Add lv-LV (haryos_model_loras)

.gitattributes

@@ -60,3 +60,4 @@ ka-GE/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 km-KH/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 kn-IN/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ko-KR/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lv-LV/tokenizer.json filter=lfs diff=lfs merge=lfs -text

lv-LV/README.md

@@ -0,0 +1,206 @@
+---
+base_model: FacebookAI/xlm-roberta-base
+library_name: peft
+tags:
+- base_model:adapter:FacebookAI/xlm-roberta-base
+- 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

lv-LV/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "FacebookAI/xlm-roberta-base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lv-LV/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e374a15351503a7966ef819b675d9e7b7635cd9e1240146cd573d556f1d1cd6
+size 4913608

lv-LV/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.807673389080177,
+    "eval_f1": 0.8020280975121211,
+    "eval_loss": 0.7037608027458191,
+    "eval_runtime": 0.708,
+    "eval_samples": 2033,
+    "eval_samples_per_second": 2871.533,
+    "eval_steps_per_second": 45.199,
+    "total_flos": 3843028539002880.0,
+    "train_loss": 1.2955143038431804,
+    "train_runtime": 69.0404,
+    "train_samples": 11514,
+    "train_samples_per_second": 833.86,
+    "train_steps_per_second": 26.072
+}

lv-LV/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.807673389080177,
+    "eval_f1": 0.8020280975121211,
+    "eval_loss": 0.7037608027458191,
+    "eval_runtime": 0.708,
+    "eval_samples": 2033,
+    "eval_samples_per_second": 2871.533,
+    "eval_steps_per_second": 45.199
+}

lv-LV/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

lv-LV/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

lv-LV/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
+size 17082999

lv-LV/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

lv-LV/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3843028539002880.0,
+    "train_loss": 1.2955143038431804,
+    "train_runtime": 69.0404,
+    "train_samples": 11514,
+    "train_samples_per_second": 833.86,
+    "train_steps_per_second": 26.072
+}

lv-LV/trainer_state.json

@@ -0,0 +1,354 @@
+{
+  "best_global_step": 1800,
+  "best_metric": 0.807673389080177,
+  "best_model_checkpoint": "haryos_model_loras/xlm-roberta-base_massive_lora_lv-LV/checkpoint-1800",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 2.4014697074890137,
+      "learning_rate": 0.00019455555555555556,
+      "loss": 3.8285,
+      "step": 50
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 4.06867790222168,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 3.6012,
+      "step": 100
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 5.772338390350342,
+      "learning_rate": 0.00018344444444444446,
+      "loss": 2.9716,
+      "step": 150
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 4.652677059173584,
+      "learning_rate": 0.00017788888888888892,
+      "loss": 2.486,
+      "step": 200
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 5.509288311004639,
+      "learning_rate": 0.00017233333333333334,
+      "loss": 2.2072,
+      "step": 250
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 5.622175693511963,
+      "learning_rate": 0.0001667777777777778,
+      "loss": 1.9821,
+      "step": 300
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 6.9041948318481445,
+      "learning_rate": 0.00016122222222222224,
+      "loss": 1.7778,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6379734382685687,
+      "eval_f1": 0.6044368425897031,
+      "eval_loss": 1.3189401626586914,
+      "eval_runtime": 0.7115,
+      "eval_samples_per_second": 2857.446,
+      "eval_steps_per_second": 44.977,
+      "step": 360
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 7.185863018035889,
+      "learning_rate": 0.00015566666666666666,
+      "loss": 1.5965,
+      "step": 400
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 6.0866570472717285,
+      "learning_rate": 0.00015011111111111112,
+      "loss": 1.4682,
+      "step": 450
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 5.591103553771973,
+      "learning_rate": 0.00014455555555555557,
+      "loss": 1.3442,
+      "step": 500
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 6.466306209564209,
+      "learning_rate": 0.000139,
+      "loss": 1.3095,
+      "step": 550
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 4.4958977699279785,
+      "learning_rate": 0.00013344444444444447,
+      "loss": 1.241,
+      "step": 600
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 6.055330276489258,
+      "learning_rate": 0.0001278888888888889,
+      "loss": 1.1922,
+      "step": 650
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 4.494913578033447,
+      "learning_rate": 0.00012233333333333334,
+      "loss": 1.1047,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7589768814559764,
+      "eval_f1": 0.7492422429714453,
+      "eval_loss": 0.8883522152900696,
+      "eval_runtime": 0.7082,
+      "eval_samples_per_second": 2870.814,
+      "eval_steps_per_second": 45.187,
+      "step": 720
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 3.117950439453125,
+      "learning_rate": 0.00011677777777777778,
+      "loss": 1.0648,
+      "step": 750
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 4.20769739151001,
+      "learning_rate": 0.00011122222222222223,
+      "loss": 0.9887,
+      "step": 800
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 6.101656913757324,
+      "learning_rate": 0.00010566666666666667,
+      "loss": 0.9929,
+      "step": 850
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 5.662967205047607,
+      "learning_rate": 0.0001001111111111111,
+      "loss": 0.9126,
+      "step": 900
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 6.445260524749756,
+      "learning_rate": 9.455555555555556e-05,
+      "loss": 0.959,
+      "step": 950
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 6.131654262542725,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 0.9376,
+      "step": 1000
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 5.821775913238525,
+      "learning_rate": 8.344444444444445e-05,
+      "loss": 0.8815,
+      "step": 1050
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7830791933103788,
+      "eval_f1": 0.7755197874978285,
+      "eval_loss": 0.7780221700668335,
+      "eval_runtime": 0.7103,
+      "eval_samples_per_second": 2862.358,
+      "eval_steps_per_second": 45.054,
+      "step": 1080
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 6.136746883392334,
+      "learning_rate": 7.788888888888888e-05,
+      "loss": 0.8615,
+      "step": 1100
+    },
+    {
+      "epoch": 3.1944444444444446,
+      "grad_norm": 5.886898994445801,
+      "learning_rate": 7.233333333333335e-05,
+      "loss": 0.8114,
+      "step": 1150
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 3.9018115997314453,
+      "learning_rate": 6.677777777777779e-05,
+      "loss": 0.8149,
+      "step": 1200
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 5.582732200622559,
+      "learning_rate": 6.122222222222222e-05,
+      "loss": 0.8632,
+      "step": 1250
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 7.175996780395508,
+      "learning_rate": 5.566666666666667e-05,
+      "loss": 0.8154,
+      "step": 1300
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 4.679837703704834,
+      "learning_rate": 5.011111111111111e-05,
+      "loss": 0.7919,
+      "step": 1350
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 4.685590744018555,
+      "learning_rate": 4.4555555555555555e-05,
+      "loss": 0.8089,
+      "step": 1400
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8071815051647812,
+      "eval_f1": 0.8010882477715093,
+      "eval_loss": 0.7250494956970215,
+      "eval_runtime": 0.7062,
+      "eval_samples_per_second": 2878.903,
+      "eval_steps_per_second": 45.315,
+      "step": 1440
+    },
+    {
+      "epoch": 4.027777777777778,
+      "grad_norm": 5.261865615844727,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.7835,
+      "step": 1450
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 8.222892761230469,
+      "learning_rate": 3.3444444444444443e-05,
+      "loss": 0.7635,
+      "step": 1500
+    },
+    {
+      "epoch": 4.305555555555555,
+      "grad_norm": 6.056962013244629,
+      "learning_rate": 2.788888888888889e-05,
+      "loss": 0.739,
+      "step": 1550
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 5.103604793548584,
+      "learning_rate": 2.2333333333333335e-05,
+      "loss": 0.7552,
+      "step": 1600
+    },
+    {
+      "epoch": 4.583333333333333,
+      "grad_norm": 40.553688049316406,
+      "learning_rate": 1.677777777777778e-05,
+      "loss": 0.7525,
+      "step": 1650
+    },
+    {
+      "epoch": 4.722222222222222,
+      "grad_norm": 5.032034873962402,
+      "learning_rate": 1.1222222222222224e-05,
+      "loss": 0.7632,
+      "step": 1700
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 4.801251411437988,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.7071,
+      "step": 1750
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.084646224975586,
+      "learning_rate": 1.1111111111111112e-07,
+      "loss": 0.7594,
+      "step": 1800
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.807673389080177,
+      "eval_f1": 0.8020280975121211,
+      "eval_loss": 0.7037608027458191,
+      "eval_runtime": 0.7131,
+      "eval_samples_per_second": 2851.11,
+      "eval_steps_per_second": 44.877,
+      "step": 1800
+    },
+    {
+      "epoch": 5.0,
+      "step": 1800,
+      "total_flos": 3843028539002880.0,
+      "train_loss": 1.2955143038431804,
+      "train_runtime": 69.0404,
+      "train_samples_per_second": 833.86,
+      "train_steps_per_second": 26.072
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3843028539002880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}