Add TaskMind LoRA adapter — trained on WhatsApp task extraction dataset

README.md

@@ -0,0 +1,62 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+model_name: taskmind_lora_r2
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for taskmind_lora_r2
+
+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 0.18.1
+- TRL: 1.1.0
+- Transformers: 4.57.0
+- Pytorch: 2.2.2
+- Datasets: 4.8.4
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08834a2d790efc7ff95520f1767a95647668b53d9fd1551642b50c1ccc7dfb4e
+size 100966336

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 %}

checkpoint-117/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 0.18.1

checkpoint-117/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-117/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08834a2d790efc7ff95520f1767a95647668b53d9fd1551642b50c1ccc7dfb4e
+size 100966336

checkpoint-117/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 %}

checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6279bcb89e66860bf87781e5a0d8e5a260e93869a1c6bba51f68f2632d8356a0
+size 202101754

checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
+size 13990

checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b5d85410c25568c0a11711d7130f8ff27272ffd2f27999a7aef996da304096
+size 1064

checkpoint-117/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
+  }
+}

checkpoint-117/tokenizer.model

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

checkpoint-117/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
+}

checkpoint-117/trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.40241146087646484,
+  "best_model_checkpoint": "out/taskmind_lora_r2/checkpoint-117",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7179150760173798,
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.5452802181243896,
+      "learning_rate": 3.6e-05,
+      "loss": 2.1281,
+      "mean_token_accuracy": 0.6145351931452752,
+      "num_tokens": 13644.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.19541779384017,
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.5751521587371826,
+      "learning_rate": 7.6e-05,
+      "loss": 1.1145,
+      "mean_token_accuracy": 0.7703276634216308,
+      "num_tokens": 27398.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.35528318025171757,
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.8191161155700684,
+      "learning_rate": 7.753424657534247e-05,
+      "loss": 0.3534,
+      "mean_token_accuracy": 0.9318128570914268,
+      "num_tokens": 41008.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.4318943719069163,
+      "eval_loss": 0.4599609375,
+      "eval_mean_token_accuracy": 0.915368656317393,
+      "eval_num_tokens": 53280.0,
+      "eval_runtime": 4.1078,
+      "eval_samples_per_second": 5.843,
+      "eval_steps_per_second": 0.73,
+      "step": 39
+    },
+    {
+      "entropy": 0.34713621363043784,
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5747274160385132,
+      "learning_rate": 7.47945205479452e-05,
+      "loss": 0.3455,
+      "mean_token_accuracy": 0.9327198296785355,
+      "num_tokens": 54619.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.29785057827830314,
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.5261789560317993,
+      "learning_rate": 7.205479452054796e-05,
+      "loss": 0.2928,
+      "mean_token_accuracy": 0.9401231810450554,
+      "num_tokens": 68310.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.25945029519498347,
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.3967696726322174,
+      "learning_rate": 6.93150684931507e-05,
+      "loss": 0.2491,
+      "mean_token_accuracy": 0.9500185340642929,
+      "num_tokens": 81865.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.2741880103945732,
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.5456269383430481,
+      "learning_rate": 6.657534246575343e-05,
+      "loss": 0.2771,
+      "mean_token_accuracy": 0.9445250034332275,
+      "num_tokens": 95656.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.3964502811431885,
+      "eval_loss": 0.4085829555988312,
+      "eval_mean_token_accuracy": 0.9256282250086466,
+      "eval_num_tokens": 106560.0,
+      "eval_runtime": 3.1585,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 0.95,
+      "step": 78
+    },
+    {
+      "entropy": 0.3172414764761925,
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.6122390627861023,
+      "learning_rate": 6.383561643835617e-05,
+      "loss": 0.321,
+      "mean_token_accuracy": 0.9391013815999031,
+      "num_tokens": 109408.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.28223426416516306,
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.47210052609443665,
+      "learning_rate": 6.109589041095891e-05,
+      "loss": 0.2494,
+      "mean_token_accuracy": 0.9481928303837777,
+      "num_tokens": 123140.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.22195697724819183,
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.48354053497314453,
+      "learning_rate": 5.835616438356165e-05,
+      "loss": 0.2218,
+      "mean_token_accuracy": 0.95259810090065,
+      "num_tokens": 136850.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.21110524237155914,
+      "epoch": 2.8205128205128203,
+      "grad_norm": 0.48064902424812317,
+      "learning_rate": 5.561643835616439e-05,
+      "loss": 0.1959,
+      "mean_token_accuracy": 0.9575912490487098,
+      "num_tokens": 150480.0,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.355695774157842,
+      "eval_loss": 0.40241146087646484,
+      "eval_mean_token_accuracy": 0.9268327752749125,
+      "eval_num_tokens": 159840.0,
+      "eval_runtime": 2.7968,
+      "eval_samples_per_second": 8.581,
+      "eval_steps_per_second": 1.073,
+      "step": 117
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 1045916207628288.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a481ec4511ff65e6d89887f1674e392bf7f467a3e700014f4a1bc5e7acd6d9fd
+size 5880

checkpoint-156/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 0.18.1

checkpoint-156/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-156/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41187d6f4c4db6ec1a4e2b4c28edb918ffe5f80e6e2da72129430775f51aba6d
+size 100966336

checkpoint-156/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 %}

checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c754aecb02d487715f450502e7bed238e14775f3efda14f514ebd9396b966b3f
+size 202101754

checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fed77b14fe062f6db72d68cedd6fd95bae3305b7a735eef3c85da43fd15d476
+size 13990

checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9720a18fb01e8f591c3c875e8c64e8a60c7b2f1d5c51255ce4e00e05afac28
+size 1064

checkpoint-156/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
+  }
+}

checkpoint-156/tokenizer.model

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

checkpoint-156/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
+}

checkpoint-156/trainer_state.json

@@ -0,0 +1,228 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.40241146087646484,
+  "best_model_checkpoint": "out/taskmind_lora_r2/checkpoint-117",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7179150760173798,
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.5452802181243896,
+      "learning_rate": 3.6e-05,
+      "loss": 2.1281,
+      "mean_token_accuracy": 0.6145351931452752,
+      "num_tokens": 13644.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.19541779384017,
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.5751521587371826,
+      "learning_rate": 7.6e-05,
+      "loss": 1.1145,
+      "mean_token_accuracy": 0.7703276634216308,
+      "num_tokens": 27398.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.35528318025171757,
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.8191161155700684,
+      "learning_rate": 7.753424657534247e-05,
+      "loss": 0.3534,
+      "mean_token_accuracy": 0.9318128570914268,
+      "num_tokens": 41008.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.4318943719069163,
+      "eval_loss": 0.4599609375,
+      "eval_mean_token_accuracy": 0.915368656317393,
+      "eval_num_tokens": 53280.0,
+      "eval_runtime": 4.1078,
+      "eval_samples_per_second": 5.843,
+      "eval_steps_per_second": 0.73,
+      "step": 39
+    },
+    {
+      "entropy": 0.34713621363043784,
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5747274160385132,
+      "learning_rate": 7.47945205479452e-05,
+      "loss": 0.3455,
+      "mean_token_accuracy": 0.9327198296785355,
+      "num_tokens": 54619.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.29785057827830314,
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.5261789560317993,
+      "learning_rate": 7.205479452054796e-05,
+      "loss": 0.2928,
+      "mean_token_accuracy": 0.9401231810450554,
+      "num_tokens": 68310.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.25945029519498347,
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.3967696726322174,
+      "learning_rate": 6.93150684931507e-05,
+      "loss": 0.2491,
+      "mean_token_accuracy": 0.9500185340642929,
+      "num_tokens": 81865.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.2741880103945732,
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.5456269383430481,
+      "learning_rate": 6.657534246575343e-05,
+      "loss": 0.2771,
+      "mean_token_accuracy": 0.9445250034332275,
+      "num_tokens": 95656.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.3964502811431885,
+      "eval_loss": 0.4085829555988312,
+      "eval_mean_token_accuracy": 0.9256282250086466,
+      "eval_num_tokens": 106560.0,
+      "eval_runtime": 3.1585,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 0.95,
+      "step": 78
+    },
+    {
+      "entropy": 0.3172414764761925,
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.6122390627861023,
+      "learning_rate": 6.383561643835617e-05,
+      "loss": 0.321,
+      "mean_token_accuracy": 0.9391013815999031,
+      "num_tokens": 109408.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.28223426416516306,
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.47210052609443665,
+      "learning_rate": 6.109589041095891e-05,
+      "loss": 0.2494,
+      "mean_token_accuracy": 0.9481928303837777,
+      "num_tokens": 123140.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.22195697724819183,
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.48354053497314453,
+      "learning_rate": 5.835616438356165e-05,
+      "loss": 0.2218,
+      "mean_token_accuracy": 0.95259810090065,
+      "num_tokens": 136850.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.21110524237155914,
+      "epoch": 2.8205128205128203,
+      "grad_norm": 0.48064902424812317,
+      "learning_rate": 5.561643835616439e-05,
+      "loss": 0.1959,
+      "mean_token_accuracy": 0.9575912490487098,
+      "num_tokens": 150480.0,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.355695774157842,
+      "eval_loss": 0.40241146087646484,
+      "eval_mean_token_accuracy": 0.9268327752749125,
+      "eval_num_tokens": 159840.0,
+      "eval_runtime": 2.7968,
+      "eval_samples_per_second": 8.581,
+      "eval_steps_per_second": 1.073,
+      "step": 117
+    },
+    {
+      "entropy": 0.23056518994271755,
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.5083797574043274,
+      "learning_rate": 5.2876712328767125e-05,
+      "loss": 0.2134,
+      "mean_token_accuracy": 0.954666568338871,
+      "num_tokens": 163947.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.21548609118908643,
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.6669173836708069,
+      "learning_rate": 5.0136986301369863e-05,
+      "loss": 0.195,
+      "mean_token_accuracy": 0.9568116649985313,
+      "num_tokens": 177722.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.19277227036654948,
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.6170966029167175,
+      "learning_rate": 4.739726027397261e-05,
+      "loss": 0.1786,
+      "mean_token_accuracy": 0.9599042758345604,
+      "num_tokens": 191348.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.1847936963662505,
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.6156774163246155,
+      "learning_rate": 4.465753424657535e-05,
+      "loss": 0.1736,
+      "mean_token_accuracy": 0.9629231780767441,
+      "num_tokens": 204961.0,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.31701664129892987,
+      "eval_loss": 0.4171659052371979,
+      "eval_mean_token_accuracy": 0.9275441765785217,
+      "eval_num_tokens": 213120.0,
+      "eval_runtime": 2.9872,
+      "eval_samples_per_second": 8.034,
+      "eval_steps_per_second": 1.004,
+      "step": 156
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 1394607930691584.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a481ec4511ff65e6d89887f1674e392bf7f467a3e700014f4a1bc5e7acd6d9fd
+size 5880

checkpoint-195/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 0.18.1

checkpoint-195/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-195/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c7fa6648fdf7f6685daa6f3e1811cde0afb89fe64d30b712cd4f58c42b3636
+size 100966336

checkpoint-195/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 %}

checkpoint-195/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8d40d7cb529d546a8086082620c383e3ef152178187b0c730f7eef159e71c2
+size 202101754

checkpoint-195/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

checkpoint-195/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17420baf1fcdd4ec52fa3b35ce07c9efe01afe13a1e76fc4d563568fc1510b9
+size 1064

checkpoint-195/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
+  }
+}

checkpoint-195/tokenizer.model

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

checkpoint-195/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
+}

checkpoint-195/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.40241146087646484,
+  "best_model_checkpoint": "out/taskmind_lora_r2/checkpoint-117",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7179150760173798,
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.5452802181243896,
+      "learning_rate": 3.6e-05,
+      "loss": 2.1281,
+      "mean_token_accuracy": 0.6145351931452752,
+      "num_tokens": 13644.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.19541779384017,
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.5751521587371826,
+      "learning_rate": 7.6e-05,
+      "loss": 1.1145,
+      "mean_token_accuracy": 0.7703276634216308,
+      "num_tokens": 27398.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.35528318025171757,
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.8191161155700684,
+      "learning_rate": 7.753424657534247e-05,
+      "loss": 0.3534,
+      "mean_token_accuracy": 0.9318128570914268,
+      "num_tokens": 41008.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.4318943719069163,
+      "eval_loss": 0.4599609375,
+      "eval_mean_token_accuracy": 0.915368656317393,
+      "eval_num_tokens": 53280.0,
+      "eval_runtime": 4.1078,
+      "eval_samples_per_second": 5.843,
+      "eval_steps_per_second": 0.73,
+      "step": 39
+    },
+    {
+      "entropy": 0.34713621363043784,
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5747274160385132,
+      "learning_rate": 7.47945205479452e-05,
+      "loss": 0.3455,
+      "mean_token_accuracy": 0.9327198296785355,
+      "num_tokens": 54619.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.29785057827830314,
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.5261789560317993,
+      "learning_rate": 7.205479452054796e-05,
+      "loss": 0.2928,
+      "mean_token_accuracy": 0.9401231810450554,
+      "num_tokens": 68310.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.25945029519498347,
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.3967696726322174,
+      "learning_rate": 6.93150684931507e-05,
+      "loss": 0.2491,
+      "mean_token_accuracy": 0.9500185340642929,
+      "num_tokens": 81865.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.2741880103945732,
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.5456269383430481,
+      "learning_rate": 6.657534246575343e-05,
+      "loss": 0.2771,
+      "mean_token_accuracy": 0.9445250034332275,
+      "num_tokens": 95656.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.3964502811431885,
+      "eval_loss": 0.4085829555988312,
+      "eval_mean_token_accuracy": 0.9256282250086466,
+      "eval_num_tokens": 106560.0,
+      "eval_runtime": 3.1585,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 0.95,
+      "step": 78
+    },
+    {
+      "entropy": 0.3172414764761925,
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.6122390627861023,
+      "learning_rate": 6.383561643835617e-05,
+      "loss": 0.321,
+      "mean_token_accuracy": 0.9391013815999031,
+      "num_tokens": 109408.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.28223426416516306,
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.47210052609443665,
+      "learning_rate": 6.109589041095891e-05,
+      "loss": 0.2494,
+      "mean_token_accuracy": 0.9481928303837777,
+      "num_tokens": 123140.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.22195697724819183,
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.48354053497314453,
+      "learning_rate": 5.835616438356165e-05,
+      "loss": 0.2218,
+      "mean_token_accuracy": 0.95259810090065,
+      "num_tokens": 136850.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.21110524237155914,
+      "epoch": 2.8205128205128203,
+      "grad_norm": 0.48064902424812317,
+      "learning_rate": 5.561643835616439e-05,
+      "loss": 0.1959,
+      "mean_token_accuracy": 0.9575912490487098,
+      "num_tokens": 150480.0,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.355695774157842,
+      "eval_loss": 0.40241146087646484,
+      "eval_mean_token_accuracy": 0.9268327752749125,
+      "eval_num_tokens": 159840.0,
+      "eval_runtime": 2.7968,
+      "eval_samples_per_second": 8.581,
+      "eval_steps_per_second": 1.073,
+      "step": 117
+    },
+    {
+      "entropy": 0.23056518994271755,
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.5083797574043274,
+      "learning_rate": 5.2876712328767125e-05,
+      "loss": 0.2134,
+      "mean_token_accuracy": 0.954666568338871,
+      "num_tokens": 163947.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.21548609118908643,
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.6669173836708069,
+      "learning_rate": 5.0136986301369863e-05,
+      "loss": 0.195,
+      "mean_token_accuracy": 0.9568116649985313,
+      "num_tokens": 177722.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.19277227036654948,
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.6170966029167175,
+      "learning_rate": 4.739726027397261e-05,
+      "loss": 0.1786,
+      "mean_token_accuracy": 0.9599042758345604,
+      "num_tokens": 191348.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.1847936963662505,
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.6156774163246155,
+      "learning_rate": 4.465753424657535e-05,
+      "loss": 0.1736,
+      "mean_token_accuracy": 0.9629231780767441,
+      "num_tokens": 204961.0,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.31701664129892987,
+      "eval_loss": 0.4171659052371979,
+      "eval_mean_token_accuracy": 0.9275441765785217,
+      "eval_num_tokens": 213120.0,
+      "eval_runtime": 2.9872,
+      "eval_samples_per_second": 8.034,
+      "eval_steps_per_second": 1.004,
+      "step": 156
+    },
+    {
+      "entropy": 0.2000537607818842,
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.6084583401679993,
+      "learning_rate": 4.1917808219178085e-05,
+      "loss": 0.1788,
+      "mean_token_accuracy": 0.961600199341774,
+      "num_tokens": 218640.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.16115494575351477,
+      "epoch": 4.358974358974359,
+      "grad_norm": 0.612944483757019,
+      "learning_rate": 3.9178082191780823e-05,
+      "loss": 0.1353,
+      "mean_token_accuracy": 0.9696354046463966,
+      "num_tokens": 232303.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.16795936021953822,
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.8854185342788696,
+      "learning_rate": 3.643835616438356e-05,
+      "loss": 0.1473,
+      "mean_token_accuracy": 0.9673726826906204,
+      "num_tokens": 245943.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.17643585596233607,
+      "epoch": 4.871794871794872,
+      "grad_norm": 0.6607788801193237,
+      "learning_rate": 3.369863013698631e-05,
+      "loss": 0.147,
+      "mean_token_accuracy": 0.9683244049549102,
+      "num_tokens": 259614.0,
+      "step": 190
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.26739776134490967,
+      "eval_loss": 0.4382016658782959,
+      "eval_mean_token_accuracy": 0.9290497899055481,
+      "eval_num_tokens": 266400.0,
+      "eval_runtime": 2.8717,
+      "eval_samples_per_second": 8.357,
+      "eval_steps_per_second": 1.045,
+      "step": 195
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 1743553992253440.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-195/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a481ec4511ff65e6d89887f1674e392bf7f467a3e700014f4a1bc5e7acd6d9fd
+size 5880

checkpoint-234/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 0.18.1

checkpoint-234/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-234/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b6550e855e6140f349cfa8819f141bf7edeec9f78290788dd857b6180fb409
+size 100966336

checkpoint-234/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 %}

checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b1ad407bcce88ff98dc8f1b11d7891299f98747c7af3173cacec45ea196670
+size 202101754

checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04480b41443f43abe08b007d9f81b1cde1f8f5a62079008c358d77853cadc4d8
+size 13990

checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e0b381b40f5af548b45cdd6103b0057b095a653e806669433d7f8f390ac50d
+size 1064