Upload folder using huggingface_hub

training_checkpoints/checkpoint-964/README.md

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

training_checkpoints/checkpoint-964/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-964/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356775fa0db9f0c8f19039a4c5cbc09867c69af4cc2d10337c77745bb7da1eac
+size 50626520

training_checkpoints/checkpoint-964/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499149db5a0687a09ea3534b60bcb25cf13aa33150d1c762c4a5df81fa27371a
+size 101430714

training_checkpoints/checkpoint-964/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e4faca249a896db7f43256b46f0b3c473b2a66a810e22f0a5c263d01a71adc
+size 14244

training_checkpoints/checkpoint-964/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a0a4d4993be777ee2e0cd0654dc5931b2f353fb7a4ed43d7720fb59180738d
+size 1064

training_checkpoints/checkpoint-964/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_checkpoints/checkpoint-964/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

training_checkpoints/checkpoint-964/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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>",
+  "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
+}

training_checkpoints/checkpoint-964/trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.7415140921427528,
+  "best_model_checkpoint": "tiny-llama-lora-new/checkpoint-643",
+  "epoch": 5.996889580093312,
+  "eval_steps": 500,
+  "global_step": 964,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8001549186676995,
+      "eval_f1_macro": 0.6790360166213908,
+      "eval_f1_micro": 0.8001549186676995,
+      "eval_f1_weighted": 0.7959404181222782,
+      "eval_loss": 0.6614832282066345,
+      "eval_macro_fpr": 0.01824293967244035,
+      "eval_macro_sensitivity": 0.6677834011062839,
+      "eval_macro_specificity": 0.9848478627893485,
+      "eval_precision": 0.8040294558027004,
+      "eval_precision_macro": 0.7265846774862527,
+      "eval_recall": 0.8001549186676995,
+      "eval_recall_macro": 0.6677834011062839,
+      "eval_runtime": 225.9328,
+      "eval_samples_per_second": 5.714,
+      "eval_steps_per_second": 0.717,
+      "eval_weighted_fpr": 0.017527173913043478,
+      "eval_weighted_sensitivity": 0.8001549186676995,
+      "eval_weighted_specificity": 0.97256302317253,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8063516653756778,
+      "eval_f1_macro": 0.723523893027765,
+      "eval_f1_micro": 0.8063516653756778,
+      "eval_f1_weighted": 0.8039099652383133,
+      "eval_loss": 0.6995529532432556,
+      "eval_macro_fpr": 0.01771710819775641,
+      "eval_macro_sensitivity": 0.7207263437235008,
+      "eval_macro_specificity": 0.9853387258716434,
+      "eval_precision": 0.8110438944279544,
+      "eval_precision_macro": 0.7448100337436813,
+      "eval_recall": 0.8063516653756778,
+      "eval_recall_macro": 0.7207263437235008,
+      "eval_runtime": 230.7469,
+      "eval_samples_per_second": 5.595,
+      "eval_steps_per_second": 0.702,
+      "eval_weighted_fpr": 0.01686454398273071,
+      "eval_weighted_sensitivity": 0.8063516653756778,
+      "eval_weighted_specificity": 0.9737292226989717,
+      "step": 321
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8125484120836561,
+      "eval_f1_macro": 0.7179663090811256,
+      "eval_f1_micro": 0.8125484120836561,
+      "eval_f1_weighted": 0.8085118934271095,
+      "eval_loss": 0.8202366828918457,
+      "eval_macro_fpr": 0.017097652587672894,
+      "eval_macro_sensitivity": 0.7080107913825292,
+      "eval_macro_specificity": 0.985578595986596,
+      "eval_precision": 0.8118501609528374,
+      "eval_precision_macro": 0.7576540712122397,
+      "eval_recall": 0.8125484120836561,
+      "eval_recall_macro": 0.7080107913825292,
+      "eval_runtime": 231.655,
+      "eval_samples_per_second": 5.573,
+      "eval_steps_per_second": 0.699,
+      "eval_weighted_fpr": 0.016211146838156484,
+      "eval_weighted_sensitivity": 0.8125484120836561,
+      "eval_weighted_specificity": 0.9711305277152844,
+      "step": 482
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 0.2932,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8140975987606507,
+      "eval_f1_macro": 0.7415140921427528,
+      "eval_f1_micro": 0.8140975987606507,
+      "eval_f1_weighted": 0.8153735617531811,
+      "eval_loss": 0.9493006467819214,
+      "eval_macro_fpr": 0.016573672675540378,
+      "eval_macro_sensitivity": 0.7326751453453961,
+      "eval_macro_specificity": 0.9859001747376132,
+      "eval_precision": 0.8204052204072106,
+      "eval_precision_macro": 0.759251934556511,
+      "eval_recall": 0.8140975987606507,
+      "eval_recall_macro": 0.7326751453453961,
+      "eval_runtime": 230.2371,
+      "eval_samples_per_second": 5.607,
+      "eval_steps_per_second": 0.704,
+      "eval_weighted_fpr": 0.016049217600641968,
+      "eval_weighted_sensitivity": 0.8140975987606507,
+      "eval_weighted_specificity": 0.974405022303545,
+      "step": 643
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8109992254066615,
+      "eval_f1_macro": 0.7413292975124365,
+      "eval_f1_micro": 0.8109992254066615,
+      "eval_f1_weighted": 0.8086569922767037,
+      "eval_loss": 1.0610005855560303,
+      "eval_macro_fpr": 0.017150663222076427,
+      "eval_macro_sensitivity": 0.7427303328596474,
+      "eval_macro_specificity": 0.9856545654845559,
+      "eval_precision": 0.8110273755487133,
+      "eval_precision_macro": 0.7595846993577862,
+      "eval_recall": 0.8109992254066615,
+      "eval_recall_macro": 0.7427303328596474,
+      "eval_runtime": 232.3513,
+      "eval_samples_per_second": 5.556,
+      "eval_steps_per_second": 0.697,
+      "eval_weighted_fpr": 0.016373641121997046,
+      "eval_weighted_sensitivity": 0.8109992254066615,
+      "eval_weighted_specificity": 0.9738192568616761,
+      "step": 803
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.814872192099148,
+      "eval_f1_macro": 0.740834009056896,
+      "eval_f1_micro": 0.814872192099148,
+      "eval_f1_weighted": 0.812828873292886,
+      "eval_loss": 1.1361573934555054,
+      "eval_macro_fpr": 0.016745822161733162,
+      "eval_macro_sensitivity": 0.7380044964762863,
+      "eval_macro_specificity": 0.9859281636821422,
+      "eval_precision": 0.8159522433901665,
+      "eval_precision_macro": 0.7731408058998965,
+      "eval_recall": 0.814872192099148,
+      "eval_recall_macro": 0.7380044964762863,
+      "eval_runtime": 230.3919,
+      "eval_samples_per_second": 5.603,
+      "eval_steps_per_second": 0.703,
+      "eval_weighted_fpr": 0.015968463954032203,
+      "eval_weighted_sensitivity": 0.814872192099148,
+      "eval_weighted_specificity": 0.9740502631329879,
+      "step": 964
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2400,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 9.296613648787046e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-964/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84303a58cbcecc7c81f1fc15ed332a0b248db008b5bd9ad0021bb2b3e07414f
+size 4600