PedramR commited on Sep 28

Commit

11254af

verified ·

1 Parent(s): 0ee7949

checkpoint-500

Browse files

Files changed (30) hide show

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/README.md +207 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_config.json +56 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_model.safetensors +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/best_metrics.json +4 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/optimizer.pt +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/rng_state.pth +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/scheduler.pt +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/trainer_state.json +384 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/training_args.bin +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/README.md +207 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/adapter_config.json +56 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/adapter_model.safetensors +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/optimizer.pt +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/rng_state.pth +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/scheduler.pt +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/trainer_state.json +384 -0
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/training_args.bin +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/config.yaml +67 -0
qwen3.5-2b-100pct-masked-weighted-v2/resolved_config.yaml +57 -0
qwen3.5-2b-100pct-masked-weighted-v2/tb/events.out.tfevents.1790605476.02b48645612f.4580.0 +3 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_baseline/metrics.json +16 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_baseline/predictions.jsonl +0 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/metrics.json +16 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/predictions.jsonl +0 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity_baseline/metrics.json +16 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity_baseline/predictions.jsonl +0 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/metrics.json +16 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/predictions.jsonl +0 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo_baseline/metrics.json +16 -0
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo_baseline/predictions.jsonl +0 -0

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/README.md ADDED Viewed

	@@ -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-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_config.json ADDED Viewed

	@@ -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": [
+    "q_proj",
+    "in_proj_b",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "out_proj",
+    "in_proj_z",
+    "k_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "in_proj_a"
+  ],
+  "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-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:90ce164ea4415c1d512535e37647dfad4669f15274cceba22515c0d5f54a6d27
+size 134604152

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/best_metrics.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "step": 500,
+  "wer": 0.21939984789822387
+}

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:99cacc22e9728e6b599b9fd6b823574377f16b958bc257e8f42e2f83aa921a2e
+size 269426431

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:90cf8e31f238979a8a77d1f114b86a765e07d4aa3555cdca9685305b07b578b8
+size 14645

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:490cfc293c61f546e9ca8bea24a6ff2f70f00dafb78159902250efed21573d84
+size 1465

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/trainer_state.json ADDED Viewed

	@@ -0,0 +1,384 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08972331572513262,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0017944663145026524,
+      "grad_norm": 2.403308153152466,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 1.210298442840576,
+      "step": 10
+    },
+    {
+      "epoch": 0.003588932629005305,
+      "grad_norm": 1.3837767839431763,
+      "learning_rate": 6.810035842293908e-06,
+      "loss": 1.238302230834961,
+      "step": 20
+    },
+    {
+      "epoch": 0.005383398943507958,
+      "grad_norm": 1.152842402458191,
+      "learning_rate": 1.039426523297491e-05,
+      "loss": 1.1493020057678223,
+      "step": 30
+    },
+    {
+      "epoch": 0.00717786525801061,
+      "grad_norm": 1.2282543182373047,
+      "learning_rate": 1.3978494623655914e-05,
+      "loss": 1.2698699951171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.008972331572513263,
+      "grad_norm": 4.5811686515808105,
+      "learning_rate": 1.7562724014336916e-05,
+      "loss": 1.336978054046631,
+      "step": 50
+    },
+    {
+      "epoch": 0.010766797887015915,
+      "grad_norm": 0.7280638217926025,
+      "learning_rate": 2.1146953405017922e-05,
+      "loss": 0.9929692268371582,
+      "step": 60
+    },
+    {
+      "epoch": 0.012561264201518567,
+      "grad_norm": 0.8359633684158325,
+      "learning_rate": 2.4731182795698928e-05,
+      "loss": 0.987311840057373,
+      "step": 70
+    },
+    {
+      "epoch": 0.01435573051602122,
+      "grad_norm": 1.061148762702942,
+      "learning_rate": 2.831541218637993e-05,
+      "loss": 1.0299980163574218,
+      "step": 80
+    },
+    {
+      "epoch": 0.01615019683052387,
+      "grad_norm": 1.4723000526428223,
+      "learning_rate": 3.1899641577060935e-05,
+      "loss": 1.1110344886779786,
+      "step": 90
+    },
+    {
+      "epoch": 0.017944663145026525,
+      "grad_norm": 5.412300109863281,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 1.1978090286254883,
+      "step": 100
+    },
+    {
+      "epoch": 0.019739129459529176,
+      "grad_norm": 0.7945532202720642,
+      "learning_rate": 3.906810035842295e-05,
+      "loss": 0.8953464508056641,
+      "step": 110
+    },
+    {
+      "epoch": 0.02153359577403183,
+      "grad_norm": 0.9241706728935242,
+      "learning_rate": 4.265232974910394e-05,
+      "loss": 0.8933357238769531,
+      "step": 120
+    },
+    {
+      "epoch": 0.023328062088534482,
+      "grad_norm": 1.2824897766113281,
+      "learning_rate": 4.6236559139784944e-05,
+      "loss": 0.9129752159118653,
+      "step": 130
+    },
+    {
+      "epoch": 0.025122528403037133,
+      "grad_norm": 1.8574696779251099,
+      "learning_rate": 4.982078853046595e-05,
+      "loss": 1.0019177436828612,
+      "step": 140
+    },
+    {
+      "epoch": 0.026916994717539788,
+      "grad_norm": 4.865994930267334,
+      "learning_rate": 5.340501792114696e-05,
+      "loss": 1.1639716148376464,
+      "step": 150
+    },
+    {
+      "epoch": 0.02871146103204244,
+      "grad_norm": 0.8981343507766724,
+      "learning_rate": 5.6989247311827965e-05,
+      "loss": 0.8498629570007324,
+      "step": 160
+    },
+    {
+      "epoch": 0.03050592734654509,
+      "grad_norm": 0.8773536086082458,
+      "learning_rate": 6.057347670250897e-05,
+      "loss": 0.8652203559875489,
+      "step": 170
+    },
+    {
+      "epoch": 0.03230039366104774,
+      "grad_norm": 1.2524876594543457,
+      "learning_rate": 6.415770609318996e-05,
+      "loss": 0.9427430152893066,
+      "step": 180
+    },
+    {
+      "epoch": 0.034094859975550396,
+      "grad_norm": 1.7148643732070923,
+      "learning_rate": 6.774193548387096e-05,
+      "loss": 0.9581910133361816,
+      "step": 190
+    },
+    {
+      "epoch": 0.03588932629005305,
+      "grad_norm": 5.458459854125977,
+      "learning_rate": 7.132616487455197e-05,
+      "loss": 1.1793695449829102,
+      "step": 200
+    },
+    {
+      "epoch": 0.037683792604555705,
+      "grad_norm": 0.7586544752120972,
+      "learning_rate": 7.491039426523297e-05,
+      "loss": 0.8673212051391601,
+      "step": 210
+    },
+    {
+      "epoch": 0.03947825891905835,
+      "grad_norm": 0.8580747246742249,
+      "learning_rate": 7.849462365591398e-05,
+      "loss": 0.8158726692199707,
+      "step": 220
+    },
+    {
+      "epoch": 0.04127272523356101,
+      "grad_norm": 1.0292130708694458,
+      "learning_rate": 8.207885304659499e-05,
+      "loss": 0.8816629409790039,
+      "step": 230
+    },
+    {
+      "epoch": 0.04306719154806366,
+      "grad_norm": 1.2191781997680664,
+      "learning_rate": 8.566308243727598e-05,
+      "loss": 0.9256319999694824,
+      "step": 240
+    },
+    {
+      "epoch": 0.04486165786256631,
+      "grad_norm": 4.896722316741943,
+      "learning_rate": 8.924731182795699e-05,
+      "loss": 1.054029369354248,
+      "step": 250
+    },
+    {
+      "epoch": 0.046656124177068964,
+      "grad_norm": 0.6555370688438416,
+      "learning_rate": 9.2831541218638e-05,
+      "loss": 0.8240686416625976,
+      "step": 260
+    },
+    {
+      "epoch": 0.04845059049157162,
+      "grad_norm": 0.8895808458328247,
+      "learning_rate": 9.6415770609319e-05,
+      "loss": 0.7868500232696534,
+      "step": 270
+    },
+    {
+      "epoch": 0.050245056806074266,
+      "grad_norm": 0.9253164529800415,
+      "learning_rate": 0.0001,
+      "loss": 0.821414852142334,
+      "step": 280
+    },
+    {
+      "epoch": 0.05203952312057692,
+      "grad_norm": 1.134040355682373,
+      "learning_rate": 9.981110691348697e-05,
+      "loss": 0.9013632774353028,
+      "step": 290
+    },
+    {
+      "epoch": 0.053833989435079575,
+      "grad_norm": 3.446653366088867,
+      "learning_rate": 9.962221382697394e-05,
+      "loss": 1.0495364189147949,
+      "step": 300
+    },
+    {
+      "epoch": 0.05562845574958222,
+      "grad_norm": 0.7303311824798584,
+      "learning_rate": 9.94333207404609e-05,
+      "loss": 0.7989195346832275,
+      "step": 310
+    },
+    {
+      "epoch": 0.05742292206408488,
+      "grad_norm": 0.8196483850479126,
+      "learning_rate": 9.924442765394787e-05,
+      "loss": 0.7937421798706055,
+      "step": 320
+    },
+    {
+      "epoch": 0.05921738837858753,
+      "grad_norm": 0.9366778135299683,
+      "learning_rate": 9.905553456743484e-05,
+      "loss": 0.809019660949707,
+      "step": 330
+    },
+    {
+      "epoch": 0.06101185469309018,
+      "grad_norm": 1.2467617988586426,
+      "learning_rate": 9.88666414809218e-05,
+      "loss": 0.930391502380371,
+      "step": 340
+    },
+    {
+      "epoch": 0.06280632100759284,
+      "grad_norm": 3.261760950088501,
+      "learning_rate": 9.867774839440876e-05,
+      "loss": 1.0620959281921387,
+      "step": 350
+    },
+    {
+      "epoch": 0.06460078732209548,
+      "grad_norm": 0.6342303156852722,
+      "learning_rate": 9.848885530789574e-05,
+      "loss": 0.8134325981140137,
+      "step": 360
+    },
+    {
+      "epoch": 0.06639525363659814,
+      "grad_norm": 0.6608202457427979,
+      "learning_rate": 9.82999622213827e-05,
+      "loss": 0.789882230758667,
+      "step": 370
+    },
+    {
+      "epoch": 0.06818971995110079,
+      "grad_norm": 0.8570723533630371,
+      "learning_rate": 9.811106913486967e-05,
+      "loss": 0.7621271133422851,
+      "step": 380
+    },
+    {
+      "epoch": 0.06998418626560345,
+      "grad_norm": 1.162699818611145,
+      "learning_rate": 9.792217604835664e-05,
+      "loss": 0.8825998306274414,
+      "step": 390
+    },
+    {
+      "epoch": 0.0717786525801061,
+      "grad_norm": 3.485926866531372,
+      "learning_rate": 9.77332829618436e-05,
+      "loss": 1.0364310264587402,
+      "step": 400
+    },
+    {
+      "epoch": 0.07357311889460875,
+      "grad_norm": 0.5732496380805969,
+      "learning_rate": 9.754438987533056e-05,
+      "loss": 0.7694174289703369,
+      "step": 410
+    },
+    {
+      "epoch": 0.07536758520911141,
+      "grad_norm": 0.683313250541687,
+      "learning_rate": 9.735549678881754e-05,
+      "loss": 0.7631448745727539,
+      "step": 420
+    },
+    {
+      "epoch": 0.07716205152361405,
+      "grad_norm": 0.8606892824172974,
+      "learning_rate": 9.716660370230451e-05,
+      "loss": 0.786726999282837,
+      "step": 430
+    },
+    {
+      "epoch": 0.0789565178381167,
+      "grad_norm": 1.1524667739868164,
+      "learning_rate": 9.697771061579146e-05,
+      "loss": 0.8868392944335938,
+      "step": 440
+    },
+    {
+      "epoch": 0.08075098415261936,
+      "grad_norm": 3.888843297958374,
+      "learning_rate": 9.678881752927843e-05,
+      "loss": 0.949896240234375,
+      "step": 450
+    },
+    {
+      "epoch": 0.08254545046712201,
+      "grad_norm": 0.540230393409729,
+      "learning_rate": 9.65999244427654e-05,
+      "loss": 0.7518480300903321,
+      "step": 460
+    },
+    {
+      "epoch": 0.08433991678162467,
+      "grad_norm": 0.7087560296058655,
+      "learning_rate": 9.641103135625237e-05,
+      "loss": 0.7413692474365234,
+      "step": 470
+    },
+    {
+      "epoch": 0.08613438309612732,
+      "grad_norm": 0.7639017105102539,
+      "learning_rate": 9.622213826973934e-05,
+      "loss": 0.8329146385192872,
+      "step": 480
+    },
+    {
+      "epoch": 0.08792884941062996,
+      "grad_norm": 1.0710383653640747,
+      "learning_rate": 9.60332451832263e-05,
+      "loss": 0.8491949081420899,
+      "step": 490
+    },
+    {
+      "epoch": 0.08972331572513262,
+      "grad_norm": 3.929804563522339,
+      "learning_rate": 9.584435209671326e-05,
+      "loss": 1.014235496520996,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5573,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0145643754992077e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:36324839c555b723546ca05f552d997ae3f0d4b9b817db61c11bbc2e65ec719c
+size 5265

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/README.md ADDED Viewed

	@@ -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-100pct-masked-weighted-v2/checkpoint-500/adapter_config.json ADDED Viewed

	@@ -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": [
+    "q_proj",
+    "in_proj_b",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "out_proj",
+    "in_proj_z",
+    "k_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "in_proj_a"
+  ],
+  "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-100pct-masked-weighted-v2/checkpoint-500/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:90ce164ea4415c1d512535e37647dfad4669f15274cceba22515c0d5f54a6d27
+size 134604152

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:99cacc22e9728e6b599b9fd6b823574377f16b958bc257e8f42e2f83aa921a2e
+size 269426431

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:90cf8e31f238979a8a77d1f114b86a765e07d4aa3555cdca9685305b07b578b8
+size 14645

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:490cfc293c61f546e9ca8bea24a6ff2f70f00dafb78159902250efed21573d84
+size 1465

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/trainer_state.json ADDED Viewed

	@@ -0,0 +1,384 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08972331572513262,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0017944663145026524,
+      "grad_norm": 2.403308153152466,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 1.210298442840576,
+      "step": 10
+    },
+    {
+      "epoch": 0.003588932629005305,
+      "grad_norm": 1.3837767839431763,
+      "learning_rate": 6.810035842293908e-06,
+      "loss": 1.238302230834961,
+      "step": 20
+    },
+    {
+      "epoch": 0.005383398943507958,
+      "grad_norm": 1.152842402458191,
+      "learning_rate": 1.039426523297491e-05,
+      "loss": 1.1493020057678223,
+      "step": 30
+    },
+    {
+      "epoch": 0.00717786525801061,
+      "grad_norm": 1.2282543182373047,
+      "learning_rate": 1.3978494623655914e-05,
+      "loss": 1.2698699951171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.008972331572513263,
+      "grad_norm": 4.5811686515808105,
+      "learning_rate": 1.7562724014336916e-05,
+      "loss": 1.336978054046631,
+      "step": 50
+    },
+    {
+      "epoch": 0.010766797887015915,
+      "grad_norm": 0.7280638217926025,
+      "learning_rate": 2.1146953405017922e-05,
+      "loss": 0.9929692268371582,
+      "step": 60
+    },
+    {
+      "epoch": 0.012561264201518567,
+      "grad_norm": 0.8359633684158325,
+      "learning_rate": 2.4731182795698928e-05,
+      "loss": 0.987311840057373,
+      "step": 70
+    },
+    {
+      "epoch": 0.01435573051602122,
+      "grad_norm": 1.061148762702942,
+      "learning_rate": 2.831541218637993e-05,
+      "loss": 1.0299980163574218,
+      "step": 80
+    },
+    {
+      "epoch": 0.01615019683052387,
+      "grad_norm": 1.4723000526428223,
+      "learning_rate": 3.1899641577060935e-05,
+      "loss": 1.1110344886779786,
+      "step": 90
+    },
+    {
+      "epoch": 0.017944663145026525,
+      "grad_norm": 5.412300109863281,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 1.1978090286254883,
+      "step": 100
+    },
+    {
+      "epoch": 0.019739129459529176,
+      "grad_norm": 0.7945532202720642,
+      "learning_rate": 3.906810035842295e-05,
+      "loss": 0.8953464508056641,
+      "step": 110
+    },
+    {
+      "epoch": 0.02153359577403183,
+      "grad_norm": 0.9241706728935242,
+      "learning_rate": 4.265232974910394e-05,
+      "loss": 0.8933357238769531,
+      "step": 120
+    },
+    {
+      "epoch": 0.023328062088534482,
+      "grad_norm": 1.2824897766113281,
+      "learning_rate": 4.6236559139784944e-05,
+      "loss": 0.9129752159118653,
+      "step": 130
+    },
+    {
+      "epoch": 0.025122528403037133,
+      "grad_norm": 1.8574696779251099,
+      "learning_rate": 4.982078853046595e-05,
+      "loss": 1.0019177436828612,
+      "step": 140
+    },
+    {
+      "epoch": 0.026916994717539788,
+      "grad_norm": 4.865994930267334,
+      "learning_rate": 5.340501792114696e-05,
+      "loss": 1.1639716148376464,
+      "step": 150
+    },
+    {
+      "epoch": 0.02871146103204244,
+      "grad_norm": 0.8981343507766724,
+      "learning_rate": 5.6989247311827965e-05,
+      "loss": 0.8498629570007324,
+      "step": 160
+    },
+    {
+      "epoch": 0.03050592734654509,
+      "grad_norm": 0.8773536086082458,
+      "learning_rate": 6.057347670250897e-05,
+      "loss": 0.8652203559875489,
+      "step": 170
+    },
+    {
+      "epoch": 0.03230039366104774,
+      "grad_norm": 1.2524876594543457,
+      "learning_rate": 6.415770609318996e-05,
+      "loss": 0.9427430152893066,
+      "step": 180
+    },
+    {
+      "epoch": 0.034094859975550396,
+      "grad_norm": 1.7148643732070923,
+      "learning_rate": 6.774193548387096e-05,
+      "loss": 0.9581910133361816,
+      "step": 190
+    },
+    {
+      "epoch": 0.03588932629005305,
+      "grad_norm": 5.458459854125977,
+      "learning_rate": 7.132616487455197e-05,
+      "loss": 1.1793695449829102,
+      "step": 200
+    },
+    {
+      "epoch": 0.037683792604555705,
+      "grad_norm": 0.7586544752120972,
+      "learning_rate": 7.491039426523297e-05,
+      "loss": 0.8673212051391601,
+      "step": 210
+    },
+    {
+      "epoch": 0.03947825891905835,
+      "grad_norm": 0.8580747246742249,
+      "learning_rate": 7.849462365591398e-05,
+      "loss": 0.8158726692199707,
+      "step": 220
+    },
+    {
+      "epoch": 0.04127272523356101,
+      "grad_norm": 1.0292130708694458,
+      "learning_rate": 8.207885304659499e-05,
+      "loss": 0.8816629409790039,
+      "step": 230
+    },
+    {
+      "epoch": 0.04306719154806366,
+      "grad_norm": 1.2191781997680664,
+      "learning_rate": 8.566308243727598e-05,
+      "loss": 0.9256319999694824,
+      "step": 240
+    },
+    {
+      "epoch": 0.04486165786256631,
+      "grad_norm": 4.896722316741943,
+      "learning_rate": 8.924731182795699e-05,
+      "loss": 1.054029369354248,
+      "step": 250
+    },
+    {
+      "epoch": 0.046656124177068964,
+      "grad_norm": 0.6555370688438416,
+      "learning_rate": 9.2831541218638e-05,
+      "loss": 0.8240686416625976,
+      "step": 260
+    },
+    {
+      "epoch": 0.04845059049157162,
+      "grad_norm": 0.8895808458328247,
+      "learning_rate": 9.6415770609319e-05,
+      "loss": 0.7868500232696534,
+      "step": 270
+    },
+    {
+      "epoch": 0.050245056806074266,
+      "grad_norm": 0.9253164529800415,
+      "learning_rate": 0.0001,
+      "loss": 0.821414852142334,
+      "step": 280
+    },
+    {
+      "epoch": 0.05203952312057692,
+      "grad_norm": 1.134040355682373,
+      "learning_rate": 9.981110691348697e-05,
+      "loss": 0.9013632774353028,
+      "step": 290
+    },
+    {
+      "epoch": 0.053833989435079575,
+      "grad_norm": 3.446653366088867,
+      "learning_rate": 9.962221382697394e-05,
+      "loss": 1.0495364189147949,
+      "step": 300
+    },
+    {
+      "epoch": 0.05562845574958222,
+      "grad_norm": 0.7303311824798584,
+      "learning_rate": 9.94333207404609e-05,
+      "loss": 0.7989195346832275,
+      "step": 310
+    },
+    {
+      "epoch": 0.05742292206408488,
+      "grad_norm": 0.8196483850479126,
+      "learning_rate": 9.924442765394787e-05,
+      "loss": 0.7937421798706055,
+      "step": 320
+    },
+    {
+      "epoch": 0.05921738837858753,
+      "grad_norm": 0.9366778135299683,
+      "learning_rate": 9.905553456743484e-05,
+      "loss": 0.809019660949707,
+      "step": 330
+    },
+    {
+      "epoch": 0.06101185469309018,
+      "grad_norm": 1.2467617988586426,
+      "learning_rate": 9.88666414809218e-05,
+      "loss": 0.930391502380371,
+      "step": 340
+    },
+    {
+      "epoch": 0.06280632100759284,
+      "grad_norm": 3.261760950088501,
+      "learning_rate": 9.867774839440876e-05,
+      "loss": 1.0620959281921387,
+      "step": 350
+    },
+    {
+      "epoch": 0.06460078732209548,
+      "grad_norm": 0.6342303156852722,
+      "learning_rate": 9.848885530789574e-05,
+      "loss": 0.8134325981140137,
+      "step": 360
+    },
+    {
+      "epoch": 0.06639525363659814,
+      "grad_norm": 0.6608202457427979,
+      "learning_rate": 9.82999622213827e-05,
+      "loss": 0.789882230758667,
+      "step": 370
+    },
+    {
+      "epoch": 0.06818971995110079,
+      "grad_norm": 0.8570723533630371,
+      "learning_rate": 9.811106913486967e-05,
+      "loss": 0.7621271133422851,
+      "step": 380
+    },
+    {
+      "epoch": 0.06998418626560345,
+      "grad_norm": 1.162699818611145,
+      "learning_rate": 9.792217604835664e-05,
+      "loss": 0.8825998306274414,
+      "step": 390
+    },
+    {
+      "epoch": 0.0717786525801061,
+      "grad_norm": 3.485926866531372,
+      "learning_rate": 9.77332829618436e-05,
+      "loss": 1.0364310264587402,
+      "step": 400
+    },
+    {
+      "epoch": 0.07357311889460875,
+      "grad_norm": 0.5732496380805969,
+      "learning_rate": 9.754438987533056e-05,
+      "loss": 0.7694174289703369,
+      "step": 410
+    },
+    {
+      "epoch": 0.07536758520911141,
+      "grad_norm": 0.683313250541687,
+      "learning_rate": 9.735549678881754e-05,
+      "loss": 0.7631448745727539,
+      "step": 420
+    },
+    {
+      "epoch": 0.07716205152361405,
+      "grad_norm": 0.8606892824172974,
+      "learning_rate": 9.716660370230451e-05,
+      "loss": 0.786726999282837,
+      "step": 430
+    },
+    {
+      "epoch": 0.0789565178381167,
+      "grad_norm": 1.1524667739868164,
+      "learning_rate": 9.697771061579146e-05,
+      "loss": 0.8868392944335938,
+      "step": 440
+    },
+    {
+      "epoch": 0.08075098415261936,
+      "grad_norm": 3.888843297958374,
+      "learning_rate": 9.678881752927843e-05,
+      "loss": 0.949896240234375,
+      "step": 450
+    },
+    {
+      "epoch": 0.08254545046712201,
+      "grad_norm": 0.540230393409729,
+      "learning_rate": 9.65999244427654e-05,
+      "loss": 0.7518480300903321,
+      "step": 460
+    },
+    {
+      "epoch": 0.08433991678162467,
+      "grad_norm": 0.7087560296058655,
+      "learning_rate": 9.641103135625237e-05,
+      "loss": 0.7413692474365234,
+      "step": 470
+    },
+    {
+      "epoch": 0.08613438309612732,
+      "grad_norm": 0.7639017105102539,
+      "learning_rate": 9.622213826973934e-05,
+      "loss": 0.8329146385192872,
+      "step": 480
+    },
+    {
+      "epoch": 0.08792884941062996,
+      "grad_norm": 1.0710383653640747,
+      "learning_rate": 9.60332451832263e-05,
+      "loss": 0.8491949081420899,
+      "step": 490
+    },
+    {
+      "epoch": 0.08972331572513262,
+      "grad_norm": 3.929804563522339,
+      "learning_rate": 9.584435209671326e-05,
+      "loss": 1.014235496520996,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5573,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0145643754992077e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:36324839c555b723546ca05f552d997ae3f0d4b9b817db61c11bbc2e65ec719c
+size 5265

qwen3.5-2b-100pct-masked-weighted-v2/config.yaml ADDED Viewed

	@@ -0,0 +1,67 @@

+model_id: Qwen/Qwen3.5-2B
+dataset_id: PedramR/ASR_Post-processing-dataset
+data_config: configs/data/default.yaml
+train_split: train
+eval_split: null
+eval_fraction: 0.1
+train_fraction: 1.0
+input_column: text_whisper
+target_column: text
+system_prompt: null
+include_punctuation: false
+output_dir: outputs/qwen-mask-weighted/qwen3.5-2b-100pct-masked-weighted-v2
+max_length: 2048
+on_long_example: drop
+mask_low_signal_corrections: true
+mask_min_similarity: 0.75
+mask_max_common_freq: 1
+recoverable_correction_weight: 2.0
+short_target_eos_weight: 0.3
+short_target_max_words: 20
+num_train_epochs: 1.0
+per_device_train_batch_size: 2
+per_device_eval_batch_size: 2
+gradient_accumulation_steps: 16
+learning_rate: 0.0001
+warmup_ratio: 0.05
+lr_scheduler_type: linear
+logging_steps: 10
+eval_steps: 500
+save_steps: 500
+save_total_limit: 3
+seed: 42
+early_stopping_patience: 3
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+load_in_4bit: false
+use_unsloth: false
+push_to_hub: true
+hub_repo_id: PedramR/ASR_Post-processing
+hub_repo_folder: qwen3.5-2b-100pct-masked-weighted-v2
+hub_private: false
+tensorboard_logging_dir: outputs/qwen-mask-weighted/qwen3.5-2b-100pct-masked-weighted-v2/tb
+resume_from_checkpoint: false
+lora_init_mode: fresh
+init_lora_from: null
+init_lora_from_subfolder: null
+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: 16
+test_max_examples: null
+test_checkpoint_max_examples: null
+test_checkpoint_eval_main: false
+test_hallucination_overlap_floor: 50.0
+test_premature_stop_ratio: 0.3
+test_premature_stop_min_input_words: 30
+test_repetition_penalty: 1.0
+test_no_repeat_ngram_size: 0
+test_baseline: true
+test_entity_dataset_id: PedramR/ASR_Post-processing-eval
+test_typo_dataset_id: PedramR/ASR_Post-processing-eval
+test_entity_row_type: entity
+test_typo_row_type: typo
+test_fix_weight: 0.5

qwen3.5-2b-100pct-masked-weighted-v2/resolved_config.yaml ADDED Viewed

	@@ -0,0 +1,57 @@

+model_id: Qwen/Qwen3.5-2B
+data_config: configs/data/default.yaml
+train_split: train
+eval_split: null
+eval_fraction: 0.1
+train_fraction: 1.0
+input_column: text_whisper
+target_column: text
+system_prompt: null
+output_dir: outputs/qwen-mask-weighted/qwen3.5-2b-100pct-masked-weighted-v2
+max_length: 2048
+on_long_example: drop
+mask_low_signal_corrections: true
+mask_min_similarity: 0.75
+mask_max_common_freq: 1
+recoverable_correction_weight: 2.0
+short_target_eos_weight: 0.3
+short_target_max_words: 20
+training:
+  num_train_epochs: 1.0
+  per_device_train_batch_size: 2
+  per_device_eval_batch_size: 2
+  gradient_accumulation_steps: 16
+  learning_rate: 0.0001
+  warmup_ratio: 0.05
+  logging_steps: 10
+  eval_steps: 500
+  save_steps: 500
+  save_total_limit: 3
+  seed: 42
+  early_stopping_patience: 3
+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-100pct-masked-weighted-v2
+  private: false
+tensorboard:
+  logging_dir: outputs/qwen-mask-weighted/qwen3.5-2b-100pct-masked-weighted-v2/tb
+test:
+  dataset_id: ErfanRou/callcc-test-1k
+  split: test
+  input_column: text_whisper
+  target_column: text
+  max_new_tokens: 1024
+  batch_size: 16
+  max_examples: null
+  checkpoint_max_examples: null
+  fix_weight: 0.5
+  checkpoint_eval_main: false
+resume_from_checkpoint: false
+use_unsloth: false

qwen3.5-2b-100pct-masked-weighted-v2/tb/events.out.tfevents.1790605476.02b48645612f.4580.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c89e173c0ed135eb5eb1ac01be76e66fd4ba283cddcfbbbadc58112f683dccce
+size 20087

qwen3.5-2b-100pct-masked-weighted-v2/test_eval_baseline/metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+  "wer": 0.26724399125199005,
+  "wer_zwnj_normalized": 0.25653208613594675,
+  "exact_match": 0.003033367037411527,
+  "fix_rate": 0.028386571209249135,
+  "preservation_rate": 0.9043148709482289,
+  "targeted_score": 0.46635072107873904,
+  "fix_rate_lenient": 0.02983948977751545,
+  "preservation_rate_lenient": 0.9093806936843613,
+  "targeted_score_lenient": 0.4696100917309384,
+  "fix_rate_recoverable": 0.030153097772668967,
+  "unrecoverable_targets": 966,
+  "hallucination_rate": 0.006066734074823054,
+  "premature_stop_rate": 0.006066734074823054,
+  "n_examples": 1978
+}

qwen3.5-2b-100pct-masked-weighted-v2/test_eval_baseline/predictions.jsonl ADDED Viewed