Upload 11 files

README-2.md

@@ -0,0 +1,202 @@
+---
+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 0.13.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_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 sha256:02976fdb9ae3241b57bf2020677ec7259cb1e162a9c4bbc92cf4a0c238f4121e
+size 67143296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2040a0390bec6b56a77c30b7dac3dd79b753c61ab4b3d96b4b44283ae1c1ce2b
+size 134433530

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463193011a5ace0c4289a8ccccb11858d0c6f6324926a9a3f329be1e718f984a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5403fe4afb7dc460666d4766bffbc976e28ad81c2134b0a93012b2970d7fa64
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "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": true,
+  "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,
+  "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
+}

trainer_state.json

@@ -0,0 +1,285 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.35,
+  "eval_steps": 100,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0125,
+      "grad_norm": 12.285691261291504,
+      "learning_rate": 2.5555555555555554e-05,
+      "loss": 19.1959,
+      "step": 25
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 1.0500800609588623,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 7.7392,
+      "step": 50
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 0.8419748544692993,
+      "learning_rate": 8.111111111111112e-05,
+      "loss": 1.2479,
+      "step": 75
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.2464624643325806,
+      "learning_rate": 0.00010888888888888889,
+      "loss": 0.7071,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.5045744180679321,
+      "eval_runtime": 690.6274,
+      "eval_samples_per_second": 1.448,
+      "eval_steps_per_second": 1.448,
+      "step": 100
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 0.8873828053474426,
+      "learning_rate": 0.00013666666666666666,
+      "loss": 0.4035,
+      "step": 125
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.9160810708999634,
+      "learning_rate": 0.00016444444444444444,
+      "loss": 0.2371,
+      "step": 150
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 0.7777899503707886,
+      "learning_rate": 0.00019222222222222224,
+      "loss": 0.1825,
+      "step": 175
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9546622037887573,
+      "learning_rate": 0.0001999952797459453,
+      "loss": 0.1328,
+      "step": 200
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.12972435355186462,
+      "eval_runtime": 689.9886,
+      "eval_samples_per_second": 1.449,
+      "eval_steps_per_second": 1.449,
+      "step": 200
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 0.6794782876968384,
+      "learning_rate": 0.00019997306349823693,
+      "loss": 0.1162,
+      "step": 225
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.8062716126441956,
+      "learning_rate": 0.00019993264143226513,
+      "loss": 0.1048,
+      "step": 250
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 0.8031811118125916,
+      "learning_rate": 0.00019987402090918067,
+      "loss": 0.0988,
+      "step": 275
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.37140652537345886,
+      "learning_rate": 0.000199797212604205,
+      "loss": 0.0885,
+      "step": 300
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.09123973548412323,
+      "eval_runtime": 689.6116,
+      "eval_samples_per_second": 1.45,
+      "eval_steps_per_second": 1.45,
+      "step": 300
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 0.3891146779060364,
+      "learning_rate": 0.0001997022305046862,
+      "loss": 0.0797,
+      "step": 325
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.2549072504043579,
+      "learning_rate": 0.00019958909190755187,
+      "loss": 0.0795,
+      "step": 350
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.16435463726520538,
+      "learning_rate": 0.0001994578174161592,
+      "loss": 0.0774,
+      "step": 375
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9256812930107117,
+      "learning_rate": 0.00019930843093654305,
+      "loss": 0.0737,
+      "step": 400
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.0729941874742508,
+      "eval_runtime": 690.0692,
+      "eval_samples_per_second": 1.449,
+      "eval_steps_per_second": 1.449,
+      "step": 400
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 0.2688423693180084,
+      "learning_rate": 0.00019914095967306223,
+      "loss": 0.0703,
+      "step": 425
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.24806413054466248,
+      "learning_rate": 0.0001989554341234457,
+      "loss": 0.0661,
+      "step": 450
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 0.2767386734485626,
+      "learning_rate": 0.00019875188807323842,
+      "loss": 0.0675,
+      "step": 475
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.120990090072155,
+      "learning_rate": 0.00019853035858964906,
+      "loss": 0.0666,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.06402209401130676,
+      "eval_runtime": 690.2132,
+      "eval_samples_per_second": 1.449,
+      "eval_steps_per_second": 1.449,
+      "step": 500
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 0.17512480914592743,
+      "learning_rate": 0.0001982908860147995,
+      "loss": 0.0634,
+      "step": 525
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.21513459086418152,
+      "learning_rate": 0.00019803351395837848,
+      "loss": 0.0667,
+      "step": 550
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 0.18517647683620453,
+      "learning_rate": 0.00019775828928969975,
+      "loss": 0.0626,
+      "step": 575
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.15308107435703278,
+      "learning_rate": 0.00019746526212916705,
+      "loss": 0.0603,
+      "step": 600
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.06020086258649826,
+      "eval_runtime": 690.5491,
+      "eval_samples_per_second": 1.448,
+      "eval_steps_per_second": 1.448,
+      "step": 600
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.1161598339676857,
+      "learning_rate": 0.00019715448583914659,
+      "loss": 0.06,
+      "step": 625
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.13704052567481995,
+      "learning_rate": 0.0001968260170142496,
+      "loss": 0.0611,
+      "step": 650
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 0.1627456545829773,
+      "learning_rate": 0.0001964799154710258,
+      "loss": 0.0595,
+      "step": 675
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.14293187856674194,
+      "learning_rate": 0.0001961162442370707,
+      "loss": 0.0606,
+      "step": 700
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.05934726819396019,
+      "eval_runtime": 690.4657,
+      "eval_samples_per_second": 1.448,
+      "eval_steps_per_second": 1.448,
+      "step": 700
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 6000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.42445094371328e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2540a924ca350288b90e35f846c0061763a5f211dac94b31f1dd6f6d61d0e24
+size 5240