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": [
+    "q_proj",
+    "v_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:fb0a8e29329845b9e73a1000863f8f667bd2bca3090e37f399d85710b2813a6d
+size 4517152

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b657d406f8fdf03701a9de3f3b4611639317e970383c8040f05bd14d7b29da36
+size 9085370

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6515220cfd9cadc1eef7596c52753da6c680aedd06b209314fc646ad877c98
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19077005a031c0f207bc2d71e26ab10be3feb3ef2e5f8e23aca8843d81fcc9a6
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d890cd5749feafe1cc0e8730bcf7682c17cc68c521fcd50051b23effa582a5e
+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 +1,193 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4385,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28506271379703535,
+      "grad_norm": 0.8346652984619141,
+      "learning_rate": 0.0001885974914481186,
+      "loss": 1.1468,
+      "step": 250
+    },
+    {
+      "epoch": 0.5701254275940707,
+      "grad_norm": 0.7933174967765808,
+      "learning_rate": 0.00017719498289623718,
+      "loss": 0.9799,
+      "step": 500
+    },
+    {
+      "epoch": 0.855188141391106,
+      "grad_norm": 0.7169309258460999,
+      "learning_rate": 0.00016579247434435576,
+      "loss": 0.943,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8826740384101868,
+      "eval_runtime": 87.0511,
+      "eval_samples_per_second": 17.909,
+      "eval_steps_per_second": 1.126,
+      "step": 877
+    },
+    {
+      "epoch": 1.1402508551881414,
+      "grad_norm": 0.7942357659339905,
+      "learning_rate": 0.00015438996579247434,
+      "loss": 0.9029,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4253135689851768,
+      "grad_norm": 0.833415150642395,
+      "learning_rate": 0.00014298745724059295,
+      "loss": 0.8786,
+      "step": 1250
+    },
+    {
+      "epoch": 1.710376282782212,
+      "grad_norm": 0.8092217445373535,
+      "learning_rate": 0.0001315849486887115,
+      "loss": 0.8515,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9954389965792474,
+      "grad_norm": 0.7863802909851074,
+      "learning_rate": 0.00012018244013683011,
+      "loss": 0.8452,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8214807510375977,
+      "eval_runtime": 87.0295,
+      "eval_samples_per_second": 17.913,
+      "eval_steps_per_second": 1.126,
+      "step": 1754
+    },
+    {
+      "epoch": 2.280501710376283,
+      "grad_norm": 1.0299004316329956,
+      "learning_rate": 0.0001087799315849487,
+      "loss": 0.8139,
+      "step": 2000
+    },
+    {
+      "epoch": 2.565564424173318,
+      "grad_norm": 0.8788676857948303,
+      "learning_rate": 9.737742303306729e-05,
+      "loss": 0.8172,
+      "step": 2250
+    },
+    {
+      "epoch": 2.8506271379703536,
+      "grad_norm": 0.9441242218017578,
+      "learning_rate": 8.597491448118586e-05,
+      "loss": 0.7919,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7865139842033386,
+      "eval_runtime": 87.0332,
+      "eval_samples_per_second": 17.913,
+      "eval_steps_per_second": 1.126,
+      "step": 2631
+    },
+    {
+      "epoch": 3.135689851767389,
+      "grad_norm": 1.2991793155670166,
+      "learning_rate": 7.457240592930444e-05,
+      "loss": 0.7961,
+      "step": 2750
+    },
+    {
+      "epoch": 3.420752565564424,
+      "grad_norm": 0.9629215598106384,
+      "learning_rate": 6.316989737742304e-05,
+      "loss": 0.7761,
+      "step": 3000
+    },
+    {
+      "epoch": 3.7058152793614596,
+      "grad_norm": 1.0487836599349976,
+      "learning_rate": 5.1767388825541616e-05,
+      "loss": 0.7673,
+      "step": 3250
+    },
+    {
+      "epoch": 3.990877993158495,
+      "grad_norm": 0.9421872496604919,
+      "learning_rate": 4.0364880273660207e-05,
+      "loss": 0.7717,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.76755291223526,
+      "eval_runtime": 87.0332,
+      "eval_samples_per_second": 17.913,
+      "eval_steps_per_second": 1.126,
+      "step": 3508
+    },
+    {
+      "epoch": 4.27594070695553,
+      "grad_norm": 0.9843165874481201,
+      "learning_rate": 2.896237172177879e-05,
+      "loss": 0.7556,
+      "step": 3750
+    },
+    {
+      "epoch": 4.561003420752566,
+      "grad_norm": 0.908370852470398,
+      "learning_rate": 1.7559863169897377e-05,
+      "loss": 0.7452,
+      "step": 4000
+    },
+    {
+      "epoch": 4.846066134549601,
+      "grad_norm": 1.0073881149291992,
+      "learning_rate": 6.2029646522234895e-06,
+      "loss": 0.7658,
+      "step": 4250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7607811093330383,
+      "eval_runtime": 87.0224,
+      "eval_samples_per_second": 17.915,
+      "eval_steps_per_second": 1.126,
+      "step": 4385
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 4385,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 2.2306963458097152e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381b334b78896d68e5f510356115cc9a1166d075d122c704c2d6b6deb05d9336
+size 5304