danielgombas/llama_3b_step2_batch_v5

.ipynb_checkpoints/args_v5-checkpoint.txt

@@ -0,0 +1,71 @@
+max_seq_length = 500
+
+def fmt(examples):
+    print(len(examples))
+    return examples
+    
+# 'lora_r' is the dimension of the LoRA attention.
+lora_r = 32
+
+# 'lora_alpha' is the alpha parameter for LoRA scaling.
+lora_alpha = 16
+
+# 'lora_dropout' is the dropout probability for LoRA layers.
+lora_dropout = 0.05
+
+# 'target_modules' is a list of the modules that should be targeted by LoRA.
+target_modules= ['k_proj', 'q_proj', 'v_proj', 'o_proj', "gate_proj", "down_proj", "up_proj"]
+
+# 'se
+
+peft_config = LoraConfig(
+        r=lora_r,
+        lora_alpha=lora_alpha,
+        lora_dropout=lora_dropout,
+        task_type=TaskType.CAUSAL_LM,
+        target_modules=target_modules,
+)
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = qa_dataset['train'],
+    eval_dataset = qa_dataset['test'],
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 4,
+    data_collator = collator,
+    # formatting_func = fmt,
+    # peft_config=peft_config,
+    args = TrainingArguments(
+        per_device_train_batch_size = 8,
+        gradient_checkpointing = True,
+        gradient_accumulation_steps = 4,
+        per_device_eval_batch_size = 40,
+        do_eval = True,
+        eval_strategy = 'steps',
+        eval_steps = 50,
+        # save_strategy = 'steps',
+        save_steps = 1000,
+
+        # Use num_train_epochs and warmup_ratio for longer runs!
+        # max_steps = 70,
+        # warmup_steps = 10,
+        # warmup_ratio = 0.1,
+        num_train_epochs = 2,
+
+        # Select a 2 to 10x smaller learning rate for the embedding matrices!
+        learning_rate = 3e-5,
+        # embedding_learning_rate = 1e-6,
+
+        # fp16 = not is_bfloat16_supported(),
+        bf16 = True,
+        logging_steps = 1,
+        optim = "adamw_torch",
+        weight_decay = 0.00,
+        lr_scheduler_type = "linear",
+        # seed = 3407,
+
+        output_dir = "llama_3b_step2_batch_v5",
+    ),
+)

README.md

@@ -3,199 +3,71 @@ library_name: transformers
 tags:
 - trl
 - sft
+- generated_from_trainer
+model-index:
+- name: llama_3b_step2_batch_v5
+  results: []
 ---
 
-# Model Card for Model ID
+<!-- 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. -->
 
-<!-- Provide a quick summary of what the model is/does. -->
+# llama_3b_step2_batch_v5
 
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3275
 
+## Model description
 
-## Model Details
+More information needed
 
-### Model Description
+## Intended uses & limitations
 
-<!-- Provide a longer summary of what this model is. -->
+More information needed
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Training and evaluation data
 
-- **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]
+More information needed
 
-### Model Sources [optional]
+## Training procedure
 
-<!-- Provide the basic links for the model. -->
+### Training hyperparameters
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 40
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
 
-## Uses
+### Training results
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9071        | 0.1363 | 50   | 0.8211          |
+| 0.7063        | 0.2727 | 100  | 0.6140          |
+| 0.5548        | 0.4090 | 150  | 0.5100          |
+| 0.3776        | 0.5453 | 200  | 0.4445          |
+| 0.4611        | 0.6817 | 250  | 0.4011          |
+| 0.3701        | 0.8180 | 300  | 0.3742          |
+| 0.325         | 0.9543 | 350  | 0.3529          |
+| 0.2093        | 1.0913 | 400  | 0.3522          |
+| 0.2459        | 1.2277 | 450  | 0.3428          |
+| 0.201         | 1.3640 | 500  | 0.3355          |
+| 0.2741        | 1.5003 | 550  | 0.3312          |
+| 0.2596        | 1.6367 | 600  | 0.3283          |
+| 0.2138        | 1.7730 | 650  | 0.3281          |
+| 0.2181        | 1.9093 | 700  | 0.3275          |
 
-### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Framework versions
 
-[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]
+- Transformers 4.46.1
+- Pytorch 2.1.0+cu118
+- Datasets 3.0.2
+- Tokenizers 0.20.1

args_v5.txt

@@ -0,0 +1,71 @@
+max_seq_length = 500
+
+def fmt(examples):
+    print(len(examples))
+    return examples
+    
+# 'lora_r' is the dimension of the LoRA attention.
+lora_r = 32
+
+# 'lora_alpha' is the alpha parameter for LoRA scaling.
+lora_alpha = 16
+
+# 'lora_dropout' is the dropout probability for LoRA layers.
+lora_dropout = 0.05
+
+# 'target_modules' is a list of the modules that should be targeted by LoRA.
+target_modules= ['k_proj', 'q_proj', 'v_proj', 'o_proj', "gate_proj", "down_proj", "up_proj"]
+
+# 'se
+
+peft_config = LoraConfig(
+        r=lora_r,
+        lora_alpha=lora_alpha,
+        lora_dropout=lora_dropout,
+        task_type=TaskType.CAUSAL_LM,
+        target_modules=target_modules,
+)
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = qa_dataset['train'],
+    eval_dataset = qa_dataset['test'],
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 4,
+    data_collator = collator,
+    # formatting_func = fmt,
+    # peft_config=peft_config,
+    args = TrainingArguments(
+        per_device_train_batch_size = 8,
+        gradient_checkpointing = True,
+        gradient_accumulation_steps = 4,
+        per_device_eval_batch_size = 40,
+        do_eval = True,
+        eval_strategy = 'steps',
+        eval_steps = 50,
+        # save_strategy = 'steps',
+        save_steps = 1000,
+
+        # Use num_train_epochs and warmup_ratio for longer runs!
+        # max_steps = 70,
+        # warmup_steps = 10,
+        # warmup_ratio = 0.1,
+        num_train_epochs = 2,
+
+        # Select a 2 to 10x smaller learning rate for the embedding matrices!
+        learning_rate = 3e-5,
+        # embedding_learning_rate = 1e-6,
+
+        # fp16 = not is_bfloat16_supported(),
+        bf16 = True,
+        logging_steps = 1,
+        optim = "adamw_torch",
+        weight_decay = 0.00,
+        lr_scheduler_type = "linear",
+        # seed = 3407,
+
+        output_dir = "llama_3b_step2_batch_v5",
+    ),
+)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832a30bb60d5864768eaa31f7df7d4cf60ceae4e278aa87b958e9e6ab963fdcd
+size 5240