checkpoint-50

edit-qwen3.5-2b/checkpoint-50/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

edit-qwen3.5-2b/checkpoint-50/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": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "in_proj_b",
+    "in_proj_z",
+    "o_proj",
+    "out_proj",
+    "in_proj_a",
+    "k_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "gate_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
+}

edit-qwen3.5-2b/checkpoint-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d832f0e7028771fce609568a9b4f180a858cb814f73d1e7249b02440397241f0
+size 134604152

edit-qwen3.5-2b/checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f35d00ee693c59692701624c37870bc1ac1fce5d3db9ccf3b386afab0acab59
+size 269426431

edit-qwen3.5-2b/checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8106c15826296de5d71c00671c582d299e589cc9f7689d0cd37d905ba9ea5c6d
+size 14645

edit-qwen3.5-2b/checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466b26b2fb2e52bf171794d0d11032cdaddebdfd2afd0dcc0ab4252a3aa9acd2
+size 1465

edit-qwen3.5-2b/checkpoint-50/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_global_step": 50,
+  "best_metric": 1.1613417863845825,
+  "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-50",
+  "epoch": 0.2881844380403458,
+  "eval_steps": 50,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05763688760806916,
+      "grad_norm": 8.908895492553711,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.8931264877319336,
+      "step": 10
+    },
+    {
+      "epoch": 0.11527377521613832,
+      "grad_norm": 10.213678359985352,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 1.3273126602172851,
+      "step": 20
+    },
+    {
+      "epoch": 0.1729106628242075,
+      "grad_norm": 4.915491580963135,
+      "learning_rate": 9.95959595959596e-05,
+      "loss": 1.0879782676696776,
+      "step": 30
+    },
+    {
+      "epoch": 0.23054755043227665,
+      "grad_norm": 7.094928741455078,
+      "learning_rate": 9.757575757575758e-05,
+      "loss": 1.152653121948242,
+      "step": 40
+    },
+    {
+      "epoch": 0.2881844380403458,
+      "grad_norm": 5.494155406951904,
+      "learning_rate": 9.555555555555557e-05,
+      "loss": 1.3036060333251953,
+      "step": 50
+    },
+    {
+      "epoch": 0.2881844380403458,
+      "eval_loss": 1.1613417863845825,
+      "eval_runtime": 2.5329,
+      "eval_samples_per_second": 56.853,
+      "eval_steps_per_second": 14.213,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 522,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3421478286965760.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

edit-qwen3.5-2b/checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33972d7442254fc5f6c1267830686f8be8e133c4a96736fbf8eb7e1ef4f9bd29
+size 5265

edit-qwen3.5-2b/config.yaml

@@ -0,0 +1,46 @@
+model_id: Qwen/Qwen3.5-2B
+output_dir: ./outputs/edit-qwen3.5-2b
+max_length: 1024
+data:
+  sources:
+  - PedramR/ASR_Post-processing-edit-dataset
+  min_window_words: 10
+  target_includes_original: true
+  train_fraction: null
+training:
+  num_train_epochs: 3.0
+  max_steps: -1
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 4
+  gradient_accumulation_steps: 4
+  learning_rate: 0.0001
+  warmup_ratio: 0.05
+  lr_scheduler_type: linear
+  logging_steps: 10
+  eval_steps: 50
+  save_steps: 50
+  save_total_limit: 2
+  seed: 42
+lora:
+  r: 32
+  alpha: 64
+  dropout: 0.05
+hub:
+  push_to_hub: true
+  repo_id: PedramR/ASR_Post-processing
+  folder: edit-qwen3.5-2b
+  private: true
+tensorboard:
+  logging_dir: null
+eval:
+  test_dataset_id: ErfanRou/callcc-test-1k
+  slices_dataset_id: PedramR/ASR_Post-processing-eval
+  corpus_freq_repo: PedramR/ASR_Post-processing-dataset
+  entities_dir: data/output-backup
+  window_words: 50
+  stride: 25
+  batch_size: 32
+  max_new_tokens: 128
+  max_examples: null
+  baseline: false
+  validation_generation: true

edit-qwen3.5-2b/tb/events.out.tfevents.1790604388.9b7939721266.4215.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db1b6639dd68b1d9e32fe838a18151a035e0ab24b3167dd2f251a969ab719fd
+size 6730