Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.14.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "v_proj",
+    "q_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 sha256:76610d49a3428c31e880c2da318f539d99b865c1a0c2895d28643dc2450f4d35
+size 4517152

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d5187b1a4ca7bbb64304c1eb573b5dde1f6513d57143afdcb8431e388a6a5c
+size 9063546

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09bd9ada897acb73d1330edcbe55eaa8ec06ed2517a35847b590eef191fea77
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4fe8e328be6e10e053e14666b2e571c45c73d9a8291556b08910e3da67b3e6
+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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07635336336565626,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0015270672673131252,
+      "grad_norm": 1.7919381856918335,
+      "learning_rate": 0.00019980267284282717,
+      "loss": 2.5081,
+      "mean_token_accuracy": 0.5467605337500572,
+      "step": 10
+    },
+    {
+      "epoch": 0.0030541345346262504,
+      "grad_norm": 2.8579838275909424,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 1.7298,
+      "mean_token_accuracy": 0.6468371748924255,
+      "step": 20
+    },
+    {
+      "epoch": 0.004581201801939375,
+      "grad_norm": 1.7089707851409912,
+      "learning_rate": 0.0001982287250728689,
+      "loss": 1.1637,
+      "mean_token_accuracy": 0.7540688991546631,
+      "step": 30
+    },
+    {
+      "epoch": 0.006108269069252501,
+      "grad_norm": 0.9711195826530457,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8899,
+      "mean_token_accuracy": 0.8186888545751572,
+      "step": 40
+    },
+    {
+      "epoch": 0.007635336336565626,
+      "grad_norm": 0.8973957896232605,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.8256,
+      "mean_token_accuracy": 0.8281645506620408,
+      "step": 50
+    },
+    {
+      "epoch": 0.00916240360387875,
+      "grad_norm": 0.9836689829826355,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.754,
+      "mean_token_accuracy": 0.8368939191102982,
+      "step": 60
+    },
+    {
+      "epoch": 0.010689470871191877,
+      "grad_norm": 1.0244220495224,
+      "learning_rate": 0.00019048270524660196,
+      "loss": 0.7019,
+      "mean_token_accuracy": 0.8408633172512054,
+      "step": 70
+    },
+    {
+      "epoch": 0.012216538138505002,
+      "grad_norm": 1.1119804382324219,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.8521306127309799,
+      "step": 80
+    },
+    {
+      "epoch": 0.013743605405818126,
+      "grad_norm": 0.7104642987251282,
+      "learning_rate": 0.00018443279255020152,
+      "loss": 0.6679,
+      "mean_token_accuracy": 0.8470089048147201,
+      "step": 90
+    },
+    {
+      "epoch": 0.015270672673131251,
+      "grad_norm": 0.7890557646751404,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6581,
+      "mean_token_accuracy": 0.8512038260698318,
+      "step": 100
+    },
+    {
+      "epoch": 0.016797739940444378,
+      "grad_norm": 0.6953688859939575,
+      "learning_rate": 0.00017705132427757895,
+      "loss": 0.6358,
+      "mean_token_accuracy": 0.8534704208374023,
+      "step": 110
+    },
+    {
+      "epoch": 0.0183248072077575,
+      "grad_norm": 0.8764053583145142,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.857587480545044,
+      "step": 120
+    },
+    {
+      "epoch": 0.019851874475070627,
+      "grad_norm": 0.8632748126983643,
+      "learning_rate": 0.00016845471059286887,
+      "loss": 0.6382,
+      "mean_token_accuracy": 0.8533297270536423,
+      "step": 130
+    },
+    {
+      "epoch": 0.021378941742383754,
+      "grad_norm": 0.9536803960800171,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.6252,
+      "mean_token_accuracy": 0.8563201695680618,
+      "step": 140
+    },
+    {
+      "epoch": 0.022906009009696877,
+      "grad_norm": 0.7280343174934387,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.6105,
+      "mean_token_accuracy": 0.8567106693983078,
+      "step": 150
+    },
+    {
+      "epoch": 0.024433076277010003,
+      "grad_norm": 0.6883084177970886,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.8576973646879196,
+      "step": 160
+    },
+    {
+      "epoch": 0.025960143544323126,
+      "grad_norm": 0.7537200450897217,
+      "learning_rate": 0.00014817536741017152,
+      "loss": 0.6182,
+      "mean_token_accuracy": 0.8572364389896393,
+      "step": 170
+    },
+    {
+      "epoch": 0.027487210811636253,
+      "grad_norm": 0.8564761877059937,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8564972043037414,
+      "step": 180
+    },
+    {
+      "epoch": 0.02901427807894938,
+      "grad_norm": 0.9395449757575989,
+      "learning_rate": 0.00013681245526846783,
+      "loss": 0.6082,
+      "mean_token_accuracy": 0.8573319047689438,
+      "step": 190
+    },
+    {
+      "epoch": 0.030541345346262502,
+      "grad_norm": 1.4290846586227417,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5852,
+      "mean_token_accuracy": 0.859686890244484,
+      "step": 200
+    },
+    {
+      "epoch": 0.032068412613575625,
+      "grad_norm": 0.8474317789077759,
+      "learning_rate": 0.0001248689887164855,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.863548994064331,
+      "step": 210
+    },
+    {
+      "epoch": 0.033595479880888755,
+      "grad_norm": 0.8646250367164612,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5862,
+      "mean_token_accuracy": 0.861778911948204,
+      "step": 220
+    },
+    {
+      "epoch": 0.03512254714820188,
+      "grad_norm": 0.9591971635818481,
+      "learning_rate": 0.00011253332335643043,
+      "loss": 0.5656,
+      "mean_token_accuracy": 0.8678788006305694,
+      "step": 230
+    },
+    {
+      "epoch": 0.036649614415515,
+      "grad_norm": 0.7952109575271606,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.581,
+      "mean_token_accuracy": 0.8648124188184738,
+      "step": 240
+    },
+    {
+      "epoch": 0.03817668168282813,
+      "grad_norm": 0.7618094086647034,
+      "learning_rate": 0.0001,
+      "loss": 0.576,
+      "mean_token_accuracy": 0.8639664649963379,
+      "step": 250
+    },
+    {
+      "epoch": 0.039703748950141254,
+      "grad_norm": 0.730375349521637,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.5915,
+      "mean_token_accuracy": 0.8597521275281906,
+      "step": 260
+    },
+    {
+      "epoch": 0.04123081621745438,
+      "grad_norm": 0.8533547520637512,
+      "learning_rate": 8.746667664356956e-05,
+      "loss": 0.5891,
+      "mean_token_accuracy": 0.859322988986969,
+      "step": 270
+    },
+    {
+      "epoch": 0.04275788348476751,
+      "grad_norm": 0.7875514626502991,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.5957,
+      "mean_token_accuracy": 0.8590130746364594,
+      "step": 280
+    },
+    {
+      "epoch": 0.04428495075208063,
+      "grad_norm": 0.8987193703651428,
+      "learning_rate": 7.513101128351454e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.8575950294733048,
+      "step": 290
+    },
+    {
+      "epoch": 0.04581201801939375,
+      "grad_norm": 0.7341880202293396,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5614,
+      "mean_token_accuracy": 0.8668889582157135,
+      "step": 300
+    },
+    {
+      "epoch": 0.047339085286706876,
+      "grad_norm": 0.7949256300926208,
+      "learning_rate": 6.318754473153221e-05,
+      "loss": 0.5936,
+      "mean_token_accuracy": 0.8569323867559433,
+      "step": 310
+    },
+    {
+      "epoch": 0.048866152554020006,
+      "grad_norm": 0.840946614742279,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5901,
+      "mean_token_accuracy": 0.863608232140541,
+      "step": 320
+    },
+    {
+      "epoch": 0.05039321982133313,
+      "grad_norm": 0.9876859188079834,
+      "learning_rate": 5.182463258982846e-05,
+      "loss": 0.5787,
+      "mean_token_accuracy": 0.8655537277460098,
+      "step": 330
+    },
+    {
+      "epoch": 0.05192028708864625,
+      "grad_norm": 0.7635581493377686,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.6074,
+      "mean_token_accuracy": 0.8565149992704392,
+      "step": 340
+    },
+    {
+      "epoch": 0.05344735435595938,
+      "grad_norm": 0.7946358919143677,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6015,
+      "mean_token_accuracy": 0.8584772288799286,
+      "step": 350
+    },
+    {
+      "epoch": 0.054974421623272506,
+      "grad_norm": 0.8052517771720886,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5552,
+      "mean_token_accuracy": 0.8673796206712723,
+      "step": 360
+    },
+    {
+      "epoch": 0.05650148889058563,
+      "grad_norm": 0.7466617226600647,
+      "learning_rate": 3.154528940713113e-05,
+      "loss": 0.5954,
+      "mean_token_accuracy": 0.8603360831737519,
+      "step": 370
+    },
+    {
+      "epoch": 0.05802855615789876,
+      "grad_norm": 0.7672128081321716,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.5764,
+      "mean_token_accuracy": 0.8672617733478546,
+      "step": 380
+    },
+    {
+      "epoch": 0.05955562342521188,
+      "grad_norm": 0.7813590168952942,
+      "learning_rate": 2.2948675722421086e-05,
+      "loss": 0.5812,
+      "mean_token_accuracy": 0.8635528743267059,
+      "step": 390
+    },
+    {
+      "epoch": 0.061082690692525005,
+      "grad_norm": 0.7313287854194641,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5563,
+      "mean_token_accuracy": 0.8667043030261994,
+      "step": 400
+    },
+    {
+      "epoch": 0.06260975795983813,
+      "grad_norm": 0.9430689215660095,
+      "learning_rate": 1.5567207449798515e-05,
+      "loss": 0.5452,
+      "mean_token_accuracy": 0.871171161532402,
+      "step": 410
+    },
+    {
+      "epoch": 0.06413682522715125,
+      "grad_norm": 0.8281370401382446,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5809,
+      "mean_token_accuracy": 0.8636080652475357,
+      "step": 420
+    },
+    {
+      "epoch": 0.06566389249446439,
+      "grad_norm": 0.704873263835907,
+      "learning_rate": 9.517294753398064e-06,
+      "loss": 0.5975,
+      "mean_token_accuracy": 0.859060087800026,
+      "step": 430
+    },
+    {
+      "epoch": 0.06719095976177751,
+      "grad_norm": 0.8515197038650513,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5867,
+      "mean_token_accuracy": 0.8638981640338897,
+      "step": 440
+    },
+    {
+      "epoch": 0.06871802702909063,
+      "grad_norm": 0.7860581874847412,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.5802,
+      "mean_token_accuracy": 0.8683864206075669,
+      "step": 450
+    },
+    {
+      "epoch": 0.07024509429640376,
+      "grad_norm": 0.8138625621795654,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 0.5918,
+      "mean_token_accuracy": 0.8596341729164123,
+      "step": 460
+    },
+    {
+      "epoch": 0.07177216156371688,
+      "grad_norm": 0.8401088714599609,
+      "learning_rate": 1.771274927131139e-06,
+      "loss": 0.6209,
+      "mean_token_accuracy": 0.8542895227670669,
+      "step": 470
+    },
+    {
+      "epoch": 0.07329922883103,
+      "grad_norm": 0.993623673915863,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 0.5791,
+      "mean_token_accuracy": 0.865888985991478,
+      "step": 480
+    },
+    {
+      "epoch": 0.07482629609834313,
+      "grad_norm": 0.8312510848045349,
+      "learning_rate": 1.973271571728441e-07,
+      "loss": 0.5615,
+      "mean_token_accuracy": 0.8679140955209732,
+      "step": 490
+    },
+    {
+      "epoch": 0.07635336336565626,
+      "grad_norm": 0.9254234433174133,
+      "learning_rate": 0.0,
+      "loss": 0.5822,
+      "mean_token_accuracy": 0.8632416158914566,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5806155567955968.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f63a4c251fcbdb587f3b66634c5cb468d2c7d24605ad4cb770ca0e96a309489
+size 5560