Initial commit

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-chat-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 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "lm_head",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_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 sha256:5a02d21b4b042969048c8340d7a2b367d9f3e0c454660d987b88c9ed17652261
+size 848784976

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c95d437f2424e40e85cda0b7eb4d736ffb25e2935cdc62b88ddc5d885420c0a
+size 164224478

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afbb2b111466e487b23df10230c683ff1e502cf1c777fa7156870bcb61407a4
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2106c385366372d71c48ec368f27d1580055c20df9ca7a3a209cc7d61c928a41
+size 1064

trainer_state.json

@@ -0,0 +1,508 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 5,
+  "global_step": 30936,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0969743987587277,
+      "grad_norm": 5.50258207321167,
+      "learning_rate": 2.451704876061911e-05,
+      "loss": 0.7801,
+      "step": 500
+    },
+    {
+      "epoch": 0.1939487975174554,
+      "grad_norm": 2.8141658306121826,
+      "learning_rate": 2.4032157958027852e-05,
+      "loss": 0.4736,
+      "step": 1000
+    },
+    {
+      "epoch": 0.29092319627618307,
+      "grad_norm": 1.9647445678710938,
+      "learning_rate": 2.3547267155436597e-05,
+      "loss": 0.3846,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3878975950349108,
+      "grad_norm": 0.9280088543891907,
+      "learning_rate": 2.306334613445052e-05,
+      "loss": 0.3573,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4848719937936385,
+      "grad_norm": 4.660079479217529,
+      "learning_rate": 2.2578455331859266e-05,
+      "loss": 0.3135,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5818463925523661,
+      "grad_norm": 2.9539144039154053,
+      "learning_rate": 2.209356452926801e-05,
+      "loss": 0.2992,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6788207913110939,
+      "grad_norm": 1.4715936183929443,
+      "learning_rate": 2.1608673726676753e-05,
+      "loss": 0.2836,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7757951900698216,
+      "grad_norm": 1.7886435985565186,
+      "learning_rate": 2.1123782924085498e-05,
+      "loss": 0.2698,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8727695888285493,
+      "grad_norm": 1.0143980979919434,
+      "learning_rate": 2.063889212149424e-05,
+      "loss": 0.2549,
+      "step": 4500
+    },
+    {
+      "epoch": 0.969743987587277,
+      "grad_norm": 4.67170524597168,
+      "learning_rate": 2.0154001318902985e-05,
+      "loss": 0.255,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.22126668691635132,
+      "eval_runtime": 1558.3887,
+      "eval_samples_per_second": 2.836,
+      "eval_steps_per_second": 0.355,
+      "step": 5156
+    },
+    {
+      "epoch": 1.0667183863460046,
+      "grad_norm": 1.17802894115448,
+      "learning_rate": 1.966911051631173e-05,
+      "loss": 0.198,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1636927851047323,
+      "grad_norm": 2.5160129070281982,
+      "learning_rate": 1.9184219713720472e-05,
+      "loss": 0.195,
+      "step": 6000
+    },
+    {
+      "epoch": 1.26066718386346,
+      "grad_norm": 2.1824357509613037,
+      "learning_rate": 1.8699328911129217e-05,
+      "loss": 0.1864,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3576415826221877,
+      "grad_norm": 1.4108847379684448,
+      "learning_rate": 1.821443810853796e-05,
+      "loss": 0.1948,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4546159813809154,
+      "grad_norm": 1.5844694375991821,
+      "learning_rate": 1.7730517087551886e-05,
+      "loss": 0.1793,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5515903801396431,
+      "grad_norm": 0.8616577386856079,
+      "learning_rate": 1.7245626284960627e-05,
+      "loss": 0.1804,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6485647788983708,
+      "grad_norm": 2.6326045989990234,
+      "learning_rate": 1.6760735482369372e-05,
+      "loss": 0.1719,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7455391776570985,
+      "grad_norm": 1.3256356716156006,
+      "learning_rate": 1.6275844679778114e-05,
+      "loss": 0.1768,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8425135764158262,
+      "grad_norm": 2.5661003589630127,
+      "learning_rate": 1.579192365879204e-05,
+      "loss": 0.171,
+      "step": 9500
+    },
+    {
+      "epoch": 1.939487975174554,
+      "grad_norm": 3.0119805335998535,
+      "learning_rate": 1.5307032856200783e-05,
+      "loss": 0.1654,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.16889868676662445,
+      "eval_runtime": 1543.9946,
+      "eval_samples_per_second": 2.863,
+      "eval_steps_per_second": 0.358,
+      "step": 10312
+    },
+    {
+      "epoch": 2.0364623739332814,
+      "grad_norm": 2.474855661392212,
+      "learning_rate": 1.4825051398425075e-05,
+      "loss": 0.1434,
+      "step": 10500
+    },
+    {
+      "epoch": 2.133436772692009,
+      "grad_norm": 1.4645425081253052,
+      "learning_rate": 1.4343069940649367e-05,
+      "loss": 0.1296,
+      "step": 11000
+    },
+    {
+      "epoch": 2.230411171450737,
+      "grad_norm": 1.1075003147125244,
+      "learning_rate": 1.3858179138058112e-05,
+      "loss": 0.1346,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3273855702094646,
+      "grad_norm": 2.3721115589141846,
+      "learning_rate": 1.3373288335466855e-05,
+      "loss": 0.1247,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4243599689681923,
+      "grad_norm": 0.8129625916481018,
+      "learning_rate": 1.2888397532875595e-05,
+      "loss": 0.1184,
+      "step": 12500
+    },
+    {
+      "epoch": 2.52133436772692,
+      "grad_norm": 2.1738102436065674,
+      "learning_rate": 1.240350673028434e-05,
+      "loss": 0.1227,
+      "step": 13000
+    },
+    {
+      "epoch": 2.6183087664856477,
+      "grad_norm": 2.0540452003479004,
+      "learning_rate": 1.1918615927693085e-05,
+      "loss": 0.1193,
+      "step": 13500
+    },
+    {
+      "epoch": 2.7152831652443754,
+      "grad_norm": 1.0573948621749878,
+      "learning_rate": 1.1433725125101828e-05,
+      "loss": 0.1184,
+      "step": 14000
+    },
+    {
+      "epoch": 2.812257564003103,
+      "grad_norm": 0.6909541487693787,
+      "learning_rate": 1.094883432251057e-05,
+      "loss": 0.1133,
+      "step": 14500
+    },
+    {
+      "epoch": 2.909231962761831,
+      "grad_norm": 3.4285881519317627,
+      "learning_rate": 1.0463943519919314e-05,
+      "loss": 0.1221,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1472880095243454,
+      "eval_runtime": 1543.9214,
+      "eval_samples_per_second": 2.863,
+      "eval_steps_per_second": 0.358,
+      "step": 15468
+    },
+    {
+      "epoch": 3.0062063615205585,
+      "grad_norm": 1.0781619548797607,
+      "learning_rate": 9.979052717328059e-06,
+      "loss": 0.1055,
+      "step": 15500
+    },
+    {
+      "epoch": 3.1031807602792862,
+      "grad_norm": 1.153516411781311,
+      "learning_rate": 9.494161914736802e-06,
+      "loss": 0.0921,
+      "step": 16000
+    },
+    {
+      "epoch": 3.200155159038014,
+      "grad_norm": 0.8690130114555359,
+      "learning_rate": 9.009271112145545e-06,
+      "loss": 0.0914,
+      "step": 16500
+    },
+    {
+      "epoch": 3.2971295577967417,
+      "grad_norm": 0.9147763848304749,
+      "learning_rate": 8.524380309554289e-06,
+      "loss": 0.0955,
+      "step": 17000
+    },
+    {
+      "epoch": 3.3941039565554694,
+      "grad_norm": 0.4283031225204468,
+      "learning_rate": 8.039489506963032e-06,
+      "loss": 0.0983,
+      "step": 17500
+    },
+    {
+      "epoch": 3.491078355314197,
+      "grad_norm": 1.6501576900482178,
+      "learning_rate": 7.554598704371776e-06,
+      "loss": 0.0937,
+      "step": 18000
+    },
+    {
+      "epoch": 3.588052754072925,
+      "grad_norm": 1.2180219888687134,
+      "learning_rate": 7.069707901780519e-06,
+      "loss": 0.0915,
+      "step": 18500
+    },
+    {
+      "epoch": 3.6850271528316525,
+      "grad_norm": 1.027410864830017,
+      "learning_rate": 6.584817099189262e-06,
+      "loss": 0.091,
+      "step": 19000
+    },
+    {
+      "epoch": 3.78200155159038,
+      "grad_norm": 1.701826810836792,
+      "learning_rate": 6.100896078203189e-06,
+      "loss": 0.0938,
+      "step": 19500
+    },
+    {
+      "epoch": 3.878975950349108,
+      "grad_norm": 1.8526573181152344,
+      "learning_rate": 5.616005275611932e-06,
+      "loss": 0.0946,
+      "step": 20000
+    },
+    {
+      "epoch": 3.9759503491078356,
+      "grad_norm": 2.527759075164795,
+      "learning_rate": 5.131114473020676e-06,
+      "loss": 0.0879,
+      "step": 20500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.13828447461128235,
+      "eval_runtime": 1543.3031,
+      "eval_samples_per_second": 2.864,
+      "eval_steps_per_second": 0.358,
+      "step": 20624
+    },
+    {
+      "epoch": 4.072924747866563,
+      "grad_norm": 1.2997472286224365,
+      "learning_rate": 1.482330921856514e-05,
+      "loss": 0.0851,
+      "step": 21000
+    },
+    {
+      "epoch": 4.169899146625291,
+      "grad_norm": 2.8086001873016357,
+      "learning_rate": 1.4580868519560117e-05,
+      "loss": 0.092,
+      "step": 21500
+    },
+    {
+      "epoch": 4.266873545384018,
+      "grad_norm": 1.3651138544082642,
+      "learning_rate": 1.4338427820555092e-05,
+      "loss": 0.091,
+      "step": 22000
+    },
+    {
+      "epoch": 4.363847944142746,
+      "grad_norm": 1.5494824647903442,
+      "learning_rate": 1.409598712155007e-05,
+      "loss": 0.0916,
+      "step": 22500
+    },
+    {
+      "epoch": 4.460822342901474,
+      "grad_norm": 1.5494245290756226,
+      "learning_rate": 1.3854031303943058e-05,
+      "loss": 0.0919,
+      "step": 23000
+    },
+    {
+      "epoch": 4.557796741660201,
+      "grad_norm": 2.636620044708252,
+      "learning_rate": 1.3611590604938032e-05,
+      "loss": 0.0936,
+      "step": 23500
+    },
+    {
+      "epoch": 4.654771140418929,
+      "grad_norm": 1.1111247539520264,
+      "learning_rate": 1.3369149905933009e-05,
+      "loss": 0.0918,
+      "step": 24000
+    },
+    {
+      "epoch": 4.751745539177657,
+      "grad_norm": 1.1152452230453491,
+      "learning_rate": 1.3126709206927986e-05,
+      "loss": 0.095,
+      "step": 24500
+    },
+    {
+      "epoch": 4.848719937936385,
+      "grad_norm": 1.1507107019424438,
+      "learning_rate": 1.2884268507922962e-05,
+      "loss": 0.0933,
+      "step": 25000
+    },
+    {
+      "epoch": 4.945694336695112,
+      "grad_norm": 0.9500592350959778,
+      "learning_rate": 1.2641827808917939e-05,
+      "loss": 0.0951,
+      "step": 25500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14213640987873077,
+      "eval_runtime": 1544.0177,
+      "eval_samples_per_second": 2.863,
+      "eval_steps_per_second": 0.358,
+      "step": 25780
+    },
+    {
+      "epoch": 5.04266873545384,
+      "grad_norm": 1.6337387561798096,
+      "learning_rate": 1.2399871991310926e-05,
+      "loss": 0.0852,
+      "step": 26000
+    },
+    {
+      "epoch": 5.139643134212568,
+      "grad_norm": 0.6484285593032837,
+      "learning_rate": 1.2157431292305903e-05,
+      "loss": 0.0751,
+      "step": 26500
+    },
+    {
+      "epoch": 5.236617532971295,
+      "grad_norm": 1.9428491592407227,
+      "learning_rate": 1.1914990593300878e-05,
+      "loss": 0.0789,
+      "step": 27000
+    },
+    {
+      "epoch": 5.333591931730023,
+      "grad_norm": 1.7594366073608398,
+      "learning_rate": 1.1672549894295855e-05,
+      "loss": 0.0795,
+      "step": 27500
+    },
+    {
+      "epoch": 5.430566330488751,
+      "grad_norm": 0.4171479046344757,
+      "learning_rate": 1.1430109195290833e-05,
+      "loss": 0.0775,
+      "step": 28000
+    },
+    {
+      "epoch": 5.5275407292474785,
+      "grad_norm": 1.192670226097107,
+      "learning_rate": 1.118766849628581e-05,
+      "loss": 0.0822,
+      "step": 28500
+    },
+    {
+      "epoch": 5.624515128006206,
+      "grad_norm": 1.016116976737976,
+      "learning_rate": 1.0945227797280785e-05,
+      "loss": 0.0811,
+      "step": 29000
+    },
+    {
+      "epoch": 5.721489526764934,
+      "grad_norm": 0.925920307636261,
+      "learning_rate": 1.0702787098275762e-05,
+      "loss": 0.0767,
+      "step": 29500
+    },
+    {
+      "epoch": 5.818463925523662,
+      "grad_norm": 1.05020010471344,
+      "learning_rate": 1.046083128066875e-05,
+      "loss": 0.0784,
+      "step": 30000
+    },
+    {
+      "epoch": 5.915438324282389,
+      "grad_norm": 1.8532640933990479,
+      "learning_rate": 1.0218390581663725e-05,
+      "loss": 0.0777,
+      "step": 30500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.14130142331123352,
+      "eval_runtime": 1544.1253,
+      "eval_samples_per_second": 2.862,
+      "eval_steps_per_second": 0.358,
+      "step": 30936
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 51560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2712794309494047e+18,
+  "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:a99ac9ed0100852da6186acc42a9510c4cea341cd3f7e907f7fb00e493e45c7d
+size 5112