Upload nishka-gkc-phi3-base - Stage 1: GKC regulatory knowledge (1.12M tokens, 15 frameworks)

README.md

@@ -0,0 +1,207 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:microsoft/Phi-3-mini-4k-instruct
+- lora
+- transformers
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_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:a7f3952289c2262a57a68735fff2edb4251613ccd88931a318a72ca49bbebfce
+size 35668592

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}

checkpoint-500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:microsoft/Phi-3-mini-4k-instruct
+- lora
+- transformers
+---
+
+# 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

checkpoint-500/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1e17c402702b87314fe32bbb8f589d3edc41d68a74e526844caf176981833f
+size 35668592

checkpoint-500/chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a08a9bc81cec1860fe463195247c698431a38b01e7e16f768e2b201bd6b2c95
+size 18256762

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a453582cebf167418c2bbb42709bd87689f7efaa2ab52f4bfccfdb6f3355458
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78671cb0716cafc72ad64642b0fcd5f1d6fb32452026a729a3bff0bdd25c8f68
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.931400966183575,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03864734299516908,
+      "grad_norm": 0.20904244482517242,
+      "learning_rate": 1.8e-05,
+      "loss": 1.844,
+      "step": 10
+    },
+    {
+      "epoch": 0.07729468599033816,
+      "grad_norm": 0.34712061285972595,
+      "learning_rate": 3.8e-05,
+      "loss": 1.9448,
+      "step": 20
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.5383477210998535,
+      "learning_rate": 5.8e-05,
+      "loss": 1.9599,
+      "step": 30
+    },
+    {
+      "epoch": 0.15458937198067632,
+      "grad_norm": 0.492592453956604,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.8732,
+      "step": 40
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 0.25009018182754517,
+      "learning_rate": 9.8e-05,
+      "loss": 1.6362,
+      "step": 50
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.30719152092933655,
+      "learning_rate": 0.000118,
+      "loss": 1.4755,
+      "step": 60
+    },
+    {
+      "epoch": 0.27053140096618356,
+      "grad_norm": 0.3933989107608795,
+      "learning_rate": 0.000138,
+      "loss": 1.6979,
+      "step": 70
+    },
+    {
+      "epoch": 0.30917874396135264,
+      "grad_norm": 0.2684394419193268,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.5439,
+      "step": 80
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.41456538438796997,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.4658,
+      "step": 90
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 0.330083429813385,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.4276,
+      "step": 100
+    },
+    {
+      "epoch": 0.4251207729468599,
+      "grad_norm": 0.3184288442134857,
+      "learning_rate": 0.00019991280043789991,
+      "loss": 1.3676,
+      "step": 110
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.35775700211524963,
+      "learning_rate": 0.00019961156508936501,
+      "loss": 1.3718,
+      "step": 120
+    },
+    {
+      "epoch": 0.5024154589371981,
+      "grad_norm": 0.2721174657344818,
+      "learning_rate": 0.00019909586582239833,
+      "loss": 1.4321,
+      "step": 130
+    },
+    {
+      "epoch": 0.5410628019323671,
+      "grad_norm": 0.2525996267795563,
+      "learning_rate": 0.00019836681293865439,
+      "loss": 1.3715,
+      "step": 140
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.3816118538379669,
+      "learning_rate": 0.00019742597609059316,
+      "loss": 1.322,
+      "step": 150
+    },
+    {
+      "epoch": 0.6183574879227053,
+      "grad_norm": 0.29589855670928955,
+      "learning_rate": 0.0001962753809020151,
+      "loss": 1.3026,
+      "step": 160
+    },
+    {
+      "epoch": 0.6570048309178744,
+      "grad_norm": 0.26840853691101074,
+      "learning_rate": 0.00019491750460688844,
+      "loss": 1.3374,
+      "step": 170
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.3895309269428253,
+      "learning_rate": 0.00019335527071585916,
+      "loss": 1.4102,
+      "step": 180
+    },
+    {
+      "epoch": 0.7342995169082126,
+      "grad_norm": 0.2829846441745758,
+      "learning_rate": 0.00019159204272192607,
+      "loss": 1.2362,
+      "step": 190
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 0.3511567711830139,
+      "learning_rate": 0.00018963161685883295,
+      "loss": 1.4196,
+      "step": 200
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 0.37351420521736145,
+      "learning_rate": 0.0001874782139277691,
+      "loss": 1.3374,
+      "step": 210
+    },
+    {
+      "epoch": 0.8502415458937198,
+      "grad_norm": 0.3010607957839966,
+      "learning_rate": 0.00018513647020997498,
+      "loss": 1.2565,
+      "step": 220
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3296530246734619,
+      "learning_rate": 0.00018261142748481857,
+      "loss": 1.2906,
+      "step": 230
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 0.3709717392921448,
+      "learning_rate": 0.00017990852217483337,
+      "loss": 1.211,
+      "step": 240
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 0.3170464038848877,
+      "learning_rate": 0.00017703357364108862,
+      "loss": 1.3196,
+      "step": 250
+    },
+    {
+      "epoch": 1.0038647342995168,
+      "grad_norm": 0.3473041355609894,
+      "learning_rate": 0.00017399277165409222,
+      "loss": 1.243,
+      "step": 260
+    },
+    {
+      "epoch": 1.042512077294686,
+      "grad_norm": 0.3345363736152649,
+      "learning_rate": 0.00017079266306720123,
+      "loss": 1.281,
+      "step": 270
+    },
+    {
+      "epoch": 1.0811594202898551,
+      "grad_norm": 0.3957246243953705,
+      "learning_rate": 0.0001674401377212322,
+      "loss": 1.282,
+      "step": 280
+    },
+    {
+      "epoch": 1.1198067632850242,
+      "grad_norm": 0.3802867531776428,
+      "learning_rate": 0.00016394241361061872,
+      "loss": 1.1369,
+      "step": 290
+    },
+    {
+      "epoch": 1.1584541062801932,
+      "grad_norm": 0.29988059401512146,
+      "learning_rate": 0.0001603070213430536,
+      "loss": 1.2696,
+      "step": 300
+    },
+    {
+      "epoch": 1.1971014492753622,
+      "grad_norm": 0.35770756006240845,
+      "learning_rate": 0.000156541787926074,
+      "loss": 1.2301,
+      "step": 310
+    },
+    {
+      "epoch": 1.2357487922705315,
+      "grad_norm": 0.34819772839546204,
+      "learning_rate": 0.00015265481991549689,
+      "loss": 1.2123,
+      "step": 320
+    },
+    {
+      "epoch": 1.2743961352657005,
+      "grad_norm": 0.36298397183418274,
+      "learning_rate": 0.00014865448596198665,
+      "loss": 1.278,
+      "step": 330
+    },
+    {
+      "epoch": 1.3130434782608695,
+      "grad_norm": 0.37550872564315796,
+      "learning_rate": 0.00014454939879333188,
+      "loss": 1.2244,
+      "step": 340
+    },
+    {
+      "epoch": 1.3516908212560386,
+      "grad_norm": 0.36302831768989563,
+      "learning_rate": 0.0001403483966712234,
+      "loss": 1.1648,
+      "step": 350
+    },
+    {
+      "epoch": 1.3903381642512076,
+      "grad_norm": 0.2909848690032959,
+      "learning_rate": 0.00013606052436245748,
+      "loss": 1.2552,
+      "step": 360
+    },
+    {
+      "epoch": 1.4289855072463769,
+      "grad_norm": 0.39212241768836975,
+      "learning_rate": 0.00013169501366553315,
+      "loss": 1.1945,
+      "step": 370
+    },
+    {
+      "epoch": 1.4676328502415459,
+      "grad_norm": 0.36006492376327515,
+      "learning_rate": 0.00012726126353456956,
+      "loss": 1.1752,
+      "step": 380
+    },
+    {
+      "epoch": 1.506280193236715,
+      "grad_norm": 0.3027125298976898,
+      "learning_rate": 0.00012276881984333736,
+      "loss": 1.2091,
+      "step": 390
+    },
+    {
+      "epoch": 1.5449275362318842,
+      "grad_norm": 0.4068925380706787,
+      "learning_rate": 0.00011822735483297129,
+      "loss": 1.266,
+      "step": 400
+    },
+    {
+      "epoch": 1.583574879227053,
+      "grad_norm": 0.33741503953933716,
+      "learning_rate": 0.0001136466462876139,
+      "loss": 1.1504,
+      "step": 410
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.2797302305698395,
+      "learning_rate": 0.00010903655648282476,
+      "loss": 1.146,
+      "step": 420
+    },
+    {
+      "epoch": 1.6608695652173913,
+      "grad_norm": 0.3735846281051636,
+      "learning_rate": 0.00010440701095207947,
+      "loss": 1.3217,
+      "step": 430
+    },
+    {
+      "epoch": 1.6995169082125603,
+      "grad_norm": 0.32088929414749146,
+      "learning_rate": 9.976797711707449e-05,
+      "loss": 1.2309,
+      "step": 440
+    },
+    {
+      "epoch": 1.7381642512077295,
+      "grad_norm": 0.2832978367805481,
+      "learning_rate": 9.512944282784609e-05,
+      "loss": 1.4267,
+      "step": 450
+    },
+    {
+      "epoch": 1.7768115942028986,
+      "grad_norm": 0.3917331099510193,
+      "learning_rate": 9.050139485890739e-05,
+      "loss": 1.1463,
+      "step": 460
+    },
+    {
+      "epoch": 1.8154589371980676,
+      "grad_norm": 0.433745414018631,
+      "learning_rate": 8.58937974077009e-05,
+      "loss": 1.0932,
+      "step": 470
+    },
+    {
+      "epoch": 1.8541062801932369,
+      "grad_norm": 0.3163188099861145,
+      "learning_rate": 8.131657064165962e-05,
+      "loss": 1.2205,
+      "step": 480
+    },
+    {
+      "epoch": 1.8927536231884057,
+      "grad_norm": 0.3267660439014435,
+      "learning_rate": 7.677956934006448e-05,
+      "loss": 1.0875,
+      "step": 490
+    },
+    {
+      "epoch": 1.931400966183575,
+      "grad_norm": 0.3485070466995239,
+      "learning_rate": 7.22925616766833e-05,
+      "loss": 1.2442,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.5354727713189888e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a33dd3953e9073d5a6de04924e24bffed5a1c65605ce20d9909eb3259a9232
+size 5432

checkpoint-777/README.md

@@ -0,0 +1,207 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:microsoft/Phi-3-mini-4k-instruct
+- lora
+- transformers
+---
+
+# 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

checkpoint-777/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-777/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f3952289c2262a57a68735fff2edb4251613ccd88931a318a72ca49bbebfce
+size 35668592

checkpoint-777/chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}

checkpoint-777/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590e90866a93bf4f7aa912439bf3400834d0cf3e8609df0b4cb2436f247f2bb3
+size 18256762

checkpoint-777/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76f0be9327e767f28dac1e692e5be27cd39361499bca91c9d2e251c5ff5c10d
+size 14244

checkpoint-777/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a50f077b56b451c418dd322dde5e9ee88aee07dcfe9592e78ab32a1e34ba2ac
+size 1064

checkpoint-777/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-777/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-777/trainer_state.json

@@ -0,0 +1,573 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 777,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03864734299516908,
+      "grad_norm": 0.20904244482517242,
+      "learning_rate": 1.8e-05,
+      "loss": 1.844,
+      "step": 10
+    },
+    {
+      "epoch": 0.07729468599033816,
+      "grad_norm": 0.34712061285972595,
+      "learning_rate": 3.8e-05,
+      "loss": 1.9448,
+      "step": 20
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.5383477210998535,
+      "learning_rate": 5.8e-05,
+      "loss": 1.9599,
+      "step": 30
+    },
+    {
+      "epoch": 0.15458937198067632,
+      "grad_norm": 0.492592453956604,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.8732,
+      "step": 40
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 0.25009018182754517,
+      "learning_rate": 9.8e-05,
+      "loss": 1.6362,
+      "step": 50
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.30719152092933655,
+      "learning_rate": 0.000118,
+      "loss": 1.4755,
+      "step": 60
+    },
+    {
+      "epoch": 0.27053140096618356,
+      "grad_norm": 0.3933989107608795,
+      "learning_rate": 0.000138,
+      "loss": 1.6979,
+      "step": 70
+    },
+    {
+      "epoch": 0.30917874396135264,
+      "grad_norm": 0.2684394419193268,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.5439,
+      "step": 80
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.41456538438796997,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.4658,
+      "step": 90
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 0.330083429813385,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.4276,
+      "step": 100
+    },
+    {
+      "epoch": 0.4251207729468599,
+      "grad_norm": 0.3184288442134857,
+      "learning_rate": 0.00019991280043789991,
+      "loss": 1.3676,
+      "step": 110
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.35775700211524963,
+      "learning_rate": 0.00019961156508936501,
+      "loss": 1.3718,
+      "step": 120
+    },
+    {
+      "epoch": 0.5024154589371981,
+      "grad_norm": 0.2721174657344818,
+      "learning_rate": 0.00019909586582239833,
+      "loss": 1.4321,
+      "step": 130
+    },
+    {
+      "epoch": 0.5410628019323671,
+      "grad_norm": 0.2525996267795563,
+      "learning_rate": 0.00019836681293865439,
+      "loss": 1.3715,
+      "step": 140
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.3816118538379669,
+      "learning_rate": 0.00019742597609059316,
+      "loss": 1.322,
+      "step": 150
+    },
+    {
+      "epoch": 0.6183574879227053,
+      "grad_norm": 0.29589855670928955,
+      "learning_rate": 0.0001962753809020151,
+      "loss": 1.3026,
+      "step": 160
+    },
+    {
+      "epoch": 0.6570048309178744,
+      "grad_norm": 0.26840853691101074,
+      "learning_rate": 0.00019491750460688844,
+      "loss": 1.3374,
+      "step": 170
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.3895309269428253,
+      "learning_rate": 0.00019335527071585916,
+      "loss": 1.4102,
+      "step": 180
+    },
+    {
+      "epoch": 0.7342995169082126,
+      "grad_norm": 0.2829846441745758,
+      "learning_rate": 0.00019159204272192607,
+      "loss": 1.2362,
+      "step": 190
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 0.3511567711830139,
+      "learning_rate": 0.00018963161685883295,
+      "loss": 1.4196,
+      "step": 200
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 0.37351420521736145,
+      "learning_rate": 0.0001874782139277691,
+      "loss": 1.3374,
+      "step": 210
+    },
+    {
+      "epoch": 0.8502415458937198,
+      "grad_norm": 0.3010607957839966,
+      "learning_rate": 0.00018513647020997498,
+      "loss": 1.2565,
+      "step": 220
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3296530246734619,
+      "learning_rate": 0.00018261142748481857,
+      "loss": 1.2906,
+      "step": 230
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 0.3709717392921448,
+      "learning_rate": 0.00017990852217483337,
+      "loss": 1.211,
+      "step": 240
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 0.3170464038848877,
+      "learning_rate": 0.00017703357364108862,
+      "loss": 1.3196,
+      "step": 250
+    },
+    {
+      "epoch": 1.0038647342995168,
+      "grad_norm": 0.3473041355609894,
+      "learning_rate": 0.00017399277165409222,
+      "loss": 1.243,
+      "step": 260
+    },
+    {
+      "epoch": 1.042512077294686,
+      "grad_norm": 0.3345363736152649,
+      "learning_rate": 0.00017079266306720123,
+      "loss": 1.281,
+      "step": 270
+    },
+    {
+      "epoch": 1.0811594202898551,
+      "grad_norm": 0.3957246243953705,
+      "learning_rate": 0.0001674401377212322,
+      "loss": 1.282,
+      "step": 280
+    },
+    {
+      "epoch": 1.1198067632850242,
+      "grad_norm": 0.3802867531776428,
+      "learning_rate": 0.00016394241361061872,
+      "loss": 1.1369,
+      "step": 290
+    },
+    {
+      "epoch": 1.1584541062801932,
+      "grad_norm": 0.29988059401512146,
+      "learning_rate": 0.0001603070213430536,
+      "loss": 1.2696,
+      "step": 300
+    },
+    {
+      "epoch": 1.1971014492753622,
+      "grad_norm": 0.35770756006240845,
+      "learning_rate": 0.000156541787926074,
+      "loss": 1.2301,
+      "step": 310
+    },
+    {
+      "epoch": 1.2357487922705315,
+      "grad_norm": 0.34819772839546204,
+      "learning_rate": 0.00015265481991549689,
+      "loss": 1.2123,
+      "step": 320
+    },
+    {
+      "epoch": 1.2743961352657005,
+      "grad_norm": 0.36298397183418274,
+      "learning_rate": 0.00014865448596198665,
+      "loss": 1.278,
+      "step": 330
+    },
+    {
+      "epoch": 1.3130434782608695,
+      "grad_norm": 0.37550872564315796,
+      "learning_rate": 0.00014454939879333188,
+      "loss": 1.2244,
+      "step": 340
+    },
+    {
+      "epoch": 1.3516908212560386,
+      "grad_norm": 0.36302831768989563,
+      "learning_rate": 0.0001403483966712234,
+      "loss": 1.1648,
+      "step": 350
+    },
+    {
+      "epoch": 1.3903381642512076,
+      "grad_norm": 0.2909848690032959,
+      "learning_rate": 0.00013606052436245748,
+      "loss": 1.2552,
+      "step": 360
+    },
+    {
+      "epoch": 1.4289855072463769,
+      "grad_norm": 0.39212241768836975,
+      "learning_rate": 0.00013169501366553315,
+      "loss": 1.1945,
+      "step": 370
+    },
+    {
+      "epoch": 1.4676328502415459,
+      "grad_norm": 0.36006492376327515,
+      "learning_rate": 0.00012726126353456956,
+      "loss": 1.1752,
+      "step": 380
+    },
+    {
+      "epoch": 1.506280193236715,
+      "grad_norm": 0.3027125298976898,
+      "learning_rate": 0.00012276881984333736,
+      "loss": 1.2091,
+      "step": 390
+    },
+    {
+      "epoch": 1.5449275362318842,
+      "grad_norm": 0.4068925380706787,
+      "learning_rate": 0.00011822735483297129,
+      "loss": 1.266,
+      "step": 400
+    },
+    {
+      "epoch": 1.583574879227053,
+      "grad_norm": 0.33741503953933716,
+      "learning_rate": 0.0001136466462876139,
+      "loss": 1.1504,
+      "step": 410
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.2797302305698395,
+      "learning_rate": 0.00010903655648282476,
+      "loss": 1.146,
+      "step": 420
+    },
+    {
+      "epoch": 1.6608695652173913,
+      "grad_norm": 0.3735846281051636,
+      "learning_rate": 0.00010440701095207947,
+      "loss": 1.3217,
+      "step": 430
+    },
+    {
+      "epoch": 1.6995169082125603,
+      "grad_norm": 0.32088929414749146,
+      "learning_rate": 9.976797711707449e-05,
+      "loss": 1.2309,
+      "step": 440
+    },
+    {
+      "epoch": 1.7381642512077295,
+      "grad_norm": 0.2832978367805481,
+      "learning_rate": 9.512944282784609e-05,
+      "loss": 1.4267,
+      "step": 450
+    },
+    {
+      "epoch": 1.7768115942028986,
+      "grad_norm": 0.3917331099510193,
+      "learning_rate": 9.050139485890739e-05,
+      "loss": 1.1463,
+      "step": 460
+    },
+    {
+      "epoch": 1.8154589371980676,
+      "grad_norm": 0.433745414018631,
+      "learning_rate": 8.58937974077009e-05,
+      "loss": 1.0932,
+      "step": 470
+    },
+    {
+      "epoch": 1.8541062801932369,
+      "grad_norm": 0.3163188099861145,
+      "learning_rate": 8.131657064165962e-05,
+      "loss": 1.2205,
+      "step": 480
+    },
+    {
+      "epoch": 1.8927536231884057,
+      "grad_norm": 0.3267660439014435,
+      "learning_rate": 7.677956934006448e-05,
+      "loss": 1.0875,
+      "step": 490
+    },
+    {
+      "epoch": 1.931400966183575,
+      "grad_norm": 0.3485070466995239,
+      "learning_rate": 7.22925616766833e-05,
+      "loss": 1.2442,
+      "step": 500
+    },
+    {
+      "epoch": 1.970048309178744,
+      "grad_norm": 0.3910083472728729,
+      "learning_rate": 6.786520818887098e-05,
+      "loss": 1.204,
+      "step": 510
+    },
+    {
+      "epoch": 2.0077294685990337,
+      "grad_norm": 0.2791394591331482,
+      "learning_rate": 6.35070409784113e-05,
+      "loss": 1.1063,
+      "step": 520
+    },
+    {
+      "epoch": 2.046376811594203,
+      "grad_norm": 0.47565358877182007,
+      "learning_rate": 5.922744318888098e-05,
+      "loss": 1.1252,
+      "step": 530
+    },
+    {
+      "epoch": 2.085024154589372,
+      "grad_norm": 0.4235258400440216,
+      "learning_rate": 5.5035628803720977e-05,
+      "loss": 1.1733,
+      "step": 540
+    },
+    {
+      "epoch": 2.123671497584541,
+      "grad_norm": 0.35786592960357666,
+      "learning_rate": 5.094062280850964e-05,
+      "loss": 1.1823,
+      "step": 550
+    },
+    {
+      "epoch": 2.1623188405797102,
+      "grad_norm": 0.4702853858470917,
+      "learning_rate": 4.695124176014938e-05,
+      "loss": 1.1925,
+      "step": 560
+    },
+    {
+      "epoch": 2.200966183574879,
+      "grad_norm": 0.291513592004776,
+      "learning_rate": 4.307607480479977e-05,
+      "loss": 1.1278,
+      "step": 570
+    },
+    {
+      "epoch": 2.2396135265700483,
+      "grad_norm": 0.4636153280735016,
+      "learning_rate": 3.93234651854275e-05,
+      "loss": 1.1733,
+      "step": 580
+    },
+    {
+      "epoch": 2.2782608695652176,
+      "grad_norm": 0.3810688853263855,
+      "learning_rate": 3.570149227878554e-05,
+      "loss": 1.0444,
+      "step": 590
+    },
+    {
+      "epoch": 2.3169082125603864,
+      "grad_norm": 0.35390421748161316,
+      "learning_rate": 3.221795420049744e-05,
+      "loss": 1.1643,
+      "step": 600
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.32782256603240967,
+      "learning_rate": 2.8880351015697338e-05,
+      "loss": 1.2468,
+      "step": 610
+    },
+    {
+      "epoch": 2.3942028985507244,
+      "grad_norm": 0.39302361011505127,
+      "learning_rate": 2.5695868591372974e-05,
+      "loss": 1.1256,
+      "step": 620
+    },
+    {
+      "epoch": 2.4328502415458937,
+      "grad_norm": 0.3332640826702118,
+      "learning_rate": 2.2671363125178635e-05,
+      "loss": 1.1721,
+      "step": 630
+    },
+    {
+      "epoch": 2.471497584541063,
+      "grad_norm": 0.4448571503162384,
+      "learning_rate": 1.9813346384026264e-05,
+      "loss": 1.1808,
+      "step": 640
+    },
+    {
+      "epoch": 2.5101449275362318,
+      "grad_norm": 0.3774722218513489,
+      "learning_rate": 1.7127971684237098e-05,
+      "loss": 1.2162,
+      "step": 650
+    },
+    {
+      "epoch": 2.548792270531401,
+      "grad_norm": 0.4215804934501648,
+      "learning_rate": 1.46210206434382e-05,
+      "loss": 1.1249,
+      "step": 660
+    },
+    {
+      "epoch": 2.58743961352657,
+      "grad_norm": 0.4009312689304352,
+      "learning_rate": 1.2297890732726814e-05,
+      "loss": 1.1052,
+      "step": 670
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 0.3767051100730896,
+      "learning_rate": 1.0163583655903463e-05,
+      "loss": 1.2906,
+      "step": 680
+    },
+    {
+      "epoch": 2.6647342995169083,
+      "grad_norm": 0.3835925757884979,
+      "learning_rate": 8.222694580792434e-06,
+      "loss": 1.2671,
+      "step": 690
+    },
+    {
+      "epoch": 2.703381642512077,
+      "grad_norm": 0.43725937604904175,
+      "learning_rate": 6.479402245835586e-06,
+      "loss": 1.1159,
+      "step": 700
+    },
+    {
+      "epoch": 2.7420289855072464,
+      "grad_norm": 0.38242438435554504,
+      "learning_rate": 4.937459963259206e-06,
+      "loss": 1.2213,
+      "step": 710
+    },
+    {
+      "epoch": 2.780676328502415,
+      "grad_norm": 0.3938469886779785,
+      "learning_rate": 3.6001875381844628e-06,
+      "loss": 1.0229,
+      "step": 720
+    },
+    {
+      "epoch": 2.8193236714975844,
+      "grad_norm": 0.39825060963630676,
+      "learning_rate": 2.470464121079885e-06,
+      "loss": 1.1102,
+      "step": 730
+    },
+    {
+      "epoch": 2.8579710144927537,
+      "grad_norm": 0.27822089195251465,
+      "learning_rate": 1.5507220089438724e-06,
+      "loss": 1.1506,
+      "step": 740
+    },
+    {
+      "epoch": 2.896618357487923,
+      "grad_norm": 0.5396693348884583,
+      "learning_rate": 8.429414085640574e-07,
+      "loss": 1.1307,
+      "step": 750
+    },
+    {
+      "epoch": 2.9352657004830918,
+      "grad_norm": 0.4899618327617645,
+      "learning_rate": 3.4864617312768686e-07,
+      "loss": 1.1499,
+      "step": 760
+    },
+    {
+      "epoch": 2.973913043478261,
+      "grad_norm": 0.41570472717285156,
+      "learning_rate": 6.890052136234726e-08,
+      "loss": 1.1361,
+      "step": 770
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.3913842345278464e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-777/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a33dd3953e9073d5a6de04924e24bffed5a1c65605ce20d9909eb3259a9232
+size 5432

logs/events.out.tfevents.1766975290.3043de093a88.929.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40101b9cdfa756dd6002978893da1339f2d358b1d22308c1811302bb62a97cb2
+size 22297

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a33dd3953e9073d5a6de04924e24bffed5a1c65605ce20d9909eb3259a9232
+size 5432

training_metadata.json

@@ -0,0 +1,48 @@
+{
+  "model_name": "microsoft/Phi-3-mini-4k-instruct",
+  "training_start": "2025-12-29 02:28:10.024982",
+  "dataset": {
+    "path": "/workspace/gkc_training_data.jsonl",
+    "examples": 4139,
+    "frameworks": {
+      "CCPA": 23,
+      "SOX": 72,
+      "NIST_CSF": 72,
+      "GLBA": 163,
+      "GDPR_V2": 213,
+      "HIPAA": 531,
+      "FERPA": 107,
+      "NIST_800_53": 1744,
+      "NIST_Privacy_Framework": 38,
+      "FTC_Privacy": 14,
+      "NIST_AI_RMF": 76,
+      "NIST_800_171": 200,
+      "NIST_CSF_2": 57,
+      "CPRA": 104,
+      "EU_AI_ACT": 672,
+      "CCPA_CPRA_Full": 53
+    }
+  },
+  "lora_config": {
+    "r": 16,
+    "alpha": 32,
+    "dropout": 0.05,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  },
+  "training_args": {
+    "epochs": 3,
+    "batch_size": 4,
+    "learning_rate": 0.0002,
+    "max_length": 2048
+  },
+  "training_end": "2025-12-29 03:32:53.030181",
+  "final_checkpoint": "/workspace/nishka-gkc-phi3-base"
+}