checkpoint-500

qwen3.5-2b/checkpoint-500/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-500/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": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "out_proj",
+    "in_proj_a",
+    "in_proj_qkv",
+    "in_proj_z",
+    "o_proj",
+    "in_proj_b",
+    "v_proj",
+    "k_proj",
+    "q_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-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633ed337666dfcbcc0fa91b11deee60e73e50d77410f5889ec22424e5ed6b94b
+size 134604152

qwen3.5-2b/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611ff8f3c45096fd8fbadbb0a254aee6a2ae017ab461e4a0f637944fec6ecc30
+size 269426431

qwen3.5-2b/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7804c1f3cddd1d7f765d5c549a0cd3f4bbf8a40211ccaeb0a728ea79475d9fcd
+size 14645

qwen3.5-2b/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41719c07cf06e0513c67fe4875b99706eda676090f324d8739cc5f84e65d03d9
+size 1465

qwen3.5-2b/checkpoint-500/trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.26393929396238863,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005278785879247773,
+      "grad_norm": 1.305302381515503,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.8562479972839355,
+      "step": 10
+    },
+    {
+      "epoch": 0.010557571758495546,
+      "grad_norm": 0.9230896830558777,
+      "learning_rate": 4e-05,
+      "loss": 0.7965596675872803,
+      "step": 20
+    },
+    {
+      "epoch": 0.01583635763774332,
+      "grad_norm": 0.7995359301567078,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.7992881298065185,
+      "step": 30
+    },
+    {
+      "epoch": 0.02111514351699109,
+      "grad_norm": 0.7340251207351685,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.6521625995635987,
+      "step": 40
+    },
+    {
+      "epoch": 0.026393929396238865,
+      "grad_norm": 1.0072991847991943,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.6839987277984619,
+      "step": 50
+    },
+    {
+      "epoch": 0.03167271527548664,
+      "grad_norm": 0.8970349431037903,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.6341384887695313,
+      "step": 60
+    },
+    {
+      "epoch": 0.03695150115473441,
+      "grad_norm": 0.883733332157135,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.6603663444519043,
+      "step": 70
+    },
+    {
+      "epoch": 0.04223028703398218,
+      "grad_norm": 0.8134523630142212,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.6564276695251465,
+      "step": 80
+    },
+    {
+      "epoch": 0.047509072913229956,
+      "grad_norm": 0.8890961408615112,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.6585474967956543,
+      "step": 90
+    },
+    {
+      "epoch": 0.05278785879247773,
+      "grad_norm": 0.7649273872375488,
+      "learning_rate": 0.00019955555555555558,
+      "loss": 0.6272543430328369,
+      "step": 100
+    },
+    {
+      "epoch": 0.0580666446717255,
+      "grad_norm": 0.7554565072059631,
+      "learning_rate": 0.00019844444444444445,
+      "loss": 0.5757376194000244,
+      "step": 110
+    },
+    {
+      "epoch": 0.06334543055097328,
+      "grad_norm": 0.7954307794570923,
+      "learning_rate": 0.00019733333333333335,
+      "loss": 0.641472053527832,
+      "step": 120
+    },
+    {
+      "epoch": 0.06862421643022105,
+      "grad_norm": 0.672359824180603,
+      "learning_rate": 0.00019622222222222225,
+      "loss": 0.563064432144165,
+      "step": 130
+    },
+    {
+      "epoch": 0.07390300230946882,
+      "grad_norm": 0.6992788314819336,
+      "learning_rate": 0.0001951111111111111,
+      "loss": 0.600986099243164,
+      "step": 140
+    },
+    {
+      "epoch": 0.0791817881887166,
+      "grad_norm": 0.6328181028366089,
+      "learning_rate": 0.000194,
+      "loss": 0.5295759201049804,
+      "step": 150
+    },
+    {
+      "epoch": 0.08446057406796437,
+      "grad_norm": 0.6692398190498352,
+      "learning_rate": 0.0001928888888888889,
+      "loss": 0.6027700901031494,
+      "step": 160
+    },
+    {
+      "epoch": 0.08973935994721215,
+      "grad_norm": 0.7081276774406433,
+      "learning_rate": 0.0001917777777777778,
+      "loss": 0.5615420341491699,
+      "step": 170
+    },
+    {
+      "epoch": 0.09501814582645991,
+      "grad_norm": 0.5484495759010315,
+      "learning_rate": 0.00019066666666666668,
+      "loss": 0.5883731842041016,
+      "step": 180
+    },
+    {
+      "epoch": 0.10029693170570769,
+      "grad_norm": 0.7612242102622986,
+      "learning_rate": 0.00018955555555555558,
+      "loss": 0.5624749183654785,
+      "step": 190
+    },
+    {
+      "epoch": 0.10557571758495546,
+      "grad_norm": 0.678548276424408,
+      "learning_rate": 0.00018844444444444445,
+      "loss": 0.5546360969543457,
+      "step": 200
+    },
+    {
+      "epoch": 0.11085450346420324,
+      "grad_norm": 0.5756900906562805,
+      "learning_rate": 0.00018733333333333335,
+      "loss": 0.5600387573242187,
+      "step": 210
+    },
+    {
+      "epoch": 0.116133289343451,
+      "grad_norm": 0.5475565791130066,
+      "learning_rate": 0.00018622222222222223,
+      "loss": 0.5820147037506104,
+      "step": 220
+    },
+    {
+      "epoch": 0.12141207522269878,
+      "grad_norm": 0.6964915990829468,
+      "learning_rate": 0.00018511111111111113,
+      "loss": 0.5699102401733398,
+      "step": 230
+    },
+    {
+      "epoch": 0.12669086110194655,
+      "grad_norm": 0.6508777737617493,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5863839626312256,
+      "step": 240
+    },
+    {
+      "epoch": 0.13196964698119432,
+      "grad_norm": 0.6375535726547241,
+      "learning_rate": 0.00018288888888888887,
+      "loss": 0.5772487640380859,
+      "step": 250
+    },
+    {
+      "epoch": 0.1372484328604421,
+      "grad_norm": 0.5595227479934692,
+      "learning_rate": 0.00018177777777777778,
+      "loss": 0.603016710281372,
+      "step": 260
+    },
+    {
+      "epoch": 0.14252721873968988,
+      "grad_norm": 0.5612871646881104,
+      "learning_rate": 0.00018066666666666668,
+      "loss": 0.5080572605133057,
+      "step": 270
+    },
+    {
+      "epoch": 0.14780600461893764,
+      "grad_norm": 0.762787938117981,
+      "learning_rate": 0.00017955555555555558,
+      "loss": 0.6409445762634277,
+      "step": 280
+    },
+    {
+      "epoch": 0.1530847904981854,
+      "grad_norm": 0.6885519623756409,
+      "learning_rate": 0.00017844444444444445,
+      "loss": 0.6149398803710937,
+      "step": 290
+    },
+    {
+      "epoch": 0.1583635763774332,
+      "grad_norm": 0.6986534595489502,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 0.5259696960449218,
+      "step": 300
+    },
+    {
+      "epoch": 0.16364236225668097,
+      "grad_norm": 0.601087212562561,
+      "learning_rate": 0.00017622222222222223,
+      "loss": 0.6464223384857177,
+      "step": 310
+    },
+    {
+      "epoch": 0.16892114813592873,
+      "grad_norm": 0.4432871639728546,
+      "learning_rate": 0.00017511111111111113,
+      "loss": 0.509718942642212,
+      "step": 320
+    },
+    {
+      "epoch": 0.1741999340151765,
+      "grad_norm": 0.5295445322990417,
+      "learning_rate": 0.000174,
+      "loss": 0.5282030582427979,
+      "step": 330
+    },
+    {
+      "epoch": 0.1794787198944243,
+      "grad_norm": 0.695189893245697,
+      "learning_rate": 0.0001728888888888889,
+      "loss": 0.5390444278717041,
+      "step": 340
+    },
+    {
+      "epoch": 0.18475750577367206,
+      "grad_norm": 0.6871212124824524,
+      "learning_rate": 0.0001717777777777778,
+      "loss": 0.6001670360565186,
+      "step": 350
+    },
+    {
+      "epoch": 0.19003629165291983,
+      "grad_norm": 0.5886061787605286,
+      "learning_rate": 0.00017066666666666668,
+      "loss": 0.5532281875610352,
+      "step": 360
+    },
+    {
+      "epoch": 0.1953150775321676,
+      "grad_norm": 0.4359692931175232,
+      "learning_rate": 0.00016955555555555555,
+      "loss": 0.5710611343383789,
+      "step": 370
+    },
+    {
+      "epoch": 0.20059386341141539,
+      "grad_norm": 0.5859516859054565,
+      "learning_rate": 0.00016844444444444445,
+      "loss": 0.527172040939331,
+      "step": 380
+    },
+    {
+      "epoch": 0.20587264929066315,
+      "grad_norm": 0.595167875289917,
+      "learning_rate": 0.00016733333333333335,
+      "loss": 0.5060821056365967,
+      "step": 390
+    },
+    {
+      "epoch": 0.21115143516991092,
+      "grad_norm": 0.5597789883613586,
+      "learning_rate": 0.00016622222222222223,
+      "loss": 0.5472925186157227,
+      "step": 400
+    },
+    {
+      "epoch": 0.21643022104915868,
+      "grad_norm": 0.5002998113632202,
+      "learning_rate": 0.00016511111111111113,
+      "loss": 0.5917861461639404,
+      "step": 410
+    },
+    {
+      "epoch": 0.22170900692840648,
+      "grad_norm": 0.6672388911247253,
+      "learning_rate": 0.000164,
+      "loss": 0.5691781044006348,
+      "step": 420
+    },
+    {
+      "epoch": 0.22698779280765424,
+      "grad_norm": 0.580162763595581,
+      "learning_rate": 0.0001628888888888889,
+      "loss": 0.5123159408569335,
+      "step": 430
+    },
+    {
+      "epoch": 0.232266578686902,
+      "grad_norm": 0.5568054914474487,
+      "learning_rate": 0.00016177777777777778,
+      "loss": 0.5455626010894775,
+      "step": 440
+    },
+    {
+      "epoch": 0.23754536456614977,
+      "grad_norm": 0.6651593446731567,
+      "learning_rate": 0.00016066666666666668,
+      "loss": 0.5399269104003906,
+      "step": 450
+    },
+    {
+      "epoch": 0.24282415044539757,
+      "grad_norm": 0.5001797080039978,
+      "learning_rate": 0.00015955555555555558,
+      "loss": 0.5277121543884278,
+      "step": 460
+    },
+    {
+      "epoch": 0.24810293632464533,
+      "grad_norm": 0.5514921545982361,
+      "learning_rate": 0.00015844444444444445,
+      "loss": 0.5342081546783447,
+      "step": 470
+    },
+    {
+      "epoch": 0.2533817222038931,
+      "grad_norm": 0.5599192380905151,
+      "learning_rate": 0.00015733333333333333,
+      "loss": 0.5150089263916016,
+      "step": 480
+    },
+    {
+      "epoch": 0.2586605080831409,
+      "grad_norm": 0.563194215297699,
+      "learning_rate": 0.00015622222222222223,
+      "loss": 0.5231950759887696,
+      "step": 490
+    },
+    {
+      "epoch": 0.26393929396238863,
+      "grad_norm": 0.7210673689842224,
+      "learning_rate": 0.00015511111111111113,
+      "loss": 0.5708573818206787,
+      "step": 500
+    },
+    {
+      "epoch": 0.26393929396238863,
+      "eval_loss": 0.534747838973999,
+      "eval_runtime": 459.3797,
+      "eval_samples_per_second": 24.383,
+      "eval_steps_per_second": 6.097,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1895,
+  "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": 5.972716588318771e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f5227842d4c60d51e48d582480b968b2a26456e3111e78999104a00e72c35c
+size 5265

qwen3.5-2b/config.yaml

@@ -3,22 +3,22 @@ dataset_id: ./asr_dataset_curated.jsonl
 train_split: train
 eval_split: null
 eval_fraction: 0.1
-train_fraction: 0.2
+train_fraction: 0.3
 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
+num_train_epochs: 1.0
+per_device_train_batch_size: 2
 per_device_eval_batch_size: 4
-gradient_accumulation_steps: 4
+gradient_accumulation_steps: 8
 learning_rate: 0.0002
 warmup_ratio: 0.05
 logging_steps: 10
-eval_steps: 100
-save_steps: 100
+eval_steps: 500
+save_steps: 500
 save_total_limit: 3
 seed: 42
 lora_r: 32
@@ -36,7 +36,7 @@ test_split: test
 test_input_column: text_whisper
 test_target_column: text
 test_max_new_tokens: 1024
-test_batch_size: 16
+test_batch_size: 8
 test_max_examples: 128
 test_checkpoint_max_examples: 128
 test_hallucination_overlap_floor: 50.0

qwen3.5-2b/resolved_config.yaml

@@ -3,7 +3,7 @@ dataset_id: ./asr_dataset_curated.jsonl
 train_split: train
 eval_split: null
 eval_fraction: 0.1
-train_fraction: 0.2
+train_fraction: 0.3
 input_column: text_whisper
 target_column: text
 system_prompt: null
@@ -11,15 +11,15 @@ 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
+  num_train_epochs: 1.0
+  per_device_train_batch_size: 2
   per_device_eval_batch_size: 4
-  gradient_accumulation_steps: 4
+  gradient_accumulation_steps: 8
   learning_rate: 0.0002
   warmup_ratio: 0.05
   logging_steps: 10
-  eval_steps: 100
-  save_steps: 100
+  eval_steps: 500
+  save_steps: 500
   save_total_limit: 3
   seed: 42
 lora:
@@ -41,7 +41,7 @@ test:
   input_column: text_whisper
   target_column: text
   max_new_tokens: 1024
-  batch_size: 16
+  batch_size: 8
   max_examples: 128
   checkpoint_max_examples: 128
 resume_from_checkpoint: false

qwen3.5-2b/tb/events.out.tfevents.1789940092.fed349279e2c.7945.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5edf34af6e6409c44a51117c3eefbd65e6a29dd830b5076248406a1704c1ab4
-size 8223
+oid sha256:77bc6da8bece00ec6484b561a5b384b999685f7234487860991e429a7adbbf15
+size 9059

qwen3.5-2b/tb/events.out.tfevents.1789942145.fed349279e2c.8211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28bdce6a24aa7629b8f847f17deb349f7296ec63e987d7db3f5fa8e21c9eab0
+size 16665

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

@@ -1,6 +1,6 @@
 {
-  "wer": 0.21637664248389224,
+  "wer": 0.4919080716351276,
   "exact_match": 0.0,
-  "hallucination_rate": 0.0,
+  "hallucination_rate": 0.09375,
   "n_examples": 128
 }

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

@@ -1,5 +1,5 @@
 {
-  "wer": 0.28090913703008474,
+  "wer": 0.28095987012328144,
   "exact_match": 0.0,
   "hallucination_rate": 0.015625,
   "n_examples": 128