Upload folder using huggingface_hub

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: meta-llama/Llama-2-7b-hf
+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 0.11.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlamaBiModel",
+    "parent_library": "llm2vec.models.bidirectional_llama"
+  },
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afebb2ec548a49e0794b97082adec44b90e86b0aeed2708a4d1f968bb2b52e48
+size 80011328

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.010905601116733554,
+    "eval_accuracy": 0.7869404549281535,
+    "eval_loss": 0.8759388327598572,
+    "eval_runtime": 249.4157,
+    "eval_samples": 5564,
+    "eval_samples_per_second": 22.308,
+    "eval_steps_per_second": 0.088,
+    "perplexity": 2.4011284942034856,
+    "total_flos": 1.3069163715939533e+18,
+    "train_loss": 1.3858390502929687,
+    "train_runtime": 13072.5982,
+    "train_samples": 5868487,
+    "train_samples_per_second": 1346.745,
+    "train_steps_per_second": 21.043
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.010905601116733554,
+    "eval_accuracy": 0.7869404549281535,
+    "eval_loss": 0.8759388327598572,
+    "eval_runtime": 249.4157,
+    "eval_samples": 5564,
+    "eval_samples_per_second": 22.308,
+    "eval_steps_per_second": 0.088,
+    "perplexity": 2.4011284942034856
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "_",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.010905601116733554,
+    "total_flos": 1.3069163715939533e+18,
+    "train_loss": 1.3858390502929687,
+    "train_runtime": 13072.5982,
+    "train_samples": 5868487,
+    "train_samples_per_second": 1346.745,
+    "train_steps_per_second": 21.043
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.010905601116733554,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010905601116733554,
+      "eval_accuracy": 0.5034676821874995,
+      "eval_loss": 2.249495029449463,
+      "eval_runtime": 250.8322,
+      "eval_samples_per_second": 22.182,
+      "eval_steps_per_second": 0.088,
+      "step": 100
+    },
+    {
+      "epoch": 0.002181120223346711,
+      "eval_accuracy": 0.6792460132466641,
+      "eval_loss": 1.3580471277236938,
+      "eval_runtime": 250.935,
+      "eval_samples_per_second": 22.173,
+      "eval_steps_per_second": 0.088,
+      "step": 200
+    },
+    {
+      "epoch": 0.0032716803350200663,
+      "eval_accuracy": 0.7194358306786471,
+      "eval_loss": 1.1734950542449951,
+      "eval_runtime": 249.8616,
+      "eval_samples_per_second": 22.268,
+      "eval_steps_per_second": 0.088,
+      "step": 300
+    },
+    {
+      "epoch": 0.004362240446693422,
+      "eval_accuracy": 0.7406081066868597,
+      "eval_loss": 1.0811182260513306,
+      "eval_runtime": 250.2334,
+      "eval_samples_per_second": 22.235,
+      "eval_steps_per_second": 0.088,
+      "step": 400
+    },
+    {
+      "epoch": 0.005452800558366777,
+      "grad_norm": 1.5124988555908203,
+      "learning_rate": 4.990911999069389e-05,
+      "loss": 1.8503,
+      "step": 500
+    },
+    {
+      "epoch": 0.005452800558366777,
+      "eval_accuracy": 0.7539559460484646,
+      "eval_loss": 1.0170289278030396,
+      "eval_runtime": 250.2283,
+      "eval_samples_per_second": 22.236,
+      "eval_steps_per_second": 0.088,
+      "step": 500
+    },
+    {
+      "epoch": 0.0065433606700401326,
+      "eval_accuracy": 0.7639956787495118,
+      "eval_loss": 0.9728907346725464,
+      "eval_runtime": 250.2409,
+      "eval_samples_per_second": 22.235,
+      "eval_steps_per_second": 0.088,
+      "step": 600
+    },
+    {
+      "epoch": 0.007633920781713488,
+      "eval_accuracy": 0.7704801005740811,
+      "eval_loss": 0.9435333013534546,
+      "eval_runtime": 250.3167,
+      "eval_samples_per_second": 22.228,
+      "eval_steps_per_second": 0.088,
+      "step": 700
+    },
+    {
+      "epoch": 0.008724480893386843,
+      "eval_accuracy": 0.7747122964825798,
+      "eval_loss": 0.924051821231842,
+      "eval_runtime": 250.2963,
+      "eval_samples_per_second": 22.23,
+      "eval_steps_per_second": 0.088,
+      "step": 800
+    },
+    {
+      "epoch": 0.009815041005060199,
+      "eval_accuracy": 0.7814711185942613,
+      "eval_loss": 0.8970186114311218,
+      "eval_runtime": 250.1321,
+      "eval_samples_per_second": 22.244,
+      "eval_steps_per_second": 0.088,
+      "step": 900
+    },
+    {
+      "epoch": 0.010905601116733554,
+      "grad_norm": 1.2721333503723145,
+      "learning_rate": 4.981823998138778e-05,
+      "loss": 0.9214,
+      "step": 1000
+    },
+    {
+      "epoch": 0.010905601116733554,
+      "eval_accuracy": 0.7872277846758073,
+      "eval_loss": 0.8725214004516602,
+      "eval_runtime": 249.8439,
+      "eval_samples_per_second": 22.27,
+      "eval_steps_per_second": 0.088,
+      "step": 1000
+    },
+    {
+      "epoch": 0.010905601116733554,
+      "step": 1000,
+      "total_flos": 1.3069163715939533e+18,
+      "train_loss": 1.3858390502929687,
+      "train_runtime": 13072.5982,
+      "train_samples_per_second": 1346.745,
+      "train_steps_per_second": 21.043
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275088,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3069163715939533e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217014ea113307106ec5681b048e9d06253d54a3b152f5e1deb254e73d0562cf
+size 6072