Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/codellama-7b-bnb-4bit
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/codellama-7b-bnb-4bit",
+  "bias": "none",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260cd1a574f76faaa3856cc307218b43cd876caf720957179e2a02f1ae86a6e5
+size 159967880

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,89 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,278 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.1637864112854004,
+      "learning_rate": 9.855072463768117e-05,
+      "loss": 1.4164,
+      "step": 10
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.1787765920162201,
+      "learning_rate": 9.565217391304348e-05,
+      "loss": 1.174,
+      "step": 20
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.08280404657125473,
+      "learning_rate": 9.27536231884058e-05,
+      "loss": 1.0135,
+      "step": 30
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.09532860666513443,
+      "learning_rate": 8.985507246376813e-05,
+      "loss": 0.9882,
+      "step": 40
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.08886633068323135,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 0.9254,
+      "step": 50
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.09311848133802414,
+      "learning_rate": 8.405797101449276e-05,
+      "loss": 0.9094,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1008237674832344,
+      "learning_rate": 8.115942028985508e-05,
+      "loss": 0.9208,
+      "step": 70
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.10439296066761017,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 0.871,
+      "step": 80
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.10166755318641663,
+      "learning_rate": 7.536231884057971e-05,
+      "loss": 0.9004,
+      "step": 90
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.11678331345319748,
+      "learning_rate": 7.246376811594203e-05,
+      "loss": 0.8548,
+      "step": 100
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.11469922214746475,
+      "learning_rate": 6.956521739130436e-05,
+      "loss": 0.8719,
+      "step": 110
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.125005841255188,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8339,
+      "step": 120
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.11550814658403397,
+      "learning_rate": 6.376811594202898e-05,
+      "loss": 0.8425,
+      "step": 130
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13516126573085785,
+      "learning_rate": 6.086956521739131e-05,
+      "loss": 0.8386,
+      "step": 140
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.12944644689559937,
+      "learning_rate": 5.797101449275363e-05,
+      "loss": 0.8006,
+      "step": 150
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.16765905916690826,
+      "learning_rate": 5.507246376811594e-05,
+      "loss": 0.8365,
+      "step": 160
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.17174550890922546,
+      "learning_rate": 5.217391304347826e-05,
+      "loss": 0.7982,
+      "step": 170
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.15086913108825684,
+      "learning_rate": 4.9275362318840584e-05,
+      "loss": 0.7715,
+      "step": 180
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.16416020691394806,
+      "learning_rate": 4.63768115942029e-05,
+      "loss": 0.7639,
+      "step": 190
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.18936575949192047,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.7792,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19060809910297394,
+      "learning_rate": 4.057971014492754e-05,
+      "loss": 0.8405,
+      "step": 210
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.1784086376428604,
+      "learning_rate": 3.7681159420289856e-05,
+      "loss": 0.7534,
+      "step": 220
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.2145889848470688,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 0.7545,
+      "step": 230
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.20068179070949554,
+      "learning_rate": 3.188405797101449e-05,
+      "loss": 0.79,
+      "step": 240
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.18748420476913452,
+      "learning_rate": 2.8985507246376814e-05,
+      "loss": 0.7743,
+      "step": 250
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.1932465136051178,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.7446,
+      "step": 260
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.20865367352962494,
+      "learning_rate": 2.318840579710145e-05,
+      "loss": 0.7449,
+      "step": 270
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2029721885919571,
+      "learning_rate": 2.028985507246377e-05,
+      "loss": 0.7537,
+      "step": 280
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.18854071199893951,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.7487,
+      "step": 290
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.20792965590953827,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.7065,
+      "step": 300
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.2359679788351059,
+      "learning_rate": 1.1594202898550725e-05,
+      "loss": 0.7282,
+      "step": 310
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.22090750932693481,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.7542,
+      "step": 320
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.21407246589660645,
+      "learning_rate": 5.797101449275362e-06,
+      "loss": 0.7101,
+      "step": 330
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.21997196972370148,
+      "learning_rate": 2.898550724637681e-06,
+      "loss": 0.7535,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2235373854637146,
+      "learning_rate": 0.0,
+      "loss": 0.7411,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 350,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 3.2986802715377664e+17,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": null
+}