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": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": [
+    "v_proj",
+    "q_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:abf6245cfabca86f5f92e466574a55d5aa2e2a1f7daedebb32fbd71f3722a064
+size 9022864

checkpoint-2727/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+---
+
+# 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-2727/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2727/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf6245cfabca86f5f92e466574a55d5aa2e2a1f7daedebb32fbd71f3722a064
+size 9022864

checkpoint-2727/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f925838e714bbb5948d42d248b6aac131b6688a34d8466fb889b39769acfe129
+size 18096570

checkpoint-2727/pytorch_model.bin

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

checkpoint-2727/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0100c9bbee45d1b1ed84834d0052e4d095914155c0fe7516ff38ade7e7ed6ce7
+size 14244

checkpoint-2727/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86317a93c4ee327ce7a7995d093fc399e0212ec59d3fb966eca87d43d63b2cc3
+size 1064

checkpoint-2727/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2727/tokenizer.model

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

checkpoint-2727/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2727/trainer_state.json

@@ -0,0 +1,973 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998166819431714,
+  "eval_steps": 500,
+  "global_step": 2727,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4652014652014653e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9304029304029305e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3956043956043955e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.0,
+      "learning_rate": 5.860805860805861e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.0,
+      "learning_rate": 7.326007326007326e-05,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.0,
+      "learning_rate": 8.791208791208791e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010256410256410256,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011721611721611722,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013186813186813188,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014652014652014652,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016117216117216118,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017582417582417582,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019047619047619048,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019942950285248574,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000197799511002445,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019616951915240425,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019453952730236348,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019290953545232276,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019127954360228199,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018964955175224124,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001880195599022005,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018638956805215975,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000184759576202119,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018312958435207826,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001814995925020375,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017986960065199674,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000178239608801956,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017660961695191524,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001749796251018745,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017334963325183375,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000171719641401793,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017008964955175223,
+      "loss": 0.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016845965770171151,
+      "loss": 0.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016682966585167074,
+      "loss": 0.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016519967400163,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016356968215158925,
+      "loss": 0.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001619396903015485,
+      "loss": 0.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016030969845150773,
+      "loss": 0.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000158679706601467,
+      "loss": 0.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015704971475142624,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015541972290138552,
+      "loss": 0.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015378973105134475,
+      "loss": 0.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000152159739201304,
+      "loss": 0.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015052974735126325,
+      "loss": 0.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001488997555012225,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014726976365118173,
+      "loss": 0.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014563977180114102,
+      "loss": 0.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014400977995110024,
+      "loss": 0.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001423797881010595,
+      "loss": 0.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014074979625101875,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000139119804400978,
+      "loss": 0.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013748981255093726,
+      "loss": 0.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001358598207008965,
+      "loss": 0.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013422982885085577,
+      "loss": 0.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000132599837000815,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013096984515077427,
+      "loss": 0.0,
+      "step": 1120
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001293398533007335,
+      "loss": 0.0,
+      "step": 1140
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012770986145069276,
+      "loss": 0.0,
+      "step": 1160
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000126079869600652,
+      "loss": 0.0,
+      "step": 1180
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012444987775061126,
+      "loss": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001228198859005705,
+      "loss": 0.0,
+      "step": 1220
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012118989405052976,
+      "loss": 0.0,
+      "step": 1240
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000119559902200489,
+      "loss": 0.0,
+      "step": 1260
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011792991035044825,
+      "loss": 0.0,
+      "step": 1280
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001162999185004075,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011466992665036676,
+      "loss": 0.0,
+      "step": 1320
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000113039934800326,
+      "loss": 0.0,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011140994295028527,
+      "loss": 0.0,
+      "step": 1360
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010977995110024451,
+      "loss": 0.0,
+      "step": 1380
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010814995925020375,
+      "loss": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010651996740016302,
+      "loss": 0.0,
+      "step": 1420
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010488997555012226,
+      "loss": 0.0,
+      "step": 1440
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001032599837000815,
+      "loss": 0.0,
+      "step": 1460
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010162999185004076,
+      "loss": 0.0,
+      "step": 1480
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0,
+      "learning_rate": 9.837000814995926e-05,
+      "loss": 0.0,
+      "step": 1520
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0,
+      "learning_rate": 9.67400162999185e-05,
+      "loss": 0.0,
+      "step": 1540
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.0,
+      "learning_rate": 9.511002444987775e-05,
+      "loss": 0.0,
+      "step": 1560
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.0,
+      "learning_rate": 9.348003259983701e-05,
+      "loss": 0.0,
+      "step": 1580
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.0,
+      "learning_rate": 9.185004074979625e-05,
+      "loss": 0.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.0,
+      "learning_rate": 9.02200488997555e-05,
+      "loss": 0.0,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0,
+      "learning_rate": 8.859005704971476e-05,
+      "loss": 0.0,
+      "step": 1640
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0,
+      "learning_rate": 8.6960065199674e-05,
+      "loss": 0.0,
+      "step": 1660
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.0,
+      "learning_rate": 8.533007334963325e-05,
+      "loss": 0.0,
+      "step": 1680
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.0,
+      "learning_rate": 8.37000814995925e-05,
+      "loss": 0.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.0,
+      "learning_rate": 8.207008964955176e-05,
+      "loss": 0.0,
+      "step": 1720
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0,
+      "learning_rate": 8.044009779951101e-05,
+      "loss": 0.0,
+      "step": 1740
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0,
+      "learning_rate": 7.881010594947025e-05,
+      "loss": 0.0,
+      "step": 1760
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0,
+      "learning_rate": 7.71801140994295e-05,
+      "loss": 0.0,
+      "step": 1780
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.0,
+      "learning_rate": 7.555012224938876e-05,
+      "loss": 0.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0,
+      "learning_rate": 7.392013039934801e-05,
+      "loss": 0.0,
+      "step": 1820
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0,
+      "learning_rate": 7.229013854930725e-05,
+      "loss": 0.0,
+      "step": 1840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0,
+      "learning_rate": 7.066014669926651e-05,
+      "loss": 0.0,
+      "step": 1860
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.0,
+      "learning_rate": 6.903015484922576e-05,
+      "loss": 0.0,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0,
+      "learning_rate": 6.740016299918502e-05,
+      "loss": 0.0,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0,
+      "learning_rate": 6.577017114914426e-05,
+      "loss": 0.0,
+      "step": 1920
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.0,
+      "learning_rate": 6.414017929910351e-05,
+      "loss": 0.0,
+      "step": 1940
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0,
+      "learning_rate": 6.251018744906276e-05,
+      "loss": 0.0,
+      "step": 1960
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0,
+      "learning_rate": 6.0880195599022005e-05,
+      "loss": 0.0,
+      "step": 1980
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0,
+      "learning_rate": 5.925020374898126e-05,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0,
+      "learning_rate": 5.762021189894051e-05,
+      "loss": 0.0,
+      "step": 2020
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.0,
+      "learning_rate": 5.5990220048899754e-05,
+      "loss": 0.0,
+      "step": 2040
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.0,
+      "learning_rate": 5.436022819885901e-05,
+      "loss": 0.0,
+      "step": 2060
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.0,
+      "learning_rate": 5.273023634881826e-05,
+      "loss": 0.0,
+      "step": 2080
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.0,
+      "learning_rate": 5.110024449877751e-05,
+      "loss": 0.0,
+      "step": 2100
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9470252648736756e-05,
+      "loss": 0.0,
+      "step": 2120
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.0,
+      "learning_rate": 4.784026079869601e-05,
+      "loss": 0.0,
+      "step": 2140
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6210268948655264e-05,
+      "loss": 0.0,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0,
+      "learning_rate": 4.458027709861451e-05,
+      "loss": 0.0,
+      "step": 2180
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.295028524857376e-05,
+      "loss": 0.0,
+      "step": 2200
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.132029339853301e-05,
+      "loss": 0.0,
+      "step": 2220
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0,
+      "learning_rate": 3.969030154849226e-05,
+      "loss": 0.0,
+      "step": 2240
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8060309698451507e-05,
+      "loss": 0.0,
+      "step": 2260
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0,
+      "learning_rate": 3.643031784841076e-05,
+      "loss": 0.0,
+      "step": 2280
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0,
+      "learning_rate": 3.480032599837001e-05,
+      "loss": 0.0,
+      "step": 2300
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0,
+      "learning_rate": 3.3170334148329255e-05,
+      "loss": 0.0,
+      "step": 2320
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.0,
+      "learning_rate": 3.154034229828851e-05,
+      "loss": 0.0,
+      "step": 2340
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.0,
+      "learning_rate": 2.991035044824776e-05,
+      "loss": 0.0,
+      "step": 2360
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8280358598207013e-05,
+      "loss": 0.0,
+      "step": 2380
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0,
+      "learning_rate": 2.665036674816626e-05,
+      "loss": 0.0,
+      "step": 2400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5020374898125508e-05,
+      "loss": 0.0,
+      "step": 2420
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3390383048084762e-05,
+      "loss": 0.0,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1760391198044012e-05,
+      "loss": 0.0,
+      "step": 2460
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0130399348003263e-05,
+      "loss": 0.0,
+      "step": 2480
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.0,
+      "learning_rate": 1.850040749796251e-05,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.0,
+      "learning_rate": 1.687041564792176e-05,
+      "loss": 0.0,
+      "step": 2520
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5240423797881013e-05,
+      "loss": 0.0,
+      "step": 2540
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0,
+      "learning_rate": 1.361043194784026e-05,
+      "loss": 0.0,
+      "step": 2560
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 1.198044009779951e-05,
+      "loss": 0.0,
+      "step": 2580
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0350448247758763e-05,
+      "loss": 0.0,
+      "step": 2600
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0,
+      "learning_rate": 8.720456397718012e-06,
+      "loss": 0.0,
+      "step": 2620
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.0,
+      "learning_rate": 7.090464547677262e-06,
+      "loss": 0.0,
+      "step": 2640
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0,
+      "learning_rate": 5.460472697636512e-06,
+      "loss": 0.0,
+      "step": 2660
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0,
+      "learning_rate": 3.830480847595763e-06,
+      "loss": 0.0,
+      "step": 2680
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2004889975550126e-06,
+      "loss": 0.0,
+      "step": 2700
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 5.704971475142625e-07,
+      "loss": 0.0,
+      "step": 2720
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2727,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 67854207762432.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2727/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48616edb7995550a027fc0ba976fa1c83bde52ee5d36d0b884282a40ce0042d
+size 4920

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": "</s>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "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:b48616edb7995550a027fc0ba976fa1c83bde52ee5d36d0b884282a40ce0042d
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+    "project_name": "DFEP-05",
+    "data_path": "DFEP-05/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": 1,
+    "model_max_length": 1024,
+    "padding": null,
+    "trainer": "default",
+    "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": "fp16",
+    "lr": 0.0002,
+    "epochs": 1,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "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": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "Ponce-01/DFEP-05",
+    "username": null
+}