Upload 23 files

README.md

@@ -1,3 +1,45 @@
 ---
-license: mit
+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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Felladrin/Llama-160M-Chat-v1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_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:b474d4c8139045e4b1fcf28051d349a2fa03bd63a0b186852fadcc2eab518c1d
+size 13587864

checkpoint-75/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Felladrin/Llama-160M-Chat-v1
+---
+
+# 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-75/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Felladrin/Llama-160M-Chat-v1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-75/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b474d4c8139045e4b1fcf28051d349a2fa03bd63a0b186852fadcc2eab518c1d
+size 13587864

checkpoint-75/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800890d948f2d2ef285050f2d04709f840d023687202c4e4d33821b67e4aadd8
+size 27273018

checkpoint-75/pytorch_model.bin

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

checkpoint-75/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145e706d52345ccbe0f6ccefa87d68e00f83f824780e693eb9e75d5c609ee060
+size 14244

checkpoint-75/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
+size 1064

checkpoint-75/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-75/tokenizer.model

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

checkpoint-75/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 %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-75/trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.912621359223301,
+  "eval_steps": 500,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.0,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000125,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000175,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019701492537313434,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019402985074626867,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019104477611940298,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018805970149253734,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018507462686567165,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018208955223880598,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001791044776119403,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017611940298507464,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017313432835820895,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017014925373134328,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016716417910447761,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016417910447761195,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016119402985074628,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015820895522388059,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015522388059701495,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015223880597014925,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001492537313432836,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.0097087378640777,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014626865671641792,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.0485436893203883,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014328358208955225,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.087378640776699,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014029850746268658,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.1262135922330097,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001373134328358209,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.1650485436893203,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013432835820895525,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.203883495145631,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013134328358208955,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.2427184466019416,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012835820895522389,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.2815533980582523,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012537313432835822,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.3203883495145632,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012238805970149255,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.3592233009708738,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011940298507462686,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.3980582524271845,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001164179104477612,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.4368932038834952,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011343283582089552,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.4757281553398058,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011044776119402987,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.5145631067961165,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010746268656716419,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.5533980582524272,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001044776119402985,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.5922330097087378,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010149253731343284,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.6310679611650487,
+      "grad_norm": 0.0,
+      "learning_rate": 9.850746268656717e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.6699029126213594,
+      "grad_norm": 0.0,
+      "learning_rate": 9.552238805970149e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.70873786407767,
+      "grad_norm": 0.0,
+      "learning_rate": 9.253731343283582e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.7475728155339807,
+      "grad_norm": 0.0,
+      "learning_rate": 8.955223880597016e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.7864077669902914,
+      "grad_norm": 0.0,
+      "learning_rate": 8.656716417910447e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.825242718446602,
+      "grad_norm": 0.0,
+      "learning_rate": 8.358208955223881e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.8640776699029127,
+      "grad_norm": 0.0,
+      "learning_rate": 8.059701492537314e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.9029126213592233,
+      "grad_norm": 0.0,
+      "learning_rate": 7.761194029850747e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.0,
+      "learning_rate": 7.46268656716418e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.9805825242718447,
+      "grad_norm": 0.0,
+      "learning_rate": 7.164179104477612e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.0194174757281553,
+      "grad_norm": 0.0,
+      "learning_rate": 6.865671641791044e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 2.058252427184466,
+      "grad_norm": 0.0,
+      "learning_rate": 6.567164179104478e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 2.0970873786407767,
+      "grad_norm": 0.0,
+      "learning_rate": 6.268656716417911e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 2.1359223300970873,
+      "grad_norm": 0.0,
+      "learning_rate": 5.970149253731343e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 2.174757281553398,
+      "grad_norm": 0.0,
+      "learning_rate": 5.671641791044776e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 2.2135922330097086,
+      "grad_norm": 0.0,
+      "learning_rate": 5.373134328358209e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 2.2524271844660193,
+      "grad_norm": 0.0,
+      "learning_rate": 5.074626865671642e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 2.29126213592233,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7761194029850745e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 2.3300970873786406,
+      "grad_norm": 0.0,
+      "learning_rate": 4.477611940298508e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 2.3689320388349513,
+      "grad_norm": 0.0,
+      "learning_rate": 4.1791044776119404e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 2.407766990291262,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8805970149253736e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 2.4466019417475726,
+      "grad_norm": 0.0,
+      "learning_rate": 3.582089552238806e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 2.4854368932038833,
+      "grad_norm": 0.0,
+      "learning_rate": 3.283582089552239e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 2.524271844660194,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9850746268656714e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 2.5631067961165046,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6865671641791047e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 2.6019417475728153,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3880597014925373e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 2.6407766990291264,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0895522388059702e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 2.679611650485437,
+      "grad_norm": 0.0,
+      "learning_rate": 1.791044776119403e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 2.7184466019417477,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4925373134328357e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.7572815533980584,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1940298507462686e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 2.796116504854369,
+      "grad_norm": 0.0,
+      "learning_rate": 8.955223880597016e-06,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 2.8349514563106797,
+      "grad_norm": 0.0,
+      "learning_rate": 5.970149253731343e-06,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 2.8737864077669903,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9850746268656716e-06,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2033753702400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-75/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce93e4c05b09c0fb5e4f645295e6737368e030aaed23d22069fadfefe118da9d
+size 4984

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 %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "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:ce93e4c05b09c0fb5e4f645295e6737368e030aaed23d22069fadfefe118da9d
+size 4984

training_params.json

@@ -0,0 +1,49 @@
+{
+    "model": "Felladrin/Llama-160M-Chat-v1",
+    "project_name": "my-autotrain-llm",
+    "data_path": "/kaggle/input/without-null/",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": 1,
+    "model_max_length": 1024,
+    "padding": null,
+    "trainer": "default",
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 0.0002,
+    "epochs": 3,
+    "batch_size": 8,
+    "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": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 128,
+    "max_completion_length": null,
+    "prompt_text_column": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "push_to_hub": false,
+    "username": null,
+    "token": null
+}