End of training

README.md

@@ -0,0 +1,55 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: ft-t5-small-on-airlineDB
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhuangc19/cs5740-sp24-assignment-4-Marcozc19/runs/5x48tgtq)
+# ft-t5-small-on-airlineDB
+
+This model is a fine-tuned version of [google t5-small](https://huggingface.co/google t5-small) on the custom airlineDB 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: 0.001
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k",
+    "v",
+    "q",
+    "o"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374486b809f42855d1e39840b69538d3989b2cbda2fc333032b2889c420941d6
+size 1199384

results/README.md

@@ -0,0 +1,55 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: ft-t5-small-on-airlineDB
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhuangc19/cs5740-sp24-assignment-4-Marcozc19/runs/9py0aixw)
+# ft-t5-small-on-airlineDB
+
+This model is a fine-tuned version of [google t5-small](https://huggingface.co/google t5-small) on the airlineDB 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: 0.001
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

results/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o",
+    "k",
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c568945c3f9bdcec2d92bf4cdbb642a7bfb6d77303ea27d46802e7c459f4e649
+size 1199384

results/checkpoint-1057/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+---
+
+# 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 0.12.0

results/checkpoint-1057/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o",
+    "k",
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/checkpoint-1057/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83de5caab9819dc25f6a27fc696a0d5d2ec1516d4017f6fccb6d26c3c303a58
+size 1199384

results/checkpoint-1057/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3682350d4723aba5a0aba5529b623ffdb31ec17eed902de03d193252f620952e
+size 2480314

results/checkpoint-1057/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4595d0dffb8db53339cf57644043c90465cd59790fa5154b6d0d0a44702faa91
+size 14244

results/checkpoint-1057/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1d698ff9783119657ac6524b5e6c6c93c386a4035a4484e25e66e9f616cf41
+size 1064

results/checkpoint-1057/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1057,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0946073793755913,
+      "grad_norm": 1.295289158821106,
+      "learning_rate": 0.0009700409965310628,
+      "loss": 2.3794,
+      "step": 100
+    },
+    {
+      "epoch": 0.1892147587511826,
+      "grad_norm": 0.7961627244949341,
+      "learning_rate": 0.0009385052034058657,
+      "loss": 0.5368,
+      "step": 200
+    },
+    {
+      "epoch": 0.28382213812677387,
+      "grad_norm": 0.8890175223350525,
+      "learning_rate": 0.0009069694102806686,
+      "loss": 0.3488,
+      "step": 300
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 0.5166388154029846,
+      "learning_rate": 0.0008754336171554715,
+      "loss": 0.2712,
+      "step": 400
+    },
+    {
+      "epoch": 0.47303689687795647,
+      "grad_norm": 0.3027492165565491,
+      "learning_rate": 0.0008438978240302744,
+      "loss": 0.2219,
+      "step": 500
+    },
+    {
+      "epoch": 0.5676442762535477,
+      "grad_norm": 0.8666072487831116,
+      "learning_rate": 0.0008123620309050773,
+      "loss": 0.1906,
+      "step": 600
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 0.5293228030204773,
+      "learning_rate": 0.0007808262377798802,
+      "loss": 0.17,
+      "step": 700
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 0.33755800127983093,
+      "learning_rate": 0.0007492904446546831,
+      "loss": 0.1506,
+      "step": 800
+    },
+    {
+      "epoch": 0.8514664143803217,
+      "grad_norm": 0.3760841190814972,
+      "learning_rate": 0.000717754651529486,
+      "loss": 0.142,
+      "step": 900
+    },
+    {
+      "epoch": 0.9460737937559129,
+      "grad_norm": 0.3145512044429779,
+      "learning_rate": 0.0006862188584042889,
+      "loss": 0.1256,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3171,
+  "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": 67458613248000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-1057/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f7dde84818f75721a88170f7e2d2127b908903ae73bb2ec9b7170b73a4470c
+size 5240

results/checkpoint-2114/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+---
+
+# 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 0.12.0

results/checkpoint-2114/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o",
+    "k",
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/checkpoint-2114/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaad80948f1b2edacc85ad652714556078357645155cf6ff5a34e04882e873cf
+size 1199384

results/checkpoint-2114/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c45b2df0f2ed170e5fbe6f9f5fb63d2d11d3a12815fad0d0d2f811fe5c92d9
+size 2480314

results/checkpoint-2114/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcf00c933e04673a9247271751f41e3ca6c6d65a93a85d06fcc2d0ecf65aca8
+size 14244

results/checkpoint-2114/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89500c61ce65eb431d9707fbc1dc1f5975a18b8f728a76d2332f712ac51b64f5
+size 1064

results/checkpoint-2114/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0946073793755913,
+      "grad_norm": 1.295289158821106,
+      "learning_rate": 0.0009700409965310628,
+      "loss": 2.3794,
+      "step": 100
+    },
+    {
+      "epoch": 0.1892147587511826,
+      "grad_norm": 0.7961627244949341,
+      "learning_rate": 0.0009385052034058657,
+      "loss": 0.5368,
+      "step": 200
+    },
+    {
+      "epoch": 0.28382213812677387,
+      "grad_norm": 0.8890175223350525,
+      "learning_rate": 0.0009069694102806686,
+      "loss": 0.3488,
+      "step": 300
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 0.5166388154029846,
+      "learning_rate": 0.0008754336171554715,
+      "loss": 0.2712,
+      "step": 400
+    },
+    {
+      "epoch": 0.47303689687795647,
+      "grad_norm": 0.3027492165565491,
+      "learning_rate": 0.0008438978240302744,
+      "loss": 0.2219,
+      "step": 500
+    },
+    {
+      "epoch": 0.5676442762535477,
+      "grad_norm": 0.8666072487831116,
+      "learning_rate": 0.0008123620309050773,
+      "loss": 0.1906,
+      "step": 600
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 0.5293228030204773,
+      "learning_rate": 0.0007808262377798802,
+      "loss": 0.17,
+      "step": 700
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 0.33755800127983093,
+      "learning_rate": 0.0007492904446546831,
+      "loss": 0.1506,
+      "step": 800
+    },
+    {
+      "epoch": 0.8514664143803217,
+      "grad_norm": 0.3760841190814972,
+      "learning_rate": 0.000717754651529486,
+      "loss": 0.142,
+      "step": 900
+    },
+    {
+      "epoch": 0.9460737937559129,
+      "grad_norm": 0.3145512044429779,
+      "learning_rate": 0.0006862188584042889,
+      "loss": 0.1256,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0406811731315042,
+      "grad_norm": 0.47477108240127563,
+      "learning_rate": 0.0006546830652790918,
+      "loss": 0.1225,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1352885525070955,
+      "grad_norm": 0.3582330644130707,
+      "learning_rate": 0.0006231472721538947,
+      "loss": 0.1148,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2298959318826868,
+      "grad_norm": 0.4500308036804199,
+      "learning_rate": 0.0005916114790286976,
+      "loss": 0.1148,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "grad_norm": 0.2415657341480255,
+      "learning_rate": 0.0005600756859035005,
+      "loss": 0.0934,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4191106906338695,
+      "grad_norm": 0.49272701144218445,
+      "learning_rate": 0.0005285398927783034,
+      "loss": 0.098,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5137180700094608,
+      "grad_norm": 0.28604432940483093,
+      "learning_rate": 0.0004970040996531063,
+      "loss": 0.1056,
+      "step": 1600
+    },
+    {
+      "epoch": 1.608325449385052,
+      "grad_norm": 0.4883616864681244,
+      "learning_rate": 0.00046546830652790914,
+      "loss": 0.0992,
+      "step": 1700
+    },
+    {
+      "epoch": 1.7029328287606433,
+      "grad_norm": 0.42010796070098877,
+      "learning_rate": 0.0004339325134027121,
+      "loss": 0.0879,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7975402081362346,
+      "grad_norm": 0.23443974554538727,
+      "learning_rate": 0.000402396720277515,
+      "loss": 0.0906,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8921475875118259,
+      "grad_norm": 0.6164644956588745,
+      "learning_rate": 0.0003708609271523179,
+      "loss": 0.0834,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "grad_norm": 0.36332041025161743,
+      "learning_rate": 0.0003393251340271208,
+      "loss": 0.0798,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3171,
+  "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": 134917226496000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-2114/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f7dde84818f75721a88170f7e2d2127b908903ae73bb2ec9b7170b73a4470c
+size 5240

results/checkpoint-265/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+---
+
+# 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 0.12.0

results/checkpoint-265/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "k",
+    "v",
+    "o"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/checkpoint-265/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e614aed572a83014ceff43aa5bda26dbc54bd3d7087b5019502ff699d2577e
+size 1199384

results/checkpoint-265/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec07c3f37a128a61ef451f9d68e2169e14ecd0f2dd0dc11d204a9b732186fa0
+size 2480314

results/checkpoint-265/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4efc1c84570c1f37c60021d020cee9fe6842e559d078a6a47efc1f12909fa83
+size 14244

results/checkpoint-265/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f7bb543b34b34820e83a4339e9306919d882eeed823fc8446fe03a0a083b74
+size 1064

results/checkpoint-265/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.411266952753067,
+      "learning_rate": 0.0008742138364779874,
+      "loss": 1.6882,
+      "step": 100
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.48857933282852173,
+      "learning_rate": 0.0007484276729559748,
+      "loss": 0.4202,
+      "step": 200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 795,
+  "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": 67969542389760.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-265/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c316e4e618671cd6106e40e33581b641f0e32194491830e31f5e903937b00c
+size 5240

results/checkpoint-3171/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+---
+
+# 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 0.12.0

results/checkpoint-3171/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o",
+    "k",
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/checkpoint-3171/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c568945c3f9bdcec2d92bf4cdbb642a7bfb6d77303ea27d46802e7c459f4e649
+size 1199384

results/checkpoint-3171/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8591971686db9b368143b3d1eff2624a2e8e6abb8226bf2c7c4bbfa5b48612
+size 2480314

results/checkpoint-3171/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be3cbaba13f3d9edaa84c7444d9a4c7dbe3e235be1aa4e7b76dc12c453641ea
+size 14244

results/checkpoint-3171/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d2492f713da91e38614bd570dec9066e528d8159a11db6db2366fbbede8a42
+size 1064

results/checkpoint-3171/trainer_state.json

@@ -0,0 +1,250 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0946073793755913,
+      "grad_norm": 1.295289158821106,
+      "learning_rate": 0.0009700409965310628,
+      "loss": 2.3794,
+      "step": 100
+    },
+    {
+      "epoch": 0.1892147587511826,
+      "grad_norm": 0.7961627244949341,
+      "learning_rate": 0.0009385052034058657,
+      "loss": 0.5368,
+      "step": 200
+    },
+    {
+      "epoch": 0.28382213812677387,
+      "grad_norm": 0.8890175223350525,
+      "learning_rate": 0.0009069694102806686,
+      "loss": 0.3488,
+      "step": 300
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 0.5166388154029846,
+      "learning_rate": 0.0008754336171554715,
+      "loss": 0.2712,
+      "step": 400
+    },
+    {
+      "epoch": 0.47303689687795647,
+      "grad_norm": 0.3027492165565491,
+      "learning_rate": 0.0008438978240302744,
+      "loss": 0.2219,
+      "step": 500
+    },
+    {
+      "epoch": 0.5676442762535477,
+      "grad_norm": 0.8666072487831116,
+      "learning_rate": 0.0008123620309050773,
+      "loss": 0.1906,
+      "step": 600
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 0.5293228030204773,
+      "learning_rate": 0.0007808262377798802,
+      "loss": 0.17,
+      "step": 700
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 0.33755800127983093,
+      "learning_rate": 0.0007492904446546831,
+      "loss": 0.1506,
+      "step": 800
+    },
+    {
+      "epoch": 0.8514664143803217,
+      "grad_norm": 0.3760841190814972,
+      "learning_rate": 0.000717754651529486,
+      "loss": 0.142,
+      "step": 900
+    },
+    {
+      "epoch": 0.9460737937559129,
+      "grad_norm": 0.3145512044429779,
+      "learning_rate": 0.0006862188584042889,
+      "loss": 0.1256,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0406811731315042,
+      "grad_norm": 0.47477108240127563,
+      "learning_rate": 0.0006546830652790918,
+      "loss": 0.1225,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1352885525070955,
+      "grad_norm": 0.3582330644130707,
+      "learning_rate": 0.0006231472721538947,
+      "loss": 0.1148,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2298959318826868,
+      "grad_norm": 0.4500308036804199,
+      "learning_rate": 0.0005916114790286976,
+      "loss": 0.1148,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "grad_norm": 0.2415657341480255,
+      "learning_rate": 0.0005600756859035005,
+      "loss": 0.0934,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4191106906338695,
+      "grad_norm": 0.49272701144218445,
+      "learning_rate": 0.0005285398927783034,
+      "loss": 0.098,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5137180700094608,
+      "grad_norm": 0.28604432940483093,
+      "learning_rate": 0.0004970040996531063,
+      "loss": 0.1056,
+      "step": 1600
+    },
+    {
+      "epoch": 1.608325449385052,
+      "grad_norm": 0.4883616864681244,
+      "learning_rate": 0.00046546830652790914,
+      "loss": 0.0992,
+      "step": 1700
+    },
+    {
+      "epoch": 1.7029328287606433,
+      "grad_norm": 0.42010796070098877,
+      "learning_rate": 0.0004339325134027121,
+      "loss": 0.0879,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7975402081362346,
+      "grad_norm": 0.23443974554538727,
+      "learning_rate": 0.000402396720277515,
+      "loss": 0.0906,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8921475875118259,
+      "grad_norm": 0.6164644956588745,
+      "learning_rate": 0.0003708609271523179,
+      "loss": 0.0834,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "grad_norm": 0.36332041025161743,
+      "learning_rate": 0.0003393251340271208,
+      "loss": 0.0798,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0813623462630084,
+      "grad_norm": 0.3371862769126892,
+      "learning_rate": 0.00030778934090192365,
+      "loss": 0.0893,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1759697256385997,
+      "grad_norm": 0.2492402046918869,
+      "learning_rate": 0.00027625354777672655,
+      "loss": 0.0768,
+      "step": 2300
+    },
+    {
+      "epoch": 2.270577105014191,
+      "grad_norm": 0.34287121891975403,
+      "learning_rate": 0.00024503311258278145,
+      "loss": 0.0776,
+      "step": 2400
+    },
+    {
+      "epoch": 2.3651844843897822,
+      "grad_norm": 0.4034591615200043,
+      "learning_rate": 0.00021349731945758435,
+      "loss": 0.0717,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4597918637653735,
+      "grad_norm": 0.3876320719718933,
+      "learning_rate": 0.00018196152633238728,
+      "loss": 0.0762,
+      "step": 2600
+    },
+    {
+      "epoch": 2.5543992431409652,
+      "grad_norm": 0.16697722673416138,
+      "learning_rate": 0.00015042573320719015,
+      "loss": 0.0688,
+      "step": 2700
+    },
+    {
+      "epoch": 2.6490066225165565,
+      "grad_norm": 0.32368209958076477,
+      "learning_rate": 0.00011888994008199306,
+      "loss": 0.0728,
+      "step": 2800
+    },
+    {
+      "epoch": 2.7436140018921478,
+      "grad_norm": 0.4008019268512726,
+      "learning_rate": 8.735414695679597e-05,
+      "loss": 0.0756,
+      "step": 2900
+    },
+    {
+      "epoch": 2.838221381267739,
+      "grad_norm": 0.25073108077049255,
+      "learning_rate": 5.581835383159887e-05,
+      "loss": 0.0766,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9328287606433303,
+      "grad_norm": 0.3861249089241028,
+      "learning_rate": 2.4282560706401765e-05,
+      "loss": 0.0717,
+      "step": 3100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3171,
+  "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": 202375839744000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-3171/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f7dde84818f75721a88170f7e2d2127b908903ae73bb2ec9b7170b73a4470c
+size 5240

results/checkpoint-530/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-t5/t5-small
+library_name: peft
+---
+
+# 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 0.12.0

results/checkpoint-530/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-t5/t5-small",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "k",
+    "v",
+    "o"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

results/checkpoint-530/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7a5783f6663cd9e93c8127b471097e9d733b6d473e492145cebc6ce7c12ee6
+size 1199384

results/checkpoint-530/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6150428e20a12ed7548d5a0498abffc48c96b926485e6a64b4fad5a746ecfcfa
+size 2480314

results/checkpoint-530/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1f4cff1dd85f07f45b41b1a931b96aaa60b98d6a80c2ab2222c15fa1315909
+size 14244

results/checkpoint-530/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9108b090300af471d2224d25a6df1144b4c8a5099b5c56d0a68d1c25734f974
+size 1064

results/checkpoint-530/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.411266952753067,
+      "learning_rate": 0.0008742138364779874,
+      "loss": 1.6882,
+      "step": 100
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.48857933282852173,
+      "learning_rate": 0.0007484276729559748,
+      "loss": 0.4202,
+      "step": 200
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 0.2623351216316223,
+      "learning_rate": 0.0006226415094339623,
+      "loss": 0.2593,
+      "step": 300
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.36103516817092896,
+      "learning_rate": 0.0004968553459119497,
+      "loss": 0.2006,
+      "step": 400
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 0.41828280687332153,
+      "learning_rate": 0.0003710691823899371,
+      "loss": 0.17,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 795,
+  "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": 135428155637760.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-530/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c316e4e618671cd6106e40e33581b641f0e32194491830e31f5e903937b00c
+size 5240

results/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f7dde84818f75721a88170f7e2d2127b908903ae73bb2ec9b7170b73a4470c
+size 5240

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aac27e60fbb62fb27e0f5513630c5fa73b2bc840cbc985370619c7d9206d7fe
+size 5240