Upload folder using huggingface_hub

README.md

@@ -0,0 +1,137 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: volume/limarp-70b-qlora
+  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)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: models/miqu-1-70b-sf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+is_llama_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: train-all-max-alpaca-llama.jsonl
+    type: completion
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./volume/limarp-70b-qlora
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 16384
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: 70b-lora
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0001
+
+train_on_inputs: true
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+eval_steps:
+eval_table_size:
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# volume/limarp-70b-qlora
+
+This model was trained from scratch on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/miqu-1-70b-sf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dceb80d1e7f9a1bc2c49a2be6073bb284b680f9a074f73f662a4ab7bd4cf367b
+size 1657155202

checkpoint-169/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: models/miqu-1-70b-sf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0

checkpoint-169/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/miqu-1-70b-sf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-169/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4033f04ee0a34017f8b1dba72e38a3e644e22c3764beb368ea077f8b1626673
+size 1656902648

checkpoint-169/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d72b0e0941488683421f5371635c5ffcb035ce6099e55cf1d9fcdd290725817
+size 831305300

checkpoint-169/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f92a69bdd4b0dbba88379df9544068d377fbbf9b2f7bd75ec7953d5cc0f4377
+size 14244

checkpoint-169/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ba009646cdc3da3968e4818e396351d8fd70d5c95ae79461d7c8052763d65d
+size 1064

checkpoint-169/trainer_state.json

@@ -0,0 +1,1035 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.027355623100304,
+  "eval_steps": 500,
+  "global_step": 169,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 1.897,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 1.9202,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3e-05,
+      "loss": 1.9071,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 1.9712,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 2.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6e-05,
+      "loss": 1.8839,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7e-05,
+      "loss": 1.9586,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8e-05,
+      "loss": 1.9625,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9e-05,
+      "loss": 1.9269,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001,
+      "loss": 1.9005,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.999756004407229e-05,
+      "loss": 1.857,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.999024041442456e-05,
+      "loss": 1.9072,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.997804182543973e-05,
+      "loss": 1.7945,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.99609654676786e-05,
+      "loss": 1.8496,
+      "step": 14
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.993901300776359e-05,
+      "loss": 1.8275,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.991218658821608e-05,
+      "loss": 1.8701,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.988048882724732e-05,
+      "loss": 1.8594,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.984392281850293e-05,
+      "loss": 1.8669,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.980249213076084e-05,
+      "loss": 1.8022,
+      "step": 19
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.97562008075832e-05,
+      "loss": 1.8139,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.970505336692153e-05,
+      "loss": 1.8775,
+      "step": 21
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.964905480067586e-05,
+      "loss": 1.7862,
+      "step": 22
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.958821057420754e-05,
+      "loss": 1.8414,
+      "step": 23
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.952252662580579e-05,
+      "loss": 1.7446,
+      "step": 24
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.94520093661082e-05,
+      "loss": 1.8705,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.937666567747501e-05,
+      "loss": 1.822,
+      "step": 26
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.92965029133174e-05,
+      "loss": 1.9357,
+      "step": 27
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.921152889737984e-05,
+      "loss": 1.7958,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.912175192297648e-05,
+      "loss": 1.7557,
+      "step": 29
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.902718075218176e-05,
+      "loss": 1.8138,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.89278246149752e-05,
+      "loss": 1.7865,
+      "step": 31
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.882369320834069e-05,
+      "loss": 1.7997,
+      "step": 32
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.87147966953199e-05,
+      "loss": 1.7534,
+      "step": 33
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.860114570402054e-05,
+      "loss": 1.7092,
+      "step": 34
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.848275132657903e-05,
+      "loss": 1.7261,
+      "step": 35
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.835962511807786e-05,
+      "loss": 1.7827,
+      "step": 36
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.823177909541794e-05,
+      "loss": 1.7948,
+      "step": 37
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.809922573614569e-05,
+      "loss": 1.8275,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.796197797723532e-05,
+      "loss": 1.7533,
+      "step": 39
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.782004921382612e-05,
+      "loss": 1.7555,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.767345329791522e-05,
+      "loss": 1.8018,
+      "step": 41
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.752220453700556e-05,
+      "loss": 1.8107,
+      "step": 42
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.736631769270957e-05,
+      "loss": 1.7941,
+      "step": 43
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.720580797930845e-05,
+      "loss": 1.8829,
+      "step": 44
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.704069106226727e-05,
+      "loss": 1.8041,
+      "step": 45
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.687098305670605e-05,
+      "loss": 1.77,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.669670052582695e-05,
+      "loss": 1.7547,
+      "step": 47
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.651786047929773e-05,
+      "loss": 1.7594,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.633448037159167e-05,
+      "loss": 1.7076,
+      "step": 49
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.614657810028402e-05,
+      "loss": 1.786,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.595417200430516e-05,
+      "loss": 1.7076,
+      "step": 51
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.575728086215092e-05,
+      "loss": 1.7508,
+      "step": 52
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.555592389004966e-05,
+      "loss": 1.7979,
+      "step": 53
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.535012074008687e-05,
+      "loss": 1.7075,
+      "step": 54
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.513989149828718e-05,
+      "loss": 1.7828,
+      "step": 55
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.492525668265399e-05,
+      "loss": 1.8179,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.470623724116692e-05,
+      "loss": 1.7802,
+      "step": 57
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.448285454973738e-05,
+      "loss": 1.7873,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.425513041012219e-05,
+      "loss": 1.7315,
+      "step": 59
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.402308704779599e-05,
+      "loss": 1.7953,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.378674710978185e-05,
+      "loss": 1.7946,
+      "step": 61
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.354613366244108e-05,
+      "loss": 1.7543,
+      "step": 62
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.7302,
+      "step": 63
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.305218058836778e-05,
+      "loss": 1.8224,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.279888917058452e-05,
+      "loss": 1.757,
+      "step": 65
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.254142065666801e-05,
+      "loss": 1.7506,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.22798001750913e-05,
+      "loss": 1.7523,
+      "step": 67
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.201405325955221e-05,
+      "loss": 1.7923,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.174420584648123e-05,
+      "loss": 1.7417,
+      "step": 69
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.14702842725101e-05,
+      "loss": 1.8008,
+      "step": 70
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.119231527190158e-05,
+      "loss": 1.7204,
+      "step": 71
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.091032597394012e-05,
+      "loss": 1.7863,
+      "step": 72
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.062434390028407e-05,
+      "loss": 1.7512,
+      "step": 73
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.033439696227965e-05,
+      "loss": 1.8159,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.004051345823689e-05,
+      "loss": 1.7654,
+      "step": 75
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.974272207066767e-05,
+      "loss": 1.712,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.944105186348646e-05,
+      "loss": 1.7975,
+      "step": 77
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.913553227917367e-05,
+      "loss": 1.7364,
+      "step": 78
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 8.882619313590212e-05,
+      "loss": 1.7615,
+      "step": 79
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.851306462462688e-05,
+      "loss": 1.6968,
+      "step": 80
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.819617730613862e-05,
+      "loss": 1.7455,
+      "step": 81
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.787556210808101e-05,
+      "loss": 1.8118,
+      "step": 82
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.755125032193214e-05,
+      "loss": 1.7766,
+      "step": 83
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.722327359995064e-05,
+      "loss": 1.7388,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.689166395208636e-05,
+      "loss": 1.6951,
+      "step": 85
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.655645374285637e-05,
+      "loss": 1.8524,
+      "step": 86
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.621767568818613e-05,
+      "loss": 1.8439,
+      "step": 87
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.587536285221656e-05,
+      "loss": 1.7917,
+      "step": 88
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.552954864407699e-05,
+      "loss": 1.7381,
+      "step": 89
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.518026681462448e-05,
+      "loss": 1.7198,
+      "step": 90
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.482755145314986e-05,
+      "loss": 1.7388,
+      "step": 91
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.44714369840506e-05,
+      "loss": 1.7147,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.41119581634711e-05,
+      "loss": 1.7247,
+      "step": 93
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.374915007591053e-05,
+      "loss": 1.7975,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.338304813079865e-05,
+      "loss": 1.6963,
+      "step": 95
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.301368805903988e-05,
+      "loss": 1.7466,
+      "step": 96
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.264110590952609e-05,
+      "loss": 1.8162,
+      "step": 97
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.226533804561827e-05,
+      "loss": 1.8318,
+      "step": 98
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.188642114159747e-05,
+      "loss": 1.8107,
+      "step": 99
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.150439217908556e-05,
+      "loss": 1.7286,
+      "step": 100
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.11192884434358e-05,
+      "loss": 1.8096,
+      "step": 101
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.073114752009387e-05,
+      "loss": 1.7905,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.034000729092968e-05,
+      "loss": 1.8094,
+      "step": 103
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.994590593054001e-05,
+      "loss": 1.7906,
+      "step": 104
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.954888190252292e-05,
+      "loss": 1.8019,
+      "step": 105
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.91489739557236e-05,
+      "loss": 1.7756,
+      "step": 106
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.874622112045269e-05,
+      "loss": 1.7668,
+      "step": 107
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.83406627046769e-05,
+      "loss": 1.7509,
+      "step": 108
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.793233829018262e-05,
+      "loss": 1.8472,
+      "step": 109
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.752128772871292e-05,
+      "loss": 1.7917,
+      "step": 110
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.710755113807794e-05,
+      "loss": 1.7408,
+      "step": 111
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.669116889823955e-05,
+      "loss": 1.6748,
+      "step": 112
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.627218164737031e-05,
+      "loss": 1.8016,
+      "step": 113
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.585063027788731e-05,
+      "loss": 1.7302,
+      "step": 114
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.542655593246103e-05,
+      "loss": 1.735,
+      "step": 115
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.777,
+      "step": 116
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.457100411161128e-05,
+      "loss": 1.7049,
+      "step": 117
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.413961013653726e-05,
+      "loss": 1.826,
+      "step": 118
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.370586017806942e-05,
+      "loss": 1.7539,
+      "step": 119
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.326979656943906e-05,
+      "loss": 1.6597,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.283146186968565e-05,
+      "loss": 1.7977,
+      "step": 121
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.239089885950316e-05,
+      "loss": 1.7501,
+      "step": 122
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.19481505370647e-05,
+      "loss": 1.7521,
+      "step": 123
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.150326011382604e-05,
+      "loss": 1.7778,
+      "step": 124
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.105627101030817e-05,
+      "loss": 1.7793,
+      "step": 125
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.060722685185961e-05,
+      "loss": 1.8148,
+      "step": 126
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.015617146439863e-05,
+      "loss": 1.7838,
+      "step": 127
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.970314887013584e-05,
+      "loss": 1.796,
+      "step": 128
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.924820328327786e-05,
+      "loss": 1.832,
+      "step": 129
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.879137910571191e-05,
+      "loss": 1.7494,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.833272092267241e-05,
+      "loss": 1.7762,
+      "step": 131
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.787227349838947e-05,
+      "loss": 1.7136,
+      "step": 132
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.741008177171995e-05,
+      "loss": 1.7987,
+      "step": 133
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.694619085176159e-05,
+      "loss": 1.7855,
+      "step": 134
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.64806460134504e-05,
+      "loss": 1.801,
+      "step": 135
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.601349269314188e-05,
+      "loss": 1.6862,
+      "step": 136
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.554477648417657e-05,
+      "loss": 1.7124,
+      "step": 137
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.507454313243015e-05,
+      "loss": 1.7362,
+      "step": 138
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.460283853184879e-05,
+      "loss": 1.6903,
+      "step": 139
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.412970871996995e-05,
+      "loss": 1.7153,
+      "step": 140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.365519987342917e-05,
+      "loss": 1.7335,
+      "step": 141
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.317935830345338e-05,
+      "loss": 1.7567,
+      "step": 142
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.270223045134096e-05,
+      "loss": 1.7885,
+      "step": 143
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.222386288392913e-05,
+      "loss": 1.8316,
+      "step": 144
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.174430228904919e-05,
+      "loss": 1.7411,
+      "step": 145
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.126359547096975e-05,
+      "loss": 1.7384,
+      "step": 146
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.078178934582885e-05,
+      "loss": 1.7717,
+      "step": 147
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.029893093705492e-05,
+      "loss": 1.7984,
+      "step": 148
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.981506737077744e-05,
+      "loss": 1.7875,
+      "step": 149
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.9330245871227454e-05,
+      "loss": 1.762,
+      "step": 150
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.884451375612865e-05,
+      "loss": 1.7517,
+      "step": 151
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.835791843207916e-05,
+      "loss": 1.7745,
+      "step": 152
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.787050738992482e-05,
+      "loss": 1.6965,
+      "step": 153
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.738232820012407e-05,
+      "loss": 1.7892,
+      "step": 154
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.6893428508105225e-05,
+      "loss": 1.7803,
+      "step": 155
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.640385602961634e-05,
+      "loss": 1.7592,
+      "step": 156
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.5913658546068295e-05,
+      "loss": 1.8219,
+      "step": 157
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.5422883899871284e-05,
+      "loss": 1.8626,
+      "step": 158
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.493157998976559e-05,
+      "loss": 1.7252,
+      "step": 159
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4439794766146746e-05,
+      "loss": 1.6911,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.39475762263856e-05,
+      "loss": 1.8046,
+      "step": 161
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.34549724101439e-05,
+      "loss": 1.7559,
+      "step": 162
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.296203139468572e-05,
+      "loss": 1.8943,
+      "step": 163
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.246880129018516e-05,
+      "loss": 1.7772,
+      "step": 164
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.197533023503089e-05,
+      "loss": 1.7057,
+      "step": 165
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 5.148166639112799e-05,
+      "loss": 1.6976,
+      "step": 166
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 5.0987857939197324e-05,
+      "loss": 1.8151,
+      "step": 167
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 5.049395307407329e-05,
+      "loss": 1.7286,
+      "step": 168
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 5e-05,
+      "loss": 1.782,
+      "step": 169
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 328,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4.6006394181082153e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-169/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e60f1b5d15ced53a534111f26d4623440cc37c60600828e28ffd0da0da5e62
+size 5304

checkpoint-328/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: models/miqu-1-70b-sf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0

checkpoint-328/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/miqu-1-70b-sf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-328/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4564e5b9c673d71626cfd1822a01639bb7359a1ed537becbef35bfbfac90b613
+size 1656902648

checkpoint-328/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff90a73d43c6abb8f89d90fcb9c7acfd2180b605f739b48056dca99d41f8df79
+size 831306452

checkpoint-328/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e0cce9ee681ee5c91cb6a1979f57530007510c951aa6c3e01374d32de1b2c2
+size 14244

checkpoint-328/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b1ee8834e6374947ee9f2cbba00e5ade3da0b80a085340ffa41a1a2d87a5d6
+size 1064

checkpoint-328/trainer_state.json

@@ -0,0 +1,1989 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.965045592705167,
+  "eval_steps": 500,
+  "global_step": 328,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 1.897,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 1.9202,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3e-05,
+      "loss": 1.9071,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 1.9712,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 2.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6e-05,
+      "loss": 1.8839,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7e-05,
+      "loss": 1.9586,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8e-05,
+      "loss": 1.9625,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9e-05,
+      "loss": 1.9269,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001,
+      "loss": 1.9005,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.999756004407229e-05,
+      "loss": 1.857,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.999024041442456e-05,
+      "loss": 1.9072,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.997804182543973e-05,
+      "loss": 1.7945,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.99609654676786e-05,
+      "loss": 1.8496,
+      "step": 14
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.993901300776359e-05,
+      "loss": 1.8275,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.991218658821608e-05,
+      "loss": 1.8701,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.988048882724732e-05,
+      "loss": 1.8594,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.984392281850293e-05,
+      "loss": 1.8669,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.980249213076084e-05,
+      "loss": 1.8022,
+      "step": 19
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.97562008075832e-05,
+      "loss": 1.8139,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.970505336692153e-05,
+      "loss": 1.8775,
+      "step": 21
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.964905480067586e-05,
+      "loss": 1.7862,
+      "step": 22
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.958821057420754e-05,
+      "loss": 1.8414,
+      "step": 23
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.952252662580579e-05,
+      "loss": 1.7446,
+      "step": 24
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.94520093661082e-05,
+      "loss": 1.8705,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.937666567747501e-05,
+      "loss": 1.822,
+      "step": 26
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.92965029133174e-05,
+      "loss": 1.9357,
+      "step": 27
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.921152889737984e-05,
+      "loss": 1.7958,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.912175192297648e-05,
+      "loss": 1.7557,
+      "step": 29
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.902718075218176e-05,
+      "loss": 1.8138,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.89278246149752e-05,
+      "loss": 1.7865,
+      "step": 31
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.882369320834069e-05,
+      "loss": 1.7997,
+      "step": 32
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.87147966953199e-05,
+      "loss": 1.7534,
+      "step": 33
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.860114570402054e-05,
+      "loss": 1.7092,
+      "step": 34
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.848275132657903e-05,
+      "loss": 1.7261,
+      "step": 35
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.835962511807786e-05,
+      "loss": 1.7827,
+      "step": 36
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.823177909541794e-05,
+      "loss": 1.7948,
+      "step": 37
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.809922573614569e-05,
+      "loss": 1.8275,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.796197797723532e-05,
+      "loss": 1.7533,
+      "step": 39
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.782004921382612e-05,
+      "loss": 1.7555,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.767345329791522e-05,
+      "loss": 1.8018,
+      "step": 41
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.752220453700556e-05,
+      "loss": 1.8107,
+      "step": 42
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.736631769270957e-05,
+      "loss": 1.7941,
+      "step": 43
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.720580797930845e-05,
+      "loss": 1.8829,
+      "step": 44
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.704069106226727e-05,
+      "loss": 1.8041,
+      "step": 45
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.687098305670605e-05,
+      "loss": 1.77,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.669670052582695e-05,
+      "loss": 1.7547,
+      "step": 47
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.651786047929773e-05,
+      "loss": 1.7594,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.633448037159167e-05,
+      "loss": 1.7076,
+      "step": 49
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.614657810028402e-05,
+      "loss": 1.786,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.595417200430516e-05,
+      "loss": 1.7076,
+      "step": 51
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.575728086215092e-05,
+      "loss": 1.7508,
+      "step": 52
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.555592389004966e-05,
+      "loss": 1.7979,
+      "step": 53
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.535012074008687e-05,
+      "loss": 1.7075,
+      "step": 54
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.513989149828718e-05,
+      "loss": 1.7828,
+      "step": 55
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.492525668265399e-05,
+      "loss": 1.8179,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.470623724116692e-05,
+      "loss": 1.7802,
+      "step": 57
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.448285454973738e-05,
+      "loss": 1.7873,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.425513041012219e-05,
+      "loss": 1.7315,
+      "step": 59
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.402308704779599e-05,
+      "loss": 1.7953,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.378674710978185e-05,
+      "loss": 1.7946,
+      "step": 61
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.354613366244108e-05,
+      "loss": 1.7543,
+      "step": 62
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.7302,
+      "step": 63
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.305218058836778e-05,
+      "loss": 1.8224,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.279888917058452e-05,
+      "loss": 1.757,
+      "step": 65
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.254142065666801e-05,
+      "loss": 1.7506,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.22798001750913e-05,
+      "loss": 1.7523,
+      "step": 67
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.201405325955221e-05,
+      "loss": 1.7923,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.174420584648123e-05,
+      "loss": 1.7417,
+      "step": 69
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.14702842725101e-05,
+      "loss": 1.8008,
+      "step": 70
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.119231527190158e-05,
+      "loss": 1.7204,
+      "step": 71
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.091032597394012e-05,
+      "loss": 1.7863,
+      "step": 72
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.062434390028407e-05,
+      "loss": 1.7512,
+      "step": 73
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.033439696227965e-05,
+      "loss": 1.8159,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.004051345823689e-05,
+      "loss": 1.7654,
+      "step": 75
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.974272207066767e-05,
+      "loss": 1.712,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.944105186348646e-05,
+      "loss": 1.7975,
+      "step": 77
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.913553227917367e-05,
+      "loss": 1.7364,
+      "step": 78
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 8.882619313590212e-05,
+      "loss": 1.7615,
+      "step": 79
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.851306462462688e-05,
+      "loss": 1.6968,
+      "step": 80
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.819617730613862e-05,
+      "loss": 1.7455,
+      "step": 81
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.787556210808101e-05,
+      "loss": 1.8118,
+      "step": 82
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.755125032193214e-05,
+      "loss": 1.7766,
+      "step": 83
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.722327359995064e-05,
+      "loss": 1.7388,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.689166395208636e-05,
+      "loss": 1.6951,
+      "step": 85
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.655645374285637e-05,
+      "loss": 1.8524,
+      "step": 86
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.621767568818613e-05,
+      "loss": 1.8439,
+      "step": 87
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.587536285221656e-05,
+      "loss": 1.7917,
+      "step": 88
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.552954864407699e-05,
+      "loss": 1.7381,
+      "step": 89
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.518026681462448e-05,
+      "loss": 1.7198,
+      "step": 90
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.482755145314986e-05,
+      "loss": 1.7388,
+      "step": 91
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.44714369840506e-05,
+      "loss": 1.7147,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.41119581634711e-05,
+      "loss": 1.7247,
+      "step": 93
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.374915007591053e-05,
+      "loss": 1.7975,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.338304813079865e-05,
+      "loss": 1.6963,
+      "step": 95
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.301368805903988e-05,
+      "loss": 1.7466,
+      "step": 96
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.264110590952609e-05,
+      "loss": 1.8162,
+      "step": 97
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.226533804561827e-05,
+      "loss": 1.8318,
+      "step": 98
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.188642114159747e-05,
+      "loss": 1.8107,
+      "step": 99
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.150439217908556e-05,
+      "loss": 1.7286,
+      "step": 100
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.11192884434358e-05,
+      "loss": 1.8096,
+      "step": 101
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.073114752009387e-05,
+      "loss": 1.7905,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.034000729092968e-05,
+      "loss": 1.8094,
+      "step": 103
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.994590593054001e-05,
+      "loss": 1.7906,
+      "step": 104
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.954888190252292e-05,
+      "loss": 1.8019,
+      "step": 105
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.91489739557236e-05,
+      "loss": 1.7756,
+      "step": 106
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.874622112045269e-05,
+      "loss": 1.7668,
+      "step": 107
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.83406627046769e-05,
+      "loss": 1.7509,
+      "step": 108
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.793233829018262e-05,
+      "loss": 1.8472,
+      "step": 109
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.752128772871292e-05,
+      "loss": 1.7917,
+      "step": 110
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.710755113807794e-05,
+      "loss": 1.7408,
+      "step": 111
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.669116889823955e-05,
+      "loss": 1.6748,
+      "step": 112
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.627218164737031e-05,
+      "loss": 1.8016,
+      "step": 113
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.585063027788731e-05,
+      "loss": 1.7302,
+      "step": 114
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.542655593246103e-05,
+      "loss": 1.735,
+      "step": 115
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.777,
+      "step": 116
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.457100411161128e-05,
+      "loss": 1.7049,
+      "step": 117
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.413961013653726e-05,
+      "loss": 1.826,
+      "step": 118
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.370586017806942e-05,
+      "loss": 1.7539,
+      "step": 119
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.326979656943906e-05,
+      "loss": 1.6597,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.283146186968565e-05,
+      "loss": 1.7977,
+      "step": 121
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.239089885950316e-05,
+      "loss": 1.7501,
+      "step": 122
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.19481505370647e-05,
+      "loss": 1.7521,
+      "step": 123
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.150326011382604e-05,
+      "loss": 1.7778,
+      "step": 124
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.105627101030817e-05,
+      "loss": 1.7793,
+      "step": 125
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.060722685185961e-05,
+      "loss": 1.8148,
+      "step": 126
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.015617146439863e-05,
+      "loss": 1.7838,
+      "step": 127
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.970314887013584e-05,
+      "loss": 1.796,
+      "step": 128
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.924820328327786e-05,
+      "loss": 1.832,
+      "step": 129
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.879137910571191e-05,
+      "loss": 1.7494,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.833272092267241e-05,
+      "loss": 1.7762,
+      "step": 131
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.787227349838947e-05,
+      "loss": 1.7136,
+      "step": 132
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.741008177171995e-05,
+      "loss": 1.7987,
+      "step": 133
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.694619085176159e-05,
+      "loss": 1.7855,
+      "step": 134
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.64806460134504e-05,
+      "loss": 1.801,
+      "step": 135
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.601349269314188e-05,
+      "loss": 1.6862,
+      "step": 136
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.554477648417657e-05,
+      "loss": 1.7124,
+      "step": 137
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.507454313243015e-05,
+      "loss": 1.7362,
+      "step": 138
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.460283853184879e-05,
+      "loss": 1.6903,
+      "step": 139
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.412970871996995e-05,
+      "loss": 1.7153,
+      "step": 140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.365519987342917e-05,
+      "loss": 1.7335,
+      "step": 141
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.317935830345338e-05,
+      "loss": 1.7567,
+      "step": 142
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.270223045134096e-05,
+      "loss": 1.7885,
+      "step": 143
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.222386288392913e-05,
+      "loss": 1.8316,
+      "step": 144
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.174430228904919e-05,
+      "loss": 1.7411,
+      "step": 145
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.126359547096975e-05,
+      "loss": 1.7384,
+      "step": 146
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.078178934582885e-05,
+      "loss": 1.7717,
+      "step": 147
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.029893093705492e-05,
+      "loss": 1.7984,
+      "step": 148
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.981506737077744e-05,
+      "loss": 1.7875,
+      "step": 149
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.9330245871227454e-05,
+      "loss": 1.762,
+      "step": 150
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.884451375612865e-05,
+      "loss": 1.7517,
+      "step": 151
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.835791843207916e-05,
+      "loss": 1.7745,
+      "step": 152
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.787050738992482e-05,
+      "loss": 1.6965,
+      "step": 153
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.738232820012407e-05,
+      "loss": 1.7892,
+      "step": 154
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.6893428508105225e-05,
+      "loss": 1.7803,
+      "step": 155
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.640385602961634e-05,
+      "loss": 1.7592,
+      "step": 156
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.5913658546068295e-05,
+      "loss": 1.8219,
+      "step": 157
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.5422883899871284e-05,
+      "loss": 1.8626,
+      "step": 158
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.493157998976559e-05,
+      "loss": 1.7252,
+      "step": 159
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4439794766146746e-05,
+      "loss": 1.6911,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.39475762263856e-05,
+      "loss": 1.8046,
+      "step": 161
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.34549724101439e-05,
+      "loss": 1.7559,
+      "step": 162
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.296203139468572e-05,
+      "loss": 1.8943,
+      "step": 163
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.246880129018516e-05,
+      "loss": 1.7772,
+      "step": 164
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.197533023503089e-05,
+      "loss": 1.7057,
+      "step": 165
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 5.148166639112799e-05,
+      "loss": 1.6976,
+      "step": 166
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 5.0987857939197324e-05,
+      "loss": 1.8151,
+      "step": 167
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 5.049395307407329e-05,
+      "loss": 1.7286,
+      "step": 168
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 5e-05,
+      "loss": 1.782,
+      "step": 169
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.950604692592672e-05,
+      "loss": 1.7561,
+      "step": 170
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.901214206080269e-05,
+      "loss": 1.6331,
+      "step": 171
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.851833360887201e-05,
+      "loss": 1.6803,
+      "step": 172
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.802466976496911e-05,
+      "loss": 1.7244,
+      "step": 173
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.7531198709814854e-05,
+      "loss": 1.7924,
+      "step": 174
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.703796860531429e-05,
+      "loss": 1.7374,
+      "step": 175
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.654502758985611e-05,
+      "loss": 1.6847,
+      "step": 176
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.6052423773614404e-05,
+      "loss": 1.7498,
+      "step": 177
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.5560205233853266e-05,
+      "loss": 1.8711,
+      "step": 178
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.506842001023442e-05,
+      "loss": 1.7231,
+      "step": 179
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.4577116100128735e-05,
+      "loss": 1.7341,
+      "step": 180
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.4086341453931716e-05,
+      "loss": 1.7211,
+      "step": 181
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.3596143970383664e-05,
+      "loss": 1.6533,
+      "step": 182
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.3106571491894786e-05,
+      "loss": 1.8128,
+      "step": 183
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.2617671799875944e-05,
+      "loss": 1.7778,
+      "step": 184
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.212949261007519e-05,
+      "loss": 1.6615,
+      "step": 185
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.1642081567920846e-05,
+      "loss": 1.8061,
+      "step": 186
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.115548624387137e-05,
+      "loss": 1.78,
+      "step": 187
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.066975412877255e-05,
+      "loss": 1.7801,
+      "step": 188
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.0184932629222575e-05,
+      "loss": 1.7524,
+      "step": 189
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.970106906294509e-05,
+      "loss": 1.7623,
+      "step": 190
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.921821065417116e-05,
+      "loss": 1.7811,
+      "step": 191
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.873640452903026e-05,
+      "loss": 1.7596,
+      "step": 192
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.825569771095082e-05,
+      "loss": 1.7775,
+      "step": 193
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.777613711607087e-05,
+      "loss": 1.7089,
+      "step": 194
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.729776954865905e-05,
+      "loss": 1.7586,
+      "step": 195
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.682064169654663e-05,
+      "loss": 1.7708,
+      "step": 196
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.6344800126570844e-05,
+      "loss": 1.7585,
+      "step": 197
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.587029128003006e-05,
+      "loss": 1.8535,
+      "step": 198
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.539716146815122e-05,
+      "loss": 1.7022,
+      "step": 199
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.492545686756986e-05,
+      "loss": 1.8033,
+      "step": 200
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.4455223515823446e-05,
+      "loss": 1.7032,
+      "step": 201
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.3986507306858125e-05,
+      "loss": 1.7893,
+      "step": 202
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.351935398654961e-05,
+      "loss": 1.8007,
+      "step": 203
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.3053809148238426e-05,
+      "loss": 1.6865,
+      "step": 204
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.258991822828007e-05,
+      "loss": 1.7272,
+      "step": 205
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.212772650161056e-05,
+      "loss": 1.6851,
+      "step": 206
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 3.16672790773276e-05,
+      "loss": 1.6703,
+      "step": 207
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.12086208942881e-05,
+      "loss": 1.7194,
+      "step": 208
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.075179671672216e-05,
+      "loss": 1.6898,
+      "step": 209
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.0296851129864168e-05,
+      "loss": 1.6836,
+      "step": 210
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.98438285356014e-05,
+      "loss": 1.6886,
+      "step": 211
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.9392773148140408e-05,
+      "loss": 1.6708,
+      "step": 212
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.894372898969186e-05,
+      "loss": 1.6964,
+      "step": 213
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.8496739886173995e-05,
+      "loss": 1.639,
+      "step": 214
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.805184946293532e-05,
+      "loss": 1.742,
+      "step": 215
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.7609101140496863e-05,
+      "loss": 1.758,
+      "step": 216
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.716853813031435e-05,
+      "loss": 1.6614,
+      "step": 217
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.6730203430560947e-05,
+      "loss": 1.7814,
+      "step": 218
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.6294139821930597e-05,
+      "loss": 1.7335,
+      "step": 219
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.5860389863462765e-05,
+      "loss": 1.7071,
+      "step": 220
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.542899588838875e-05,
+      "loss": 1.7433,
+      "step": 221
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7727,
+      "step": 222
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.4573444067538986e-05,
+      "loss": 1.6221,
+      "step": 223
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.414936972211272e-05,
+      "loss": 1.7824,
+      "step": 224
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.3727818352629712e-05,
+      "loss": 1.832,
+      "step": 225
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.3308831101760486e-05,
+      "loss": 1.6692,
+      "step": 226
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.289244886192207e-05,
+      "loss": 1.7652,
+      "step": 227
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.247871227128709e-05,
+      "loss": 1.7668,
+      "step": 228
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.2067661709817383e-05,
+      "loss": 1.7603,
+      "step": 229
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.1659337295323118e-05,
+      "loss": 1.7214,
+      "step": 230
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.125377887954732e-05,
+      "loss": 1.664,
+      "step": 231
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.0851026044276406e-05,
+      "loss": 1.7438,
+      "step": 232
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.0451118097477094e-05,
+      "loss": 1.7077,
+      "step": 233
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.005409406946e-05,
+      "loss": 1.6965,
+      "step": 234
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.9659992709070345e-05,
+      "loss": 1.7149,
+      "step": 235
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.9268852479906147e-05,
+      "loss": 1.7308,
+      "step": 236
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.888071155656421e-05,
+      "loss": 1.8064,
+      "step": 237
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.849560782091445e-05,
+      "loss": 1.7866,
+      "step": 238
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.811357885840254e-05,
+      "loss": 1.7135,
+      "step": 239
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.7734661954381754e-05,
+      "loss": 1.7349,
+      "step": 240
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.7358894090473925e-05,
+      "loss": 1.7935,
+      "step": 241
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.6986311940960147e-05,
+      "loss": 1.693,
+      "step": 242
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.661695186920138e-05,
+      "loss": 1.8604,
+      "step": 243
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.6250849924089484e-05,
+      "loss": 1.741,
+      "step": 244
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.5888041836528915e-05,
+      "loss": 1.6668,
+      "step": 245
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.552856301594942e-05,
+      "loss": 1.6838,
+      "step": 246
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.5172448546850165e-05,
+      "loss": 1.7143,
+      "step": 247
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.4819733185375534e-05,
+      "loss": 1.6719,
+      "step": 248
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.4470451355923027e-05,
+      "loss": 1.7879,
+      "step": 249
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.4124637147783432e-05,
+      "loss": 1.6943,
+      "step": 250
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.378232431181386e-05,
+      "loss": 1.7382,
+      "step": 251
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.3443546257143624e-05,
+      "loss": 1.7818,
+      "step": 252
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.3108336047913633e-05,
+      "loss": 1.6781,
+      "step": 253
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.277672640004936e-05,
+      "loss": 1.6687,
+      "step": 254
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2448749678067856e-05,
+      "loss": 1.7702,
+      "step": 255
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2124437891918993e-05,
+      "loss": 1.7324,
+      "step": 256
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.1803822693861378e-05,
+      "loss": 1.7849,
+      "step": 257
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1486935375373126e-05,
+      "loss": 1.6662,
+      "step": 258
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1173806864097886e-05,
+      "loss": 1.7473,
+      "step": 259
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0864467720826343e-05,
+      "loss": 1.7529,
+      "step": 260
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.0558948136513535e-05,
+      "loss": 1.7526,
+      "step": 261
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.0257277929332332e-05,
+      "loss": 1.721,
+      "step": 262
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.959486541763119e-06,
+      "loss": 1.7076,
+      "step": 263
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.66560303772035e-06,
+      "loss": 1.7822,
+      "step": 264
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.375656099715934e-06,
+      "loss": 1.7664,
+      "step": 265
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.08967402605988e-06,
+      "loss": 1.6733,
+      "step": 266
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.80768472809842e-06,
+      "loss": 1.717,
+      "step": 267
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.529715727489912e-06,
+      "loss": 1.7967,
+      "step": 268
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.255794153518798e-06,
+      "loss": 1.5902,
+      "step": 269
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.985946740447791e-06,
+      "loss": 1.785,
+      "step": 270
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.720199824908692e-06,
+      "loss": 1.7182,
+      "step": 271
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.458579343331995e-06,
+      "loss": 1.7056,
+      "step": 272
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.2011108294154804e-06,
+      "loss": 1.7588,
+      "step": 273
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.947819411632223e-06,
+      "loss": 1.6806,
+      "step": 274
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6865,
+      "step": 275
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 6.45386633755894e-06,
+      "loss": 1.7063,
+      "step": 276
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.213252890218163e-06,
+      "loss": 1.6924,
+      "step": 277
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.976912952204017e-06,
+      "loss": 1.7508,
+      "step": 278
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 5.74486958987781e-06,
+      "loss": 1.7623,
+      "step": 279
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 5.51714545026264e-06,
+      "loss": 1.7495,
+      "step": 280
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 5.293762758833071e-06,
+      "loss": 1.7111,
+      "step": 281
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 5.074743317346009e-06,
+      "loss": 1.7635,
+      "step": 282
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.860108501712824e-06,
+      "loss": 1.6867,
+      "step": 283
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.649879259913137e-06,
+      "loss": 1.7256,
+      "step": 284
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.4440761099503455e-06,
+      "loss": 1.7276,
+      "step": 285
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.242719137849077e-06,
+      "loss": 1.7283,
+      "step": 286
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.045827995694834e-06,
+      "loss": 1.7619,
+      "step": 287
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.853421899715992e-06,
+      "loss": 1.7451,
+      "step": 288
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.6655196284083317e-06,
+      "loss": 1.7501,
+      "step": 289
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.4821395207022766e-06,
+      "loss": 1.8164,
+      "step": 290
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.303299474173066e-06,
+      "loss": 1.6923,
+      "step": 291
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.1290169432939553e-06,
+      "loss": 1.823,
+      "step": 292
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.9593089377327245e-06,
+      "loss": 1.7789,
+      "step": 293
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.794192020691544e-06,
+      "loss": 1.732,
+      "step": 294
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.6336823072904304e-06,
+      "loss": 1.6913,
+      "step": 295
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.4777954629944477e-06,
+      "loss": 1.8344,
+      "step": 296
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.3265467020847866e-06,
+      "loss": 1.7282,
+      "step": 297
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.179950786173879e-06,
+      "loss": 1.715,
+      "step": 298
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.038022022764685e-06,
+      "loss": 1.6707,
+      "step": 299
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.9007742638543102e-06,
+      "loss": 1.7191,
+      "step": 300
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.7682209045820686e-06,
+      "loss": 1.6994,
+      "step": 301
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.6403748819221466e-06,
+      "loss": 1.7857,
+      "step": 302
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.5172486734209789e-06,
+      "loss": 1.8173,
+      "step": 303
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.3988542959794627e-06,
+      "loss": 1.8064,
+      "step": 304
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.2852033046801104e-06,
+      "loss": 1.741,
+      "step": 305
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1763067916593262e-06,
+      "loss": 1.7858,
+      "step": 306
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.0721753850247984e-06,
+      "loss": 1.6811,
+      "step": 307
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 9.728192478182574e-07,
+      "loss": 1.8126,
+      "step": 308
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.782480770235247e-07,
+      "loss": 1.8005,
+      "step": 309
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 1.8307,
+      "step": 310
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.034970866825974e-07,
+      "loss": 1.6815,
+      "step": 311
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.233343225249933e-07,
+      "loss": 1.6576,
+      "step": 312
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.479906338917984e-07,
+      "loss": 1.647,
+      "step": 313
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.774733741942206e-07,
+      "loss": 1.698,
+      "step": 314
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.1178942579248036e-07,
+      "loss": 1.722,
+      "step": 315
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.5094519932415417e-07,
+      "loss": 1.7361,
+      "step": 316
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.9494663307847447e-07,
+      "loss": 1.7881,
+      "step": 317
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.437991924167937e-07,
+      "loss": 1.7061,
+      "step": 318
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.975078692391552e-07,
+      "loss": 1.8235,
+      "step": 319
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.560771814970885e-07,
+      "loss": 1.7096,
+      "step": 320
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.195111727526843e-07,
+      "loss": 1.7408,
+      "step": 321
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 8.781341178393244e-08,
+      "loss": 1.6738,
+      "step": 322
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.098699223641702e-08,
+      "loss": 1.7742,
+      "step": 323
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.9034532321408076e-08,
+      "loss": 1.6591,
+      "step": 324
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.1958174560282595e-08,
+      "loss": 1.841,
+      "step": 325
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.75958557545842e-09,
+      "loss": 1.7205,
+      "step": 326
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.4399559277132888e-09,
+      "loss": 1.7067,
+      "step": 327
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0,
+      "loss": 1.7346,
+      "step": 328
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 328,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8.91586250599406e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-328/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e60f1b5d15ced53a534111f26d4623440cc37c60600828e28ffd0da0da5e62
+size 5304

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "models/miqu-1-70b-sf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32764,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "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_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}