Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: models/tofu_ft_llama2-7b
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+    "alpha_pattern": {},
+    "auto_mapping": null,
+    "base_model_name_or_path": "locuslab/tofu_ft_llama2-7b",
+    "bias": "none",
+    "eva_config": null,
+    "exclude_modules": null,
+    "fan_in_fan_out": false,
+    "inference_mode": true,
+    "init_lora_weights": true,
+    "layer_replication": null,
+    "layers_pattern": null,
+    "layers_to_transform": null,
+    "loftq_config": {},
+    "lora_alpha": 32,
+    "lora_bias": false,
+    "lora_dropout": 0.05,
+    "megatron_config": null,
+    "megatron_core": "megatron.core",
+    "modules_to_save": null,
+    "peft_type": "LORA",
+    "r": 8,
+    "rank_pattern": {},
+    "revision": null,
+    "target_modules": [
+        "k_proj",
+        "gate_proj",
+        "o_proj",
+        "v_proj",
+        "q_proj",
+        "up_proj",
+        "down_proj"
+    ],
+    "task_type": "CAUSAL_LM",
+    "use_dora": false,
+    "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0560a70098244d508dba895e0e9a143751d05c5fef07b913a2dcfd543e4985eb
+size 40036488

added_tokens.json

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

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "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 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 37.0,
+  "eval_steps": 0,
+  "global_step": 37,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.002,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5070388375349495,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.0119,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5070388375349495,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.0032,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.31938507733027843,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": -0.0015,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.31938507733027843,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0073,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.43541534478865934,
+      "learning_rate": 8.611111111111112e-06,
+      "loss": -0.0001,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.43541534478865934,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0014,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5428982959575133,
+      "learning_rate": 8.055555555555557e-06,
+      "loss": -0.0026,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5428982959575133,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.0012,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.9728643220805211,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0027,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.9728643220805211,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": -0.0017,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.8713152262560704,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": -0.0037,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.8713152262560704,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": -0.0057,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.2483582246181377,
+      "learning_rate": 6.3888888888888885e-06,
+      "loss": -0.0042,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.2483582246181377,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": -0.0059,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.338516376367072,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": -0.0054,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.338516376367072,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": -0.0068,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.8582031188698118,
+      "learning_rate": 5.2777777777777785e-06,
+      "loss": -0.0046,
+      "step": 18
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 1.8582031188698118,
+      "learning_rate": 5e-06,
+      "loss": -0.0113,
+      "step": 19
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.091199450117605,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": -0.0107,
+      "step": 20
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 2.091199450117605,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": -0.0096,
+      "step": 21
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 2.314746448196812,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": -0.012,
+      "step": 22
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 2.314746448196812,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": -0.0153,
+      "step": 23
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 2.2454811354700968,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": -0.0111,
+      "step": 24
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 2.2454811354700968,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": -0.0088,
+      "step": 25
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 2.811270150717608,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": -0.0149,
+      "step": 26
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 2.811270150717608,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": -0.019,
+      "step": 27
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 2.678124329751125,
+      "learning_rate": 2.5e-06,
+      "loss": -0.0171,
+      "step": 28
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 2.678124329751125,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": -0.0129,
+      "step": 29
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.596705407383602,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": -0.0182,
+      "step": 30
+    },
+    {
+      "epoch": 31.0,
+      "grad_norm": 2.596705407383602,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": -0.0202,
+      "step": 31
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 3.201965282085345,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": -0.023,
+      "step": 32
+    },
+    {
+      "epoch": 33.0,
+      "grad_norm": 3.201965282085345,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": -0.0188,
+      "step": 33
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 2.7138214701675016,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": -0.0216,
+      "step": 34
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 2.7138214701675016,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": -0.025,
+      "step": 35
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 3.3327313390783866,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": -0.0233,
+      "step": 36
+    },
+    {
+      "epoch": 37.0,
+      "grad_norm": 3.3327313390783866,
+      "learning_rate": 0.0,
+      "loss": -0.0247,
+      "step": 37
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 37,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 37,
+  "save_steps": 3,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4006b154120bd245232df602133888bbc044f335b053d300afa0fe124f3e69d
+size 6968