Upload 34 files

model/README.md

@@ -0,0 +1,62 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+model_name: tinyllama-medical-lora
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for tinyllama-medical-lora
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.26.2
+- Transformers: 4.57.3
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

model/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5034ab4f54b398db6138791a0115c724c2d7419d6559d41e2e615685ba29a87b
+size 4528840

model/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

model/checkpoint-252/README.md

@@ -0,0 +1,209 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

model/checkpoint-252/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/checkpoint-252/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48c2370a39adeb0f6742a2b32e0a66f0ed1e55ac2f3e76e253880920bfa19f8
+size 4528840

model/checkpoint-252/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

model/checkpoint-252/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe1d3742a92c90afc995152f00115fe5efc94c08772890c7d9f08527ad0c2a6
+size 5296011

model/checkpoint-252/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223b0ea1a835257fb98821529a6586e915276afb8933ab54cbe89c7fd896faf4
+size 14645

model/checkpoint-252/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e222c8f6d70a64a7be434a77e12dba6b8fa450472e392f38aef10b0cb19a6bfb
+size 1465

model/checkpoint-252/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
+  }
+}

model/checkpoint-252/tokenizer.model

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

model/checkpoint-252/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

model/checkpoint-252/trainer_state.json

@@ -0,0 +1,284 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6945084899663925,
+      "epoch": 0.16,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.0001942857142857143,
+      "loss": 1.6568,
+      "mean_token_accuracy": 0.6660789601504803,
+      "num_tokens": 3578.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7567030429840088,
+      "epoch": 0.32,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018793650793650794,
+      "loss": 0.5374,
+      "mean_token_accuracy": 0.9151218816637993,
+      "num_tokens": 7168.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.3767241083085537,
+      "epoch": 0.48,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00018158730158730158,
+      "loss": 0.2313,
+      "mean_token_accuracy": 0.9639480978250503,
+      "num_tokens": 10765.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.11644666939973831,
+      "epoch": 0.64,
+      "grad_norm": 1.6171875,
+      "learning_rate": 0.00017523809523809525,
+      "loss": 0.0879,
+      "mean_token_accuracy": 0.9775604054331779,
+      "num_tokens": 14360.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.09643888566643,
+      "epoch": 0.8,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00016888888888888889,
+      "loss": 0.0704,
+      "mean_token_accuracy": 0.9787676453590393,
+      "num_tokens": 17939.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.07870416343212128,
+      "epoch": 0.96,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00016253968253968255,
+      "loss": 0.0613,
+      "mean_token_accuracy": 0.9781275555491448,
+      "num_tokens": 21503.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.06506191292091419,
+      "epoch": 1.112,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.0001561904761904762,
+      "loss": 0.0603,
+      "mean_token_accuracy": 0.979121606600912,
+      "num_tokens": 24901.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.06247333232313394,
+      "epoch": 1.272,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00014984126984126986,
+      "loss": 0.0561,
+      "mean_token_accuracy": 0.9788626194000244,
+      "num_tokens": 28481.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.06256919410079717,
+      "epoch": 1.432,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.0001434920634920635,
+      "loss": 0.0573,
+      "mean_token_accuracy": 0.9789639458060264,
+      "num_tokens": 32086.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06354112001135945,
+      "epoch": 1.592,
+      "grad_norm": 0.25,
+      "learning_rate": 0.00013714285714285716,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9794268563389779,
+      "num_tokens": 35669.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06055063921958208,
+      "epoch": 1.752,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.0001307936507936508,
+      "loss": 0.0585,
+      "mean_token_accuracy": 0.9791461735963821,
+      "num_tokens": 39248.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06182145280763507,
+      "epoch": 1.912,
+      "grad_norm": 0.23828125,
+      "learning_rate": 0.00012444444444444444,
+      "loss": 0.0566,
+      "mean_token_accuracy": 0.9789005950093269,
+      "num_tokens": 42847.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.061306838828482126,
+      "epoch": 2.064,
+      "grad_norm": 0.197265625,
+      "learning_rate": 0.0001180952380952381,
+      "loss": 0.0571,
+      "mean_token_accuracy": 0.9782133165158724,
+      "num_tokens": 46232.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06099967770278454,
+      "epoch": 2.224,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00011174603174603176,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.9792280271649361,
+      "num_tokens": 49832.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.059232624247670174,
+      "epoch": 2.384,
+      "grad_norm": 0.20703125,
+      "learning_rate": 0.00010539682539682541,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9804230973124504,
+      "num_tokens": 53452.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05805135918781161,
+      "epoch": 2.544,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 9.904761904761905e-05,
+      "loss": 0.0543,
+      "mean_token_accuracy": 0.9793034762144088,
+      "num_tokens": 57025.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05772697534412145,
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.287109375,
+      "learning_rate": 9.26984126984127e-05,
+      "loss": 0.0554,
+      "mean_token_accuracy": 0.9804835677146911,
+      "num_tokens": 60568.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.05884762229397893,
+      "epoch": 2.864,
+      "grad_norm": 0.228515625,
+      "learning_rate": 8.634920634920635e-05,
+      "loss": 0.0549,
+      "mean_token_accuracy": 0.9786250367760658,
+      "num_tokens": 64154.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.059985080929963214,
+      "epoch": 3.016,
+      "grad_norm": 0.185546875,
+      "learning_rate": 8e-05,
+      "loss": 0.0556,
+      "mean_token_accuracy": 0.9794995596534327,
+      "num_tokens": 67556.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.05724337324500084,
+      "epoch": 3.176,
+      "grad_norm": 0.296875,
+      "learning_rate": 7.365079365079366e-05,
+      "loss": 0.056,
+      "mean_token_accuracy": 0.9790969446301461,
+      "num_tokens": 71127.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.05909126764163375,
+      "epoch": 3.336,
+      "grad_norm": 0.228515625,
+      "learning_rate": 6.730158730158731e-05,
+      "loss": 0.0535,
+      "mean_token_accuracy": 0.9792171016335487,
+      "num_tokens": 74707.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.05850943056866527,
+      "epoch": 3.496,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 6.0952380952380964e-05,
+      "loss": 0.0527,
+      "mean_token_accuracy": 0.979849337041378,
+      "num_tokens": 78304.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.05798638556152582,
+      "epoch": 3.656,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 5.46031746031746e-05,
+      "loss": 0.0528,
+      "mean_token_accuracy": 0.9787673026323318,
+      "num_tokens": 81920.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.058623119723051786,
+      "epoch": 3.816,
+      "grad_norm": 0.34375,
+      "learning_rate": 4.8253968253968255e-05,
+      "loss": 0.0549,
+      "mean_token_accuracy": 0.9786330401897431,
+      "num_tokens": 85474.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.05803300961852074,
+      "epoch": 3.976,
+      "grad_norm": 0.333984375,
+      "learning_rate": 4.190476190476191e-05,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9784177452325821,
+      "num_tokens": 89084.0,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 571722087186432.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

model/checkpoint-252/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836f93796543a92fe4ff87df40f049346c24746c007b4ebfcd9582ba8df4aab6
+size 6225

model/checkpoint-315/README.md

@@ -0,0 +1,209 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

model/checkpoint-315/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/checkpoint-315/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5034ab4f54b398db6138791a0115c724c2d7419d6559d41e2e615685ba29a87b
+size 4528840

model/checkpoint-315/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

model/checkpoint-315/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff128dd4c93f9b8ee2bc9dd46c0757d053b7268a4537a09b1086d71ef1f056
+size 5296203

model/checkpoint-315/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a12dc8a2bb0acc60d4a2afb1b8df320bda55d911c14d668d41835456ec48f2f
+size 14645

model/checkpoint-315/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1ad5bceb26ebd94ddf87be4c3a4b6b55a91ae603f87ea70fc9687ee0c47e4e
+size 1465

model/checkpoint-315/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
+  }
+}

model/checkpoint-315/tokenizer.model

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

model/checkpoint-315/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

model/checkpoint-315/trainer_state.json

@@ -0,0 +1,344 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6945084899663925,
+      "epoch": 0.16,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.0001942857142857143,
+      "loss": 1.6568,
+      "mean_token_accuracy": 0.6660789601504803,
+      "num_tokens": 3578.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7567030429840088,
+      "epoch": 0.32,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018793650793650794,
+      "loss": 0.5374,
+      "mean_token_accuracy": 0.9151218816637993,
+      "num_tokens": 7168.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.3767241083085537,
+      "epoch": 0.48,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00018158730158730158,
+      "loss": 0.2313,
+      "mean_token_accuracy": 0.9639480978250503,
+      "num_tokens": 10765.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.11644666939973831,
+      "epoch": 0.64,
+      "grad_norm": 1.6171875,
+      "learning_rate": 0.00017523809523809525,
+      "loss": 0.0879,
+      "mean_token_accuracy": 0.9775604054331779,
+      "num_tokens": 14360.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.09643888566643,
+      "epoch": 0.8,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00016888888888888889,
+      "loss": 0.0704,
+      "mean_token_accuracy": 0.9787676453590393,
+      "num_tokens": 17939.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.07870416343212128,
+      "epoch": 0.96,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00016253968253968255,
+      "loss": 0.0613,
+      "mean_token_accuracy": 0.9781275555491448,
+      "num_tokens": 21503.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.06506191292091419,
+      "epoch": 1.112,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.0001561904761904762,
+      "loss": 0.0603,
+      "mean_token_accuracy": 0.979121606600912,
+      "num_tokens": 24901.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.06247333232313394,
+      "epoch": 1.272,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00014984126984126986,
+      "loss": 0.0561,
+      "mean_token_accuracy": 0.9788626194000244,
+      "num_tokens": 28481.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.06256919410079717,
+      "epoch": 1.432,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.0001434920634920635,
+      "loss": 0.0573,
+      "mean_token_accuracy": 0.9789639458060264,
+      "num_tokens": 32086.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06354112001135945,
+      "epoch": 1.592,
+      "grad_norm": 0.25,
+      "learning_rate": 0.00013714285714285716,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9794268563389779,
+      "num_tokens": 35669.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06055063921958208,
+      "epoch": 1.752,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.0001307936507936508,
+      "loss": 0.0585,
+      "mean_token_accuracy": 0.9791461735963821,
+      "num_tokens": 39248.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06182145280763507,
+      "epoch": 1.912,
+      "grad_norm": 0.23828125,
+      "learning_rate": 0.00012444444444444444,
+      "loss": 0.0566,
+      "mean_token_accuracy": 0.9789005950093269,
+      "num_tokens": 42847.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.061306838828482126,
+      "epoch": 2.064,
+      "grad_norm": 0.197265625,
+      "learning_rate": 0.0001180952380952381,
+      "loss": 0.0571,
+      "mean_token_accuracy": 0.9782133165158724,
+      "num_tokens": 46232.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06099967770278454,
+      "epoch": 2.224,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00011174603174603176,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.9792280271649361,
+      "num_tokens": 49832.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.059232624247670174,
+      "epoch": 2.384,
+      "grad_norm": 0.20703125,
+      "learning_rate": 0.00010539682539682541,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9804230973124504,
+      "num_tokens": 53452.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05805135918781161,
+      "epoch": 2.544,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 9.904761904761905e-05,
+      "loss": 0.0543,
+      "mean_token_accuracy": 0.9793034762144088,
+      "num_tokens": 57025.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05772697534412145,
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.287109375,
+      "learning_rate": 9.26984126984127e-05,
+      "loss": 0.0554,
+      "mean_token_accuracy": 0.9804835677146911,
+      "num_tokens": 60568.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.05884762229397893,
+      "epoch": 2.864,
+      "grad_norm": 0.228515625,
+      "learning_rate": 8.634920634920635e-05,
+      "loss": 0.0549,
+      "mean_token_accuracy": 0.9786250367760658,
+      "num_tokens": 64154.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.059985080929963214,
+      "epoch": 3.016,
+      "grad_norm": 0.185546875,
+      "learning_rate": 8e-05,
+      "loss": 0.0556,
+      "mean_token_accuracy": 0.9794995596534327,
+      "num_tokens": 67556.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.05724337324500084,
+      "epoch": 3.176,
+      "grad_norm": 0.296875,
+      "learning_rate": 7.365079365079366e-05,
+      "loss": 0.056,
+      "mean_token_accuracy": 0.9790969446301461,
+      "num_tokens": 71127.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.05909126764163375,
+      "epoch": 3.336,
+      "grad_norm": 0.228515625,
+      "learning_rate": 6.730158730158731e-05,
+      "loss": 0.0535,
+      "mean_token_accuracy": 0.9792171016335487,
+      "num_tokens": 74707.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.05850943056866527,
+      "epoch": 3.496,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 6.0952380952380964e-05,
+      "loss": 0.0527,
+      "mean_token_accuracy": 0.979849337041378,
+      "num_tokens": 78304.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.05798638556152582,
+      "epoch": 3.656,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 5.46031746031746e-05,
+      "loss": 0.0528,
+      "mean_token_accuracy": 0.9787673026323318,
+      "num_tokens": 81920.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.058623119723051786,
+      "epoch": 3.816,
+      "grad_norm": 0.34375,
+      "learning_rate": 4.8253968253968255e-05,
+      "loss": 0.0549,
+      "mean_token_accuracy": 0.9786330401897431,
+      "num_tokens": 85474.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.05803300961852074,
+      "epoch": 3.976,
+      "grad_norm": 0.333984375,
+      "learning_rate": 4.190476190476191e-05,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9784177452325821,
+      "num_tokens": 89084.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.058468575050172056,
+      "epoch": 4.128,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.053,
+      "mean_token_accuracy": 0.980533872780047,
+      "num_tokens": 92475.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.05833202926442027,
+      "epoch": 4.288,
+      "grad_norm": 0.2734375,
+      "learning_rate": 2.920634920634921e-05,
+      "loss": 0.0528,
+      "mean_token_accuracy": 0.9793538480997086,
+      "num_tokens": 96031.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.057458093389868736,
+      "epoch": 4.448,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9790615141391754,
+      "num_tokens": 99636.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.05768435606732965,
+      "epoch": 4.608,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.6507936507936507e-05,
+      "loss": 0.0523,
+      "mean_token_accuracy": 0.9792853400111199,
+      "num_tokens": 103226.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.05801067296415567,
+      "epoch": 4.768,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.015873015873016e-05,
+      "loss": 0.0526,
+      "mean_token_accuracy": 0.9782511860132217,
+      "num_tokens": 106801.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.057603081967681644,
+      "epoch": 4.928,
+      "grad_norm": 0.21484375,
+      "learning_rate": 3.8095238095238102e-06,
+      "loss": 0.0525,
+      "mean_token_accuracy": 0.9789468124508858,
+      "num_tokens": 110398.0,
+      "step": 310
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 714497094205440.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

model/checkpoint-315/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836f93796543a92fe4ff87df40f049346c24746c007b4ebfcd9582ba8df4aab6
+size 6225

model/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

model/tokenizer.model

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

model/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}