Upload 14 files

README.md

@@ -1,202 +1,59 @@
 ---
+license: other
 library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
 base_model: huggyllama/llama-7b
+model-index:
+- name: custom1
+  results: []
 ---
 
-# Model Card for Model ID
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-<!-- Provide a quick summary of what the model is/does. -->
+# custom1
 
+This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the identity dataset.
 
+## Model description
 
-## Model Details
+More information needed
 
-### Model Description
+## Intended uses & limitations
 
-<!-- Provide a longer summary of what this model is. -->
+More information needed
 
+## Training and evaluation data
 
+More information needed
 
-- **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]
+## Training procedure
 
-### Model Sources [optional]
+### Training hyperparameters
 
-<!-- Provide the basic links for the model. -->
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Training results
 
-## 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 0.10.0
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96a881cc1162f43841907d1843d92771fa4ff2e7b2a60c91e0a18c95a6f4c5d
+oid sha256:d754527c09091f5c684d740413ac5fda645f387b868be523e3787f15e614ea73
 size 16794200

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.841918294849023,
+  "epoch": 2.9982238010657194,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1266,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1687,6 +1687,106 @@
       "learning_rate": 3.345485990286029e-07,
       "loss": 1.9999,
       "step": 1200
+    },
+    {
+      "epoch": 2.8537596210775606,
+      "grad_norm": 1.529491901397705,
+      "learning_rate": 2.8587263868213585e-07,
+      "loss": 2.1399,
+      "step": 1205
+    },
+    {
+      "epoch": 2.865600947306098,
+      "grad_norm": 1.5479165315628052,
+      "learning_rate": 2.410013050375859e-07,
+      "loss": 1.8664,
+      "step": 1210
+    },
+    {
+      "epoch": 2.877442273534636,
+      "grad_norm": 1.1747933626174927,
+      "learning_rate": 1.999415058312276e-07,
+      "loss": 1.9633,
+      "step": 1215
+    },
+    {
+      "epoch": 2.8892835997631736,
+      "grad_norm": 1.358820915222168,
+      "learning_rate": 1.6269956203107117e-07,
+      "loss": 2.0106,
+      "step": 1220
+    },
+    {
+      "epoch": 2.901124925991711,
+      "grad_norm": 1.554287314414978,
+      "learning_rate": 1.2928120686377388e-07,
+      "loss": 1.7896,
+      "step": 1225
+    },
+    {
+      "epoch": 2.9129662522202486,
+      "grad_norm": 1.5915781259536743,
+      "learning_rate": 9.969158493204067e-08,
+      "loss": 1.8759,
+      "step": 1230
+    },
+    {
+      "epoch": 2.924807578448786,
+      "grad_norm": 1.6586300134658813,
+      "learning_rate": 7.393525142262991e-08,
+      "loss": 1.9413,
+      "step": 1235
+    },
+    {
+      "epoch": 2.936648904677324,
+      "grad_norm": 1.416338562965393,
+      "learning_rate": 5.2016171405103174e-08,
+      "loss": 1.8404,
+      "step": 1240
+    },
+    {
+      "epoch": 2.9484902309058616,
+      "grad_norm": 1.3145766258239746,
+      "learning_rate": 3.393771922142741e-08,
+      "loss": 2.0654,
+      "step": 1245
+    },
+    {
+      "epoch": 2.960331557134399,
+      "grad_norm": 1.3440285921096802,
+      "learning_rate": 1.9702677966507154e-08,
+      "loss": 1.8111,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9721728833629366,
+      "grad_norm": 1.3247921466827393,
+      "learning_rate": 9.31323905974113e-09,
+      "loss": 1.8708,
+      "step": 1255
+    },
+    {
+      "epoch": 2.984014209591474,
+      "grad_norm": 1.7957427501678467,
+      "learning_rate": 2.771001907653226e-09,
+      "loss": 1.8842,
+      "step": 1260
+    },
+    {
+      "epoch": 2.995855535820012,
+      "grad_norm": 1.4069582223892212,
+      "learning_rate": 7.697365768943864e-11,
+      "loss": 1.9665,
+      "step": 1265
+    },
+    {
+      "epoch": 2.9982238010657194,
+      "step": 1266,
+      "total_flos": 6.019503790030848e+16,
+      "train_loss": 1.9697479162170988,
+      "train_runtime": 4932.4291,
+      "train_samples_per_second": 4.109,
+      "train_steps_per_second": 0.257
     }
   ],
   "logging_steps": 5,
@@ -1694,7 +1794,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.69903990243328e+16,
+  "total_flos": 6.019503790030848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null