, "loss_ema": 0.166393037497039, "loss_sum": 9.550168424844742, "mtp_loss_ema": 0, "mtp_loss_sum": 0, "eval_losses_avg": [0.2669239677488804, 0.2087830863893032, 0.18562059849500656, 0.17422222346067429, 0.16747690364718437, 0.16181137412786484, 0.15829269029200077, 0.15605521947145462, 0.15283420123159885, 0.1499126348644495, 0.14830303378403187, 0.14638864435255527, 0.1452154479920864, 0.1440908331423998, 0.14218942821025848, 0.1416184939444065, 0.14071348309516907, 0.13887083530426025, 0.13866095431149006, 0.13731765188276768, 0.13701613806188107, 0.1358004603534937, 0.13419232331216335, 0.1340783443301916, 0.13359127007424831, 0.13340670242905617, 0.13154898025095463, 0.13112467527389526, 0.12966893799602985, 0.1300010159611702, 0.12925688736140728, 0.1286165565252304, 0.12809292040765285, 0.12784288451075554, 0.1277215015143156, 0.12710174918174744, 0.12699639797210693, 0.12620864622294903, 0.12637895718216896, 0.1255951076745987, 0.12555144913494587, 0.12513052485883236]}

train_config.json

@@ -0,0 +1 @@
+{"comet": false, "comet_api_key": null, "comet_workspace": null, "comet_project": null, "comet_run_id": "cifqwmbd", "wandb": false, "wandb_api_key": null, "wandb_entity": null, "wandb_project": null, "wandb_run_id": "cifqwmbd", "base_model_dir": "/llm-downloader-destination/base/fireworks/qwen2p5-1p5b-instruct/hf", "output_model_dir": "gs://fireworks-artifacts-resource-kb1orm3qomz-bdc607/tuned-model-cifqwmbd/ca474e/avito-validation-20251206-172226/checkpoint", "checkpoint_dir": "/dev/shm/checkpoints", "gcs_checkpoint_dir": "gs://fireworks-artifacts-resource-kb1orm3qomz-bdc607/tuned-model-cifqwmbd/ca474e/avito-validation-20251206-172226/checkpoints/checkpoints", "max_checkpoints_to_keep": 1, "checkpoint_interval": 3600, "save_final_checkpoint": false, "train": true, "learning_rate": 1e-05, "learning_rate_warmup_steps": 0, "grad_accum_steps": 1, "correct_grad_accum_loss": false, "epochs": 2, "early_stop": false, "seed": 42, "dataset_dir": "/mnt/staging/dataset", "eval_auto_carveout": true, "eval_dataset_dir": null, "train_limit": null, "max_context_len": 32768, "batch_size": 32768, "max_data_workers": 0, "min_evals_per_epoch": 4, "precision": null, "status_file": "gs://fireworks-fine-tuning-job-status/sftj-resource-kb1orm3qomz-cifqwmbd-d2b26ffc-2c64-4df2-ad05-0855d9c254e0", "billing_file": "gs://fireworks-fine-tuning-metadata/sftj-resource-kb1orm3qomz-cifqwmbd/billing-d2b26ffc-2c64-4df2-ad05-0855d9c254e0", "metrics_file": "gs://fireworks-fine-tuning-metadata/sftj-resource-kb1orm3qomz-cifqwmbd/metrics.jsonl", "profile": null, "weight_sharding": null, "activation_sharding": null, "empty_weights": false, "nan_ratio_threshold": 0.05, "fast_api_port": 80, "optimizer": "adamw", "target_shard_size_gb": null, "peft_addon_dir": null, "lora_rank": 16, "lora_dropout": 0.05, "template_kind": "conversation", "template": null, "eval_train_ratio": 0.02, "mtp_config": {"enable_mtp": false, "freeze_base_model": false, "num_draft_tokens": 1}, "qat": true, "kld": false, "teft_tokens": [], "skip_dataset_filtering": false}