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": 0.045,
+  "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 sha256:600b7b7f2ab72601fb1a5b3f4540ce2ece571c988a4dabdac8d3064f7f10d882
+size 9022864

checkpoint-72/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-72/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": 0.045,
+  "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-72/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600b7b7f2ab72601fb1a5b3f4540ce2ece571c988a4dabdac8d3064f7f10d882
+size 9022864

checkpoint-72/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082ea6cfae6d7752d0998ba95221d1cbe5fe625676a0a4e0340bcd36124c3018
+size 18096570

checkpoint-72/pytorch_model.bin

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

checkpoint-72/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43bcc3e599f3eb98503de5dd95e8b076a5d52023eca741e8ab5ac1da3782c74
+size 14244

checkpoint-72/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6882e79f6e071b11f33a79b95f4c19fb3729802faaa5f1316357343377a7e7bc
+size 1064

checkpoint-72/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-72/tokenizer.model

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

checkpoint-72/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-72/trainer_state.json

@@ -0,0 +1,525 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.0,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000125,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000175,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000196875,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019375000000000002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000190625,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001875,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000184375,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018125000000000001,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000178125,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000175,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017187500000000002,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016875,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000165625,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000159375,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015625,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000153125,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000146875,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014375,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014062500000000002,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001375,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000134375,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013125000000000002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000128125,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000125,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012187500000000001,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011875,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000115625,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000109375,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010625000000000001,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000103125,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.0,
+      "learning_rate": 9.687500000000001e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.0,
+      "learning_rate": 9.375e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.0,
+      "learning_rate": 9.062500000000001e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.0,
+      "learning_rate": 8.75e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0,
+      "learning_rate": 8.4375e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.0,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.0,
+      "learning_rate": 7.8125e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.0,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.0,
+      "learning_rate": 7.1875e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.0,
+      "learning_rate": 6.875e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.0,
+      "learning_rate": 6.562500000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.0,
+      "learning_rate": 6.25e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.0,
+      "learning_rate": 5.9375e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 0.0,
+      "learning_rate": 5.3125000000000004e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 0.0,
+      "learning_rate": 4.375e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 0.0,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.0,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 0.0,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 0.0,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.0,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 0.0,
+      "learning_rate": 3.125e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 72
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1791530237952.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-72/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df172c1f49f73baa890ac3ea77f62c57714bd2d8e6edfa943ff0f93930196eb7
+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:df172c1f49f73baa890ac3ea77f62c57714bd2d8e6edfa943ff0f93930196eb7
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+    "project_name": "myautotrain",
+    "data_path": "myautotrain/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": null,
+    "lr": 0.0002,
+    "epochs": 4,
+    "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": null,
+    "target_modules": null,
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.045,
+    "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": "superlazycoder/tiny_llama_fine_tuned",
+    "username": null
+}