Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+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 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": [
+    "c_attn"
+  ],
+  "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:f548a4701f561175083517c8e8307d92758cdc482fa881d4cdbe6119540f5b5b
+size 2362376

checkpoint-3974/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: openai-community/gpt2
+---
+
+# 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 0.9.0

checkpoint-3974/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3974/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f548a4701f561175083517c8e8307d92758cdc482fa881d4cdbe6119540f5b5b
+size 2362376

checkpoint-3974/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee1b1728e8438fe34ac5a1d4b3f905cdd824398966e3701d5b2df7154c1bff7
+size 4739222

checkpoint-3974/pytorch_model.bin

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

checkpoint-3974/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f5efd5470f93f6ba67a6c1f9e2a6cf7039c47ad4f1d8f4059c3ecc90dc2d12
+size 14512

checkpoint-3974/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f1c5f2ea587f8120cbd4eb653bcd8566e2411e33003bf23b3bf0456d83bc15
+size 14512

checkpoint-3974/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5436738daf65b792bb8914b09ff52c37d8f1f0a855135763a7e9bf41f62ea41
+size 1064

checkpoint-3974/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3974/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3974/trainer_state.json

@@ -0,0 +1,1127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998741980123286,
+  "eval_steps": 500,
+  "global_step": 3974,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3939279019832611,
+      "learning_rate": 1.2562814070351759e-05,
+      "loss": 4.4744,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.4029081165790558,
+      "learning_rate": 2.5125628140703518e-05,
+      "loss": 4.4566,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.38896021246910095,
+      "learning_rate": 3.768844221105528e-05,
+      "loss": 4.4112,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.3309621214866638,
+      "learning_rate": 5.0251256281407036e-05,
+      "loss": 4.2634,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.36627885699272156,
+      "learning_rate": 6.28140703517588e-05,
+      "loss": 4.1502,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.32366621494293213,
+      "learning_rate": 7.537688442211056e-05,
+      "loss": 3.9593,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.297305166721344,
+      "learning_rate": 8.793969849246232e-05,
+      "loss": 3.8315,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.31555816531181335,
+      "learning_rate": 0.00010050251256281407,
+      "loss": 3.8021,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.28000104427337646,
+      "learning_rate": 0.00011306532663316583,
+      "loss": 3.689,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2804722487926483,
+      "learning_rate": 0.0001256281407035176,
+      "loss": 3.6452,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3214639723300934,
+      "learning_rate": 0.00013819095477386937,
+      "loss": 3.6317,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3243967592716217,
+      "learning_rate": 0.00015075376884422112,
+      "loss": 3.6302,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3477385938167572,
+      "learning_rate": 0.00016331658291457289,
+      "loss": 3.5881,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4255552589893341,
+      "learning_rate": 0.00017587939698492463,
+      "loss": 3.6165,
+      "step": 350
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.32802626490592957,
+      "learning_rate": 0.0001884422110552764,
+      "loss": 3.6214,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3549612760543823,
+      "learning_rate": 0.0001998881431767338,
+      "loss": 3.5841,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.31946343183517456,
+      "learning_rate": 0.00019848993288590605,
+      "loss": 3.544,
+      "step": 425
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.38572484254837036,
+      "learning_rate": 0.0001970917225950783,
+      "loss": 3.5418,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.42264020442962646,
+      "learning_rate": 0.00019569351230425057,
+      "loss": 3.5095,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3461235463619232,
+      "learning_rate": 0.00019429530201342282,
+      "loss": 3.5163,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3953052759170532,
+      "learning_rate": 0.0001928970917225951,
+      "loss": 3.5208,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.36267855763435364,
+      "learning_rate": 0.00019149888143176735,
+      "loss": 3.5165,
+      "step": 550
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.37477219104766846,
+      "learning_rate": 0.0001901006711409396,
+      "loss": 3.4831,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4207465946674347,
+      "learning_rate": 0.00018870246085011188,
+      "loss": 3.4899,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.38875311613082886,
+      "learning_rate": 0.00018730425055928413,
+      "loss": 3.5172,
+      "step": 625
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.37320446968078613,
+      "learning_rate": 0.00018590604026845638,
+      "loss": 3.5124,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.37162256240844727,
+      "learning_rate": 0.00018450782997762866,
+      "loss": 3.4748,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.38408517837524414,
+      "learning_rate": 0.00018310961968680088,
+      "loss": 3.486,
+      "step": 700
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3887028694152832,
+      "learning_rate": 0.00018171140939597316,
+      "loss": 3.4736,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.4443490505218506,
+      "learning_rate": 0.0001803131991051454,
+      "loss": 3.479,
+      "step": 750
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.39757394790649414,
+      "learning_rate": 0.0001789149888143177,
+      "loss": 3.4492,
+      "step": 775
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.35315626859664917,
+      "learning_rate": 0.00017751677852348994,
+      "loss": 3.4435,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.3870226740837097,
+      "learning_rate": 0.0001761185682326622,
+      "loss": 3.4377,
+      "step": 825
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4453731179237366,
+      "learning_rate": 0.00017472035794183446,
+      "loss": 3.4614,
+      "step": 850
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.43639248609542847,
+      "learning_rate": 0.00017332214765100671,
+      "loss": 3.4889,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.42209935188293457,
+      "learning_rate": 0.00017192393736017897,
+      "loss": 3.4426,
+      "step": 900
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.4586125314235687,
+      "learning_rate": 0.00017052572706935124,
+      "loss": 3.4278,
+      "step": 925
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.38476869463920593,
+      "learning_rate": 0.0001691275167785235,
+      "loss": 3.4459,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.38706693053245544,
+      "learning_rate": 0.00016772930648769577,
+      "loss": 3.4564,
+      "step": 975
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3744584321975708,
+      "learning_rate": 0.00016633109619686802,
+      "loss": 3.4613,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3903864622116089,
+      "learning_rate": 0.00016493288590604027,
+      "loss": 3.45,
+      "step": 1025
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4096889793872833,
+      "learning_rate": 0.00016353467561521255,
+      "loss": 3.405,
+      "step": 1050
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.39897987246513367,
+      "learning_rate": 0.0001621364653243848,
+      "loss": 3.405,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.39934077858924866,
+      "learning_rate": 0.00016073825503355705,
+      "loss": 3.4276,
+      "step": 1100
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.38111913204193115,
+      "learning_rate": 0.00015934004474272933,
+      "loss": 3.407,
+      "step": 1125
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.43283891677856445,
+      "learning_rate": 0.00015794183445190158,
+      "loss": 3.3952,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.43224990367889404,
+      "learning_rate": 0.00015654362416107385,
+      "loss": 3.4114,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.3882638216018677,
+      "learning_rate": 0.0001551454138702461,
+      "loss": 3.4266,
+      "step": 1200
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.4062541127204895,
+      "learning_rate": 0.00015374720357941835,
+      "loss": 3.4472,
+      "step": 1225
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.40274298191070557,
+      "learning_rate": 0.0001523489932885906,
+      "loss": 3.4207,
+      "step": 1250
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3987756669521332,
+      "learning_rate": 0.00015095078299776286,
+      "loss": 3.3942,
+      "step": 1275
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.37407705187797546,
+      "learning_rate": 0.00014955257270693513,
+      "loss": 3.3894,
+      "step": 1300
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.38793492317199707,
+      "learning_rate": 0.00014815436241610738,
+      "loss": 3.3811,
+      "step": 1325
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.39553505182266235,
+      "learning_rate": 0.00014675615212527963,
+      "loss": 3.3722,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.40836596488952637,
+      "learning_rate": 0.0001453579418344519,
+      "loss": 3.4253,
+      "step": 1375
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.41444289684295654,
+      "learning_rate": 0.00014395973154362416,
+      "loss": 3.3802,
+      "step": 1400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3889537453651428,
+      "learning_rate": 0.00014256152125279644,
+      "loss": 3.3584,
+      "step": 1425
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.47589465975761414,
+      "learning_rate": 0.0001411633109619687,
+      "loss": 3.3628,
+      "step": 1450
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.4026196002960205,
+      "learning_rate": 0.00013976510067114094,
+      "loss": 3.3638,
+      "step": 1475
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.4240950345993042,
+      "learning_rate": 0.00013836689038031322,
+      "loss": 3.3838,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.3979630470275879,
+      "learning_rate": 0.00013696868008948547,
+      "loss": 3.365,
+      "step": 1525
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.40804243087768555,
+      "learning_rate": 0.00013557046979865772,
+      "loss": 3.3546,
+      "step": 1550
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4044090807437897,
+      "learning_rate": 0.00013417225950783,
+      "loss": 3.371,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4067833125591278,
+      "learning_rate": 0.00013277404921700225,
+      "loss": 3.3327,
+      "step": 1600
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.44250789284706116,
+      "learning_rate": 0.00013137583892617452,
+      "loss": 3.3723,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3748351037502289,
+      "learning_rate": 0.00012997762863534677,
+      "loss": 3.356,
+      "step": 1650
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3744029700756073,
+      "learning_rate": 0.00012857941834451902,
+      "loss": 3.3758,
+      "step": 1675
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.39975643157958984,
+      "learning_rate": 0.0001271812080536913,
+      "loss": 3.4049,
+      "step": 1700
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.4390547573566437,
+      "learning_rate": 0.00012578299776286352,
+      "loss": 3.3334,
+      "step": 1725
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4836800694465637,
+      "learning_rate": 0.0001243847874720358,
+      "loss": 3.3636,
+      "step": 1750
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3915925920009613,
+      "learning_rate": 0.00012298657718120805,
+      "loss": 3.369,
+      "step": 1775
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3820320665836334,
+      "learning_rate": 0.00012158836689038032,
+      "loss": 3.3817,
+      "step": 1800
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4624602198600769,
+      "learning_rate": 0.00012019015659955257,
+      "loss": 3.3862,
+      "step": 1825
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.42159679532051086,
+      "learning_rate": 0.00011879194630872483,
+      "loss": 3.3466,
+      "step": 1850
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4151483476161957,
+      "learning_rate": 0.0001173937360178971,
+      "loss": 3.3739,
+      "step": 1875
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.45305246114730835,
+      "learning_rate": 0.00011599552572706936,
+      "loss": 3.3451,
+      "step": 1900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.4354460537433624,
+      "learning_rate": 0.00011459731543624161,
+      "loss": 3.3258,
+      "step": 1925
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4107976257801056,
+      "learning_rate": 0.00011319910514541387,
+      "loss": 3.3841,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4533105194568634,
+      "learning_rate": 0.00011180089485458614,
+      "loss": 3.3479,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.454975962638855,
+      "learning_rate": 0.0001104026845637584,
+      "loss": 3.336,
+      "step": 2000
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5079920887947083,
+      "learning_rate": 0.00010900447427293066,
+      "loss": 3.327,
+      "step": 2025
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5311482548713684,
+      "learning_rate": 0.00010760626398210291,
+      "loss": 3.3706,
+      "step": 2050
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.42152655124664307,
+      "learning_rate": 0.00010620805369127518,
+      "loss": 3.353,
+      "step": 2075
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.40225550532341003,
+      "learning_rate": 0.00010480984340044744,
+      "loss": 3.3351,
+      "step": 2100
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.4132668673992157,
+      "learning_rate": 0.0001034116331096197,
+      "loss": 3.308,
+      "step": 2125
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.473305344581604,
+      "learning_rate": 0.00010201342281879196,
+      "loss": 3.3375,
+      "step": 2150
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.43594586849212646,
+      "learning_rate": 0.00010061521252796422,
+      "loss": 3.3298,
+      "step": 2175
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5282984375953674,
+      "learning_rate": 9.921700223713647e-05,
+      "loss": 3.3179,
+      "step": 2200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.45690715312957764,
+      "learning_rate": 9.781879194630873e-05,
+      "loss": 3.3583,
+      "step": 2225
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.4544149339199066,
+      "learning_rate": 9.642058165548098e-05,
+      "loss": 3.3033,
+      "step": 2250
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.4424913823604584,
+      "learning_rate": 9.502237136465325e-05,
+      "loss": 3.3326,
+      "step": 2275
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4259510934352875,
+      "learning_rate": 9.362416107382551e-05,
+      "loss": 3.3324,
+      "step": 2300
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.46472057700157166,
+      "learning_rate": 9.222595078299778e-05,
+      "loss": 3.3123,
+      "step": 2325
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4864007830619812,
+      "learning_rate": 9.082774049217003e-05,
+      "loss": 3.3349,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4463450312614441,
+      "learning_rate": 8.942953020134228e-05,
+      "loss": 3.2947,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4468083679676056,
+      "learning_rate": 8.803131991051454e-05,
+      "loss": 3.3423,
+      "step": 2400
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.4376937448978424,
+      "learning_rate": 8.66331096196868e-05,
+      "loss": 3.3563,
+      "step": 2425
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.43003320693969727,
+      "learning_rate": 8.523489932885907e-05,
+      "loss": 3.3341,
+      "step": 2450
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.47375035285949707,
+      "learning_rate": 8.383668903803132e-05,
+      "loss": 3.3327,
+      "step": 2475
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.42449191212654114,
+      "learning_rate": 8.243847874720358e-05,
+      "loss": 3.367,
+      "step": 2500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.455077201128006,
+      "learning_rate": 8.104026845637585e-05,
+      "loss": 3.314,
+      "step": 2525
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5218727588653564,
+      "learning_rate": 7.964205816554811e-05,
+      "loss": 3.3207,
+      "step": 2550
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.40510672330856323,
+      "learning_rate": 7.824384787472036e-05,
+      "loss": 3.3055,
+      "step": 2575
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4328942596912384,
+      "learning_rate": 7.684563758389261e-05,
+      "loss": 3.3301,
+      "step": 2600
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.42730334401130676,
+      "learning_rate": 7.544742729306487e-05,
+      "loss": 3.3455,
+      "step": 2625
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.45374396443367004,
+      "learning_rate": 7.404921700223714e-05,
+      "loss": 3.3332,
+      "step": 2650
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.4406868517398834,
+      "learning_rate": 7.26510067114094e-05,
+      "loss": 3.3121,
+      "step": 2675
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.49322813749313354,
+      "learning_rate": 7.125279642058165e-05,
+      "loss": 3.3065,
+      "step": 2700
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.48299440741539,
+      "learning_rate": 6.985458612975392e-05,
+      "loss": 3.2902,
+      "step": 2725
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.45161083340644836,
+      "learning_rate": 6.851230425055929e-05,
+      "loss": 3.3131,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.43272122740745544,
+      "learning_rate": 6.711409395973155e-05,
+      "loss": 3.3448,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4966789484024048,
+      "learning_rate": 6.571588366890381e-05,
+      "loss": 3.3083,
+      "step": 2800
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.435917466878891,
+      "learning_rate": 6.431767337807607e-05,
+      "loss": 3.3005,
+      "step": 2825
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.46452581882476807,
+      "learning_rate": 6.291946308724832e-05,
+      "loss": 3.3002,
+      "step": 2850
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.426553875207901,
+      "learning_rate": 6.152125279642058e-05,
+      "loss": 3.3169,
+      "step": 2875
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.46474194526672363,
+      "learning_rate": 6.012304250559284e-05,
+      "loss": 3.2887,
+      "step": 2900
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5483251214027405,
+      "learning_rate": 5.87248322147651e-05,
+      "loss": 3.2878,
+      "step": 2925
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4654993414878845,
+      "learning_rate": 5.7326621923937364e-05,
+      "loss": 3.3023,
+      "step": 2950
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.43446651101112366,
+      "learning_rate": 5.592841163310962e-05,
+      "loss": 3.322,
+      "step": 2975
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.44535747170448303,
+      "learning_rate": 5.4530201342281885e-05,
+      "loss": 3.3118,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.4716418385505676,
+      "learning_rate": 5.313199105145414e-05,
+      "loss": 3.3211,
+      "step": 3025
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.48301395773887634,
+      "learning_rate": 5.1733780760626406e-05,
+      "loss": 3.2996,
+      "step": 3050
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4252597987651825,
+      "learning_rate": 5.033557046979866e-05,
+      "loss": 3.3022,
+      "step": 3075
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.4170271158218384,
+      "learning_rate": 4.893736017897092e-05,
+      "loss": 3.345,
+      "step": 3100
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.42665281891822815,
+      "learning_rate": 4.753914988814318e-05,
+      "loss": 3.2633,
+      "step": 3125
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.4138229787349701,
+      "learning_rate": 4.6140939597315434e-05,
+      "loss": 3.3365,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.40854546427726746,
+      "learning_rate": 4.47427293064877e-05,
+      "loss": 3.3349,
+      "step": 3175
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.4516899585723877,
+      "learning_rate": 4.3344519015659955e-05,
+      "loss": 3.2872,
+      "step": 3200
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.436982125043869,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 3.296,
+      "step": 3225
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.425311803817749,
+      "learning_rate": 4.0548098434004476e-05,
+      "loss": 3.2947,
+      "step": 3250
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.45536327362060547,
+      "learning_rate": 3.914988814317674e-05,
+      "loss": 3.2968,
+      "step": 3275
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.3970387279987335,
+      "learning_rate": 3.775167785234899e-05,
+      "loss": 3.2714,
+      "step": 3300
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.4497933089733124,
+      "learning_rate": 3.6353467561521254e-05,
+      "loss": 3.3117,
+      "step": 3325
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.46388792991638184,
+      "learning_rate": 3.495525727069351e-05,
+      "loss": 3.3066,
+      "step": 3350
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.4629228115081787,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 3.2982,
+      "step": 3375
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.46318650245666504,
+      "learning_rate": 3.215883668903803e-05,
+      "loss": 3.3504,
+      "step": 3400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.43514785170555115,
+      "learning_rate": 3.076062639821029e-05,
+      "loss": 3.3057,
+      "step": 3425
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.41652512550354004,
+      "learning_rate": 2.936241610738255e-05,
+      "loss": 3.2861,
+      "step": 3450
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.4423655569553375,
+      "learning_rate": 2.796420581655481e-05,
+      "loss": 3.2521,
+      "step": 3475
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4741450846195221,
+      "learning_rate": 2.656599552572707e-05,
+      "loss": 3.3239,
+      "step": 3500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.4872516095638275,
+      "learning_rate": 2.516778523489933e-05,
+      "loss": 3.2751,
+      "step": 3525
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.4238009750843048,
+      "learning_rate": 2.376957494407159e-05,
+      "loss": 3.2813,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4463885724544525,
+      "learning_rate": 2.237136465324385e-05,
+      "loss": 3.2873,
+      "step": 3575
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.46087589859962463,
+      "learning_rate": 2.097315436241611e-05,
+      "loss": 3.2789,
+      "step": 3600
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.4878619611263275,
+      "learning_rate": 1.957494407158837e-05,
+      "loss": 3.3153,
+      "step": 3625
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4896848201751709,
+      "learning_rate": 1.8176733780760627e-05,
+      "loss": 3.2989,
+      "step": 3650
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4557226002216339,
+      "learning_rate": 1.6778523489932888e-05,
+      "loss": 3.3095,
+      "step": 3675
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.43755295872688293,
+      "learning_rate": 1.5380313199105145e-05,
+      "loss": 3.3334,
+      "step": 3700
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.4965628683567047,
+      "learning_rate": 1.3982102908277405e-05,
+      "loss": 3.2972,
+      "step": 3725
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.4985644519329071,
+      "learning_rate": 1.2583892617449666e-05,
+      "loss": 3.2875,
+      "step": 3750
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.40080615878105164,
+      "learning_rate": 1.1185682326621925e-05,
+      "loss": 3.2693,
+      "step": 3775
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.42183899879455566,
+      "learning_rate": 9.787472035794185e-06,
+      "loss": 3.321,
+      "step": 3800
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5553184747695923,
+      "learning_rate": 8.389261744966444e-06,
+      "loss": 3.298,
+      "step": 3825
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.4350402355194092,
+      "learning_rate": 6.991051454138703e-06,
+      "loss": 3.2908,
+      "step": 3850
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.4002743363380432,
+      "learning_rate": 5.592841163310962e-06,
+      "loss": 3.2781,
+      "step": 3875
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.4503081142902374,
+      "learning_rate": 4.194630872483222e-06,
+      "loss": 3.2933,
+      "step": 3900
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.45145291090011597,
+      "learning_rate": 2.796420581655481e-06,
+      "loss": 3.2727,
+      "step": 3925
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.42662373185157776,
+      "learning_rate": 1.3982102908277406e-06,
+      "loss": 3.2763,
+      "step": 3950
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3974,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.6729202912919552e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3974/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7118fd57cba915713484955bbe38fb751c053c01083bbea219382833985477
+size 4920

handler.py

@@ -0,0 +1,32 @@
+from typing import  Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+from peft import PeftModel
+import json
+import os
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
+        model = AutoModelForCausalLM.from_pretrained(
+            base_model_path,
+            torch_dtype=torch.float16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            device_map="auto",
+        )
+        tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+        model.resize_token_embeddings(len(tokenizer))
+        model = PeftModel.from_pretrained(model, path)
+        model = model.merge_and_unload()
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+peft==0.9.0
+transformers==4.38.2

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7118fd57cba915713484955bbe38fb751c053c01083bbea219382833985477
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "openai-community/gpt2",
+    "project_name": "my-autotrain-llm",
+    "data_path": "my-autotrain-llm/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": 1024,
+    "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": "rishiai/gpt2tyyyy",
+    "username": null
+}