Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: 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)
+# qlora-out
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5840
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.767         | 0.24  | 20   | 0.6343          |
+| 0.6849        | 0.48  | 40   | 0.5669          |
+| 0.6761        | 0.72  | 60   | 0.5247          |
+| 0.5534        | 0.96  | 80   | 0.5044          |
+| 0.4757        | 1.2   | 100  | 0.5023          |
+| 0.5158        | 1.44  | 120  | 0.4883          |
+| 0.5414        | 1.68  | 140  | 0.4809          |
+| 0.4715        | 1.92  | 160  | 0.4748          |
+| 0.4037        | 2.16  | 180  | 0.4873          |
+| 0.4213        | 2.4   | 200  | 0.5194          |
+| 0.2988        | 2.64  | 220  | 0.6278          |
+| 0.3477        | 2.88  | 240  | 0.5840          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e842683bfb66221f206c6cdad2956f3bb4a757a02dd45f5f3bbfbef87746bc0
+size 671250189

checkpoint-166/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-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]
+- **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 Data 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 Data 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.dev0

checkpoint-166/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-166/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166fc8f89f9ca0b3dddf118720d2539c6372bf55d5d9bb2841316aa253632974
+size 671250189

checkpoint-166/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a575d9e6b8d05571ccf75e4a7730b9a7421fa147e98c4aa2215290dcae9b9d
+size 336724767

checkpoint-166/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6071068c8352dee689d3b7fdbd57ddb4970ea215124748737b761bf5a805e6c
+size 14575

checkpoint-166/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3beff71e0e44718131cd3e9e920e1b706ca54992b31cf4135d21c8c0ff363a95
+size 627

checkpoint-166/trainer_state.json

@@ -0,0 +1,1079 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9910044977511245,
+  "eval_steps": 20,
+  "global_step": 166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-06,
+      "loss": 2.4137,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-06,
+      "loss": 2.5757,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.2254,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4e-06,
+      "loss": 2.3859,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 2.2279,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 2.4677,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7e-06,
+      "loss": 2.3097,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8e-06,
+      "loss": 2.1753,
+      "step": 8
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.9567,
+      "step": 9
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.4897,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.1e-05,
+      "loss": 1.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.2799,
+      "step": 12
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.3e-05,
+      "loss": 0.941,
+      "step": 13
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.4e-05,
+      "loss": 0.9046,
+      "step": 14
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.8112,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.6e-05,
+      "loss": 0.8297,
+      "step": 16
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.6999999999999996e-05,
+      "loss": 0.7657,
+      "step": 17
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 0.8527,
+      "step": 18
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9e-05,
+      "loss": 0.8213,
+      "step": 19
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.767,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.6342860460281372,
+      "eval_runtime": 35.077,
+      "eval_samples_per_second": 46.441,
+      "eval_steps_per_second": 11.632,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.1e-05,
+      "loss": 0.8794,
+      "step": 21
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.2e-05,
+      "loss": 0.7471,
+      "step": 22
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.2999999999999997e-05,
+      "loss": 0.8795,
+      "step": 23
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 0.7741,
+      "step": 24
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.774,
+      "step": 25
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.6e-05,
+      "loss": 0.7771,
+      "step": 26
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 0.8314,
+      "step": 27
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.8e-05,
+      "loss": 0.6423,
+      "step": 28
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.8999999999999997e-05,
+      "loss": 0.8044,
+      "step": 29
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.6982,
+      "step": 30
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.0999999999999995e-05,
+      "loss": 0.7646,
+      "step": 31
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.2e-05,
+      "loss": 0.7309,
+      "step": 32
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 0.7731,
+      "step": 33
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.399999999999999e-05,
+      "loss": 0.7677,
+      "step": 34
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6812,
+      "step": 35
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 0.7012,
+      "step": 36
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.7e-05,
+      "loss": 0.743,
+      "step": 37
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7018,
+      "step": 38
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9e-05,
+      "loss": 0.6283,
+      "step": 39
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.9999999999999996e-05,
+      "loss": 0.6849,
+      "step": 40
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5668678283691406,
+      "eval_runtime": 35.2083,
+      "eval_samples_per_second": 46.268,
+      "eval_steps_per_second": 11.588,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.0999999999999994e-05,
+      "loss": 0.674,
+      "step": 41
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6649,
+      "step": 42
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6876,
+      "step": 43
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.4e-05,
+      "loss": 0.6865,
+      "step": 44
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 0.7319,
+      "step": 45
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.599999999999999e-05,
+      "loss": 0.6688,
+      "step": 46
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.7e-05,
+      "loss": 0.737,
+      "step": 47
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 0.6599,
+      "step": 48
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.899999999999999e-05,
+      "loss": 0.6748,
+      "step": 49
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.7997,
+      "step": 50
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.1e-05,
+      "loss": 0.6429,
+      "step": 51
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.2e-05,
+      "loss": 0.6107,
+      "step": 52
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.2999999999999994e-05,
+      "loss": 0.7678,
+      "step": 53
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 0.686,
+      "step": 54
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.499999999999999e-05,
+      "loss": 0.6825,
+      "step": 55
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.6e-05,
+      "loss": 0.5791,
+      "step": 56
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 0.7382,
+      "step": 57
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.7999999999999994e-05,
+      "loss": 0.6888,
+      "step": 58
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.899999999999999e-05,
+      "loss": 0.6067,
+      "step": 59
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6761,
+      "step": 60
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.5247214436531067,
+      "eval_runtime": 35.3754,
+      "eval_samples_per_second": 46.049,
+      "eval_steps_per_second": 11.533,
+      "step": 60
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 6.1e-05,
+      "loss": 0.6388,
+      "step": 61
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.199999999999999e-05,
+      "loss": 0.5719,
+      "step": 62
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 0.6878,
+      "step": 63
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.4e-05,
+      "loss": 0.6075,
+      "step": 64
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.5e-05,
+      "loss": 0.583,
+      "step": 65
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 0.6215,
+      "step": 66
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.699999999999999e-05,
+      "loss": 0.6645,
+      "step": 67
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.799999999999999e-05,
+      "loss": 0.6785,
+      "step": 68
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.9e-05,
+      "loss": 0.5568,
+      "step": 69
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7e-05,
+      "loss": 0.5797,
+      "step": 70
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.099999999999999e-05,
+      "loss": 0.6467,
+      "step": 71
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 0.5555,
+      "step": 72
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.3e-05,
+      "loss": 0.6119,
+      "step": 73
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.4e-05,
+      "loss": 0.6903,
+      "step": 74
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.5e-05,
+      "loss": 0.6461,
+      "step": 75
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5789,
+      "step": 76
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.699999999999999e-05,
+      "loss": 0.5349,
+      "step": 77
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.8e-05,
+      "loss": 0.5261,
+      "step": 78
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.899999999999998e-05,
+      "loss": 0.6659,
+      "step": 79
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.999999999999999e-05,
+      "loss": 0.5534,
+      "step": 80
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5044009685516357,
+      "eval_runtime": 35.1756,
+      "eval_samples_per_second": 46.31,
+      "eval_steps_per_second": 11.599,
+      "step": 80
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.1e-05,
+      "loss": 0.5247,
+      "step": 81
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.199999999999999e-05,
+      "loss": 0.6016,
+      "step": 82
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.3e-05,
+      "loss": 0.642,
+      "step": 83
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 8.4e-05,
+      "loss": 0.6376,
+      "step": 84
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.499999999999999e-05,
+      "loss": 0.6491,
+      "step": 85
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 8.6e-05,
+      "loss": 0.5976,
+      "step": 86
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 0.6259,
+      "step": 87
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.8e-05,
+      "loss": 0.515,
+      "step": 88
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.9e-05,
+      "loss": 0.5182,
+      "step": 89
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.4986,
+      "step": 90
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.099999999999999e-05,
+      "loss": 0.5622,
+      "step": 91
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.199999999999999e-05,
+      "loss": 0.6323,
+      "step": 92
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.3e-05,
+      "loss": 0.5946,
+      "step": 93
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 9.4e-05,
+      "loss": 0.5888,
+      "step": 94
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 9.499999999999999e-05,
+      "loss": 0.526,
+      "step": 95
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 0.5157,
+      "step": 96
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 9.699999999999999e-05,
+      "loss": 0.4719,
+      "step": 97
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 9.799999999999998e-05,
+      "loss": 0.5578,
+      "step": 98
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 9.9e-05,
+      "loss": 0.5357,
+      "step": 99
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 0.4757,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5023330450057983,
+      "eval_runtime": 35.2525,
+      "eval_samples_per_second": 46.21,
+      "eval_steps_per_second": 11.574,
+      "step": 100
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00010099999999999999,
+      "loss": 0.5517,
+      "step": 101
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.000102,
+      "loss": 0.4868,
+      "step": 102
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00010299999999999998,
+      "loss": 0.5257,
+      "step": 103
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000104,
+      "loss": 0.5651,
+      "step": 104
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 0.5424,
+      "step": 105
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00010599999999999999,
+      "loss": 0.5472,
+      "step": 106
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000107,
+      "loss": 0.5045,
+      "step": 107
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 0.5533,
+      "step": 108
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00010899999999999999,
+      "loss": 0.479,
+      "step": 109
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00010999999999999998,
+      "loss": 0.5794,
+      "step": 110
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 0.487,
+      "step": 111
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.000112,
+      "loss": 0.6611,
+      "step": 112
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00011299999999999998,
+      "loss": 0.4638,
+      "step": 113
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.5047,
+      "step": 114
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.000115,
+      "loss": 0.4416,
+      "step": 115
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00011599999999999999,
+      "loss": 0.4736,
+      "step": 116
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.000117,
+      "loss": 0.545,
+      "step": 117
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011799999999999998,
+      "loss": 0.502,
+      "step": 118
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011899999999999999,
+      "loss": 0.5108,
+      "step": 119
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.5158,
+      "step": 120
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.4883132874965668,
+      "eval_runtime": 35.2497,
+      "eval_samples_per_second": 46.213,
+      "eval_steps_per_second": 11.575,
+      "step": 120
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012099999999999999,
+      "loss": 0.5845,
+      "step": 121
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.000122,
+      "loss": 0.52,
+      "step": 122
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 0.4885,
+      "step": 123
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012399999999999998,
+      "loss": 0.4641,
+      "step": 124
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.000125,
+      "loss": 0.5046,
+      "step": 125
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 0.5195,
+      "step": 126
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.000127,
+      "loss": 0.512,
+      "step": 127
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.000128,
+      "loss": 0.4458,
+      "step": 128
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.000129,
+      "loss": 0.5912,
+      "step": 129
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00013,
+      "loss": 0.4515,
+      "step": 130
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00013099999999999999,
+      "loss": 0.5619,
+      "step": 131
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 0.7071,
+      "step": 132
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.000133,
+      "loss": 0.5515,
+      "step": 133
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00013399999999999998,
+      "loss": 0.4863,
+      "step": 134
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.000135,
+      "loss": 0.5102,
+      "step": 135
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00013599999999999997,
+      "loss": 0.4338,
+      "step": 136
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.000137,
+      "loss": 0.5132,
+      "step": 137
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.000138,
+      "loss": 0.5793,
+      "step": 138
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.000139,
+      "loss": 0.4992,
+      "step": 139
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00014,
+      "loss": 0.5414,
+      "step": 140
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.48085713386535645,
+      "eval_runtime": 35.2966,
+      "eval_samples_per_second": 46.152,
+      "eval_steps_per_second": 11.559,
+      "step": 140
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 0.5303,
+      "step": 141
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00014199999999999998,
+      "loss": 0.4456,
+      "step": 142
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00014299999999999998,
+      "loss": 0.5117,
+      "step": 143
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 0.6139,
+      "step": 144
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.000145,
+      "loss": 0.4346,
+      "step": 145
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.000146,
+      "loss": 0.5148,
+      "step": 146
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.000147,
+      "loss": 0.4928,
+      "step": 147
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.000148,
+      "loss": 0.6429,
+      "step": 148
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.000149,
+      "loss": 0.4687,
+      "step": 149
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015,
+      "loss": 0.6071,
+      "step": 150
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015099999999999998,
+      "loss": 0.5215,
+      "step": 151
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.000152,
+      "loss": 0.5806,
+      "step": 152
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.5801,
+      "step": 153
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00015399999999999998,
+      "loss": 0.5104,
+      "step": 154
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.000155,
+      "loss": 0.5002,
+      "step": 155
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.000156,
+      "loss": 0.508,
+      "step": 156
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.000157,
+      "loss": 0.5223,
+      "step": 157
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00015799999999999996,
+      "loss": 0.6085,
+      "step": 158
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.000159,
+      "loss": 0.5328,
+      "step": 159
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00015999999999999999,
+      "loss": 0.4715,
+      "step": 160
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.47481799125671387,
+      "eval_runtime": 35.1736,
+      "eval_samples_per_second": 46.313,
+      "eval_steps_per_second": 11.6,
+      "step": 160
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00016099999999999998,
+      "loss": 0.4352,
+      "step": 161
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.000162,
+      "loss": 0.5532,
+      "step": 162
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00016299999999999998,
+      "loss": 0.4916,
+      "step": 163
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00016399999999999997,
+      "loss": 0.4879,
+      "step": 164
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.000165,
+      "loss": 0.5124,
+      "step": 165
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.000166,
+      "loss": 0.5515,
+      "step": 166
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 249,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.9089513439895224e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-166/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3830cab5058e45763dede36e071a76743149bc2f5b60978574c35a5bc13fec
+size 4475

checkpoint-249/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-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]
+- **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 Data 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 Data 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.dev0

checkpoint-249/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-249/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e842683bfb66221f206c6cdad2956f3bb4a757a02dd45f5f3bbfbef87746bc0
+size 671250189

checkpoint-249/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8982ad64c81a0df8795522afcb555f89d6198fba82986cfb15fef3f1b8a89f
+size 336724767

checkpoint-249/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78a6a48a2f624c740dd3a8978a9ce724f04e57dd54a98aa7e753be0aed1e62f
+size 14575

checkpoint-249/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea3ac0912b94b9d0e20278fdb566e2c63f1b1e767a3a1f745ab597bb46814bf
+size 627

checkpoint-249/trainer_state.json

@@ -0,0 +1,1609 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9865067466266866,
+  "eval_steps": 20,
+  "global_step": 249,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-06,
+      "loss": 2.4137,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-06,
+      "loss": 2.5757,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.2254,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4e-06,
+      "loss": 2.3859,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 2.2279,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 2.4677,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7e-06,
+      "loss": 2.3097,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8e-06,
+      "loss": 2.1753,
+      "step": 8
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.9567,
+      "step": 9
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.4897,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.1e-05,
+      "loss": 1.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.2799,
+      "step": 12
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.3e-05,
+      "loss": 0.941,
+      "step": 13
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.4e-05,
+      "loss": 0.9046,
+      "step": 14
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.8112,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.6e-05,
+      "loss": 0.8297,
+      "step": 16
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.6999999999999996e-05,
+      "loss": 0.7657,
+      "step": 17
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 0.8527,
+      "step": 18
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9e-05,
+      "loss": 0.8213,
+      "step": 19
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.767,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.6342860460281372,
+      "eval_runtime": 35.077,
+      "eval_samples_per_second": 46.441,
+      "eval_steps_per_second": 11.632,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.1e-05,
+      "loss": 0.8794,
+      "step": 21
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.2e-05,
+      "loss": 0.7471,
+      "step": 22
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.2999999999999997e-05,
+      "loss": 0.8795,
+      "step": 23
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 0.7741,
+      "step": 24
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.774,
+      "step": 25
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.6e-05,
+      "loss": 0.7771,
+      "step": 26
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 0.8314,
+      "step": 27
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.8e-05,
+      "loss": 0.6423,
+      "step": 28
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.8999999999999997e-05,
+      "loss": 0.8044,
+      "step": 29
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.6982,
+      "step": 30
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.0999999999999995e-05,
+      "loss": 0.7646,
+      "step": 31
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.2e-05,
+      "loss": 0.7309,
+      "step": 32
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 0.7731,
+      "step": 33
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.399999999999999e-05,
+      "loss": 0.7677,
+      "step": 34
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6812,
+      "step": 35
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 0.7012,
+      "step": 36
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.7e-05,
+      "loss": 0.743,
+      "step": 37
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7018,
+      "step": 38
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9e-05,
+      "loss": 0.6283,
+      "step": 39
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.9999999999999996e-05,
+      "loss": 0.6849,
+      "step": 40
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5668678283691406,
+      "eval_runtime": 35.2083,
+      "eval_samples_per_second": 46.268,
+      "eval_steps_per_second": 11.588,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.0999999999999994e-05,
+      "loss": 0.674,
+      "step": 41
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6649,
+      "step": 42
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6876,
+      "step": 43
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.4e-05,
+      "loss": 0.6865,
+      "step": 44
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 0.7319,
+      "step": 45
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.599999999999999e-05,
+      "loss": 0.6688,
+      "step": 46
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.7e-05,
+      "loss": 0.737,
+      "step": 47
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 0.6599,
+      "step": 48
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.899999999999999e-05,
+      "loss": 0.6748,
+      "step": 49
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.7997,
+      "step": 50
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.1e-05,
+      "loss": 0.6429,
+      "step": 51
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.2e-05,
+      "loss": 0.6107,
+      "step": 52
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.2999999999999994e-05,
+      "loss": 0.7678,
+      "step": 53
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 0.686,
+      "step": 54
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.499999999999999e-05,
+      "loss": 0.6825,
+      "step": 55
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.6e-05,
+      "loss": 0.5791,
+      "step": 56
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 0.7382,
+      "step": 57
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.7999999999999994e-05,
+      "loss": 0.6888,
+      "step": 58
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.899999999999999e-05,
+      "loss": 0.6067,
+      "step": 59
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6761,
+      "step": 60
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.5247214436531067,
+      "eval_runtime": 35.3754,
+      "eval_samples_per_second": 46.049,
+      "eval_steps_per_second": 11.533,
+      "step": 60
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 6.1e-05,
+      "loss": 0.6388,
+      "step": 61
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.199999999999999e-05,
+      "loss": 0.5719,
+      "step": 62
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 0.6878,
+      "step": 63
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.4e-05,
+      "loss": 0.6075,
+      "step": 64
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.5e-05,
+      "loss": 0.583,
+      "step": 65
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 0.6215,
+      "step": 66
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.699999999999999e-05,
+      "loss": 0.6645,
+      "step": 67
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.799999999999999e-05,
+      "loss": 0.6785,
+      "step": 68
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.9e-05,
+      "loss": 0.5568,
+      "step": 69
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7e-05,
+      "loss": 0.5797,
+      "step": 70
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.099999999999999e-05,
+      "loss": 0.6467,
+      "step": 71
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 0.5555,
+      "step": 72
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.3e-05,
+      "loss": 0.6119,
+      "step": 73
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.4e-05,
+      "loss": 0.6903,
+      "step": 74
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.5e-05,
+      "loss": 0.6461,
+      "step": 75
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5789,
+      "step": 76
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.699999999999999e-05,
+      "loss": 0.5349,
+      "step": 77
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.8e-05,
+      "loss": 0.5261,
+      "step": 78
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.899999999999998e-05,
+      "loss": 0.6659,
+      "step": 79
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.999999999999999e-05,
+      "loss": 0.5534,
+      "step": 80
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5044009685516357,
+      "eval_runtime": 35.1756,
+      "eval_samples_per_second": 46.31,
+      "eval_steps_per_second": 11.599,
+      "step": 80
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.1e-05,
+      "loss": 0.5247,
+      "step": 81
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.199999999999999e-05,
+      "loss": 0.6016,
+      "step": 82
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.3e-05,
+      "loss": 0.642,
+      "step": 83
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 8.4e-05,
+      "loss": 0.6376,
+      "step": 84
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.499999999999999e-05,
+      "loss": 0.6491,
+      "step": 85
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 8.6e-05,
+      "loss": 0.5976,
+      "step": 86
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 0.6259,
+      "step": 87
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.8e-05,
+      "loss": 0.515,
+      "step": 88
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.9e-05,
+      "loss": 0.5182,
+      "step": 89
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.4986,
+      "step": 90
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.099999999999999e-05,
+      "loss": 0.5622,
+      "step": 91
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.199999999999999e-05,
+      "loss": 0.6323,
+      "step": 92
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.3e-05,
+      "loss": 0.5946,
+      "step": 93
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 9.4e-05,
+      "loss": 0.5888,
+      "step": 94
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 9.499999999999999e-05,
+      "loss": 0.526,
+      "step": 95
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 0.5157,
+      "step": 96
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 9.699999999999999e-05,
+      "loss": 0.4719,
+      "step": 97
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 9.799999999999998e-05,
+      "loss": 0.5578,
+      "step": 98
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 9.9e-05,
+      "loss": 0.5357,
+      "step": 99
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 0.4757,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5023330450057983,
+      "eval_runtime": 35.2525,
+      "eval_samples_per_second": 46.21,
+      "eval_steps_per_second": 11.574,
+      "step": 100
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00010099999999999999,
+      "loss": 0.5517,
+      "step": 101
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.000102,
+      "loss": 0.4868,
+      "step": 102
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00010299999999999998,
+      "loss": 0.5257,
+      "step": 103
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000104,
+      "loss": 0.5651,
+      "step": 104
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 0.5424,
+      "step": 105
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00010599999999999999,
+      "loss": 0.5472,
+      "step": 106
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000107,
+      "loss": 0.5045,
+      "step": 107
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 0.5533,
+      "step": 108
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00010899999999999999,
+      "loss": 0.479,
+      "step": 109
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00010999999999999998,
+      "loss": 0.5794,
+      "step": 110
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 0.487,
+      "step": 111
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.000112,
+      "loss": 0.6611,
+      "step": 112
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00011299999999999998,
+      "loss": 0.4638,
+      "step": 113
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.5047,
+      "step": 114
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.000115,
+      "loss": 0.4416,
+      "step": 115
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00011599999999999999,
+      "loss": 0.4736,
+      "step": 116
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.000117,
+      "loss": 0.545,
+      "step": 117
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011799999999999998,
+      "loss": 0.502,
+      "step": 118
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011899999999999999,
+      "loss": 0.5108,
+      "step": 119
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.5158,
+      "step": 120
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.4883132874965668,
+      "eval_runtime": 35.2497,
+      "eval_samples_per_second": 46.213,
+      "eval_steps_per_second": 11.575,
+      "step": 120
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012099999999999999,
+      "loss": 0.5845,
+      "step": 121
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.000122,
+      "loss": 0.52,
+      "step": 122
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 0.4885,
+      "step": 123
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012399999999999998,
+      "loss": 0.4641,
+      "step": 124
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.000125,
+      "loss": 0.5046,
+      "step": 125
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 0.5195,
+      "step": 126
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.000127,
+      "loss": 0.512,
+      "step": 127
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.000128,
+      "loss": 0.4458,
+      "step": 128
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.000129,
+      "loss": 0.5912,
+      "step": 129
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00013,
+      "loss": 0.4515,
+      "step": 130
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00013099999999999999,
+      "loss": 0.5619,
+      "step": 131
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 0.7071,
+      "step": 132
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.000133,
+      "loss": 0.5515,
+      "step": 133
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00013399999999999998,
+      "loss": 0.4863,
+      "step": 134
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.000135,
+      "loss": 0.5102,
+      "step": 135
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00013599999999999997,
+      "loss": 0.4338,
+      "step": 136
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.000137,
+      "loss": 0.5132,
+      "step": 137
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.000138,
+      "loss": 0.5793,
+      "step": 138
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.000139,
+      "loss": 0.4992,
+      "step": 139
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00014,
+      "loss": 0.5414,
+      "step": 140
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.48085713386535645,
+      "eval_runtime": 35.2966,
+      "eval_samples_per_second": 46.152,
+      "eval_steps_per_second": 11.559,
+      "step": 140
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 0.5303,
+      "step": 141
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00014199999999999998,
+      "loss": 0.4456,
+      "step": 142
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00014299999999999998,
+      "loss": 0.5117,
+      "step": 143
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 0.6139,
+      "step": 144
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.000145,
+      "loss": 0.4346,
+      "step": 145
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.000146,
+      "loss": 0.5148,
+      "step": 146
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.000147,
+      "loss": 0.4928,
+      "step": 147
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.000148,
+      "loss": 0.6429,
+      "step": 148
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.000149,
+      "loss": 0.4687,
+      "step": 149
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00015,
+      "loss": 0.6071,
+      "step": 150
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00015099999999999998,
+      "loss": 0.5215,
+      "step": 151
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.000152,
+      "loss": 0.5806,
+      "step": 152
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.5801,
+      "step": 153
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00015399999999999998,
+      "loss": 0.5104,
+      "step": 154
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.000155,
+      "loss": 0.5002,
+      "step": 155
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.000156,
+      "loss": 0.508,
+      "step": 156
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.000157,
+      "loss": 0.5223,
+      "step": 157
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00015799999999999996,
+      "loss": 0.6085,
+      "step": 158
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.000159,
+      "loss": 0.5328,
+      "step": 159
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00015999999999999999,
+      "loss": 0.4715,
+      "step": 160
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.47481799125671387,
+      "eval_runtime": 35.1736,
+      "eval_samples_per_second": 46.313,
+      "eval_steps_per_second": 11.6,
+      "step": 160
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00016099999999999998,
+      "loss": 0.4352,
+      "step": 161
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.000162,
+      "loss": 0.5532,
+      "step": 162
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00016299999999999998,
+      "loss": 0.4916,
+      "step": 163
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00016399999999999997,
+      "loss": 0.4879,
+      "step": 164
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.000165,
+      "loss": 0.5124,
+      "step": 165
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.000166,
+      "loss": 0.5515,
+      "step": 166
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00016699999999999997,
+      "loss": 0.5126,
+      "step": 167
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.000168,
+      "loss": 0.5941,
+      "step": 168
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.000169,
+      "loss": 0.4991,
+      "step": 169
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.00016999999999999999,
+      "loss": 0.5356,
+      "step": 170
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 0.4748,
+      "step": 171
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.000172,
+      "loss": 0.4136,
+      "step": 172
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00017299999999999998,
+      "loss": 0.3894,
+      "step": 173
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.3978,
+      "step": 174
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.000175,
+      "loss": 0.4861,
+      "step": 175
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.000176,
+      "loss": 0.5061,
+      "step": 176
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 0.4545,
+      "step": 177
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.000178,
+      "loss": 0.4327,
+      "step": 178
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.000179,
+      "loss": 0.3695,
+      "step": 179
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.4037,
+      "step": 180
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 0.48729604482650757,
+      "eval_runtime": 35.2277,
+      "eval_samples_per_second": 46.242,
+      "eval_steps_per_second": 11.582,
+      "step": 180
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.000181,
+      "loss": 0.3969,
+      "step": 181
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00018199999999999998,
+      "loss": 0.4611,
+      "step": 182
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.3434,
+      "step": 183
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.00018399999999999997,
+      "loss": 0.4017,
+      "step": 184
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.000185,
+      "loss": 0.3848,
+      "step": 185
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.000186,
+      "loss": 0.3548,
+      "step": 186
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00018699999999999996,
+      "loss": 0.446,
+      "step": 187
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.000188,
+      "loss": 0.3788,
+      "step": 188
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 0.4564,
+      "step": 189
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00018999999999999998,
+      "loss": 0.3292,
+      "step": 190
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.000191,
+      "loss": 0.4338,
+      "step": 191
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00019199999999999998,
+      "loss": 0.4,
+      "step": 192
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00019299999999999997,
+      "loss": 0.3872,
+      "step": 193
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.00019399999999999997,
+      "loss": 0.4046,
+      "step": 194
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.000195,
+      "loss": 0.4431,
+      "step": 195
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.00019599999999999997,
+      "loss": 0.4568,
+      "step": 196
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00019699999999999996,
+      "loss": 0.324,
+      "step": 197
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.000198,
+      "loss": 0.3629,
+      "step": 198
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.00019899999999999999,
+      "loss": 0.3195,
+      "step": 199
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 0.4213,
+      "step": 200
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.5193601846694946,
+      "eval_runtime": 35.074,
+      "eval_samples_per_second": 46.445,
+      "eval_steps_per_second": 11.633,
+      "step": 200
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.000201,
+      "loss": 0.3644,
+      "step": 201
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.00020199999999999998,
+      "loss": 0.3512,
+      "step": 202
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.00020299999999999997,
+      "loss": 0.3081,
+      "step": 203
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.000204,
+      "loss": 0.4205,
+      "step": 204
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.000205,
+      "loss": 0.4365,
+      "step": 205
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00020599999999999997,
+      "loss": 0.3399,
+      "step": 206
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.3069,
+      "step": 207
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 0.000208,
+      "loss": 0.3603,
+      "step": 208
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.00020899999999999998,
+      "loss": 0.3856,
+      "step": 209
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.3315,
+      "step": 210
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.00021099999999999998,
+      "loss": 0.3774,
+      "step": 211
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.00021199999999999998,
+      "loss": 0.3271,
+      "step": 212
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00021299999999999997,
+      "loss": 0.3988,
+      "step": 213
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.000214,
+      "loss": 0.3555,
+      "step": 214
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.000215,
+      "loss": 0.4195,
+      "step": 215
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.00021599999999999996,
+      "loss": 0.5629,
+      "step": 216
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.000217,
+      "loss": 0.3774,
+      "step": 217
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.00021799999999999999,
+      "loss": 0.3255,
+      "step": 218
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00021899999999999998,
+      "loss": 0.2932,
+      "step": 219
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.00021999999999999995,
+      "loss": 0.2988,
+      "step": 220
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.6278083920478821,
+      "eval_runtime": 35.4299,
+      "eval_samples_per_second": 45.978,
+      "eval_steps_per_second": 11.516,
+      "step": 220
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00022099999999999998,
+      "loss": 0.4582,
+      "step": 221
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.00022199999999999998,
+      "loss": 0.361,
+      "step": 222
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.00022299999999999997,
+      "loss": 0.3557,
+      "step": 223
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.000224,
+      "loss": 0.432,
+      "step": 224
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.000225,
+      "loss": 0.2846,
+      "step": 225
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.00022599999999999996,
+      "loss": 0.3854,
+      "step": 226
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.000227,
+      "loss": 0.3946,
+      "step": 227
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.3812,
+      "step": 228
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00022899999999999998,
+      "loss": 0.348,
+      "step": 229
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00023,
+      "loss": 0.3094,
+      "step": 230
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.00023099999999999998,
+      "loss": 0.4102,
+      "step": 231
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.00023199999999999997,
+      "loss": 0.4329,
+      "step": 232
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.00023299999999999997,
+      "loss": 0.394,
+      "step": 233
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.000234,
+      "loss": 0.378,
+      "step": 234
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.00023499999999999997,
+      "loss": 0.3824,
+      "step": 235
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00023599999999999996,
+      "loss": 0.4943,
+      "step": 236
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.000237,
+      "loss": 0.3159,
+      "step": 237
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.00023799999999999998,
+      "loss": 0.4219,
+      "step": 238
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.00023899999999999998,
+      "loss": 0.2945,
+      "step": 239
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.3477,
+      "step": 240
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 0.5839571952819824,
+      "eval_runtime": 35.1498,
+      "eval_samples_per_second": 46.344,
+      "eval_steps_per_second": 11.607,
+      "step": 240
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00024099999999999998,
+      "loss": 0.4324,
+      "step": 241
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00024199999999999997,
+      "loss": 0.3769,
+      "step": 242
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.000243,
+      "loss": 0.3396,
+      "step": 243
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.000244,
+      "loss": 0.3101,
+      "step": 244
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.000245,
+      "loss": 0.332,
+      "step": 245
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.3818,
+      "step": 246
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.000247,
+      "loss": 0.3042,
+      "step": 247
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.00024799999999999996,
+      "loss": 0.37,
+      "step": 248
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.000249,
+      "loss": 0.3134,
+      "step": 249
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 249,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.850548033903395e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-249/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3830cab5058e45763dede36e071a76743149bc2f5b60978574c35a5bc13fec
+size 4475

checkpoint-83/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-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]
+- **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 Data 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 Data 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.dev0

checkpoint-83/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-83/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87317f2c199b69b914797f2dec5046c4e8cf457dfb52d72e562a0b3fa324459
+size 671250189

checkpoint-83/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254249817c2f47ac00e60954cb7806bb0bfc9b99fac554194b9f60ceea3333f3
+size 336724767

checkpoint-83/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd1fdc559fb988701ded7585ffdaae2aced0b8aa9000a73f3da65fabea29f82
+size 14575

checkpoint-83/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041034fe4504aeeddd3d4ceabab995d7cb94c8766e74825ab0b900bb4e5b23a2
+size 627

checkpoint-83/trainer_state.json

@@ -0,0 +1,549 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9955022488755623,
+  "eval_steps": 20,
+  "global_step": 83,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-06,
+      "loss": 2.4137,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-06,
+      "loss": 2.5757,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.2254,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4e-06,
+      "loss": 2.3859,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 2.2279,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 2.4677,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7e-06,
+      "loss": 2.3097,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8e-06,
+      "loss": 2.1753,
+      "step": 8
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.9567,
+      "step": 9
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.4897,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.1e-05,
+      "loss": 1.3339,
+      "step": 11
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.2799,
+      "step": 12
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.3e-05,
+      "loss": 0.941,
+      "step": 13
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.4e-05,
+      "loss": 0.9046,
+      "step": 14
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.8112,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.6e-05,
+      "loss": 0.8297,
+      "step": 16
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.6999999999999996e-05,
+      "loss": 0.7657,
+      "step": 17
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 0.8527,
+      "step": 18
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9e-05,
+      "loss": 0.8213,
+      "step": 19
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.767,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.6342860460281372,
+      "eval_runtime": 35.077,
+      "eval_samples_per_second": 46.441,
+      "eval_steps_per_second": 11.632,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.1e-05,
+      "loss": 0.8794,
+      "step": 21
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.2e-05,
+      "loss": 0.7471,
+      "step": 22
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.2999999999999997e-05,
+      "loss": 0.8795,
+      "step": 23
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 0.7741,
+      "step": 24
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.774,
+      "step": 25
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.6e-05,
+      "loss": 0.7771,
+      "step": 26
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 0.8314,
+      "step": 27
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.8e-05,
+      "loss": 0.6423,
+      "step": 28
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.8999999999999997e-05,
+      "loss": 0.8044,
+      "step": 29
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.6982,
+      "step": 30
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.0999999999999995e-05,
+      "loss": 0.7646,
+      "step": 31
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.2e-05,
+      "loss": 0.7309,
+      "step": 32
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 0.7731,
+      "step": 33
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.399999999999999e-05,
+      "loss": 0.7677,
+      "step": 34
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6812,
+      "step": 35
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 0.7012,
+      "step": 36
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.7e-05,
+      "loss": 0.743,
+      "step": 37
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7018,
+      "step": 38
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9e-05,
+      "loss": 0.6283,
+      "step": 39
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.9999999999999996e-05,
+      "loss": 0.6849,
+      "step": 40
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5668678283691406,
+      "eval_runtime": 35.2083,
+      "eval_samples_per_second": 46.268,
+      "eval_steps_per_second": 11.588,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.0999999999999994e-05,
+      "loss": 0.674,
+      "step": 41
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6649,
+      "step": 42
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6876,
+      "step": 43
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.4e-05,
+      "loss": 0.6865,
+      "step": 44
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 0.7319,
+      "step": 45
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.599999999999999e-05,
+      "loss": 0.6688,
+      "step": 46
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.7e-05,
+      "loss": 0.737,
+      "step": 47
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 0.6599,
+      "step": 48
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.899999999999999e-05,
+      "loss": 0.6748,
+      "step": 49
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.7997,
+      "step": 50
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.1e-05,
+      "loss": 0.6429,
+      "step": 51
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.2e-05,
+      "loss": 0.6107,
+      "step": 52
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.2999999999999994e-05,
+      "loss": 0.7678,
+      "step": 53
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 0.686,
+      "step": 54
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.499999999999999e-05,
+      "loss": 0.6825,
+      "step": 55
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.6e-05,
+      "loss": 0.5791,
+      "step": 56
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 0.7382,
+      "step": 57
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.7999999999999994e-05,
+      "loss": 0.6888,
+      "step": 58
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.899999999999999e-05,
+      "loss": 0.6067,
+      "step": 59
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6761,
+      "step": 60
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.5247214436531067,
+      "eval_runtime": 35.3754,
+      "eval_samples_per_second": 46.049,
+      "eval_steps_per_second": 11.533,
+      "step": 60
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 6.1e-05,
+      "loss": 0.6388,
+      "step": 61
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.199999999999999e-05,
+      "loss": 0.5719,
+      "step": 62
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 0.6878,
+      "step": 63
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.4e-05,
+      "loss": 0.6075,
+      "step": 64
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.5e-05,
+      "loss": 0.583,
+      "step": 65
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 0.6215,
+      "step": 66
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.699999999999999e-05,
+      "loss": 0.6645,
+      "step": 67
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.799999999999999e-05,
+      "loss": 0.6785,
+      "step": 68
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.9e-05,
+      "loss": 0.5568,
+      "step": 69
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7e-05,
+      "loss": 0.5797,
+      "step": 70
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.099999999999999e-05,
+      "loss": 0.6467,
+      "step": 71
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 0.5555,
+      "step": 72
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.3e-05,
+      "loss": 0.6119,
+      "step": 73
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.4e-05,
+      "loss": 0.6903,
+      "step": 74
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.5e-05,
+      "loss": 0.6461,
+      "step": 75
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5789,
+      "step": 76
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.699999999999999e-05,
+      "loss": 0.5349,
+      "step": 77
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.8e-05,
+      "loss": 0.5261,
+      "step": 78
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.899999999999998e-05,
+      "loss": 0.6659,
+      "step": 79
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.999999999999999e-05,
+      "loss": 0.5534,
+      "step": 80
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5044009685516357,
+      "eval_runtime": 35.1756,
+      "eval_samples_per_second": 46.31,
+      "eval_steps_per_second": 11.599,
+      "step": 80
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.1e-05,
+      "loss": 0.5247,
+      "step": 81
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.199999999999999e-05,
+      "loss": 0.6016,
+      "step": 82
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.3e-05,
+      "loss": 0.642,
+      "step": 83
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 249,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.544756719947612e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-83/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3830cab5058e45763dede36e071a76743149bc2f5b60978574c35a5bc13fec
+size 4475

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "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": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "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": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}