Initial model upload

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: bigcode-openrail-m
+base_model: bigcode/starcoder
+tags:
+- generated_from_trainer
+model-index:
+- name: starcoder-finetune
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# starcoder-finetune
+
+This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 35
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2.dev0
+- Transformers 4.53.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_attn",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7735461853d479d44c7d08042aa816d0e40fae541ca6e21a902a77077bc94b
+size 441754760

checkpoint-35/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bigcode/starcoder
+library_name: peft
+---
+
+# 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 0.15.2.dev0

checkpoint-35/adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_attn",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-35/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7735461853d479d44c7d08042aa816d0e40fae541ca6e21a902a77077bc94b
+size 441754760

checkpoint-35/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc527966c2ff9df28be541e5d72f923dc3d6b0cbe28812a179c9cdcde9e12b6
+size 883695034

checkpoint-35/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1812bf0f1deabf107f30b99a1298283b4312b6bec72e3b1d842fb41d9d085829
+size 14244

checkpoint-35/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cdce33ebc5972235a89e7008a7bf54a98fa227109b4975663485ad96089f907
+size 1064

checkpoint-35/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100.0,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 0.04918956756591797,
+      "learning_rate": 0.0,
+      "loss": 0.5625,
+      "step": 1
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.04941160976886749,
+      "learning_rate": 5e-05,
+      "loss": 0.5623,
+      "step": 2
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.05087224394083023,
+      "learning_rate": 0.0001,
+      "loss": 0.5009,
+      "step": 3
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 0.053648702800273895,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5467,
+      "step": 4
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.056984659284353256,
+      "learning_rate": 0.0002,
+      "loss": 0.5003,
+      "step": 5
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.06416453421115875,
+      "learning_rate": 0.00019948693233918952,
+      "loss": 0.4514,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.07367783039808273,
+      "learning_rate": 0.00019795299412524945,
+      "loss": 0.4195,
+      "step": 7
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.09809113293886185,
+      "learning_rate": 0.00019541392564000488,
+      "loss": 0.3534,
+      "step": 8
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.2686680257320404,
+      "learning_rate": 0.00019189578116202307,
+      "loss": 0.3339,
+      "step": 9
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.12331166863441467,
+      "learning_rate": 0.00018743466161445823,
+      "loss": 0.2941,
+      "step": 10
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 0.13653112947940826,
+      "learning_rate": 0.00018207634412072764,
+      "loss": 0.2648,
+      "step": 11
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.12992143630981445,
+      "learning_rate": 0.0001758758122692791,
+      "loss": 0.2015,
+      "step": 12
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 0.13980498909950256,
+      "learning_rate": 0.00016889669190756868,
+      "loss": 0.1789,
+      "step": 13
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1361037641763687,
+      "learning_rate": 0.0001612105982547663,
+      "loss": 0.1397,
+      "step": 14
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.11609825491905212,
+      "learning_rate": 0.00015289640103269625,
+      "loss": 0.1201,
+      "step": 15
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.099339060485363,
+      "learning_rate": 0.00014403941515576344,
+      "loss": 0.0973,
+      "step": 16
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 0.09612716734409332,
+      "learning_rate": 0.00013473052528448201,
+      "loss": 0.0855,
+      "step": 17
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.10055588185787201,
+      "learning_rate": 0.00012506525322587207,
+      "loss": 0.0849,
+      "step": 18
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 0.08217591792345047,
+      "learning_rate": 0.00011514277775045768,
+      "loss": 0.0725,
+      "step": 19
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07315342128276825,
+      "learning_rate": 0.00010506491688387127,
+      "loss": 0.0684,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.08092162758111954,
+      "learning_rate": 9.493508311612874e-05,
+      "loss": 0.0573,
+      "step": 21
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 0.06385105103254318,
+      "learning_rate": 8.485722224954237e-05,
+      "loss": 0.0594,
+      "step": 22
+    },
+    {
+      "epoch": 0.6571428571428571,
+      "grad_norm": 0.05351648107171059,
+      "learning_rate": 7.493474677412794e-05,
+      "loss": 0.0552,
+      "step": 23
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.05012252926826477,
+      "learning_rate": 6.526947471551798e-05,
+      "loss": 0.0607,
+      "step": 24
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.04566913843154907,
+      "learning_rate": 5.596058484423656e-05,
+      "loss": 0.0547,
+      "step": 25
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 0.044832587242126465,
+      "learning_rate": 4.710359896730379e-05,
+      "loss": 0.0483,
+      "step": 26
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.05177149549126625,
+      "learning_rate": 3.878940174523371e-05,
+      "loss": 0.0544,
+      "step": 27
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.04932279884815216,
+      "learning_rate": 3.110330809243134e-05,
+      "loss": 0.0483,
+      "step": 28
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 0.05275353044271469,
+      "learning_rate": 2.4124187730720917e-05,
+      "loss": 0.0479,
+      "step": 29
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.04073500633239746,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 0.0525,
+      "step": 30
+    },
+    {
+      "epoch": 0.8857142857142857,
+      "grad_norm": 0.04079524427652359,
+      "learning_rate": 1.2565338385541792e-05,
+      "loss": 0.0469,
+      "step": 31
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.06132270023226738,
+      "learning_rate": 8.10421883797694e-06,
+      "loss": 0.0421,
+      "step": 32
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.04404183104634285,
+      "learning_rate": 4.586074359995119e-06,
+      "loss": 0.0467,
+      "step": 33
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 0.03794850781559944,
+      "learning_rate": 2.0470058747505516e-06,
+      "loss": 0.0467,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.04732782021164894,
+      "learning_rate": 5.130676608104845e-07,
+      "loss": 0.0425,
+      "step": 35
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.2046170486276096e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-35/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b671e9c9edb8dfc9b290aee0d9cf45701cf889d4eda48c3d083d9855beeaa1f
+size 5368

runs/Jun06_06-53-39_193fa9622865/events.out.tfevents.1749193234.193fa9622865.6025.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e89fdf1bd1ca85299e4bdf4a53cdb12eb9ee9d77e12aeed52a84af85508470
+size 13346

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b671e9c9edb8dfc9b290aee0d9cf45701cf889d4eda48c3d083d9855beeaa1f
+size 5368