Duplicate from YongkangZOU/evoxtral-lora

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,135 @@
+---
+library_name: peft
+base_model: mistralai/Voxtral-Mini-3B-2507
+tags:
+  - voxtral
+  - lora
+  - speech-recognition
+  - expressive-transcription
+  - audio
+  - mistral
+  - hackathon
+datasets:
+  - custom
+language:
+  - en
+license: apache-2.0
+pipeline_tag: automatic-speech-recognition
+---
+
+# Evoxtral LoRA — Expressive Tagged Transcription
+
+A LoRA adapter for [Voxtral-Mini-3B-2507](https://huggingface.co/mistralai/Voxtral-Mini-3B-2507) that produces transcriptions enriched with inline expressive audio tags from the [ElevenLabs v3 tag set](https://elevenlabs.io/docs/api-reference/text-to-speech).
+
+Built for the **Mistral AI Online Hackathon 2026** (W&B Fine-Tuning Track).
+
+## What It Does
+
+Standard ASR:
+> So I was thinking maybe we could try that new restaurant downtown. I mean if you're free this weekend.
+
+Evoxtral:
+> [nervous] So... [stammers] I was thinking maybe we could... [clears throat] try that new restaurant downtown? [laughs nervously] I mean, if you're free this weekend?
+
+## Evaluation Results
+
+| Metric | Base Voxtral | Evoxtral (finetuned) | Improvement |
+|--------|-------------|---------------------|-------------|
+| **WER** (Word Error Rate) | 6.64% | **4.47%** | 32.7% better |
+| **Tag F1** (Expressive Tag Accuracy) | 22.0% | **67.2%** | 3x better |
+
+Evaluated on 50 held-out test samples. The finetuned model dramatically improves expressive tag generation while also improving raw transcription accuracy.
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base model | `mistralai/Voxtral-Mini-3B-2507` |
+| Method | LoRA (PEFT) |
+| LoRA rank | 64 |
+| LoRA alpha | 128 |
+| LoRA dropout | 0.05 |
+| Target modules | q/k/v/o_proj, gate/up/down_proj, multi_modal_projector |
+| Learning rate | 2e-4 |
+| Scheduler | Cosine |
+| Epochs | 3 |
+| Batch size | 2 (effective 16 with grad accum 8) |
+| NEFTune noise alpha | 5.0 |
+| Precision | bf16 |
+| GPU | NVIDIA A10G (24GB) |
+| Training time | ~25 minutes |
+| Trainable params | 124.8M / 4.8B (2.6%) |
+
+## Dataset
+
+Custom synthetic dataset of 1,010 audio samples generated with ElevenLabs TTS v3:
+- **808** train / **101** validation / **101** test
+- Each sample has audio + tagged transcription with inline ElevenLabs v3 expressive tags
+- Tags include: `[sighs]`, `[laughs]`, `[whispers]`, `[nervous]`, `[frustrated]`, `[clears throat]`, `[pause]`, `[excited]`, and more
+- Audio encoder (Whisper-based) was frozen during training
+
+## Usage
+
+```python
+import torch
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+from peft import PeftModel
+
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+adapter_id = "YongkangZOU/evoxtral-lora"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+base_model = VoxtralForConditionalGeneration.from_pretrained(
+    repo_id, dtype=torch.bfloat16, device_map="auto"
+)
+model = PeftModel.from_pretrained(base_model, adapter_id)
+
+# Transcribe audio with expressive tags
+inputs = processor.apply_transcription_request(
+    language="en",
+    audio=["path/to/audio.wav"],
+    format=["WAV"],
+    model_id=repo_id,
+    return_tensors="pt",
+)
+inputs = inputs.to(model.device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
+transcription = processor.batch_decode(
+    outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True
+)[0]
+print(transcription)
+# [nervous] So... I was thinking maybe we could [clears throat] try that new restaurant downtown?
+```
+
+## W&B Tracking
+
+All training and evaluation runs are tracked on Weights & Biases:
+- [Training run](https://wandb.ai/yongkang-zou-ai/evoxtral/runs/t8ak7a20)
+- [Base model eval](https://wandb.ai/yongkang-zou-ai/evoxtral/runs/f9l2zwvs)
+- [Finetuned model eval](https://wandb.ai/yongkang-zou-ai/evoxtral/runs/b32c74im)
+- [Project dashboard](https://wandb.ai/yongkang-zou-ai/evoxtral)
+
+## Supported Tags
+
+The model can produce any tag from the ElevenLabs v3 expressive tag set, including:
+
+`[laughs]` `[sighs]` `[gasps]` `[clears throat]` `[whispers]` `[sniffs]` `[pause]` `[nervous]` `[frustrated]` `[excited]` `[sad]` `[angry]` `[calm]` `[stammers]` `[yawns]` and more.
+
+## Limitations
+
+- Trained on synthetic (TTS-generated) audio, not natural speech recordings
+- Tag F1 of 67.2% means ~1/3 of tags may be missed or misplaced
+- English only
+- Best results on conversational and emotionally expressive speech
+
+## Citation
+
+```bibtex
+@misc{evoxtral2026,
+  title={Evoxtral: Expressive Tagged Transcription with Voxtral},
+  author={Yongkang Zou},
+  year={2026},
+  url={https://huggingface.co/YongkangZOU/evoxtral-lora}
+}
+```

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Voxtral-Mini-3B-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "multi_modal_projector.linear_2",
+    "multi_modal_projector.linear_1",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909e030619cbaf52ad33e05db26cb9c97df78cb0fdfda94637a1445ba7e49df8
+size 499212672

checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Voxtral-Mini-3B-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Voxtral-Mini-3B-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Voxtral-Mini-3B-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "multi_modal_projector.linear_2",
+    "multi_modal_projector.linear_1",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc014b17b21116e68d7fd7a381fcac925f79117813361778c41606a6e7f2b6f
+size 499212672

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537338d486df707334d1c928b076d95c11cf5978af93a6649a1bbee9ec7c0478
+size 998774363

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a70d660bebd66c60c022cbf431d1fd0561c8127e390216fdabeb26c1afe8e6
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd446f12be119caf8b207903edb080afe016482b1d3e825a8f6c7eed7b5aad20
+size 1465

checkpoint-100/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.1666431427001953,
+  "best_model_checkpoint": "/output/evoxtral-lora/checkpoint-100",
+  "epoch": 1.9702970297029703,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 5.802285194396973,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.9557,
+      "step": 5
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 2.306023597717285,
+      "learning_rate": 3.6e-05,
+      "loss": 0.461,
+      "step": 10
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 2.0266661643981934,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.3281,
+      "step": 15
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 1.5811512470245361,
+      "learning_rate": 7.6e-05,
+      "loss": 0.2656,
+      "step": 20
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 1.5266460180282593,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2477,
+      "step": 25
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 1.0605043172836304,
+      "learning_rate": 0.000116,
+      "loss": 0.2199,
+      "step": 30
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 1.4974918365478516,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.1935,
+      "step": 35
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 1.1257297992706299,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.1739,
+      "step": 40
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.9485541582107544,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.1829,
+      "step": 45
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.6643406748771667,
+      "learning_rate": 0.000196,
+      "loss": 0.1887,
+      "step": 50
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "eval_loss": 0.1841340959072113,
+      "eval_runtime": 17.7494,
+      "eval_samples_per_second": 5.69,
+      "eval_steps_per_second": 2.873,
+      "step": 50
+    },
+    {
+      "epoch": 1.0792079207920793,
+      "grad_norm": 0.7675807476043701,
+      "learning_rate": 0.0001992566788083908,
+      "loss": 0.1535,
+      "step": 55
+    },
+    {
+      "epoch": 1.1782178217821782,
+      "grad_norm": 0.6500945687294006,
+      "learning_rate": 0.0001962558656223516,
+      "loss": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 1.2772277227722773,
+      "grad_norm": 3.4771132469177246,
+      "learning_rate": 0.00019102070542141328,
+      "loss": 0.1058,
+      "step": 65
+    },
+    {
+      "epoch": 1.3762376237623761,
+      "grad_norm": 6.509069919586182,
+      "learning_rate": 0.0001836727197823842,
+      "loss": 0.148,
+      "step": 70
+    },
+    {
+      "epoch": 1.4752475247524752,
+      "grad_norm": 1.21564519405365,
+      "learning_rate": 0.0001743824744123196,
+      "loss": 0.154,
+      "step": 75
+    },
+    {
+      "epoch": 1.5742574257425743,
+      "grad_norm": 0.9891815185546875,
+      "learning_rate": 0.00016336561987834153,
+      "loss": 0.1472,
+      "step": 80
+    },
+    {
+      "epoch": 1.6732673267326734,
+      "grad_norm": 0.8960129022598267,
+      "learning_rate": 0.00015087788580152206,
+      "loss": 0.1388,
+      "step": 85
+    },
+    {
+      "epoch": 1.7722772277227723,
+      "grad_norm": 0.6417158842086792,
+      "learning_rate": 0.00013720914471250644,
+      "loss": 0.1544,
+      "step": 90
+    },
+    {
+      "epoch": 1.8712871287128712,
+      "grad_norm": 0.6971271634101868,
+      "learning_rate": 0.00012267668336210413,
+      "loss": 0.1216,
+      "step": 95
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "grad_norm": 0.6400907039642334,
+      "learning_rate": 0.00010761783767709182,
+      "loss": 0.1347,
+      "step": 100
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "eval_loss": 0.1666431427001953,
+      "eval_runtime": 17.7221,
+      "eval_samples_per_second": 5.699,
+      "eval_steps_per_second": 2.878,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8528360565456896e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd58f49b2411a3bf3ec16af828d493672732a1ebe34589d3922b365ec57325e
+size 5777

checkpoint-150/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Voxtral-Mini-3B-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Voxtral-Mini-3B-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-150/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Voxtral-Mini-3B-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "multi_modal_projector.linear_2",
+    "multi_modal_projector.linear_1",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909e030619cbaf52ad33e05db26cb9c97df78cb0fdfda94637a1445ba7e49df8
+size 499212672

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6e2cdcbc3a06663bb885d19ddec826a2746e78cdbe7f851777e8edf2c516ca
+size 998774363

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6f8e4476c92bbe0a1f1dc469afe36379c0cc6e449e17836caca06905a8dc02
+size 14645

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a5aefeb0dad12da4b38995b66f32da699ab73f2ff6844ca83eaa0d41c6ed50
+size 1465

checkpoint-150/trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.1592499166727066,
+  "best_model_checkpoint": "/output/evoxtral-lora/checkpoint-150",
+  "epoch": 2.9504950495049505,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 5.802285194396973,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.9557,
+      "step": 5
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 2.306023597717285,
+      "learning_rate": 3.6e-05,
+      "loss": 0.461,
+      "step": 10
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 2.0266661643981934,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.3281,
+      "step": 15
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 1.5811512470245361,
+      "learning_rate": 7.6e-05,
+      "loss": 0.2656,
+      "step": 20
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 1.5266460180282593,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2477,
+      "step": 25
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 1.0605043172836304,
+      "learning_rate": 0.000116,
+      "loss": 0.2199,
+      "step": 30
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 1.4974918365478516,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.1935,
+      "step": 35
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 1.1257297992706299,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.1739,
+      "step": 40
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.9485541582107544,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.1829,
+      "step": 45
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.6643406748771667,
+      "learning_rate": 0.000196,
+      "loss": 0.1887,
+      "step": 50
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "eval_loss": 0.1841340959072113,
+      "eval_runtime": 17.7494,
+      "eval_samples_per_second": 5.69,
+      "eval_steps_per_second": 2.873,
+      "step": 50
+    },
+    {
+      "epoch": 1.0792079207920793,
+      "grad_norm": 0.7675807476043701,
+      "learning_rate": 0.0001992566788083908,
+      "loss": 0.1535,
+      "step": 55
+    },
+    {
+      "epoch": 1.1782178217821782,
+      "grad_norm": 0.6500945687294006,
+      "learning_rate": 0.0001962558656223516,
+      "loss": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 1.2772277227722773,
+      "grad_norm": 3.4771132469177246,
+      "learning_rate": 0.00019102070542141328,
+      "loss": 0.1058,
+      "step": 65
+    },
+    {
+      "epoch": 1.3762376237623761,
+      "grad_norm": 6.509069919586182,
+      "learning_rate": 0.0001836727197823842,
+      "loss": 0.148,
+      "step": 70
+    },
+    {
+      "epoch": 1.4752475247524752,
+      "grad_norm": 1.21564519405365,
+      "learning_rate": 0.0001743824744123196,
+      "loss": 0.154,
+      "step": 75
+    },
+    {
+      "epoch": 1.5742574257425743,
+      "grad_norm": 0.9891815185546875,
+      "learning_rate": 0.00016336561987834153,
+      "loss": 0.1472,
+      "step": 80
+    },
+    {
+      "epoch": 1.6732673267326734,
+      "grad_norm": 0.8960129022598267,
+      "learning_rate": 0.00015087788580152206,
+      "loss": 0.1388,
+      "step": 85
+    },
+    {
+      "epoch": 1.7722772277227723,
+      "grad_norm": 0.6417158842086792,
+      "learning_rate": 0.00013720914471250644,
+      "loss": 0.1544,
+      "step": 90
+    },
+    {
+      "epoch": 1.8712871287128712,
+      "grad_norm": 0.6971271634101868,
+      "learning_rate": 0.00012267668336210413,
+      "loss": 0.1216,
+      "step": 95
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "grad_norm": 0.6400907039642334,
+      "learning_rate": 0.00010761783767709182,
+      "loss": 0.1347,
+      "step": 100
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "eval_loss": 0.1666431427001953,
+      "eval_runtime": 17.7221,
+      "eval_samples_per_second": 5.699,
+      "eval_steps_per_second": 2.878,
+      "step": 100
+    },
+    {
+      "epoch": 2.0594059405940595,
+      "grad_norm": 0.40439656376838684,
+      "learning_rate": 9.238216232290822e-05,
+      "loss": 0.0851,
+      "step": 105
+    },
+    {
+      "epoch": 2.1584158415841586,
+      "grad_norm": 0.47545361518859863,
+      "learning_rate": 7.732331663789592e-05,
+      "loss": 0.0614,
+      "step": 110
+    },
+    {
+      "epoch": 2.2574257425742577,
+      "grad_norm": 0.42001137137413025,
+      "learning_rate": 6.279085528749359e-05,
+      "loss": 0.0607,
+      "step": 115
+    },
+    {
+      "epoch": 2.3564356435643563,
+      "grad_norm": 0.7629411220550537,
+      "learning_rate": 4.912211419847794e-05,
+      "loss": 0.0556,
+      "step": 120
+    },
+    {
+      "epoch": 2.4554455445544554,
+      "grad_norm": 0.4428424537181854,
+      "learning_rate": 3.663438012165848e-05,
+      "loss": 0.0449,
+      "step": 125
+    },
+    {
+      "epoch": 2.5544554455445545,
+      "grad_norm": 0.564255952835083,
+      "learning_rate": 2.5617525587680402e-05,
+      "loss": 0.0484,
+      "step": 130
+    },
+    {
+      "epoch": 2.6534653465346536,
+      "grad_norm": 0.4994179308414459,
+      "learning_rate": 1.6327280217615792e-05,
+      "loss": 0.0447,
+      "step": 135
+    },
+    {
+      "epoch": 2.7524752475247523,
+      "grad_norm": 0.4854471981525421,
+      "learning_rate": 8.979294578586738e-06,
+      "loss": 0.0475,
+      "step": 140
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "grad_norm": 0.6532300114631653,
+      "learning_rate": 3.7441343776484117e-06,
+      "loss": 0.0477,
+      "step": 145
+    },
+    {
+      "epoch": 2.9504950495049505,
+      "grad_norm": 0.39523014426231384,
+      "learning_rate": 7.433211916092142e-07,
+      "loss": 0.0478,
+      "step": 150
+    },
+    {
+      "epoch": 2.9504950495049505,
+      "eval_loss": 0.1592499166727066,
+      "eval_runtime": 17.8203,
+      "eval_samples_per_second": 5.668,
+      "eval_steps_per_second": 2.862,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.773627471680307e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd58f49b2411a3bf3ec16af828d493672732a1ebe34589d3922b365ec57325e
+size 5777

checkpoint-153/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Voxtral-Mini-3B-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Voxtral-Mini-3B-2507
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-153/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Voxtral-Mini-3B-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "multi_modal_projector.linear_2",
+    "multi_modal_projector.linear_1",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-153/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f764480fa4d0b56f064d10cb530f070f40a39ef0d5f7b02c4cd7c0b623a46324
+size 499212672

checkpoint-153/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9dd86a9509b79108a2d96f051b1a1069453f3feee74726a3053f456d26cb92d
+size 998774363

checkpoint-153/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bda35c561ec5058b4d5495313dfd4d8ddd1b2711a8071d69c8abe265eb1029
+size 14645

checkpoint-153/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70962943a8986eb124d40ffe067f22ad7b7aad7f2e9e9d76f6959f3047a499c3
+size 1465

checkpoint-153/trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.1592499166727066,
+  "best_model_checkpoint": "/output/evoxtral-lora/checkpoint-150",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 5.802285194396973,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.9557,
+      "step": 5
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 2.306023597717285,
+      "learning_rate": 3.6e-05,
+      "loss": 0.461,
+      "step": 10
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 2.0266661643981934,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.3281,
+      "step": 15
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 1.5811512470245361,
+      "learning_rate": 7.6e-05,
+      "loss": 0.2656,
+      "step": 20
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 1.5266460180282593,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2477,
+      "step": 25
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 1.0605043172836304,
+      "learning_rate": 0.000116,
+      "loss": 0.2199,
+      "step": 30
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 1.4974918365478516,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.1935,
+      "step": 35
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 1.1257297992706299,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.1739,
+      "step": 40
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.9485541582107544,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.1829,
+      "step": 45
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.6643406748771667,
+      "learning_rate": 0.000196,
+      "loss": 0.1887,
+      "step": 50
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "eval_loss": 0.1841340959072113,
+      "eval_runtime": 17.7494,
+      "eval_samples_per_second": 5.69,
+      "eval_steps_per_second": 2.873,
+      "step": 50
+    },
+    {
+      "epoch": 1.0792079207920793,
+      "grad_norm": 0.7675807476043701,
+      "learning_rate": 0.0001992566788083908,
+      "loss": 0.1535,
+      "step": 55
+    },
+    {
+      "epoch": 1.1782178217821782,
+      "grad_norm": 0.6500945687294006,
+      "learning_rate": 0.0001962558656223516,
+      "loss": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 1.2772277227722773,
+      "grad_norm": 3.4771132469177246,
+      "learning_rate": 0.00019102070542141328,
+      "loss": 0.1058,
+      "step": 65
+    },
+    {
+      "epoch": 1.3762376237623761,
+      "grad_norm": 6.509069919586182,
+      "learning_rate": 0.0001836727197823842,
+      "loss": 0.148,
+      "step": 70
+    },
+    {
+      "epoch": 1.4752475247524752,
+      "grad_norm": 1.21564519405365,
+      "learning_rate": 0.0001743824744123196,
+      "loss": 0.154,
+      "step": 75
+    },
+    {
+      "epoch": 1.5742574257425743,
+      "grad_norm": 0.9891815185546875,
+      "learning_rate": 0.00016336561987834153,
+      "loss": 0.1472,
+      "step": 80
+    },
+    {
+      "epoch": 1.6732673267326734,
+      "grad_norm": 0.8960129022598267,
+      "learning_rate": 0.00015087788580152206,
+      "loss": 0.1388,
+      "step": 85
+    },
+    {
+      "epoch": 1.7722772277227723,
+      "grad_norm": 0.6417158842086792,
+      "learning_rate": 0.00013720914471250644,
+      "loss": 0.1544,
+      "step": 90
+    },
+    {
+      "epoch": 1.8712871287128712,
+      "grad_norm": 0.6971271634101868,
+      "learning_rate": 0.00012267668336210413,
+      "loss": 0.1216,
+      "step": 95
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "grad_norm": 0.6400907039642334,
+      "learning_rate": 0.00010761783767709182,
+      "loss": 0.1347,
+      "step": 100
+    },
+    {
+      "epoch": 1.9702970297029703,
+      "eval_loss": 0.1666431427001953,
+      "eval_runtime": 17.7221,
+      "eval_samples_per_second": 5.699,
+      "eval_steps_per_second": 2.878,
+      "step": 100
+    },
+    {
+      "epoch": 2.0594059405940595,
+      "grad_norm": 0.40439656376838684,
+      "learning_rate": 9.238216232290822e-05,
+      "loss": 0.0851,
+      "step": 105
+    },
+    {
+      "epoch": 2.1584158415841586,
+      "grad_norm": 0.47545361518859863,
+      "learning_rate": 7.732331663789592e-05,
+      "loss": 0.0614,
+      "step": 110
+    },
+    {
+      "epoch": 2.2574257425742577,
+      "grad_norm": 0.42001137137413025,
+      "learning_rate": 6.279085528749359e-05,
+      "loss": 0.0607,
+      "step": 115
+    },
+    {
+      "epoch": 2.3564356435643563,
+      "grad_norm": 0.7629411220550537,
+      "learning_rate": 4.912211419847794e-05,
+      "loss": 0.0556,
+      "step": 120
+    },
+    {
+      "epoch": 2.4554455445544554,
+      "grad_norm": 0.4428424537181854,
+      "learning_rate": 3.663438012165848e-05,
+      "loss": 0.0449,
+      "step": 125
+    },
+    {
+      "epoch": 2.5544554455445545,
+      "grad_norm": 0.564255952835083,
+      "learning_rate": 2.5617525587680402e-05,
+      "loss": 0.0484,
+      "step": 130
+    },
+    {
+      "epoch": 2.6534653465346536,
+      "grad_norm": 0.4994179308414459,
+      "learning_rate": 1.6327280217615792e-05,
+      "loss": 0.0447,
+      "step": 135
+    },
+    {
+      "epoch": 2.7524752475247523,
+      "grad_norm": 0.4854471981525421,
+      "learning_rate": 8.979294578586738e-06,
+      "loss": 0.0475,
+      "step": 140
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "grad_norm": 0.6532300114631653,
+      "learning_rate": 3.7441343776484117e-06,
+      "loss": 0.0477,
+      "step": 145
+    },
+    {
+      "epoch": 2.9504950495049505,
+      "grad_norm": 0.39523014426231384,
+      "learning_rate": 7.433211916092142e-07,
+      "loss": 0.0478,
+      "step": 150
+    },
+    {
+      "epoch": 2.9504950495049505,
+      "eval_loss": 0.1592499166727066,
+      "eval_runtime": 17.8203,
+      "eval_samples_per_second": 5.668,
+      "eval_steps_per_second": 2.862,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8196216707792896e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-153/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd58f49b2411a3bf3ec16af828d493672732a1ebe34589d3922b365ec57325e
+size 5777

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "VoxtralProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aaf3836c2a5332f029ce85a7a62255c966f47b6797ef81dedd0ade9c862e4a8
+size 14894206

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd58f49b2411a3bf3ec16af828d493672732a1ebe34589d3922b365ec57325e
+size 5777