Upload folder using huggingface_hub

README.md

@@ -1,3 +1,208 @@
 ---
-license: cc-by-nc-4.0
+library_name: peft
+base_model: allenai/tulu-2-dpo-70b
 ---
+
+# 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]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/tulu-2-dpo-70b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "lm_head",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "embed_tokens",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589036b50dc5de2de2cbcb49718727624a91ef2c5358785a3dc1f649685b9bdd
+size 416913160

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<PAD>": 32000
+}

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,390 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 0.9219,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001292029674220179,
+      "loss": 0.8431,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00020478185834579558,
+      "loss": 0.8259,
+      "step": 3
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002584059348440358,
+      "loss": 0.8513,
+      "step": 4
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8788,
+      "step": 5
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8157,
+      "step": 6
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8119,
+      "step": 7
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8002,
+      "step": 8
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.743,
+      "step": 9
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.793,
+      "step": 10
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.22686079972512133,
+      "eval_loss": 0.7526410222053528,
+      "eval_runtime": 229.5348,
+      "eval_samples_per_second": 0.157,
+      "eval_steps_per_second": 0.009,
+      "step": 10
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.7927,
+      "step": 11
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.7881,
+      "step": 12
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.7832,
+      "step": 13
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.7478,
+      "step": 14
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.7615,
+      "step": 15
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.741,
+      "step": 16
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.7564,
+      "step": 17
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7315,
+      "step": 18
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.7531,
+      "step": 19
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.7549,
+      "step": 20
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.22750504660052398,
+      "eval_loss": 0.7324042320251465,
+      "eval_runtime": 224.0786,
+      "eval_samples_per_second": 0.161,
+      "eval_steps_per_second": 0.009,
+      "step": 20
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.7742,
+      "step": 21
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7763,
+      "step": 22
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.6916,
+      "step": 23
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.6979,
+      "step": 24
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7256,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7626,
+      "step": 26
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.7329,
+      "step": 27
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003,
+      "loss": 0.6927,
+      "step": 28
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003,
+      "loss": 0.6781,
+      "step": 29
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003,
+      "loss": 0.672,
+      "step": 30
+    },
+    {
+      "epoch": 1.11,
+      "eval_accuracy": 0.2278271700382253,
+      "eval_loss": 0.7340984344482422,
+      "eval_runtime": 224.2193,
+      "eval_samples_per_second": 0.161,
+      "eval_steps_per_second": 0.009,
+      "step": 30
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003,
+      "loss": 0.6875,
+      "step": 31
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003,
+      "loss": 0.7242,
+      "step": 32
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0003,
+      "loss": 0.7121,
+      "step": 33
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0003,
+      "loss": 0.6614,
+      "step": 34
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003,
+      "loss": 0.6649,
+      "step": 35
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003,
+      "loss": 0.6056,
+      "step": 36
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0003,
+      "loss": 0.656,
+      "step": 37
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0003,
+      "loss": 0.6624,
+      "step": 38
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0003,
+      "loss": 0.6428,
+      "step": 39
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0003,
+      "loss": 0.6425,
+      "step": 40
+    },
+    {
+      "epoch": 1.48,
+      "eval_accuracy": 0.22737619722544344,
+      "eval_loss": 0.7448343634605408,
+      "eval_runtime": 223.9913,
+      "eval_samples_per_second": 0.161,
+      "eval_steps_per_second": 0.009,
+      "step": 40
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0003,
+      "loss": 0.6096,
+      "step": 41
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003,
+      "loss": 0.6172,
+      "step": 42
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0003,
+      "loss": 0.5967,
+      "step": 43
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0003,
+      "loss": 0.5958,
+      "step": 44
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0003,
+      "loss": 0.5921,
+      "step": 45
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0003,
+      "loss": 0.6026,
+      "step": 46
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0003,
+      "loss": 0.5941,
+      "step": 47
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0003,
+      "loss": 0.612,
+      "step": 48
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0003,
+      "loss": 0.6084,
+      "step": 49
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0003,
+      "loss": 0.5446,
+      "step": 50
+    },
+    {
+      "epoch": 1.85,
+      "eval_accuracy": 0.22646351415195637,
+      "eval_loss": 0.7739428281784058,
+      "eval_runtime": 223.8688,
+      "eval_samples_per_second": 0.161,
+      "eval_steps_per_second": 0.009,
+      "step": 50
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0003,
+      "loss": 0.5375,
+      "step": 51
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0003,
+      "loss": 0.5548,
+      "step": 52
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0003,
+      "loss": 0.6092,
+      "step": 53
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0003,
+      "loss": 0.4286,
+      "step": 54
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 68912311697408.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10e2406c45753a1eb70d61a651d9a39c3e4b3972c1b87a803b1b0296b9d2f51
+size 6904