Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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 sha256:4ffd2ef1a49c60c65b059b97b620faeb9a1a30f7fa3df5c48729793a8fb4ba6c
+size 33571624

checkpoint-380/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: TinyPixel/Llama-2-7B-bf16-sharded
+---
+
+# 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 0.10.0

checkpoint-380/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-380/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffd2ef1a49c60c65b059b97b620faeb9a1a30f7fa3df5c48729793a8fb4ba6c
+size 33571624

checkpoint-380/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90df5e0496acec27518ddf406acd9901a815b05877b925e9d4c884b1cb766ef
+size 67217018

checkpoint-380/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-380/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bad18e3c801326d631ce197264e3a77e02c6de697b4b22ff889633f8be3924
+size 14244

checkpoint-380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8f04e98c3eac435a55fac4d3bb3b9598b213120a9f4f81c9602631ee3fadd8
+size 1064

checkpoint-380/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-380/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-380/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1200,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-380/trainer_state.json

@@ -0,0 +1,462 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.18415243923664093,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.9158,
+      "step": 6
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.17151106894016266,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.8454,
+      "step": 12
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.253557026386261,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.9068,
+      "step": 18
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.44574955105781555,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.781,
+      "step": 24
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.3264688551425934,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.6487,
+      "step": 30
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.33505332469940186,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 0.6935,
+      "step": 36
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.3825117349624634,
+      "learning_rate": 0.0001976608187134503,
+      "loss": 0.606,
+      "step": 42
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.31299710273742676,
+      "learning_rate": 0.00019415204678362573,
+      "loss": 0.513,
+      "step": 48
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.5375415682792664,
+      "learning_rate": 0.00019064327485380117,
+      "loss": 0.5365,
+      "step": 54
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.4755648374557495,
+      "learning_rate": 0.0001871345029239766,
+      "loss": 0.3908,
+      "step": 60
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 0.9289490580558777,
+      "learning_rate": 0.00018362573099415207,
+      "loss": 0.3798,
+      "step": 66
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 0.4700639247894287,
+      "learning_rate": 0.0001801169590643275,
+      "loss": 0.4379,
+      "step": 72
+    },
+    {
+      "epoch": 4.11,
+      "grad_norm": 0.5703785419464111,
+      "learning_rate": 0.00017660818713450294,
+      "loss": 0.3724,
+      "step": 78
+    },
+    {
+      "epoch": 4.42,
+      "grad_norm": 0.6487219333648682,
+      "learning_rate": 0.00017309941520467836,
+      "loss": 0.3439,
+      "step": 84
+    },
+    {
+      "epoch": 4.74,
+      "grad_norm": 0.599611759185791,
+      "learning_rate": 0.0001695906432748538,
+      "loss": 0.2867,
+      "step": 90
+    },
+    {
+      "epoch": 5.05,
+      "grad_norm": 0.5314879417419434,
+      "learning_rate": 0.00016608187134502925,
+      "loss": 0.3,
+      "step": 96
+    },
+    {
+      "epoch": 5.37,
+      "grad_norm": 1.1346584558486938,
+      "learning_rate": 0.0001625730994152047,
+      "loss": 0.2441,
+      "step": 102
+    },
+    {
+      "epoch": 5.68,
+      "grad_norm": 0.7600080370903015,
+      "learning_rate": 0.00015906432748538012,
+      "loss": 0.2277,
+      "step": 108
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8896855711936951,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.2157,
+      "step": 114
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7400574684143066,
+      "learning_rate": 0.00015204678362573098,
+      "loss": 0.1671,
+      "step": 120
+    },
+    {
+      "epoch": 6.63,
+      "grad_norm": 0.7485764622688293,
+      "learning_rate": 0.00014853801169590643,
+      "loss": 0.2079,
+      "step": 126
+    },
+    {
+      "epoch": 6.95,
+      "grad_norm": 0.7054488658905029,
+      "learning_rate": 0.00014502923976608188,
+      "loss": 0.1424,
+      "step": 132
+    },
+    {
+      "epoch": 7.26,
+      "grad_norm": 1.1137595176696777,
+      "learning_rate": 0.00014152046783625732,
+      "loss": 0.1406,
+      "step": 138
+    },
+    {
+      "epoch": 7.58,
+      "grad_norm": 0.860434889793396,
+      "learning_rate": 0.00013801169590643274,
+      "loss": 0.1158,
+      "step": 144
+    },
+    {
+      "epoch": 7.89,
+      "grad_norm": 0.7475857138633728,
+      "learning_rate": 0.0001345029239766082,
+      "loss": 0.11,
+      "step": 150
+    },
+    {
+      "epoch": 8.21,
+      "grad_norm": 0.5861940979957581,
+      "learning_rate": 0.00013099415204678364,
+      "loss": 0.0968,
+      "step": 156
+    },
+    {
+      "epoch": 8.53,
+      "grad_norm": 0.6981809139251709,
+      "learning_rate": 0.00012748538011695908,
+      "loss": 0.104,
+      "step": 162
+    },
+    {
+      "epoch": 8.84,
+      "grad_norm": 0.7109177112579346,
+      "learning_rate": 0.0001239766081871345,
+      "loss": 0.0704,
+      "step": 168
+    },
+    {
+      "epoch": 9.16,
+      "grad_norm": 0.4005749523639679,
+      "learning_rate": 0.00012046783625730995,
+      "loss": 0.0757,
+      "step": 174
+    },
+    {
+      "epoch": 9.47,
+      "grad_norm": 0.719237744808197,
+      "learning_rate": 0.00011695906432748539,
+      "loss": 0.0697,
+      "step": 180
+    },
+    {
+      "epoch": 9.79,
+      "grad_norm": 0.9757436513900757,
+      "learning_rate": 0.00011345029239766083,
+      "loss": 0.0614,
+      "step": 186
+    },
+    {
+      "epoch": 10.11,
+      "grad_norm": 0.5613590478897095,
+      "learning_rate": 0.00010994152046783625,
+      "loss": 0.0496,
+      "step": 192
+    },
+    {
+      "epoch": 10.42,
+      "grad_norm": 0.49901968240737915,
+      "learning_rate": 0.00010643274853801171,
+      "loss": 0.0476,
+      "step": 198
+    },
+    {
+      "epoch": 10.74,
+      "grad_norm": 0.637506902217865,
+      "learning_rate": 0.00010292397660818713,
+      "loss": 0.0442,
+      "step": 204
+    },
+    {
+      "epoch": 11.05,
+      "grad_norm": 0.3163486421108246,
+      "learning_rate": 9.941520467836257e-05,
+      "loss": 0.0327,
+      "step": 210
+    },
+    {
+      "epoch": 11.37,
+      "grad_norm": 0.34687891602516174,
+      "learning_rate": 9.590643274853801e-05,
+      "loss": 0.0302,
+      "step": 216
+    },
+    {
+      "epoch": 11.68,
+      "grad_norm": 0.505370020866394,
+      "learning_rate": 9.239766081871345e-05,
+      "loss": 0.0278,
+      "step": 222
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.4929355382919312,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0429,
+      "step": 228
+    },
+    {
+      "epoch": 12.32,
+      "grad_norm": 0.2789619266986847,
+      "learning_rate": 8.538011695906433e-05,
+      "loss": 0.0213,
+      "step": 234
+    },
+    {
+      "epoch": 12.63,
+      "grad_norm": 0.41602373123168945,
+      "learning_rate": 8.187134502923976e-05,
+      "loss": 0.0188,
+      "step": 240
+    },
+    {
+      "epoch": 12.95,
+      "grad_norm": 0.38267752528190613,
+      "learning_rate": 7.836257309941521e-05,
+      "loss": 0.027,
+      "step": 246
+    },
+    {
+      "epoch": 13.26,
+      "grad_norm": 0.3227517008781433,
+      "learning_rate": 7.485380116959064e-05,
+      "loss": 0.0172,
+      "step": 252
+    },
+    {
+      "epoch": 13.58,
+      "grad_norm": 0.5111700892448425,
+      "learning_rate": 7.134502923976609e-05,
+      "loss": 0.0189,
+      "step": 258
+    },
+    {
+      "epoch": 13.89,
+      "grad_norm": 0.25930657982826233,
+      "learning_rate": 6.783625730994152e-05,
+      "loss": 0.0157,
+      "step": 264
+    },
+    {
+      "epoch": 14.21,
+      "grad_norm": 0.4176621437072754,
+      "learning_rate": 6.432748538011695e-05,
+      "loss": 0.0166,
+      "step": 270
+    },
+    {
+      "epoch": 14.53,
+      "grad_norm": 0.45017266273498535,
+      "learning_rate": 6.0818713450292395e-05,
+      "loss": 0.0148,
+      "step": 276
+    },
+    {
+      "epoch": 14.84,
+      "grad_norm": 0.2901971638202667,
+      "learning_rate": 5.7309941520467835e-05,
+      "loss": 0.013,
+      "step": 282
+    },
+    {
+      "epoch": 15.16,
+      "grad_norm": 0.1628808230161667,
+      "learning_rate": 5.3801169590643275e-05,
+      "loss": 0.0112,
+      "step": 288
+    },
+    {
+      "epoch": 15.47,
+      "grad_norm": 0.2727632224559784,
+      "learning_rate": 5.0292397660818715e-05,
+      "loss": 0.011,
+      "step": 294
+    },
+    {
+      "epoch": 15.79,
+      "grad_norm": 0.15591496229171753,
+      "learning_rate": 4.678362573099415e-05,
+      "loss": 0.0098,
+      "step": 300
+    },
+    {
+      "epoch": 16.11,
+      "grad_norm": 0.15791279077529907,
+      "learning_rate": 4.327485380116959e-05,
+      "loss": 0.013,
+      "step": 306
+    },
+    {
+      "epoch": 16.42,
+      "grad_norm": 0.07889483869075775,
+      "learning_rate": 3.976608187134503e-05,
+      "loss": 0.0116,
+      "step": 312
+    },
+    {
+      "epoch": 16.74,
+      "grad_norm": 0.12881968915462494,
+      "learning_rate": 3.625730994152047e-05,
+      "loss": 0.0088,
+      "step": 318
+    },
+    {
+      "epoch": 17.05,
+      "grad_norm": 0.1373162418603897,
+      "learning_rate": 3.274853801169591e-05,
+      "loss": 0.0078,
+      "step": 324
+    },
+    {
+      "epoch": 17.37,
+      "grad_norm": 0.07368919253349304,
+      "learning_rate": 2.9239766081871346e-05,
+      "loss": 0.0075,
+      "step": 330
+    },
+    {
+      "epoch": 17.68,
+      "grad_norm": 0.10508895665407181,
+      "learning_rate": 2.5730994152046783e-05,
+      "loss": 0.0085,
+      "step": 336
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.10840031504631042,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0079,
+      "step": 342
+    },
+    {
+      "epoch": 18.32,
+      "grad_norm": 0.07944358885288239,
+      "learning_rate": 1.871345029239766e-05,
+      "loss": 0.0072,
+      "step": 348
+    },
+    {
+      "epoch": 18.63,
+      "grad_norm": 0.10223820805549622,
+      "learning_rate": 1.5204678362573099e-05,
+      "loss": 0.008,
+      "step": 354
+    },
+    {
+      "epoch": 18.95,
+      "grad_norm": 0.11620509624481201,
+      "learning_rate": 1.1695906432748537e-05,
+      "loss": 0.0078,
+      "step": 360
+    },
+    {
+      "epoch": 19.26,
+      "grad_norm": 0.08788104355335236,
+      "learning_rate": 8.187134502923977e-06,
+      "loss": 0.0083,
+      "step": 366
+    },
+    {
+      "epoch": 19.58,
+      "grad_norm": 0.1308579444885254,
+      "learning_rate": 4.678362573099415e-06,
+      "loss": 0.0071,
+      "step": 372
+    },
+    {
+      "epoch": 19.89,
+      "grad_norm": 0.09444822371006012,
+      "learning_rate": 1.1695906432748538e-06,
+      "loss": 0.0079,
+      "step": 378
+    }
+  ],
+  "logging_steps": 6,
+  "max_steps": 380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 3.007882350034944e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b35f1702a8421b57910707769e782c258b2a2e7af81e526fb83d2c78fa7cc7
+size 4920

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1200,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b35f1702a8421b57910707769e782c258b2a2e7af81e526fb83d2c78fa7cc7
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "TinyPixel/Llama-2-7B-bf16-sharded",
+    "project_name": "myllm",
+    "data_path": "aienthuguy/casesTest",
+    "train_split": "test",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": -1,
+    "model_max_length": 1200,
+    "padding": null,
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": null,
+    "lr": 0.0002,
+    "epochs": 20,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": null,
+    "quantization": "int4",
+    "target_modules": null,
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "push_to_hub": true,
+    "repo_id": "aienthuguy/test_case_assistant",
+    "username": null
+}