Upload folder using huggingface_hub

checkpoint-2500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: unsloth/whisper-large-v3
+library_name: peft
+tags:
+- base_model:adapter:unsloth/whisper-large-v3
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.17.1

checkpoint-2500/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "unsloth/whisper-large-v3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 96,
+  "lora_bias": false,
+  "lora_dropout": 0.03,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "v_proj",
+    "k_proj",
+    "out_proj",
+    "fc1",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501eb3d7f9f8b5311e533e02cb9d61628716511864ef95d036648054e454e03c
+size 461518936

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de45c75114dbb898af678502623f4b74e7281ae72bf5aefd9c066e3ba3512e6
+size 923614691

checkpoint-2500/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": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7104350460c05ccddb4e2089ba6f3e04f93ac716a355855e44c838499173fa8
+size 14645

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeabe13d164dac8d378d855d727cd3376a2cd495027a3f2d372238b9d56b447a
+size 1383

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d17d87e0a0a3a1c05689c14631ac4d16cf15d1ad2802c69ca29012ebb3f7c8
+size 1465

checkpoint-2500/trainer_state.json

@@ -0,0 +1,759 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 25.988627552339103,
+  "best_model_checkpoint": "./whisper_hindi_improved_20251107_025049/checkpoint-2500",
+  "epoch": 4.440888888888889,
+  "eval_steps": 2500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0017777777777777779,
+      "grad_norm": 2.3702774047851562,
+      "learning_rate": 0.0,
+      "loss": 1.709,
+      "step": 1
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 1.9324116706848145,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.6572,
+      "step": 25
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.2866696119308472,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 1.4396,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.3138173818588257,
+      "learning_rate": 2.96e-06,
+      "loss": 1.2875,
+      "step": 75
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.7148733139038086,
+      "learning_rate": 3.96e-06,
+      "loss": 1.1774,
+      "step": 100
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.3908791542053223,
+      "learning_rate": 4.960000000000001e-06,
+      "loss": 0.9828,
+      "step": 125
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.2608166933059692,
+      "learning_rate": 5.9600000000000005e-06,
+      "loss": 0.8516,
+      "step": 150
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 1.0959410667419434,
+      "learning_rate": 6.96e-06,
+      "loss": 0.7003,
+      "step": 175
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.9897862076759338,
+      "learning_rate": 7.960000000000002e-06,
+      "loss": 0.5892,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8703014850616455,
+      "learning_rate": 8.920000000000001e-06,
+      "loss": 0.5283,
+      "step": 225
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.1597092151641846,
+      "learning_rate": 9.88e-06,
+      "loss": 0.44,
+      "step": 250
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 1.4660991430282593,
+      "learning_rate": 1.0880000000000001e-05,
+      "loss": 0.3696,
+      "step": 275
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.0865031480789185,
+      "learning_rate": 1.188e-05,
+      "loss": 0.3017,
+      "step": 300
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 1.193084716796875,
+      "learning_rate": 1.2880000000000002e-05,
+      "loss": 0.2839,
+      "step": 325
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.3478896617889404,
+      "learning_rate": 1.3880000000000001e-05,
+      "loss": 0.27,
+      "step": 350
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8208823204040527,
+      "learning_rate": 1.4880000000000002e-05,
+      "loss": 0.2765,
+      "step": 375
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.9162499904632568,
+      "learning_rate": 1.588e-05,
+      "loss": 0.2573,
+      "step": 400
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.1928578615188599,
+      "learning_rate": 1.688e-05,
+      "loss": 0.2454,
+      "step": 425
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9198476672172546,
+      "learning_rate": 1.788e-05,
+      "loss": 0.2584,
+      "step": 450
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 1.10727059841156,
+      "learning_rate": 1.8880000000000002e-05,
+      "loss": 0.2775,
+      "step": 475
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.9461928606033325,
+      "learning_rate": 1.9880000000000003e-05,
+      "loss": 0.2326,
+      "step": 500
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.3022490739822388,
+      "learning_rate": 1.9999990252244153e-05,
+      "loss": 0.2619,
+      "step": 525
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.7707226276397705,
+      "learning_rate": 1.9999955510784705e-05,
+      "loss": 0.2265,
+      "step": 550
+    },
+    {
+      "epoch": 1.0213333333333334,
+      "grad_norm": 0.9355465173721313,
+      "learning_rate": 1.999989559444917e-05,
+      "loss": 0.2344,
+      "step": 575
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "grad_norm": 0.8835461735725403,
+      "learning_rate": 1.9999810503388386e-05,
+      "loss": 0.2047,
+      "step": 600
+    },
+    {
+      "epoch": 1.1102222222222222,
+      "grad_norm": 0.9200624823570251,
+      "learning_rate": 1.999970023781657e-05,
+      "loss": 0.2164,
+      "step": 625
+    },
+    {
+      "epoch": 1.1546666666666667,
+      "grad_norm": 1.170629620552063,
+      "learning_rate": 1.999956479801132e-05,
+      "loss": 0.2378,
+      "step": 650
+    },
+    {
+      "epoch": 1.199111111111111,
+      "grad_norm": 0.9934321641921997,
+      "learning_rate": 1.9999404184313595e-05,
+      "loss": 0.2198,
+      "step": 675
+    },
+    {
+      "epoch": 1.2435555555555555,
+      "grad_norm": 1.0553075075149536,
+      "learning_rate": 1.999921839712775e-05,
+      "loss": 0.2063,
+      "step": 700
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.8540263772010803,
+      "learning_rate": 1.9999007436921497e-05,
+      "loss": 0.1994,
+      "step": 725
+    },
+    {
+      "epoch": 1.3324444444444445,
+      "grad_norm": 1.1836203336715698,
+      "learning_rate": 1.9998771304225933e-05,
+      "loss": 0.1885,
+      "step": 750
+    },
+    {
+      "epoch": 1.3768888888888888,
+      "grad_norm": 1.1124310493469238,
+      "learning_rate": 1.999850999963552e-05,
+      "loss": 0.2055,
+      "step": 775
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "grad_norm": 0.9094732999801636,
+      "learning_rate": 1.9998223523808092e-05,
+      "loss": 0.192,
+      "step": 800
+    },
+    {
+      "epoch": 1.4657777777777778,
+      "grad_norm": 0.9388139843940735,
+      "learning_rate": 1.999791187746485e-05,
+      "loss": 0.2103,
+      "step": 825
+    },
+    {
+      "epoch": 1.5102222222222221,
+      "grad_norm": 0.8892160058021545,
+      "learning_rate": 1.9997575061390368e-05,
+      "loss": 0.1898,
+      "step": 850
+    },
+    {
+      "epoch": 1.5546666666666666,
+      "grad_norm": 0.9697235822677612,
+      "learning_rate": 1.9997213076432575e-05,
+      "loss": 0.1987,
+      "step": 875
+    },
+    {
+      "epoch": 1.5991111111111111,
+      "grad_norm": 0.886682391166687,
+      "learning_rate": 1.9996825923502766e-05,
+      "loss": 0.1955,
+      "step": 900
+    },
+    {
+      "epoch": 1.6435555555555554,
+      "grad_norm": 0.8804945945739746,
+      "learning_rate": 1.9996413603575603e-05,
+      "loss": 0.1842,
+      "step": 925
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.9214787483215332,
+      "learning_rate": 1.9995976117689103e-05,
+      "loss": 0.1854,
+      "step": 950
+    },
+    {
+      "epoch": 1.7324444444444445,
+      "grad_norm": 0.7763159275054932,
+      "learning_rate": 1.999551346694463e-05,
+      "loss": 0.1868,
+      "step": 975
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "grad_norm": 0.8259502053260803,
+      "learning_rate": 1.999502565250691e-05,
+      "loss": 0.1915,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8213333333333335,
+      "grad_norm": 1.0171443223953247,
+      "learning_rate": 1.999451267560401e-05,
+      "loss": 0.1884,
+      "step": 1025
+    },
+    {
+      "epoch": 1.8657777777777778,
+      "grad_norm": 0.782338559627533,
+      "learning_rate": 1.999397453752736e-05,
+      "loss": 0.1931,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9102222222222223,
+      "grad_norm": 0.7394895553588867,
+      "learning_rate": 1.9993411239631713e-05,
+      "loss": 0.1926,
+      "step": 1075
+    },
+    {
+      "epoch": 1.9546666666666668,
+      "grad_norm": 1.1669658422470093,
+      "learning_rate": 1.999282278333517e-05,
+      "loss": 0.1886,
+      "step": 1100
+    },
+    {
+      "epoch": 1.999111111111111,
+      "grad_norm": 0.5342193841934204,
+      "learning_rate": 1.9992209170119177e-05,
+      "loss": 0.1892,
+      "step": 1125
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 0.9362142086029053,
+      "learning_rate": 1.99915704015285e-05,
+      "loss": 0.1675,
+      "step": 1150
+    },
+    {
+      "epoch": 2.087111111111111,
+      "grad_norm": 0.6746439933776855,
+      "learning_rate": 1.9990906479171236e-05,
+      "loss": 0.1589,
+      "step": 1175
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "grad_norm": 0.8524124622344971,
+      "learning_rate": 1.9990217404718807e-05,
+      "loss": 0.1523,
+      "step": 1200
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 1.0020498037338257,
+      "learning_rate": 1.9989503179905963e-05,
+      "loss": 0.1647,
+      "step": 1225
+    },
+    {
+      "epoch": 2.2204444444444444,
+      "grad_norm": 0.9763280153274536,
+      "learning_rate": 1.9988763806530765e-05,
+      "loss": 0.1502,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2648888888888887,
+      "grad_norm": 0.7576664090156555,
+      "learning_rate": 1.998799928645458e-05,
+      "loss": 0.1439,
+      "step": 1275
+    },
+    {
+      "epoch": 2.3093333333333335,
+      "grad_norm": 0.772350549697876,
+      "learning_rate": 1.9987209621602086e-05,
+      "loss": 0.1539,
+      "step": 1300
+    },
+    {
+      "epoch": 2.3537777777777777,
+      "grad_norm": 0.5643001198768616,
+      "learning_rate": 1.9986394813961267e-05,
+      "loss": 0.162,
+      "step": 1325
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 1.1751031875610352,
+      "learning_rate": 1.9985554865583394e-05,
+      "loss": 0.1523,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4426666666666668,
+      "grad_norm": 0.7075941562652588,
+      "learning_rate": 1.9984689778583044e-05,
+      "loss": 0.16,
+      "step": 1375
+    },
+    {
+      "epoch": 2.487111111111111,
+      "grad_norm": 0.6978412866592407,
+      "learning_rate": 1.998379955513807e-05,
+      "loss": 0.1543,
+      "step": 1400
+    },
+    {
+      "epoch": 2.5315555555555553,
+      "grad_norm": 0.8001956939697266,
+      "learning_rate": 1.9982884197489602e-05,
+      "loss": 0.149,
+      "step": 1425
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.8669373989105225,
+      "learning_rate": 1.9981943707942064e-05,
+      "loss": 0.1492,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6204444444444444,
+      "grad_norm": 0.9674304723739624,
+      "learning_rate": 1.9980978088863125e-05,
+      "loss": 0.152,
+      "step": 1475
+    },
+    {
+      "epoch": 2.664888888888889,
+      "grad_norm": 0.6418324112892151,
+      "learning_rate": 1.9979987342683736e-05,
+      "loss": 0.1481,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7093333333333334,
+      "grad_norm": 0.8923436999320984,
+      "learning_rate": 1.9978971471898105e-05,
+      "loss": 0.1558,
+      "step": 1525
+    },
+    {
+      "epoch": 2.7537777777777777,
+      "grad_norm": 0.8257409930229187,
+      "learning_rate": 1.997793047906367e-05,
+      "loss": 0.1459,
+      "step": 1550
+    },
+    {
+      "epoch": 2.7982222222222224,
+      "grad_norm": 0.9598385095596313,
+      "learning_rate": 1.9976864366801146e-05,
+      "loss": 0.1431,
+      "step": 1575
+    },
+    {
+      "epoch": 2.8426666666666667,
+      "grad_norm": 0.8788126111030579,
+      "learning_rate": 1.9975773137794458e-05,
+      "loss": 0.1475,
+      "step": 1600
+    },
+    {
+      "epoch": 2.887111111111111,
+      "grad_norm": 0.9696657657623291,
+      "learning_rate": 1.9974656794790777e-05,
+      "loss": 0.1679,
+      "step": 1625
+    },
+    {
+      "epoch": 2.9315555555555557,
+      "grad_norm": 0.7172701358795166,
+      "learning_rate": 1.99735153406005e-05,
+      "loss": 0.1608,
+      "step": 1650
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.7976154685020447,
+      "learning_rate": 1.9972348778097225e-05,
+      "loss": 0.156,
+      "step": 1675
+    },
+    {
+      "epoch": 3.0195555555555558,
+      "grad_norm": 0.6643044352531433,
+      "learning_rate": 1.9971157110217782e-05,
+      "loss": 0.1322,
+      "step": 1700
+    },
+    {
+      "epoch": 3.064,
+      "grad_norm": 0.8205846548080444,
+      "learning_rate": 1.9969940339962192e-05,
+      "loss": 0.1173,
+      "step": 1725
+    },
+    {
+      "epoch": 3.1084444444444443,
+      "grad_norm": 0.5853546261787415,
+      "learning_rate": 1.996869847039367e-05,
+      "loss": 0.1327,
+      "step": 1750
+    },
+    {
+      "epoch": 3.152888888888889,
+      "grad_norm": 0.8844691514968872,
+      "learning_rate": 1.9967431504638624e-05,
+      "loss": 0.1294,
+      "step": 1775
+    },
+    {
+      "epoch": 3.1973333333333334,
+      "grad_norm": 0.8210035562515259,
+      "learning_rate": 1.9966139445886633e-05,
+      "loss": 0.1119,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2417777777777776,
+      "grad_norm": 1.1607897281646729,
+      "learning_rate": 1.996482229739046e-05,
+      "loss": 0.117,
+      "step": 1825
+    },
+    {
+      "epoch": 3.2862222222222224,
+      "grad_norm": 1.3166520595550537,
+      "learning_rate": 1.9963480062466022e-05,
+      "loss": 0.1253,
+      "step": 1850
+    },
+    {
+      "epoch": 3.3306666666666667,
+      "grad_norm": 0.9852168560028076,
+      "learning_rate": 1.996211274449239e-05,
+      "loss": 0.1275,
+      "step": 1875
+    },
+    {
+      "epoch": 3.375111111111111,
+      "grad_norm": 0.6811080574989319,
+      "learning_rate": 1.9960720346911798e-05,
+      "loss": 0.116,
+      "step": 1900
+    },
+    {
+      "epoch": 3.4195555555555557,
+      "grad_norm": 0.6788239479064941,
+      "learning_rate": 1.995930287322959e-05,
+      "loss": 0.1193,
+      "step": 1925
+    },
+    {
+      "epoch": 3.464,
+      "grad_norm": 0.9439682960510254,
+      "learning_rate": 1.9957860327014262e-05,
+      "loss": 0.1341,
+      "step": 1950
+    },
+    {
+      "epoch": 3.5084444444444447,
+      "grad_norm": 0.7991074919700623,
+      "learning_rate": 1.995639271189742e-05,
+      "loss": 0.1315,
+      "step": 1975
+    },
+    {
+      "epoch": 3.552888888888889,
+      "grad_norm": 0.7587019205093384,
+      "learning_rate": 1.9954900031573788e-05,
+      "loss": 0.1317,
+      "step": 2000
+    },
+    {
+      "epoch": 3.5973333333333333,
+      "grad_norm": 0.801716685295105,
+      "learning_rate": 1.995338228980118e-05,
+      "loss": 0.1283,
+      "step": 2025
+    },
+    {
+      "epoch": 3.6417777777777776,
+      "grad_norm": 1.0118695497512817,
+      "learning_rate": 1.9951839490400514e-05,
+      "loss": 0.1318,
+      "step": 2050
+    },
+    {
+      "epoch": 3.6862222222222223,
+      "grad_norm": 0.7447464466094971,
+      "learning_rate": 1.9950271637255787e-05,
+      "loss": 0.1261,
+      "step": 2075
+    },
+    {
+      "epoch": 3.7306666666666666,
+      "grad_norm": 0.6883965134620667,
+      "learning_rate": 1.9948678734314062e-05,
+      "loss": 0.1324,
+      "step": 2100
+    },
+    {
+      "epoch": 3.7751111111111113,
+      "grad_norm": 1.0719166994094849,
+      "learning_rate": 1.9947060785585472e-05,
+      "loss": 0.1323,
+      "step": 2125
+    },
+    {
+      "epoch": 3.8195555555555556,
+      "grad_norm": 0.7405015230178833,
+      "learning_rate": 1.99454177951432e-05,
+      "loss": 0.121,
+      "step": 2150
+    },
+    {
+      "epoch": 3.864,
+      "grad_norm": 0.8354102373123169,
+      "learning_rate": 1.994374976712348e-05,
+      "loss": 0.123,
+      "step": 2175
+    },
+    {
+      "epoch": 3.9084444444444446,
+      "grad_norm": 0.7395333647727966,
+      "learning_rate": 1.9942056705725564e-05,
+      "loss": 0.1185,
+      "step": 2200
+    },
+    {
+      "epoch": 3.952888888888889,
+      "grad_norm": 0.8350748419761658,
+      "learning_rate": 1.9940338615211732e-05,
+      "loss": 0.1316,
+      "step": 2225
+    },
+    {
+      "epoch": 3.997333333333333,
+      "grad_norm": 0.7887341976165771,
+      "learning_rate": 1.9938595499907274e-05,
+      "loss": 0.1264,
+      "step": 2250
+    },
+    {
+      "epoch": 4.0408888888888885,
+      "grad_norm": 1.299972653388977,
+      "learning_rate": 1.9936827364200483e-05,
+      "loss": 0.1071,
+      "step": 2275
+    },
+    {
+      "epoch": 4.085333333333334,
+      "grad_norm": 0.6423847675323486,
+      "learning_rate": 1.993503421254264e-05,
+      "loss": 0.0976,
+      "step": 2300
+    },
+    {
+      "epoch": 4.129777777777778,
+      "grad_norm": 0.732215404510498,
+      "learning_rate": 1.9933216049448003e-05,
+      "loss": 0.0944,
+      "step": 2325
+    },
+    {
+      "epoch": 4.174222222222222,
+      "grad_norm": 1.239856243133545,
+      "learning_rate": 1.9931372879493788e-05,
+      "loss": 0.0991,
+      "step": 2350
+    },
+    {
+      "epoch": 4.218666666666667,
+      "grad_norm": 0.661592960357666,
+      "learning_rate": 1.9929504707320176e-05,
+      "loss": 0.0956,
+      "step": 2375
+    },
+    {
+      "epoch": 4.263111111111111,
+      "grad_norm": 1.2171379327774048,
+      "learning_rate": 1.9927611537630293e-05,
+      "loss": 0.0945,
+      "step": 2400
+    },
+    {
+      "epoch": 4.307555555555556,
+      "grad_norm": 1.1166738271713257,
+      "learning_rate": 1.9925693375190187e-05,
+      "loss": 0.1044,
+      "step": 2425
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.6641908884048462,
+      "learning_rate": 1.9923750224828833e-05,
+      "loss": 0.0957,
+      "step": 2450
+    },
+    {
+      "epoch": 4.396444444444445,
+      "grad_norm": 0.683151125907898,
+      "learning_rate": 1.9921782091438108e-05,
+      "loss": 0.0996,
+      "step": 2475
+    },
+    {
+      "epoch": 4.440888888888889,
+      "grad_norm": 0.9200541973114014,
+      "learning_rate": 1.9919788979972785e-05,
+      "loss": 0.1,
+      "step": 2500
+    },
+    {
+      "epoch": 4.440888888888889,
+      "eval_loss": 0.20267285406589508,
+      "eval_runtime": 1404.9789,
+      "eval_samples_per_second": 0.712,
+      "eval_steps_per_second": 0.089,
+      "eval_wer": 25.988627552339103,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 89,
+  "save_steps": 2500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 10,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.46412752338944e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027f038ae6f343b4bd6b983c6a2c48944efa6a9718f9ff1866c6b3b364f90e98
+size 6033

logs/events.out.tfevents.1762483946.f66a7246828a.93445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707789b00b23b1c62c14400b2705cc9834ae3acbd0386562fb0be38fdb2a564e
+size 27593

wer_log.txt

@@ -0,0 +1,5 @@
+=== WER Training Log ===
+Model: openai/whisper-large-v3
+Language: Hindi
+
+Step 2500: WER=25.9886%, Loss=0.2027