Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_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:e52e5de0d1b873cba47bf4145ac07c1063dfd13c74a3ce7536f96788b2eba1a5
+size 335604696

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddd883df0233482261a654462804797bd9c8ad6aa98bfb1c3bc8e07cba80f90
+size 170920084

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22aabfa2f2fd91f64e86fe1cd4039bfeb4d4353977175431d7ec5747a6ee332
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "[control_768]",
+    "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 46,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 19.929826736450195,
+      "learning_rate": 4.000000000000001e-06,
+      "logits/chosen": -3.0748565196990967,
+      "logits/rejected": -3.152794599533081,
+      "logps/chosen": -36.31090545654297,
+      "logps/rejected": -134.4405059814453,
+      "loss": 0.3779,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.6441326141357422,
+      "rewards/margins": 0.904403567314148,
+      "rewards/rejected": -0.26027101278305054,
+      "step": 5
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 3.05119252204895,
+      "learning_rate": 4.883490980137327e-06,
+      "logits/chosen": -3.1105563640594482,
+      "logits/rejected": -3.1778032779693604,
+      "logps/chosen": -36.36132049560547,
+      "logps/rejected": -153.5985107421875,
+      "loss": 0.0799,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.6721876263618469,
+      "rewards/margins": 3.4296391010284424,
+      "rewards/rejected": -2.7574515342712402,
+      "step": 10
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 1.094469428062439,
+      "learning_rate": 4.428722949554858e-06,
+      "logits/chosen": -3.132211685180664,
+      "logits/rejected": -3.186828136444092,
+      "logps/chosen": -37.853267669677734,
+      "logps/rejected": -183.9494171142578,
+      "loss": 0.0219,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.2748956084251404,
+      "rewards/margins": 6.2910261154174805,
+      "rewards/rejected": -6.016129970550537,
+      "step": 15
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.7709254026412964,
+      "learning_rate": 3.6942995462806574e-06,
+      "logits/chosen": -3.1636807918548584,
+      "logits/rejected": -3.2063403129577637,
+      "logps/chosen": -45.52863693237305,
+      "logps/rejected": -208.6585693359375,
+      "loss": 0.0069,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.3155127465724945,
+      "rewards/margins": 8.49041748046875,
+      "rewards/rejected": -8.805930137634277,
+      "step": 20
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.9683974385261536,
+      "learning_rate": 2.786708563496002e-06,
+      "logits/chosen": -3.113715410232544,
+      "logits/rejected": -3.1793715953826904,
+      "logps/chosen": -51.341712951660156,
+      "logps/rejected": -242.5277557373047,
+      "loss": 0.0146,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.7139601111412048,
+      "rewards/margins": 10.961573600769043,
+      "rewards/rejected": -11.675535202026367,
+      "step": 25
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.03986353427171707,
+      "learning_rate": 1.8375462445083464e-06,
+      "logits/chosen": -3.1167349815368652,
+      "logits/rejected": -3.1624913215637207,
+      "logps/chosen": -54.55385208129883,
+      "logps/rejected": -239.08016967773438,
+      "loss": 0.0179,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.0596555471420288,
+      "rewards/margins": 11.23798942565918,
+      "rewards/rejected": -12.297645568847656,
+      "step": 30
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 1.12047278881073,
+      "learning_rate": 9.844364725834058e-07,
+      "logits/chosen": -3.0820581912994385,
+      "logits/rejected": -3.2092998027801514,
+      "logps/chosen": -49.54092788696289,
+      "logps/rejected": -246.6052703857422,
+      "loss": 0.0341,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.7901324033737183,
+      "rewards/margins": 12.993329048156738,
+      "rewards/rejected": -13.783464431762695,
+      "step": 35
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.246961310505867,
+      "learning_rate": 3.510759825319976e-07,
+      "logits/chosen": -3.0782217979431152,
+      "logits/rejected": -3.200848340988159,
+      "logps/chosen": -52.44266891479492,
+      "logps/rejected": -264.9075012207031,
+      "loss": 0.0246,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.9691983461380005,
+      "rewards/margins": 13.385457992553711,
+      "rewards/rejected": -14.354657173156738,
+      "step": 40
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 3.052009105682373,
+      "learning_rate": 2.9298940549128962e-08,
+      "logits/chosen": -3.0829412937164307,
+      "logits/rejected": -3.2069015502929688,
+      "logps/chosen": -53.714805603027344,
+      "logps/rejected": -255.4803009033203,
+      "loss": 0.0202,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.093703269958496,
+      "rewards/margins": 12.441967964172363,
+      "rewards/rejected": -13.535670280456543,
+      "step": 45
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 46,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a970c0e24d36a0d6a6929cef1b3fa169fda9489e7d5e1c3ae8f40d84ebf09faa
+size 6200