Add files using upload-large-folder tool

Power/README.md

@@ -0,0 +1,62 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Power
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Power
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the power dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.0

Power/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.753086419753085,
+    "total_flos": 2.0386871270503875e+18,
+    "train_loss": 0.6034941236178081,
+    "train_runtime": 4431.3984,
+    "train_samples_per_second": 8.747,
+    "train_steps_per_second": 0.135
+}

Power/checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-100/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.292181069958848,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.407626107753595e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-150/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/checkpoint-150/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-150/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-150/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.938271604938271,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    },
+    {
+      "epoch": 3.6213991769547325,
+      "grad_norm": 0.5937617421150208,
+      "learning_rate": 4.894973780788722e-06,
+      "logits/chosen": 1.8367125988006592,
+      "logits/rejected": 1.8536920547485352,
+      "logps/chosen": -67.41716003417969,
+      "logps/rejected": -72.06455993652344,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.00015740413800813258,
+      "rewards/margins": 0.013882984407246113,
+      "rewards/rejected": -0.01404038816690445,
+      "step": 110
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8695696592330933,
+      "learning_rate": 4.849231551964771e-06,
+      "logits/chosen": 1.8238048553466797,
+      "logits/rejected": 1.7972408533096313,
+      "logps/chosen": -104.34183502197266,
+      "logps/rejected": -81.703369140625,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.00020323302305769175,
+      "rewards/margins": 0.011230283416807652,
+      "rewards/rejected": -0.011027050204575062,
+      "step": 120
+    },
+    {
+      "epoch": 4.279835390946502,
+      "grad_norm": 0.7833828926086426,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": 1.7440074682235718,
+      "logits/rejected": 1.7824723720550537,
+      "logps/chosen": -92.3200912475586,
+      "logps/rejected": -85.88248443603516,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0005388978170230985,
+      "rewards/margins": 0.011814715340733528,
+      "rewards/rejected": -0.011275815777480602,
+      "step": 130
+    },
+    {
+      "epoch": 4.609053497942387,
+      "grad_norm": 0.7381640672683716,
+      "learning_rate": 4.734081600808531e-06,
+      "logits/chosen": 1.6734364032745361,
+      "logits/rejected": 1.7311270236968994,
+      "logps/chosen": -88.11524963378906,
+      "logps/rejected": -97.87281799316406,
+      "loss": 0.682,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.006451706402003765,
+      "rewards/margins": 0.021939774975180626,
+      "rewards/rejected": -0.028391480445861816,
+      "step": 140
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.7793841361999512,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 1.8139768838882446,
+      "logits/rejected": 1.766761064529419,
+      "logps/chosen": -77.28334045410156,
+      "logps/rejected": -78.78504943847656,
+      "loss": 0.6777,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.011237703263759613,
+      "rewards/margins": 0.03930521756410599,
+      "rewards/rejected": -0.050542913377285004,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0929507662351565e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/checkpoint-200/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-200/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-200/trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.584362139917696,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    },
+    {
+      "epoch": 3.6213991769547325,
+      "grad_norm": 0.5937617421150208,
+      "learning_rate": 4.894973780788722e-06,
+      "logits/chosen": 1.8367125988006592,
+      "logits/rejected": 1.8536920547485352,
+      "logps/chosen": -67.41716003417969,
+      "logps/rejected": -72.06455993652344,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.00015740413800813258,
+      "rewards/margins": 0.013882984407246113,
+      "rewards/rejected": -0.01404038816690445,
+      "step": 110
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8695696592330933,
+      "learning_rate": 4.849231551964771e-06,
+      "logits/chosen": 1.8238048553466797,
+      "logits/rejected": 1.7972408533096313,
+      "logps/chosen": -104.34183502197266,
+      "logps/rejected": -81.703369140625,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.00020323302305769175,
+      "rewards/margins": 0.011230283416807652,
+      "rewards/rejected": -0.011027050204575062,
+      "step": 120
+    },
+    {
+      "epoch": 4.279835390946502,
+      "grad_norm": 0.7833828926086426,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": 1.7440074682235718,
+      "logits/rejected": 1.7824723720550537,
+      "logps/chosen": -92.3200912475586,
+      "logps/rejected": -85.88248443603516,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0005388978170230985,
+      "rewards/margins": 0.011814715340733528,
+      "rewards/rejected": -0.011275815777480602,
+      "step": 130
+    },
+    {
+      "epoch": 4.609053497942387,
+      "grad_norm": 0.7381640672683716,
+      "learning_rate": 4.734081600808531e-06,
+      "logits/chosen": 1.6734364032745361,
+      "logits/rejected": 1.7311270236968994,
+      "logps/chosen": -88.11524963378906,
+      "logps/rejected": -97.87281799316406,
+      "loss": 0.682,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.006451706402003765,
+      "rewards/margins": 0.021939774975180626,
+      "rewards/rejected": -0.028391480445861816,
+      "step": 140
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.7793841361999512,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 1.8139768838882446,
+      "logits/rejected": 1.766761064529419,
+      "logps/chosen": -77.28334045410156,
+      "logps/rejected": -78.78504943847656,
+      "loss": 0.6777,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.011237703263759613,
+      "rewards/margins": 0.03930521756410599,
+      "rewards/rejected": -0.050542913377285004,
+      "step": 150
+    },
+    {
+      "epoch": 5.267489711934156,
+      "grad_norm": 0.7763285040855408,
+      "learning_rate": 4.588719528532342e-06,
+      "logits/chosen": 1.7640300989151,
+      "logits/rejected": 1.6494834423065186,
+      "logps/chosen": -91.71728515625,
+      "logps/rejected": -85.06828308105469,
+      "loss": 0.6714,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.034448202699422836,
+      "rewards/margins": 0.02681097947061062,
+      "rewards/rejected": -0.0612591877579689,
+      "step": 160
+    },
+    {
+      "epoch": 5.596707818930041,
+      "grad_norm": 0.9756498336791992,
+      "learning_rate": 4.50530798188761e-06,
+      "logits/chosen": 1.8123546838760376,
+      "logits/rejected": 1.7651164531707764,
+      "logps/chosen": -95.57429504394531,
+      "logps/rejected": -83.24696350097656,
+      "loss": 0.6667,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.02284305915236473,
+      "rewards/margins": 0.04916313290596008,
+      "rewards/rejected": -0.07200618833303452,
+      "step": 170
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.8213481903076172,
+      "learning_rate": 4.415111107797445e-06,
+      "logits/chosen": 1.7565195560455322,
+      "logits/rejected": 1.8321483135223389,
+      "logps/chosen": -90.69538879394531,
+      "logps/rejected": -77.74930572509766,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.030663728713989258,
+      "rewards/margins": 0.07017870247364044,
+      "rewards/rejected": -0.1008424386382103,
+      "step": 180
+    },
+    {
+      "epoch": 6.255144032921811,
+      "grad_norm": 1.067845344543457,
+      "learning_rate": 4.318434103932622e-06,
+      "logits/chosen": 1.7998554706573486,
+      "logits/rejected": 1.7774969339370728,
+      "logps/chosen": -86.76210021972656,
+      "logps/rejected": -86.25608825683594,
+      "loss": 0.66,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.07478730380535126,
+      "rewards/margins": 0.07410295307636261,
+      "rewards/rejected": -0.14889024198055267,
+      "step": 190
+    },
+    {
+      "epoch": 6.584362139917696,
+      "grad_norm": 0.905776858329773,
+      "learning_rate": 4.215604094671835e-06,
+      "logits/chosen": 1.8654216527938843,
+      "logits/rejected": 1.8751890659332275,
+      "logps/chosen": -74.4819107055664,
+      "logps/rejected": -85.82235717773438,
+      "loss": 0.654,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.08698664605617523,
+      "rewards/margins": 0.06426878273487091,
+      "rewards/rejected": -0.15125542879104614,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.780674400174735e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-250/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-250/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/checkpoint-250/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-250/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-250/trainer_state.json

@@ -0,0 +1,408 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.23045267489712,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    },
+    {
+      "epoch": 3.6213991769547325,
+      "grad_norm": 0.5937617421150208,
+      "learning_rate": 4.894973780788722e-06,
+      "logits/chosen": 1.8367125988006592,
+      "logits/rejected": 1.8536920547485352,
+      "logps/chosen": -67.41716003417969,
+      "logps/rejected": -72.06455993652344,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.00015740413800813258,
+      "rewards/margins": 0.013882984407246113,
+      "rewards/rejected": -0.01404038816690445,
+      "step": 110
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8695696592330933,
+      "learning_rate": 4.849231551964771e-06,
+      "logits/chosen": 1.8238048553466797,
+      "logits/rejected": 1.7972408533096313,
+      "logps/chosen": -104.34183502197266,
+      "logps/rejected": -81.703369140625,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.00020323302305769175,
+      "rewards/margins": 0.011230283416807652,
+      "rewards/rejected": -0.011027050204575062,
+      "step": 120
+    },
+    {
+      "epoch": 4.279835390946502,
+      "grad_norm": 0.7833828926086426,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": 1.7440074682235718,
+      "logits/rejected": 1.7824723720550537,
+      "logps/chosen": -92.3200912475586,
+      "logps/rejected": -85.88248443603516,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0005388978170230985,
+      "rewards/margins": 0.011814715340733528,
+      "rewards/rejected": -0.011275815777480602,
+      "step": 130
+    },
+    {
+      "epoch": 4.609053497942387,
+      "grad_norm": 0.7381640672683716,
+      "learning_rate": 4.734081600808531e-06,
+      "logits/chosen": 1.6734364032745361,
+      "logits/rejected": 1.7311270236968994,
+      "logps/chosen": -88.11524963378906,
+      "logps/rejected": -97.87281799316406,
+      "loss": 0.682,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.006451706402003765,
+      "rewards/margins": 0.021939774975180626,
+      "rewards/rejected": -0.028391480445861816,
+      "step": 140
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.7793841361999512,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 1.8139768838882446,
+      "logits/rejected": 1.766761064529419,
+      "logps/chosen": -77.28334045410156,
+      "logps/rejected": -78.78504943847656,
+      "loss": 0.6777,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.011237703263759613,
+      "rewards/margins": 0.03930521756410599,
+      "rewards/rejected": -0.050542913377285004,
+      "step": 150
+    },
+    {
+      "epoch": 5.267489711934156,
+      "grad_norm": 0.7763285040855408,
+      "learning_rate": 4.588719528532342e-06,
+      "logits/chosen": 1.7640300989151,
+      "logits/rejected": 1.6494834423065186,
+      "logps/chosen": -91.71728515625,
+      "logps/rejected": -85.06828308105469,
+      "loss": 0.6714,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.034448202699422836,
+      "rewards/margins": 0.02681097947061062,
+      "rewards/rejected": -0.0612591877579689,
+      "step": 160
+    },
+    {
+      "epoch": 5.596707818930041,
+      "grad_norm": 0.9756498336791992,
+      "learning_rate": 4.50530798188761e-06,
+      "logits/chosen": 1.8123546838760376,
+      "logits/rejected": 1.7651164531707764,
+      "logps/chosen": -95.57429504394531,
+      "logps/rejected": -83.24696350097656,
+      "loss": 0.6667,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.02284305915236473,
+      "rewards/margins": 0.04916313290596008,
+      "rewards/rejected": -0.07200618833303452,
+      "step": 170
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.8213481903076172,
+      "learning_rate": 4.415111107797445e-06,
+      "logits/chosen": 1.7565195560455322,
+      "logits/rejected": 1.8321483135223389,
+      "logps/chosen": -90.69538879394531,
+      "logps/rejected": -77.74930572509766,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.030663728713989258,
+      "rewards/margins": 0.07017870247364044,
+      "rewards/rejected": -0.1008424386382103,
+      "step": 180
+    },
+    {
+      "epoch": 6.255144032921811,
+      "grad_norm": 1.067845344543457,
+      "learning_rate": 4.318434103932622e-06,
+      "logits/chosen": 1.7998554706573486,
+      "logits/rejected": 1.7774969339370728,
+      "logps/chosen": -86.76210021972656,
+      "logps/rejected": -86.25608825683594,
+      "loss": 0.66,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.07478730380535126,
+      "rewards/margins": 0.07410295307636261,
+      "rewards/rejected": -0.14889024198055267,
+      "step": 190
+    },
+    {
+      "epoch": 6.584362139917696,
+      "grad_norm": 0.905776858329773,
+      "learning_rate": 4.215604094671835e-06,
+      "logits/chosen": 1.8654216527938843,
+      "logits/rejected": 1.8751890659332275,
+      "logps/chosen": -74.4819107055664,
+      "logps/rejected": -85.82235717773438,
+      "loss": 0.654,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.08698664605617523,
+      "rewards/margins": 0.06426878273487091,
+      "rewards/rejected": -0.15125542879104614,
+      "step": 200
+    },
+    {
+      "epoch": 6.91358024691358,
+      "grad_norm": 0.9491797685623169,
+      "learning_rate": 4.106969024216348e-06,
+      "logits/chosen": 1.7801555395126343,
+      "logits/rejected": 1.8760993480682373,
+      "logps/chosen": -88.22879028320312,
+      "logps/rejected": -91.16268157958984,
+      "loss": 0.6381,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.05148346349596977,
+      "rewards/margins": 0.13421732187271118,
+      "rewards/rejected": -0.18570080399513245,
+      "step": 210
+    },
+    {
+      "epoch": 7.242798353909465,
+      "grad_norm": 1.0432075262069702,
+      "learning_rate": 3.992896479256966e-06,
+      "logits/chosen": 1.761461853981018,
+      "logits/rejected": 1.7890026569366455,
+      "logps/chosen": -76.50201416015625,
+      "logps/rejected": -83.002685546875,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.1096138209104538,
+      "rewards/margins": 0.13470278680324554,
+      "rewards/rejected": -0.24431662261486053,
+      "step": 220
+    },
+    {
+      "epoch": 7.57201646090535,
+      "grad_norm": 0.9662573933601379,
+      "learning_rate": 3.8737724451770155e-06,
+      "logits/chosen": 1.7268747091293335,
+      "logits/rejected": 1.8781719207763672,
+      "logps/chosen": -85.2467269897461,
+      "logps/rejected": -88.09255981445312,
+      "loss": 0.6253,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09576521068811417,
+      "rewards/margins": 0.19639071822166443,
+      "rewards/rejected": -0.292155921459198,
+      "step": 230
+    },
+    {
+      "epoch": 7.901234567901234,
+      "grad_norm": 1.0413649082183838,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 1.8745641708374023,
+      "logits/rejected": 1.9019807577133179,
+      "logps/chosen": -82.0667724609375,
+      "logps/rejected": -70.83448791503906,
+      "loss": 0.627,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.1119164451956749,
+      "rewards/margins": 0.1671919822692871,
+      "rewards/rejected": -0.2791084349155426,
+      "step": 240
+    },
+    {
+      "epoch": 8.23045267489712,
+      "grad_norm": 1.1005665063858032,
+      "learning_rate": 3.621997950501156e-06,
+      "logits/chosen": 1.8319737911224365,
+      "logits/rejected": 1.8594881296157837,
+      "logps/chosen": -82.2616195678711,
+      "logps/rejected": -94.71448516845703,
+      "loss": 0.6196,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.21282243728637695,
+      "rewards/margins": 0.11685125529766083,
+      "rewards/rejected": -0.3296736776828766,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.48930125339689e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-300/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-300/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-300/trainer_state.json

@@ -0,0 +1,483 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.876543209876543,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    },
+    {
+      "epoch": 3.6213991769547325,
+      "grad_norm": 0.5937617421150208,
+      "learning_rate": 4.894973780788722e-06,
+      "logits/chosen": 1.8367125988006592,
+      "logits/rejected": 1.8536920547485352,
+      "logps/chosen": -67.41716003417969,
+      "logps/rejected": -72.06455993652344,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.00015740413800813258,
+      "rewards/margins": 0.013882984407246113,
+      "rewards/rejected": -0.01404038816690445,
+      "step": 110
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8695696592330933,
+      "learning_rate": 4.849231551964771e-06,
+      "logits/chosen": 1.8238048553466797,
+      "logits/rejected": 1.7972408533096313,
+      "logps/chosen": -104.34183502197266,
+      "logps/rejected": -81.703369140625,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.00020323302305769175,
+      "rewards/margins": 0.011230283416807652,
+      "rewards/rejected": -0.011027050204575062,
+      "step": 120
+    },
+    {
+      "epoch": 4.279835390946502,
+      "grad_norm": 0.7833828926086426,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": 1.7440074682235718,
+      "logits/rejected": 1.7824723720550537,
+      "logps/chosen": -92.3200912475586,
+      "logps/rejected": -85.88248443603516,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0005388978170230985,
+      "rewards/margins": 0.011814715340733528,
+      "rewards/rejected": -0.011275815777480602,
+      "step": 130
+    },
+    {
+      "epoch": 4.609053497942387,
+      "grad_norm": 0.7381640672683716,
+      "learning_rate": 4.734081600808531e-06,
+      "logits/chosen": 1.6734364032745361,
+      "logits/rejected": 1.7311270236968994,
+      "logps/chosen": -88.11524963378906,
+      "logps/rejected": -97.87281799316406,
+      "loss": 0.682,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.006451706402003765,
+      "rewards/margins": 0.021939774975180626,
+      "rewards/rejected": -0.028391480445861816,
+      "step": 140
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.7793841361999512,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 1.8139768838882446,
+      "logits/rejected": 1.766761064529419,
+      "logps/chosen": -77.28334045410156,
+      "logps/rejected": -78.78504943847656,
+      "loss": 0.6777,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.011237703263759613,
+      "rewards/margins": 0.03930521756410599,
+      "rewards/rejected": -0.050542913377285004,
+      "step": 150
+    },
+    {
+      "epoch": 5.267489711934156,
+      "grad_norm": 0.7763285040855408,
+      "learning_rate": 4.588719528532342e-06,
+      "logits/chosen": 1.7640300989151,
+      "logits/rejected": 1.6494834423065186,
+      "logps/chosen": -91.71728515625,
+      "logps/rejected": -85.06828308105469,
+      "loss": 0.6714,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.034448202699422836,
+      "rewards/margins": 0.02681097947061062,
+      "rewards/rejected": -0.0612591877579689,
+      "step": 160
+    },
+    {
+      "epoch": 5.596707818930041,
+      "grad_norm": 0.9756498336791992,
+      "learning_rate": 4.50530798188761e-06,
+      "logits/chosen": 1.8123546838760376,
+      "logits/rejected": 1.7651164531707764,
+      "logps/chosen": -95.57429504394531,
+      "logps/rejected": -83.24696350097656,
+      "loss": 0.6667,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.02284305915236473,
+      "rewards/margins": 0.04916313290596008,
+      "rewards/rejected": -0.07200618833303452,
+      "step": 170
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.8213481903076172,
+      "learning_rate": 4.415111107797445e-06,
+      "logits/chosen": 1.7565195560455322,
+      "logits/rejected": 1.8321483135223389,
+      "logps/chosen": -90.69538879394531,
+      "logps/rejected": -77.74930572509766,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.030663728713989258,
+      "rewards/margins": 0.07017870247364044,
+      "rewards/rejected": -0.1008424386382103,
+      "step": 180
+    },
+    {
+      "epoch": 6.255144032921811,
+      "grad_norm": 1.067845344543457,
+      "learning_rate": 4.318434103932622e-06,
+      "logits/chosen": 1.7998554706573486,
+      "logits/rejected": 1.7774969339370728,
+      "logps/chosen": -86.76210021972656,
+      "logps/rejected": -86.25608825683594,
+      "loss": 0.66,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.07478730380535126,
+      "rewards/margins": 0.07410295307636261,
+      "rewards/rejected": -0.14889024198055267,
+      "step": 190
+    },
+    {
+      "epoch": 6.584362139917696,
+      "grad_norm": 0.905776858329773,
+      "learning_rate": 4.215604094671835e-06,
+      "logits/chosen": 1.8654216527938843,
+      "logits/rejected": 1.8751890659332275,
+      "logps/chosen": -74.4819107055664,
+      "logps/rejected": -85.82235717773438,
+      "loss": 0.654,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.08698664605617523,
+      "rewards/margins": 0.06426878273487091,
+      "rewards/rejected": -0.15125542879104614,
+      "step": 200
+    },
+    {
+      "epoch": 6.91358024691358,
+      "grad_norm": 0.9491797685623169,
+      "learning_rate": 4.106969024216348e-06,
+      "logits/chosen": 1.7801555395126343,
+      "logits/rejected": 1.8760993480682373,
+      "logps/chosen": -88.22879028320312,
+      "logps/rejected": -91.16268157958984,
+      "loss": 0.6381,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.05148346349596977,
+      "rewards/margins": 0.13421732187271118,
+      "rewards/rejected": -0.18570080399513245,
+      "step": 210
+    },
+    {
+      "epoch": 7.242798353909465,
+      "grad_norm": 1.0432075262069702,
+      "learning_rate": 3.992896479256966e-06,
+      "logits/chosen": 1.761461853981018,
+      "logits/rejected": 1.7890026569366455,
+      "logps/chosen": -76.50201416015625,
+      "logps/rejected": -83.002685546875,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.1096138209104538,
+      "rewards/margins": 0.13470278680324554,
+      "rewards/rejected": -0.24431662261486053,
+      "step": 220
+    },
+    {
+      "epoch": 7.57201646090535,
+      "grad_norm": 0.9662573933601379,
+      "learning_rate": 3.8737724451770155e-06,
+      "logits/chosen": 1.7268747091293335,
+      "logits/rejected": 1.8781719207763672,
+      "logps/chosen": -85.2467269897461,
+      "logps/rejected": -88.09255981445312,
+      "loss": 0.6253,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09576521068811417,
+      "rewards/margins": 0.19639071822166443,
+      "rewards/rejected": -0.292155921459198,
+      "step": 230
+    },
+    {
+      "epoch": 7.901234567901234,
+      "grad_norm": 1.0413649082183838,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 1.8745641708374023,
+      "logits/rejected": 1.9019807577133179,
+      "logps/chosen": -82.0667724609375,
+      "logps/rejected": -70.83448791503906,
+      "loss": 0.627,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.1119164451956749,
+      "rewards/margins": 0.1671919822692871,
+      "rewards/rejected": -0.2791084349155426,
+      "step": 240
+    },
+    {
+      "epoch": 8.23045267489712,
+      "grad_norm": 1.1005665063858032,
+      "learning_rate": 3.621997950501156e-06,
+      "logits/chosen": 1.8319737911224365,
+      "logits/rejected": 1.8594881296157837,
+      "logps/chosen": -82.2616195678711,
+      "logps/rejected": -94.71448516845703,
+      "loss": 0.6196,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.21282243728637695,
+      "rewards/margins": 0.11685125529766083,
+      "rewards/rejected": -0.3296736776828766,
+      "step": 250
+    },
+    {
+      "epoch": 8.559670781893004,
+      "grad_norm": 1.0339275598526,
+      "learning_rate": 3.4901994150978926e-06,
+      "logits/chosen": 1.8168909549713135,
+      "logits/rejected": 1.8122689723968506,
+      "logps/chosen": -86.70075988769531,
+      "logps/rejected": -87.91035461425781,
+      "loss": 0.6097,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.21122360229492188,
+      "rewards/margins": 0.1889980137348175,
+      "rewards/rejected": -0.40022164583206177,
+      "step": 260
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 1.0026566982269287,
+      "learning_rate": 3.3550503583141726e-06,
+      "logits/chosen": 1.7882308959960938,
+      "logits/rejected": 1.7757456302642822,
+      "logps/chosen": -98.28022766113281,
+      "logps/rejected": -99.22371673583984,
+      "loss": 0.6042,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.23864057660102844,
+      "rewards/margins": 0.17245283722877502,
+      "rewards/rejected": -0.4110933840274811,
+      "step": 270
+    },
+    {
+      "epoch": 9.218106995884774,
+      "grad_norm": 0.9841915965080261,
+      "learning_rate": 3.217008081777726e-06,
+      "logits/chosen": 1.8728599548339844,
+      "logits/rejected": 1.7537968158721924,
+      "logps/chosen": -110.29930114746094,
+      "logps/rejected": -76.87739562988281,
+      "loss": 0.5986,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.16357959806919098,
+      "rewards/margins": 0.30878886580467224,
+      "rewards/rejected": -0.47236841917037964,
+      "step": 280
+    },
+    {
+      "epoch": 9.547325102880658,
+      "grad_norm": 1.0610634088516235,
+      "learning_rate": 3.0765396768561005e-06,
+      "logits/chosen": 1.8760344982147217,
+      "logits/rejected": 1.8611949682235718,
+      "logps/chosen": -83.32715606689453,
+      "logps/rejected": -91.76313781738281,
+      "loss": 0.5953,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.24952685832977295,
+      "rewards/margins": 0.23791106045246124,
+      "rewards/rejected": -0.4874378740787506,
+      "step": 290
+    },
+    {
+      "epoch": 9.876543209876543,
+      "grad_norm": 1.0584696531295776,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.713905692100525,
+      "logits/rejected": 1.761605978012085,
+      "logps/chosen": -84.4806900024414,
+      "logps/rejected": -84.85515594482422,
+      "loss": 0.5853,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.3275205194950104,
+      "rewards/margins": 0.20603664219379425,
+      "rewards/rejected": -0.5335571765899658,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.019216299349246e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-400/trainer_state.json

@@ -0,0 +1,633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.168724279835391,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5260242819786072,
+      "learning_rate": 5e-06,
+      "logits/chosen": 1.827275037765503,
+      "logits/rejected": 1.8168131113052368,
+      "logps/chosen": -86.74467468261719,
+      "logps/rejected": -79.20576477050781,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.0014693590346723795,
+      "rewards/margins": -0.0025326632894575596,
+      "rewards/rejected": 0.00400202302262187,
+      "step": 60
+    },
+    {
+      "epoch": 2.3045267489711936,
+      "grad_norm": 0.5231289267539978,
+      "learning_rate": 4.995770395678171e-06,
+      "logits/chosen": 1.7851394414901733,
+      "logits/rejected": 1.8952877521514893,
+      "logps/chosen": -81.03253173828125,
+      "logps/rejected": -88.5263442993164,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.003017458599060774,
+      "rewards/margins": -0.002731734188273549,
+      "rewards/rejected": -0.0002857256622519344,
+      "step": 70
+    },
+    {
+      "epoch": 2.633744855967078,
+      "grad_norm": 0.5552361011505127,
+      "learning_rate": 4.983095894354858e-06,
+      "logits/chosen": 1.8227930068969727,
+      "logits/rejected": 1.7752052545547485,
+      "logps/chosen": -89.98479461669922,
+      "logps/rejected": -72.01054382324219,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0013810636010020971,
+      "rewards/margins": -0.0008344938978552818,
+      "rewards/rejected": 0.0022155570331960917,
+      "step": 80
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.603434681892395,
+      "learning_rate": 4.962019382530521e-06,
+      "logits/chosen": 1.829049825668335,
+      "logits/rejected": 1.78665030002594,
+      "logps/chosen": -81.95549011230469,
+      "logps/rejected": -76.07003021240234,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0062006814405322075,
+      "rewards/margins": 0.003528360743075609,
+      "rewards/rejected": 0.00267231953330338,
+      "step": 90
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 0.6200206279754639,
+      "learning_rate": 4.93261217644956e-06,
+      "logits/chosen": 1.7920262813568115,
+      "logits/rejected": 1.7817165851593018,
+      "logps/chosen": -84.39167022705078,
+      "logps/rejected": -85.04205322265625,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.0063859038054943085,
+      "rewards/margins": 0.007152262143790722,
+      "rewards/rejected": -0.0007663581636734307,
+      "step": 100
+    },
+    {
+      "epoch": 3.6213991769547325,
+      "grad_norm": 0.5937617421150208,
+      "learning_rate": 4.894973780788722e-06,
+      "logits/chosen": 1.8367125988006592,
+      "logits/rejected": 1.8536920547485352,
+      "logps/chosen": -67.41716003417969,
+      "logps/rejected": -72.06455993652344,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.00015740413800813258,
+      "rewards/margins": 0.013882984407246113,
+      "rewards/rejected": -0.01404038816690445,
+      "step": 110
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8695696592330933,
+      "learning_rate": 4.849231551964771e-06,
+      "logits/chosen": 1.8238048553466797,
+      "logits/rejected": 1.7972408533096313,
+      "logps/chosen": -104.34183502197266,
+      "logps/rejected": -81.703369140625,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.00020323302305769175,
+      "rewards/margins": 0.011230283416807652,
+      "rewards/rejected": -0.011027050204575062,
+      "step": 120
+    },
+    {
+      "epoch": 4.279835390946502,
+      "grad_norm": 0.7833828926086426,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": 1.7440074682235718,
+      "logits/rejected": 1.7824723720550537,
+      "logps/chosen": -92.3200912475586,
+      "logps/rejected": -85.88248443603516,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0005388978170230985,
+      "rewards/margins": 0.011814715340733528,
+      "rewards/rejected": -0.011275815777480602,
+      "step": 130
+    },
+    {
+      "epoch": 4.609053497942387,
+      "grad_norm": 0.7381640672683716,
+      "learning_rate": 4.734081600808531e-06,
+      "logits/chosen": 1.6734364032745361,
+      "logits/rejected": 1.7311270236968994,
+      "logps/chosen": -88.11524963378906,
+      "logps/rejected": -97.87281799316406,
+      "loss": 0.682,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.006451706402003765,
+      "rewards/margins": 0.021939774975180626,
+      "rewards/rejected": -0.028391480445861816,
+      "step": 140
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.7793841361999512,
+      "learning_rate": 4.665063509461098e-06,
+      "logits/chosen": 1.8139768838882446,
+      "logits/rejected": 1.766761064529419,
+      "logps/chosen": -77.28334045410156,
+      "logps/rejected": -78.78504943847656,
+      "loss": 0.6777,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.011237703263759613,
+      "rewards/margins": 0.03930521756410599,
+      "rewards/rejected": -0.050542913377285004,
+      "step": 150
+    },
+    {
+      "epoch": 5.267489711934156,
+      "grad_norm": 0.7763285040855408,
+      "learning_rate": 4.588719528532342e-06,
+      "logits/chosen": 1.7640300989151,
+      "logits/rejected": 1.6494834423065186,
+      "logps/chosen": -91.71728515625,
+      "logps/rejected": -85.06828308105469,
+      "loss": 0.6714,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.034448202699422836,
+      "rewards/margins": 0.02681097947061062,
+      "rewards/rejected": -0.0612591877579689,
+      "step": 160
+    },
+    {
+      "epoch": 5.596707818930041,
+      "grad_norm": 0.9756498336791992,
+      "learning_rate": 4.50530798188761e-06,
+      "logits/chosen": 1.8123546838760376,
+      "logits/rejected": 1.7651164531707764,
+      "logps/chosen": -95.57429504394531,
+      "logps/rejected": -83.24696350097656,
+      "loss": 0.6667,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.02284305915236473,
+      "rewards/margins": 0.04916313290596008,
+      "rewards/rejected": -0.07200618833303452,
+      "step": 170
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.8213481903076172,
+      "learning_rate": 4.415111107797445e-06,
+      "logits/chosen": 1.7565195560455322,
+      "logits/rejected": 1.8321483135223389,
+      "logps/chosen": -90.69538879394531,
+      "logps/rejected": -77.74930572509766,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.030663728713989258,
+      "rewards/margins": 0.07017870247364044,
+      "rewards/rejected": -0.1008424386382103,
+      "step": 180
+    },
+    {
+      "epoch": 6.255144032921811,
+      "grad_norm": 1.067845344543457,
+      "learning_rate": 4.318434103932622e-06,
+      "logits/chosen": 1.7998554706573486,
+      "logits/rejected": 1.7774969339370728,
+      "logps/chosen": -86.76210021972656,
+      "logps/rejected": -86.25608825683594,
+      "loss": 0.66,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.07478730380535126,
+      "rewards/margins": 0.07410295307636261,
+      "rewards/rejected": -0.14889024198055267,
+      "step": 190
+    },
+    {
+      "epoch": 6.584362139917696,
+      "grad_norm": 0.905776858329773,
+      "learning_rate": 4.215604094671835e-06,
+      "logits/chosen": 1.8654216527938843,
+      "logits/rejected": 1.8751890659332275,
+      "logps/chosen": -74.4819107055664,
+      "logps/rejected": -85.82235717773438,
+      "loss": 0.654,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.08698664605617523,
+      "rewards/margins": 0.06426878273487091,
+      "rewards/rejected": -0.15125542879104614,
+      "step": 200
+    },
+    {
+      "epoch": 6.91358024691358,
+      "grad_norm": 0.9491797685623169,
+      "learning_rate": 4.106969024216348e-06,
+      "logits/chosen": 1.7801555395126343,
+      "logits/rejected": 1.8760993480682373,
+      "logps/chosen": -88.22879028320312,
+      "logps/rejected": -91.16268157958984,
+      "loss": 0.6381,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.05148346349596977,
+      "rewards/margins": 0.13421732187271118,
+      "rewards/rejected": -0.18570080399513245,
+      "step": 210
+    },
+    {
+      "epoch": 7.242798353909465,
+      "grad_norm": 1.0432075262069702,
+      "learning_rate": 3.992896479256966e-06,
+      "logits/chosen": 1.761461853981018,
+      "logits/rejected": 1.7890026569366455,
+      "logps/chosen": -76.50201416015625,
+      "logps/rejected": -83.002685546875,
+      "loss": 0.6387,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.1096138209104538,
+      "rewards/margins": 0.13470278680324554,
+      "rewards/rejected": -0.24431662261486053,
+      "step": 220
+    },
+    {
+      "epoch": 7.57201646090535,
+      "grad_norm": 0.9662573933601379,
+      "learning_rate": 3.8737724451770155e-06,
+      "logits/chosen": 1.7268747091293335,
+      "logits/rejected": 1.8781719207763672,
+      "logps/chosen": -85.2467269897461,
+      "logps/rejected": -88.09255981445312,
+      "loss": 0.6253,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.09576521068811417,
+      "rewards/margins": 0.19639071822166443,
+      "rewards/rejected": -0.292155921459198,
+      "step": 230
+    },
+    {
+      "epoch": 7.901234567901234,
+      "grad_norm": 1.0413649082183838,
+      "learning_rate": 3.7500000000000005e-06,
+      "logits/chosen": 1.8745641708374023,
+      "logits/rejected": 1.9019807577133179,
+      "logps/chosen": -82.0667724609375,
+      "logps/rejected": -70.83448791503906,
+      "loss": 0.627,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.1119164451956749,
+      "rewards/margins": 0.1671919822692871,
+      "rewards/rejected": -0.2791084349155426,
+      "step": 240
+    },
+    {
+      "epoch": 8.23045267489712,
+      "grad_norm": 1.1005665063858032,
+      "learning_rate": 3.621997950501156e-06,
+      "logits/chosen": 1.8319737911224365,
+      "logits/rejected": 1.8594881296157837,
+      "logps/chosen": -82.2616195678711,
+      "logps/rejected": -94.71448516845703,
+      "loss": 0.6196,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.21282243728637695,
+      "rewards/margins": 0.11685125529766083,
+      "rewards/rejected": -0.3296736776828766,
+      "step": 250
+    },
+    {
+      "epoch": 8.559670781893004,
+      "grad_norm": 1.0339275598526,
+      "learning_rate": 3.4901994150978926e-06,
+      "logits/chosen": 1.8168909549713135,
+      "logits/rejected": 1.8122689723968506,
+      "logps/chosen": -86.70075988769531,
+      "logps/rejected": -87.91035461425781,
+      "loss": 0.6097,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.21122360229492188,
+      "rewards/margins": 0.1889980137348175,
+      "rewards/rejected": -0.40022164583206177,
+      "step": 260
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 1.0026566982269287,
+      "learning_rate": 3.3550503583141726e-06,
+      "logits/chosen": 1.7882308959960938,
+      "logits/rejected": 1.7757456302642822,
+      "logps/chosen": -98.28022766113281,
+      "logps/rejected": -99.22371673583984,
+      "loss": 0.6042,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.23864057660102844,
+      "rewards/margins": 0.17245283722877502,
+      "rewards/rejected": -0.4110933840274811,
+      "step": 270
+    },
+    {
+      "epoch": 9.218106995884774,
+      "grad_norm": 0.9841915965080261,
+      "learning_rate": 3.217008081777726e-06,
+      "logits/chosen": 1.8728599548339844,
+      "logits/rejected": 1.7537968158721924,
+      "logps/chosen": -110.29930114746094,
+      "logps/rejected": -76.87739562988281,
+      "loss": 0.5986,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.16357959806919098,
+      "rewards/margins": 0.30878886580467224,
+      "rewards/rejected": -0.47236841917037964,
+      "step": 280
+    },
+    {
+      "epoch": 9.547325102880658,
+      "grad_norm": 1.0610634088516235,
+      "learning_rate": 3.0765396768561005e-06,
+      "logits/chosen": 1.8760344982147217,
+      "logits/rejected": 1.8611949682235718,
+      "logps/chosen": -83.32715606689453,
+      "logps/rejected": -91.76313781738281,
+      "loss": 0.5953,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.24952685832977295,
+      "rewards/margins": 0.23791106045246124,
+      "rewards/rejected": -0.4874378740787506,
+      "step": 290
+    },
+    {
+      "epoch": 9.876543209876543,
+      "grad_norm": 1.0584696531295776,
+      "learning_rate": 2.9341204441673267e-06,
+      "logits/chosen": 1.713905692100525,
+      "logits/rejected": 1.761605978012085,
+      "logps/chosen": -84.4806900024414,
+      "logps/rejected": -84.85515594482422,
+      "loss": 0.5853,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.3275205194950104,
+      "rewards/margins": 0.20603664219379425,
+      "rewards/rejected": -0.5335571765899658,
+      "step": 300
+    },
+    {
+      "epoch": 10.205761316872428,
+      "grad_norm": 1.2500941753387451,
+      "learning_rate": 2.7902322853130758e-06,
+      "logits/chosen": 1.70700204372406,
+      "logits/rejected": 1.7708561420440674,
+      "logps/chosen": -83.38414001464844,
+      "logps/rejected": -84.97639465332031,
+      "loss": 0.5889,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.2745892405509949,
+      "rewards/margins": 0.3200107514858246,
+      "rewards/rejected": -0.5945999622344971,
+      "step": 310
+    },
+    {
+      "epoch": 10.534979423868313,
+      "grad_norm": 1.0091391801834106,
+      "learning_rate": 2.6453620722761897e-06,
+      "logits/chosen": 1.656237006187439,
+      "logits/rejected": 1.7875343561172485,
+      "logps/chosen": -76.54080200195312,
+      "logps/rejected": -99.77791595458984,
+      "loss": 0.5805,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.2655033469200134,
+      "rewards/margins": 0.23930945992469788,
+      "rewards/rejected": -0.5048128366470337,
+      "step": 320
+    },
+    {
+      "epoch": 10.864197530864198,
+      "grad_norm": 1.280364990234375,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7501579523086548,
+      "logits/rejected": 1.8710143566131592,
+      "logps/chosen": -95.80509948730469,
+      "logps/rejected": -98.95433044433594,
+      "loss": 0.5681,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.25459492206573486,
+      "rewards/margins": 0.4196421504020691,
+      "rewards/rejected": -0.674237072467804,
+      "step": 330
+    },
+    {
+      "epoch": 11.193415637860083,
+      "grad_norm": 1.0981961488723755,
+      "learning_rate": 2.3546379277238107e-06,
+      "logits/chosen": 1.781877875328064,
+      "logits/rejected": 1.8056217432022095,
+      "logps/chosen": -80.20987701416016,
+      "logps/rejected": -94.3116226196289,
+      "loss": 0.5684,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.39583852887153625,
+      "rewards/margins": 0.2972935140132904,
+      "rewards/rejected": -0.6931320428848267,
+      "step": 340
+    },
+    {
+      "epoch": 11.522633744855966,
+      "grad_norm": 1.1398284435272217,
+      "learning_rate": 2.2097677146869242e-06,
+      "logits/chosen": 1.7265570163726807,
+      "logits/rejected": 1.7091245651245117,
+      "logps/chosen": -75.80311584472656,
+      "logps/rejected": -79.35089111328125,
+      "loss": 0.5656,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.3116758465766907,
+      "rewards/margins": 0.42105427384376526,
+      "rewards/rejected": -0.7327300906181335,
+      "step": 350
+    },
+    {
+      "epoch": 11.851851851851851,
+      "grad_norm": 1.1577041149139404,
+      "learning_rate": 2.0658795558326745e-06,
+      "logits/chosen": 1.692983865737915,
+      "logits/rejected": 1.7239530086517334,
+      "logps/chosen": -91.54319763183594,
+      "logps/rejected": -93.06980895996094,
+      "loss": 0.5699,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.38909879326820374,
+      "rewards/margins": 0.34535473585128784,
+      "rewards/rejected": -0.734453558921814,
+      "step": 360
+    },
+    {
+      "epoch": 12.181069958847736,
+      "grad_norm": 1.405211329460144,
+      "learning_rate": 1.9234603231439e-06,
+      "logits/chosen": 1.7344582080841064,
+      "logits/rejected": 1.7111711502075195,
+      "logps/chosen": -88.46275329589844,
+      "logps/rejected": -82.77845001220703,
+      "loss": 0.5577,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.3398984372615814,
+      "rewards/margins": 0.4276389181613922,
+      "rewards/rejected": -0.7675372958183289,
+      "step": 370
+    },
+    {
+      "epoch": 12.510288065843621,
+      "grad_norm": 1.4324347972869873,
+      "learning_rate": 1.7829919182222752e-06,
+      "logits/chosen": 1.7103168964385986,
+      "logits/rejected": 1.7571923732757568,
+      "logps/chosen": -83.42256927490234,
+      "logps/rejected": -95.48295593261719,
+      "loss": 0.5493,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.39600270986557007,
+      "rewards/margins": 0.447258323431015,
+      "rewards/rejected": -0.8432610630989075,
+      "step": 380
+    },
+    {
+      "epoch": 12.839506172839506,
+      "grad_norm": 1.1979031562805176,
+      "learning_rate": 1.6449496416858285e-06,
+      "logits/chosen": 1.6545474529266357,
+      "logits/rejected": 1.7649863958358765,
+      "logps/chosen": -78.60997772216797,
+      "logps/rejected": -91.09608459472656,
+      "loss": 0.5618,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.3745049834251404,
+      "rewards/margins": 0.4601859450340271,
+      "rewards/rejected": -0.8346909284591675,
+      "step": 390
+    },
+    {
+      "epoch": 13.168724279835391,
+      "grad_norm": 1.164794683456421,
+      "learning_rate": 1.509800584902108e-06,
+      "logits/chosen": 1.7000430822372437,
+      "logits/rejected": 1.7276875972747803,
+      "logps/chosen": -90.08226013183594,
+      "logps/rejected": -82.01007843017578,
+      "loss": 0.5517,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.3675037622451782,
+      "rewards/margins": 0.44133225083351135,
+      "rewards/rejected": -0.8088359832763672,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.358654720167641e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/checkpoint-450/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-450/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-50/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0

Power/checkpoint-50/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/checkpoint-50/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/checkpoint-50/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

Power/checkpoint-50/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.646090534979424,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5561477541923523,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": 1.7485754489898682,
+      "logits/rejected": 1.8832639455795288,
+      "logps/chosen": -70.18267059326172,
+      "logps/rejected": -77.9986343383789,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.005453853867948055,
+      "rewards/margins": 0.013218576088547707,
+      "rewards/rejected": -0.007764720823615789,
+      "step": 10
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.48141908645629883,
+      "learning_rate": 1.6666666666666667e-06,
+      "logits/chosen": 1.9016907215118408,
+      "logits/rejected": 1.9251121282577515,
+      "logps/chosen": -96.5027847290039,
+      "logps/rejected": -87.00735473632812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.005797500256448984,
+      "rewards/margins": -0.0004409264656715095,
+      "rewards/rejected": -0.005356573965400457,
+      "step": 20
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.4639015197753906,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": 1.7938541173934937,
+      "logits/rejected": 1.6962993144989014,
+      "logps/chosen": -71.47590637207031,
+      "logps/rejected": -66.45989227294922,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.004830303601920605,
+      "rewards/margins": -0.00935445912182331,
+      "rewards/rejected": 0.004524155054241419,
+      "step": 30
+    },
+    {
+      "epoch": 1.316872427983539,
+      "grad_norm": 0.44931092858314514,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": 1.8256213665008545,
+      "logits/rejected": 1.8677200078964233,
+      "logps/chosen": -75.90711975097656,
+      "logps/rejected": -76.26548767089844,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.004859285429120064,
+      "rewards/margins": -0.007447429001331329,
+      "rewards/rejected": 0.0025881435722112656,
+      "step": 40
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 0.512350857257843,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": 1.7572576999664307,
+      "logits/rejected": 1.7408854961395264,
+      "logps/chosen": -80.90664672851562,
+      "logps/rejected": -85.82096862792969,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.00120059447363019,
+      "rewards/margins": -0.0018891148502007127,
+      "rewards/rejected": 0.0006885197362862527,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7075005624732877e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/dpo/README.md

@@ -0,0 +1,72 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: dpo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dpo
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the power dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6761
+- Rewards/chosen: -0.0345
+- Rewards/rejected: -0.0681
+- Rewards/accuracies: 0.5200
+- Rewards/margins: 0.0336
+- Logps/rejected: -85.4496
+- Logps/chosen: -71.8206
+- Logits/rejected: 1.8751
+- Logits/chosen: 1.6702
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.0

Power/dpo/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/dpo/checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Power/dpo/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Power/dpo/checkpoint-100/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.669724770642202,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.4546981155872345,
+      "learning_rate": 1.8518518518518519e-06,
+      "logits/chosen": 1.790213942527771,
+      "logits/rejected": 1.8330585956573486,
+      "logps/chosen": -75.35237121582031,
+      "logps/rejected": -77.22242736816406,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.006426649633795023,
+      "rewards/margins": -0.008417336270213127,
+      "rewards/rejected": 0.0019906857050955296,
+      "step": 10
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.5062414407730103,
+      "learning_rate": 3.7037037037037037e-06,
+      "logits/chosen": 1.8213964700698853,
+      "logits/rejected": 1.7818235158920288,
+      "logps/chosen": -83.15866088867188,
+      "logps/rejected": -78.38325500488281,
+      "loss": 0.695,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.006863894872367382,
+      "rewards/margins": -0.010942240245640278,
+      "rewards/rejected": 0.0040783449076116085,
+      "step": 20
+    },
+    {
+      "epoch": 1.1009174311926606,
+      "grad_norm": 0.5203150510787964,
+      "learning_rate": 4.998119881260576e-06,
+      "logits/chosen": 1.811631441116333,
+      "logits/rejected": 1.7203019857406616,
+      "logps/chosen": -96.63399505615234,
+      "logps/rejected": -83.23392486572266,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.00417748000472784,
+      "rewards/margins": -0.006159568205475807,
+      "rewards/rejected": 0.0019820884335786104,
+      "step": 30
+    },
+    {
+      "epoch": 1.4678899082568808,
+      "grad_norm": 0.5335714221000671,
+      "learning_rate": 4.964774158361991e-06,
+      "logits/chosen": 1.8185322284698486,
+      "logits/rejected": 1.7785847187042236,
+      "logps/chosen": -80.90029907226562,
+      "logps/rejected": -76.1764144897461,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.008144860155880451,
+      "rewards/margins": -0.001973528414964676,
+      "rewards/rejected": -0.006171331740915775,
+      "step": 40
+    },
+    {
+      "epoch": 1.834862385321101,
+      "grad_norm": 0.5139996409416199,
+      "learning_rate": 4.8902889044347e-06,
+      "logits/chosen": 1.8735860586166382,
+      "logits/rejected": 1.886704683303833,
+      "logps/chosen": -87.01000213623047,
+      "logps/rejected": -89.1278305053711,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.0030386822763830423,
+      "rewards/margins": 0.006321282591670752,
+      "rewards/rejected": -0.009359965100884438,
+      "step": 50
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 0.596449077129364,
+      "learning_rate": 4.775907352415367e-06,
+      "logits/chosen": 1.7842556238174438,
+      "logits/rejected": 1.7772290706634521,
+      "logps/chosen": -89.68411254882812,
+      "logps/rejected": -85.80751037597656,
+      "loss": 0.693,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.002062492538243532,
+      "rewards/margins": -0.0020373582374304533,
+      "rewards/rejected": -2.5133975213975646e-05,
+      "step": 60
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 0.605808436870575,
+      "learning_rate": 4.623538644118244e-06,
+      "logits/chosen": 1.7955410480499268,
+      "logits/rejected": 1.742892861366272,
+      "logps/chosen": -77.76892852783203,
+      "logps/rejected": -75.139892578125,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.005501260980963707,
+      "rewards/margins": 0.003699531313031912,
+      "rewards/rejected": -0.009200791828334332,
+      "step": 70
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 0.6306387782096863,
+      "learning_rate": 4.435725964760331e-06,
+      "logits/chosen": 1.7294387817382812,
+      "logits/rejected": 1.7057327032089233,
+      "logps/chosen": -86.89958190917969,
+      "logps/rejected": -75.46858215332031,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.00010954421304631978,
+      "rewards/margins": 0.00032598042162135243,
+      "rewards/rejected": -0.00021643625223077834,
+      "step": 80
+    },
+    {
+      "epoch": 3.302752293577982,
+      "grad_norm": 0.5730260014533997,
+      "learning_rate": 4.215604094671835e-06,
+      "logits/chosen": 1.879805326461792,
+      "logits/rejected": 1.9939963817596436,
+      "logps/chosen": -68.91841125488281,
+      "logps/rejected": -82.97428894042969,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": 0.0012840941781178117,
+      "rewards/margins": 0.004185027442872524,
+      "rewards/rejected": -0.0029009338468313217,
+      "step": 90
+    },
+    {
+      "epoch": 3.669724770642202,
+      "grad_norm": 0.903571605682373,
+      "learning_rate": 3.966847086696045e-06,
+      "logits/chosen": 1.7714732885360718,
+      "logits/rejected": 1.7483131885528564,
+      "logps/chosen": -88.14640808105469,
+      "logps/rejected": -79.63529968261719,
+      "loss": 0.6869,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 2.6259198421030305e-05,
+      "rewards/margins": 0.016201479360461235,
+      "rewards/rejected": -0.016175217926502228,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.411424963377234e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Power/dpo/checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+library_name: peft
+---
+
+# 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 0.12.0