checkpoint-100

qwen3.5-2b/best_checkpoint_wer/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-2B
+- 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 0.21.0

qwen3.5-2b/best_checkpoint_wer/adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "in_proj_a",
+    "gate_proj",
+    "out_proj",
+    "q_proj",
+    "k_proj",
+    "in_proj_b",
+    "o_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

qwen3.5-2b/best_checkpoint_wer/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e249ff273f8df09605bca89a1571361cd7bfc966c1a24f7672d253f488458f
+size 134604152

qwen3.5-2b/best_checkpoint_wer/best_metrics.json

@@ -0,0 +1,7 @@
+{
+  "step": 100,
+  "wer": 0.46168322007318346,
+  "exact_match": 0.00390625,
+  "hallucination_rate": 0.09375,
+  "n_examples": 256
+}

qwen3.5-2b/best_checkpoint_wer/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216255d2009f78676e6a71be2913f7485c161494a3b1b2ad6b608621d991684e
+size 269426431

qwen3.5-2b/best_checkpoint_wer/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd3c954d401b65bf65ab4946a048a3a709cb2bbbe22c8401248fde3d9108ce2
+size 14645

qwen3.5-2b/best_checkpoint_wer/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5161ab58165f1ba32df42f8d11c180d6e456f2660b1a85bbaf6c2be2e076253a
+size 1465

qwen3.5-2b/best_checkpoint_wer/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07914523149980214,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007914523149980214,
+      "grad_norm": 1.404574990272522,
+      "learning_rate": 7.086614173228347e-06,
+      "loss": 0.9118253707885742,
+      "step": 10
+    },
+    {
+      "epoch": 0.015829046299960427,
+      "grad_norm": 0.868704617023468,
+      "learning_rate": 1.4960629921259845e-05,
+      "loss": 0.8003530502319336,
+      "step": 20
+    },
+    {
+      "epoch": 0.02374356944994064,
+      "grad_norm": 0.8633992075920105,
+      "learning_rate": 2.283464566929134e-05,
+      "loss": 0.7220969676971436,
+      "step": 30
+    },
+    {
+      "epoch": 0.031658092599920855,
+      "grad_norm": 0.7782989740371704,
+      "learning_rate": 3.070866141732284e-05,
+      "loss": 0.7230673789978027,
+      "step": 40
+    },
+    {
+      "epoch": 0.03957261574990107,
+      "grad_norm": 1.0865058898925781,
+      "learning_rate": 3.858267716535433e-05,
+      "loss": 0.7225656986236573,
+      "step": 50
+    },
+    {
+      "epoch": 0.04748713889988128,
+      "grad_norm": 0.8686597943305969,
+      "learning_rate": 4.645669291338583e-05,
+      "loss": 0.6066381454467773,
+      "step": 60
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": 0.9904829263687134,
+      "learning_rate": 5.433070866141733e-05,
+      "loss": 0.7127069473266602,
+      "step": 70
+    },
+    {
+      "epoch": 0.06331618519984171,
+      "grad_norm": 0.9868095517158508,
+      "learning_rate": 6.220472440944882e-05,
+      "loss": 0.6702294826507569,
+      "step": 80
+    },
+    {
+      "epoch": 0.07123070834982193,
+      "grad_norm": 1.1342442035675049,
+      "learning_rate": 7.007874015748031e-05,
+      "loss": 0.6693508148193359,
+      "step": 90
+    },
+    {
+      "epoch": 0.07914523149980214,
+      "grad_norm": 1.1382489204406738,
+      "learning_rate": 7.795275590551181e-05,
+      "loss": 0.6664952278137207,
+      "step": 100
+    },
+    {
+      "epoch": 0.07914523149980214,
+      "eval_loss": 0.6436748504638672,
+      "eval_runtime": 461.1275,
+      "eval_samples_per_second": 24.29,
+      "eval_steps_per_second": 6.074,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2528,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5094044096262656e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b/best_checkpoint_wer/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ac5fc1677740bc79510bd3bb17e1d48a8cb3ceab532db738ff37384e2efc7b
+size 5201

qwen3.5-2b/checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-2B
+- 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 0.21.0

qwen3.5-2b/checkpoint-100/adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "in_proj_a",
+    "gate_proj",
+    "out_proj",
+    "q_proj",
+    "k_proj",
+    "in_proj_b",
+    "o_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

qwen3.5-2b/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e249ff273f8df09605bca89a1571361cd7bfc966c1a24f7672d253f488458f
+size 134604152

qwen3.5-2b/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216255d2009f78676e6a71be2913f7485c161494a3b1b2ad6b608621d991684e
+size 269426431

qwen3.5-2b/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd3c954d401b65bf65ab4946a048a3a709cb2bbbe22c8401248fde3d9108ce2
+size 14645

qwen3.5-2b/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5161ab58165f1ba32df42f8d11c180d6e456f2660b1a85bbaf6c2be2e076253a
+size 1465

qwen3.5-2b/checkpoint-100/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07914523149980214,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007914523149980214,
+      "grad_norm": 1.404574990272522,
+      "learning_rate": 7.086614173228347e-06,
+      "loss": 0.9118253707885742,
+      "step": 10
+    },
+    {
+      "epoch": 0.015829046299960427,
+      "grad_norm": 0.868704617023468,
+      "learning_rate": 1.4960629921259845e-05,
+      "loss": 0.8003530502319336,
+      "step": 20
+    },
+    {
+      "epoch": 0.02374356944994064,
+      "grad_norm": 0.8633992075920105,
+      "learning_rate": 2.283464566929134e-05,
+      "loss": 0.7220969676971436,
+      "step": 30
+    },
+    {
+      "epoch": 0.031658092599920855,
+      "grad_norm": 0.7782989740371704,
+      "learning_rate": 3.070866141732284e-05,
+      "loss": 0.7230673789978027,
+      "step": 40
+    },
+    {
+      "epoch": 0.03957261574990107,
+      "grad_norm": 1.0865058898925781,
+      "learning_rate": 3.858267716535433e-05,
+      "loss": 0.7225656986236573,
+      "step": 50
+    },
+    {
+      "epoch": 0.04748713889988128,
+      "grad_norm": 0.8686597943305969,
+      "learning_rate": 4.645669291338583e-05,
+      "loss": 0.6066381454467773,
+      "step": 60
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": 0.9904829263687134,
+      "learning_rate": 5.433070866141733e-05,
+      "loss": 0.7127069473266602,
+      "step": 70
+    },
+    {
+      "epoch": 0.06331618519984171,
+      "grad_norm": 0.9868095517158508,
+      "learning_rate": 6.220472440944882e-05,
+      "loss": 0.6702294826507569,
+      "step": 80
+    },
+    {
+      "epoch": 0.07123070834982193,
+      "grad_norm": 1.1342442035675049,
+      "learning_rate": 7.007874015748031e-05,
+      "loss": 0.6693508148193359,
+      "step": 90
+    },
+    {
+      "epoch": 0.07914523149980214,
+      "grad_norm": 1.1382489204406738,
+      "learning_rate": 7.795275590551181e-05,
+      "loss": 0.6664952278137207,
+      "step": 100
+    },
+    {
+      "epoch": 0.07914523149980214,
+      "eval_loss": 0.6436748504638672,
+      "eval_runtime": 461.1275,
+      "eval_samples_per_second": 24.29,
+      "eval_steps_per_second": 6.074,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2528,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5094044096262656e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ac5fc1677740bc79510bd3bb17e1d48a8cb3ceab532db738ff37384e2efc7b
+size 5201

qwen3.5-2b/config.yaml

@@ -0,0 +1,43 @@
+model_id: Qwen/Qwen3.5-2B
+dataset_id: ./asr_dataset_curated.jsonl
+train_split: train
+eval_split: null
+eval_fraction: 0.1
+train_fraction: 0.2
+input_column: text_whisper
+target_column: text
+system_prompt: null
+output_dir: outputs/model-comparison/qwen3.5-2b
+max_length: 2048
+on_long_example: drop
+num_train_epochs: 2.0
+per_device_train_batch_size: 4
+per_device_eval_batch_size: 4
+gradient_accumulation_steps: 4
+learning_rate: 0.0001
+warmup_ratio: 0.05
+logging_steps: 10
+eval_steps: 100
+save_steps: 100
+save_total_limit: 3
+seed: 42
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+load_in_4bit: false
+push_to_hub: true
+hub_repo_id: PedramR/ASR_Post-processing
+hub_repo_folder: qwen3.5-2b
+hub_private: false
+tensorboard_logging_dir: outputs/model-comparison/qwen3.5-2b/tb
+resume_from_checkpoint: false
+test_dataset_id: ErfanRou/callcc-test-1k
+test_split: test
+test_input_column: text_whisper
+test_target_column: text
+test_max_new_tokens: 1024
+test_batch_size: 32
+test_max_examples: 256
+test_checkpoint_max_examples: 256
+test_hallucination_overlap_floor: 50.0
+test_baseline: true

qwen3.5-2b/resolved_config.yaml

@@ -0,0 +1,47 @@
+model_id: Qwen/Qwen3.5-2B
+dataset_id: ./asr_dataset_curated.jsonl
+train_split: train
+eval_split: null
+eval_fraction: 0.1
+train_fraction: 0.2
+input_column: text_whisper
+target_column: text
+system_prompt: null
+output_dir: outputs/model-comparison/qwen3.5-2b
+max_length: 2048
+on_long_example: drop
+training:
+  num_train_epochs: 2.0
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 4
+  gradient_accumulation_steps: 4
+  learning_rate: 0.0001
+  warmup_ratio: 0.05
+  logging_steps: 10
+  eval_steps: 100
+  save_steps: 100
+  save_total_limit: 3
+  seed: 42
+lora:
+  r: 32
+  alpha: 64
+  dropout: 0.05
+quantization:
+  load_in_4bit: false
+hub:
+  push_to_hub: true
+  repo_id: PedramR/ASR_Post-processing
+  folder: qwen3.5-2b
+  private: false
+tensorboard:
+  logging_dir: outputs/model-comparison/qwen3.5-2b/tb
+test:
+  dataset_id: ErfanRou/callcc-test-1k
+  split: test
+  input_column: text_whisper
+  target_column: text
+  max_new_tokens: 1024
+  batch_size: 32
+  max_examples: 256
+  checkpoint_max_examples: 256
+resume_from_checkpoint: false

qwen3.5-2b/tb/events.out.tfevents.1789917137.fed349279e2c.5234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b069aa8c454d9883a34c2b91f1c35e49efbb70cfda0f42b3562ed70c289156
+size 5626

qwen3.5-2b/tb/events.out.tfevents.1789935605.fed349279e2c.6800.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0139cee80096285d8fea48be42a8f621dd14dbc5d59e0f5e222f23b85ad793ee
+size 8223

qwen3.5-2b/test_eval/metrics.json

@@ -0,0 +1,6 @@
+{
+  "wer": 0.46168322007318346,
+  "exact_match": 0.00390625,
+  "hallucination_rate": 0.09375,
+  "n_examples": 256
+}

qwen3.5-2b/test_eval_baseline/metrics.json

@@ -0,0 +1,6 @@
+{
+  "wer": 0.27462624150548876,
+  "exact_match": 0.0,
+  "hallucination_rate": 0.015625,
+  "n_examples": 256
+}