Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vilsonrodrigues/falcon-7b-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d353ad955b99b530c25237bba913a17def83fc6d7b0fbf210a2e36be70a8dff
+size 18898606

checkpoint-80/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: vilsonrodrigues/falcon-7b-sharded
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-80/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vilsonrodrigues/falcon-7b-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-80/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d353ad955b99b530c25237bba913a17def83fc6d7b0fbf210a2e36be70a8dff
+size 18898606

checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71c62dc4069384492d62ac5b388a68bf0c7435460395342d317dacd7b49fd74
+size 37803066

checkpoint-80/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2587924e4ede8439651703e3c77e6b322a85e9ef3f46b1c48e400398c59924
+size 14244

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0ad751608bb1f65d75e4c79bf22f0a1cfe737e1d81d092b1221458be1c8fb4
+size 1064

checkpoint-80/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

checkpoint-80/tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-80/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 28.571428571428573,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "learning_rate": 5e-05,
+      "loss": 1.8155,
+      "step": 2
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0001,
+      "loss": 1.848,
+      "step": 4
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.8329,
+      "step": 6
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0002,
+      "loss": 1.8311,
+      "step": 8
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.00019444444444444446,
+      "loss": 1.8991,
+      "step": 10
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 1.7408,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 1.8108,
+      "step": 14
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.8031,
+      "step": 16
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.00017222222222222224,
+      "loss": 1.7605,
+      "step": 18
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.7367,
+      "step": 20
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.0001611111111111111,
+      "loss": 1.7215,
+      "step": 22
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.7342,
+      "step": 24
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7194,
+      "step": 26
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 1.6771,
+      "step": 28
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 1.6938,
+      "step": 30
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.5943,
+      "step": 32
+    },
+    {
+      "epoch": 12.14,
+      "learning_rate": 0.00012777777777777776,
+      "loss": 1.686,
+      "step": 34
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 1.6046,
+      "step": 36
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 1.5834,
+      "step": 38
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.6078,
+      "step": 40
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.00010555555555555557,
+      "loss": 1.5769,
+      "step": 42
+    },
+    {
+      "epoch": 15.71,
+      "learning_rate": 0.0001,
+      "loss": 1.5473,
+      "step": 44
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 9.444444444444444e-05,
+      "loss": 1.5717,
+      "step": 46
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.5053,
+      "step": 48
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.5388,
+      "step": 50
+    },
+    {
+      "epoch": 18.57,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 1.4342,
+      "step": 52
+    },
+    {
+      "epoch": 19.29,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 1.5222,
+      "step": 54
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.4665,
+      "step": 56
+    },
+    {
+      "epoch": 20.71,
+      "learning_rate": 6.111111111111112e-05,
+      "loss": 1.4485,
+      "step": 58
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 1.4478,
+      "step": 60
+    },
+    {
+      "epoch": 22.14,
+      "learning_rate": 5e-05,
+      "loss": 1.4553,
+      "step": 62
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.4205,
+      "step": 64
+    },
+    {
+      "epoch": 23.57,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.4115,
+      "step": 66
+    },
+    {
+      "epoch": 24.29,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.3992,
+      "step": 68
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.4159,
+      "step": 70
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.3851,
+      "step": 72
+    },
+    {
+      "epoch": 26.43,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.3877,
+      "step": 74
+    },
+    {
+      "epoch": 27.14,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 1.4048,
+      "step": 76
+    },
+    {
+      "epoch": 27.86,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 1.3533,
+      "step": 78
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 0.0,
+      "loss": 1.3752,
+      "step": 80
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 80,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 6.5185089847296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f74e8108d8095a18caa00afb42f0a12067a557c2ff9079de01cd5a823679b5
+size 4472

runs/Oct15_16-18-34_1cb9b508df49/events.out.tfevents.1697386715.1cb9b508df49.5138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b678e78c8569d866f7261b61598ca035e2d5e993ccda91d0cbfd0e65fde2139e
+size 5192

runs/Oct15_16-22-33_1cb9b508df49/events.out.tfevents.1697386954.1cb9b508df49.6976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd771e400af8a52b650cda700988dcc65a0510e5f7bc81d2d6502086ac215bea
+size 5192

runs/Oct15_16-26-32_1cb9b508df49/events.out.tfevents.1697387193.1cb9b508df49.8048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb861346ce7d5b0c1233333b1cc73ec3e83da56185ba468046a17a94c4d18a5
+size 7080

runs/Oct15_16-38-20_1cb9b508df49/events.out.tfevents.1697387901.1cb9b508df49.11098.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3ce8ba9cc47643cde44a0975a81ea6d0e6f4fef784e729ca32055bda718277
+size 8620

runs/Oct15_17-06-35_1cb9b508df49/events.out.tfevents.1697389596.1cb9b508df49.18318.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb77034638a1c9377ff32eb05f1a25dcb15694ae090b705e1a87b31195da12f4
+size 11700

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f74e8108d8095a18caa00afb42f0a12067a557c2ff9079de01cd5a823679b5
+size 4472

training_params.json

@@ -0,0 +1 @@
+{"model": "vilsonrodrigues/falcon-7b-sharded", "data_path": "data/", "project_name": "my_autotrain_llm", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 40, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 5, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 2048, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "maxmendola/FalconCS27C", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "disable_gradient_checkpointing": false}