Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: chargoddard/Yi-6B-Llama
+model-index:
+- name: model-update
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# model-update
+
+This model is a fine-tuned version of [chargoddard/Yi-6B-Llama](https://huggingface.co/chargoddard/Yi-6B-Llama) on the oncc_medqa_instruct dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "chargoddard/Yi-6B-Llama",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "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_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cdb0eeb571aa0c2f87bef30e2083bf6727c1a2320c98e0500b994b85cea41c
+size 13124104

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.358406629228946,
+    "train_runtime": 800.1231,
+    "train_samples_per_second": 4.066,
+    "train_steps_per_second": 0.126
+}

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /workspace/model
+---
+
+# 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 0.8.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "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_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08e9fc82f17ba7a28387fa22b3294d93028f6f85dc688798d69ec6dc09632fe
+size 13124104

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8ade3f1342b70ce34ddcc4e0f4718ca7b553db90188389ea0a6e26a901813c
+size 26321605

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c72e8d36a05a982cd2947a5d181d5f8e613d46270acdbcfe65a195ea6bda46
+size 15607

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf8120aa2f3dc2e6ec59249421f56fe5e51ff955146f2456ddcec561f8e2337a
+size 15607

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9283128548e036d52bd040a3831b7928036afbfdfc596b518dc0a1f860ededc7
+size 627

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9828009828009828,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000125,
+      "loss": 1.6979,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000375,
+      "loss": 0.7265,
+      "step": 20
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004969974623692023,
+      "loss": 0.1676,
+      "step": 30
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004640417248825666,
+      "loss": 0.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00039928964792569654,
+      "loss": 0.1458,
+      "step": 50
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00031236028601449537,
+      "loss": 0.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002161671750624673,
+      "loss": 0.1502,
+      "step": 70
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00012500000000000006,
+      "loss": 0.1432,
+      "step": 80
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.2401832620310204e-05,
+      "loss": 0.1426,
+      "step": 90
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.157280346029916e-06,
+      "loss": 0.1354,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 101,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 5.498116162505933e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b364c2a141e55b094faf42c78d3d1ca139ada42a4780c3ad12f5e893f115e625
+size 4411

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.358406629228946,
+    "train_runtime": 800.1231,
+    "train_samples_per_second": 4.066,
+    "train_steps_per_second": 0.126
+}

trainer_log.jsonl

@@ -0,0 +1,11 @@
+{"current_steps": 10, "total_steps": 101, "loss": 1.6979, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000125, "epoch": 0.1, "percentage": 9.9, "elapsed_time": "0:01:18", "remaining_time": "0:11:58"}
+{"current_steps": 20, "total_steps": 101, "loss": 0.7265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000375, "epoch": 0.2, "percentage": 19.8, "elapsed_time": "0:02:35", "remaining_time": "0:10:31"}
+{"current_steps": 30, "total_steps": 101, "loss": 0.1676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004969974623692023, "epoch": 0.29, "percentage": 29.7, "elapsed_time": "0:03:56", "remaining_time": "0:09:18"}
+{"current_steps": 40, "total_steps": 101, "loss": 0.1557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004640417248825666, "epoch": 0.39, "percentage": 39.6, "elapsed_time": "0:05:15", "remaining_time": "0:08:01"}
+{"current_steps": 50, "total_steps": 101, "loss": 0.1458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039928964792569654, "epoch": 0.49, "percentage": 49.5, "elapsed_time": "0:06:31", "remaining_time": "0:06:38"}
+{"current_steps": 60, "total_steps": 101, "loss": 0.1429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00031236028601449537, "epoch": 0.59, "percentage": 59.41, "elapsed_time": "0:07:52", "remaining_time": "0:05:22"}
+{"current_steps": 70, "total_steps": 101, "loss": 0.1502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002161671750624673, "epoch": 0.69, "percentage": 69.31, "elapsed_time": "0:09:12", "remaining_time": "0:04:04"}
+{"current_steps": 80, "total_steps": 101, "loss": 0.1432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012500000000000006, "epoch": 0.79, "percentage": 79.21, "elapsed_time": "0:10:34", "remaining_time": "0:02:46"}
+{"current_steps": 90, "total_steps": 101, "loss": 0.1426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2401832620310204e-05, "epoch": 0.88, "percentage": 89.11, "elapsed_time": "0:11:54", "remaining_time": "0:01:27"}
+{"current_steps": 100, "total_steps": 101, "loss": 0.1354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.157280346029916e-06, "epoch": 0.98, "percentage": 99.01, "elapsed_time": "0:13:10", "remaining_time": "0:00:07"}
+{"current_steps": 101, "total_steps": 101, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 100.0, "elapsed_time": "0:13:19", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9926289926289926,
+  "eval_steps": 500,
+  "global_step": 101,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000125,
+      "loss": 1.6979,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000375,
+      "loss": 0.7265,
+      "step": 20
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004969974623692023,
+      "loss": 0.1676,
+      "step": 30
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004640417248825666,
+      "loss": 0.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00039928964792569654,
+      "loss": 0.1458,
+      "step": 50
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00031236028601449537,
+      "loss": 0.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002161671750624673,
+      "loss": 0.1502,
+      "step": 70
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00012500000000000006,
+      "loss": 0.1432,
+      "step": 80
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.2401832620310204e-05,
+      "loss": 0.1426,
+      "step": 90
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.157280346029916e-06,
+      "loss": 0.1354,
+      "step": 100
+    },
+    {
+      "epoch": 0.99,
+      "step": 101,
+      "total_flos": 5.556156411097907e+16,
+      "train_loss": 0.358406629228946,
+      "train_runtime": 800.1231,
+      "train_samples_per_second": 4.066,
+      "train_steps_per_second": 0.126
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 101,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 5.556156411097907e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b364c2a141e55b094faf42c78d3d1ca139ada42a4780c3ad12f5e893f115e625
+size 4411