Upload 13 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",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_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:b5c6a59725418df59a6a6fdc28e47d78b6dd424e85d6343e661a880b20b47b47
+size 159967880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e92bad9d54861204c5bd9e9e68486e1b2f4e225b6c119d92e5aa826f3705dd
+size 320200274

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d4fbb4eb2a12b17b73babfa38b90bdafc73a682a0af60498a1e002b1fd5b3a
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7ae1d79be755d94030c63fe2e8483abc7a826d35307f4c5e39d3222c511c5c
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70732dec4f14211b78555ce1acfc091b59c12a05595924c42e5da10d3a62cd6d
+size 1064

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 +1,279 @@
+{
+  "best_global_step": null,
+  "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": 0.19107265770435333,
+      "learning_rate": 9.884057971014493e-05,
+      "loss": 1.497,
+      "step": 10
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.325986385345459,
+      "learning_rate": 9.594202898550724e-05,
+      "loss": 1.0934,
+      "step": 20
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.20094609260559082,
+      "learning_rate": 9.304347826086957e-05,
+      "loss": 0.5926,
+      "step": 30
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.1155015081167221,
+      "learning_rate": 9.01449275362319e-05,
+      "loss": 0.4471,
+      "step": 40
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.07334408909082413,
+      "learning_rate": 8.724637681159421e-05,
+      "loss": 0.4144,
+      "step": 50
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.06551826000213623,
+      "learning_rate": 8.434782608695653e-05,
+      "loss": 0.4008,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0648423582315445,
+      "learning_rate": 8.144927536231884e-05,
+      "loss": 0.4122,
+      "step": 70
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.06590145081281662,
+      "learning_rate": 7.855072463768116e-05,
+      "loss": 0.4008,
+      "step": 80
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.08473498374223709,
+      "learning_rate": 7.565217391304347e-05,
+      "loss": 0.3864,
+      "step": 90
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.06001104414463043,
+      "learning_rate": 7.27536231884058e-05,
+      "loss": 0.3976,
+      "step": 100
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.06179409101605415,
+      "learning_rate": 6.985507246376813e-05,
+      "loss": 0.3786,
+      "step": 110
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.062009744346141815,
+      "learning_rate": 6.695652173913044e-05,
+      "loss": 0.3828,
+      "step": 120
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.06417125463485718,
+      "learning_rate": 6.405797101449276e-05,
+      "loss": 0.3838,
+      "step": 130
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.06350455433130264,
+      "learning_rate": 6.115942028985507e-05,
+      "loss": 0.38,
+      "step": 140
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.06708157062530518,
+      "learning_rate": 5.826086956521739e-05,
+      "loss": 0.3752,
+      "step": 150
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.06464693695306778,
+      "learning_rate": 5.536231884057971e-05,
+      "loss": 0.3725,
+      "step": 160
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.0726727843284607,
+      "learning_rate": 5.2463768115942036e-05,
+      "loss": 0.3706,
+      "step": 170
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.06855019927024841,
+      "learning_rate": 4.956521739130435e-05,
+      "loss": 0.3725,
+      "step": 180
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.06969580799341202,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.3652,
+      "step": 190
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.08501672744750977,
+      "learning_rate": 4.3768115942028986e-05,
+      "loss": 0.3674,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10496016591787338,
+      "learning_rate": 4.086956521739131e-05,
+      "loss": 0.3626,
+      "step": 210
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.09126557409763336,
+      "learning_rate": 3.797101449275363e-05,
+      "loss": 0.3675,
+      "step": 220
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.06742043793201447,
+      "learning_rate": 3.5072463768115943e-05,
+      "loss": 0.3497,
+      "step": 230
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.07663198560476303,
+      "learning_rate": 3.217391304347826e-05,
+      "loss": 0.3477,
+      "step": 240
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.07194419205188751,
+      "learning_rate": 2.9275362318840583e-05,
+      "loss": 0.3498,
+      "step": 250
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.08223498612642288,
+      "learning_rate": 2.63768115942029e-05,
+      "loss": 0.3587,
+      "step": 260
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.0830773413181305,
+      "learning_rate": 2.347826086956522e-05,
+      "loss": 0.3447,
+      "step": 270
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0731896385550499,
+      "learning_rate": 2.0579710144927537e-05,
+      "loss": 0.3461,
+      "step": 280
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.07246264070272446,
+      "learning_rate": 1.7681159420289855e-05,
+      "loss": 0.3499,
+      "step": 290
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.07950613647699356,
+      "learning_rate": 1.4782608695652176e-05,
+      "loss": 0.3338,
+      "step": 300
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.07959512621164322,
+      "learning_rate": 1.1884057971014494e-05,
+      "loss": 0.3433,
+      "step": 310
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.07705967128276825,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 0.3497,
+      "step": 320
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.07584396004676819,
+      "learning_rate": 6.086956521739131e-06,
+      "loss": 0.3461,
+      "step": 330
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.0770997479557991,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 0.3419,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.08247802406549454,
+      "learning_rate": 2.898550724637681e-07,
+      "loss": 0.3512,
+      "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": 2.6122392741593088e+17,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa081d6c21fc6b7d736b628c8939570c4b061e4d2a1728bfaa2297ce1654d6be
+size 5560