Upload folder using huggingface_hub

README.md

@@ -0,0 +1,79 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: lora-out5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# lora-out5
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1214
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2.5e-07
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8362        | 0.03  | 1    | 1.7488          |
+| 2.035         | 2.46  | 80   | 1.6462          |
+| 1.5489        | 4.92  | 160  | 1.4901          |
+| 1.4392        | 7.38  | 240  | 1.3567          |
+| 1.2196        | 9.85  | 320  | 1.2475          |
+| 1.3219        | 12.31 | 400  | 1.2089          |
+| 1.2171        | 14.77 | 480  | 1.1870          |
+| 1.1686        | 17.23 | 560  | 1.1730          |
+| 1.1506        | 19.69 | 640  | 1.1615          |
+| 1.1829        | 22.15 | 720  | 1.1513          |
+| 1.267         | 24.62 | 800  | 1.1454          |
+| 1.0857        | 27.08 | 880  | 1.1367          |
+| 1.0795        | 29.54 | 960  | 1.1345          |
+| 1.0453        | 32.0  | 1040 | 1.1317          |
+| 1.2093        | 34.46 | 1120 | 1.1283          |
+| 1.1442        | 36.92 | 1200 | 1.1253          |
+| 0.966         | 39.38 | 1280 | 1.1239          |
+| 0.9576        | 41.85 | 1360 | 1.1227          |
+| 1.0146        | 44.31 | 1440 | 1.1222          |
+| 1.0243        | 46.77 | 1520 | 1.1213          |
+| 1.0192        | 49.23 | 1600 | 1.1214          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.7
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382cee0d188362b14c68ae8f7f7f6f2e5d20d32454cbdf6c9d18bb9fcee105da
+size 4005763213

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-1040/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: ./NeverSleep_Noromaid-13b-v0.1.1/
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2

checkpoint-1040/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1040/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1021028b5160d94237e78c538c60ab2c854155139b92f9783fb0d312e44fd1
+size 4005637552

checkpoint-1040/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a542d589628322238a136a80220ad7c47769d2b0fad2330409652db55b3640
+size 2007352159

checkpoint-1040/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9417334df38c258286a4594dfa3d7dfdffe2c39a705cc56eec44e05720e955
+size 14575

checkpoint-1040/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3387b786bd67ff8ef15a508cf26abe46e62b045c1859dcd45566de3f3e0b06
+size 627

checkpoint-1040/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c358b1c810a69ea433dd5d29f474567432f37c0574609fc5626a2db2ddb233f
+size 4603

checkpoint-1235/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: ./NeverSleep_Noromaid-13b-v0.1.1/
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2

checkpoint-1235/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1235/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44f2a5a9140a2df8bafb5586ec20ea5e9a355c3f12d232e49392c079c43e874
+size 4005637552

checkpoint-1235/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91e9347877d17b73ae0d9fa80f6c53e4ecbd62b740fe05a5bd03afbf1e6cd53
+size 2007352159

checkpoint-1235/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729c28c266482563f484f33c8e7eb00db90286466c41865f142a830b6df3226d
+size 14575

checkpoint-1235/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e633b173ea25f484d7ef6fe279b20e0169338dac453e8d07a631af20913f58
+size 627

checkpoint-1235/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c358b1c810a69ea433dd5d29f474567432f37c0574609fc5626a2db2ddb233f
+size 4603

checkpoint-1560/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: ./NeverSleep_Noromaid-13b-v0.1.1/
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2

checkpoint-1560/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1560/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0502c483e75c09fd533c4f1697bf5769fe0849200ea28273bad8babf39ccbd
+size 4005637552

checkpoint-1560/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a53bbcecdab88ea1bf02db0a94adee284484a2fc575747628b76b2b4e4cc46
+size 2007352159

checkpoint-1560/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2ac6b6c8327171662356e9a6c90f6ae3a377af50b66965ed0b535428c1ad78
+size 14575

checkpoint-1560/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0ec90ec619739fd803d81a9523646ae1ea00672786215d1ab11748e4efb751
+size 627

checkpoint-1560/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c358b1c810a69ea433dd5d29f474567432f37c0574609fc5626a2db2ddb233f
+size 4603

checkpoint-715/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: ./NeverSleep_Noromaid-13b-v0.1.1/
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2

checkpoint-715/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-715/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a303e67ed61b192363856ae74195a01bac862cbabc97f49cf8a68a6caa046a6
+size 4005637552

checkpoint-715/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81910ed3f202dd9ab952cbc1195d717b7da031b48622685ab87d6b25a17feed
+size 2007352159

checkpoint-715/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee27af610ca0495321df5989114ee80ec471861c40bee8a93bcbc900e4f47494
+size 14575

checkpoint-715/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b4c74a1098c53a19c72b5731e064082712032dd90a3f9654a724892bb076ff9
+size 627

checkpoint-715/trainer_state.json

@@ -0,0 +1,4382 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 22.0,
+  "eval_steps": 80,
+  "global_step": 715,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8362,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.7487908601760864,
+      "eval_runtime": 1.7201,
+      "eval_samples_per_second": 4.07,
+      "eval_steps_per_second": 2.326,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7387,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9194,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8898,
+      "step": 4
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7892,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9383,
+      "step": 6
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6433,
+      "step": 7
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9912,
+      "step": 8
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.967,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8385,
+      "step": 10
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.5e-07,
+      "loss": 2.0755,
+      "step": 11
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.852,
+      "step": 12
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.5e-07,
+      "loss": 2.0098,
+      "step": 13
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8534,
+      "step": 14
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.5e-07,
+      "loss": 2.2001,
+      "step": 15
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7698,
+      "step": 16
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9215,
+      "step": 17
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8275,
+      "step": 18
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8526,
+      "step": 19
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8421,
+      "step": 20
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7406,
+      "step": 21
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8343,
+      "step": 22
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8616,
+      "step": 23
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6493,
+      "step": 24
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.931,
+      "step": 25
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9538,
+      "step": 26
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.5e-07,
+      "loss": 2.013,
+      "step": 27
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5e-07,
+      "loss": 2.0858,
+      "step": 28
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.5e-07,
+      "loss": 2.0456,
+      "step": 29
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7464,
+      "step": 30
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8876,
+      "step": 31
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7079,
+      "step": 32
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8358,
+      "step": 33
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.5e-07,
+      "loss": 2.0894,
+      "step": 34
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8563,
+      "step": 35
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.893,
+      "step": 36
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9089,
+      "step": 37
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7537,
+      "step": 38
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8376,
+      "step": 39
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7036,
+      "step": 40
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8212,
+      "step": 41
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8071,
+      "step": 42
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8911,
+      "step": 43
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.88,
+      "step": 44
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7136,
+      "step": 45
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6818,
+      "step": 46
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9645,
+      "step": 47
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9903,
+      "step": 48
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8368,
+      "step": 49
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7862,
+      "step": 50
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9217,
+      "step": 51
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8417,
+      "step": 52
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8408,
+      "step": 53
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8922,
+      "step": 54
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7651,
+      "step": 55
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7586,
+      "step": 56
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9452,
+      "step": 57
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7795,
+      "step": 58
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.875,
+      "step": 59
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8503,
+      "step": 60
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7522,
+      "step": 61
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7527,
+      "step": 62
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8297,
+      "step": 63
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7751,
+      "step": 64
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9007,
+      "step": 65
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.829,
+      "step": 66
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7726,
+      "step": 67
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8103,
+      "step": 68
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8264,
+      "step": 69
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7188,
+      "step": 70
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8933,
+      "step": 71
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6881,
+      "step": 72
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6726,
+      "step": 73
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8541,
+      "step": 74
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8042,
+      "step": 75
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7049,
+      "step": 76
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6737,
+      "step": 77
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6985,
+      "step": 78
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7261,
+      "step": 79
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.5e-07,
+      "loss": 2.035,
+      "step": 80
+    },
+    {
+      "epoch": 2.46,
+      "eval_loss": 1.646209955215454,
+      "eval_runtime": 1.7493,
+      "eval_samples_per_second": 4.002,
+      "eval_steps_per_second": 2.287,
+      "step": 80
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7559,
+      "step": 81
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6864,
+      "step": 82
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8974,
+      "step": 83
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.822,
+      "step": 84
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6783,
+      "step": 85
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8375,
+      "step": 86
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7302,
+      "step": 87
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7164,
+      "step": 88
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6118,
+      "step": 89
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7528,
+      "step": 90
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.9012,
+      "step": 91
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6869,
+      "step": 92
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7648,
+      "step": 93
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6151,
+      "step": 94
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7853,
+      "step": 95
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7481,
+      "step": 96
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7218,
+      "step": 97
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8767,
+      "step": 98
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7954,
+      "step": 99
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6822,
+      "step": 100
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.821,
+      "step": 101
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6984,
+      "step": 102
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7225,
+      "step": 103
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6312,
+      "step": 104
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7467,
+      "step": 105
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.679,
+      "step": 106
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.791,
+      "step": 107
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7233,
+      "step": 108
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8198,
+      "step": 109
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6536,
+      "step": 110
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6672,
+      "step": 111
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.8259,
+      "step": 112
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7671,
+      "step": 113
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5717,
+      "step": 114
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7491,
+      "step": 115
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4921,
+      "step": 116
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7512,
+      "step": 117
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5921,
+      "step": 118
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6179,
+      "step": 119
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7484,
+      "step": 120
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6551,
+      "step": 121
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6753,
+      "step": 122
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.816,
+      "step": 123
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7982,
+      "step": 124
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5347,
+      "step": 125
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6895,
+      "step": 126
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6968,
+      "step": 127
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6039,
+      "step": 128
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6148,
+      "step": 129
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6244,
+      "step": 130
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5743,
+      "step": 131
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5876,
+      "step": 132
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7865,
+      "step": 133
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.731,
+      "step": 134
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6661,
+      "step": 135
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6231,
+      "step": 136
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5479,
+      "step": 137
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7758,
+      "step": 138
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6865,
+      "step": 139
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6355,
+      "step": 140
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6922,
+      "step": 141
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5235,
+      "step": 142
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6388,
+      "step": 143
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.536,
+      "step": 144
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6105,
+      "step": 145
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6795,
+      "step": 146
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5493,
+      "step": 147
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6987,
+      "step": 148
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.529,
+      "step": 149
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5458,
+      "step": 150
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5496,
+      "step": 151
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6442,
+      "step": 152
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.727,
+      "step": 153
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6884,
+      "step": 154
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5979,
+      "step": 155
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5635,
+      "step": 156
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.805,
+      "step": 157
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.565,
+      "step": 158
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5836,
+      "step": 159
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5489,
+      "step": 160
+    },
+    {
+      "epoch": 4.92,
+      "eval_loss": 1.490054965019226,
+      "eval_runtime": 1.7397,
+      "eval_samples_per_second": 4.024,
+      "eval_steps_per_second": 2.299,
+      "step": 160
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6744,
+      "step": 161
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5578,
+      "step": 162
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5033,
+      "step": 163
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.701,
+      "step": 164
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5297,
+      "step": 165
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5086,
+      "step": 166
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5426,
+      "step": 167
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5224,
+      "step": 168
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4174,
+      "step": 169
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5665,
+      "step": 170
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5093,
+      "step": 171
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4894,
+      "step": 172
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.7075,
+      "step": 173
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5987,
+      "step": 174
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5064,
+      "step": 175
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5896,
+      "step": 176
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5435,
+      "step": 177
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5764,
+      "step": 178
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6604,
+      "step": 179
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6184,
+      "step": 180
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6953,
+      "step": 181
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5764,
+      "step": 182
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4756,
+      "step": 183
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6062,
+      "step": 184
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5978,
+      "step": 185
+    },
+    {
+      "epoch": 5.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4222,
+      "step": 186
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5142,
+      "step": 187
+    },
+    {
+      "epoch": 5.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4466,
+      "step": 188
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5513,
+      "step": 189
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4656,
+      "step": 190
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5972,
+      "step": 191
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4809,
+      "step": 192
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6644,
+      "step": 193
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5554,
+      "step": 194
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5099,
+      "step": 195
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5775,
+      "step": 196
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4642,
+      "step": 197
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4549,
+      "step": 198
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4262,
+      "step": 199
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3087,
+      "step": 200
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4069,
+      "step": 201
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5301,
+      "step": 202
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4505,
+      "step": 203
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5708,
+      "step": 204
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5237,
+      "step": 205
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6189,
+      "step": 206
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3563,
+      "step": 207
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6897,
+      "step": 208
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4593,
+      "step": 209
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6024,
+      "step": 210
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4543,
+      "step": 211
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5193,
+      "step": 212
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3936,
+      "step": 213
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5552,
+      "step": 214
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.453,
+      "step": 215
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4554,
+      "step": 216
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6442,
+      "step": 217
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.439,
+      "step": 218
+    },
+    {
+      "epoch": 6.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4309,
+      "step": 219
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4857,
+      "step": 220
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5154,
+      "step": 221
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3941,
+      "step": 222
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5596,
+      "step": 223
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4859,
+      "step": 224
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4801,
+      "step": 225
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5035,
+      "step": 226
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6068,
+      "step": 227
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4447,
+      "step": 228
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5094,
+      "step": 229
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5474,
+      "step": 230
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4545,
+      "step": 231
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4672,
+      "step": 232
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.6396,
+      "step": 233
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.374,
+      "step": 234
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4521,
+      "step": 235
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2984,
+      "step": 236
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4511,
+      "step": 237
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.405,
+      "step": 238
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.296,
+      "step": 239
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4392,
+      "step": 240
+    },
+    {
+      "epoch": 7.38,
+      "eval_loss": 1.3567150831222534,
+      "eval_runtime": 1.7364,
+      "eval_samples_per_second": 4.031,
+      "eval_steps_per_second": 2.304,
+      "step": 240
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5595,
+      "step": 241
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5671,
+      "step": 242
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4832,
+      "step": 243
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4415,
+      "step": 244
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4649,
+      "step": 245
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5053,
+      "step": 246
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5084,
+      "step": 247
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4543,
+      "step": 248
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3008,
+      "step": 249
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.324,
+      "step": 250
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5586,
+      "step": 251
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4245,
+      "step": 252
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4361,
+      "step": 253
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4301,
+      "step": 254
+    },
+    {
+      "epoch": 7.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5183,
+      "step": 255
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.46,
+      "step": 256
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2602,
+      "step": 257
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.358,
+      "step": 258
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2598,
+      "step": 259
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3058,
+      "step": 260
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4428,
+      "step": 261
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4506,
+      "step": 262
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4627,
+      "step": 263
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4584,
+      "step": 264
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.356,
+      "step": 265
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4304,
+      "step": 266
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2296,
+      "step": 267
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4255,
+      "step": 268
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4978,
+      "step": 269
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4115,
+      "step": 270
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4366,
+      "step": 271
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2477,
+      "step": 272
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.453,
+      "step": 273
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3008,
+      "step": 274
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2511,
+      "step": 275
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4864,
+      "step": 276
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4733,
+      "step": 277
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4998,
+      "step": 278
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4771,
+      "step": 279
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4164,
+      "step": 280
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2803,
+      "step": 281
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3673,
+      "step": 282
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3849,
+      "step": 283
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4484,
+      "step": 284
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.397,
+      "step": 285
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5398,
+      "step": 286
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2841,
+      "step": 287
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2991,
+      "step": 288
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3,
+      "step": 289
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.413,
+      "step": 290
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3346,
+      "step": 291
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3362,
+      "step": 292
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1674,
+      "step": 293
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4128,
+      "step": 294
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.461,
+      "step": 295
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3092,
+      "step": 296
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2157,
+      "step": 297
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3718,
+      "step": 298
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4823,
+      "step": 299
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4398,
+      "step": 300
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3343,
+      "step": 301
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1481,
+      "step": 302
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3867,
+      "step": 303
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3983,
+      "step": 304
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3382,
+      "step": 305
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4251,
+      "step": 306
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2907,
+      "step": 307
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2584,
+      "step": 308
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3281,
+      "step": 309
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4022,
+      "step": 310
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3523,
+      "step": 311
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5241,
+      "step": 312
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1701,
+      "step": 313
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.194,
+      "step": 314
+    },
+    {
+      "epoch": 9.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4622,
+      "step": 315
+    },
+    {
+      "epoch": 9.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1747,
+      "step": 316
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4286,
+      "step": 317
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3895,
+      "step": 318
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3746,
+      "step": 319
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2196,
+      "step": 320
+    },
+    {
+      "epoch": 9.85,
+      "eval_loss": 1.2475242614746094,
+      "eval_runtime": 1.7503,
+      "eval_samples_per_second": 3.999,
+      "eval_steps_per_second": 2.285,
+      "step": 320
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2543,
+      "step": 321
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.239,
+      "step": 322
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3088,
+      "step": 323
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.299,
+      "step": 324
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3273,
+      "step": 325
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3335,
+      "step": 326
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.317,
+      "step": 327
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3048,
+      "step": 328
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.429,
+      "step": 329
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2001,
+      "step": 330
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3512,
+      "step": 331
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2161,
+      "step": 332
+    },
+    {
+      "epoch": 10.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2098,
+      "step": 333
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3637,
+      "step": 334
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3788,
+      "step": 335
+    },
+    {
+      "epoch": 10.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2368,
+      "step": 336
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.348,
+      "step": 337
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0986,
+      "step": 338
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3233,
+      "step": 339
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3211,
+      "step": 341
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.5044,
+      "step": 342
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3033,
+      "step": 343
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4222,
+      "step": 344
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4241,
+      "step": 345
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3264,
+      "step": 346
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4957,
+      "step": 347
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1016,
+      "step": 348
+    },
+    {
+      "epoch": 10.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2492,
+      "step": 349
+    },
+    {
+      "epoch": 10.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1237,
+      "step": 350
+    },
+    {
+      "epoch": 10.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4371,
+      "step": 351
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.438,
+      "step": 352
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2182,
+      "step": 353
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2577,
+      "step": 354
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2687,
+      "step": 355
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3387,
+      "step": 356
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3571,
+      "step": 357
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2289,
+      "step": 358
+    },
+    {
+      "epoch": 11.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2925,
+      "step": 359
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3187,
+      "step": 360
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3628,
+      "step": 361
+    },
+    {
+      "epoch": 11.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2547,
+      "step": 362
+    },
+    {
+      "epoch": 11.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3169,
+      "step": 363
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2921,
+      "step": 364
+    },
+    {
+      "epoch": 11.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3426,
+      "step": 365
+    },
+    {
+      "epoch": 11.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4212,
+      "step": 366
+    },
+    {
+      "epoch": 11.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2466,
+      "step": 367
+    },
+    {
+      "epoch": 11.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3367,
+      "step": 368
+    },
+    {
+      "epoch": 11.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3179,
+      "step": 369
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2568,
+      "step": 370
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1769,
+      "step": 371
+    },
+    {
+      "epoch": 11.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3068,
+      "step": 372
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1623,
+      "step": 373
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2147,
+      "step": 374
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4786,
+      "step": 375
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3387,
+      "step": 376
+    },
+    {
+      "epoch": 11.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.261,
+      "step": 377
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2758,
+      "step": 378
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2917,
+      "step": 379
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3428,
+      "step": 380
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4322,
+      "step": 381
+    },
+    {
+      "epoch": 11.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2796,
+      "step": 382
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.318,
+      "step": 383
+    },
+    {
+      "epoch": 11.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2229,
+      "step": 384
+    },
+    {
+      "epoch": 11.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1542,
+      "step": 385
+    },
+    {
+      "epoch": 11.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3305,
+      "step": 386
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3448,
+      "step": 387
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2508,
+      "step": 388
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3033,
+      "step": 389
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1879,
+      "step": 390
+    },
+    {
+      "epoch": 12.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3695,
+      "step": 391
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.278,
+      "step": 392
+    },
+    {
+      "epoch": 12.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4726,
+      "step": 393
+    },
+    {
+      "epoch": 12.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.142,
+      "step": 394
+    },
+    {
+      "epoch": 12.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2075,
+      "step": 395
+    },
+    {
+      "epoch": 12.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4716,
+      "step": 396
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.336,
+      "step": 397
+    },
+    {
+      "epoch": 12.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0818,
+      "step": 398
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3366,
+      "step": 399
+    },
+    {
+      "epoch": 12.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3219,
+      "step": 400
+    },
+    {
+      "epoch": 12.31,
+      "eval_loss": 1.2088563442230225,
+      "eval_runtime": 1.7541,
+      "eval_samples_per_second": 3.991,
+      "eval_steps_per_second": 2.28,
+      "step": 400
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4101,
+      "step": 401
+    },
+    {
+      "epoch": 12.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2773,
+      "step": 402
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3575,
+      "step": 403
+    },
+    {
+      "epoch": 12.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.089,
+      "step": 404
+    },
+    {
+      "epoch": 12.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4164,
+      "step": 405
+    },
+    {
+      "epoch": 12.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3292,
+      "step": 406
+    },
+    {
+      "epoch": 12.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3447,
+      "step": 407
+    },
+    {
+      "epoch": 12.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4455,
+      "step": 408
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3716,
+      "step": 409
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.338,
+      "step": 410
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2842,
+      "step": 411
+    },
+    {
+      "epoch": 12.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0655,
+      "step": 412
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1405,
+      "step": 413
+    },
+    {
+      "epoch": 12.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3488,
+      "step": 414
+    },
+    {
+      "epoch": 12.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1401,
+      "step": 415
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2261,
+      "step": 416
+    },
+    {
+      "epoch": 12.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2211,
+      "step": 417
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.235,
+      "step": 418
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2779,
+      "step": 419
+    },
+    {
+      "epoch": 12.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.228,
+      "step": 420
+    },
+    {
+      "epoch": 12.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3058,
+      "step": 421
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2325,
+      "step": 422
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3127,
+      "step": 423
+    },
+    {
+      "epoch": 13.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.382,
+      "step": 424
+    },
+    {
+      "epoch": 13.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3625,
+      "step": 425
+    },
+    {
+      "epoch": 13.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3533,
+      "step": 426
+    },
+    {
+      "epoch": 13.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2046,
+      "step": 427
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2991,
+      "step": 428
+    },
+    {
+      "epoch": 13.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1785,
+      "step": 429
+    },
+    {
+      "epoch": 13.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2795,
+      "step": 430
+    },
+    {
+      "epoch": 13.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.248,
+      "step": 431
+    },
+    {
+      "epoch": 13.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3476,
+      "step": 432
+    },
+    {
+      "epoch": 13.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.277,
+      "step": 433
+    },
+    {
+      "epoch": 13.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2044,
+      "step": 434
+    },
+    {
+      "epoch": 13.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1909,
+      "step": 435
+    },
+    {
+      "epoch": 13.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2544,
+      "step": 436
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2036,
+      "step": 437
+    },
+    {
+      "epoch": 13.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2141,
+      "step": 438
+    },
+    {
+      "epoch": 13.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2086,
+      "step": 439
+    },
+    {
+      "epoch": 13.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3863,
+      "step": 440
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2435,
+      "step": 441
+    },
+    {
+      "epoch": 13.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3655,
+      "step": 442
+    },
+    {
+      "epoch": 13.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3562,
+      "step": 443
+    },
+    {
+      "epoch": 13.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3441,
+      "step": 444
+    },
+    {
+      "epoch": 13.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.342,
+      "step": 445
+    },
+    {
+      "epoch": 13.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0318,
+      "step": 446
+    },
+    {
+      "epoch": 13.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3068,
+      "step": 447
+    },
+    {
+      "epoch": 13.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4054,
+      "step": 448
+    },
+    {
+      "epoch": 13.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1914,
+      "step": 449
+    },
+    {
+      "epoch": 13.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3734,
+      "step": 450
+    },
+    {
+      "epoch": 13.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3705,
+      "step": 451
+    },
+    {
+      "epoch": 13.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2954,
+      "step": 452
+    },
+    {
+      "epoch": 13.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2625,
+      "step": 453
+    },
+    {
+      "epoch": 13.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0147,
+      "step": 454
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2888,
+      "step": 455
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1156,
+      "step": 456
+    },
+    {
+      "epoch": 14.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.421,
+      "step": 457
+    },
+    {
+      "epoch": 14.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2285,
+      "step": 458
+    },
+    {
+      "epoch": 14.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2881,
+      "step": 459
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2028,
+      "step": 460
+    },
+    {
+      "epoch": 14.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2213,
+      "step": 461
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2455,
+      "step": 462
+    },
+    {
+      "epoch": 14.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2788,
+      "step": 463
+    },
+    {
+      "epoch": 14.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1349,
+      "step": 464
+    },
+    {
+      "epoch": 14.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3234,
+      "step": 465
+    },
+    {
+      "epoch": 14.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2652,
+      "step": 466
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3123,
+      "step": 467
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3447,
+      "step": 468
+    },
+    {
+      "epoch": 14.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2818,
+      "step": 469
+    },
+    {
+      "epoch": 14.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1331,
+      "step": 470
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2309,
+      "step": 471
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2867,
+      "step": 472
+    },
+    {
+      "epoch": 14.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3339,
+      "step": 473
+    },
+    {
+      "epoch": 14.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4158,
+      "step": 474
+    },
+    {
+      "epoch": 14.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.529,
+      "step": 475
+    },
+    {
+      "epoch": 14.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.258,
+      "step": 476
+    },
+    {
+      "epoch": 14.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3033,
+      "step": 477
+    },
+    {
+      "epoch": 14.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.147,
+      "step": 478
+    },
+    {
+      "epoch": 14.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3166,
+      "step": 479
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2171,
+      "step": 480
+    },
+    {
+      "epoch": 14.77,
+      "eval_loss": 1.1870461702346802,
+      "eval_runtime": 1.7297,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.312,
+      "step": 480
+    },
+    {
+      "epoch": 14.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.18,
+      "step": 481
+    },
+    {
+      "epoch": 14.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2117,
+      "step": 482
+    },
+    {
+      "epoch": 14.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.148,
+      "step": 483
+    },
+    {
+      "epoch": 14.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3961,
+      "step": 484
+    },
+    {
+      "epoch": 14.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3331,
+      "step": 485
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3485,
+      "step": 486
+    },
+    {
+      "epoch": 14.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0999,
+      "step": 487
+    },
+    {
+      "epoch": 15.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2521,
+      "step": 488
+    },
+    {
+      "epoch": 15.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2097,
+      "step": 489
+    },
+    {
+      "epoch": 15.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2557,
+      "step": 490
+    },
+    {
+      "epoch": 15.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2638,
+      "step": 491
+    },
+    {
+      "epoch": 15.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3549,
+      "step": 492
+    },
+    {
+      "epoch": 15.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2417,
+      "step": 493
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2861,
+      "step": 494
+    },
+    {
+      "epoch": 15.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2428,
+      "step": 495
+    },
+    {
+      "epoch": 15.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1561,
+      "step": 496
+    },
+    {
+      "epoch": 15.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2641,
+      "step": 497
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3073,
+      "step": 498
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2227,
+      "step": 499
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3311,
+      "step": 500
+    },
+    {
+      "epoch": 15.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2581,
+      "step": 501
+    },
+    {
+      "epoch": 15.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2751,
+      "step": 502
+    },
+    {
+      "epoch": 15.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4222,
+      "step": 503
+    },
+    {
+      "epoch": 15.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3263,
+      "step": 504
+    },
+    {
+      "epoch": 15.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2236,
+      "step": 505
+    },
+    {
+      "epoch": 15.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3125,
+      "step": 506
+    },
+    {
+      "epoch": 15.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.424,
+      "step": 507
+    },
+    {
+      "epoch": 15.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2231,
+      "step": 508
+    },
+    {
+      "epoch": 15.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2089,
+      "step": 509
+    },
+    {
+      "epoch": 15.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4663,
+      "step": 510
+    },
+    {
+      "epoch": 15.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3236,
+      "step": 511
+    },
+    {
+      "epoch": 15.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2133,
+      "step": 512
+    },
+    {
+      "epoch": 15.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1598,
+      "step": 513
+    },
+    {
+      "epoch": 15.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3023,
+      "step": 514
+    },
+    {
+      "epoch": 15.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.139,
+      "step": 515
+    },
+    {
+      "epoch": 15.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1881,
+      "step": 516
+    },
+    {
+      "epoch": 15.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1448,
+      "step": 517
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2321,
+      "step": 518
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2134,
+      "step": 519
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3268,
+      "step": 520
+    },
+    {
+      "epoch": 16.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3858,
+      "step": 521
+    },
+    {
+      "epoch": 16.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3358,
+      "step": 522
+    },
+    {
+      "epoch": 16.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2051,
+      "step": 523
+    },
+    {
+      "epoch": 16.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1431,
+      "step": 524
+    },
+    {
+      "epoch": 16.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2539,
+      "step": 525
+    },
+    {
+      "epoch": 16.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3096,
+      "step": 526
+    },
+    {
+      "epoch": 16.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1879,
+      "step": 527
+    },
+    {
+      "epoch": 16.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3215,
+      "step": 528
+    },
+    {
+      "epoch": 16.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2835,
+      "step": 529
+    },
+    {
+      "epoch": 16.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2596,
+      "step": 530
+    },
+    {
+      "epoch": 16.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2635,
+      "step": 531
+    },
+    {
+      "epoch": 16.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4138,
+      "step": 532
+    },
+    {
+      "epoch": 16.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2552,
+      "step": 533
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.337,
+      "step": 534
+    },
+    {
+      "epoch": 16.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1408,
+      "step": 535
+    },
+    {
+      "epoch": 16.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2962,
+      "step": 536
+    },
+    {
+      "epoch": 16.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3547,
+      "step": 537
+    },
+    {
+      "epoch": 16.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2199,
+      "step": 538
+    },
+    {
+      "epoch": 16.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2924,
+      "step": 539
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1342,
+      "step": 540
+    },
+    {
+      "epoch": 16.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2628,
+      "step": 541
+    },
+    {
+      "epoch": 16.68,
+      "learning_rate": 2.5e-07,
+      "loss": 0.9506,
+      "step": 542
+    },
+    {
+      "epoch": 16.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3052,
+      "step": 543
+    },
+    {
+      "epoch": 16.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3089,
+      "step": 544
+    },
+    {
+      "epoch": 16.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3776,
+      "step": 545
+    },
+    {
+      "epoch": 16.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0516,
+      "step": 546
+    },
+    {
+      "epoch": 16.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1433,
+      "step": 547
+    },
+    {
+      "epoch": 16.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3056,
+      "step": 548
+    },
+    {
+      "epoch": 16.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2652,
+      "step": 549
+    },
+    {
+      "epoch": 16.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2002,
+      "step": 550
+    },
+    {
+      "epoch": 16.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.181,
+      "step": 551
+    },
+    {
+      "epoch": 16.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0902,
+      "step": 552
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2845,
+      "step": 553
+    },
+    {
+      "epoch": 17.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2646,
+      "step": 554
+    },
+    {
+      "epoch": 17.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0982,
+      "step": 555
+    },
+    {
+      "epoch": 17.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1109,
+      "step": 556
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2508,
+      "step": 557
+    },
+    {
+      "epoch": 17.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2859,
+      "step": 558
+    },
+    {
+      "epoch": 17.2,
+      "learning_rate": 2.5e-07,
+      "loss": 0.9845,
+      "step": 559
+    },
+    {
+      "epoch": 17.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1686,
+      "step": 560
+    },
+    {
+      "epoch": 17.23,
+      "eval_loss": 1.173031210899353,
+      "eval_runtime": 1.7371,
+      "eval_samples_per_second": 4.03,
+      "eval_steps_per_second": 2.303,
+      "step": 560
+    },
+    {
+      "epoch": 17.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2483,
+      "step": 561
+    },
+    {
+      "epoch": 17.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3438,
+      "step": 562
+    },
+    {
+      "epoch": 17.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2862,
+      "step": 563
+    },
+    {
+      "epoch": 17.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2464,
+      "step": 564
+    },
+    {
+      "epoch": 17.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3084,
+      "step": 565
+    },
+    {
+      "epoch": 17.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2382,
+      "step": 566
+    },
+    {
+      "epoch": 17.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2763,
+      "step": 567
+    },
+    {
+      "epoch": 17.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1901,
+      "step": 568
+    },
+    {
+      "epoch": 17.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0708,
+      "step": 569
+    },
+    {
+      "epoch": 17.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2879,
+      "step": 570
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2257,
+      "step": 571
+    },
+    {
+      "epoch": 17.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.06,
+      "step": 572
+    },
+    {
+      "epoch": 17.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3583,
+      "step": 573
+    },
+    {
+      "epoch": 17.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2269,
+      "step": 574
+    },
+    {
+      "epoch": 17.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3294,
+      "step": 575
+    },
+    {
+      "epoch": 17.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3498,
+      "step": 576
+    },
+    {
+      "epoch": 17.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0898,
+      "step": 577
+    },
+    {
+      "epoch": 17.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2676,
+      "step": 578
+    },
+    {
+      "epoch": 17.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3162,
+      "step": 579
+    },
+    {
+      "epoch": 17.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3982,
+      "step": 580
+    },
+    {
+      "epoch": 17.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3926,
+      "step": 581
+    },
+    {
+      "epoch": 17.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1394,
+      "step": 582
+    },
+    {
+      "epoch": 17.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2473,
+      "step": 583
+    },
+    {
+      "epoch": 17.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1476,
+      "step": 584
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.226,
+      "step": 585
+    },
+    {
+      "epoch": 18.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2704,
+      "step": 586
+    },
+    {
+      "epoch": 18.06,
+      "learning_rate": 2.5e-07,
+      "loss": 0.9477,
+      "step": 587
+    },
+    {
+      "epoch": 18.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3465,
+      "step": 588
+    },
+    {
+      "epoch": 18.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3294,
+      "step": 589
+    },
+    {
+      "epoch": 18.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.057,
+      "step": 590
+    },
+    {
+      "epoch": 18.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2434,
+      "step": 591
+    },
+    {
+      "epoch": 18.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2729,
+      "step": 592
+    },
+    {
+      "epoch": 18.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1356,
+      "step": 593
+    },
+    {
+      "epoch": 18.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1587,
+      "step": 594
+    },
+    {
+      "epoch": 18.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1197,
+      "step": 595
+    },
+    {
+      "epoch": 18.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1778,
+      "step": 596
+    },
+    {
+      "epoch": 18.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1198,
+      "step": 597
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3865,
+      "step": 598
+    },
+    {
+      "epoch": 18.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2218,
+      "step": 599
+    },
+    {
+      "epoch": 18.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0191,
+      "step": 600
+    },
+    {
+      "epoch": 18.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3666,
+      "step": 601
+    },
+    {
+      "epoch": 18.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3141,
+      "step": 602
+    },
+    {
+      "epoch": 18.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.279,
+      "step": 603
+    },
+    {
+      "epoch": 18.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.32,
+      "step": 604
+    },
+    {
+      "epoch": 18.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3216,
+      "step": 605
+    },
+    {
+      "epoch": 18.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1378,
+      "step": 606
+    },
+    {
+      "epoch": 18.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.174,
+      "step": 607
+    },
+    {
+      "epoch": 18.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1897,
+      "step": 608
+    },
+    {
+      "epoch": 18.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2227,
+      "step": 609
+    },
+    {
+      "epoch": 18.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2315,
+      "step": 610
+    },
+    {
+      "epoch": 18.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1637,
+      "step": 611
+    },
+    {
+      "epoch": 18.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2978,
+      "step": 612
+    },
+    {
+      "epoch": 18.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2103,
+      "step": 613
+    },
+    {
+      "epoch": 18.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3145,
+      "step": 614
+    },
+    {
+      "epoch": 18.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2807,
+      "step": 615
+    },
+    {
+      "epoch": 18.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2668,
+      "step": 616
+    },
+    {
+      "epoch": 18.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2986,
+      "step": 617
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1996,
+      "step": 618
+    },
+    {
+      "epoch": 19.05,
+      "learning_rate": 2.5e-07,
+      "loss": 0.9905,
+      "step": 619
+    },
+    {
+      "epoch": 19.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3338,
+      "step": 620
+    },
+    {
+      "epoch": 19.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0955,
+      "step": 621
+    },
+    {
+      "epoch": 19.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1721,
+      "step": 622
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2088,
+      "step": 623
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3623,
+      "step": 624
+    },
+    {
+      "epoch": 19.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0578,
+      "step": 625
+    },
+    {
+      "epoch": 19.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0765,
+      "step": 626
+    },
+    {
+      "epoch": 19.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3624,
+      "step": 627
+    },
+    {
+      "epoch": 19.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1778,
+      "step": 628
+    },
+    {
+      "epoch": 19.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2267,
+      "step": 629
+    },
+    {
+      "epoch": 19.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2311,
+      "step": 630
+    },
+    {
+      "epoch": 19.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3226,
+      "step": 631
+    },
+    {
+      "epoch": 19.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2294,
+      "step": 632
+    },
+    {
+      "epoch": 19.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0192,
+      "step": 633
+    },
+    {
+      "epoch": 19.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2559,
+      "step": 634
+    },
+    {
+      "epoch": 19.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2497,
+      "step": 635
+    },
+    {
+      "epoch": 19.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.4026,
+      "step": 636
+    },
+    {
+      "epoch": 19.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2551,
+      "step": 637
+    },
+    {
+      "epoch": 19.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2695,
+      "step": 638
+    },
+    {
+      "epoch": 19.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2047,
+      "step": 639
+    },
+    {
+      "epoch": 19.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1506,
+      "step": 640
+    },
+    {
+      "epoch": 19.69,
+      "eval_loss": 1.161481261253357,
+      "eval_runtime": 1.7425,
+      "eval_samples_per_second": 4.017,
+      "eval_steps_per_second": 2.296,
+      "step": 640
+    },
+    {
+      "epoch": 19.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2597,
+      "step": 641
+    },
+    {
+      "epoch": 19.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1908,
+      "step": 642
+    },
+    {
+      "epoch": 19.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2338,
+      "step": 643
+    },
+    {
+      "epoch": 19.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.31,
+      "step": 644
+    },
+    {
+      "epoch": 19.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0713,
+      "step": 645
+    },
+    {
+      "epoch": 19.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2727,
+      "step": 646
+    },
+    {
+      "epoch": 19.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2029,
+      "step": 647
+    },
+    {
+      "epoch": 19.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3007,
+      "step": 648
+    },
+    {
+      "epoch": 19.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3173,
+      "step": 649
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2024,
+      "step": 650
+    },
+    {
+      "epoch": 20.03,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1753,
+      "step": 651
+    },
+    {
+      "epoch": 20.06,
+      "learning_rate": 2.5e-07,
+      "loss": 1.273,
+      "step": 652
+    },
+    {
+      "epoch": 20.09,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2252,
+      "step": 653
+    },
+    {
+      "epoch": 20.12,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2582,
+      "step": 654
+    },
+    {
+      "epoch": 20.15,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2634,
+      "step": 655
+    },
+    {
+      "epoch": 20.18,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2168,
+      "step": 656
+    },
+    {
+      "epoch": 20.22,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2868,
+      "step": 657
+    },
+    {
+      "epoch": 20.25,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2229,
+      "step": 658
+    },
+    {
+      "epoch": 20.28,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0799,
+      "step": 659
+    },
+    {
+      "epoch": 20.31,
+      "learning_rate": 2.5e-07,
+      "loss": 1.187,
+      "step": 660
+    },
+    {
+      "epoch": 20.34,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3681,
+      "step": 661
+    },
+    {
+      "epoch": 20.37,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1951,
+      "step": 662
+    },
+    {
+      "epoch": 20.4,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0643,
+      "step": 663
+    },
+    {
+      "epoch": 20.43,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2073,
+      "step": 664
+    },
+    {
+      "epoch": 20.46,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2797,
+      "step": 665
+    },
+    {
+      "epoch": 20.49,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3999,
+      "step": 666
+    },
+    {
+      "epoch": 20.52,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2501,
+      "step": 667
+    },
+    {
+      "epoch": 20.55,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2163,
+      "step": 668
+    },
+    {
+      "epoch": 20.58,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3067,
+      "step": 669
+    },
+    {
+      "epoch": 20.62,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1854,
+      "step": 670
+    },
+    {
+      "epoch": 20.65,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1188,
+      "step": 671
+    },
+    {
+      "epoch": 20.68,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2344,
+      "step": 672
+    },
+    {
+      "epoch": 20.71,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2431,
+      "step": 673
+    },
+    {
+      "epoch": 20.74,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1848,
+      "step": 674
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3042,
+      "step": 675
+    },
+    {
+      "epoch": 20.8,
+      "learning_rate": 2.5e-07,
+      "loss": 1.121,
+      "step": 676
+    },
+    {
+      "epoch": 20.83,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1777,
+      "step": 677
+    },
+    {
+      "epoch": 20.86,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2183,
+      "step": 678
+    },
+    {
+      "epoch": 20.89,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1327,
+      "step": 679
+    },
+    {
+      "epoch": 20.92,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1136,
+      "step": 680
+    },
+    {
+      "epoch": 20.95,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2761,
+      "step": 681
+    },
+    {
+      "epoch": 20.98,
+      "learning_rate": 2.5e-07,
+      "loss": 1.079,
+      "step": 682
+    },
+    {
+      "epoch": 21.02,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2263,
+      "step": 683
+    },
+    {
+      "epoch": 21.05,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2507,
+      "step": 684
+    },
+    {
+      "epoch": 21.08,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1574,
+      "step": 685
+    },
+    {
+      "epoch": 21.11,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0829,
+      "step": 686
+    },
+    {
+      "epoch": 21.14,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2645,
+      "step": 687
+    },
+    {
+      "epoch": 21.17,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2632,
+      "step": 688
+    },
+    {
+      "epoch": 21.2,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2332,
+      "step": 689
+    },
+    {
+      "epoch": 21.23,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2069,
+      "step": 690
+    },
+    {
+      "epoch": 21.26,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2087,
+      "step": 691
+    },
+    {
+      "epoch": 21.29,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1768,
+      "step": 692
+    },
+    {
+      "epoch": 21.32,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0126,
+      "step": 693
+    },
+    {
+      "epoch": 21.35,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3168,
+      "step": 694
+    },
+    {
+      "epoch": 21.38,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0629,
+      "step": 695
+    },
+    {
+      "epoch": 21.42,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1156,
+      "step": 696
+    },
+    {
+      "epoch": 21.45,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2308,
+      "step": 697
+    },
+    {
+      "epoch": 21.48,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2688,
+      "step": 698
+    },
+    {
+      "epoch": 21.51,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1114,
+      "step": 699
+    },
+    {
+      "epoch": 21.54,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0432,
+      "step": 700
+    },
+    {
+      "epoch": 21.57,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2938,
+      "step": 701
+    },
+    {
+      "epoch": 21.6,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2673,
+      "step": 702
+    },
+    {
+      "epoch": 21.63,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2795,
+      "step": 703
+    },
+    {
+      "epoch": 21.66,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1992,
+      "step": 704
+    },
+    {
+      "epoch": 21.69,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2114,
+      "step": 705
+    },
+    {
+      "epoch": 21.72,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1559,
+      "step": 706
+    },
+    {
+      "epoch": 21.75,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1923,
+      "step": 707
+    },
+    {
+      "epoch": 21.78,
+      "learning_rate": 2.5e-07,
+      "loss": 1.135,
+      "step": 708
+    },
+    {
+      "epoch": 21.82,
+      "learning_rate": 2.5e-07,
+      "loss": 1.1937,
+      "step": 709
+    },
+    {
+      "epoch": 21.85,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3328,
+      "step": 710
+    },
+    {
+      "epoch": 21.88,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2513,
+      "step": 711
+    },
+    {
+      "epoch": 21.91,
+      "learning_rate": 2.5e-07,
+      "loss": 1.197,
+      "step": 712
+    },
+    {
+      "epoch": 21.94,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0483,
+      "step": 713
+    },
+    {
+      "epoch": 21.97,
+      "learning_rate": 2.5e-07,
+      "loss": 1.3072,
+      "step": 714
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2929,
+      "step": 715
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 65,
+  "total_flos": 1.1332584807727104e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-715/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c358b1c810a69ea433dd5d29f474567432f37c0574609fc5626a2db2ddb233f
+size 4603

checkpoint-975/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: ./NeverSleep_Noromaid-13b-v0.1.1/
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2

checkpoint-975/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-975/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b9f37d21e76d17c9d2df4aafd722bc1cd925ed48bd9e23242e3c69676019cb
+size 4005637552

checkpoint-975/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e99ff80a14dc14551b9b10f4b22228f42357d01fbbecd2c8d9507bbef93627b
+size 2007352159

checkpoint-975/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bae2602d66e11cf54949dce7bd9fa50f05836ba53bf914029ecbb7e6d6fb1e7
+size 14575

checkpoint-975/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585ac4cbd0d7887c969d6a27c976182c94bea53c3b830f86879cda818834992a
+size 627

checkpoint-975/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c358b1c810a69ea433dd5d29f474567432f37c0574609fc5626a2db2ddb233f
+size 4603

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "./NeverSleep_Noromaid-13b-v0.1.1/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_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
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}