Upload folder using huggingface_hub

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: tokyotech-llm/Swallow-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": "tokyotech-llm/Swallow-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",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_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:bd4cde981b7617e9be0e29523a1d8d548aecddfe263b67b034d43fb0dc720633
+size 80011328

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.017292660994673862,
+    "eval_accuracy": 0.7482334712737478,
+    "eval_loss": 1.1277046203613281,
+    "eval_runtime": 159.2816,
+    "eval_samples": 3547,
+    "eval_samples_per_second": 22.269,
+    "eval_steps_per_second": 0.088,
+    "perplexity": 3.088558942137329,
+    "total_flos": 1.3159164755627213e+18,
+    "train_loss": 1.6568055419921874,
+    "train_runtime": 12202.9628,
+    "train_samples": 3700988,
+    "train_samples_per_second": 909.858,
+    "train_steps_per_second": 14.217
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.017292660994673862,
+    "eval_accuracy": 0.7482334712737478,
+    "eval_loss": 1.1277046203613281,
+    "eval_runtime": 159.2816,
+    "eval_samples": 3547,
+    "eval_samples_per_second": 22.269,
+    "eval_steps_per_second": 0.088,
+    "perplexity": 3.088558942137329
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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
+  },
+  "mask_token": "_",
+  "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:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
+size 914000

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.017292660994673862,
+    "total_flos": 1.3159164755627213e+18,
+    "train_loss": 1.6568055419921874,
+    "train_runtime": 12202.9628,
+    "train_samples": 3700988,
+    "train_samples_per_second": 909.858,
+    "train_steps_per_second": 14.217
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.017292660994673862,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001729266099467386,
+      "eval_accuracy": 0.5147599845329504,
+      "eval_loss": 2.3851237297058105,
+      "eval_runtime": 162.2957,
+      "eval_samples_per_second": 21.855,
+      "eval_steps_per_second": 0.086,
+      "step": 100
+    },
+    {
+      "epoch": 0.003458532198934772,
+      "eval_accuracy": 0.664822956946066,
+      "eval_loss": 1.5685330629348755,
+      "eval_runtime": 160.1519,
+      "eval_samples_per_second": 22.148,
+      "eval_steps_per_second": 0.087,
+      "step": 200
+    },
+    {
+      "epoch": 0.005187798298402158,
+      "eval_accuracy": 0.6968067616966134,
+      "eval_loss": 1.3908480405807495,
+      "eval_runtime": 160.2009,
+      "eval_samples_per_second": 22.141,
+      "eval_steps_per_second": 0.087,
+      "step": 300
+    },
+    {
+      "epoch": 0.006917064397869544,
+      "eval_accuracy": 0.712278134986332,
+      "eval_loss": 1.3142558336257935,
+      "eval_runtime": 161.1937,
+      "eval_samples_per_second": 22.005,
+      "eval_steps_per_second": 0.087,
+      "step": 400
+    },
+    {
+      "epoch": 0.008646330497336931,
+      "grad_norm": 1.4352248907089233,
+      "learning_rate": 4.985589449171105e-05,
+      "loss": 2.1403,
+      "step": 500
+    },
+    {
+      "epoch": 0.008646330497336931,
+      "eval_accuracy": 0.7214570506536847,
+      "eval_loss": 1.2621606588363647,
+      "eval_runtime": 160.0804,
+      "eval_samples_per_second": 22.158,
+      "eval_steps_per_second": 0.087,
+      "step": 500
+    },
+    {
+      "epoch": 0.010375596596804317,
+      "eval_accuracy": 0.7294319423505166,
+      "eval_loss": 1.2215678691864014,
+      "eval_runtime": 161.111,
+      "eval_samples_per_second": 22.016,
+      "eval_steps_per_second": 0.087,
+      "step": 600
+    },
+    {
+      "epoch": 0.012104862696271703,
+      "eval_accuracy": 0.734985971027901,
+      "eval_loss": 1.1908366680145264,
+      "eval_runtime": 160.2095,
+      "eval_samples_per_second": 22.14,
+      "eval_steps_per_second": 0.087,
+      "step": 700
+    },
+    {
+      "epoch": 0.013834128795739089,
+      "eval_accuracy": 0.7399843258033025,
+      "eval_loss": 1.1652381420135498,
+      "eval_runtime": 161.2145,
+      "eval_samples_per_second": 22.002,
+      "eval_steps_per_second": 0.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.015563394895206474,
+      "eval_accuracy": 0.7441422484377028,
+      "eval_loss": 1.1482852697372437,
+      "eval_runtime": 160.0254,
+      "eval_samples_per_second": 22.165,
+      "eval_steps_per_second": 0.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.017292660994673862,
+      "grad_norm": 1.6683523654937744,
+      "learning_rate": 4.9711788983422105e-05,
+      "loss": 1.1733,
+      "step": 1000
+    },
+    {
+      "epoch": 0.017292660994673862,
+      "eval_accuracy": 0.7479334730370067,
+      "eval_loss": 1.1267001628875732,
+      "eval_runtime": 160.2361,
+      "eval_samples_per_second": 22.136,
+      "eval_steps_per_second": 0.087,
+      "step": 1000
+    },
+    {
+      "epoch": 0.017292660994673862,
+      "step": 1000,
+      "total_flos": 1.3159164755627213e+18,
+      "train_loss": 1.6568055419921874,
+      "train_runtime": 12202.9628,
+      "train_samples_per_second": 909.858,
+      "train_steps_per_second": 14.217
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 173484,
+  "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": 1.3159164755627213e+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 sha256:106824cce2695add5f79c40a79f8e37eff5a43b6990b80f0455326acb146d8f6
+size 6072