Upload folder using huggingface_hub

README.md

@@ -0,0 +1,75 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-v0.1
+model-index:
+- name: workspace/volume/mixtral-limarp-qlora-out
+  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)
+# workspace/volume/mixtral-limarp-qlora-out
+
+This model was trained from scratch on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "w1",
+    "v_proj",
+    "w3",
+    "gate"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9ab0025bafd0267f97835f074b285bb9e5c2827470206b837fc440ca05394e
+size 1938496613

checkpoint-115/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: models/Mixtral-8x7B-v0.1
+---
+
+# 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: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-115/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "w1",
+    "v_proj",
+    "w3",
+    "gate"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-115/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3325b593f902aa766b1861cf4bb0ffb41f54adc36bc17df51c974b7b3bd8cbf
+size 1938077512

checkpoint-115/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c920569256807a690052012e9ba2fdc360ea4ee86dbdc010f21e7ee84eb797
+size 972996831

checkpoint-115/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af82624dc04e27b7f63234d76639124e7f2b8f8afb2f33f340506801de4a55ef
+size 14575

checkpoint-115/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47eab85b5cc8364eb29207976030680ce8627d3ffac7bedc36614e446c4622dc
+size 627

checkpoint-115/trainer_state.json

@@ -0,0 +1,711 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9956709956709957,
+  "eval_steps": 500,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2.0642,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.0704,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 2.0758,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 2.0031,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-05,
+      "loss": 2.0466,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-05,
+      "loss": 2.027,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7e-05,
+      "loss": 2.0737,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8e-05,
+      "loss": 2.1039,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9e-05,
+      "loss": 2.0212,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001,
+      "loss": 2.047,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.999780139628657e-05,
+      "loss": 2.0435,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.99912057785006e-05,
+      "loss": 2.0305,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.998021372668808e-05,
+      "loss": 1.9602,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.996482620753565e-05,
+      "loss": 2.0138,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.994504457428558e-05,
+      "loss": 2.065,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.992087056661677e-05,
+      "loss": 2.0051,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989230631049171e-05,
+      "loss": 2.008,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.985935431796962e-05,
+      "loss": 1.9578,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.982201748698542e-05,
+      "loss": 1.9591,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.978029910109491e-05,
+      "loss": 1.9495,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.973420282918601e-05,
+      "loss": 1.9121,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.968373272515612e-05,
+      "loss": 1.9639,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.962889322755555e-05,
+      "loss": 1.9431,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.956968915919725e-05,
+      "loss": 1.9283,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.950612572673255e-05,
+      "loss": 1.9112,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.943820852019344e-05,
+      "loss": 1.9942,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.936594351250082e-05,
+      "loss": 1.9536,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.928933705893924e-05,
+      "loss": 1.9364,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.920839589659803e-05,
+      "loss": 1.9485,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.91231271437788e-05,
+      "loss": 1.9743,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.903353829936943e-05,
+      "loss": 1.9492,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.893963724218455e-05,
+      "loss": 1.9612,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.884143223027266e-05,
+      "loss": 1.8852,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.873893190018995e-05,
+      "loss": 1.9104,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.863214526624065e-05,
+      "loss": 1.9762,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.852108171968436e-05,
+      "loss": 1.9602,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.840575102791013e-05,
+      "loss": 1.9283,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.828616333357743e-05,
+      "loss": 1.8863,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.816232915372423e-05,
+      "loss": 1.9776,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.8034259378842e-05,
+      "loss": 1.8874,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.790196527191811e-05,
+      "loss": 1.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.776545846744509e-05,
+      "loss": 1.9399,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.762475097039767e-05,
+      "loss": 1.8758,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.747985515517683e-05,
+      "loss": 1.903,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.733078376452171e-05,
+      "loss": 1.9438,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.717754990838881e-05,
+      "loss": 1.885,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.702016706279913e-05,
+      "loss": 1.9278,
+      "step": 47
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.685864906865303e-05,
+      "loss": 1.9612,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.669301013051297e-05,
+      "loss": 1.9352,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.652326481535435e-05,
+      "loss": 1.9198,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.634942805128433e-05,
+      "loss": 1.9552,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.617151512622917e-05,
+      "loss": 1.9767,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.598954168658955e-05,
+      "loss": 1.9933,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.580352373586467e-05,
+      "loss": 1.9751,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.561347763324484e-05,
+      "loss": 1.8376,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.541942009217273e-05,
+      "loss": 1.9485,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.522136817887353e-05,
+      "loss": 1.885,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.501933931085416e-05,
+      "loss": 1.9241,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.481335125537138e-05,
+      "loss": 1.8931,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.460342212786932e-05,
+      "loss": 1.9544,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.43895703903864e-05,
+      "loss": 1.8637,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.417181484993154e-05,
+      "loss": 1.964,
+      "step": 62
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.395017465683036e-05,
+      "loss": 1.8605,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.372466930304091e-05,
+      "loss": 1.9388,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.349531862043952e-05,
+      "loss": 1.9195,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.32621427790767e-05,
+      "loss": 1.9328,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.302516228540327e-05,
+      "loss": 1.8901,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.278439798046697e-05,
+      "loss": 1.9296,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.253987103807958e-05,
+      "loss": 1.9282,
+      "step": 69
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.229160296295488e-05,
+      "loss": 1.9448,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.203961558881731e-05,
+      "loss": 1.9211,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.178393107648193e-05,
+      "loss": 1.8658,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.15245719119055e-05,
+      "loss": 1.9358,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.126156090420888e-05,
+      "loss": 1.9446,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.099492118367123e-05,
+      "loss": 1.8403,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.072467619969572e-05,
+      "loss": 1.9857,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.878,
+      "step": 77
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.017346582226289e-05,
+      "loss": 1.9484,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 8.98925489045329e-05,
+      "loss": 1.8543,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.960812367055646e-05,
+      "loss": 1.8613,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.93202151338687e-05,
+      "loss": 1.887,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.902884861434065e-05,
+      "loss": 1.8897,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.873404973595285e-05,
+      "loss": 1.93,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.843584442454158e-05,
+      "loss": 1.951,
+      "step": 84
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.81342589055191e-05,
+      "loss": 1.9591,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.782931970156707e-05,
+      "loss": 1.8649,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.752105363030414e-05,
+      "loss": 1.9752,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.720948780192746e-05,
+      "loss": 1.9189,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.689464961682852e-05,
+      "loss": 1.9188,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.657656676318346e-05,
+      "loss": 1.9376,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.625526721451798e-05,
+      "loss": 1.8662,
+      "step": 91
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.593077922724733e-05,
+      "loss": 1.8113,
+      "step": 92
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.560313133819125e-05,
+      "loss": 1.8575,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.527235236206436e-05,
+      "loss": 1.8991,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.493847138894209e-05,
+      "loss": 1.8475,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.46015177817023e-05,
+      "loss": 1.8795,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.426152117344313e-05,
+      "loss": 1.8596,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.391851146487675e-05,
+      "loss": 1.9481,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.357251882169994e-05,
+      "loss": 1.9213,
+      "step": 99
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.322357367194109e-05,
+      "loss": 1.9243,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.28717067032843e-05,
+      "loss": 1.8764,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.251694886037052e-05,
+      "loss": 1.9728,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.215933134207618e-05,
+      "loss": 1.884,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.179888559876943e-05,
+      "loss": 1.9589,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 8.143564332954425e-05,
+      "loss": 2.017,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.106963647943274e-05,
+      "loss": 1.9672,
+      "step": 106
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.070089723659566e-05,
+      "loss": 1.8711,
+      "step": 107
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.032945802949179e-05,
+      "loss": 1.9211,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.995535152402591e-05,
+      "loss": 1.9019,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.957861062067614e-05,
+      "loss": 1.8887,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.919926845160037e-05,
+      "loss": 1.9923,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.881735837772274e-05,
+      "loss": 1.8621,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.843291398579946e-05,
+      "loss": 1.9584,
+      "step": 113
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.804596908546529e-05,
+      "loss": 1.943,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.765655770625997e-05,
+      "loss": 1.8953,
+      "step": 115
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 115,
+  "total_flos": 2.6099686427118797e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-115/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e39737902bc1aa013dd8f6b24d000cda19aabe9b71208ae812379be1726ec8c
+size 4795

checkpoint-230/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: models/Mixtral-8x7B-v0.1
+---
+
+# 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: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-230/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "w1",
+    "v_proj",
+    "w3",
+    "gate"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-230/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a909a20ca6a9c570131f7517e93fad8bc853beaea325236e5bb10e5e1ece599
+size 1938077512

checkpoint-230/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af45f6bff42bccd81acdde64bf933c8b06fcf5b63fabb60d634fd0b60a48ba40
+size 972996831

checkpoint-230/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668f14d6f24cf58549da323e7e5973480780596e6861e4b5823f339b027234ed
+size 14575

checkpoint-230/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6eeffe63d8c7884ee8ede6b834a2f9647394e073b51e591f22421636a2fca8
+size 627

checkpoint-230/trainer_state.json

@@ -0,0 +1,1401 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9653679653679652,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2.0642,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.0704,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 2.0758,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 2.0031,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-05,
+      "loss": 2.0466,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-05,
+      "loss": 2.027,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7e-05,
+      "loss": 2.0737,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8e-05,
+      "loss": 2.1039,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9e-05,
+      "loss": 2.0212,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001,
+      "loss": 2.047,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.999780139628657e-05,
+      "loss": 2.0435,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.99912057785006e-05,
+      "loss": 2.0305,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.998021372668808e-05,
+      "loss": 1.9602,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.996482620753565e-05,
+      "loss": 2.0138,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.994504457428558e-05,
+      "loss": 2.065,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.992087056661677e-05,
+      "loss": 2.0051,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989230631049171e-05,
+      "loss": 2.008,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.985935431796962e-05,
+      "loss": 1.9578,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.982201748698542e-05,
+      "loss": 1.9591,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.978029910109491e-05,
+      "loss": 1.9495,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.973420282918601e-05,
+      "loss": 1.9121,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.968373272515612e-05,
+      "loss": 1.9639,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.962889322755555e-05,
+      "loss": 1.9431,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.956968915919725e-05,
+      "loss": 1.9283,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.950612572673255e-05,
+      "loss": 1.9112,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.943820852019344e-05,
+      "loss": 1.9942,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.936594351250082e-05,
+      "loss": 1.9536,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.928933705893924e-05,
+      "loss": 1.9364,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.920839589659803e-05,
+      "loss": 1.9485,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.91231271437788e-05,
+      "loss": 1.9743,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.903353829936943e-05,
+      "loss": 1.9492,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.893963724218455e-05,
+      "loss": 1.9612,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.884143223027266e-05,
+      "loss": 1.8852,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.873893190018995e-05,
+      "loss": 1.9104,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.863214526624065e-05,
+      "loss": 1.9762,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.852108171968436e-05,
+      "loss": 1.9602,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.840575102791013e-05,
+      "loss": 1.9283,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.828616333357743e-05,
+      "loss": 1.8863,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.816232915372423e-05,
+      "loss": 1.9776,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.8034259378842e-05,
+      "loss": 1.8874,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.790196527191811e-05,
+      "loss": 1.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.776545846744509e-05,
+      "loss": 1.9399,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.762475097039767e-05,
+      "loss": 1.8758,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.747985515517683e-05,
+      "loss": 1.903,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.733078376452171e-05,
+      "loss": 1.9438,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.717754990838881e-05,
+      "loss": 1.885,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.702016706279913e-05,
+      "loss": 1.9278,
+      "step": 47
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.685864906865303e-05,
+      "loss": 1.9612,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.669301013051297e-05,
+      "loss": 1.9352,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.652326481535435e-05,
+      "loss": 1.9198,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.634942805128433e-05,
+      "loss": 1.9552,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.617151512622917e-05,
+      "loss": 1.9767,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.598954168658955e-05,
+      "loss": 1.9933,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.580352373586467e-05,
+      "loss": 1.9751,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.561347763324484e-05,
+      "loss": 1.8376,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.541942009217273e-05,
+      "loss": 1.9485,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.522136817887353e-05,
+      "loss": 1.885,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.501933931085416e-05,
+      "loss": 1.9241,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.481335125537138e-05,
+      "loss": 1.8931,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.460342212786932e-05,
+      "loss": 1.9544,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.43895703903864e-05,
+      "loss": 1.8637,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.417181484993154e-05,
+      "loss": 1.964,
+      "step": 62
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.395017465683036e-05,
+      "loss": 1.8605,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.372466930304091e-05,
+      "loss": 1.9388,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.349531862043952e-05,
+      "loss": 1.9195,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.32621427790767e-05,
+      "loss": 1.9328,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.302516228540327e-05,
+      "loss": 1.8901,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.278439798046697e-05,
+      "loss": 1.9296,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.253987103807958e-05,
+      "loss": 1.9282,
+      "step": 69
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.229160296295488e-05,
+      "loss": 1.9448,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.203961558881731e-05,
+      "loss": 1.9211,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.178393107648193e-05,
+      "loss": 1.8658,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.15245719119055e-05,
+      "loss": 1.9358,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.126156090420888e-05,
+      "loss": 1.9446,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.099492118367123e-05,
+      "loss": 1.8403,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.072467619969572e-05,
+      "loss": 1.9857,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.878,
+      "step": 77
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.017346582226289e-05,
+      "loss": 1.9484,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 8.98925489045329e-05,
+      "loss": 1.8543,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.960812367055646e-05,
+      "loss": 1.8613,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.93202151338687e-05,
+      "loss": 1.887,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.902884861434065e-05,
+      "loss": 1.8897,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.873404973595285e-05,
+      "loss": 1.93,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.843584442454158e-05,
+      "loss": 1.951,
+      "step": 84
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.81342589055191e-05,
+      "loss": 1.9591,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.782931970156707e-05,
+      "loss": 1.8649,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.752105363030414e-05,
+      "loss": 1.9752,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.720948780192746e-05,
+      "loss": 1.9189,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.689464961682852e-05,
+      "loss": 1.9188,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.657656676318346e-05,
+      "loss": 1.9376,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.625526721451798e-05,
+      "loss": 1.8662,
+      "step": 91
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.593077922724733e-05,
+      "loss": 1.8113,
+      "step": 92
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.560313133819125e-05,
+      "loss": 1.8575,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.527235236206436e-05,
+      "loss": 1.8991,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.493847138894209e-05,
+      "loss": 1.8475,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.46015177817023e-05,
+      "loss": 1.8795,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.426152117344313e-05,
+      "loss": 1.8596,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.391851146487675e-05,
+      "loss": 1.9481,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.357251882169994e-05,
+      "loss": 1.9213,
+      "step": 99
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.322357367194109e-05,
+      "loss": 1.9243,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.28717067032843e-05,
+      "loss": 1.8764,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.251694886037052e-05,
+      "loss": 1.9728,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.215933134207618e-05,
+      "loss": 1.884,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.179888559876943e-05,
+      "loss": 1.9589,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 8.143564332954425e-05,
+      "loss": 2.017,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.106963647943274e-05,
+      "loss": 1.9672,
+      "step": 106
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.070089723659566e-05,
+      "loss": 1.8711,
+      "step": 107
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.032945802949179e-05,
+      "loss": 1.9211,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.995535152402591e-05,
+      "loss": 1.9019,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.957861062067614e-05,
+      "loss": 1.8887,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.919926845160037e-05,
+      "loss": 1.9923,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.881735837772274e-05,
+      "loss": 1.8621,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.843291398579946e-05,
+      "loss": 1.9584,
+      "step": 113
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.804596908546529e-05,
+      "loss": 1.943,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.765655770625997e-05,
+      "loss": 1.8953,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.726471409463572e-05,
+      "loss": 1.9394,
+      "step": 116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.687047271094527e-05,
+      "loss": 1.91,
+      "step": 117
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.64738682264115e-05,
+      "loss": 1.9356,
+      "step": 118
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.607493552007805e-05,
+      "loss": 1.9421,
+      "step": 119
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.56737096757421e-05,
+      "loss": 1.8658,
+      "step": 120
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.527022597886895e-05,
+      "loss": 1.9158,
+      "step": 121
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.486451991348872e-05,
+      "loss": 1.9376,
+      "step": 122
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.445662715907591e-05,
+      "loss": 1.9365,
+      "step": 123
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 7.40465835874115e-05,
+      "loss": 1.8633,
+      "step": 124
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.363442525942826e-05,
+      "loss": 1.8888,
+      "step": 125
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.322018842203941e-05,
+      "loss": 1.8944,
+      "step": 126
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.280390950495093e-05,
+      "loss": 1.8644,
+      "step": 127
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.238562511745768e-05,
+      "loss": 1.9133,
+      "step": 128
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7.196537204522401e-05,
+      "loss": 1.8339,
+      "step": 129
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.154318724704853e-05,
+      "loss": 1.8625,
+      "step": 130
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.111910785161381e-05,
+      "loss": 1.8877,
+      "step": 131
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.06931711542212e-05,
+      "loss": 1.9571,
+      "step": 132
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.026541461351092e-05,
+      "loss": 1.8926,
+      "step": 133
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 6.983587584816769e-05,
+      "loss": 1.8999,
+      "step": 134
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.940459263361249e-05,
+      "loss": 1.8957,
+      "step": 135
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 6.897160289868042e-05,
+      "loss": 1.9096,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.853694472228503e-05,
+      "loss": 1.8695,
+      "step": 137
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.810065633006956e-05,
+      "loss": 1.8959,
+      "step": 138
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.766277609104518e-05,
+      "loss": 1.8242,
+      "step": 139
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.722334251421665e-05,
+      "loss": 1.8903,
+      "step": 140
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.678239424519575e-05,
+      "loss": 1.8978,
+      "step": 141
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.633997006280252e-05,
+      "loss": 1.8537,
+      "step": 142
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.589610887565503e-05,
+      "loss": 1.842,
+      "step": 143
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9226,
+      "step": 144
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.500423175001705e-05,
+      "loss": 1.8413,
+      "step": 145
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.4556294246901e-05,
+      "loss": 1.8876,
+      "step": 146
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.410707660288155e-05,
+      "loss": 1.902,
+      "step": 147
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.36566183240219e-05,
+      "loss": 1.9084,
+      "step": 148
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.320495902549183e-05,
+      "loss": 1.8314,
+      "step": 149
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.275213842808383e-05,
+      "loss": 1.9189,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.229819635471972e-05,
+      "loss": 1.8738,
+      "step": 151
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.184317272694867e-05,
+      "loss": 1.8302,
+      "step": 152
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.138710756143613e-05,
+      "loss": 1.91,
+      "step": 153
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.093004096644481e-05,
+      "loss": 1.8405,
+      "step": 154
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.0472013138307235e-05,
+      "loss": 1.8767,
+      "step": 155
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.001306435789072e-05,
+      "loss": 1.8827,
+      "step": 156
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.9553234987055006e-05,
+      "loss": 1.938,
+      "step": 157
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.909256546510257e-05,
+      "loss": 1.8674,
+      "step": 158
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.86310963052223e-05,
+      "loss": 1.9161,
+      "step": 159
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.816886809092651e-05,
+      "loss": 1.8738,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.770592147248196e-05,
+      "loss": 1.855,
+      "step": 161
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 5.7242297163334804e-05,
+      "loss": 1.895,
+      "step": 162
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.6778035936530184e-05,
+      "loss": 1.8702,
+      "step": 163
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.631317862112636e-05,
+      "loss": 1.9038,
+      "step": 164
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.584776609860414e-05,
+      "loss": 1.8444,
+      "step": 165
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.538183929927152e-05,
+      "loss": 1.9575,
+      "step": 166
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.4915439198664164e-05,
+      "loss": 1.9068,
+      "step": 167
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.4448606813941805e-05,
+      "loss": 1.8192,
+      "step": 168
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.3981383200281e-05,
+      "loss": 1.8179,
+      "step": 169
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.351380944726465e-05,
+      "loss": 1.9271,
+      "step": 170
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.3045926675268344e-05,
+      "loss": 1.8794,
+      "step": 171
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.257777603184407e-05,
+      "loss": 1.9613,
+      "step": 172
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.210939868810156e-05,
+      "loss": 1.9117,
+      "step": 173
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.16408358350875e-05,
+      "loss": 1.8796,
+      "step": 174
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.117212868016303e-05,
+      "loss": 1.881,
+      "step": 175
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5.07033184433798e-05,
+      "loss": 1.9096,
+      "step": 176
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 5.023444635385493e-05,
+      "loss": 1.9094,
+      "step": 177
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 4.9765553646145086e-05,
+      "loss": 1.9166,
+      "step": 178
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 4.9296681556620207e-05,
+      "loss": 1.8408,
+      "step": 179
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.882787131983698e-05,
+      "loss": 1.9153,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.835916416491251e-05,
+      "loss": 1.8751,
+      "step": 181
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.789060131189845e-05,
+      "loss": 1.9234,
+      "step": 182
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.742222396815593e-05,
+      "loss": 1.937,
+      "step": 183
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.6954073324731654e-05,
+      "loss": 1.9361,
+      "step": 184
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.648619055273537e-05,
+      "loss": 1.8353,
+      "step": 185
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.601861679971901e-05,
+      "loss": 1.9344,
+      "step": 186
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.5551393186058213e-05,
+      "loss": 1.788,
+      "step": 187
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.508456080133584e-05,
+      "loss": 1.8955,
+      "step": 188
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.461816070072851e-05,
+      "loss": 1.9064,
+      "step": 189
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.415223390139588e-05,
+      "loss": 1.858,
+      "step": 190
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.368682137887365e-05,
+      "loss": 1.8601,
+      "step": 191
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.322196406346984e-05,
+      "loss": 1.9734,
+      "step": 192
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.27577028366652e-05,
+      "loss": 1.8557,
+      "step": 193
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.229407852751806e-05,
+      "loss": 1.9431,
+      "step": 194
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.183113190907349e-05,
+      "loss": 1.9365,
+      "step": 195
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.136890369477772e-05,
+      "loss": 1.831,
+      "step": 196
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.090743453489744e-05,
+      "loss": 1.8685,
+      "step": 197
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.0446765012945006e-05,
+      "loss": 1.8634,
+      "step": 198
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.998693564210929e-05,
+      "loss": 1.8493,
+      "step": 199
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.952798686169279e-05,
+      "loss": 1.8875,
+      "step": 200
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.9069959033555195e-05,
+      "loss": 1.9417,
+      "step": 201
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.861289243856388e-05,
+      "loss": 1.8595,
+      "step": 202
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.8156827273051365e-05,
+      "loss": 1.8732,
+      "step": 203
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.770180364528029e-05,
+      "loss": 1.8268,
+      "step": 204
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.7247861571916185e-05,
+      "loss": 1.869,
+      "step": 205
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.679504097450816e-05,
+      "loss": 1.8882,
+      "step": 206
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.6343381675978116e-05,
+      "loss": 1.849,
+      "step": 207
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.5892923397118474e-05,
+      "loss": 1.88,
+      "step": 208
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.5443705753099014e-05,
+      "loss": 1.884,
+      "step": 209
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.499576824998298e-05,
+      "loss": 1.8501,
+      "step": 210
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.8654,
+      "step": 211
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.410389112434499e-05,
+      "loss": 1.8698,
+      "step": 212
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.366002993719747e-05,
+      "loss": 1.8402,
+      "step": 213
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.321760575480427e-05,
+      "loss": 1.8361,
+      "step": 214
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.277665748578336e-05,
+      "loss": 1.8392,
+      "step": 215
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.233722390895483e-05,
+      "loss": 1.9025,
+      "step": 216
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.1899343669930446e-05,
+      "loss": 1.8904,
+      "step": 217
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.146305527771499e-05,
+      "loss": 1.9215,
+      "step": 218
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.102839710131958e-05,
+      "loss": 1.8426,
+      "step": 219
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.0595407366387504e-05,
+      "loss": 1.9003,
+      "step": 220
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.016412415183233e-05,
+      "loss": 1.8339,
+      "step": 221
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.9734585386489093e-05,
+      "loss": 1.8936,
+      "step": 222
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.93068288457788e-05,
+      "loss": 1.8554,
+      "step": 223
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.8880892148386198e-05,
+      "loss": 1.9069,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.8456812752951485e-05,
+      "loss": 1.9439,
+      "step": 225
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.8034627954775994e-05,
+      "loss": 1.888,
+      "step": 226
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.7614374882542317e-05,
+      "loss": 1.9194,
+      "step": 227
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.719609049504911e-05,
+      "loss": 1.895,
+      "step": 228
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.677981157796059e-05,
+      "loss": 1.8856,
+      "step": 229
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.636557474057173e-05,
+      "loss": 1.8132,
+      "step": 230
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 115,
+  "total_flos": 5.211426518110568e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-230/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e39737902bc1aa013dd8f6b24d000cda19aabe9b71208ae812379be1726ec8c
+size 4795

checkpoint-345/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: models/Mixtral-8x7B-v0.1
+---
+
+# 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: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-345/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "w1",
+    "v_proj",
+    "w3",
+    "gate"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-345/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf652549174df3df03046aeeab44f7f064f420fccbaac711a2ef3918db73879
+size 1938077512

checkpoint-345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c781620ff6f9887affde54d887e1a0061dc8ec9ec959be9595d325ab08e3f2
+size 972998687

checkpoint-345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942b2dd789f3258b07280489bf08f2bfc3c8d694d13c0348dd1fd15347b760de
+size 14575

checkpoint-345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3f7fc1aafbb579094c3e8aa83cdc71ce8c488b4be46f18c6438e1775f7d238
+size 627

checkpoint-345/trainer_state.json

@@ -0,0 +1,2091 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9393939393939394,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2.0642,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.0704,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 2.0758,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 2.0031,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-05,
+      "loss": 2.0466,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6e-05,
+      "loss": 2.027,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7e-05,
+      "loss": 2.0737,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8e-05,
+      "loss": 2.1039,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9e-05,
+      "loss": 2.0212,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001,
+      "loss": 2.047,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.999780139628657e-05,
+      "loss": 2.0435,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.99912057785006e-05,
+      "loss": 2.0305,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.998021372668808e-05,
+      "loss": 1.9602,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.996482620753565e-05,
+      "loss": 2.0138,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.994504457428558e-05,
+      "loss": 2.065,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.992087056661677e-05,
+      "loss": 2.0051,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989230631049171e-05,
+      "loss": 2.008,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.985935431796962e-05,
+      "loss": 1.9578,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.982201748698542e-05,
+      "loss": 1.9591,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.978029910109491e-05,
+      "loss": 1.9495,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.973420282918601e-05,
+      "loss": 1.9121,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.968373272515612e-05,
+      "loss": 1.9639,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.962889322755555e-05,
+      "loss": 1.9431,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.956968915919725e-05,
+      "loss": 1.9283,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.950612572673255e-05,
+      "loss": 1.9112,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.943820852019344e-05,
+      "loss": 1.9942,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.936594351250082e-05,
+      "loss": 1.9536,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.928933705893924e-05,
+      "loss": 1.9364,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.920839589659803e-05,
+      "loss": 1.9485,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.91231271437788e-05,
+      "loss": 1.9743,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.903353829936943e-05,
+      "loss": 1.9492,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.893963724218455e-05,
+      "loss": 1.9612,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.884143223027266e-05,
+      "loss": 1.8852,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.873893190018995e-05,
+      "loss": 1.9104,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.863214526624065e-05,
+      "loss": 1.9762,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.852108171968436e-05,
+      "loss": 1.9602,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.840575102791013e-05,
+      "loss": 1.9283,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.828616333357743e-05,
+      "loss": 1.8863,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.816232915372423e-05,
+      "loss": 1.9776,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.8034259378842e-05,
+      "loss": 1.8874,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.790196527191811e-05,
+      "loss": 1.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.776545846744509e-05,
+      "loss": 1.9399,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.762475097039767e-05,
+      "loss": 1.8758,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.747985515517683e-05,
+      "loss": 1.903,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.733078376452171e-05,
+      "loss": 1.9438,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.717754990838881e-05,
+      "loss": 1.885,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.702016706279913e-05,
+      "loss": 1.9278,
+      "step": 47
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.685864906865303e-05,
+      "loss": 1.9612,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.669301013051297e-05,
+      "loss": 1.9352,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.652326481535435e-05,
+      "loss": 1.9198,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.634942805128433e-05,
+      "loss": 1.9552,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.617151512622917e-05,
+      "loss": 1.9767,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.598954168658955e-05,
+      "loss": 1.9933,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.580352373586467e-05,
+      "loss": 1.9751,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.561347763324484e-05,
+      "loss": 1.8376,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.541942009217273e-05,
+      "loss": 1.9485,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.522136817887353e-05,
+      "loss": 1.885,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.501933931085416e-05,
+      "loss": 1.9241,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.481335125537138e-05,
+      "loss": 1.8931,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.460342212786932e-05,
+      "loss": 1.9544,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.43895703903864e-05,
+      "loss": 1.8637,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.417181484993154e-05,
+      "loss": 1.964,
+      "step": 62
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.395017465683036e-05,
+      "loss": 1.8605,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.372466930304091e-05,
+      "loss": 1.9388,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.349531862043952e-05,
+      "loss": 1.9195,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.32621427790767e-05,
+      "loss": 1.9328,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.302516228540327e-05,
+      "loss": 1.8901,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.278439798046697e-05,
+      "loss": 1.9296,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.253987103807958e-05,
+      "loss": 1.9282,
+      "step": 69
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.229160296295488e-05,
+      "loss": 1.9448,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.203961558881731e-05,
+      "loss": 1.9211,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.178393107648193e-05,
+      "loss": 1.8658,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.15245719119055e-05,
+      "loss": 1.9358,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.126156090420888e-05,
+      "loss": 1.9446,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.099492118367123e-05,
+      "loss": 1.8403,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.072467619969572e-05,
+      "loss": 1.9857,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.878,
+      "step": 77
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.017346582226289e-05,
+      "loss": 1.9484,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 8.98925489045329e-05,
+      "loss": 1.8543,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.960812367055646e-05,
+      "loss": 1.8613,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.93202151338687e-05,
+      "loss": 1.887,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.902884861434065e-05,
+      "loss": 1.8897,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.873404973595285e-05,
+      "loss": 1.93,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.843584442454158e-05,
+      "loss": 1.951,
+      "step": 84
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.81342589055191e-05,
+      "loss": 1.9591,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.782931970156707e-05,
+      "loss": 1.8649,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.752105363030414e-05,
+      "loss": 1.9752,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.720948780192746e-05,
+      "loss": 1.9189,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.689464961682852e-05,
+      "loss": 1.9188,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.657656676318346e-05,
+      "loss": 1.9376,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.625526721451798e-05,
+      "loss": 1.8662,
+      "step": 91
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.593077922724733e-05,
+      "loss": 1.8113,
+      "step": 92
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.560313133819125e-05,
+      "loss": 1.8575,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.527235236206436e-05,
+      "loss": 1.8991,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.493847138894209e-05,
+      "loss": 1.8475,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.46015177817023e-05,
+      "loss": 1.8795,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.426152117344313e-05,
+      "loss": 1.8596,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.391851146487675e-05,
+      "loss": 1.9481,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.357251882169994e-05,
+      "loss": 1.9213,
+      "step": 99
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.322357367194109e-05,
+      "loss": 1.9243,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.28717067032843e-05,
+      "loss": 1.8764,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.251694886037052e-05,
+      "loss": 1.9728,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.215933134207618e-05,
+      "loss": 1.884,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.179888559876943e-05,
+      "loss": 1.9589,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 8.143564332954425e-05,
+      "loss": 2.017,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.106963647943274e-05,
+      "loss": 1.9672,
+      "step": 106
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.070089723659566e-05,
+      "loss": 1.8711,
+      "step": 107
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.032945802949179e-05,
+      "loss": 1.9211,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.995535152402591e-05,
+      "loss": 1.9019,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.957861062067614e-05,
+      "loss": 1.8887,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.919926845160037e-05,
+      "loss": 1.9923,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.881735837772274e-05,
+      "loss": 1.8621,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.843291398579946e-05,
+      "loss": 1.9584,
+      "step": 113
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.804596908546529e-05,
+      "loss": 1.943,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.765655770625997e-05,
+      "loss": 1.8953,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.726471409463572e-05,
+      "loss": 1.9394,
+      "step": 116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.687047271094527e-05,
+      "loss": 1.91,
+      "step": 117
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.64738682264115e-05,
+      "loss": 1.9356,
+      "step": 118
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.607493552007805e-05,
+      "loss": 1.9421,
+      "step": 119
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.56737096757421e-05,
+      "loss": 1.8658,
+      "step": 120
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.527022597886895e-05,
+      "loss": 1.9158,
+      "step": 121
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.486451991348872e-05,
+      "loss": 1.9376,
+      "step": 122
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.445662715907591e-05,
+      "loss": 1.9365,
+      "step": 123
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 7.40465835874115e-05,
+      "loss": 1.8633,
+      "step": 124
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.363442525942826e-05,
+      "loss": 1.8888,
+      "step": 125
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.322018842203941e-05,
+      "loss": 1.8944,
+      "step": 126
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.280390950495093e-05,
+      "loss": 1.8644,
+      "step": 127
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.238562511745768e-05,
+      "loss": 1.9133,
+      "step": 128
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7.196537204522401e-05,
+      "loss": 1.8339,
+      "step": 129
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.154318724704853e-05,
+      "loss": 1.8625,
+      "step": 130
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.111910785161381e-05,
+      "loss": 1.8877,
+      "step": 131
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.06931711542212e-05,
+      "loss": 1.9571,
+      "step": 132
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.026541461351092e-05,
+      "loss": 1.8926,
+      "step": 133
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 6.983587584816769e-05,
+      "loss": 1.8999,
+      "step": 134
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.940459263361249e-05,
+      "loss": 1.8957,
+      "step": 135
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 6.897160289868042e-05,
+      "loss": 1.9096,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.853694472228503e-05,
+      "loss": 1.8695,
+      "step": 137
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 6.810065633006956e-05,
+      "loss": 1.8959,
+      "step": 138
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.766277609104518e-05,
+      "loss": 1.8242,
+      "step": 139
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.722334251421665e-05,
+      "loss": 1.8903,
+      "step": 140
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.678239424519575e-05,
+      "loss": 1.8978,
+      "step": 141
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.633997006280252e-05,
+      "loss": 1.8537,
+      "step": 142
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.589610887565503e-05,
+      "loss": 1.842,
+      "step": 143
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9226,
+      "step": 144
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.500423175001705e-05,
+      "loss": 1.8413,
+      "step": 145
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.4556294246901e-05,
+      "loss": 1.8876,
+      "step": 146
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.410707660288155e-05,
+      "loss": 1.902,
+      "step": 147
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.36566183240219e-05,
+      "loss": 1.9084,
+      "step": 148
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.320495902549183e-05,
+      "loss": 1.8314,
+      "step": 149
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.275213842808383e-05,
+      "loss": 1.9189,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.229819635471972e-05,
+      "loss": 1.8738,
+      "step": 151
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.184317272694867e-05,
+      "loss": 1.8302,
+      "step": 152
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.138710756143613e-05,
+      "loss": 1.91,
+      "step": 153
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.093004096644481e-05,
+      "loss": 1.8405,
+      "step": 154
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.0472013138307235e-05,
+      "loss": 1.8767,
+      "step": 155
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.001306435789072e-05,
+      "loss": 1.8827,
+      "step": 156
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.9553234987055006e-05,
+      "loss": 1.938,
+      "step": 157
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.909256546510257e-05,
+      "loss": 1.8674,
+      "step": 158
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.86310963052223e-05,
+      "loss": 1.9161,
+      "step": 159
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.816886809092651e-05,
+      "loss": 1.8738,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.770592147248196e-05,
+      "loss": 1.855,
+      "step": 161
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 5.7242297163334804e-05,
+      "loss": 1.895,
+      "step": 162
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.6778035936530184e-05,
+      "loss": 1.8702,
+      "step": 163
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.631317862112636e-05,
+      "loss": 1.9038,
+      "step": 164
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.584776609860414e-05,
+      "loss": 1.8444,
+      "step": 165
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.538183929927152e-05,
+      "loss": 1.9575,
+      "step": 166
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.4915439198664164e-05,
+      "loss": 1.9068,
+      "step": 167
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.4448606813941805e-05,
+      "loss": 1.8192,
+      "step": 168
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.3981383200281e-05,
+      "loss": 1.8179,
+      "step": 169
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.351380944726465e-05,
+      "loss": 1.9271,
+      "step": 170
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.3045926675268344e-05,
+      "loss": 1.8794,
+      "step": 171
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.257777603184407e-05,
+      "loss": 1.9613,
+      "step": 172
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.210939868810156e-05,
+      "loss": 1.9117,
+      "step": 173
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.16408358350875e-05,
+      "loss": 1.8796,
+      "step": 174
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.117212868016303e-05,
+      "loss": 1.881,
+      "step": 175
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5.07033184433798e-05,
+      "loss": 1.9096,
+      "step": 176
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 5.023444635385493e-05,
+      "loss": 1.9094,
+      "step": 177
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 4.9765553646145086e-05,
+      "loss": 1.9166,
+      "step": 178
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 4.9296681556620207e-05,
+      "loss": 1.8408,
+      "step": 179
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.882787131983698e-05,
+      "loss": 1.9153,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.835916416491251e-05,
+      "loss": 1.8751,
+      "step": 181
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.789060131189845e-05,
+      "loss": 1.9234,
+      "step": 182
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.742222396815593e-05,
+      "loss": 1.937,
+      "step": 183
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.6954073324731654e-05,
+      "loss": 1.9361,
+      "step": 184
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.648619055273537e-05,
+      "loss": 1.8353,
+      "step": 185
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.601861679971901e-05,
+      "loss": 1.9344,
+      "step": 186
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.5551393186058213e-05,
+      "loss": 1.788,
+      "step": 187
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.508456080133584e-05,
+      "loss": 1.8955,
+      "step": 188
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.461816070072851e-05,
+      "loss": 1.9064,
+      "step": 189
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.415223390139588e-05,
+      "loss": 1.858,
+      "step": 190
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.368682137887365e-05,
+      "loss": 1.8601,
+      "step": 191
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.322196406346984e-05,
+      "loss": 1.9734,
+      "step": 192
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.27577028366652e-05,
+      "loss": 1.8557,
+      "step": 193
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.229407852751806e-05,
+      "loss": 1.9431,
+      "step": 194
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.183113190907349e-05,
+      "loss": 1.9365,
+      "step": 195
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.136890369477772e-05,
+      "loss": 1.831,
+      "step": 196
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.090743453489744e-05,
+      "loss": 1.8685,
+      "step": 197
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.0446765012945006e-05,
+      "loss": 1.8634,
+      "step": 198
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.998693564210929e-05,
+      "loss": 1.8493,
+      "step": 199
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.952798686169279e-05,
+      "loss": 1.8875,
+      "step": 200
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.9069959033555195e-05,
+      "loss": 1.9417,
+      "step": 201
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.861289243856388e-05,
+      "loss": 1.8595,
+      "step": 202
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.8156827273051365e-05,
+      "loss": 1.8732,
+      "step": 203
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.770180364528029e-05,
+      "loss": 1.8268,
+      "step": 204
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.7247861571916185e-05,
+      "loss": 1.869,
+      "step": 205
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.679504097450816e-05,
+      "loss": 1.8882,
+      "step": 206
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.6343381675978116e-05,
+      "loss": 1.849,
+      "step": 207
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.5892923397118474e-05,
+      "loss": 1.88,
+      "step": 208
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.5443705753099014e-05,
+      "loss": 1.884,
+      "step": 209
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.499576824998298e-05,
+      "loss": 1.8501,
+      "step": 210
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.8654,
+      "step": 211
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.410389112434499e-05,
+      "loss": 1.8698,
+      "step": 212
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.366002993719747e-05,
+      "loss": 1.8402,
+      "step": 213
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.321760575480427e-05,
+      "loss": 1.8361,
+      "step": 214
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.277665748578336e-05,
+      "loss": 1.8392,
+      "step": 215
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.233722390895483e-05,
+      "loss": 1.9025,
+      "step": 216
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.1899343669930446e-05,
+      "loss": 1.8904,
+      "step": 217
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.146305527771499e-05,
+      "loss": 1.9215,
+      "step": 218
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.102839710131958e-05,
+      "loss": 1.8426,
+      "step": 219
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.0595407366387504e-05,
+      "loss": 1.9003,
+      "step": 220
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.016412415183233e-05,
+      "loss": 1.8339,
+      "step": 221
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.9734585386489093e-05,
+      "loss": 1.8936,
+      "step": 222
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.93068288457788e-05,
+      "loss": 1.8554,
+      "step": 223
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.8880892148386198e-05,
+      "loss": 1.9069,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.8456812752951485e-05,
+      "loss": 1.9439,
+      "step": 225
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.8034627954775994e-05,
+      "loss": 1.888,
+      "step": 226
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.7614374882542317e-05,
+      "loss": 1.9194,
+      "step": 227
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.719609049504911e-05,
+      "loss": 1.895,
+      "step": 228
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.677981157796059e-05,
+      "loss": 1.8856,
+      "step": 229
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.636557474057173e-05,
+      "loss": 1.8132,
+      "step": 230
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.5953416412588503e-05,
+      "loss": 1.7674,
+      "step": 231
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.554337284092411e-05,
+      "loss": 1.8213,
+      "step": 232
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.5135480086511302e-05,
+      "loss": 1.9571,
+      "step": 233
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.472977402113107e-05,
+      "loss": 1.792,
+      "step": 234
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.4326290324257894e-05,
+      "loss": 1.9039,
+      "step": 235
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.3925064479921984e-05,
+      "loss": 1.8781,
+      "step": 236
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.3526131773588516e-05,
+      "loss": 1.7439,
+      "step": 237
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.3129527289054713e-05,
+      "loss": 1.8181,
+      "step": 238
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.2735285905364306e-05,
+      "loss": 1.8142,
+      "step": 239
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.234344229374003e-05,
+      "loss": 1.8818,
+      "step": 240
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.195403091453473e-05,
+      "loss": 1.8229,
+      "step": 241
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.156708601420053e-05,
+      "loss": 1.79,
+      "step": 242
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.1182641622277273e-05,
+      "loss": 1.8767,
+      "step": 243
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.0800731548399637e-05,
+      "loss": 1.8782,
+      "step": 244
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 2.042138937932388e-05,
+      "loss": 1.8134,
+      "step": 245
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.0044648475974094e-05,
+      "loss": 1.8738,
+      "step": 246
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.9670541970508223e-05,
+      "loss": 1.8041,
+      "step": 247
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.9299102763404336e-05,
+      "loss": 1.8396,
+      "step": 248
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.893036352056728e-05,
+      "loss": 1.9001,
+      "step": 249
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.8564356670455767e-05,
+      "loss": 1.7747,
+      "step": 250
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.8201114401230585e-05,
+      "loss": 1.9078,
+      "step": 251
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.7840668657923835e-05,
+      "loss": 1.9058,
+      "step": 252
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.748305113962948e-05,
+      "loss": 1.8619,
+      "step": 253
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.7128293296715703e-05,
+      "loss": 1.9236,
+      "step": 254
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.677642632805892e-05,
+      "loss": 1.8204,
+      "step": 255
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.6427481178300062e-05,
+      "loss": 1.8528,
+      "step": 256
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.6081488535123275e-05,
+      "loss": 1.8695,
+      "step": 257
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.5738478826556886e-05,
+      "loss": 1.8079,
+      "step": 258
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.539848221829769e-05,
+      "loss": 1.8897,
+      "step": 259
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.5061528611057918e-05,
+      "loss": 1.8215,
+      "step": 260
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.4727647637935649e-05,
+      "loss": 1.8931,
+      "step": 261
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.4396868661808777e-05,
+      "loss": 1.7798,
+      "step": 262
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.4069220772752683e-05,
+      "loss": 1.8395,
+      "step": 263
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.3744732785482034e-05,
+      "loss": 1.7538,
+      "step": 264
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.3423433236816563e-05,
+      "loss": 1.753,
+      "step": 265
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.3105350383171483e-05,
+      "loss": 1.9531,
+      "step": 266
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.2790512198072558e-05,
+      "loss": 1.8359,
+      "step": 267
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2478946369695882e-05,
+      "loss": 1.901,
+      "step": 268
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.2170680298432935e-05,
+      "loss": 1.8663,
+      "step": 269
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.1865741094480909e-05,
+      "loss": 1.8337,
+      "step": 270
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1564155575458413e-05,
+      "loss": 1.8878,
+      "step": 271
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.126595026404717e-05,
+      "loss": 1.8277,
+      "step": 272
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.0971151385659356e-05,
+      "loss": 1.8477,
+      "step": 273
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.067978486613131e-05,
+      "loss": 1.945,
+      "step": 274
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.0391876329443533e-05,
+      "loss": 1.7664,
+      "step": 275
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.010745109546713e-05,
+      "loss": 1.8162,
+      "step": 276
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.826534177737107e-06,
+      "loss": 1.8063,
+      "step": 277
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8191,
+      "step": 278
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 9.275323800304286e-06,
+      "loss": 1.8882,
+      "step": 279
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.005078816328771e-06,
+      "loss": 1.8194,
+      "step": 280
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.738439095791123e-06,
+      "loss": 1.8051,
+      "step": 281
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.475428088094517e-06,
+      "loss": 1.8454,
+      "step": 282
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.216068923518072e-06,
+      "loss": 1.9187,
+      "step": 283
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.960384411182709e-06,
+      "loss": 1.8383,
+      "step": 284
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.708397037045129e-06,
+      "loss": 1.9316,
+      "step": 285
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.460128961920432e-06,
+      "loss": 1.8221,
+      "step": 286
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.215602019533041e-06,
+      "loss": 1.8184,
+      "step": 287
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.974837714596733e-06,
+      "loss": 1.8572,
+      "step": 288
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.737857220923305e-06,
+      "loss": 1.8122,
+      "step": 289
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.50468137956049e-06,
+      "loss": 1.8512,
+      "step": 290
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 6.275330696959108e-06,
+      "loss": 1.8534,
+      "step": 291
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 6.049825343169652e-06,
+      "loss": 1.7876,
+      "step": 292
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.828185150068472e-06,
+      "loss": 1.9367,
+      "step": 293
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.610429609613616e-06,
+      "loss": 1.8474,
+      "step": 294
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 5.3965778721306755e-06,
+      "loss": 1.8483,
+      "step": 295
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.186648744628636e-06,
+      "loss": 1.9065,
+      "step": 296
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.980660689145855e-06,
+      "loss": 1.8586,
+      "step": 297
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.778631821126473e-06,
+      "loss": 1.8758,
+      "step": 298
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.580579907827287e-06,
+      "loss": 1.8067,
+      "step": 299
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.386522366755169e-06,
+      "loss": 1.8208,
+      "step": 300
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.1964762641353294e-06,
+      "loss": 1.7676,
+      "step": 301
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.010458313410459e-06,
+      "loss": 1.799,
+      "step": 302
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.8284848737708325e-06,
+      "loss": 1.7849,
+      "step": 303
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.6505719487156697e-06,
+      "loss": 1.7941,
+      "step": 304
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.476735184645674e-06,
+      "loss": 1.8647,
+      "step": 305
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.306989869487037e-06,
+      "loss": 1.8437,
+      "step": 306
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.1413509313469812e-06,
+      "loss": 1.8539,
+      "step": 307
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.9798329372008825e-06,
+      "loss": 1.8604,
+      "step": 308
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.8224500916111952e-06,
+      "loss": 1.7929,
+      "step": 309
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.6692162354782944e-06,
+      "loss": 1.8269,
+      "step": 310
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.520144844823169e-06,
+      "loss": 1.8311,
+      "step": 311
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.3752490296023387e-06,
+      "loss": 1.8252,
+      "step": 312
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.2345415325549123e-06,
+      "loss": 1.853,
+      "step": 313
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.0980347280818935e-06,
+      "loss": 1.8513,
+      "step": 314
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.9657406211579966e-06,
+      "loss": 1.918,
+      "step": 315
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.8376708462757796e-06,
+      "loss": 1.838,
+      "step": 316
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.713836666422569e-06,
+      "loss": 1.8308,
+      "step": 317
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.594248972089879e-06,
+      "loss": 1.8581,
+      "step": 318
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.4789182803156332e-06,
+      "loss": 1.8513,
+      "step": 319
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.3678547337593494e-06,
+      "loss": 1.8293,
+      "step": 320
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.2610680998100478e-06,
+      "loss": 1.8001,
+      "step": 321
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.1585677697273312e-06,
+      "loss": 1.8864,
+      "step": 322
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.060362757815453e-06,
+      "loss": 1.8015,
+      "step": 323
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 9.664617006305664e-07,
+      "loss": 1.8198,
+      "step": 324
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.768728562211947e-07,
+      "loss": 1.876,
+      "step": 325
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 7.916041034019772e-07,
+      "loss": 1.879,
+      "step": 326
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 7.106629410607691e-07,
+      "loss": 1.7792,
+      "step": 327
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.340564874991905e-07,
+      "loss": 1.9045,
+      "step": 328
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 5.617914798065616e-07,
+      "loss": 1.7875,
+      "step": 329
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 4.938742732674529e-07,
+      "loss": 1.7886,
+      "step": 330
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.303108408027667e-07,
+      "loss": 1.8113,
+      "step": 331
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.7110677244445167e-07,
+      "loss": 1.8897,
+      "step": 332
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 3.162672748438844e-07,
+      "loss": 1.8716,
+      "step": 333
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.657971708139917e-07,
+      "loss": 1.8585,
+      "step": 334
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.1970089890509527e-07,
+      "loss": 1.774,
+      "step": 335
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.7798251301458513e-07,
+      "loss": 1.9125,
+      "step": 336
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.4064568203037697e-07,
+      "loss": 1.8269,
+      "step": 337
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.076936895082925e-07,
+      "loss": 1.815,
+      "step": 338
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.912943338324596e-08,
+      "loss": 1.8106,
+      "step": 339
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.4955425714431353e-08,
+      "loss": 1.7958,
+      "step": 340
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.517379246436026e-08,
+      "loss": 1.8876,
+      "step": 341
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.9786273311928062e-08,
+      "loss": 1.8588,
+      "step": 342
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 8.794221499408561e-09,
+      "loss": 1.8221,
+      "step": 343
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.198603713432501e-09,
+      "loss": 1.853,
+      "step": 344
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.0,
+      "loss": 1.7843,
+      "step": 345
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 115,
+  "total_flos": 7.812884393509257e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e39737902bc1aa013dd8f6b24d000cda19aabe9b71208ae812379be1726ec8c
+size 4795

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "models/Mixtral-8x7B-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_z_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}