Uploading best Arabic ChatGPT model

best/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Alibaba-NLP/gte-multilingual-base
+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 0.15.1

best/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score",
+    "classifier",
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

best/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8a96fe357136fb003b2c1835a677503192b8d378101a5990ba69eaa7002eb9
+size 3549156

best/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

best/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

best/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7681486b047f585cb3d4a74af864b81970cea49ab8306649b824b3f75ec278d
+size 5432

checkpoint-320/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Alibaba-NLP/gte-multilingual-base
+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 0.15.1

checkpoint-320/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score",
+    "classifier",
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-320/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8a96fe357136fb003b2c1835a677503192b8d378101a5990ba69eaa7002eb9
+size 3549156

checkpoint-320/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffadd8e36f765697672502ee135f0a8a08a43f6c3a09b738ade8cb1daeecb07
+size 11839994

checkpoint-320/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fb3645fadec5890b85fd29fbce9e3179556bd07ea96860a352e7f0c1c0f114
+size 14244

checkpoint-320/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e128d035a8be12949b84ee25f3b314315dce72524f36488617dc277b37128a0
+size 1000

checkpoint-320/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-320/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

checkpoint-320/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-320/trainer_state.json

@@ -0,0 +1,682 @@
+{
+  "best_metric": 0.1395142674446106,
+  "best_model_checkpoint": "/home/steam3/origin-ai/results/multilingual-train-test-table-results/ablation-arabic-mgte/arabic_chatgpt__3__bulgarian_true-and-fake-news_chatgpt;russian_chatgpt;bulgarian_true-and-fake-news_davinci/checkpoint-320",
+  "epoch": 0.20317460317460317,
+  "eval_steps": 10,
+  "global_step": 320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006349206349206349,
+      "grad_norm": 3.314401388168335,
+      "learning_rate": 9.993646759847523e-05,
+      "loss": 0.6929,
+      "step": 10
+    },
+    {
+      "epoch": 0.006349206349206349,
+      "eval_accuracy": 0.5251851851851852,
+      "eval_f1": 0.6566684520621318,
+      "eval_loss": 0.6887626647949219,
+      "eval_precision": 0.514261744966443,
+      "eval_recall": 0.9081481481481481,
+      "eval_roc_auc": 0.5891390946502058,
+      "eval_runtime": 5.5333,
+      "eval_samples_per_second": 487.955,
+      "eval_steps_per_second": 15.362,
+      "step": 10
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "grad_norm": 2.6429762840270996,
+      "learning_rate": 9.980940279542568e-05,
+      "loss": 0.688,
+      "step": 20
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "eval_accuracy": 0.5637037037037037,
+      "eval_f1": 0.2929171668667467,
+      "eval_loss": 0.674746036529541,
+      "eval_precision": 0.7721518987341772,
+      "eval_recall": 0.18074074074074073,
+      "eval_roc_auc": 0.6710831275720164,
+      "eval_runtime": 5.528,
+      "eval_samples_per_second": 488.42,
+      "eval_steps_per_second": 15.376,
+      "step": 20
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "grad_norm": 3.3568179607391357,
+      "learning_rate": 9.968233799237612e-05,
+      "loss": 0.6482,
+      "step": 30
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "eval_accuracy": 0.5981481481481481,
+      "eval_f1": 0.3710144927536232,
+      "eval_loss": 0.6537347435951233,
+      "eval_precision": 0.8533333333333334,
+      "eval_recall": 0.23703703703703705,
+      "eval_roc_auc": 0.7466732510288066,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.853,
+      "eval_steps_per_second": 15.421,
+      "step": 30
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "grad_norm": 2.775456666946411,
+      "learning_rate": 9.955527318932655e-05,
+      "loss": 0.6524,
+      "step": 40
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "eval_accuracy": 0.7307407407407407,
+      "eval_f1": 0.7163480296527507,
+      "eval_loss": 0.6117509603500366,
+      "eval_precision": 0.7568013190436933,
+      "eval_recall": 0.68,
+      "eval_roc_auc": 0.8087465020576132,
+      "eval_runtime": 5.5237,
+      "eval_samples_per_second": 488.803,
+      "eval_steps_per_second": 15.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.0409586429595947,
+      "learning_rate": 9.942820838627701e-05,
+      "loss": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_f1": 0.7790883009244501,
+      "eval_loss": 0.5712039470672607,
+      "eval_precision": 0.6838276440962507,
+      "eval_recall": 0.9051851851851852,
+      "eval_roc_auc": 0.8662809327846365,
+      "eval_runtime": 5.5269,
+      "eval_samples_per_second": 488.52,
+      "eval_steps_per_second": 15.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 5.313755035400391,
+      "learning_rate": 9.930114358322745e-05,
+      "loss": 0.5608,
+      "step": 60
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8195937873357229,
+      "eval_loss": 0.48943084478378296,
+      "eval_precision": 0.8863049095607235,
+      "eval_recall": 0.7622222222222222,
+      "eval_roc_auc": 0.9197953360768176,
+      "eval_runtime": 5.541,
+      "eval_samples_per_second": 487.279,
+      "eval_steps_per_second": 15.34,
+      "step": 60
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.1755828857421875,
+      "learning_rate": 9.91740787801779e-05,
+      "loss": 0.4534,
+      "step": 70
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8533505988993202,
+      "eval_loss": 0.4028916656970978,
+      "eval_precision": 0.757906843013226,
+      "eval_recall": 0.9762962962962963,
+      "eval_roc_auc": 0.95520438957476,
+      "eval_runtime": 5.5166,
+      "eval_samples_per_second": 489.434,
+      "eval_steps_per_second": 15.408,
+      "step": 70
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "grad_norm": 2.359863758087158,
+      "learning_rate": 9.904701397712835e-05,
+      "loss": 0.2939,
+      "step": 80
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "eval_accuracy": 0.87,
+      "eval_f1": 0.882804674457429,
+      "eval_loss": 0.30669787526130676,
+      "eval_precision": 0.8036474164133739,
+      "eval_recall": 0.9792592592592593,
+      "eval_roc_auc": 0.967720987654321,
+      "eval_runtime": 5.5661,
+      "eval_samples_per_second": 485.082,
+      "eval_steps_per_second": 15.271,
+      "step": 80
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 2.1184494495391846,
+      "learning_rate": 9.893265565438374e-05,
+      "loss": 0.2494,
+      "step": 90
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "eval_accuracy": 0.9244444444444444,
+      "eval_f1": 0.9246676514032496,
+      "eval_loss": 0.19904199242591858,
+      "eval_precision": 0.9219440353460973,
+      "eval_recall": 0.9274074074074075,
+      "eval_roc_auc": 0.9763517146776406,
+      "eval_runtime": 5.5491,
+      "eval_samples_per_second": 486.564,
+      "eval_steps_per_second": 15.318,
+      "step": 90
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.1063764095306396,
+      "learning_rate": 9.880559085133418e-05,
+      "loss": 0.174,
+      "step": 100
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "eval_accuracy": 0.8692592592592593,
+      "eval_f1": 0.8829963539940338,
+      "eval_loss": 0.4303587079048157,
+      "eval_precision": 0.7990401919616077,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.9744661179698217,
+      "eval_runtime": 5.5309,
+      "eval_samples_per_second": 488.17,
+      "eval_steps_per_second": 15.368,
+      "step": 100
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "grad_norm": 11.44679069519043,
+      "learning_rate": 9.869123252858958e-05,
+      "loss": 0.269,
+      "step": 110
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9302824454772971,
+      "eval_loss": 0.2445582151412964,
+      "eval_precision": 0.899101589495508,
+      "eval_recall": 0.9637037037037037,
+      "eval_roc_auc": 0.9810120713305899,
+      "eval_runtime": 5.5203,
+      "eval_samples_per_second": 489.102,
+      "eval_steps_per_second": 15.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.09498822689056396,
+      "learning_rate": 9.856416772554004e-05,
+      "loss": 0.1981,
+      "step": 120
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "eval_accuracy": 0.9303703703703704,
+      "eval_f1": 0.9330960854092527,
+      "eval_loss": 0.24259698390960693,
+      "eval_precision": 0.897945205479452,
+      "eval_recall": 0.9711111111111111,
+      "eval_roc_auc": 0.9832271604938272,
+      "eval_runtime": 5.5208,
+      "eval_samples_per_second": 489.057,
+      "eval_steps_per_second": 15.396,
+      "step": 120
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "grad_norm": 0.047983940690755844,
+      "learning_rate": 9.843710292249048e-05,
+      "loss": 0.2035,
+      "step": 130
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "eval_accuracy": 0.9288888888888889,
+      "eval_f1": 0.9320594479830149,
+      "eval_loss": 0.2548026740550995,
+      "eval_precision": 0.8922764227642277,
+      "eval_recall": 0.9755555555555555,
+      "eval_roc_auc": 0.9850041152263376,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 130
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.1345868706703186,
+      "learning_rate": 9.831003811944091e-05,
+      "loss": 0.2392,
+      "step": 140
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "eval_accuracy": 0.9214814814814815,
+      "eval_f1": 0.9260293091416608,
+      "eval_loss": 0.28311270475387573,
+      "eval_precision": 0.8753298153034301,
+      "eval_recall": 0.9829629629629629,
+      "eval_roc_auc": 0.9863648834019204,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.727,
+      "eval_steps_per_second": 15.386,
+      "step": 140
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.3760770559310913,
+      "learning_rate": 9.818297331639137e-05,
+      "loss": 0.1965,
+      "step": 150
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_accuracy": 0.8429629629629629,
+      "eval_f1": 0.8640153944836434,
+      "eval_loss": 0.5912654995918274,
+      "eval_precision": 0.7618778280542986,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9832545953360768,
+      "eval_runtime": 5.5302,
+      "eval_samples_per_second": 488.232,
+      "eval_steps_per_second": 15.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "grad_norm": 3.2790462970733643,
+      "learning_rate": 9.805590851334181e-05,
+      "loss": 0.3521,
+      "step": 160
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "eval_accuracy": 0.9185185185185185,
+      "eval_f1": 0.9238754325259516,
+      "eval_loss": 0.25474533438682556,
+      "eval_precision": 0.8668831168831169,
+      "eval_recall": 0.9888888888888889,
+      "eval_roc_auc": 0.9880035665294925,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.123,
+      "eval_steps_per_second": 15.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "grad_norm": 3.765111207962036,
+      "learning_rate": 9.792884371029225e-05,
+      "loss": 0.4232,
+      "step": 170
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "eval_accuracy": 0.9474074074074074,
+      "eval_f1": 0.9478324761204996,
+      "eval_loss": 0.14082331955432892,
+      "eval_precision": 0.9402332361516035,
+      "eval_recall": 0.9555555555555556,
+      "eval_roc_auc": 0.9880447187928669,
+      "eval_runtime": 5.5338,
+      "eval_samples_per_second": 487.911,
+      "eval_steps_per_second": 15.36,
+      "step": 170
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.110823154449463,
+      "learning_rate": 9.780177890724271e-05,
+      "loss": 0.1239,
+      "step": 180
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9098915989159891,
+      "eval_loss": 0.26993757486343384,
+      "eval_precision": 0.83832709113608,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9881753086419753,
+      "eval_runtime": 5.5165,
+      "eval_samples_per_second": 489.445,
+      "eval_steps_per_second": 15.408,
+      "step": 180
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "grad_norm": 1.8782886266708374,
+      "learning_rate": 9.767471410419315e-05,
+      "loss": 0.1301,
+      "step": 190
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9396825396825397,
+      "eval_loss": 0.17670103907585144,
+      "eval_precision": 0.896969696969697,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.989798353909465,
+      "eval_runtime": 5.514,
+      "eval_samples_per_second": 489.66,
+      "eval_steps_per_second": 15.415,
+      "step": 190
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 4.296081066131592,
+      "learning_rate": 9.754764930114358e-05,
+      "loss": 0.1532,
+      "step": 200
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9275563258232236,
+      "eval_loss": 0.25379836559295654,
+      "eval_precision": 0.8716612377850163,
+      "eval_recall": 0.9911111111111112,
+      "eval_roc_auc": 0.99000658436214,
+      "eval_runtime": 5.5116,
+      "eval_samples_per_second": 489.878,
+      "eval_steps_per_second": 15.422,
+      "step": 200
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.7609732151031494,
+      "learning_rate": 9.742058449809403e-05,
+      "loss": 0.2815,
+      "step": 210
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_accuracy": 0.9285185185185185,
+      "eval_f1": 0.9328695652173913,
+      "eval_loss": 0.24461880326271057,
+      "eval_precision": 0.879344262295082,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9911909465020576,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.978,
+      "eval_steps_per_second": 15.425,
+      "step": 210
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "grad_norm": 0.20786483585834503,
+      "learning_rate": 9.729351969504448e-05,
+      "loss": 0.1336,
+      "step": 220
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "eval_accuracy": 0.9518518518518518,
+      "eval_f1": 0.9534717251252685,
+      "eval_loss": 0.1563795804977417,
+      "eval_precision": 0.9224376731301939,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.992451303155007,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.68,
+      "eval_steps_per_second": 15.416,
+      "step": 220
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "grad_norm": 0.6910555362701416,
+      "learning_rate": 9.716645489199492e-05,
+      "loss": 0.1237,
+      "step": 230
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "eval_accuracy": 0.937037037037037,
+      "eval_f1": 0.9404344779257183,
+      "eval_loss": 0.22764083743095398,
+      "eval_precision": 0.8922872340425532,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9923105624142661,
+      "eval_runtime": 5.5171,
+      "eval_samples_per_second": 489.388,
+      "eval_steps_per_second": 15.407,
+      "step": 230
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.4784867763519287,
+      "learning_rate": 9.703939008894538e-05,
+      "loss": 0.063,
+      "step": 240
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "eval_accuracy": 0.8637037037037038,
+      "eval_f1": 0.8799739073711677,
+      "eval_loss": 0.616968035697937,
+      "eval_precision": 0.7861305361305362,
+      "eval_recall": 0.9992592592592593,
+      "eval_roc_auc": 0.9860919067215363,
+      "eval_runtime": 5.5121,
+      "eval_samples_per_second": 489.827,
+      "eval_steps_per_second": 15.42,
+      "step": 240
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": NaN,
+      "learning_rate": 9.692503176620077e-05,
+      "loss": 0.1347,
+      "step": 250
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_accuracy": 0.9388888888888889,
+      "eval_f1": 0.9420442571127503,
+      "eval_loss": 0.24191488325595856,
+      "eval_precision": 0.8957915831663327,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9917956104252401,
+      "eval_runtime": 5.5139,
+      "eval_samples_per_second": 489.672,
+      "eval_steps_per_second": 15.416,
+      "step": 250
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "grad_norm": 9.05746078491211,
+      "learning_rate": 9.679796696315121e-05,
+      "loss": 0.1642,
+      "step": 260
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "eval_accuracy": 0.9425925925925925,
+      "eval_f1": 0.9452103216684341,
+      "eval_loss": 0.2284214049577713,
+      "eval_precision": 0.9039891818796484,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9920307270233196,
+      "eval_runtime": 5.5153,
+      "eval_samples_per_second": 489.547,
+      "eval_steps_per_second": 15.412,
+      "step": 260
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.0563305616378784,
+      "learning_rate": 9.667090216010166e-05,
+      "loss": 0.1503,
+      "step": 270
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "eval_accuracy": 0.894074074074074,
+      "eval_f1": 0.9040912139503688,
+      "eval_loss": 0.4835222661495209,
+      "eval_precision": 0.8259803921568627,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9872872427983539,
+      "eval_runtime": 5.5128,
+      "eval_samples_per_second": 489.765,
+      "eval_steps_per_second": 15.419,
+      "step": 270
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.09033135324716568,
+      "learning_rate": 9.65438373570521e-05,
+      "loss": 0.0974,
+      "step": 280
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_accuracy": 0.9507407407407408,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.19544483721256256,
+      "eval_precision": 0.9216909216909217,
+      "eval_recall": 0.9851851851851852,
+      "eval_roc_auc": 0.9924573388203017,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.975,
+      "eval_steps_per_second": 15.425,
+      "step": 280
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "grad_norm": 0.0589861236512661,
+      "learning_rate": 9.641677255400255e-05,
+      "loss": 0.1201,
+      "step": 290
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "eval_accuracy": 0.9174074074074074,
+      "eval_f1": 0.923394022672621,
+      "eval_loss": 0.3497244715690613,
+      "eval_precision": 0.8609865470852018,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9902913580246913,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.85,
+      "eval_steps_per_second": 15.421,
+      "step": 290
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.337423324584961,
+      "learning_rate": 9.628970775095299e-05,
+      "loss": 0.1636,
+      "step": 300
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "eval_accuracy": 0.8674074074074074,
+      "eval_f1": 0.882699868938401,
+      "eval_loss": 0.6298528909683228,
+      "eval_precision": 0.7914218566392479,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.985441975308642,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.684,
+      "eval_steps_per_second": 15.416,
+      "step": 300
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "grad_norm": 5.734988212585449,
+      "learning_rate": 9.616264294790343e-05,
+      "loss": 0.2139,
+      "step": 310
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "eval_accuracy": 0.9418518518518518,
+      "eval_f1": 0.944620811287478,
+      "eval_loss": 0.20854391157627106,
+      "eval_precision": 0.9016835016835016,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9917333333333334,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.776,
+      "eval_steps_per_second": 15.419,
+      "step": 310
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "grad_norm": 0.2367023378610611,
+      "learning_rate": 9.603557814485387e-05,
+      "loss": 0.1894,
+      "step": 320
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "eval_accuracy": 0.9562962962962963,
+      "eval_f1": 0.9572463768115942,
+      "eval_loss": 0.1395142674446106,
+      "eval_precision": 0.9368794326241134,
+      "eval_recall": 0.9785185185185186,
+      "eval_roc_auc": 0.9925939643347051,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.717,
+      "eval_steps_per_second": 15.417,
+      "step": 320
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 50,
+        "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-320/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7681486b047f585cb3d4a74af864b81970cea49ab8306649b824b3f75ec278d
+size 5432

checkpoint-790/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Alibaba-NLP/gte-multilingual-base
+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 0.15.1

checkpoint-790/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score",
+    "classifier",
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-790/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851cd9eac1854073e68cde254facb637fdd54f14ee74c249c15f2930efc328b7
+size 3549156

checkpoint-790/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7a0d5b3c7dfaccd811e55cc99d164ec0a4af45d46d305f3f9ab13f57e09e21
+size 11839994

checkpoint-790/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5fc6a35ef8287f5306d79ace3cc25b807f2e5fcdb2d382efd032b157c476db
+size 14244

checkpoint-790/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e680ad2d1109269d4ba1110431839070077a8dd17d23bdd919b7444114fc6a
+size 1000

checkpoint-790/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-790/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

checkpoint-790/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-790/trainer_state.json

@@ -0,0 +1,1622 @@
+{
+  "best_metric": 0.1395142674446106,
+  "best_model_checkpoint": "/home/steam3/origin-ai/results/multilingual-train-test-table-results/ablation-arabic-mgte/arabic_chatgpt__3__bulgarian_true-and-fake-news_chatgpt;russian_chatgpt;bulgarian_true-and-fake-news_davinci/checkpoint-320",
+  "epoch": 0.5015873015873016,
+  "eval_steps": 10,
+  "global_step": 790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006349206349206349,
+      "grad_norm": 3.314401388168335,
+      "learning_rate": 9.993646759847523e-05,
+      "loss": 0.6929,
+      "step": 10
+    },
+    {
+      "epoch": 0.006349206349206349,
+      "eval_accuracy": 0.5251851851851852,
+      "eval_f1": 0.6566684520621318,
+      "eval_loss": 0.6887626647949219,
+      "eval_precision": 0.514261744966443,
+      "eval_recall": 0.9081481481481481,
+      "eval_roc_auc": 0.5891390946502058,
+      "eval_runtime": 5.5333,
+      "eval_samples_per_second": 487.955,
+      "eval_steps_per_second": 15.362,
+      "step": 10
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "grad_norm": 2.6429762840270996,
+      "learning_rate": 9.980940279542568e-05,
+      "loss": 0.688,
+      "step": 20
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "eval_accuracy": 0.5637037037037037,
+      "eval_f1": 0.2929171668667467,
+      "eval_loss": 0.674746036529541,
+      "eval_precision": 0.7721518987341772,
+      "eval_recall": 0.18074074074074073,
+      "eval_roc_auc": 0.6710831275720164,
+      "eval_runtime": 5.528,
+      "eval_samples_per_second": 488.42,
+      "eval_steps_per_second": 15.376,
+      "step": 20
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "grad_norm": 3.3568179607391357,
+      "learning_rate": 9.968233799237612e-05,
+      "loss": 0.6482,
+      "step": 30
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "eval_accuracy": 0.5981481481481481,
+      "eval_f1": 0.3710144927536232,
+      "eval_loss": 0.6537347435951233,
+      "eval_precision": 0.8533333333333334,
+      "eval_recall": 0.23703703703703705,
+      "eval_roc_auc": 0.7466732510288066,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.853,
+      "eval_steps_per_second": 15.421,
+      "step": 30
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "grad_norm": 2.775456666946411,
+      "learning_rate": 9.955527318932655e-05,
+      "loss": 0.6524,
+      "step": 40
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "eval_accuracy": 0.7307407407407407,
+      "eval_f1": 0.7163480296527507,
+      "eval_loss": 0.6117509603500366,
+      "eval_precision": 0.7568013190436933,
+      "eval_recall": 0.68,
+      "eval_roc_auc": 0.8087465020576132,
+      "eval_runtime": 5.5237,
+      "eval_samples_per_second": 488.803,
+      "eval_steps_per_second": 15.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.0409586429595947,
+      "learning_rate": 9.942820838627701e-05,
+      "loss": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_f1": 0.7790883009244501,
+      "eval_loss": 0.5712039470672607,
+      "eval_precision": 0.6838276440962507,
+      "eval_recall": 0.9051851851851852,
+      "eval_roc_auc": 0.8662809327846365,
+      "eval_runtime": 5.5269,
+      "eval_samples_per_second": 488.52,
+      "eval_steps_per_second": 15.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 5.313755035400391,
+      "learning_rate": 9.930114358322745e-05,
+      "loss": 0.5608,
+      "step": 60
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8195937873357229,
+      "eval_loss": 0.48943084478378296,
+      "eval_precision": 0.8863049095607235,
+      "eval_recall": 0.7622222222222222,
+      "eval_roc_auc": 0.9197953360768176,
+      "eval_runtime": 5.541,
+      "eval_samples_per_second": 487.279,
+      "eval_steps_per_second": 15.34,
+      "step": 60
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.1755828857421875,
+      "learning_rate": 9.91740787801779e-05,
+      "loss": 0.4534,
+      "step": 70
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8533505988993202,
+      "eval_loss": 0.4028916656970978,
+      "eval_precision": 0.757906843013226,
+      "eval_recall": 0.9762962962962963,
+      "eval_roc_auc": 0.95520438957476,
+      "eval_runtime": 5.5166,
+      "eval_samples_per_second": 489.434,
+      "eval_steps_per_second": 15.408,
+      "step": 70
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "grad_norm": 2.359863758087158,
+      "learning_rate": 9.904701397712835e-05,
+      "loss": 0.2939,
+      "step": 80
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "eval_accuracy": 0.87,
+      "eval_f1": 0.882804674457429,
+      "eval_loss": 0.30669787526130676,
+      "eval_precision": 0.8036474164133739,
+      "eval_recall": 0.9792592592592593,
+      "eval_roc_auc": 0.967720987654321,
+      "eval_runtime": 5.5661,
+      "eval_samples_per_second": 485.082,
+      "eval_steps_per_second": 15.271,
+      "step": 80
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 2.1184494495391846,
+      "learning_rate": 9.893265565438374e-05,
+      "loss": 0.2494,
+      "step": 90
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "eval_accuracy": 0.9244444444444444,
+      "eval_f1": 0.9246676514032496,
+      "eval_loss": 0.19904199242591858,
+      "eval_precision": 0.9219440353460973,
+      "eval_recall": 0.9274074074074075,
+      "eval_roc_auc": 0.9763517146776406,
+      "eval_runtime": 5.5491,
+      "eval_samples_per_second": 486.564,
+      "eval_steps_per_second": 15.318,
+      "step": 90
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.1063764095306396,
+      "learning_rate": 9.880559085133418e-05,
+      "loss": 0.174,
+      "step": 100
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "eval_accuracy": 0.8692592592592593,
+      "eval_f1": 0.8829963539940338,
+      "eval_loss": 0.4303587079048157,
+      "eval_precision": 0.7990401919616077,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.9744661179698217,
+      "eval_runtime": 5.5309,
+      "eval_samples_per_second": 488.17,
+      "eval_steps_per_second": 15.368,
+      "step": 100
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "grad_norm": 11.44679069519043,
+      "learning_rate": 9.869123252858958e-05,
+      "loss": 0.269,
+      "step": 110
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9302824454772971,
+      "eval_loss": 0.2445582151412964,
+      "eval_precision": 0.899101589495508,
+      "eval_recall": 0.9637037037037037,
+      "eval_roc_auc": 0.9810120713305899,
+      "eval_runtime": 5.5203,
+      "eval_samples_per_second": 489.102,
+      "eval_steps_per_second": 15.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.09498822689056396,
+      "learning_rate": 9.856416772554004e-05,
+      "loss": 0.1981,
+      "step": 120
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "eval_accuracy": 0.9303703703703704,
+      "eval_f1": 0.9330960854092527,
+      "eval_loss": 0.24259698390960693,
+      "eval_precision": 0.897945205479452,
+      "eval_recall": 0.9711111111111111,
+      "eval_roc_auc": 0.9832271604938272,
+      "eval_runtime": 5.5208,
+      "eval_samples_per_second": 489.057,
+      "eval_steps_per_second": 15.396,
+      "step": 120
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "grad_norm": 0.047983940690755844,
+      "learning_rate": 9.843710292249048e-05,
+      "loss": 0.2035,
+      "step": 130
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "eval_accuracy": 0.9288888888888889,
+      "eval_f1": 0.9320594479830149,
+      "eval_loss": 0.2548026740550995,
+      "eval_precision": 0.8922764227642277,
+      "eval_recall": 0.9755555555555555,
+      "eval_roc_auc": 0.9850041152263376,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 130
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.1345868706703186,
+      "learning_rate": 9.831003811944091e-05,
+      "loss": 0.2392,
+      "step": 140
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "eval_accuracy": 0.9214814814814815,
+      "eval_f1": 0.9260293091416608,
+      "eval_loss": 0.28311270475387573,
+      "eval_precision": 0.8753298153034301,
+      "eval_recall": 0.9829629629629629,
+      "eval_roc_auc": 0.9863648834019204,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.727,
+      "eval_steps_per_second": 15.386,
+      "step": 140
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.3760770559310913,
+      "learning_rate": 9.818297331639137e-05,
+      "loss": 0.1965,
+      "step": 150
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_accuracy": 0.8429629629629629,
+      "eval_f1": 0.8640153944836434,
+      "eval_loss": 0.5912654995918274,
+      "eval_precision": 0.7618778280542986,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9832545953360768,
+      "eval_runtime": 5.5302,
+      "eval_samples_per_second": 488.232,
+      "eval_steps_per_second": 15.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "grad_norm": 3.2790462970733643,
+      "learning_rate": 9.805590851334181e-05,
+      "loss": 0.3521,
+      "step": 160
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "eval_accuracy": 0.9185185185185185,
+      "eval_f1": 0.9238754325259516,
+      "eval_loss": 0.25474533438682556,
+      "eval_precision": 0.8668831168831169,
+      "eval_recall": 0.9888888888888889,
+      "eval_roc_auc": 0.9880035665294925,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.123,
+      "eval_steps_per_second": 15.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "grad_norm": 3.765111207962036,
+      "learning_rate": 9.792884371029225e-05,
+      "loss": 0.4232,
+      "step": 170
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "eval_accuracy": 0.9474074074074074,
+      "eval_f1": 0.9478324761204996,
+      "eval_loss": 0.14082331955432892,
+      "eval_precision": 0.9402332361516035,
+      "eval_recall": 0.9555555555555556,
+      "eval_roc_auc": 0.9880447187928669,
+      "eval_runtime": 5.5338,
+      "eval_samples_per_second": 487.911,
+      "eval_steps_per_second": 15.36,
+      "step": 170
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.110823154449463,
+      "learning_rate": 9.780177890724271e-05,
+      "loss": 0.1239,
+      "step": 180
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9098915989159891,
+      "eval_loss": 0.26993757486343384,
+      "eval_precision": 0.83832709113608,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9881753086419753,
+      "eval_runtime": 5.5165,
+      "eval_samples_per_second": 489.445,
+      "eval_steps_per_second": 15.408,
+      "step": 180
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "grad_norm": 1.8782886266708374,
+      "learning_rate": 9.767471410419315e-05,
+      "loss": 0.1301,
+      "step": 190
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9396825396825397,
+      "eval_loss": 0.17670103907585144,
+      "eval_precision": 0.896969696969697,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.989798353909465,
+      "eval_runtime": 5.514,
+      "eval_samples_per_second": 489.66,
+      "eval_steps_per_second": 15.415,
+      "step": 190
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 4.296081066131592,
+      "learning_rate": 9.754764930114358e-05,
+      "loss": 0.1532,
+      "step": 200
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9275563258232236,
+      "eval_loss": 0.25379836559295654,
+      "eval_precision": 0.8716612377850163,
+      "eval_recall": 0.9911111111111112,
+      "eval_roc_auc": 0.99000658436214,
+      "eval_runtime": 5.5116,
+      "eval_samples_per_second": 489.878,
+      "eval_steps_per_second": 15.422,
+      "step": 200
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.7609732151031494,
+      "learning_rate": 9.742058449809403e-05,
+      "loss": 0.2815,
+      "step": 210
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_accuracy": 0.9285185185185185,
+      "eval_f1": 0.9328695652173913,
+      "eval_loss": 0.24461880326271057,
+      "eval_precision": 0.879344262295082,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9911909465020576,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.978,
+      "eval_steps_per_second": 15.425,
+      "step": 210
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "grad_norm": 0.20786483585834503,
+      "learning_rate": 9.729351969504448e-05,
+      "loss": 0.1336,
+      "step": 220
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "eval_accuracy": 0.9518518518518518,
+      "eval_f1": 0.9534717251252685,
+      "eval_loss": 0.1563795804977417,
+      "eval_precision": 0.9224376731301939,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.992451303155007,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.68,
+      "eval_steps_per_second": 15.416,
+      "step": 220
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "grad_norm": 0.6910555362701416,
+      "learning_rate": 9.716645489199492e-05,
+      "loss": 0.1237,
+      "step": 230
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "eval_accuracy": 0.937037037037037,
+      "eval_f1": 0.9404344779257183,
+      "eval_loss": 0.22764083743095398,
+      "eval_precision": 0.8922872340425532,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9923105624142661,
+      "eval_runtime": 5.5171,
+      "eval_samples_per_second": 489.388,
+      "eval_steps_per_second": 15.407,
+      "step": 230
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.4784867763519287,
+      "learning_rate": 9.703939008894538e-05,
+      "loss": 0.063,
+      "step": 240
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "eval_accuracy": 0.8637037037037038,
+      "eval_f1": 0.8799739073711677,
+      "eval_loss": 0.616968035697937,
+      "eval_precision": 0.7861305361305362,
+      "eval_recall": 0.9992592592592593,
+      "eval_roc_auc": 0.9860919067215363,
+      "eval_runtime": 5.5121,
+      "eval_samples_per_second": 489.827,
+      "eval_steps_per_second": 15.42,
+      "step": 240
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": NaN,
+      "learning_rate": 9.692503176620077e-05,
+      "loss": 0.1347,
+      "step": 250
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_accuracy": 0.9388888888888889,
+      "eval_f1": 0.9420442571127503,
+      "eval_loss": 0.24191488325595856,
+      "eval_precision": 0.8957915831663327,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9917956104252401,
+      "eval_runtime": 5.5139,
+      "eval_samples_per_second": 489.672,
+      "eval_steps_per_second": 15.416,
+      "step": 250
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "grad_norm": 9.05746078491211,
+      "learning_rate": 9.679796696315121e-05,
+      "loss": 0.1642,
+      "step": 260
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "eval_accuracy": 0.9425925925925925,
+      "eval_f1": 0.9452103216684341,
+      "eval_loss": 0.2284214049577713,
+      "eval_precision": 0.9039891818796484,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9920307270233196,
+      "eval_runtime": 5.5153,
+      "eval_samples_per_second": 489.547,
+      "eval_steps_per_second": 15.412,
+      "step": 260
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.0563305616378784,
+      "learning_rate": 9.667090216010166e-05,
+      "loss": 0.1503,
+      "step": 270
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "eval_accuracy": 0.894074074074074,
+      "eval_f1": 0.9040912139503688,
+      "eval_loss": 0.4835222661495209,
+      "eval_precision": 0.8259803921568627,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9872872427983539,
+      "eval_runtime": 5.5128,
+      "eval_samples_per_second": 489.765,
+      "eval_steps_per_second": 15.419,
+      "step": 270
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.09033135324716568,
+      "learning_rate": 9.65438373570521e-05,
+      "loss": 0.0974,
+      "step": 280
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_accuracy": 0.9507407407407408,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.19544483721256256,
+      "eval_precision": 0.9216909216909217,
+      "eval_recall": 0.9851851851851852,
+      "eval_roc_auc": 0.9924573388203017,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.975,
+      "eval_steps_per_second": 15.425,
+      "step": 280
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "grad_norm": 0.0589861236512661,
+      "learning_rate": 9.641677255400255e-05,
+      "loss": 0.1201,
+      "step": 290
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "eval_accuracy": 0.9174074074074074,
+      "eval_f1": 0.923394022672621,
+      "eval_loss": 0.3497244715690613,
+      "eval_precision": 0.8609865470852018,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9902913580246913,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.85,
+      "eval_steps_per_second": 15.421,
+      "step": 290
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.337423324584961,
+      "learning_rate": 9.628970775095299e-05,
+      "loss": 0.1636,
+      "step": 300
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "eval_accuracy": 0.8674074074074074,
+      "eval_f1": 0.882699868938401,
+      "eval_loss": 0.6298528909683228,
+      "eval_precision": 0.7914218566392479,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.985441975308642,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.684,
+      "eval_steps_per_second": 15.416,
+      "step": 300
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "grad_norm": 5.734988212585449,
+      "learning_rate": 9.616264294790343e-05,
+      "loss": 0.2139,
+      "step": 310
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "eval_accuracy": 0.9418518518518518,
+      "eval_f1": 0.944620811287478,
+      "eval_loss": 0.20854391157627106,
+      "eval_precision": 0.9016835016835016,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9917333333333334,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.776,
+      "eval_steps_per_second": 15.419,
+      "step": 310
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "grad_norm": 0.2367023378610611,
+      "learning_rate": 9.603557814485387e-05,
+      "loss": 0.1894,
+      "step": 320
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "eval_accuracy": 0.9562962962962963,
+      "eval_f1": 0.9572463768115942,
+      "eval_loss": 0.1395142674446106,
+      "eval_precision": 0.9368794326241134,
+      "eval_recall": 0.9785185185185186,
+      "eval_roc_auc": 0.9925939643347051,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.717,
+      "eval_steps_per_second": 15.417,
+      "step": 320
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 14.949374198913574,
+      "learning_rate": 9.590851334180433e-05,
+      "loss": 0.057,
+      "step": 330
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "eval_accuracy": 0.9255555555555556,
+      "eval_f1": 0.9305219495333564,
+      "eval_loss": 0.29976287484169006,
+      "eval_precision": 0.8723266364225535,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900480109739369,
+      "eval_runtime": 5.5137,
+      "eval_samples_per_second": 489.687,
+      "eval_steps_per_second": 15.416,
+      "step": 330
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "grad_norm": 3.3133888244628906,
+      "learning_rate": 9.578144853875477e-05,
+      "loss": 0.2029,
+      "step": 340
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3038364350795746,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9897953360768176,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.19,
+      "eval_steps_per_second": 15.4,
+      "step": 340
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.5984865427017212,
+      "learning_rate": 9.565438373570522e-05,
+      "loss": 0.0849,
+      "step": 350
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9525521207764198,
+      "eval_loss": 0.15116137266159058,
+      "eval_precision": 0.9252793296089385,
+      "eval_recall": 0.9814814814814815,
+      "eval_roc_auc": 0.9926340192043897,
+      "eval_runtime": 5.5231,
+      "eval_samples_per_second": 488.853,
+      "eval_steps_per_second": 15.39,
+      "step": 350
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 5.849670886993408,
+      "learning_rate": 9.552731893265566e-05,
+      "loss": 0.2559,
+      "step": 360
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "eval_accuracy": 0.9392592592592592,
+      "eval_f1": 0.9424561403508772,
+      "eval_loss": 0.22722864151000977,
+      "eval_precision": 0.8953333333333333,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9912104252400549,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 360
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "grad_norm": 0.2203754186630249,
+      "learning_rate": 9.54002541296061e-05,
+      "loss": 0.0809,
+      "step": 370
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9279061745429459,
+      "eval_loss": 0.29464688897132874,
+      "eval_precision": 0.868302130406714,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9903662551440329,
+      "eval_runtime": 5.5169,
+      "eval_samples_per_second": 489.409,
+      "eval_steps_per_second": 15.407,
+      "step": 370
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "grad_norm": 9.942216873168945,
+      "learning_rate": 9.527318932655654e-05,
+      "loss": 0.193,
+      "step": 380
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9436222692036645,
+      "eval_loss": 0.20582349598407745,
+      "eval_precision": 0.8998655913978495,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9918285322359396,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.479,
+      "eval_steps_per_second": 15.41,
+      "step": 380
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 11.672406196594238,
+      "learning_rate": 9.5146124523507e-05,
+      "loss": 0.208,
+      "step": 390
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "eval_accuracy": 0.9296296296296296,
+      "eval_f1": 0.9339360222531293,
+      "eval_loss": 0.24709771573543549,
+      "eval_precision": 0.8800786369593709,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9910834019204389,
+      "eval_runtime": 5.5183,
+      "eval_samples_per_second": 489.282,
+      "eval_steps_per_second": 15.403,
+      "step": 390
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.7513141632080078,
+      "learning_rate": 9.501905972045744e-05,
+      "loss": 0.141,
+      "step": 400
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "eval_accuracy": 0.9248148148148149,
+      "eval_f1": 0.9298306256481161,
+      "eval_loss": 0.2548695504665375,
+      "eval_precision": 0.8716785482825664,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9910268861454047,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.718,
+      "eval_steps_per_second": 15.417,
+      "step": 400
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "grad_norm": 0.11584247648715973,
+      "learning_rate": 9.489199491740788e-05,
+      "loss": 0.067,
+      "step": 410
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "eval_accuracy": 0.9403703703703704,
+      "eval_f1": 0.9435285864608909,
+      "eval_loss": 0.20395933091640472,
+      "eval_precision": 0.8960692871419054,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9919632373113855,
+      "eval_runtime": 5.5068,
+      "eval_samples_per_second": 490.299,
+      "eval_steps_per_second": 15.435,
+      "step": 410
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 5.374762058258057,
+      "learning_rate": 9.476493011435832e-05,
+      "loss": 0.0581,
+      "step": 420
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_accuracy": 0.9362962962962963,
+      "eval_f1": 0.9399021663172606,
+      "eval_loss": 0.21634648740291595,
+      "eval_precision": 0.8895502645502645,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9913909465020577,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.778,
+      "eval_steps_per_second": 15.419,
+      "step": 420
+    },
+    {
+      "epoch": 0.273015873015873,
+      "grad_norm": 0.1900794953107834,
+      "learning_rate": 9.463786531130877e-05,
+      "loss": 0.0425,
+      "step": 430
+    },
+    {
+      "epoch": 0.273015873015873,
+      "eval_accuracy": 0.9018518518518519,
+      "eval_f1": 0.9104427171341669,
+      "eval_loss": 0.3560587167739868,
+      "eval_precision": 0.8371659415786202,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9883901234567901,
+      "eval_runtime": 5.5144,
+      "eval_samples_per_second": 489.628,
+      "eval_steps_per_second": 15.414,
+      "step": 430
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "grad_norm": 0.9057045578956604,
+      "learning_rate": 9.451080050825921e-05,
+      "loss": 0.0736,
+      "step": 440
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "eval_accuracy": 0.8792592592592593,
+      "eval_f1": 0.8921244209133025,
+      "eval_loss": 0.4899263083934784,
+      "eval_precision": 0.80622009569378,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9859388203017831,
+      "eval_runtime": 5.5176,
+      "eval_samples_per_second": 489.34,
+      "eval_steps_per_second": 15.405,
+      "step": 440
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 12.068155288696289,
+      "learning_rate": 9.438373570520967e-05,
+      "loss": 0.0788,
+      "step": 450
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_accuracy": 0.9311111111111111,
+      "eval_f1": 0.935326842837274,
+      "eval_loss": 0.27715030312538147,
+      "eval_precision": 0.8813892529488859,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.990839231824417,
+      "eval_runtime": 5.5146,
+      "eval_samples_per_second": 489.612,
+      "eval_steps_per_second": 15.414,
+      "step": 450
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "grad_norm": 0.20492731034755707,
+      "learning_rate": 9.425667090216011e-05,
+      "loss": 0.1801,
+      "step": 460
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "eval_accuracy": 0.924074074074074,
+      "eval_f1": 0.9292371418709009,
+      "eval_loss": 0.32135429978370667,
+      "eval_precision": 0.870071105365223,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9897657064471879,
+      "eval_runtime": 5.5135,
+      "eval_samples_per_second": 489.707,
+      "eval_steps_per_second": 15.417,
+      "step": 460
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "grad_norm": 0.016238894313573837,
+      "learning_rate": 9.412960609911055e-05,
+      "loss": 0.0886,
+      "step": 470
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "eval_accuracy": 0.9348148148148148,
+      "eval_f1": 0.9385045422781272,
+      "eval_loss": 0.26370832324028015,
+      "eval_precision": 0.8882275132275133,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9905368998628258,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.473,
+      "eval_steps_per_second": 15.409,
+      "step": 470
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.18422342836856842,
+      "learning_rate": 9.400254129606099e-05,
+      "loss": 0.0303,
+      "step": 480
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_accuracy": 0.8840740740740741,
+      "eval_f1": 0.8959095443964084,
+      "eval_loss": 0.4938906133174896,
+      "eval_precision": 0.8129149064574532,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9840238683127571,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.015,
+      "eval_steps_per_second": 15.395,
+      "step": 480
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.018785802647471428,
+      "learning_rate": 9.387547649301143e-05,
+      "loss": 0.0849,
+      "step": 490
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "eval_accuracy": 0.914074074074074,
+      "eval_f1": 0.920656634746922,
+      "eval_loss": 0.3513197600841522,
+      "eval_precision": 0.855146124523507,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9879089163237311,
+      "eval_runtime": 5.5492,
+      "eval_samples_per_second": 486.557,
+      "eval_steps_per_second": 15.318,
+      "step": 490
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 17.461837768554688,
+      "learning_rate": 9.374841168996189e-05,
+      "loss": 0.2025,
+      "step": 500
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_accuracy": 0.9414814814814815,
+      "eval_f1": 0.9443661971830986,
+      "eval_loss": 0.23329515755176544,
+      "eval_precision": 0.9,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.990923182441701,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.954,
+      "eval_steps_per_second": 15.393,
+      "step": 500
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 0.4385194182395935,
+      "learning_rate": 9.362134688691233e-05,
+      "loss": 0.4251,
+      "step": 510
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "eval_accuracy": 0.952962962962963,
+      "eval_f1": 0.9547559672247952,
+      "eval_loss": 0.17835260927677155,
+      "eval_precision": 0.9196980096087852,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9925997256515775,
+      "eval_runtime": 5.5197,
+      "eval_samples_per_second": 489.161,
+      "eval_steps_per_second": 15.4,
+      "step": 510
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "grad_norm": 2.7863709926605225,
+      "learning_rate": 9.349428208386277e-05,
+      "loss": 0.1384,
+      "step": 520
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "eval_accuracy": 0.9525925925925925,
+      "eval_f1": 0.9543834640057021,
+      "eval_loss": 0.17517130076885223,
+      "eval_precision": 0.9196428571428571,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9930340192043895,
+      "eval_runtime": 5.5216,
+      "eval_samples_per_second": 488.99,
+      "eval_steps_per_second": 15.394,
+      "step": 520
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "grad_norm": 0.09477631747722626,
+      "learning_rate": 9.336721728081323e-05,
+      "loss": 0.0516,
+      "step": 530
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "eval_accuracy": 0.94,
+      "eval_f1": 0.9430379746835443,
+      "eval_loss": 0.2342747449874878,
+      "eval_precision": 0.8975903614457831,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9920493827160494,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.195,
+      "eval_steps_per_second": 15.401,
+      "step": 530
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.060261718928813934,
+      "learning_rate": 9.324015247776366e-05,
+      "loss": 0.0048,
+      "step": 540
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "eval_accuracy": 0.927037037037037,
+      "eval_f1": 0.9316684009712105,
+      "eval_loss": 0.2969974875450134,
+      "eval_precision": 0.8760600130463144,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.991082853223594,
+      "eval_runtime": 5.5259,
+      "eval_samples_per_second": 488.608,
+      "eval_steps_per_second": 15.382,
+      "step": 540
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.1148306354880333,
+      "learning_rate": 9.31130876747141e-05,
+      "loss": 0.0832,
+      "step": 550
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "eval_accuracy": 0.96,
+      "eval_f1": 0.9609544468546638,
+      "eval_loss": 0.1580500602722168,
+      "eval_precision": 0.9385593220338984,
+      "eval_recall": 0.9844444444444445,
+      "eval_roc_auc": 0.9940183813443072,
+      "eval_runtime": 5.5217,
+      "eval_samples_per_second": 488.978,
+      "eval_steps_per_second": 15.394,
+      "step": 550
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.034114107489585876,
+      "learning_rate": 9.298602287166456e-05,
+      "loss": 0.1202,
+      "step": 560
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_accuracy": 0.9485185185185185,
+      "eval_f1": 0.9507266926621766,
+      "eval_loss": 0.23128464818000793,
+      "eval_precision": 0.91162474507138,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9926241426611797,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.125,
+      "eval_steps_per_second": 15.398,
+      "step": 560
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 0.02656545117497444,
+      "learning_rate": 9.2858958068615e-05,
+      "loss": 0.1321,
+      "step": 570
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "eval_accuracy": 0.9514814814814815,
+      "eval_f1": 0.9534635879218473,
+      "eval_loss": 0.22296707332134247,
+      "eval_precision": 0.9160409556313993,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9931102880658437,
+      "eval_runtime": 5.5181,
+      "eval_samples_per_second": 489.3,
+      "eval_steps_per_second": 15.404,
+      "step": 570
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "grad_norm": 0.03909531608223915,
+      "learning_rate": 9.273189326556544e-05,
+      "loss": 0.0552,
+      "step": 580
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "eval_accuracy": 0.9092592592592592,
+      "eval_f1": 0.916695001700102,
+      "eval_loss": 0.4478496313095093,
+      "eval_precision": 0.8472658705216844,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9875185185185186,
+      "eval_runtime": 5.5291,
+      "eval_samples_per_second": 488.323,
+      "eval_steps_per_second": 15.373,
+      "step": 580
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "grad_norm": 0.01843447797000408,
+      "learning_rate": 9.26048284625159e-05,
+      "loss": 0.1449,
+      "step": 590
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9101958136394328,
+      "eval_loss": 0.4929225444793701,
+      "eval_precision": 0.8362282878411911,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.985960768175583,
+      "eval_runtime": 5.5503,
+      "eval_samples_per_second": 486.461,
+      "eval_steps_per_second": 15.315,
+      "step": 590
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.1456720530986786,
+      "learning_rate": 9.249047013977129e-05,
+      "loss": 0.068,
+      "step": 600
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9401888772298006,
+      "eval_loss": 0.29736340045928955,
+      "eval_precision": 0.8906560636182903,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9906285322359396,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.726,
+      "eval_steps_per_second": 15.386,
+      "step": 600
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "grad_norm": 0.00903715193271637,
+      "learning_rate": 9.236340533672173e-05,
+      "loss": 0.0065,
+      "step": 610
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "eval_accuracy": 0.9588888888888889,
+      "eval_f1": 0.9601436265709156,
+      "eval_loss": 0.19618448615074158,
+      "eval_precision": 0.9317073170731708,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9935338820301782,
+      "eval_runtime": 5.5182,
+      "eval_samples_per_second": 489.287,
+      "eval_steps_per_second": 15.403,
+      "step": 610
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "grad_norm": 0.04093470424413681,
+      "learning_rate": 9.223634053367217e-05,
+      "loss": 0.131,
+      "step": 620
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3867323100566864,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9864683127572016,
+      "eval_runtime": 5.5187,
+      "eval_samples_per_second": 489.248,
+      "eval_steps_per_second": 15.402,
+      "step": 620
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.493297576904297,
+      "learning_rate": 9.210927573062263e-05,
+      "loss": 0.2599,
+      "step": 630
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.8918518518518519,
+      "eval_f1": 0.9022757697456493,
+      "eval_loss": 0.5704190731048584,
+      "eval_precision": 0.8229548229548229,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.981446364883402,
+      "eval_runtime": 5.5214,
+      "eval_samples_per_second": 489.005,
+      "eval_steps_per_second": 15.395,
+      "step": 630
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "grad_norm": 0.01696428842842579,
+      "learning_rate": 9.198221092757307e-05,
+      "loss": 0.0087,
+      "step": 640
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9324090121317158,
+      "eval_loss": 0.3256017863750458,
+      "eval_precision": 0.8762214983713354,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9897610425240055,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.017,
+      "eval_steps_per_second": 15.395,
+      "step": 640
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.01224907673895359,
+      "learning_rate": 9.185514612452351e-05,
+      "loss": 0.0602,
+      "step": 650
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "eval_accuracy": 0.9207407407407407,
+      "eval_f1": 0.9263592567102547,
+      "eval_loss": 0.3757924735546112,
+      "eval_precision": 0.8650385604113111,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9885146776406035,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.951,
+      "eval_steps_per_second": 15.393,
+      "step": 650
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "grad_norm": 0.01693762093782425,
+      "learning_rate": 9.172808132147396e-05,
+      "loss": 0.4184,
+      "step": 660
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "eval_accuracy": 0.9548148148148148,
+      "eval_f1": 0.9564285714285714,
+      "eval_loss": 0.1783735305070877,
+      "eval_precision": 0.923448275862069,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9926477366255145,
+      "eval_runtime": 5.5199,
+      "eval_samples_per_second": 489.135,
+      "eval_steps_per_second": 15.399,
+      "step": 660
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "grad_norm": 0.3128555119037628,
+      "learning_rate": 9.16010165184244e-05,
+      "loss": 0.0977,
+      "step": 670
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "eval_accuracy": 0.9492592592592592,
+      "eval_f1": 0.9513667021654242,
+      "eval_loss": 0.18898966908454895,
+      "eval_precision": 0.9134287661895024,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9929882030178325,
+      "eval_runtime": 5.513,
+      "eval_samples_per_second": 489.751,
+      "eval_steps_per_second": 15.418,
+      "step": 670
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "grad_norm": 7.7761383056640625,
+      "learning_rate": 9.147395171537485e-05,
+      "loss": 0.1996,
+      "step": 680
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "eval_accuracy": 0.9096296296296297,
+      "eval_f1": 0.9168937329700273,
+      "eval_loss": 0.3682536780834198,
+      "eval_precision": 0.8486759142496847,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9902880658436214,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.232,
+      "eval_steps_per_second": 15.402,
+      "step": 680
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "grad_norm": 0.04118531197309494,
+      "learning_rate": 9.13468869123253e-05,
+      "loss": 0.0329,
+      "step": 690
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "eval_accuracy": 0.9048148148148148,
+      "eval_f1": 0.9128518141742964,
+      "eval_loss": 0.38119447231292725,
+      "eval_precision": 0.841776110068793,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900367626886146,
+      "eval_runtime": 5.5111,
+      "eval_samples_per_second": 489.917,
+      "eval_steps_per_second": 15.423,
+      "step": 690
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.560464382171631,
+      "learning_rate": 9.121982210927574e-05,
+      "loss": 0.1425,
+      "step": 700
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9529579472558802,
+      "eval_loss": 0.177493155002594,
+      "eval_precision": 0.9182692307692307,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9938277091906722,
+      "eval_runtime": 5.5066,
+      "eval_samples_per_second": 490.322,
+      "eval_steps_per_second": 15.436,
+      "step": 700
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "grad_norm": 0.03769376501441002,
+      "learning_rate": 9.109275730622618e-05,
+      "loss": 0.1651,
+      "step": 710
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "eval_accuracy": 0.9448148148148148,
+      "eval_f1": 0.9474055771267208,
+      "eval_loss": 0.20647479593753815,
+      "eval_precision": 0.9049224544841538,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9933665294924554,
+      "eval_runtime": 5.5143,
+      "eval_samples_per_second": 489.634,
+      "eval_steps_per_second": 15.414,
+      "step": 710
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 10.711636543273926,
+      "learning_rate": 9.096569250317662e-05,
+      "loss": 0.1278,
+      "step": 720
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "eval_accuracy": 0.9359259259259259,
+      "eval_f1": 0.9395738735592036,
+      "eval_loss": 0.25338342785835266,
+      "eval_precision": 0.8889623265036352,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9929604938271603,
+      "eval_runtime": 5.5162,
+      "eval_samples_per_second": 489.471,
+      "eval_steps_per_second": 15.409,
+      "step": 720
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "grad_norm": 0.17392298579216003,
+      "learning_rate": 9.083862770012706e-05,
+      "loss": 0.0979,
+      "step": 730
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "eval_accuracy": 0.9440740740740741,
+      "eval_f1": 0.9468497008095741,
+      "eval_loss": 0.22556233406066895,
+      "eval_precision": 0.9020791415157612,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9937440329218106,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.224,
+      "eval_steps_per_second": 15.401,
+      "step": 730
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "grad_norm": 3.3036723136901855,
+      "learning_rate": 9.071156289707752e-05,
+      "loss": 0.0228,
+      "step": 740
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302004146510021,
+      "eval_loss": 0.317281037569046,
+      "eval_precision": 0.8717616580310881,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9925075445816187,
+      "eval_runtime": 5.5192,
+      "eval_samples_per_second": 489.2,
+      "eval_steps_per_second": 15.401,
+      "step": 740
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.8324198722839355,
+      "learning_rate": 9.058449809402796e-05,
+      "loss": 0.1754,
+      "step": 750
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_accuracy": 0.9581481481481482,
+      "eval_f1": 0.9594254937163376,
+      "eval_loss": 0.1706221103668213,
+      "eval_precision": 0.9310104529616725,
+      "eval_recall": 0.9896296296296296,
+      "eval_roc_auc": 0.9952694101508917,
+      "eval_runtime": 5.5194,
+      "eval_samples_per_second": 489.187,
+      "eval_steps_per_second": 15.4,
+      "step": 750
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "grad_norm": 0.046114906668663025,
+      "learning_rate": 9.04574332909784e-05,
+      "loss": 0.0727,
+      "step": 760
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "eval_accuracy": 0.9088888888888889,
+      "eval_f1": 0.9163265306122449,
+      "eval_loss": 0.42058730125427246,
+      "eval_precision": 0.8471698113207548,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9914013717421125,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.781,
+      "eval_steps_per_second": 15.419,
+      "step": 760
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.3374621272087097,
+      "learning_rate": 9.033036848792885e-05,
+      "loss": 0.1076,
+      "step": 770
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9438596491228071,
+      "eval_loss": 0.2562646269798279,
+      "eval_precision": 0.8966666666666666,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.993437585733882,
+      "eval_runtime": 5.5242,
+      "eval_samples_per_second": 488.761,
+      "eval_steps_per_second": 15.387,
+      "step": 770
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "grad_norm": 0.027243219316005707,
+      "learning_rate": 9.020330368487929e-05,
+      "loss": 0.0842,
+      "step": 780
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "eval_accuracy": 0.9633333333333334,
+      "eval_f1": 0.9640130861504908,
+      "eval_loss": 0.14165127277374268,
+      "eval_precision": 0.9464668094218416,
+      "eval_recall": 0.9822222222222222,
+      "eval_roc_auc": 0.9951972565157751,
+      "eval_runtime": 5.5142,
+      "eval_samples_per_second": 489.648,
+      "eval_steps_per_second": 15.415,
+      "step": 780
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "grad_norm": 1.7387934923171997,
+      "learning_rate": 9.007623888182973e-05,
+      "loss": 0.134,
+      "step": 790
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "eval_accuracy": 0.9577777777777777,
+      "eval_f1": 0.958963282937365,
+      "eval_loss": 0.1754920780658722,
+      "eval_precision": 0.9327731092436975,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.994798353909465,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.682,
+      "eval_steps_per_second": 15.416,
+      "step": 790
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 50,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 47
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-790/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7681486b047f585cb3d4a74af864b81970cea49ab8306649b824b3f75ec278d
+size 5432

checkpoint-800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Alibaba-NLP/gte-multilingual-base
+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 0.15.1

checkpoint-800/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score",
+    "classifier",
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299a8e0e1e5c31a3a88f198a8aa86bb9e4385e3aab7d50e06f9ab18945af5499
+size 3549156

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e823ea18b52dea7783619a9da4eadc1d5717cb251fc04577ed8bc0456f1e130e
+size 11839994

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5473ad39ccc132f0fd791bb36a2a07d10794102860ea2aa851479570ebd274
+size 14244

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd6523e2235324d4e70aabfbd47a2ac773386ef2a0f899ed705a9b0dc14d8bc
+size 1000

checkpoint-800/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

checkpoint-800/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,1642 @@
+{
+  "best_metric": 0.1395142674446106,
+  "best_model_checkpoint": "/home/steam3/origin-ai/results/multilingual-train-test-table-results/ablation-arabic-mgte/arabic_chatgpt__3__bulgarian_true-and-fake-news_chatgpt;russian_chatgpt;bulgarian_true-and-fake-news_davinci/checkpoint-320",
+  "epoch": 0.5079365079365079,
+  "eval_steps": 10,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006349206349206349,
+      "grad_norm": 3.314401388168335,
+      "learning_rate": 9.993646759847523e-05,
+      "loss": 0.6929,
+      "step": 10
+    },
+    {
+      "epoch": 0.006349206349206349,
+      "eval_accuracy": 0.5251851851851852,
+      "eval_f1": 0.6566684520621318,
+      "eval_loss": 0.6887626647949219,
+      "eval_precision": 0.514261744966443,
+      "eval_recall": 0.9081481481481481,
+      "eval_roc_auc": 0.5891390946502058,
+      "eval_runtime": 5.5333,
+      "eval_samples_per_second": 487.955,
+      "eval_steps_per_second": 15.362,
+      "step": 10
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "grad_norm": 2.6429762840270996,
+      "learning_rate": 9.980940279542568e-05,
+      "loss": 0.688,
+      "step": 20
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "eval_accuracy": 0.5637037037037037,
+      "eval_f1": 0.2929171668667467,
+      "eval_loss": 0.674746036529541,
+      "eval_precision": 0.7721518987341772,
+      "eval_recall": 0.18074074074074073,
+      "eval_roc_auc": 0.6710831275720164,
+      "eval_runtime": 5.528,
+      "eval_samples_per_second": 488.42,
+      "eval_steps_per_second": 15.376,
+      "step": 20
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "grad_norm": 3.3568179607391357,
+      "learning_rate": 9.968233799237612e-05,
+      "loss": 0.6482,
+      "step": 30
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "eval_accuracy": 0.5981481481481481,
+      "eval_f1": 0.3710144927536232,
+      "eval_loss": 0.6537347435951233,
+      "eval_precision": 0.8533333333333334,
+      "eval_recall": 0.23703703703703705,
+      "eval_roc_auc": 0.7466732510288066,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.853,
+      "eval_steps_per_second": 15.421,
+      "step": 30
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "grad_norm": 2.775456666946411,
+      "learning_rate": 9.955527318932655e-05,
+      "loss": 0.6524,
+      "step": 40
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "eval_accuracy": 0.7307407407407407,
+      "eval_f1": 0.7163480296527507,
+      "eval_loss": 0.6117509603500366,
+      "eval_precision": 0.7568013190436933,
+      "eval_recall": 0.68,
+      "eval_roc_auc": 0.8087465020576132,
+      "eval_runtime": 5.5237,
+      "eval_samples_per_second": 488.803,
+      "eval_steps_per_second": 15.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.0409586429595947,
+      "learning_rate": 9.942820838627701e-05,
+      "loss": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_f1": 0.7790883009244501,
+      "eval_loss": 0.5712039470672607,
+      "eval_precision": 0.6838276440962507,
+      "eval_recall": 0.9051851851851852,
+      "eval_roc_auc": 0.8662809327846365,
+      "eval_runtime": 5.5269,
+      "eval_samples_per_second": 488.52,
+      "eval_steps_per_second": 15.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 5.313755035400391,
+      "learning_rate": 9.930114358322745e-05,
+      "loss": 0.5608,
+      "step": 60
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8195937873357229,
+      "eval_loss": 0.48943084478378296,
+      "eval_precision": 0.8863049095607235,
+      "eval_recall": 0.7622222222222222,
+      "eval_roc_auc": 0.9197953360768176,
+      "eval_runtime": 5.541,
+      "eval_samples_per_second": 487.279,
+      "eval_steps_per_second": 15.34,
+      "step": 60
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.1755828857421875,
+      "learning_rate": 9.91740787801779e-05,
+      "loss": 0.4534,
+      "step": 70
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8533505988993202,
+      "eval_loss": 0.4028916656970978,
+      "eval_precision": 0.757906843013226,
+      "eval_recall": 0.9762962962962963,
+      "eval_roc_auc": 0.95520438957476,
+      "eval_runtime": 5.5166,
+      "eval_samples_per_second": 489.434,
+      "eval_steps_per_second": 15.408,
+      "step": 70
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "grad_norm": 2.359863758087158,
+      "learning_rate": 9.904701397712835e-05,
+      "loss": 0.2939,
+      "step": 80
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "eval_accuracy": 0.87,
+      "eval_f1": 0.882804674457429,
+      "eval_loss": 0.30669787526130676,
+      "eval_precision": 0.8036474164133739,
+      "eval_recall": 0.9792592592592593,
+      "eval_roc_auc": 0.967720987654321,
+      "eval_runtime": 5.5661,
+      "eval_samples_per_second": 485.082,
+      "eval_steps_per_second": 15.271,
+      "step": 80
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 2.1184494495391846,
+      "learning_rate": 9.893265565438374e-05,
+      "loss": 0.2494,
+      "step": 90
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "eval_accuracy": 0.9244444444444444,
+      "eval_f1": 0.9246676514032496,
+      "eval_loss": 0.19904199242591858,
+      "eval_precision": 0.9219440353460973,
+      "eval_recall": 0.9274074074074075,
+      "eval_roc_auc": 0.9763517146776406,
+      "eval_runtime": 5.5491,
+      "eval_samples_per_second": 486.564,
+      "eval_steps_per_second": 15.318,
+      "step": 90
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.1063764095306396,
+      "learning_rate": 9.880559085133418e-05,
+      "loss": 0.174,
+      "step": 100
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "eval_accuracy": 0.8692592592592593,
+      "eval_f1": 0.8829963539940338,
+      "eval_loss": 0.4303587079048157,
+      "eval_precision": 0.7990401919616077,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.9744661179698217,
+      "eval_runtime": 5.5309,
+      "eval_samples_per_second": 488.17,
+      "eval_steps_per_second": 15.368,
+      "step": 100
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "grad_norm": 11.44679069519043,
+      "learning_rate": 9.869123252858958e-05,
+      "loss": 0.269,
+      "step": 110
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9302824454772971,
+      "eval_loss": 0.2445582151412964,
+      "eval_precision": 0.899101589495508,
+      "eval_recall": 0.9637037037037037,
+      "eval_roc_auc": 0.9810120713305899,
+      "eval_runtime": 5.5203,
+      "eval_samples_per_second": 489.102,
+      "eval_steps_per_second": 15.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.09498822689056396,
+      "learning_rate": 9.856416772554004e-05,
+      "loss": 0.1981,
+      "step": 120
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "eval_accuracy": 0.9303703703703704,
+      "eval_f1": 0.9330960854092527,
+      "eval_loss": 0.24259698390960693,
+      "eval_precision": 0.897945205479452,
+      "eval_recall": 0.9711111111111111,
+      "eval_roc_auc": 0.9832271604938272,
+      "eval_runtime": 5.5208,
+      "eval_samples_per_second": 489.057,
+      "eval_steps_per_second": 15.396,
+      "step": 120
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "grad_norm": 0.047983940690755844,
+      "learning_rate": 9.843710292249048e-05,
+      "loss": 0.2035,
+      "step": 130
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "eval_accuracy": 0.9288888888888889,
+      "eval_f1": 0.9320594479830149,
+      "eval_loss": 0.2548026740550995,
+      "eval_precision": 0.8922764227642277,
+      "eval_recall": 0.9755555555555555,
+      "eval_roc_auc": 0.9850041152263376,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 130
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.1345868706703186,
+      "learning_rate": 9.831003811944091e-05,
+      "loss": 0.2392,
+      "step": 140
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "eval_accuracy": 0.9214814814814815,
+      "eval_f1": 0.9260293091416608,
+      "eval_loss": 0.28311270475387573,
+      "eval_precision": 0.8753298153034301,
+      "eval_recall": 0.9829629629629629,
+      "eval_roc_auc": 0.9863648834019204,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.727,
+      "eval_steps_per_second": 15.386,
+      "step": 140
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.3760770559310913,
+      "learning_rate": 9.818297331639137e-05,
+      "loss": 0.1965,
+      "step": 150
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_accuracy": 0.8429629629629629,
+      "eval_f1": 0.8640153944836434,
+      "eval_loss": 0.5912654995918274,
+      "eval_precision": 0.7618778280542986,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9832545953360768,
+      "eval_runtime": 5.5302,
+      "eval_samples_per_second": 488.232,
+      "eval_steps_per_second": 15.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "grad_norm": 3.2790462970733643,
+      "learning_rate": 9.805590851334181e-05,
+      "loss": 0.3521,
+      "step": 160
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "eval_accuracy": 0.9185185185185185,
+      "eval_f1": 0.9238754325259516,
+      "eval_loss": 0.25474533438682556,
+      "eval_precision": 0.8668831168831169,
+      "eval_recall": 0.9888888888888889,
+      "eval_roc_auc": 0.9880035665294925,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.123,
+      "eval_steps_per_second": 15.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "grad_norm": 3.765111207962036,
+      "learning_rate": 9.792884371029225e-05,
+      "loss": 0.4232,
+      "step": 170
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "eval_accuracy": 0.9474074074074074,
+      "eval_f1": 0.9478324761204996,
+      "eval_loss": 0.14082331955432892,
+      "eval_precision": 0.9402332361516035,
+      "eval_recall": 0.9555555555555556,
+      "eval_roc_auc": 0.9880447187928669,
+      "eval_runtime": 5.5338,
+      "eval_samples_per_second": 487.911,
+      "eval_steps_per_second": 15.36,
+      "step": 170
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.110823154449463,
+      "learning_rate": 9.780177890724271e-05,
+      "loss": 0.1239,
+      "step": 180
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9098915989159891,
+      "eval_loss": 0.26993757486343384,
+      "eval_precision": 0.83832709113608,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9881753086419753,
+      "eval_runtime": 5.5165,
+      "eval_samples_per_second": 489.445,
+      "eval_steps_per_second": 15.408,
+      "step": 180
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "grad_norm": 1.8782886266708374,
+      "learning_rate": 9.767471410419315e-05,
+      "loss": 0.1301,
+      "step": 190
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9396825396825397,
+      "eval_loss": 0.17670103907585144,
+      "eval_precision": 0.896969696969697,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.989798353909465,
+      "eval_runtime": 5.514,
+      "eval_samples_per_second": 489.66,
+      "eval_steps_per_second": 15.415,
+      "step": 190
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 4.296081066131592,
+      "learning_rate": 9.754764930114358e-05,
+      "loss": 0.1532,
+      "step": 200
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9275563258232236,
+      "eval_loss": 0.25379836559295654,
+      "eval_precision": 0.8716612377850163,
+      "eval_recall": 0.9911111111111112,
+      "eval_roc_auc": 0.99000658436214,
+      "eval_runtime": 5.5116,
+      "eval_samples_per_second": 489.878,
+      "eval_steps_per_second": 15.422,
+      "step": 200
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.7609732151031494,
+      "learning_rate": 9.742058449809403e-05,
+      "loss": 0.2815,
+      "step": 210
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_accuracy": 0.9285185185185185,
+      "eval_f1": 0.9328695652173913,
+      "eval_loss": 0.24461880326271057,
+      "eval_precision": 0.879344262295082,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9911909465020576,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.978,
+      "eval_steps_per_second": 15.425,
+      "step": 210
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "grad_norm": 0.20786483585834503,
+      "learning_rate": 9.729351969504448e-05,
+      "loss": 0.1336,
+      "step": 220
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "eval_accuracy": 0.9518518518518518,
+      "eval_f1": 0.9534717251252685,
+      "eval_loss": 0.1563795804977417,
+      "eval_precision": 0.9224376731301939,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.992451303155007,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.68,
+      "eval_steps_per_second": 15.416,
+      "step": 220
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "grad_norm": 0.6910555362701416,
+      "learning_rate": 9.716645489199492e-05,
+      "loss": 0.1237,
+      "step": 230
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "eval_accuracy": 0.937037037037037,
+      "eval_f1": 0.9404344779257183,
+      "eval_loss": 0.22764083743095398,
+      "eval_precision": 0.8922872340425532,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9923105624142661,
+      "eval_runtime": 5.5171,
+      "eval_samples_per_second": 489.388,
+      "eval_steps_per_second": 15.407,
+      "step": 230
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.4784867763519287,
+      "learning_rate": 9.703939008894538e-05,
+      "loss": 0.063,
+      "step": 240
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "eval_accuracy": 0.8637037037037038,
+      "eval_f1": 0.8799739073711677,
+      "eval_loss": 0.616968035697937,
+      "eval_precision": 0.7861305361305362,
+      "eval_recall": 0.9992592592592593,
+      "eval_roc_auc": 0.9860919067215363,
+      "eval_runtime": 5.5121,
+      "eval_samples_per_second": 489.827,
+      "eval_steps_per_second": 15.42,
+      "step": 240
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": NaN,
+      "learning_rate": 9.692503176620077e-05,
+      "loss": 0.1347,
+      "step": 250
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_accuracy": 0.9388888888888889,
+      "eval_f1": 0.9420442571127503,
+      "eval_loss": 0.24191488325595856,
+      "eval_precision": 0.8957915831663327,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9917956104252401,
+      "eval_runtime": 5.5139,
+      "eval_samples_per_second": 489.672,
+      "eval_steps_per_second": 15.416,
+      "step": 250
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "grad_norm": 9.05746078491211,
+      "learning_rate": 9.679796696315121e-05,
+      "loss": 0.1642,
+      "step": 260
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "eval_accuracy": 0.9425925925925925,
+      "eval_f1": 0.9452103216684341,
+      "eval_loss": 0.2284214049577713,
+      "eval_precision": 0.9039891818796484,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9920307270233196,
+      "eval_runtime": 5.5153,
+      "eval_samples_per_second": 489.547,
+      "eval_steps_per_second": 15.412,
+      "step": 260
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.0563305616378784,
+      "learning_rate": 9.667090216010166e-05,
+      "loss": 0.1503,
+      "step": 270
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "eval_accuracy": 0.894074074074074,
+      "eval_f1": 0.9040912139503688,
+      "eval_loss": 0.4835222661495209,
+      "eval_precision": 0.8259803921568627,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9872872427983539,
+      "eval_runtime": 5.5128,
+      "eval_samples_per_second": 489.765,
+      "eval_steps_per_second": 15.419,
+      "step": 270
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.09033135324716568,
+      "learning_rate": 9.65438373570521e-05,
+      "loss": 0.0974,
+      "step": 280
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_accuracy": 0.9507407407407408,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.19544483721256256,
+      "eval_precision": 0.9216909216909217,
+      "eval_recall": 0.9851851851851852,
+      "eval_roc_auc": 0.9924573388203017,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.975,
+      "eval_steps_per_second": 15.425,
+      "step": 280
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "grad_norm": 0.0589861236512661,
+      "learning_rate": 9.641677255400255e-05,
+      "loss": 0.1201,
+      "step": 290
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "eval_accuracy": 0.9174074074074074,
+      "eval_f1": 0.923394022672621,
+      "eval_loss": 0.3497244715690613,
+      "eval_precision": 0.8609865470852018,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9902913580246913,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.85,
+      "eval_steps_per_second": 15.421,
+      "step": 290
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.337423324584961,
+      "learning_rate": 9.628970775095299e-05,
+      "loss": 0.1636,
+      "step": 300
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "eval_accuracy": 0.8674074074074074,
+      "eval_f1": 0.882699868938401,
+      "eval_loss": 0.6298528909683228,
+      "eval_precision": 0.7914218566392479,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.985441975308642,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.684,
+      "eval_steps_per_second": 15.416,
+      "step": 300
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "grad_norm": 5.734988212585449,
+      "learning_rate": 9.616264294790343e-05,
+      "loss": 0.2139,
+      "step": 310
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "eval_accuracy": 0.9418518518518518,
+      "eval_f1": 0.944620811287478,
+      "eval_loss": 0.20854391157627106,
+      "eval_precision": 0.9016835016835016,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9917333333333334,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.776,
+      "eval_steps_per_second": 15.419,
+      "step": 310
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "grad_norm": 0.2367023378610611,
+      "learning_rate": 9.603557814485387e-05,
+      "loss": 0.1894,
+      "step": 320
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "eval_accuracy": 0.9562962962962963,
+      "eval_f1": 0.9572463768115942,
+      "eval_loss": 0.1395142674446106,
+      "eval_precision": 0.9368794326241134,
+      "eval_recall": 0.9785185185185186,
+      "eval_roc_auc": 0.9925939643347051,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.717,
+      "eval_steps_per_second": 15.417,
+      "step": 320
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 14.949374198913574,
+      "learning_rate": 9.590851334180433e-05,
+      "loss": 0.057,
+      "step": 330
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "eval_accuracy": 0.9255555555555556,
+      "eval_f1": 0.9305219495333564,
+      "eval_loss": 0.29976287484169006,
+      "eval_precision": 0.8723266364225535,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900480109739369,
+      "eval_runtime": 5.5137,
+      "eval_samples_per_second": 489.687,
+      "eval_steps_per_second": 15.416,
+      "step": 330
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "grad_norm": 3.3133888244628906,
+      "learning_rate": 9.578144853875477e-05,
+      "loss": 0.2029,
+      "step": 340
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3038364350795746,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9897953360768176,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.19,
+      "eval_steps_per_second": 15.4,
+      "step": 340
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.5984865427017212,
+      "learning_rate": 9.565438373570522e-05,
+      "loss": 0.0849,
+      "step": 350
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9525521207764198,
+      "eval_loss": 0.15116137266159058,
+      "eval_precision": 0.9252793296089385,
+      "eval_recall": 0.9814814814814815,
+      "eval_roc_auc": 0.9926340192043897,
+      "eval_runtime": 5.5231,
+      "eval_samples_per_second": 488.853,
+      "eval_steps_per_second": 15.39,
+      "step": 350
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 5.849670886993408,
+      "learning_rate": 9.552731893265566e-05,
+      "loss": 0.2559,
+      "step": 360
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "eval_accuracy": 0.9392592592592592,
+      "eval_f1": 0.9424561403508772,
+      "eval_loss": 0.22722864151000977,
+      "eval_precision": 0.8953333333333333,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9912104252400549,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 360
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "grad_norm": 0.2203754186630249,
+      "learning_rate": 9.54002541296061e-05,
+      "loss": 0.0809,
+      "step": 370
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9279061745429459,
+      "eval_loss": 0.29464688897132874,
+      "eval_precision": 0.868302130406714,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9903662551440329,
+      "eval_runtime": 5.5169,
+      "eval_samples_per_second": 489.409,
+      "eval_steps_per_second": 15.407,
+      "step": 370
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "grad_norm": 9.942216873168945,
+      "learning_rate": 9.527318932655654e-05,
+      "loss": 0.193,
+      "step": 380
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9436222692036645,
+      "eval_loss": 0.20582349598407745,
+      "eval_precision": 0.8998655913978495,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9918285322359396,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.479,
+      "eval_steps_per_second": 15.41,
+      "step": 380
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 11.672406196594238,
+      "learning_rate": 9.5146124523507e-05,
+      "loss": 0.208,
+      "step": 390
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "eval_accuracy": 0.9296296296296296,
+      "eval_f1": 0.9339360222531293,
+      "eval_loss": 0.24709771573543549,
+      "eval_precision": 0.8800786369593709,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9910834019204389,
+      "eval_runtime": 5.5183,
+      "eval_samples_per_second": 489.282,
+      "eval_steps_per_second": 15.403,
+      "step": 390
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.7513141632080078,
+      "learning_rate": 9.501905972045744e-05,
+      "loss": 0.141,
+      "step": 400
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "eval_accuracy": 0.9248148148148149,
+      "eval_f1": 0.9298306256481161,
+      "eval_loss": 0.2548695504665375,
+      "eval_precision": 0.8716785482825664,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9910268861454047,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.718,
+      "eval_steps_per_second": 15.417,
+      "step": 400
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "grad_norm": 0.11584247648715973,
+      "learning_rate": 9.489199491740788e-05,
+      "loss": 0.067,
+      "step": 410
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "eval_accuracy": 0.9403703703703704,
+      "eval_f1": 0.9435285864608909,
+      "eval_loss": 0.20395933091640472,
+      "eval_precision": 0.8960692871419054,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9919632373113855,
+      "eval_runtime": 5.5068,
+      "eval_samples_per_second": 490.299,
+      "eval_steps_per_second": 15.435,
+      "step": 410
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 5.374762058258057,
+      "learning_rate": 9.476493011435832e-05,
+      "loss": 0.0581,
+      "step": 420
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_accuracy": 0.9362962962962963,
+      "eval_f1": 0.9399021663172606,
+      "eval_loss": 0.21634648740291595,
+      "eval_precision": 0.8895502645502645,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9913909465020577,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.778,
+      "eval_steps_per_second": 15.419,
+      "step": 420
+    },
+    {
+      "epoch": 0.273015873015873,
+      "grad_norm": 0.1900794953107834,
+      "learning_rate": 9.463786531130877e-05,
+      "loss": 0.0425,
+      "step": 430
+    },
+    {
+      "epoch": 0.273015873015873,
+      "eval_accuracy": 0.9018518518518519,
+      "eval_f1": 0.9104427171341669,
+      "eval_loss": 0.3560587167739868,
+      "eval_precision": 0.8371659415786202,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9883901234567901,
+      "eval_runtime": 5.5144,
+      "eval_samples_per_second": 489.628,
+      "eval_steps_per_second": 15.414,
+      "step": 430
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "grad_norm": 0.9057045578956604,
+      "learning_rate": 9.451080050825921e-05,
+      "loss": 0.0736,
+      "step": 440
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "eval_accuracy": 0.8792592592592593,
+      "eval_f1": 0.8921244209133025,
+      "eval_loss": 0.4899263083934784,
+      "eval_precision": 0.80622009569378,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9859388203017831,
+      "eval_runtime": 5.5176,
+      "eval_samples_per_second": 489.34,
+      "eval_steps_per_second": 15.405,
+      "step": 440
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 12.068155288696289,
+      "learning_rate": 9.438373570520967e-05,
+      "loss": 0.0788,
+      "step": 450
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_accuracy": 0.9311111111111111,
+      "eval_f1": 0.935326842837274,
+      "eval_loss": 0.27715030312538147,
+      "eval_precision": 0.8813892529488859,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.990839231824417,
+      "eval_runtime": 5.5146,
+      "eval_samples_per_second": 489.612,
+      "eval_steps_per_second": 15.414,
+      "step": 450
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "grad_norm": 0.20492731034755707,
+      "learning_rate": 9.425667090216011e-05,
+      "loss": 0.1801,
+      "step": 460
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "eval_accuracy": 0.924074074074074,
+      "eval_f1": 0.9292371418709009,
+      "eval_loss": 0.32135429978370667,
+      "eval_precision": 0.870071105365223,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9897657064471879,
+      "eval_runtime": 5.5135,
+      "eval_samples_per_second": 489.707,
+      "eval_steps_per_second": 15.417,
+      "step": 460
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "grad_norm": 0.016238894313573837,
+      "learning_rate": 9.412960609911055e-05,
+      "loss": 0.0886,
+      "step": 470
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "eval_accuracy": 0.9348148148148148,
+      "eval_f1": 0.9385045422781272,
+      "eval_loss": 0.26370832324028015,
+      "eval_precision": 0.8882275132275133,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9905368998628258,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.473,
+      "eval_steps_per_second": 15.409,
+      "step": 470
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.18422342836856842,
+      "learning_rate": 9.400254129606099e-05,
+      "loss": 0.0303,
+      "step": 480
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_accuracy": 0.8840740740740741,
+      "eval_f1": 0.8959095443964084,
+      "eval_loss": 0.4938906133174896,
+      "eval_precision": 0.8129149064574532,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9840238683127571,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.015,
+      "eval_steps_per_second": 15.395,
+      "step": 480
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.018785802647471428,
+      "learning_rate": 9.387547649301143e-05,
+      "loss": 0.0849,
+      "step": 490
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "eval_accuracy": 0.914074074074074,
+      "eval_f1": 0.920656634746922,
+      "eval_loss": 0.3513197600841522,
+      "eval_precision": 0.855146124523507,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9879089163237311,
+      "eval_runtime": 5.5492,
+      "eval_samples_per_second": 486.557,
+      "eval_steps_per_second": 15.318,
+      "step": 490
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 17.461837768554688,
+      "learning_rate": 9.374841168996189e-05,
+      "loss": 0.2025,
+      "step": 500
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_accuracy": 0.9414814814814815,
+      "eval_f1": 0.9443661971830986,
+      "eval_loss": 0.23329515755176544,
+      "eval_precision": 0.9,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.990923182441701,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.954,
+      "eval_steps_per_second": 15.393,
+      "step": 500
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 0.4385194182395935,
+      "learning_rate": 9.362134688691233e-05,
+      "loss": 0.4251,
+      "step": 510
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "eval_accuracy": 0.952962962962963,
+      "eval_f1": 0.9547559672247952,
+      "eval_loss": 0.17835260927677155,
+      "eval_precision": 0.9196980096087852,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9925997256515775,
+      "eval_runtime": 5.5197,
+      "eval_samples_per_second": 489.161,
+      "eval_steps_per_second": 15.4,
+      "step": 510
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "grad_norm": 2.7863709926605225,
+      "learning_rate": 9.349428208386277e-05,
+      "loss": 0.1384,
+      "step": 520
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "eval_accuracy": 0.9525925925925925,
+      "eval_f1": 0.9543834640057021,
+      "eval_loss": 0.17517130076885223,
+      "eval_precision": 0.9196428571428571,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9930340192043895,
+      "eval_runtime": 5.5216,
+      "eval_samples_per_second": 488.99,
+      "eval_steps_per_second": 15.394,
+      "step": 520
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "grad_norm": 0.09477631747722626,
+      "learning_rate": 9.336721728081323e-05,
+      "loss": 0.0516,
+      "step": 530
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "eval_accuracy": 0.94,
+      "eval_f1": 0.9430379746835443,
+      "eval_loss": 0.2342747449874878,
+      "eval_precision": 0.8975903614457831,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9920493827160494,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.195,
+      "eval_steps_per_second": 15.401,
+      "step": 530
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.060261718928813934,
+      "learning_rate": 9.324015247776366e-05,
+      "loss": 0.0048,
+      "step": 540
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "eval_accuracy": 0.927037037037037,
+      "eval_f1": 0.9316684009712105,
+      "eval_loss": 0.2969974875450134,
+      "eval_precision": 0.8760600130463144,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.991082853223594,
+      "eval_runtime": 5.5259,
+      "eval_samples_per_second": 488.608,
+      "eval_steps_per_second": 15.382,
+      "step": 540
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.1148306354880333,
+      "learning_rate": 9.31130876747141e-05,
+      "loss": 0.0832,
+      "step": 550
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "eval_accuracy": 0.96,
+      "eval_f1": 0.9609544468546638,
+      "eval_loss": 0.1580500602722168,
+      "eval_precision": 0.9385593220338984,
+      "eval_recall": 0.9844444444444445,
+      "eval_roc_auc": 0.9940183813443072,
+      "eval_runtime": 5.5217,
+      "eval_samples_per_second": 488.978,
+      "eval_steps_per_second": 15.394,
+      "step": 550
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.034114107489585876,
+      "learning_rate": 9.298602287166456e-05,
+      "loss": 0.1202,
+      "step": 560
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_accuracy": 0.9485185185185185,
+      "eval_f1": 0.9507266926621766,
+      "eval_loss": 0.23128464818000793,
+      "eval_precision": 0.91162474507138,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9926241426611797,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.125,
+      "eval_steps_per_second": 15.398,
+      "step": 560
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 0.02656545117497444,
+      "learning_rate": 9.2858958068615e-05,
+      "loss": 0.1321,
+      "step": 570
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "eval_accuracy": 0.9514814814814815,
+      "eval_f1": 0.9534635879218473,
+      "eval_loss": 0.22296707332134247,
+      "eval_precision": 0.9160409556313993,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9931102880658437,
+      "eval_runtime": 5.5181,
+      "eval_samples_per_second": 489.3,
+      "eval_steps_per_second": 15.404,
+      "step": 570
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "grad_norm": 0.03909531608223915,
+      "learning_rate": 9.273189326556544e-05,
+      "loss": 0.0552,
+      "step": 580
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "eval_accuracy": 0.9092592592592592,
+      "eval_f1": 0.916695001700102,
+      "eval_loss": 0.4478496313095093,
+      "eval_precision": 0.8472658705216844,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9875185185185186,
+      "eval_runtime": 5.5291,
+      "eval_samples_per_second": 488.323,
+      "eval_steps_per_second": 15.373,
+      "step": 580
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "grad_norm": 0.01843447797000408,
+      "learning_rate": 9.26048284625159e-05,
+      "loss": 0.1449,
+      "step": 590
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9101958136394328,
+      "eval_loss": 0.4929225444793701,
+      "eval_precision": 0.8362282878411911,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.985960768175583,
+      "eval_runtime": 5.5503,
+      "eval_samples_per_second": 486.461,
+      "eval_steps_per_second": 15.315,
+      "step": 590
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.1456720530986786,
+      "learning_rate": 9.249047013977129e-05,
+      "loss": 0.068,
+      "step": 600
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9401888772298006,
+      "eval_loss": 0.29736340045928955,
+      "eval_precision": 0.8906560636182903,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9906285322359396,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.726,
+      "eval_steps_per_second": 15.386,
+      "step": 600
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "grad_norm": 0.00903715193271637,
+      "learning_rate": 9.236340533672173e-05,
+      "loss": 0.0065,
+      "step": 610
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "eval_accuracy": 0.9588888888888889,
+      "eval_f1": 0.9601436265709156,
+      "eval_loss": 0.19618448615074158,
+      "eval_precision": 0.9317073170731708,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9935338820301782,
+      "eval_runtime": 5.5182,
+      "eval_samples_per_second": 489.287,
+      "eval_steps_per_second": 15.403,
+      "step": 610
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "grad_norm": 0.04093470424413681,
+      "learning_rate": 9.223634053367217e-05,
+      "loss": 0.131,
+      "step": 620
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3867323100566864,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9864683127572016,
+      "eval_runtime": 5.5187,
+      "eval_samples_per_second": 489.248,
+      "eval_steps_per_second": 15.402,
+      "step": 620
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.493297576904297,
+      "learning_rate": 9.210927573062263e-05,
+      "loss": 0.2599,
+      "step": 630
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.8918518518518519,
+      "eval_f1": 0.9022757697456493,
+      "eval_loss": 0.5704190731048584,
+      "eval_precision": 0.8229548229548229,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.981446364883402,
+      "eval_runtime": 5.5214,
+      "eval_samples_per_second": 489.005,
+      "eval_steps_per_second": 15.395,
+      "step": 630
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "grad_norm": 0.01696428842842579,
+      "learning_rate": 9.198221092757307e-05,
+      "loss": 0.0087,
+      "step": 640
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9324090121317158,
+      "eval_loss": 0.3256017863750458,
+      "eval_precision": 0.8762214983713354,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9897610425240055,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.017,
+      "eval_steps_per_second": 15.395,
+      "step": 640
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.01224907673895359,
+      "learning_rate": 9.185514612452351e-05,
+      "loss": 0.0602,
+      "step": 650
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "eval_accuracy": 0.9207407407407407,
+      "eval_f1": 0.9263592567102547,
+      "eval_loss": 0.3757924735546112,
+      "eval_precision": 0.8650385604113111,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9885146776406035,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.951,
+      "eval_steps_per_second": 15.393,
+      "step": 650
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "grad_norm": 0.01693762093782425,
+      "learning_rate": 9.172808132147396e-05,
+      "loss": 0.4184,
+      "step": 660
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "eval_accuracy": 0.9548148148148148,
+      "eval_f1": 0.9564285714285714,
+      "eval_loss": 0.1783735305070877,
+      "eval_precision": 0.923448275862069,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9926477366255145,
+      "eval_runtime": 5.5199,
+      "eval_samples_per_second": 489.135,
+      "eval_steps_per_second": 15.399,
+      "step": 660
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "grad_norm": 0.3128555119037628,
+      "learning_rate": 9.16010165184244e-05,
+      "loss": 0.0977,
+      "step": 670
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "eval_accuracy": 0.9492592592592592,
+      "eval_f1": 0.9513667021654242,
+      "eval_loss": 0.18898966908454895,
+      "eval_precision": 0.9134287661895024,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9929882030178325,
+      "eval_runtime": 5.513,
+      "eval_samples_per_second": 489.751,
+      "eval_steps_per_second": 15.418,
+      "step": 670
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "grad_norm": 7.7761383056640625,
+      "learning_rate": 9.147395171537485e-05,
+      "loss": 0.1996,
+      "step": 680
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "eval_accuracy": 0.9096296296296297,
+      "eval_f1": 0.9168937329700273,
+      "eval_loss": 0.3682536780834198,
+      "eval_precision": 0.8486759142496847,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9902880658436214,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.232,
+      "eval_steps_per_second": 15.402,
+      "step": 680
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "grad_norm": 0.04118531197309494,
+      "learning_rate": 9.13468869123253e-05,
+      "loss": 0.0329,
+      "step": 690
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "eval_accuracy": 0.9048148148148148,
+      "eval_f1": 0.9128518141742964,
+      "eval_loss": 0.38119447231292725,
+      "eval_precision": 0.841776110068793,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900367626886146,
+      "eval_runtime": 5.5111,
+      "eval_samples_per_second": 489.917,
+      "eval_steps_per_second": 15.423,
+      "step": 690
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.560464382171631,
+      "learning_rate": 9.121982210927574e-05,
+      "loss": 0.1425,
+      "step": 700
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9529579472558802,
+      "eval_loss": 0.177493155002594,
+      "eval_precision": 0.9182692307692307,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9938277091906722,
+      "eval_runtime": 5.5066,
+      "eval_samples_per_second": 490.322,
+      "eval_steps_per_second": 15.436,
+      "step": 700
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "grad_norm": 0.03769376501441002,
+      "learning_rate": 9.109275730622618e-05,
+      "loss": 0.1651,
+      "step": 710
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "eval_accuracy": 0.9448148148148148,
+      "eval_f1": 0.9474055771267208,
+      "eval_loss": 0.20647479593753815,
+      "eval_precision": 0.9049224544841538,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9933665294924554,
+      "eval_runtime": 5.5143,
+      "eval_samples_per_second": 489.634,
+      "eval_steps_per_second": 15.414,
+      "step": 710
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 10.711636543273926,
+      "learning_rate": 9.096569250317662e-05,
+      "loss": 0.1278,
+      "step": 720
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "eval_accuracy": 0.9359259259259259,
+      "eval_f1": 0.9395738735592036,
+      "eval_loss": 0.25338342785835266,
+      "eval_precision": 0.8889623265036352,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9929604938271603,
+      "eval_runtime": 5.5162,
+      "eval_samples_per_second": 489.471,
+      "eval_steps_per_second": 15.409,
+      "step": 720
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "grad_norm": 0.17392298579216003,
+      "learning_rate": 9.083862770012706e-05,
+      "loss": 0.0979,
+      "step": 730
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "eval_accuracy": 0.9440740740740741,
+      "eval_f1": 0.9468497008095741,
+      "eval_loss": 0.22556233406066895,
+      "eval_precision": 0.9020791415157612,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9937440329218106,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.224,
+      "eval_steps_per_second": 15.401,
+      "step": 730
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "grad_norm": 3.3036723136901855,
+      "learning_rate": 9.071156289707752e-05,
+      "loss": 0.0228,
+      "step": 740
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302004146510021,
+      "eval_loss": 0.317281037569046,
+      "eval_precision": 0.8717616580310881,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9925075445816187,
+      "eval_runtime": 5.5192,
+      "eval_samples_per_second": 489.2,
+      "eval_steps_per_second": 15.401,
+      "step": 740
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.8324198722839355,
+      "learning_rate": 9.058449809402796e-05,
+      "loss": 0.1754,
+      "step": 750
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_accuracy": 0.9581481481481482,
+      "eval_f1": 0.9594254937163376,
+      "eval_loss": 0.1706221103668213,
+      "eval_precision": 0.9310104529616725,
+      "eval_recall": 0.9896296296296296,
+      "eval_roc_auc": 0.9952694101508917,
+      "eval_runtime": 5.5194,
+      "eval_samples_per_second": 489.187,
+      "eval_steps_per_second": 15.4,
+      "step": 750
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "grad_norm": 0.046114906668663025,
+      "learning_rate": 9.04574332909784e-05,
+      "loss": 0.0727,
+      "step": 760
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "eval_accuracy": 0.9088888888888889,
+      "eval_f1": 0.9163265306122449,
+      "eval_loss": 0.42058730125427246,
+      "eval_precision": 0.8471698113207548,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9914013717421125,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.781,
+      "eval_steps_per_second": 15.419,
+      "step": 760
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.3374621272087097,
+      "learning_rate": 9.033036848792885e-05,
+      "loss": 0.1076,
+      "step": 770
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9438596491228071,
+      "eval_loss": 0.2562646269798279,
+      "eval_precision": 0.8966666666666666,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.993437585733882,
+      "eval_runtime": 5.5242,
+      "eval_samples_per_second": 488.761,
+      "eval_steps_per_second": 15.387,
+      "step": 770
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "grad_norm": 0.027243219316005707,
+      "learning_rate": 9.020330368487929e-05,
+      "loss": 0.0842,
+      "step": 780
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "eval_accuracy": 0.9633333333333334,
+      "eval_f1": 0.9640130861504908,
+      "eval_loss": 0.14165127277374268,
+      "eval_precision": 0.9464668094218416,
+      "eval_recall": 0.9822222222222222,
+      "eval_roc_auc": 0.9951972565157751,
+      "eval_runtime": 5.5142,
+      "eval_samples_per_second": 489.648,
+      "eval_steps_per_second": 15.415,
+      "step": 780
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "grad_norm": 1.7387934923171997,
+      "learning_rate": 9.007623888182973e-05,
+      "loss": 0.134,
+      "step": 790
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "eval_accuracy": 0.9577777777777777,
+      "eval_f1": 0.958963282937365,
+      "eval_loss": 0.1754920780658722,
+      "eval_precision": 0.9327731092436975,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.994798353909465,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.682,
+      "eval_steps_per_second": 15.416,
+      "step": 790
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.11948162317276001,
+      "learning_rate": 8.994917407878019e-05,
+      "loss": 0.068,
+      "step": 800
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "eval_accuracy": 0.9596296296296296,
+      "eval_f1": 0.9608054656598346,
+      "eval_loss": 0.1783217042684555,
+      "eval_precision": 0.93361285814116,
+      "eval_recall": 0.9896296296296296,
+      "eval_roc_auc": 0.9951489711934156,
+      "eval_runtime": 5.5179,
+      "eval_samples_per_second": 489.316,
+      "eval_steps_per_second": 15.404,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 50,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 48
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7681486b047f585cb3d4a74af864b81970cea49ab8306649b824b3f75ec278d
+size 5432

checkpoint-810/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Alibaba-NLP/gte-multilingual-base
+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 0.15.1

checkpoint-810/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score",
+    "classifier",
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-810/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac28d74a51320708fac8f1202842e41b9a9079e17c4375d23141a0421383a7a
+size 3549156

checkpoint-810/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e18efad853ce72a3748c0f6fd0d1ff04eb632bd2771c975497f2ef3d2d0d62
+size 11839994

checkpoint-810/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf3a12a9b72736aec84ccbc888bbcb3900faa9ad6a9e8b251d8d70b260ead9a
+size 14244

checkpoint-810/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e2537ac6ba6e7b988533c51153f00d41efe27f6f75778a80d48c1ef086058a
+size 1000

checkpoint-810/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-810/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

checkpoint-810/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-810/trainer_state.json

@@ -0,0 +1,1662 @@
+{
+  "best_metric": 0.1395142674446106,
+  "best_model_checkpoint": "/home/steam3/origin-ai/results/multilingual-train-test-table-results/ablation-arabic-mgte/arabic_chatgpt__3__bulgarian_true-and-fake-news_chatgpt;russian_chatgpt;bulgarian_true-and-fake-news_davinci/checkpoint-320",
+  "epoch": 0.5142857142857142,
+  "eval_steps": 10,
+  "global_step": 810,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006349206349206349,
+      "grad_norm": 3.314401388168335,
+      "learning_rate": 9.993646759847523e-05,
+      "loss": 0.6929,
+      "step": 10
+    },
+    {
+      "epoch": 0.006349206349206349,
+      "eval_accuracy": 0.5251851851851852,
+      "eval_f1": 0.6566684520621318,
+      "eval_loss": 0.6887626647949219,
+      "eval_precision": 0.514261744966443,
+      "eval_recall": 0.9081481481481481,
+      "eval_roc_auc": 0.5891390946502058,
+      "eval_runtime": 5.5333,
+      "eval_samples_per_second": 487.955,
+      "eval_steps_per_second": 15.362,
+      "step": 10
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "grad_norm": 2.6429762840270996,
+      "learning_rate": 9.980940279542568e-05,
+      "loss": 0.688,
+      "step": 20
+    },
+    {
+      "epoch": 0.012698412698412698,
+      "eval_accuracy": 0.5637037037037037,
+      "eval_f1": 0.2929171668667467,
+      "eval_loss": 0.674746036529541,
+      "eval_precision": 0.7721518987341772,
+      "eval_recall": 0.18074074074074073,
+      "eval_roc_auc": 0.6710831275720164,
+      "eval_runtime": 5.528,
+      "eval_samples_per_second": 488.42,
+      "eval_steps_per_second": 15.376,
+      "step": 20
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "grad_norm": 3.3568179607391357,
+      "learning_rate": 9.968233799237612e-05,
+      "loss": 0.6482,
+      "step": 30
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "eval_accuracy": 0.5981481481481481,
+      "eval_f1": 0.3710144927536232,
+      "eval_loss": 0.6537347435951233,
+      "eval_precision": 0.8533333333333334,
+      "eval_recall": 0.23703703703703705,
+      "eval_roc_auc": 0.7466732510288066,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.853,
+      "eval_steps_per_second": 15.421,
+      "step": 30
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "grad_norm": 2.775456666946411,
+      "learning_rate": 9.955527318932655e-05,
+      "loss": 0.6524,
+      "step": 40
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "eval_accuracy": 0.7307407407407407,
+      "eval_f1": 0.7163480296527507,
+      "eval_loss": 0.6117509603500366,
+      "eval_precision": 0.7568013190436933,
+      "eval_recall": 0.68,
+      "eval_roc_auc": 0.8087465020576132,
+      "eval_runtime": 5.5237,
+      "eval_samples_per_second": 488.803,
+      "eval_steps_per_second": 15.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.0409586429595947,
+      "learning_rate": 9.942820838627701e-05,
+      "loss": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_f1": 0.7790883009244501,
+      "eval_loss": 0.5712039470672607,
+      "eval_precision": 0.6838276440962507,
+      "eval_recall": 0.9051851851851852,
+      "eval_roc_auc": 0.8662809327846365,
+      "eval_runtime": 5.5269,
+      "eval_samples_per_second": 488.52,
+      "eval_steps_per_second": 15.379,
+      "step": 50
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 5.313755035400391,
+      "learning_rate": 9.930114358322745e-05,
+      "loss": 0.5608,
+      "step": 60
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8195937873357229,
+      "eval_loss": 0.48943084478378296,
+      "eval_precision": 0.8863049095607235,
+      "eval_recall": 0.7622222222222222,
+      "eval_roc_auc": 0.9197953360768176,
+      "eval_runtime": 5.541,
+      "eval_samples_per_second": 487.279,
+      "eval_steps_per_second": 15.34,
+      "step": 60
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.1755828857421875,
+      "learning_rate": 9.91740787801779e-05,
+      "loss": 0.4534,
+      "step": 70
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "eval_accuracy": 0.8322222222222222,
+      "eval_f1": 0.8533505988993202,
+      "eval_loss": 0.4028916656970978,
+      "eval_precision": 0.757906843013226,
+      "eval_recall": 0.9762962962962963,
+      "eval_roc_auc": 0.95520438957476,
+      "eval_runtime": 5.5166,
+      "eval_samples_per_second": 489.434,
+      "eval_steps_per_second": 15.408,
+      "step": 70
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "grad_norm": 2.359863758087158,
+      "learning_rate": 9.904701397712835e-05,
+      "loss": 0.2939,
+      "step": 80
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "eval_accuracy": 0.87,
+      "eval_f1": 0.882804674457429,
+      "eval_loss": 0.30669787526130676,
+      "eval_precision": 0.8036474164133739,
+      "eval_recall": 0.9792592592592593,
+      "eval_roc_auc": 0.967720987654321,
+      "eval_runtime": 5.5661,
+      "eval_samples_per_second": 485.082,
+      "eval_steps_per_second": 15.271,
+      "step": 80
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 2.1184494495391846,
+      "learning_rate": 9.893265565438374e-05,
+      "loss": 0.2494,
+      "step": 90
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "eval_accuracy": 0.9244444444444444,
+      "eval_f1": 0.9246676514032496,
+      "eval_loss": 0.19904199242591858,
+      "eval_precision": 0.9219440353460973,
+      "eval_recall": 0.9274074074074075,
+      "eval_roc_auc": 0.9763517146776406,
+      "eval_runtime": 5.5491,
+      "eval_samples_per_second": 486.564,
+      "eval_steps_per_second": 15.318,
+      "step": 90
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.1063764095306396,
+      "learning_rate": 9.880559085133418e-05,
+      "loss": 0.174,
+      "step": 100
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "eval_accuracy": 0.8692592592592593,
+      "eval_f1": 0.8829963539940338,
+      "eval_loss": 0.4303587079048157,
+      "eval_precision": 0.7990401919616077,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.9744661179698217,
+      "eval_runtime": 5.5309,
+      "eval_samples_per_second": 488.17,
+      "eval_steps_per_second": 15.368,
+      "step": 100
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "grad_norm": 11.44679069519043,
+      "learning_rate": 9.869123252858958e-05,
+      "loss": 0.269,
+      "step": 110
+    },
+    {
+      "epoch": 0.06984126984126984,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9302824454772971,
+      "eval_loss": 0.2445582151412964,
+      "eval_precision": 0.899101589495508,
+      "eval_recall": 0.9637037037037037,
+      "eval_roc_auc": 0.9810120713305899,
+      "eval_runtime": 5.5203,
+      "eval_samples_per_second": 489.102,
+      "eval_steps_per_second": 15.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.09498822689056396,
+      "learning_rate": 9.856416772554004e-05,
+      "loss": 0.1981,
+      "step": 120
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "eval_accuracy": 0.9303703703703704,
+      "eval_f1": 0.9330960854092527,
+      "eval_loss": 0.24259698390960693,
+      "eval_precision": 0.897945205479452,
+      "eval_recall": 0.9711111111111111,
+      "eval_roc_auc": 0.9832271604938272,
+      "eval_runtime": 5.5208,
+      "eval_samples_per_second": 489.057,
+      "eval_steps_per_second": 15.396,
+      "step": 120
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "grad_norm": 0.047983940690755844,
+      "learning_rate": 9.843710292249048e-05,
+      "loss": 0.2035,
+      "step": 130
+    },
+    {
+      "epoch": 0.08253968253968254,
+      "eval_accuracy": 0.9288888888888889,
+      "eval_f1": 0.9320594479830149,
+      "eval_loss": 0.2548026740550995,
+      "eval_precision": 0.8922764227642277,
+      "eval_recall": 0.9755555555555555,
+      "eval_roc_auc": 0.9850041152263376,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 130
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.1345868706703186,
+      "learning_rate": 9.831003811944091e-05,
+      "loss": 0.2392,
+      "step": 140
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "eval_accuracy": 0.9214814814814815,
+      "eval_f1": 0.9260293091416608,
+      "eval_loss": 0.28311270475387573,
+      "eval_precision": 0.8753298153034301,
+      "eval_recall": 0.9829629629629629,
+      "eval_roc_auc": 0.9863648834019204,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.727,
+      "eval_steps_per_second": 15.386,
+      "step": 140
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.3760770559310913,
+      "learning_rate": 9.818297331639137e-05,
+      "loss": 0.1965,
+      "step": 150
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_accuracy": 0.8429629629629629,
+      "eval_f1": 0.8640153944836434,
+      "eval_loss": 0.5912654995918274,
+      "eval_precision": 0.7618778280542986,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9832545953360768,
+      "eval_runtime": 5.5302,
+      "eval_samples_per_second": 488.232,
+      "eval_steps_per_second": 15.37,
+      "step": 150
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "grad_norm": 3.2790462970733643,
+      "learning_rate": 9.805590851334181e-05,
+      "loss": 0.3521,
+      "step": 160
+    },
+    {
+      "epoch": 0.10158730158730159,
+      "eval_accuracy": 0.9185185185185185,
+      "eval_f1": 0.9238754325259516,
+      "eval_loss": 0.25474533438682556,
+      "eval_precision": 0.8668831168831169,
+      "eval_recall": 0.9888888888888889,
+      "eval_roc_auc": 0.9880035665294925,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.123,
+      "eval_steps_per_second": 15.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "grad_norm": 3.765111207962036,
+      "learning_rate": 9.792884371029225e-05,
+      "loss": 0.4232,
+      "step": 170
+    },
+    {
+      "epoch": 0.10793650793650794,
+      "eval_accuracy": 0.9474074074074074,
+      "eval_f1": 0.9478324761204996,
+      "eval_loss": 0.14082331955432892,
+      "eval_precision": 0.9402332361516035,
+      "eval_recall": 0.9555555555555556,
+      "eval_roc_auc": 0.9880447187928669,
+      "eval_runtime": 5.5338,
+      "eval_samples_per_second": 487.911,
+      "eval_steps_per_second": 15.36,
+      "step": 170
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.110823154449463,
+      "learning_rate": 9.780177890724271e-05,
+      "loss": 0.1239,
+      "step": 180
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9098915989159891,
+      "eval_loss": 0.26993757486343384,
+      "eval_precision": 0.83832709113608,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9881753086419753,
+      "eval_runtime": 5.5165,
+      "eval_samples_per_second": 489.445,
+      "eval_steps_per_second": 15.408,
+      "step": 180
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "grad_norm": 1.8782886266708374,
+      "learning_rate": 9.767471410419315e-05,
+      "loss": 0.1301,
+      "step": 190
+    },
+    {
+      "epoch": 0.12063492063492064,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9396825396825397,
+      "eval_loss": 0.17670103907585144,
+      "eval_precision": 0.896969696969697,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.989798353909465,
+      "eval_runtime": 5.514,
+      "eval_samples_per_second": 489.66,
+      "eval_steps_per_second": 15.415,
+      "step": 190
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 4.296081066131592,
+      "learning_rate": 9.754764930114358e-05,
+      "loss": 0.1532,
+      "step": 200
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9275563258232236,
+      "eval_loss": 0.25379836559295654,
+      "eval_precision": 0.8716612377850163,
+      "eval_recall": 0.9911111111111112,
+      "eval_roc_auc": 0.99000658436214,
+      "eval_runtime": 5.5116,
+      "eval_samples_per_second": 489.878,
+      "eval_steps_per_second": 15.422,
+      "step": 200
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.7609732151031494,
+      "learning_rate": 9.742058449809403e-05,
+      "loss": 0.2815,
+      "step": 210
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_accuracy": 0.9285185185185185,
+      "eval_f1": 0.9328695652173913,
+      "eval_loss": 0.24461880326271057,
+      "eval_precision": 0.879344262295082,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9911909465020576,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.978,
+      "eval_steps_per_second": 15.425,
+      "step": 210
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "grad_norm": 0.20786483585834503,
+      "learning_rate": 9.729351969504448e-05,
+      "loss": 0.1336,
+      "step": 220
+    },
+    {
+      "epoch": 0.13968253968253969,
+      "eval_accuracy": 0.9518518518518518,
+      "eval_f1": 0.9534717251252685,
+      "eval_loss": 0.1563795804977417,
+      "eval_precision": 0.9224376731301939,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.992451303155007,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.68,
+      "eval_steps_per_second": 15.416,
+      "step": 220
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "grad_norm": 0.6910555362701416,
+      "learning_rate": 9.716645489199492e-05,
+      "loss": 0.1237,
+      "step": 230
+    },
+    {
+      "epoch": 0.14603174603174604,
+      "eval_accuracy": 0.937037037037037,
+      "eval_f1": 0.9404344779257183,
+      "eval_loss": 0.22764083743095398,
+      "eval_precision": 0.8922872340425532,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9923105624142661,
+      "eval_runtime": 5.5171,
+      "eval_samples_per_second": 489.388,
+      "eval_steps_per_second": 15.407,
+      "step": 230
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.4784867763519287,
+      "learning_rate": 9.703939008894538e-05,
+      "loss": 0.063,
+      "step": 240
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "eval_accuracy": 0.8637037037037038,
+      "eval_f1": 0.8799739073711677,
+      "eval_loss": 0.616968035697937,
+      "eval_precision": 0.7861305361305362,
+      "eval_recall": 0.9992592592592593,
+      "eval_roc_auc": 0.9860919067215363,
+      "eval_runtime": 5.5121,
+      "eval_samples_per_second": 489.827,
+      "eval_steps_per_second": 15.42,
+      "step": 240
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": NaN,
+      "learning_rate": 9.692503176620077e-05,
+      "loss": 0.1347,
+      "step": 250
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_accuracy": 0.9388888888888889,
+      "eval_f1": 0.9420442571127503,
+      "eval_loss": 0.24191488325595856,
+      "eval_precision": 0.8957915831663327,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9917956104252401,
+      "eval_runtime": 5.5139,
+      "eval_samples_per_second": 489.672,
+      "eval_steps_per_second": 15.416,
+      "step": 250
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "grad_norm": 9.05746078491211,
+      "learning_rate": 9.679796696315121e-05,
+      "loss": 0.1642,
+      "step": 260
+    },
+    {
+      "epoch": 0.16507936507936508,
+      "eval_accuracy": 0.9425925925925925,
+      "eval_f1": 0.9452103216684341,
+      "eval_loss": 0.2284214049577713,
+      "eval_precision": 0.9039891818796484,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9920307270233196,
+      "eval_runtime": 5.5153,
+      "eval_samples_per_second": 489.547,
+      "eval_steps_per_second": 15.412,
+      "step": 260
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.0563305616378784,
+      "learning_rate": 9.667090216010166e-05,
+      "loss": 0.1503,
+      "step": 270
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "eval_accuracy": 0.894074074074074,
+      "eval_f1": 0.9040912139503688,
+      "eval_loss": 0.4835222661495209,
+      "eval_precision": 0.8259803921568627,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9872872427983539,
+      "eval_runtime": 5.5128,
+      "eval_samples_per_second": 489.765,
+      "eval_steps_per_second": 15.419,
+      "step": 270
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.09033135324716568,
+      "learning_rate": 9.65438373570521e-05,
+      "loss": 0.0974,
+      "step": 280
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_accuracy": 0.9507407407407408,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.19544483721256256,
+      "eval_precision": 0.9216909216909217,
+      "eval_recall": 0.9851851851851852,
+      "eval_roc_auc": 0.9924573388203017,
+      "eval_runtime": 5.5105,
+      "eval_samples_per_second": 489.975,
+      "eval_steps_per_second": 15.425,
+      "step": 280
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "grad_norm": 0.0589861236512661,
+      "learning_rate": 9.641677255400255e-05,
+      "loss": 0.1201,
+      "step": 290
+    },
+    {
+      "epoch": 0.18412698412698414,
+      "eval_accuracy": 0.9174074074074074,
+      "eval_f1": 0.923394022672621,
+      "eval_loss": 0.3497244715690613,
+      "eval_precision": 0.8609865470852018,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9902913580246913,
+      "eval_runtime": 5.5119,
+      "eval_samples_per_second": 489.85,
+      "eval_steps_per_second": 15.421,
+      "step": 290
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.337423324584961,
+      "learning_rate": 9.628970775095299e-05,
+      "loss": 0.1636,
+      "step": 300
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "eval_accuracy": 0.8674074074074074,
+      "eval_f1": 0.882699868938401,
+      "eval_loss": 0.6298528909683228,
+      "eval_precision": 0.7914218566392479,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.985441975308642,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.684,
+      "eval_steps_per_second": 15.416,
+      "step": 300
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "grad_norm": 5.734988212585449,
+      "learning_rate": 9.616264294790343e-05,
+      "loss": 0.2139,
+      "step": 310
+    },
+    {
+      "epoch": 0.19682539682539682,
+      "eval_accuracy": 0.9418518518518518,
+      "eval_f1": 0.944620811287478,
+      "eval_loss": 0.20854391157627106,
+      "eval_precision": 0.9016835016835016,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9917333333333334,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.776,
+      "eval_steps_per_second": 15.419,
+      "step": 310
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "grad_norm": 0.2367023378610611,
+      "learning_rate": 9.603557814485387e-05,
+      "loss": 0.1894,
+      "step": 320
+    },
+    {
+      "epoch": 0.20317460317460317,
+      "eval_accuracy": 0.9562962962962963,
+      "eval_f1": 0.9572463768115942,
+      "eval_loss": 0.1395142674446106,
+      "eval_precision": 0.9368794326241134,
+      "eval_recall": 0.9785185185185186,
+      "eval_roc_auc": 0.9925939643347051,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.717,
+      "eval_steps_per_second": 15.417,
+      "step": 320
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 14.949374198913574,
+      "learning_rate": 9.590851334180433e-05,
+      "loss": 0.057,
+      "step": 330
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "eval_accuracy": 0.9255555555555556,
+      "eval_f1": 0.9305219495333564,
+      "eval_loss": 0.29976287484169006,
+      "eval_precision": 0.8723266364225535,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900480109739369,
+      "eval_runtime": 5.5137,
+      "eval_samples_per_second": 489.687,
+      "eval_steps_per_second": 15.416,
+      "step": 330
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "grad_norm": 3.3133888244628906,
+      "learning_rate": 9.578144853875477e-05,
+      "loss": 0.2029,
+      "step": 340
+    },
+    {
+      "epoch": 0.21587301587301588,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3038364350795746,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9897953360768176,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.19,
+      "eval_steps_per_second": 15.4,
+      "step": 340
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.5984865427017212,
+      "learning_rate": 9.565438373570522e-05,
+      "loss": 0.0849,
+      "step": 350
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9525521207764198,
+      "eval_loss": 0.15116137266159058,
+      "eval_precision": 0.9252793296089385,
+      "eval_recall": 0.9814814814814815,
+      "eval_roc_auc": 0.9926340192043897,
+      "eval_runtime": 5.5231,
+      "eval_samples_per_second": 488.853,
+      "eval_steps_per_second": 15.39,
+      "step": 350
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 5.849670886993408,
+      "learning_rate": 9.552731893265566e-05,
+      "loss": 0.2559,
+      "step": 360
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "eval_accuracy": 0.9392592592592592,
+      "eval_f1": 0.9424561403508772,
+      "eval_loss": 0.22722864151000977,
+      "eval_precision": 0.8953333333333333,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9912104252400549,
+      "eval_runtime": 5.5252,
+      "eval_samples_per_second": 488.669,
+      "eval_steps_per_second": 15.384,
+      "step": 360
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "grad_norm": 0.2203754186630249,
+      "learning_rate": 9.54002541296061e-05,
+      "loss": 0.0809,
+      "step": 370
+    },
+    {
+      "epoch": 0.23492063492063492,
+      "eval_accuracy": 0.9225925925925926,
+      "eval_f1": 0.9279061745429459,
+      "eval_loss": 0.29464688897132874,
+      "eval_precision": 0.868302130406714,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9903662551440329,
+      "eval_runtime": 5.5169,
+      "eval_samples_per_second": 489.409,
+      "eval_steps_per_second": 15.407,
+      "step": 370
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "grad_norm": 9.942216873168945,
+      "learning_rate": 9.527318932655654e-05,
+      "loss": 0.193,
+      "step": 380
+    },
+    {
+      "epoch": 0.24126984126984127,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9436222692036645,
+      "eval_loss": 0.20582349598407745,
+      "eval_precision": 0.8998655913978495,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9918285322359396,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.479,
+      "eval_steps_per_second": 15.41,
+      "step": 380
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 11.672406196594238,
+      "learning_rate": 9.5146124523507e-05,
+      "loss": 0.208,
+      "step": 390
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "eval_accuracy": 0.9296296296296296,
+      "eval_f1": 0.9339360222531293,
+      "eval_loss": 0.24709771573543549,
+      "eval_precision": 0.8800786369593709,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9910834019204389,
+      "eval_runtime": 5.5183,
+      "eval_samples_per_second": 489.282,
+      "eval_steps_per_second": 15.403,
+      "step": 390
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.7513141632080078,
+      "learning_rate": 9.501905972045744e-05,
+      "loss": 0.141,
+      "step": 400
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "eval_accuracy": 0.9248148148148149,
+      "eval_f1": 0.9298306256481161,
+      "eval_loss": 0.2548695504665375,
+      "eval_precision": 0.8716785482825664,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9910268861454047,
+      "eval_runtime": 5.5134,
+      "eval_samples_per_second": 489.718,
+      "eval_steps_per_second": 15.417,
+      "step": 400
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "grad_norm": 0.11584247648715973,
+      "learning_rate": 9.489199491740788e-05,
+      "loss": 0.067,
+      "step": 410
+    },
+    {
+      "epoch": 0.26031746031746034,
+      "eval_accuracy": 0.9403703703703704,
+      "eval_f1": 0.9435285864608909,
+      "eval_loss": 0.20395933091640472,
+      "eval_precision": 0.8960692871419054,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9919632373113855,
+      "eval_runtime": 5.5068,
+      "eval_samples_per_second": 490.299,
+      "eval_steps_per_second": 15.435,
+      "step": 410
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 5.374762058258057,
+      "learning_rate": 9.476493011435832e-05,
+      "loss": 0.0581,
+      "step": 420
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_accuracy": 0.9362962962962963,
+      "eval_f1": 0.9399021663172606,
+      "eval_loss": 0.21634648740291595,
+      "eval_precision": 0.8895502645502645,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9913909465020577,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.778,
+      "eval_steps_per_second": 15.419,
+      "step": 420
+    },
+    {
+      "epoch": 0.273015873015873,
+      "grad_norm": 0.1900794953107834,
+      "learning_rate": 9.463786531130877e-05,
+      "loss": 0.0425,
+      "step": 430
+    },
+    {
+      "epoch": 0.273015873015873,
+      "eval_accuracy": 0.9018518518518519,
+      "eval_f1": 0.9104427171341669,
+      "eval_loss": 0.3560587167739868,
+      "eval_precision": 0.8371659415786202,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9883901234567901,
+      "eval_runtime": 5.5144,
+      "eval_samples_per_second": 489.628,
+      "eval_steps_per_second": 15.414,
+      "step": 430
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "grad_norm": 0.9057045578956604,
+      "learning_rate": 9.451080050825921e-05,
+      "loss": 0.0736,
+      "step": 440
+    },
+    {
+      "epoch": 0.27936507936507937,
+      "eval_accuracy": 0.8792592592592593,
+      "eval_f1": 0.8921244209133025,
+      "eval_loss": 0.4899263083934784,
+      "eval_precision": 0.80622009569378,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9859388203017831,
+      "eval_runtime": 5.5176,
+      "eval_samples_per_second": 489.34,
+      "eval_steps_per_second": 15.405,
+      "step": 440
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 12.068155288696289,
+      "learning_rate": 9.438373570520967e-05,
+      "loss": 0.0788,
+      "step": 450
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_accuracy": 0.9311111111111111,
+      "eval_f1": 0.935326842837274,
+      "eval_loss": 0.27715030312538147,
+      "eval_precision": 0.8813892529488859,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.990839231824417,
+      "eval_runtime": 5.5146,
+      "eval_samples_per_second": 489.612,
+      "eval_steps_per_second": 15.414,
+      "step": 450
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "grad_norm": 0.20492731034755707,
+      "learning_rate": 9.425667090216011e-05,
+      "loss": 0.1801,
+      "step": 460
+    },
+    {
+      "epoch": 0.2920634920634921,
+      "eval_accuracy": 0.924074074074074,
+      "eval_f1": 0.9292371418709009,
+      "eval_loss": 0.32135429978370667,
+      "eval_precision": 0.870071105365223,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9897657064471879,
+      "eval_runtime": 5.5135,
+      "eval_samples_per_second": 489.707,
+      "eval_steps_per_second": 15.417,
+      "step": 460
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "grad_norm": 0.016238894313573837,
+      "learning_rate": 9.412960609911055e-05,
+      "loss": 0.0886,
+      "step": 470
+    },
+    {
+      "epoch": 0.2984126984126984,
+      "eval_accuracy": 0.9348148148148148,
+      "eval_f1": 0.9385045422781272,
+      "eval_loss": 0.26370832324028015,
+      "eval_precision": 0.8882275132275133,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.9905368998628258,
+      "eval_runtime": 5.5161,
+      "eval_samples_per_second": 489.473,
+      "eval_steps_per_second": 15.409,
+      "step": 470
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.18422342836856842,
+      "learning_rate": 9.400254129606099e-05,
+      "loss": 0.0303,
+      "step": 480
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_accuracy": 0.8840740740740741,
+      "eval_f1": 0.8959095443964084,
+      "eval_loss": 0.4938906133174896,
+      "eval_precision": 0.8129149064574532,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9840238683127571,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.015,
+      "eval_steps_per_second": 15.395,
+      "step": 480
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.018785802647471428,
+      "learning_rate": 9.387547649301143e-05,
+      "loss": 0.0849,
+      "step": 490
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "eval_accuracy": 0.914074074074074,
+      "eval_f1": 0.920656634746922,
+      "eval_loss": 0.3513197600841522,
+      "eval_precision": 0.855146124523507,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9879089163237311,
+      "eval_runtime": 5.5492,
+      "eval_samples_per_second": 486.557,
+      "eval_steps_per_second": 15.318,
+      "step": 490
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 17.461837768554688,
+      "learning_rate": 9.374841168996189e-05,
+      "loss": 0.2025,
+      "step": 500
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_accuracy": 0.9414814814814815,
+      "eval_f1": 0.9443661971830986,
+      "eval_loss": 0.23329515755176544,
+      "eval_precision": 0.9,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.990923182441701,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.954,
+      "eval_steps_per_second": 15.393,
+      "step": 500
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 0.4385194182395935,
+      "learning_rate": 9.362134688691233e-05,
+      "loss": 0.4251,
+      "step": 510
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "eval_accuracy": 0.952962962962963,
+      "eval_f1": 0.9547559672247952,
+      "eval_loss": 0.17835260927677155,
+      "eval_precision": 0.9196980096087852,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9925997256515775,
+      "eval_runtime": 5.5197,
+      "eval_samples_per_second": 489.161,
+      "eval_steps_per_second": 15.4,
+      "step": 510
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "grad_norm": 2.7863709926605225,
+      "learning_rate": 9.349428208386277e-05,
+      "loss": 0.1384,
+      "step": 520
+    },
+    {
+      "epoch": 0.33015873015873015,
+      "eval_accuracy": 0.9525925925925925,
+      "eval_f1": 0.9543834640057021,
+      "eval_loss": 0.17517130076885223,
+      "eval_precision": 0.9196428571428571,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9930340192043895,
+      "eval_runtime": 5.5216,
+      "eval_samples_per_second": 488.99,
+      "eval_steps_per_second": 15.394,
+      "step": 520
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "grad_norm": 0.09477631747722626,
+      "learning_rate": 9.336721728081323e-05,
+      "loss": 0.0516,
+      "step": 530
+    },
+    {
+      "epoch": 0.33650793650793653,
+      "eval_accuracy": 0.94,
+      "eval_f1": 0.9430379746835443,
+      "eval_loss": 0.2342747449874878,
+      "eval_precision": 0.8975903614457831,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9920493827160494,
+      "eval_runtime": 5.5193,
+      "eval_samples_per_second": 489.195,
+      "eval_steps_per_second": 15.401,
+      "step": 530
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.060261718928813934,
+      "learning_rate": 9.324015247776366e-05,
+      "loss": 0.0048,
+      "step": 540
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "eval_accuracy": 0.927037037037037,
+      "eval_f1": 0.9316684009712105,
+      "eval_loss": 0.2969974875450134,
+      "eval_precision": 0.8760600130463144,
+      "eval_recall": 0.9948148148148148,
+      "eval_roc_auc": 0.991082853223594,
+      "eval_runtime": 5.5259,
+      "eval_samples_per_second": 488.608,
+      "eval_steps_per_second": 15.382,
+      "step": 540
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.1148306354880333,
+      "learning_rate": 9.31130876747141e-05,
+      "loss": 0.0832,
+      "step": 550
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "eval_accuracy": 0.96,
+      "eval_f1": 0.9609544468546638,
+      "eval_loss": 0.1580500602722168,
+      "eval_precision": 0.9385593220338984,
+      "eval_recall": 0.9844444444444445,
+      "eval_roc_auc": 0.9940183813443072,
+      "eval_runtime": 5.5217,
+      "eval_samples_per_second": 488.978,
+      "eval_steps_per_second": 15.394,
+      "step": 550
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.034114107489585876,
+      "learning_rate": 9.298602287166456e-05,
+      "loss": 0.1202,
+      "step": 560
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_accuracy": 0.9485185185185185,
+      "eval_f1": 0.9507266926621766,
+      "eval_loss": 0.23128464818000793,
+      "eval_precision": 0.91162474507138,
+      "eval_recall": 0.9933333333333333,
+      "eval_roc_auc": 0.9926241426611797,
+      "eval_runtime": 5.5201,
+      "eval_samples_per_second": 489.125,
+      "eval_steps_per_second": 15.398,
+      "step": 560
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 0.02656545117497444,
+      "learning_rate": 9.2858958068615e-05,
+      "loss": 0.1321,
+      "step": 570
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "eval_accuracy": 0.9514814814814815,
+      "eval_f1": 0.9534635879218473,
+      "eval_loss": 0.22296707332134247,
+      "eval_precision": 0.9160409556313993,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9931102880658437,
+      "eval_runtime": 5.5181,
+      "eval_samples_per_second": 489.3,
+      "eval_steps_per_second": 15.404,
+      "step": 570
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "grad_norm": 0.03909531608223915,
+      "learning_rate": 9.273189326556544e-05,
+      "loss": 0.0552,
+      "step": 580
+    },
+    {
+      "epoch": 0.3682539682539683,
+      "eval_accuracy": 0.9092592592592592,
+      "eval_f1": 0.916695001700102,
+      "eval_loss": 0.4478496313095093,
+      "eval_precision": 0.8472658705216844,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.9875185185185186,
+      "eval_runtime": 5.5291,
+      "eval_samples_per_second": 488.323,
+      "eval_steps_per_second": 15.373,
+      "step": 580
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "grad_norm": 0.01843447797000408,
+      "learning_rate": 9.26048284625159e-05,
+      "loss": 0.1449,
+      "step": 590
+    },
+    {
+      "epoch": 0.3746031746031746,
+      "eval_accuracy": 0.9014814814814814,
+      "eval_f1": 0.9101958136394328,
+      "eval_loss": 0.4929225444793701,
+      "eval_precision": 0.8362282878411911,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.985960768175583,
+      "eval_runtime": 5.5503,
+      "eval_samples_per_second": 486.461,
+      "eval_steps_per_second": 15.315,
+      "step": 590
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.1456720530986786,
+      "learning_rate": 9.249047013977129e-05,
+      "loss": 0.068,
+      "step": 600
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9401888772298006,
+      "eval_loss": 0.29736340045928955,
+      "eval_precision": 0.8906560636182903,
+      "eval_recall": 0.9955555555555555,
+      "eval_roc_auc": 0.9906285322359396,
+      "eval_runtime": 5.5246,
+      "eval_samples_per_second": 488.726,
+      "eval_steps_per_second": 15.386,
+      "step": 600
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "grad_norm": 0.00903715193271637,
+      "learning_rate": 9.236340533672173e-05,
+      "loss": 0.0065,
+      "step": 610
+    },
+    {
+      "epoch": 0.3873015873015873,
+      "eval_accuracy": 0.9588888888888889,
+      "eval_f1": 0.9601436265709156,
+      "eval_loss": 0.19618448615074158,
+      "eval_precision": 0.9317073170731708,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9935338820301782,
+      "eval_runtime": 5.5182,
+      "eval_samples_per_second": 489.287,
+      "eval_steps_per_second": 15.403,
+      "step": 610
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "grad_norm": 0.04093470424413681,
+      "learning_rate": 9.223634053367217e-05,
+      "loss": 0.131,
+      "step": 620
+    },
+    {
+      "epoch": 0.39365079365079364,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302486187845304,
+      "eval_loss": 0.3867323100566864,
+      "eval_precision": 0.871280724450194,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9864683127572016,
+      "eval_runtime": 5.5187,
+      "eval_samples_per_second": 489.248,
+      "eval_steps_per_second": 15.402,
+      "step": 620
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.493297576904297,
+      "learning_rate": 9.210927573062263e-05,
+      "loss": 0.2599,
+      "step": 630
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.8918518518518519,
+      "eval_f1": 0.9022757697456493,
+      "eval_loss": 0.5704190731048584,
+      "eval_precision": 0.8229548229548229,
+      "eval_recall": 0.9985185185185185,
+      "eval_roc_auc": 0.981446364883402,
+      "eval_runtime": 5.5214,
+      "eval_samples_per_second": 489.005,
+      "eval_steps_per_second": 15.395,
+      "step": 630
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "grad_norm": 0.01696428842842579,
+      "learning_rate": 9.198221092757307e-05,
+      "loss": 0.0087,
+      "step": 640
+    },
+    {
+      "epoch": 0.40634920634920635,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9324090121317158,
+      "eval_loss": 0.3256017863750458,
+      "eval_precision": 0.8762214983713354,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9897610425240055,
+      "eval_runtime": 5.5213,
+      "eval_samples_per_second": 489.017,
+      "eval_steps_per_second": 15.395,
+      "step": 640
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.01224907673895359,
+      "learning_rate": 9.185514612452351e-05,
+      "loss": 0.0602,
+      "step": 650
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "eval_accuracy": 0.9207407407407407,
+      "eval_f1": 0.9263592567102547,
+      "eval_loss": 0.3757924735546112,
+      "eval_precision": 0.8650385604113111,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9885146776406035,
+      "eval_runtime": 5.522,
+      "eval_samples_per_second": 488.951,
+      "eval_steps_per_second": 15.393,
+      "step": 650
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "grad_norm": 0.01693762093782425,
+      "learning_rate": 9.172808132147396e-05,
+      "loss": 0.4184,
+      "step": 660
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "eval_accuracy": 0.9548148148148148,
+      "eval_f1": 0.9564285714285714,
+      "eval_loss": 0.1783735305070877,
+      "eval_precision": 0.923448275862069,
+      "eval_recall": 0.9918518518518519,
+      "eval_roc_auc": 0.9926477366255145,
+      "eval_runtime": 5.5199,
+      "eval_samples_per_second": 489.135,
+      "eval_steps_per_second": 15.399,
+      "step": 660
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "grad_norm": 0.3128555119037628,
+      "learning_rate": 9.16010165184244e-05,
+      "loss": 0.0977,
+      "step": 670
+    },
+    {
+      "epoch": 0.4253968253968254,
+      "eval_accuracy": 0.9492592592592592,
+      "eval_f1": 0.9513667021654242,
+      "eval_loss": 0.18898966908454895,
+      "eval_precision": 0.9134287661895024,
+      "eval_recall": 0.9925925925925926,
+      "eval_roc_auc": 0.9929882030178325,
+      "eval_runtime": 5.513,
+      "eval_samples_per_second": 489.751,
+      "eval_steps_per_second": 15.418,
+      "step": 670
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "grad_norm": 7.7761383056640625,
+      "learning_rate": 9.147395171537485e-05,
+      "loss": 0.1996,
+      "step": 680
+    },
+    {
+      "epoch": 0.43174603174603177,
+      "eval_accuracy": 0.9096296296296297,
+      "eval_f1": 0.9168937329700273,
+      "eval_loss": 0.3682536780834198,
+      "eval_precision": 0.8486759142496847,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9902880658436214,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.232,
+      "eval_steps_per_second": 15.402,
+      "step": 680
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "grad_norm": 0.04118531197309494,
+      "learning_rate": 9.13468869123253e-05,
+      "loss": 0.0329,
+      "step": 690
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "eval_accuracy": 0.9048148148148148,
+      "eval_f1": 0.9128518141742964,
+      "eval_loss": 0.38119447231292725,
+      "eval_precision": 0.841776110068793,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9900367626886146,
+      "eval_runtime": 5.5111,
+      "eval_samples_per_second": 489.917,
+      "eval_steps_per_second": 15.423,
+      "step": 690
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.560464382171631,
+      "learning_rate": 9.121982210927574e-05,
+      "loss": 0.1425,
+      "step": 700
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.9511111111111111,
+      "eval_f1": 0.9529579472558802,
+      "eval_loss": 0.177493155002594,
+      "eval_precision": 0.9182692307692307,
+      "eval_recall": 0.9903703703703703,
+      "eval_roc_auc": 0.9938277091906722,
+      "eval_runtime": 5.5066,
+      "eval_samples_per_second": 490.322,
+      "eval_steps_per_second": 15.436,
+      "step": 700
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "grad_norm": 0.03769376501441002,
+      "learning_rate": 9.109275730622618e-05,
+      "loss": 0.1651,
+      "step": 710
+    },
+    {
+      "epoch": 0.4507936507936508,
+      "eval_accuracy": 0.9448148148148148,
+      "eval_f1": 0.9474055771267208,
+      "eval_loss": 0.20647479593753815,
+      "eval_precision": 0.9049224544841538,
+      "eval_recall": 0.9940740740740741,
+      "eval_roc_auc": 0.9933665294924554,
+      "eval_runtime": 5.5143,
+      "eval_samples_per_second": 489.634,
+      "eval_steps_per_second": 15.414,
+      "step": 710
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 10.711636543273926,
+      "learning_rate": 9.096569250317662e-05,
+      "loss": 0.1278,
+      "step": 720
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "eval_accuracy": 0.9359259259259259,
+      "eval_f1": 0.9395738735592036,
+      "eval_loss": 0.25338342785835266,
+      "eval_precision": 0.8889623265036352,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9929604938271603,
+      "eval_runtime": 5.5162,
+      "eval_samples_per_second": 489.471,
+      "eval_steps_per_second": 15.409,
+      "step": 720
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "grad_norm": 0.17392298579216003,
+      "learning_rate": 9.083862770012706e-05,
+      "loss": 0.0979,
+      "step": 730
+    },
+    {
+      "epoch": 0.4634920634920635,
+      "eval_accuracy": 0.9440740740740741,
+      "eval_f1": 0.9468497008095741,
+      "eval_loss": 0.22556233406066895,
+      "eval_precision": 0.9020791415157612,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9937440329218106,
+      "eval_runtime": 5.5189,
+      "eval_samples_per_second": 489.224,
+      "eval_steps_per_second": 15.401,
+      "step": 730
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "grad_norm": 3.3036723136901855,
+      "learning_rate": 9.071156289707752e-05,
+      "loss": 0.0228,
+      "step": 740
+    },
+    {
+      "epoch": 0.46984126984126984,
+      "eval_accuracy": 0.9251851851851852,
+      "eval_f1": 0.9302004146510021,
+      "eval_loss": 0.317281037569046,
+      "eval_precision": 0.8717616580310881,
+      "eval_recall": 0.997037037037037,
+      "eval_roc_auc": 0.9925075445816187,
+      "eval_runtime": 5.5192,
+      "eval_samples_per_second": 489.2,
+      "eval_steps_per_second": 15.401,
+      "step": 740
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.8324198722839355,
+      "learning_rate": 9.058449809402796e-05,
+      "loss": 0.1754,
+      "step": 750
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_accuracy": 0.9581481481481482,
+      "eval_f1": 0.9594254937163376,
+      "eval_loss": 0.1706221103668213,
+      "eval_precision": 0.9310104529616725,
+      "eval_recall": 0.9896296296296296,
+      "eval_roc_auc": 0.9952694101508917,
+      "eval_runtime": 5.5194,
+      "eval_samples_per_second": 489.187,
+      "eval_steps_per_second": 15.4,
+      "step": 750
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "grad_norm": 0.046114906668663025,
+      "learning_rate": 9.04574332909784e-05,
+      "loss": 0.0727,
+      "step": 760
+    },
+    {
+      "epoch": 0.48253968253968255,
+      "eval_accuracy": 0.9088888888888889,
+      "eval_f1": 0.9163265306122449,
+      "eval_loss": 0.42058730125427246,
+      "eval_precision": 0.8471698113207548,
+      "eval_recall": 0.9977777777777778,
+      "eval_roc_auc": 0.9914013717421125,
+      "eval_runtime": 5.5127,
+      "eval_samples_per_second": 489.781,
+      "eval_steps_per_second": 15.419,
+      "step": 760
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.3374621272087097,
+      "learning_rate": 9.033036848792885e-05,
+      "loss": 0.1076,
+      "step": 770
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "eval_accuracy": 0.9407407407407408,
+      "eval_f1": 0.9438596491228071,
+      "eval_loss": 0.2562646269798279,
+      "eval_precision": 0.8966666666666666,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.993437585733882,
+      "eval_runtime": 5.5242,
+      "eval_samples_per_second": 488.761,
+      "eval_steps_per_second": 15.387,
+      "step": 770
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "grad_norm": 0.027243219316005707,
+      "learning_rate": 9.020330368487929e-05,
+      "loss": 0.0842,
+      "step": 780
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "eval_accuracy": 0.9633333333333334,
+      "eval_f1": 0.9640130861504908,
+      "eval_loss": 0.14165127277374268,
+      "eval_precision": 0.9464668094218416,
+      "eval_recall": 0.9822222222222222,
+      "eval_roc_auc": 0.9951972565157751,
+      "eval_runtime": 5.5142,
+      "eval_samples_per_second": 489.648,
+      "eval_steps_per_second": 15.415,
+      "step": 780
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "grad_norm": 1.7387934923171997,
+      "learning_rate": 9.007623888182973e-05,
+      "loss": 0.134,
+      "step": 790
+    },
+    {
+      "epoch": 0.5015873015873016,
+      "eval_accuracy": 0.9577777777777777,
+      "eval_f1": 0.958963282937365,
+      "eval_loss": 0.1754920780658722,
+      "eval_precision": 0.9327731092436975,
+      "eval_recall": 0.9866666666666667,
+      "eval_roc_auc": 0.994798353909465,
+      "eval_runtime": 5.5138,
+      "eval_samples_per_second": 489.682,
+      "eval_steps_per_second": 15.416,
+      "step": 790
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.11948162317276001,
+      "learning_rate": 8.994917407878019e-05,
+      "loss": 0.068,
+      "step": 800
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "eval_accuracy": 0.9596296296296296,
+      "eval_f1": 0.9608054656598346,
+      "eval_loss": 0.1783217042684555,
+      "eval_precision": 0.93361285814116,
+      "eval_recall": 0.9896296296296296,
+      "eval_roc_auc": 0.9951489711934156,
+      "eval_runtime": 5.5179,
+      "eval_samples_per_second": 489.316,
+      "eval_steps_per_second": 15.404,
+      "step": 800
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.7914234399795532,
+      "learning_rate": 8.982210927573063e-05,
+      "loss": 0.051,
+      "step": 810
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "eval_accuracy": 0.9366666666666666,
+      "eval_f1": 0.9402306885704299,
+      "eval_loss": 0.2965752184391022,
+      "eval_precision": 0.8901389808074123,
+      "eval_recall": 0.9962962962962963,
+      "eval_roc_auc": 0.9928847736625515,
+      "eval_runtime": 5.5153,
+      "eval_samples_per_second": 489.551,
+      "eval_steps_per_second": 15.412,
+      "step": 810
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 50,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 49
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}