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 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ehartford/dolphin-2.1-mistral-7b",
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7def8994775e26cb5102fffd7ded91f2f0090743510121ad98c3c44158de56a9
+size 27308941

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-350/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: ehartford/dolphin-2.1-mistral-7b
+---
+
+# 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-350/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ehartford/dolphin-2.1-mistral-7b",
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-350/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7def8994775e26cb5102fffd7ded91f2f0090743510121ad98c3c44158de56a9
+size 27308941

checkpoint-350/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef953110cfab59dbc60faefe976dd86b5d48a895eb8d702001b829d432dec41
+size 54633541

checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c35d11d20eff1657c51e3abcc4e85a1c9daa8329f51d0fd3a3ab0485cd6d6f5
+size 14575

checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6591746860121f439a0d9945e1de2e4243740b973e9264c8457e9afb122cf804
+size 627

checkpoint-350/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

checkpoint-350/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-350/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

checkpoint-350/trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 69.0909090909091,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.194805194805195e-06,
+      "loss": 1.8662,
+      "step": 11
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 1.5883,
+      "step": 22
+    },
+    {
+      "epoch": 6.05,
+      "learning_rate": 1.6623376623376623e-05,
+      "loss": 1.0967,
+      "step": 33
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 2.2337662337662336e-05,
+      "loss": 0.7579,
+      "step": 44
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 2.8051948051948052e-05,
+      "loss": 0.5478,
+      "step": 55
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 3.324675324675325e-05,
+      "loss": 0.4326,
+      "step": 66
+    },
+    {
+      "epoch": 15.04,
+      "learning_rate": 3.8441558441558445e-05,
+      "loss": 0.3292,
+      "step": 77
+    },
+    {
+      "epoch": 17.05,
+      "learning_rate": 4.415584415584416e-05,
+      "loss": 0.2404,
+      "step": 88
+    },
+    {
+      "epoch": 19.07,
+      "learning_rate": 4.987012987012987e-05,
+      "loss": 0.1739,
+      "step": 99
+    },
+    {
+      "epoch": 21.09,
+      "learning_rate": 5.558441558441558e-05,
+      "loss": 0.1312,
+      "step": 110
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 6.12987012987013e-05,
+      "loss": 0.0961,
+      "step": 121
+    },
+    {
+      "epoch": 26.04,
+      "learning_rate": 6.701298701298702e-05,
+      "loss": 0.0595,
+      "step": 132
+    },
+    {
+      "epoch": 28.05,
+      "learning_rate": 7.16883116883117e-05,
+      "loss": 0.1897,
+      "step": 143
+    },
+    {
+      "epoch": 30.07,
+      "learning_rate": 7.74025974025974e-05,
+      "loss": 0.0537,
+      "step": 154
+    },
+    {
+      "epoch": 32.09,
+      "learning_rate": 8.311688311688312e-05,
+      "loss": 0.0264,
+      "step": 165
+    },
+    {
+      "epoch": 35.02,
+      "learning_rate": 8.883116883116883e-05,
+      "loss": 0.0199,
+      "step": 176
+    },
+    {
+      "epoch": 37.04,
+      "learning_rate": 9.454545454545455e-05,
+      "loss": 0.0176,
+      "step": 187
+    },
+    {
+      "epoch": 39.05,
+      "learning_rate": 0.00010025974025974026,
+      "loss": 0.015,
+      "step": 198
+    },
+    {
+      "epoch": 41.07,
+      "learning_rate": 0.00010597402597402598,
+      "loss": 0.0134,
+      "step": 209
+    },
+    {
+      "epoch": 43.09,
+      "learning_rate": 0.00011168831168831168,
+      "loss": 0.0094,
+      "step": 220
+    },
+    {
+      "epoch": 46.02,
+      "learning_rate": 0.0001174025974025974,
+      "loss": 0.0064,
+      "step": 231
+    },
+    {
+      "epoch": 48.04,
+      "learning_rate": 0.0001231168831168831,
+      "loss": 0.0084,
+      "step": 242
+    },
+    {
+      "epoch": 50.05,
+      "learning_rate": 0.00012883116883116884,
+      "loss": 0.0077,
+      "step": 253
+    },
+    {
+      "epoch": 52.07,
+      "learning_rate": 0.00013454545454545455,
+      "loss": 0.0082,
+      "step": 264
+    },
+    {
+      "epoch": 54.09,
+      "learning_rate": 0.00014025974025974028,
+      "loss": 0.0058,
+      "step": 275
+    },
+    {
+      "epoch": 57.02,
+      "learning_rate": 0.00014597402597402599,
+      "loss": 0.006,
+      "step": 286
+    },
+    {
+      "epoch": 59.04,
+      "learning_rate": 0.0001516883116883117,
+      "loss": 0.0095,
+      "step": 297
+    },
+    {
+      "epoch": 61.05,
+      "learning_rate": 0.00015740259740259742,
+      "loss": 0.006,
+      "step": 308
+    },
+    {
+      "epoch": 63.07,
+      "learning_rate": 0.00016311688311688313,
+      "loss": 0.0068,
+      "step": 319
+    },
+    {
+      "epoch": 65.09,
+      "learning_rate": 0.00016883116883116884,
+      "loss": 0.0086,
+      "step": 330
+    },
+    {
+      "epoch": 68.02,
+      "learning_rate": 0.00017454545454545454,
+      "loss": 0.0036,
+      "step": 341
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 3850,
+  "num_train_epochs": 70,
+  "save_steps": 500,
+  "total_flos": 6.12217506496512e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d75a678e3da8729f1fa1f449353b9e0a20a60ada8928e433cdd29590a90b2f
+size 4027

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d75a678e3da8729f1fa1f449353b9e0a20a60ada8928e433cdd29590a90b2f
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "ehartford/dolphin-2.1-mistral-7b", "data_path": "ashwinpreyan/prodoction", "project_name": "percival", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 70, "batch_size": 4, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "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": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "ashwinpreyan/percival-a", "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false}