Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/full_training_llama3/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/full_training_llama3/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/full_training_llama3/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+openbiollm_8b_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text

biomistral_7b_dare_lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: BioMistral/BioMistral-7B-DARE
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:BioMistral/BioMistral-7B-DARE
+- lora
+- transformers
+---
+
+# 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 0.18.1

biomistral_7b_dare_lora/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

biomistral_7b_dare_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e626522ead10840dd0205c4a8d4a16585ae5cff9399f651c8ae0d07018c134e1
+size 109086416

biomistral_7b_dare_lora/chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}

biomistral_7b_dare_lora/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/full_training_biomistral/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: BioMistral/BioMistral-7B-DARE
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:BioMistral/BioMistral-7B-DARE
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoints/full_training_biomistral/checkpoint-1000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoints/full_training_biomistral/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e626522ead10840dd0205c4a8d4a16585ae5cff9399f651c8ae0d07018c134e1
+size 109086416

checkpoints/full_training_biomistral/checkpoint-1000/chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}

checkpoints/full_training_biomistral/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342c3bb60fe210ec0dcbedd20dc882b3dc829dbe2a2a05ed3e97f2037b52ae86
+size 218319354

checkpoints/full_training_biomistral/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a544c2f9a8602913206edd2eaf54e3bccce3166803be74b3cf45eef30172ea
+size 14244

checkpoints/full_training_biomistral/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63166ffadf6296a0da805a3a8d95a4bfb5a5180d9cca577f1e1e14a43a42260
+size 1064

checkpoints/full_training_biomistral/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/full_training_biomistral/checkpoint-1000/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.6868895888328552,
+  "best_model_checkpoint": "/workspace/medisimplifier/checkpoints/full_training_biomistral/checkpoint-1000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4177701473236084,
+      "learning_rate": 0.00019999627041039135,
+      "loss": 0.8399433898925781,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.3435115814208984,
+      "learning_rate": 0.00019932104775631846,
+      "loss": 0.7292498016357422,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3991986513137817,
+      "learning_rate": 0.00019748935819749987,
+      "loss": 0.7462101745605468,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5255440473556519,
+      "learning_rate": 0.0001945225294222997,
+      "loss": 0.7331835174560547,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4309399127960205,
+      "learning_rate": 0.0001904551063672452,
+      "loss": 0.7239613342285156,
+      "step": 250
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4074270725250244,
+      "learning_rate": 0.0001853344489853074,
+      "loss": 0.7315120697021484,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4281959533691406,
+      "learning_rate": 0.0001792201807996622,
+      "loss": 0.7249378967285156,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5213158130645752,
+      "learning_rate": 0.00017218349466382023,
+      "loss": 0.7271736907958984,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2553246021270752,
+      "learning_rate": 0.00016430632381166305,
+      "loss": 0.7179476165771485,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2599660158157349,
+      "learning_rate": 0.00015568038784945077,
+      "loss": 0.7246416473388672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7085821032524109,
+      "eval_runtime": 84.7026,
+      "eval_samples_per_second": 11.794,
+      "eval_steps_per_second": 2.952,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.2058591842651367,
+      "learning_rate": 0.00014640612479800686,
+      "loss": 0.6286650466918945,
+      "step": 550
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2758371829986572,
+      "learning_rate": 0.00013659152162008676,
+      "loss": 0.6379350280761719,
+      "step": 600
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.2779815196990967,
+      "learning_rate": 0.00012635085684994767,
+      "loss": 0.6482433319091797,
+      "step": 650
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.2724528312683105,
+      "learning_rate": 0.00011580336996559343,
+      "loss": 0.6435096740722657,
+      "step": 700
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.2503466606140137,
+      "learning_rate": 0.00010507187299715815,
+      "loss": 0.6361804962158203,
+      "step": 750
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.309194803237915,
+      "learning_rate": 9.428132053747712e-05,
+      "loss": 0.636002197265625,
+      "step": 800
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.2687519788742065,
+      "learning_rate": 8.355735480524874e-05,
+      "loss": 0.6357472229003907,
+      "step": 850
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0980808734893799,
+      "learning_rate": 7.30248427016697e-05,
+      "loss": 0.6348814010620117,
+      "step": 900
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.15554678440094,
+      "learning_rate": 6.28064218946542e-05,
+      "loss": 0.6314722061157226,
+      "step": 950
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1698943376541138,
+      "learning_rate": 5.302107285963045e-05,
+      "loss": 0.6311819076538085,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6868895888328552,
+      "eval_runtime": 84.5159,
+      "eval_samples_per_second": 11.82,
+      "eval_steps_per_second": 2.958,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4031973577423585e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/full_training_biomistral/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6639d9fd4a2b337584447a5bbe411991aadcadc50dc40e7273e44bf4f7c0db
+size 4856

checkpoints/full_training_biomistral/checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: BioMistral/BioMistral-7B-DARE
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:BioMistral/BioMistral-7B-DARE
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoints/full_training_biomistral/checkpoint-1500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoints/full_training_biomistral/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed249e88d1c3fe3efb020c486d1b026f370a8d1d981212ae38d0a166d6566b25
+size 109086416

checkpoints/full_training_biomistral/checkpoint-1500/chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}

checkpoints/full_training_biomistral/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26bf6a027ac71c17a603052d8942ff26cd124e7e4c7de55bedd1f2d3fc31daf
+size 218319354

checkpoints/full_training_biomistral/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe1978919374efd0997761c05a94ff338f4b8cf5e6d9ae89736c3885b082711
+size 14244

checkpoints/full_training_biomistral/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4e625cf5525cf235a8c7e4c6984ba05d1b5436f9e969799dcec0119a3a6c2a
+size 1064

checkpoints/full_training_biomistral/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/full_training_biomistral/checkpoint-1500/trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.6868895888328552,
+  "best_model_checkpoint": "/workspace/medisimplifier/checkpoints/full_training_biomistral/checkpoint-1000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4177701473236084,
+      "learning_rate": 0.00019999627041039135,
+      "loss": 0.8399433898925781,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.3435115814208984,
+      "learning_rate": 0.00019932104775631846,
+      "loss": 0.7292498016357422,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3991986513137817,
+      "learning_rate": 0.00019748935819749987,
+      "loss": 0.7462101745605468,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5255440473556519,
+      "learning_rate": 0.0001945225294222997,
+      "loss": 0.7331835174560547,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4309399127960205,
+      "learning_rate": 0.0001904551063672452,
+      "loss": 0.7239613342285156,
+      "step": 250
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4074270725250244,
+      "learning_rate": 0.0001853344489853074,
+      "loss": 0.7315120697021484,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4281959533691406,
+      "learning_rate": 0.0001792201807996622,
+      "loss": 0.7249378967285156,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5213158130645752,
+      "learning_rate": 0.00017218349466382023,
+      "loss": 0.7271736907958984,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2553246021270752,
+      "learning_rate": 0.00016430632381166305,
+      "loss": 0.7179476165771485,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2599660158157349,
+      "learning_rate": 0.00015568038784945077,
+      "loss": 0.7246416473388672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7085821032524109,
+      "eval_runtime": 84.7026,
+      "eval_samples_per_second": 11.794,
+      "eval_steps_per_second": 2.952,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.2058591842651367,
+      "learning_rate": 0.00014640612479800686,
+      "loss": 0.6286650466918945,
+      "step": 550
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2758371829986572,
+      "learning_rate": 0.00013659152162008676,
+      "loss": 0.6379350280761719,
+      "step": 600
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.2779815196990967,
+      "learning_rate": 0.00012635085684994767,
+      "loss": 0.6482433319091797,
+      "step": 650
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.2724528312683105,
+      "learning_rate": 0.00011580336996559343,
+      "loss": 0.6435096740722657,
+      "step": 700
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.2503466606140137,
+      "learning_rate": 0.00010507187299715815,
+      "loss": 0.6361804962158203,
+      "step": 750
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.309194803237915,
+      "learning_rate": 9.428132053747712e-05,
+      "loss": 0.636002197265625,
+      "step": 800
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.2687519788742065,
+      "learning_rate": 8.355735480524874e-05,
+      "loss": 0.6357472229003907,
+      "step": 850
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0980808734893799,
+      "learning_rate": 7.30248427016697e-05,
+      "loss": 0.6348814010620117,
+      "step": 900
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.15554678440094,
+      "learning_rate": 6.28064218946542e-05,
+      "loss": 0.6314722061157226,
+      "step": 950
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1698943376541138,
+      "learning_rate": 5.302107285963045e-05,
+      "loss": 0.6311819076538085,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6868895888328552,
+      "eval_runtime": 84.5159,
+      "eval_samples_per_second": 11.82,
+      "eval_steps_per_second": 2.958,
+      "step": 1000
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.143906831741333,
+      "learning_rate": 4.3782733503678886e-05,
+      "loss": 0.5183572387695312,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.314713954925537,
+      "learning_rate": 3.519897250394612e-05,
+      "loss": 0.5180675888061523,
+      "step": 1100
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.205331563949585,
+      "learning_rate": 2.736973680761702e-05,
+      "loss": 0.5105087280273437,
+      "step": 1150
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1719871759414673,
+      "learning_rate": 2.038618787720925e-05,
+      "loss": 0.5108313751220703,
+      "step": 1200
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1759802103042603,
+      "learning_rate": 1.432964023163028e-05,
+      "loss": 0.5100440216064454,
+      "step": 1250
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.2717361450195312,
+      "learning_rate": 9.270614642331376e-06,
+      "loss": 0.5174772262573242,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.2481423616409302,
+      "learning_rate": 5.2680170088822425e-06,
+      "loss": 0.5131646347045898,
+      "step": 1350
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.1682120561599731,
+      "learning_rate": 2.368452474912153e-06,
+      "loss": 0.5116761398315429,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.1784641742706299,
+      "learning_rate": 6.056827706632185e-07,
+      "loss": 0.5085794448852539,
+      "step": 1450
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2798943519592285,
+      "learning_rate": 2.331007089351189e-10,
+      "loss": 0.5112796020507813,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7085273265838623,
+      "eval_runtime": 83.6901,
+      "eval_samples_per_second": 11.937,
+      "eval_steps_per_second": 2.987,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.1047960366135378e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/full_training_biomistral/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6639d9fd4a2b337584447a5bbe411991aadcadc50dc40e7273e44bf4f7c0db
+size 4856

checkpoints/full_training_biomistral/checkpoint-500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: BioMistral/BioMistral-7B-DARE
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:BioMistral/BioMistral-7B-DARE
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoints/full_training_biomistral/checkpoint-500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoints/full_training_biomistral/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6204323279992b5c6fc2d24fdf2cef27faf3b6209f63d0f038340aab19d82cf3
+size 109086416

checkpoints/full_training_biomistral/checkpoint-500/chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}

checkpoints/full_training_biomistral/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5babf7fee2a33830ebd6390a7642c28c3f37d27eeeff16bf1466c4c101f4f6d6
+size 218319354

checkpoints/full_training_biomistral/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c596492a018c7cef2dbfd1400a84c1995bd96ea69ea212fb61301f598a2a0389
+size 14244

checkpoints/full_training_biomistral/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0485de3bea4b3789196b8fb2a33f53fc4c078162cb5a4ba28365ffa6c77e3227
+size 1064

checkpoints/full_training_biomistral/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/full_training_biomistral/checkpoint-500/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.7085821032524109,
+  "best_model_checkpoint": "/workspace/medisimplifier/checkpoints/full_training_biomistral/checkpoint-500",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4177701473236084,
+      "learning_rate": 0.00019999627041039135,
+      "loss": 0.8399433898925781,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.3435115814208984,
+      "learning_rate": 0.00019932104775631846,
+      "loss": 0.7292498016357422,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3991986513137817,
+      "learning_rate": 0.00019748935819749987,
+      "loss": 0.7462101745605468,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5255440473556519,
+      "learning_rate": 0.0001945225294222997,
+      "loss": 0.7331835174560547,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4309399127960205,
+      "learning_rate": 0.0001904551063672452,
+      "loss": 0.7239613342285156,
+      "step": 250
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4074270725250244,
+      "learning_rate": 0.0001853344489853074,
+      "loss": 0.7315120697021484,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4281959533691406,
+      "learning_rate": 0.0001792201807996622,
+      "loss": 0.7249378967285156,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5213158130645752,
+      "learning_rate": 0.00017218349466382023,
+      "loss": 0.7271736907958984,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2553246021270752,
+      "learning_rate": 0.00016430632381166305,
+      "loss": 0.7179476165771485,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2599660158157349,
+      "learning_rate": 0.00015568038784945077,
+      "loss": 0.7246416473388672,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7085821032524109,
+      "eval_runtime": 84.7026,
+      "eval_samples_per_second": 11.794,
+      "eval_steps_per_second": 2.952,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.015986788711793e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/full_training_biomistral/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6639d9fd4a2b337584447a5bbe411991aadcadc50dc40e7273e44bf4f7c0db
+size 4856

checkpoints/full_training_llama3/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: aaditya/Llama3-OpenBioLLM-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:aaditya/Llama3-OpenBioLLM-8B
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoints/full_training_llama3/checkpoint-1000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "aaditya/Llama3-OpenBioLLM-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoints/full_training_llama3/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676984272154d3537892057467a9bbd6fe05e2ac42e9f97aa7f1cfcd7f3cb950
+size 109086416

checkpoints/full_training_llama3/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058e89dd803e7a7d84565464fabc716a3cef759cb574e32e38db4a4f31106686
+size 218319354

checkpoints/full_training_llama3/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a544c2f9a8602913206edd2eaf54e3bccce3166803be74b3cf45eef30172ea
+size 14244

checkpoints/full_training_llama3/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63166ffadf6296a0da805a3a8d95a4bfb5a5180d9cca577f1e1e14a43a42260
+size 1064

checkpoints/full_training_llama3/checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534938d96e8bc525762c02c60dcbca48974ec7fb23ccf0072ff76d3ac61e7783
+size 17209036

checkpoints/full_training_llama3/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoints/full_training_llama3/checkpoint-1000/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.765940248966217,
+  "best_model_checkpoint": "/workspace/medisimplifier/checkpoints/full_training_llama3/checkpoint-1000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8529252409934998,
+      "learning_rate": 0.00019999627041039135,
+      "loss": 1.0474996948242188,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7320457100868225,
+      "learning_rate": 0.00019932104775631846,
+      "loss": 0.8225428771972656,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.7186092138290405,
+      "learning_rate": 0.00019748935819749987,
+      "loss": 0.8300324249267578,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7772836685180664,
+      "learning_rate": 0.0001945225294222997,
+      "loss": 0.8121639251708984,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7707756757736206,
+      "learning_rate": 0.0001904551063672452,
+      "loss": 0.7978531646728516,
+      "step": 250
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6957331895828247,
+      "learning_rate": 0.0001853344489853074,
+      "loss": 0.8011433410644532,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.7072925567626953,
+      "learning_rate": 0.0001792201807996622,
+      "loss": 0.7936522674560547,
+      "step": 350
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6817747950553894,
+      "learning_rate": 0.00017218349466382023,
+      "loss": 0.7956649017333984,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6376733779907227,
+      "learning_rate": 0.00016430632381166305,
+      "loss": 0.7857054901123047,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6680275201797485,
+      "learning_rate": 0.00015568038784945077,
+      "loss": 0.7932262420654297,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7795636057853699,
+      "eval_runtime": 87.6111,
+      "eval_samples_per_second": 11.403,
+      "eval_steps_per_second": 2.854,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.6502048373222351,
+      "learning_rate": 0.00014640612479800686,
+      "loss": 0.7020484924316406,
+      "step": 550
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7146771550178528,
+      "learning_rate": 0.00013659152162008676,
+      "loss": 0.7077577972412109,
+      "step": 600
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.6823922991752625,
+      "learning_rate": 0.00012635085684994767,
+      "loss": 0.7162642669677735,
+      "step": 650
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7355015873908997,
+      "learning_rate": 0.00011580336996559343,
+      "loss": 0.7105405426025391,
+      "step": 700
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.6940415501594543,
+      "learning_rate": 0.00010507187299715815,
+      "loss": 0.7042336273193359,
+      "step": 750
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7427050471305847,
+      "learning_rate": 9.428132053747712e-05,
+      "loss": 0.7039394378662109,
+      "step": 800
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.6916703581809998,
+      "learning_rate": 8.355735480524874e-05,
+      "loss": 0.7027620697021484,
+      "step": 850
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6551830172538757,
+      "learning_rate": 7.30248427016697e-05,
+      "loss": 0.7022518920898437,
+      "step": 900
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.7114452719688416,
+      "learning_rate": 6.28064218946542e-05,
+      "loss": 0.7016622924804687,
+      "step": 950
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7508624792098999,
+      "learning_rate": 5.302107285963045e-05,
+      "loss": 0.7013800048828125,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.765940248966217,
+      "eval_runtime": 87.598,
+      "eval_samples_per_second": 11.404,
+      "eval_steps_per_second": 2.854,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4807032380543468e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/full_training_llama3/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1069c5fea6c3bfef207c84dcf470113aca494113b4783981afb5c04afd26adb5
+size 4856