Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: meta-llama/Meta-Llama-3-8B
+---
+
+# 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 0.10.1.dev0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "lm_head",
+    "o_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 sha256:9d6b4e7a461f1a72587d8e80d558748209b86e2878846f06aa2b4477bc8eba02
+size 2189529112

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9634e43737c9717979b1768b8b01a7e23975bf01fc3a47a39b2df757ab4d5f83
+size 44670300

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661f9b6ea8dff12eb0b2e02a5374ff35894222ea9230491780077b7939749a24
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c36f74f1d6d5e1a1e9e6fdb783d57687abed6999fd2e522fc67e0c7365ec199
+size 1064

trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 2.632924795150757,
+      "learning_rate": 2.3169601482854498e-05,
+      "loss": 0.8913,
+      "step": 400
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 2.3553333282470703,
+      "learning_rate": 2.1316033364226137e-05,
+      "loss": 0.7055,
+      "step": 800
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.3810371160507202,
+      "learning_rate": 1.946246524559778e-05,
+      "loss": 0.6621,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 2.1988062858581543,
+      "learning_rate": 1.7608897126969417e-05,
+      "loss": 0.6527,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 2.7631494998931885,
+      "learning_rate": 1.5755329008341056e-05,
+      "loss": 0.6426,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.627460479736328,
+      "learning_rate": 1.3901760889712698e-05,
+      "loss": 0.6242,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6276328563690186,
+      "eval_runtime": 438.1461,
+      "eval_samples_per_second": 1.369,
+      "eval_steps_per_second": 0.087,
+      "step": 2700
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 2.762786865234375,
+      "learning_rate": 1.2048192771084338e-05,
+      "loss": 0.6002,
+      "step": 2800
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 3.1197636127471924,
+      "learning_rate": 1.0194624652455977e-05,
+      "loss": 0.5341,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 3.382873058319092,
+      "learning_rate": 8.341056533827618e-06,
+      "loss": 0.5167,
+      "step": 3600
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 4.067070007324219,
+      "learning_rate": 6.487488415199258e-06,
+      "loss": 0.5067,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 6.997328281402588,
+      "learning_rate": 4.633920296570899e-06,
+      "loss": 0.5007,
+      "step": 4400
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 4.422049522399902,
+      "learning_rate": 2.7803521779425395e-06,
+      "loss": 0.4968,
+      "step": 4800
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 3.440484046936035,
+      "learning_rate": 9.267840593141798e-07,
+      "loss": 0.4926,
+      "step": 5200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5777664184570312,
+      "eval_runtime": 422.1796,
+      "eval_samples_per_second": 1.421,
+      "eval_steps_per_second": 0.09,
+      "step": 5400
+    }
+  ],
+  "logging_steps": 400,
+  "max_steps": 5400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.9993910803390464e+17,
+  "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 sha256:4253efe8a1458de04e43199ac737eee87b8bc34d6a22c3b37698b2aa3c709284
+size 5112