danielgombas/llama_3b_step2_batch_v2

.ipynb_checkpoints/args_v2-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 = 2,
+        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_v2",
+    ),
+)

README.md

@@ -3,199 +3,115 @@ library_name: transformers
 tags:
 - trl
 - sft
+- generated_from_trainer
+model-index:
+- name: llama_3b_step2_batch_v2
+  results: []
 ---
 
-# 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. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **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]
+<!-- 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. -->
+
+# llama_3b_step2_batch_v2
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3132
+
+## 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 40
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- 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
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.993         | 0.0341 | 50   | 1.1011          |
+| 1.0449        | 0.0682 | 100  | 0.9752          |
+| 0.9894        | 0.1023 | 150  | 0.8698          |
+| 0.6199        | 0.1364 | 200  | 0.7913          |
+| 0.5326        | 0.1704 | 250  | 0.7341          |
+| 0.8109        | 0.2045 | 300  | 0.6799          |
+| 0.7554        | 0.2386 | 350  | 0.6332          |
+| 0.9877        | 0.2727 | 400  | 0.5993          |
+| 0.3571        | 0.3068 | 450  | 0.5726          |
+| 0.4539        | 0.3409 | 500  | 0.5439          |
+| 0.464         | 0.3750 | 550  | 0.5147          |
+| 0.4051        | 0.4091 | 600  | 0.4904          |
+| 0.5371        | 0.4432 | 650  | 0.4732          |
+| 0.4954        | 0.4772 | 700  | 0.4549          |
+| 0.4594        | 0.5113 | 750  | 0.4399          |
+| 0.4755        | 0.5454 | 800  | 0.4281          |
+| 0.2948        | 0.5795 | 850  | 0.4118          |
+| 0.3699        | 0.6136 | 900  | 0.4021          |
+| 0.319         | 0.6477 | 950  | 0.3927          |
+| 0.3359        | 0.6818 | 1000 | 0.3802          |
+| 0.4056        | 0.7159 | 1050 | 0.3746          |
+| 0.2975        | 0.7500 | 1100 | 0.3643          |
+| 0.3868        | 0.7840 | 1150 | 0.3596          |
+| 0.3485        | 0.8181 | 1200 | 0.3512          |
+| 0.3546        | 0.8522 | 1250 | 0.3476          |
+| 0.3697        | 0.8863 | 1300 | 0.3416          |
+| 0.4056        | 0.9204 | 1350 | 0.3388          |
+| 0.3189        | 0.9545 | 1400 | 0.3332          |
+| 0.4173        | 0.9886 | 1450 | 0.3286          |
+| 0.1779        | 1.0228 | 1500 | 0.3338          |
+| 0.2877        | 1.0569 | 1550 | 0.3300          |
+| 0.1506        | 1.0910 | 1600 | 0.3301          |
+| 0.2075        | 1.1251 | 1650 | 0.3289          |
+| 0.1956        | 1.1592 | 1700 | 0.3271          |
+| 0.162         | 1.1933 | 1750 | 0.3276          |
+| 0.2416        | 1.2274 | 1800 | 0.3228          |
+| 0.2364        | 1.2615 | 1850 | 0.3243          |
+| 0.1602        | 1.2956 | 1900 | 0.3219          |
+| 0.1566        | 1.3296 | 1950 | 0.3211          |
+| 0.1784        | 1.3637 | 2000 | 0.3215          |
+| 0.1627        | 1.3978 | 2050 | 0.3190          |
+| 0.1907        | 1.4319 | 2100 | 0.3183          |
+| 0.1182        | 1.4660 | 2150 | 0.3183          |
+| 0.1585        | 1.5001 | 2200 | 0.3179          |
+| 0.2261        | 1.5342 | 2250 | 0.3158          |
+| 0.1457        | 1.5683 | 2300 | 0.3150          |
+| 0.2589        | 1.6024 | 2350 | 0.3146          |
+| 0.2253        | 1.6364 | 2400 | 0.3144          |
+| 0.1741        | 1.6705 | 2450 | 0.3143          |
+| 0.1477        | 1.7046 | 2500 | 0.3141          |
+| 0.1886        | 1.7387 | 2550 | 0.3141          |
+| 0.2211        | 1.7728 | 2600 | 0.3139          |
+| 0.238         | 1.8069 | 2650 | 0.3138          |
+| 0.2863        | 1.8410 | 2700 | 0.3137          |
+| 0.2603        | 1.8751 | 2750 | 0.3135          |
+| 0.2484        | 1.9092 | 2800 | 0.3133          |
+| 0.2343        | 1.9432 | 2850 | 0.3132          |
+| 0.254         | 1.9773 | 2900 | 0.3132          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.1.0+cu118
+- Datasets 3.0.2
+- Tokenizers 0.20.1

args_v2.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 = 2,
+        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_v2",
+    ),
+)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa39175d2ef0b886e4b9dd3b7b39382be9b1e33a3d2acf2ab7666712e70893d
+size 5240