Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-204/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_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 sha256:7e9fa71e39dbd2326f8614effad2ef4f6709472d5276904dceeed757fd65b366
+size 78480072

checkpoint-204/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b-it
+---
+
+# 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-204/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-204/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9fa71e39dbd2326f8614effad2ef4f6709472d5276904dceeed757fd65b366
+size 78480072

checkpoint-204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64978afba9bcf378d7b62f2269e614ee6fc357a8e7ec9aa0fc88c5f8f22f05d8
+size 157104826

checkpoint-204/pytorch_model.bin

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

checkpoint-204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9578f66dec159cafd72f71d5014289b4c3d8bfc20011c2c6da34e199dbf5ae2e
+size 14244

checkpoint-204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff6be810637e6e4d65b7e39f3beb2f888d1079c25156eef09d7d3c242c50f42
+size 1064

checkpoint-204/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-204/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

checkpoint-204/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-204/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-204/trainer_state.json

@@ -0,0 +1,735 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.950901508331299,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.8735,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 8.133766174316406,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 2.126,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.692324161529541,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 1.926,
+      "step": 6
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.0254693031311035,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.9762,
+      "step": 8
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.805467128753662,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 1.7727,
+      "step": 10
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.195497989654541,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 1.6793,
+      "step": 12
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.377630710601807,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 1.629,
+      "step": 14
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.5771281719207764,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 1.4296,
+      "step": 16
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.8232216835021973,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 1.4971,
+      "step": 18
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.096635341644287,
+      "learning_rate": 2.7142857142857144e-05,
+      "loss": 1.2129,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4359596967697144,
+      "learning_rate": 3e-05,
+      "loss": 1.0623,
+      "step": 22
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.3408057689666748,
+      "learning_rate": 2.9672131147540984e-05,
+      "loss": 1.1274,
+      "step": 24
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5449613332748413,
+      "learning_rate": 2.9344262295081968e-05,
+      "loss": 1.0534,
+      "step": 26
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.266711950302124,
+      "learning_rate": 2.901639344262295e-05,
+      "loss": 1.0022,
+      "step": 28
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2879749536514282,
+      "learning_rate": 2.8688524590163935e-05,
+      "loss": 0.8819,
+      "step": 30
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.1592856645584106,
+      "learning_rate": 2.836065573770492e-05,
+      "loss": 0.9526,
+      "step": 32
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3098297119140625,
+      "learning_rate": 2.8032786885245902e-05,
+      "loss": 0.8577,
+      "step": 34
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.294083833694458,
+      "learning_rate": 2.7704918032786886e-05,
+      "loss": 0.8352,
+      "step": 36
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0912269353866577,
+      "learning_rate": 2.737704918032787e-05,
+      "loss": 0.7198,
+      "step": 38
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0710548162460327,
+      "learning_rate": 2.7049180327868853e-05,
+      "loss": 0.7445,
+      "step": 40
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0573712587356567,
+      "learning_rate": 2.6721311475409837e-05,
+      "loss": 0.6865,
+      "step": 42
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0720133781433105,
+      "learning_rate": 2.639344262295082e-05,
+      "loss": 0.6729,
+      "step": 44
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.1398358345031738,
+      "learning_rate": 2.6065573770491804e-05,
+      "loss": 0.6805,
+      "step": 46
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.3724112510681152,
+      "learning_rate": 2.5737704918032787e-05,
+      "loss": 0.6923,
+      "step": 48
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1828075647354126,
+      "learning_rate": 2.5409836065573774e-05,
+      "loss": 0.6927,
+      "step": 50
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9459984302520752,
+      "learning_rate": 2.5081967213114754e-05,
+      "loss": 0.6539,
+      "step": 52
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.0317862033843994,
+      "learning_rate": 2.4754098360655738e-05,
+      "loss": 0.6816,
+      "step": 54
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9241882562637329,
+      "learning_rate": 2.442622950819672e-05,
+      "loss": 0.6342,
+      "step": 56
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2747896909713745,
+      "learning_rate": 2.4098360655737705e-05,
+      "loss": 0.6752,
+      "step": 58
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2308931350708008,
+      "learning_rate": 2.377049180327869e-05,
+      "loss": 0.6703,
+      "step": 60
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.9486699104309082,
+      "learning_rate": 2.3442622950819672e-05,
+      "loss": 0.6265,
+      "step": 62
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9226927757263184,
+      "learning_rate": 2.3114754098360656e-05,
+      "loss": 0.6806,
+      "step": 64
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9970481991767883,
+      "learning_rate": 2.278688524590164e-05,
+      "loss": 0.6684,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9154540300369263,
+      "learning_rate": 2.2459016393442626e-05,
+      "loss": 0.6076,
+      "step": 68
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.9942613840103149,
+      "learning_rate": 2.213114754098361e-05,
+      "loss": 0.6423,
+      "step": 70
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.7813049554824829,
+      "learning_rate": 2.180327868852459e-05,
+      "loss": 0.6045,
+      "step": 72
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.8933289051055908,
+      "learning_rate": 2.1475409836065574e-05,
+      "loss": 0.6022,
+      "step": 74
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.1493891477584839,
+      "learning_rate": 2.1147540983606557e-05,
+      "loss": 0.6012,
+      "step": 76
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.102952480316162,
+      "learning_rate": 2.081967213114754e-05,
+      "loss": 0.6232,
+      "step": 78
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0626366138458252,
+      "learning_rate": 2.0491803278688525e-05,
+      "loss": 0.6064,
+      "step": 80
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.103053331375122,
+      "learning_rate": 2.0163934426229508e-05,
+      "loss": 0.5939,
+      "step": 82
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.2533128261566162,
+      "learning_rate": 1.9836065573770492e-05,
+      "loss": 0.6151,
+      "step": 84
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.1883020401000977,
+      "learning_rate": 1.9508196721311475e-05,
+      "loss": 0.5898,
+      "step": 86
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.941169023513794,
+      "learning_rate": 1.9180327868852462e-05,
+      "loss": 0.5877,
+      "step": 88
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.0497690439224243,
+      "learning_rate": 1.8852459016393442e-05,
+      "loss": 0.603,
+      "step": 90
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.006282091140747,
+      "learning_rate": 1.8524590163934426e-05,
+      "loss": 0.5779,
+      "step": 92
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.8880963325500488,
+      "learning_rate": 1.819672131147541e-05,
+      "loss": 0.5785,
+      "step": 94
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.8170259594917297,
+      "learning_rate": 1.7868852459016393e-05,
+      "loss": 0.5973,
+      "step": 96
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.9137255549430847,
+      "learning_rate": 1.7540983606557377e-05,
+      "loss": 0.5859,
+      "step": 98
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.8934600353240967,
+      "learning_rate": 1.721311475409836e-05,
+      "loss": 0.5712,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.9546217322349548,
+      "learning_rate": 1.6885245901639344e-05,
+      "loss": 0.5977,
+      "step": 102
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.1362155675888062,
+      "learning_rate": 1.6557377049180328e-05,
+      "loss": 0.5957,
+      "step": 104
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.0691664218902588,
+      "learning_rate": 1.6229508196721314e-05,
+      "loss": 0.6303,
+      "step": 106
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.1143447160720825,
+      "learning_rate": 1.5901639344262298e-05,
+      "loss": 0.5946,
+      "step": 108
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.9838765859603882,
+      "learning_rate": 1.5573770491803278e-05,
+      "loss": 0.6253,
+      "step": 110
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.0309878587722778,
+      "learning_rate": 1.5245901639344264e-05,
+      "loss": 0.5695,
+      "step": 112
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.0644599199295044,
+      "learning_rate": 1.4918032786885245e-05,
+      "loss": 0.5974,
+      "step": 114
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.9344809651374817,
+      "learning_rate": 1.4590163934426229e-05,
+      "loss": 0.5772,
+      "step": 116
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.9217023253440857,
+      "learning_rate": 1.4262295081967213e-05,
+      "loss": 0.5659,
+      "step": 118
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.1142168045043945,
+      "learning_rate": 1.3934426229508198e-05,
+      "loss": 0.5811,
+      "step": 120
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.1095991134643555,
+      "learning_rate": 1.3606557377049181e-05,
+      "loss": 0.6029,
+      "step": 122
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0066099166870117,
+      "learning_rate": 1.3278688524590163e-05,
+      "loss": 0.5568,
+      "step": 124
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.8575509190559387,
+      "learning_rate": 1.2950819672131147e-05,
+      "loss": 0.5703,
+      "step": 126
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.1447674036026,
+      "learning_rate": 1.2622950819672132e-05,
+      "loss": 0.5836,
+      "step": 128
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.9783082604408264,
+      "learning_rate": 1.2295081967213116e-05,
+      "loss": 0.5948,
+      "step": 130
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.0990079641342163,
+      "learning_rate": 1.19672131147541e-05,
+      "loss": 0.568,
+      "step": 132
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0109045505523682,
+      "learning_rate": 1.1639344262295081e-05,
+      "loss": 0.5628,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0725024938583374,
+      "learning_rate": 1.1311475409836065e-05,
+      "loss": 0.5838,
+      "step": 136
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.1007121801376343,
+      "learning_rate": 1.098360655737705e-05,
+      "loss": 0.5584,
+      "step": 138
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.9721304774284363,
+      "learning_rate": 1.0655737704918034e-05,
+      "loss": 0.563,
+      "step": 140
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.0708929300308228,
+      "learning_rate": 1.0327868852459017e-05,
+      "loss": 0.5351,
+      "step": 142
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.0382109880447388,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.6197,
+      "step": 144
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.1190615892410278,
+      "learning_rate": 9.672131147540984e-06,
+      "loss": 0.5663,
+      "step": 146
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.0649045705795288,
+      "learning_rate": 9.344262295081968e-06,
+      "loss": 0.5553,
+      "step": 148
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.201451063156128,
+      "learning_rate": 9.016393442622952e-06,
+      "loss": 0.5765,
+      "step": 150
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.0463545322418213,
+      "learning_rate": 8.688524590163935e-06,
+      "loss": 0.5466,
+      "step": 152
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.2062188386917114,
+      "learning_rate": 8.360655737704917e-06,
+      "loss": 0.5732,
+      "step": 154
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.1948459148406982,
+      "learning_rate": 8.032786885245902e-06,
+      "loss": 0.554,
+      "step": 156
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.0267665386199951,
+      "learning_rate": 7.704918032786886e-06,
+      "loss": 0.5366,
+      "step": 158
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.9985692501068115,
+      "learning_rate": 7.377049180327869e-06,
+      "loss": 0.5424,
+      "step": 160
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.119655728340149,
+      "learning_rate": 7.049180327868853e-06,
+      "loss": 0.5553,
+      "step": 162
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.9959714412689209,
+      "learning_rate": 6.721311475409837e-06,
+      "loss": 0.5895,
+      "step": 164
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 1.0639784336090088,
+      "learning_rate": 6.393442622950819e-06,
+      "loss": 0.5704,
+      "step": 166
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.1006407737731934,
+      "learning_rate": 6.065573770491804e-06,
+      "loss": 0.5416,
+      "step": 168
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.98119056224823,
+      "learning_rate": 5.7377049180327865e-06,
+      "loss": 0.5839,
+      "step": 170
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.1397459506988525,
+      "learning_rate": 5.409836065573771e-06,
+      "loss": 0.5604,
+      "step": 172
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.0882867574691772,
+      "learning_rate": 5.081967213114754e-06,
+      "loss": 0.556,
+      "step": 174
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 1.1950050592422485,
+      "learning_rate": 4.754098360655738e-06,
+      "loss": 0.5694,
+      "step": 176
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.0115201473236084,
+      "learning_rate": 4.426229508196722e-06,
+      "loss": 0.5464,
+      "step": 178
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 1.1844886541366577,
+      "learning_rate": 4.098360655737705e-06,
+      "loss": 0.5489,
+      "step": 180
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.192030668258667,
+      "learning_rate": 3.770491803278689e-06,
+      "loss": 0.5359,
+      "step": 182
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.2273727655410767,
+      "learning_rate": 3.4426229508196724e-06,
+      "loss": 0.5721,
+      "step": 184
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.950477123260498,
+      "learning_rate": 3.114754098360656e-06,
+      "loss": 0.5534,
+      "step": 186
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.9607704877853394,
+      "learning_rate": 2.7868852459016396e-06,
+      "loss": 0.5706,
+      "step": 188
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.0138517618179321,
+      "learning_rate": 2.4590163934426227e-06,
+      "loss": 0.5592,
+      "step": 190
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 1.1338858604431152,
+      "learning_rate": 2.1311475409836063e-06,
+      "loss": 0.5659,
+      "step": 192
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.057421088218689,
+      "learning_rate": 1.80327868852459e-06,
+      "loss": 0.586,
+      "step": 194
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.1511048078536987,
+      "learning_rate": 1.4754098360655737e-06,
+      "loss": 0.5768,
+      "step": 196
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.9774185419082642,
+      "learning_rate": 1.1475409836065575e-06,
+      "loss": 0.564,
+      "step": 198
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.1010777950286865,
+      "learning_rate": 8.196721311475409e-07,
+      "loss": 0.5891,
+      "step": 200
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.024880290031433,
+      "learning_rate": 4.918032786885246e-07,
+      "loss": 0.5536,
+      "step": 202
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9065414667129517,
+      "learning_rate": 1.639344262295082e-07,
+      "loss": 0.5979,
+      "step": 204
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5017254261424128.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d710233b4efc4325284d83fa644be7a9b845012b5adc27d29db3f1b667db0b
+size 4984

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

runs/Mar20_21-51-31_r-mjmanashti-fine-tuning-models-z9zxggp6-28099-uqwsz/events.out.tfevents.1710971493.r-mjmanashti-fine-tuning-models-z9zxggp6-28099-uqwsz.54.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9af5dcc0d5aa550372e10f4ba1200cba998e70aae452913bab2da37775d16f3
-size 26137
+oid sha256:c9119235d09b595a20549bc9a1053c662373dd2b3f9ce41a01b4a2c1f9d81b0f
+size 26702

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d710233b4efc4325284d83fa644be7a9b845012b5adc27d29db3f1b667db0b
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "google/gemma-2b-it",
+    "project_name": "fingemma-2b-ti",
+    "data_path": "fingemma-2b-ti/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "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": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "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": "mjmanashti/fingemma-2b-ti",
+    "username": "mjmanashti"
+}