Upload folder using huggingface_hub

.gitattributes

@@ -1,2 +1,3 @@
 adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
 last-checkpoint/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/optimizer.pt filter=lfs diff=lfs merge=lfs -text

checkpoint-400/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b-instruct
+---
+
+# 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 0.10.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "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": [
+    "lm_head",
+    "dense_h_to_4h",
+    "dense",
+    "query_key_value",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ed79b11216a51a61c91ceb6718a283c1617543152b0ba5f4b575170cbc1765
+size 1316913776

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e122fe10c25f35bb9aa91f429c7959bcc622d43d2158400d186b24f4a4c6df
+size 8908124

checkpoint-400/trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08587376556462001,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0021468441391155,
+      "grad_norm": 1.7282733917236328,
+      "learning_rate": 0.0004989265779304422,
+      "loss": 1.4129,
+      "step": 10
+    },
+    {
+      "epoch": 0.004293688278231,
+      "grad_norm": 2.1508498191833496,
+      "learning_rate": 0.0004978531558608846,
+      "loss": 1.2225,
+      "step": 20
+    },
+    {
+      "epoch": 0.006440532417346501,
+      "grad_norm": 1.6386512517929077,
+      "learning_rate": 0.0004967797337913268,
+      "loss": 1.1663,
+      "step": 30
+    },
+    {
+      "epoch": 0.008587376556462,
+      "grad_norm": 1.2367421388626099,
+      "learning_rate": 0.000495706311721769,
+      "loss": 1.1373,
+      "step": 40
+    },
+    {
+      "epoch": 0.010734220695577501,
+      "grad_norm": 1.2300989627838135,
+      "learning_rate": 0.0004946328896522112,
+      "loss": 1.1143,
+      "step": 50
+    },
+    {
+      "epoch": 0.012881064834693002,
+      "grad_norm": 1.1807990074157715,
+      "learning_rate": 0.0004935594675826536,
+      "loss": 1.0937,
+      "step": 60
+    },
+    {
+      "epoch": 0.015027908973808502,
+      "grad_norm": 0.9375188946723938,
+      "learning_rate": 0.0004924860455130958,
+      "loss": 1.0732,
+      "step": 70
+    },
+    {
+      "epoch": 0.017174753112924,
+      "grad_norm": 0.9801538586616516,
+      "learning_rate": 0.000491412623443538,
+      "loss": 1.0369,
+      "step": 80
+    },
+    {
+      "epoch": 0.019321597252039503,
+      "grad_norm": 0.9229792356491089,
+      "learning_rate": 0.0004903392013739802,
+      "loss": 1.0093,
+      "step": 90
+    },
+    {
+      "epoch": 0.021468441391155002,
+      "grad_norm": 1.011305570602417,
+      "learning_rate": 0.0004892657793044225,
+      "loss": 1.0161,
+      "step": 100
+    },
+    {
+      "epoch": 0.0236152855302705,
+      "grad_norm": 0.9356452822685242,
+      "learning_rate": 0.00048819235723486477,
+      "loss": 0.9939,
+      "step": 110
+    },
+    {
+      "epoch": 0.025762129669386003,
+      "grad_norm": 1.0092449188232422,
+      "learning_rate": 0.00048711893516530704,
+      "loss": 0.9647,
+      "step": 120
+    },
+    {
+      "epoch": 0.027908973808501502,
+      "grad_norm": 0.9663442373275757,
+      "learning_rate": 0.0004860455130957492,
+      "loss": 0.9595,
+      "step": 130
+    },
+    {
+      "epoch": 0.030055817947617004,
+      "grad_norm": 1.1502243280410767,
+      "learning_rate": 0.0004849720910261915,
+      "loss": 0.9422,
+      "step": 140
+    },
+    {
+      "epoch": 0.0322026620867325,
+      "grad_norm": 0.970102846622467,
+      "learning_rate": 0.00048389866895663376,
+      "loss": 0.945,
+      "step": 150
+    },
+    {
+      "epoch": 0.034349506225848,
+      "grad_norm": 1.2466392517089844,
+      "learning_rate": 0.00048282524688707604,
+      "loss": 0.9385,
+      "step": 160
+    },
+    {
+      "epoch": 0.0364963503649635,
+      "grad_norm": 1.0010186433792114,
+      "learning_rate": 0.00048175182481751826,
+      "loss": 0.9301,
+      "step": 170
+    },
+    {
+      "epoch": 0.038643194504079006,
+      "grad_norm": 1.2516905069351196,
+      "learning_rate": 0.0004806784027479605,
+      "loss": 0.919,
+      "step": 180
+    },
+    {
+      "epoch": 0.040790038643194505,
+      "grad_norm": 0.8497525453567505,
+      "learning_rate": 0.00047960498067840275,
+      "loss": 0.9054,
+      "step": 190
+    },
+    {
+      "epoch": 0.042936882782310004,
+      "grad_norm": 1.0371205806732178,
+      "learning_rate": 0.00047853155860884503,
+      "loss": 0.9109,
+      "step": 200
+    },
+    {
+      "epoch": 0.0450837269214255,
+      "grad_norm": 1.3313541412353516,
+      "learning_rate": 0.00047745813653928725,
+      "loss": 0.9131,
+      "step": 210
+    },
+    {
+      "epoch": 0.047230571060541,
+      "grad_norm": 0.9448315501213074,
+      "learning_rate": 0.0004763847144697295,
+      "loss": 0.9014,
+      "step": 220
+    },
+    {
+      "epoch": 0.04937741519965651,
+      "grad_norm": 1.274882435798645,
+      "learning_rate": 0.00047531129240017175,
+      "loss": 0.8786,
+      "step": 230
+    },
+    {
+      "epoch": 0.051524259338772006,
+      "grad_norm": 1.3116368055343628,
+      "learning_rate": 0.000474237870330614,
+      "loss": 0.9075,
+      "step": 240
+    },
+    {
+      "epoch": 0.053671103477887505,
+      "grad_norm": 0.9970440864562988,
+      "learning_rate": 0.00047316444826105624,
+      "loss": 0.8932,
+      "step": 250
+    },
+    {
+      "epoch": 0.055817947617003004,
+      "grad_norm": 1.698472499847412,
+      "learning_rate": 0.0004720910261914985,
+      "loss": 0.8838,
+      "step": 260
+    },
+    {
+      "epoch": 0.0579647917561185,
+      "grad_norm": 1.0129982233047485,
+      "learning_rate": 0.0004710176041219408,
+      "loss": 0.8779,
+      "step": 270
+    },
+    {
+      "epoch": 0.06011163589523401,
+      "grad_norm": 1.0594947338104248,
+      "learning_rate": 0.00046994418205238296,
+      "loss": 0.8631,
+      "step": 280
+    },
+    {
+      "epoch": 0.06225848003434951,
+      "grad_norm": 0.7768178582191467,
+      "learning_rate": 0.00046887075998282524,
+      "loss": 0.8666,
+      "step": 290
+    },
+    {
+      "epoch": 0.064405324173465,
+      "grad_norm": 0.9108049869537354,
+      "learning_rate": 0.0004677973379132675,
+      "loss": 0.8676,
+      "step": 300
+    },
+    {
+      "epoch": 0.06655216831258051,
+      "grad_norm": 1.4127992391586304,
+      "learning_rate": 0.0004667239158437098,
+      "loss": 0.8951,
+      "step": 310
+    },
+    {
+      "epoch": 0.068699012451696,
+      "grad_norm": 1.1507939100265503,
+      "learning_rate": 0.000465650493774152,
+      "loss": 0.863,
+      "step": 320
+    },
+    {
+      "epoch": 0.07084585659081151,
+      "grad_norm": 1.1579265594482422,
+      "learning_rate": 0.00046457707170459423,
+      "loss": 0.8716,
+      "step": 330
+    },
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 0.9873006343841553,
+      "learning_rate": 0.0004635036496350365,
+      "loss": 0.8569,
+      "step": 340
+    },
+    {
+      "epoch": 0.07513954486904251,
+      "grad_norm": 1.1990203857421875,
+      "learning_rate": 0.0004624302275654788,
+      "loss": 0.8776,
+      "step": 350
+    },
+    {
+      "epoch": 0.07728638900815801,
+      "grad_norm": 1.1173065900802612,
+      "learning_rate": 0.000461356805495921,
+      "loss": 0.865,
+      "step": 360
+    },
+    {
+      "epoch": 0.0794332331472735,
+      "grad_norm": 1.2493510246276855,
+      "learning_rate": 0.0004602833834263633,
+      "loss": 0.8609,
+      "step": 370
+    },
+    {
+      "epoch": 0.08158007728638901,
+      "grad_norm": 1.1254737377166748,
+      "learning_rate": 0.0004592099613568055,
+      "loss": 0.8697,
+      "step": 380
+    },
+    {
+      "epoch": 0.0837269214255045,
+      "grad_norm": 1.1009331941604614,
+      "learning_rate": 0.0004581365392872477,
+      "loss": 0.8653,
+      "step": 390
+    },
+    {
+      "epoch": 0.08587376556462001,
+      "grad_norm": 1.3970990180969238,
+      "learning_rate": 0.00045706311721769,
+      "loss": 0.8542,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4658,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 2.976872891771059e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}