Upload folder using huggingface_hub

README.md

@@ -0,0 +1,151 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: JY623/KoSOLAR-v2.0
+model-index:
+- name: qlora-out/v1.2
+  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: JY623/KoSOLAR-v2.0
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+push_dataset_to_hub:
+datasets:
+  - path: kyujinpy/KOR-OpenOrca-Platypus-v3
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./qlora-out/v1.2
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+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:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 2
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: false
+
+warmup_steps: 20
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+```
+
+</details><br>
+
+# qlora-out/v1.2
+
+This model is a fine-tuned version of [JY623/KoSOLAR-v2.0](https://huggingface.co/JY623/KoSOLAR-v2.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.1419
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 7
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 28
+- total_eval_batch_size: 7
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 13.4775       | 0.0   | 1    | 13.4330         |
+| 6.9219        | 0.25  | 64   | 6.2022          |
+| 5.5416        | 0.5   | 128  | 5.2780          |
+| 5.4282        | 0.75  | 192  | 5.1929          |
+| 5.4864        | 1.0   | 256  | 5.1416          |
+| 5.2877        | 1.24  | 320  | 5.1441          |
+| 5.1731        | 1.49  | 384  | 5.1413          |
+| 5.6221        | 1.74  | 448  | 5.1406          |
+| 5.3737        | 1.99  | 512  | 5.1419          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "JY623/KoSOLAR-v2.0",
+  "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",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8ffd79d6f9619469f3bfb984a5365af2b06f81f2df30508fdf665cd7e2c811
+size 503559370

checkpoint-256/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: JY623/KoSOLAR-v2.0
+---
+
+# 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 0.9.0

checkpoint-256/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "JY623/KoSOLAR-v2.0",
+  "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",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-256/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3ee956bccbead6fd7e0ea8ae28b55369886e4c116ebc74f8036b91c467e133
+size 503407240

checkpoint-256/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926c619b95fea7414ad6b2e63db19a29f02bfc49ac722884e46798b7a4343e5e
+size 1007047506

checkpoint-256/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e476e90b9456db0e513e94f2e35362b3965e15141137a4c9e3d2fb6a65635a41
+size 15728

checkpoint-256/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d9b8c2570c0d9b6f2307313f2c1a7f1e3d822422d69243a478cf5d59da0742
+size 15728

checkpoint-256/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83b9657ec724cbdbbfed58ad9c8bcc97e18e5d012cc72f5b4eddadab03deae5
+size 15728

checkpoint-256/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e22e19677dd891f0cb047c86a5e9ea2cffca1f51987c60052c281bbbffe5d0
+size 15728

checkpoint-256/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a159fc7d01782aa38326dde95cd6a38584e0ad2c6e204aa21052a4eab6eb4a07
+size 15728

checkpoint-256/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b626eae65dc8d09e39c90dcb56470356c7d1fa697552bd789fd6d61acd5095
+size 15728

checkpoint-256/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b59ded2a5476b484b4f9dd34737c7845d24e547a86f2cedf5a6222f83fb951e
+size 15728

checkpoint-256/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9a21337c0cfd4a6defcff3f1fa6cce5870542bbc17bcc07e9881f2c3a0fc04
+size 1064

checkpoint-256/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-256/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-256/trainer_state.json

@@ -0,0 +1,1853 @@
+{
+  "best_metric": 5.141561985015869,
+  "best_model_checkpoint": "./qlora-out/v1.2/checkpoint-256",
+  "epoch": 1.0,
+  "eval_steps": 64,
+  "global_step": 256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.009024755097925663,
+      "learning_rate": 1e-05,
+      "loss": 13.4775,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 13.432984352111816,
+      "eval_runtime": 117.1907,
+      "eval_samples_per_second": 14.464,
+      "eval_steps_per_second": 2.074,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.008986919187009335,
+      "learning_rate": 2e-05,
+      "loss": 13.4709,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.008954666554927826,
+      "learning_rate": 3e-05,
+      "loss": 13.4803,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.009628714993596077,
+      "learning_rate": 4e-05,
+      "loss": 13.4636,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.010959964245557785,
+      "learning_rate": 5e-05,
+      "loss": 13.435,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.01327170804142952,
+      "learning_rate": 6e-05,
+      "loss": 13.4603,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.016410112380981445,
+      "learning_rate": 7e-05,
+      "loss": 13.459,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.020337102934718132,
+      "learning_rate": 8e-05,
+      "loss": 13.4504,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.025200409814715385,
+      "learning_rate": 9e-05,
+      "loss": 13.4827,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.03093448095023632,
+      "learning_rate": 0.0001,
+      "loss": 13.441,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.03790152817964554,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 13.4603,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.04524616152048111,
+      "learning_rate": 0.00012,
+      "loss": 13.4387,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.054408054798841476,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 13.4697,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.06374166905879974,
+      "learning_rate": 0.00014,
+      "loss": 13.4468,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.07343802601099014,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 13.3862,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.08400653302669525,
+      "learning_rate": 0.00016,
+      "loss": 13.3262,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.09511911123991013,
+      "learning_rate": 0.00017,
+      "loss": 13.2573,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.10723020881414413,
+      "learning_rate": 0.00018,
+      "loss": 13.2185,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.12024787068367004,
+      "learning_rate": 0.00019,
+      "loss": 13.1834,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.13525475561618805,
+      "learning_rate": 0.0002,
+      "loss": 13.1029,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.14704181253910065,
+      "learning_rate": 0.0001999979613716069,
+      "loss": 13.0303,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16100184619426727,
+      "learning_rate": 0.00019999184556954776,
+      "loss": 12.9015,
+      "step": 22
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.17425554990768433,
+      "learning_rate": 0.00019998165284317945,
+      "loss": 12.8389,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.18788361549377441,
+      "learning_rate": 0.00019996738360808565,
+      "loss": 12.7146,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.20275714993476868,
+      "learning_rate": 0.00019994903844605972,
+      "loss": 12.5686,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.21356578171253204,
+      "learning_rate": 0.000199926618105081,
+      "loss": 12.4685,
+      "step": 26
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2230716049671173,
+      "learning_rate": 0.0001999001234992844,
+      "loss": 12.33,
+      "step": 27
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2376524955034256,
+      "learning_rate": 0.000199869555708923,
+      "loss": 12.1648,
+      "step": 28
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2519569396972656,
+      "learning_rate": 0.0001998349159803241,
+      "loss": 12.0116,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.257049024105072,
+      "learning_rate": 0.00019979620572583846,
+      "loss": 11.8535,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.27328285574913025,
+      "learning_rate": 0.00019975342652378246,
+      "loss": 11.6906,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2857399880886078,
+      "learning_rate": 0.00019970658011837404,
+      "loss": 11.4716,
+      "step": 32
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2988531291484833,
+      "learning_rate": 0.0001996556684196615,
+      "loss": 11.3095,
+      "step": 33
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.316837877035141,
+      "learning_rate": 0.00019960069350344548,
+      "loss": 11.0641,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3310101628303528,
+      "learning_rate": 0.0001995416576111945,
+      "loss": 10.8383,
+      "step": 35
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3369371294975281,
+      "learning_rate": 0.00019947856314995349,
+      "loss": 10.6568,
+      "step": 36
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3535173535346985,
+      "learning_rate": 0.00019941141269224564,
+      "loss": 10.3978,
+      "step": 37
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3756394684314728,
+      "learning_rate": 0.0001993402089759675,
+      "loss": 10.1159,
+      "step": 38
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.38187795877456665,
+      "learning_rate": 0.00019926495490427753,
+      "loss": 9.879,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.39641591906547546,
+      "learning_rate": 0.0001991856535454774,
+      "loss": 9.5833,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40500307083129883,
+      "learning_rate": 0.00019910230813288712,
+      "loss": 9.3309,
+      "step": 41
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.42996540665626526,
+      "learning_rate": 0.00019901492206471325,
+      "loss": 8.8893,
+      "step": 42
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.41511279344558716,
+      "learning_rate": 0.00019892349890391015,
+      "loss": 8.597,
+      "step": 43
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.35860675573349,
+      "learning_rate": 0.00019882804237803488,
+      "loss": 8.4768,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3302132785320282,
+      "learning_rate": 0.00019872855637909504,
+      "loss": 8.3176,
+      "step": 45
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.43532317876815796,
+      "learning_rate": 0.00019862504496339037,
+      "loss": 8.1118,
+      "step": 46
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6842054724693298,
+      "learning_rate": 0.000198517512351347,
+      "loss": 8.1977,
+      "step": 47
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8128633499145508,
+      "learning_rate": 0.0001984059629273457,
+      "loss": 8.1527,
+      "step": 48
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8130613565444946,
+      "learning_rate": 0.00019829040123954297,
+      "loss": 8.0821,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7518128752708435,
+      "learning_rate": 0.00019817083199968552,
+      "loss": 7.8393,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5997517108917236,
+      "learning_rate": 0.00019804726008291828,
+      "loss": 7.557,
+      "step": 51
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.42999598383903503,
+      "learning_rate": 0.00019791969052758562,
+      "loss": 7.5165,
+      "step": 52
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.3002629578113556,
+      "learning_rate": 0.00019778812853502592,
+      "loss": 7.3037,
+      "step": 53
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.24435582756996155,
+      "learning_rate": 0.00019765257946935944,
+      "loss": 7.3316,
+      "step": 54
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2515851855278015,
+      "learning_rate": 0.00019751304885726967,
+      "loss": 7.1767,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2763000726699829,
+      "learning_rate": 0.00019736954238777792,
+      "loss": 7.0993,
+      "step": 56
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2830991744995117,
+      "learning_rate": 0.00019722206591201146,
+      "loss": 7.1805,
+      "step": 57
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.30122554302215576,
+      "learning_rate": 0.00019707062544296498,
+      "loss": 7.0762,
+      "step": 58
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.3070628046989441,
+      "learning_rate": 0.0001969152271552552,
+      "loss": 7.1017,
+      "step": 59
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.30436331033706665,
+      "learning_rate": 0.00019675587738486936,
+      "loss": 7.3221,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2854003608226776,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 6.9803,
+      "step": 61
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.27880895137786865,
+      "learning_rate": 0.0001964253495453141,
+      "loss": 6.7288,
+      "step": 62
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2640041410923004,
+      "learning_rate": 0.00019625418495261343,
+      "loss": 6.8195,
+      "step": 63
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2415798306465149,
+      "learning_rate": 0.00019607909582962477,
+      "loss": 6.9219,
+      "step": 64
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 6.202152252197266,
+      "eval_runtime": 118.0179,
+      "eval_samples_per_second": 14.362,
+      "eval_steps_per_second": 2.059,
+      "step": 64
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.18691398203372955,
+      "learning_rate": 0.0001959000893151813,
+      "loss": 6.6136,
+      "step": 65
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.15952067077159882,
+      "learning_rate": 0.00019571717270783828,
+      "loss": 6.4341,
+      "step": 66
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14711293578147888,
+      "learning_rate": 0.00019553035346557543,
+      "loss": 6.414,
+      "step": 67
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1670265942811966,
+      "learning_rate": 0.00019533963920549306,
+      "loss": 6.4894,
+      "step": 68
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2034294307231903,
+      "learning_rate": 0.00019514503770350127,
+      "loss": 6.3448,
+      "step": 69
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.22955259680747986,
+      "learning_rate": 0.00019494655689400293,
+      "loss": 6.3133,
+      "step": 70
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2635420262813568,
+      "learning_rate": 0.00019474420486957042,
+      "loss": 6.3256,
+      "step": 71
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.26006290316581726,
+      "learning_rate": 0.00019453798988061535,
+      "loss": 6.4601,
+      "step": 72
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.22863267362117767,
+      "learning_rate": 0.0001943279203350523,
+      "loss": 6.1397,
+      "step": 73
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.18543188273906708,
+      "learning_rate": 0.00019411400479795617,
+      "loss": 6.5625,
+      "step": 74
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.14754259586334229,
+      "learning_rate": 0.00019389625199121263,
+      "loss": 6.2912,
+      "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12668511271476746,
+      "learning_rate": 0.00019367467079316279,
+      "loss": 6.2679,
+      "step": 76
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1176210567355156,
+      "learning_rate": 0.0001934492702382411,
+      "loss": 6.2426,
+      "step": 77
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12420424073934555,
+      "learning_rate": 0.00019322005951660697,
+      "loss": 6.3293,
+      "step": 78
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1415456086397171,
+      "learning_rate": 0.00019298704797377013,
+      "loss": 6.0938,
+      "step": 79
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1544170081615448,
+      "learning_rate": 0.0001927502451102095,
+      "loss": 6.1926,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14980632066726685,
+      "learning_rate": 0.00019250966058098588,
+      "loss": 6.1425,
+      "step": 81
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13148672878742218,
+      "learning_rate": 0.00019226530419534833,
+      "loss": 6.0866,
+      "step": 82
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14052827656269073,
+      "learning_rate": 0.00019201718591633417,
+      "loss": 6.1682,
+      "step": 83
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1245439425110817,
+      "learning_rate": 0.0001917653158603628,
+      "loss": 6.0281,
+      "step": 84
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1110084131360054,
+      "learning_rate": 0.00019150970429682314,
+      "loss": 6.0577,
+      "step": 85
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.08920083940029144,
+      "learning_rate": 0.000191250361647655,
+      "loss": 6.0772,
+      "step": 86
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.09026093780994415,
+      "learning_rate": 0.0001909872984869242,
+      "loss": 6.2326,
+      "step": 87
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.11133856326341629,
+      "learning_rate": 0.00019072052554039122,
+      "loss": 5.8261,
+      "step": 88
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.11304065585136414,
+      "learning_rate": 0.00019045005368507418,
+      "loss": 6.3169,
+      "step": 89
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.10704243183135986,
+      "learning_rate": 0.00019017589394880515,
+      "loss": 5.9967,
+      "step": 90
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1576884537935257,
+      "learning_rate": 0.0001898980575097806,
+      "loss": 5.7186,
+      "step": 91
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.12191645801067352,
+      "learning_rate": 0.00018961655569610557,
+      "loss": 5.8001,
+      "step": 92
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1100529134273529,
+      "learning_rate": 0.00018933139998533188,
+      "loss": 5.9882,
+      "step": 93
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.10520044714212418,
+      "learning_rate": 0.00018904260200399006,
+      "loss": 5.8127,
+      "step": 94
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.08245933800935745,
+      "learning_rate": 0.00018875017352711545,
+      "loss": 6.0165,
+      "step": 95
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.07817509770393372,
+      "learning_rate": 0.00018845412647776794,
+      "loss": 5.9087,
+      "step": 96
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.07296270877122879,
+      "learning_rate": 0.00018815447292654596,
+      "loss": 5.8837,
+      "step": 97
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.077950619161129,
+      "learning_rate": 0.00018785122509109426,
+      "loss": 5.9915,
+      "step": 98
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.09345076233148575,
+      "learning_rate": 0.00018754439533560574,
+      "loss": 5.9908,
+      "step": 99
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.10249783098697662,
+      "learning_rate": 0.00018723399617031751,
+      "loss": 6.0887,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.11731438338756561,
+      "learning_rate": 0.00018692004025100054,
+      "loss": 6.0414,
+      "step": 101
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.06663200259208679,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 5.881,
+      "step": 102
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07221497595310211,
+      "learning_rate": 0.00018628150949793261,
+      "loss": 5.6574,
+      "step": 103
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.061096612364053726,
+      "learning_rate": 0.00018595696069872013,
+      "loss": 5.8519,
+      "step": 104
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.06478705257177353,
+      "learning_rate": 0.00018562890721349434,
+      "loss": 5.7816,
+      "step": 105
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.06368556618690491,
+      "learning_rate": 0.00018529736241783824,
+      "loss": 5.872,
+      "step": 106
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07194569706916809,
+      "learning_rate": 0.00018496233982968457,
+      "loss": 5.9662,
+      "step": 107
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07953158766031265,
+      "learning_rate": 0.00018462385310876443,
+      "loss": 5.783,
+      "step": 108
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.06713347882032394,
+      "learning_rate": 0.00018428191605605068,
+      "loss": 5.8917,
+      "step": 109
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.06519600003957748,
+      "learning_rate": 0.000183936542613195,
+      "loss": 5.797,
+      "step": 110
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0615142360329628,
+      "learning_rate": 0.00018358774686195954,
+      "loss": 5.8417,
+      "step": 111
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.07100021839141846,
+      "learning_rate": 0.00018323554302364272,
+      "loss": 5.6852,
+      "step": 112
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.08909253031015396,
+      "learning_rate": 0.00018287994545849946,
+      "loss": 5.7358,
+      "step": 113
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.052479445934295654,
+      "learning_rate": 0.00018252096866515558,
+      "loss": 5.7226,
+      "step": 114
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.05653544142842293,
+      "learning_rate": 0.00018215862728001677,
+      "loss": 5.6749,
+      "step": 115
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.07588440924882889,
+      "learning_rate": 0.00018179293607667178,
+      "loss": 5.7824,
+      "step": 116
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.05357549712061882,
+      "learning_rate": 0.00018142390996528994,
+      "loss": 5.6497,
+      "step": 117
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.07835177332162857,
+      "learning_rate": 0.0001810515639920135,
+      "loss": 5.823,
+      "step": 118
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.05335072800517082,
+      "learning_rate": 0.00018067591333834383,
+      "loss": 5.6614,
+      "step": 119
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0556107759475708,
+      "learning_rate": 0.00018029697332052277,
+      "loss": 5.735,
+      "step": 120
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.05811074376106262,
+      "learning_rate": 0.0001799147593889079,
+      "loss": 5.5866,
+      "step": 121
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06357719749212265,
+      "learning_rate": 0.00017952928712734268,
+      "loss": 5.6589,
+      "step": 122
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.07032563537359238,
+      "learning_rate": 0.000179140572252521,
+      "loss": 5.5309,
+      "step": 123
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06277754157781601,
+      "learning_rate": 0.00017874863061334657,
+      "loss": 5.6021,
+      "step": 124
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.0650109127163887,
+      "learning_rate": 0.00017835347819028643,
+      "loss": 5.7339,
+      "step": 125
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.07425089180469513,
+      "learning_rate": 0.00017795513109471954,
+      "loss": 5.5569,
+      "step": 126
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.05482316017150879,
+      "learning_rate": 0.0001775536055682799,
+      "loss": 5.7093,
+      "step": 127
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.04600892961025238,
+      "learning_rate": 0.0001771489179821943,
+      "loss": 5.5416,
+      "step": 128
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 5.278008937835693,
+      "eval_runtime": 118.0858,
+      "eval_samples_per_second": 14.354,
+      "eval_steps_per_second": 2.058,
+      "step": 128
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.046527788043022156,
+      "learning_rate": 0.0001767410848366148,
+      "loss": 5.61,
+      "step": 129
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.050605978816747665,
+      "learning_rate": 0.000176330122759946,
+      "loss": 5.4324,
+      "step": 130
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.04772460088133812,
+      "learning_rate": 0.00017591604850816705,
+      "loss": 5.5366,
+      "step": 131
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.06192879006266594,
+      "learning_rate": 0.00017549887896414851,
+      "loss": 5.6139,
+      "step": 132
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1338934600353241,
+      "learning_rate": 0.0001750786311369639,
+      "loss": 5.7635,
+      "step": 133
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.07604615390300751,
+      "learning_rate": 0.00017465532216119625,
+      "loss": 5.8955,
+      "step": 134
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.050154052674770355,
+      "learning_rate": 0.00017422896929623959,
+      "loss": 5.5455,
+      "step": 135
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.057466309517621994,
+      "learning_rate": 0.00017379958992559493,
+      "loss": 5.7089,
+      "step": 136
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.055996015667915344,
+      "learning_rate": 0.00017336720155616185,
+      "loss": 5.6818,
+      "step": 137
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.07138606905937195,
+      "learning_rate": 0.0001729318218175245,
+      "loss": 5.6629,
+      "step": 138
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.07406231015920639,
+      "learning_rate": 0.0001724934684612328,
+      "loss": 5.5892,
+      "step": 139
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06853732466697693,
+      "learning_rate": 0.0001720521593600787,
+      "loss": 5.4891,
+      "step": 140
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.04835648089647293,
+      "learning_rate": 0.00017160791250736752,
+      "loss": 5.5121,
+      "step": 141
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.05019184201955795,
+      "learning_rate": 0.00017116074601618417,
+      "loss": 5.7229,
+      "step": 142
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04837877303361893,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.7613,
+      "step": 143
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04546854645013809,
+      "learning_rate": 0.00017025772716520323,
+      "loss": 5.5808,
+      "step": 144
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.053208645433187485,
+      "learning_rate": 0.000169801911623803,
+      "loss": 5.5359,
+      "step": 145
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.04370814561843872,
+      "learning_rate": 0.00016934325007922417,
+      "loss": 5.6874,
+      "step": 146
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.03918847441673279,
+      "learning_rate": 0.00016888176123227577,
+      "loss": 5.4949,
+      "step": 147
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.07932115346193314,
+      "learning_rate": 0.00016841746389904304,
+      "loss": 5.8311,
+      "step": 148
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.049384649842977524,
+      "learning_rate": 0.00016795037701012057,
+      "loss": 5.763,
+      "step": 149
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.04727654159069061,
+      "learning_rate": 0.00016748051960984022,
+      "loss": 5.7183,
+      "step": 150
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.04280374199151993,
+      "learning_rate": 0.00016700791085549473,
+      "loss": 5.4721,
+      "step": 151
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.08193852752447128,
+      "learning_rate": 0.00016653257001655652,
+      "loss": 5.4723,
+      "step": 152
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.058386653661727905,
+      "learning_rate": 0.00016605451647389236,
+      "loss": 5.5226,
+      "step": 153
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.05409287288784981,
+      "learning_rate": 0.00016557376971897266,
+      "loss": 5.7237,
+      "step": 154
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.03722846135497093,
+      "learning_rate": 0.00016509034935307715,
+      "loss": 5.6341,
+      "step": 155
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.07390096038579941,
+      "learning_rate": 0.00016460427508649546,
+      "loss": 5.7795,
+      "step": 156
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.038613855838775635,
+      "learning_rate": 0.00016411556673772364,
+      "loss": 5.4934,
+      "step": 157
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.052825428545475006,
+      "learning_rate": 0.00016362424423265598,
+      "loss": 5.3813,
+      "step": 158
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.035356536507606506,
+      "learning_rate": 0.00016313032760377271,
+      "loss": 5.5633,
+      "step": 159
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.038892149925231934,
+      "learning_rate": 0.00016263383698932306,
+      "loss": 5.4557,
+      "step": 160
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.043012477457523346,
+      "learning_rate": 0.00016213479263250434,
+      "loss": 5.4882,
+      "step": 161
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.03944695368409157,
+      "learning_rate": 0.00016163321488063637,
+      "loss": 5.5918,
+      "step": 162
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06338631361722946,
+      "learning_rate": 0.00016112912418433218,
+      "loss": 5.5623,
+      "step": 163
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.047581642866134644,
+      "learning_rate": 0.0001606225410966638,
+      "loss": 5.6071,
+      "step": 164
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.035596996545791626,
+      "learning_rate": 0.00016011348627232463,
+      "loss": 5.4562,
+      "step": 165
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.041574880480766296,
+      "learning_rate": 0.000159601980466787,
+      "loss": 5.5685,
+      "step": 166
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.07232942432165146,
+      "learning_rate": 0.00015908804453545607,
+      "loss": 5.6704,
+      "step": 167
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04852332919836044,
+      "learning_rate": 0.00015857169943281948,
+      "loss": 5.3836,
+      "step": 168
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04303191974759102,
+      "learning_rate": 0.000158052966211593,
+      "loss": 5.5911,
+      "step": 169
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04516925662755966,
+      "learning_rate": 0.00015753186602186209,
+      "loss": 5.532,
+      "step": 170
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.05235312879085541,
+      "learning_rate": 0.00015700842011021955,
+      "loss": 5.6902,
+      "step": 171
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.04326900467276573,
+      "learning_rate": 0.00015648264981889934,
+      "loss": 5.6425,
+      "step": 172
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.04079822823405266,
+      "learning_rate": 0.00015595457658490643,
+      "loss": 5.619,
+      "step": 173
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0557156540453434,
+      "learning_rate": 0.0001554242219391425,
+      "loss": 5.352,
+      "step": 174
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.06979982554912567,
+      "learning_rate": 0.00015489160750552832,
+      "loss": 5.7106,
+      "step": 175
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.05179354175925255,
+      "learning_rate": 0.00015435675500012212,
+      "loss": 5.7409,
+      "step": 176
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.04983863607048988,
+      "learning_rate": 0.0001538196862302339,
+      "loss": 5.6446,
+      "step": 177
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.040575865656137466,
+      "learning_rate": 0.00015328042309353657,
+      "loss": 5.6534,
+      "step": 178
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0419522225856781,
+      "learning_rate": 0.00015273898757717293,
+      "loss": 5.7551,
+      "step": 179
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0641922652721405,
+      "learning_rate": 0.00015219540175685938,
+      "loss": 5.6773,
+      "step": 180
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.07758746296167374,
+      "learning_rate": 0.00015164968779598557,
+      "loss": 5.3518,
+      "step": 181
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.036839358508586884,
+      "learning_rate": 0.00015110186794471103,
+      "loss": 5.6357,
+      "step": 182
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.03718819469213486,
+      "learning_rate": 0.00015055196453905788,
+      "loss": 5.5973,
+      "step": 183
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.04714547097682953,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.5771,
+      "step": 184
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.04743782430887222,
+      "learning_rate": 0.00014944599683254902,
+      "loss": 5.5583,
+      "step": 185
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.03646031394600868,
+      "learning_rate": 0.0001488899776248367,
+      "loss": 5.5805,
+      "step": 186
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.03820512071251869,
+      "learning_rate": 0.00014833196504719388,
+      "loss": 5.6603,
+      "step": 187
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0345190055668354,
+      "learning_rate": 0.0001477719818512263,
+      "loss": 5.5955,
+      "step": 188
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.04769587889313698,
+      "learning_rate": 0.00014721005086888676,
+      "loss": 5.6999,
+      "step": 189
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0692368894815445,
+      "learning_rate": 0.00014664619501154443,
+      "loss": 5.4506,
+      "step": 190
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03599226102232933,
+      "learning_rate": 0.0001460804372690505,
+      "loss": 5.4122,
+      "step": 191
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03820048272609711,
+      "learning_rate": 0.0001455128007088009,
+      "loss": 5.4282,
+      "step": 192
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 5.192940711975098,
+      "eval_runtime": 118.1006,
+      "eval_samples_per_second": 14.352,
+      "eval_steps_per_second": 2.058,
+      "step": 192
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03974439203739166,
+      "learning_rate": 0.0001449433084747958,
+      "loss": 5.4563,
+      "step": 193
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.034280966967344284,
+      "learning_rate": 0.00014437198378669598,
+      "loss": 5.4544,
+      "step": 194
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.048673514276742935,
+      "learning_rate": 0.00014379884993887606,
+      "loss": 5.5972,
+      "step": 195
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.0692707970738411,
+      "learning_rate": 0.00014322393029947468,
+      "loss": 5.6211,
+      "step": 196
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.04898356273770332,
+      "learning_rate": 0.000142647248309442,
+      "loss": 5.3995,
+      "step": 197
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.058041736483573914,
+      "learning_rate": 0.0001420688274815834,
+      "loss": 5.4633,
+      "step": 198
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.036273758858442307,
+      "learning_rate": 0.0001414886913996015,
+      "loss": 5.5174,
+      "step": 199
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.08915985375642776,
+      "learning_rate": 0.00014090686371713402,
+      "loss": 5.7644,
+      "step": 200
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.03881510719656944,
+      "learning_rate": 0.00014032336815678956,
+      "loss": 5.3306,
+      "step": 201
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.03407745435833931,
+      "learning_rate": 0.00013973822850918055,
+      "loss": 5.3793,
+      "step": 202
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.04425397515296936,
+      "learning_rate": 0.00013915146863195291,
+      "loss": 5.5079,
+      "step": 203
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03599456697702408,
+      "learning_rate": 0.0001385631124488136,
+      "loss": 5.6079,
+      "step": 204
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06741538643836975,
+      "learning_rate": 0.00013797318394855496,
+      "loss": 5.4523,
+      "step": 205
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.04686039686203003,
+      "learning_rate": 0.00013738170718407687,
+      "loss": 5.3534,
+      "step": 206
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.03939492255449295,
+      "learning_rate": 0.00013678870627140585,
+      "loss": 5.39,
+      "step": 207
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.03362642973661423,
+      "learning_rate": 0.00013619420538871178,
+      "loss": 5.4704,
+      "step": 208
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.04307378828525543,
+      "learning_rate": 0.00013559822877532232,
+      "loss": 5.3642,
+      "step": 209
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.05713765695691109,
+      "learning_rate": 0.00013500080073073435,
+      "loss": 5.6962,
+      "step": 210
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0568612739443779,
+      "learning_rate": 0.0001344019456136234,
+      "loss": 5.6521,
+      "step": 211
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.03639932721853256,
+      "learning_rate": 0.00013380168784085027,
+      "loss": 5.4487,
+      "step": 212
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.03534509986639023,
+      "learning_rate": 0.00013320005188646587,
+      "loss": 5.4749,
+      "step": 213
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.03920762613415718,
+      "learning_rate": 0.00013259706228071285,
+      "loss": 5.5691,
+      "step": 214
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0338614359498024,
+      "learning_rate": 0.00013199274360902588,
+      "loss": 5.4251,
+      "step": 215
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.04901224374771118,
+      "learning_rate": 0.0001313871205110291,
+      "loss": 5.6354,
+      "step": 216
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.042758435010910034,
+      "learning_rate": 0.00013078021767953124,
+      "loss": 5.5125,
+      "step": 217
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.035222314298152924,
+      "learning_rate": 0.00013017205985951926,
+      "loss": 5.4903,
+      "step": 218
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.06844358146190643,
+      "learning_rate": 0.0001295626718471491,
+      "loss": 5.6841,
+      "step": 219
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.033597927540540695,
+      "learning_rate": 0.00012895207848873487,
+      "loss": 5.3933,
+      "step": 220
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.05063093453645706,
+      "learning_rate": 0.0001283403046797357,
+      "loss": 5.4618,
+      "step": 221
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.03585563227534294,
+      "learning_rate": 0.0001277273753637408,
+      "loss": 5.4886,
+      "step": 222
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.04604891687631607,
+      "learning_rate": 0.00012711331553145222,
+      "loss": 5.67,
+      "step": 223
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.034121155738830566,
+      "learning_rate": 0.0001264981502196662,
+      "loss": 5.4705,
+      "step": 224
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.04434522986412048,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 5.4958,
+      "step": 225
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.030158868059515953,
+      "learning_rate": 0.00012526460352912995,
+      "loss": 5.5153,
+      "step": 226
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0346997007727623,
+      "learning_rate": 0.00012464627244524593,
+      "loss": 5.5369,
+      "step": 227
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.08054299652576447,
+      "learning_rate": 0.00012402693646954607,
+      "loss": 5.8509,
+      "step": 228
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.05208098143339157,
+      "learning_rate": 0.0001234066208539485,
+      "loss": 5.3976,
+      "step": 229
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.062221452593803406,
+      "learning_rate": 0.00012278535089031378,
+      "loss": 5.2981,
+      "step": 230
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.040150679647922516,
+      "learning_rate": 0.0001221631519094136,
+      "loss": 5.6089,
+      "step": 231
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.05412865802645683,
+      "learning_rate": 0.00012154004927989815,
+      "loss": 5.4375,
+      "step": 232
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.038796316832304,
+      "learning_rate": 0.00012091606840726169,
+      "loss": 5.5065,
+      "step": 233
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0440991073846817,
+      "learning_rate": 0.00012029123473280668,
+      "loss": 5.522,
+      "step": 234
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.054540976881980896,
+      "learning_rate": 0.00011966557373260654,
+      "loss": 5.3513,
+      "step": 235
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.04210669547319412,
+      "learning_rate": 0.00011903911091646684,
+      "loss": 5.5149,
+      "step": 236
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.05175742134451866,
+      "learning_rate": 0.00011841187182688526,
+      "loss": 5.4831,
+      "step": 237
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.04814860597252846,
+      "learning_rate": 0.00011778388203801018,
+      "loss": 5.441,
+      "step": 238
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.03201444074511528,
+      "learning_rate": 0.00011715516715459785,
+      "loss": 5.3987,
+      "step": 239
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.036201510578393936,
+      "learning_rate": 0.0001165257528109685,
+      "loss": 5.4906,
+      "step": 240
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.062432534992694855,
+      "learning_rate": 0.00011589566466996123,
+      "loss": 5.5572,
+      "step": 241
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.03997960314154625,
+      "learning_rate": 0.00011526492842188745,
+      "loss": 5.3745,
+      "step": 242
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.06984079629182816,
+      "learning_rate": 0.00011463356978348371,
+      "loss": 5.4129,
+      "step": 243
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07232825458049774,
+      "learning_rate": 0.00011400161449686293,
+      "loss": 5.518,
+      "step": 244
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.06185632199048996,
+      "learning_rate": 0.00011336908832846484,
+      "loss": 5.6377,
+      "step": 245
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.033329036086797714,
+      "learning_rate": 0.0001127360170680057,
+      "loss": 5.4242,
+      "step": 246
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.03494875878095627,
+      "learning_rate": 0.00011210242652742631,
+      "loss": 5.3739,
+      "step": 247
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.03172081336379051,
+      "learning_rate": 0.00011146834253984006,
+      "loss": 5.4698,
+      "step": 248
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.04552210494875908,
+      "learning_rate": 0.00011083379095847932,
+      "loss": 5.5625,
+      "step": 249
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.051661595702171326,
+      "learning_rate": 0.00011019879765564153,
+      "loss": 5.3063,
+      "step": 250
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.04173550382256508,
+      "learning_rate": 0.00010956338852163424,
+      "loss": 5.4449,
+      "step": 251
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.036143746227025986,
+      "learning_rate": 0.00010892758946371944,
+      "loss": 5.4327,
+      "step": 252
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.054287999868392944,
+      "learning_rate": 0.00010829142640505738,
+      "loss": 5.6596,
+      "step": 253
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.0568251796066761,
+      "learning_rate": 0.0001076549252836496,
+      "loss": 5.3534,
+      "step": 254
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.05703786015510559,
+      "learning_rate": 0.00010701811205128113,
+      "loss": 5.2521,
+      "step": 255
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03435615077614784,
+      "learning_rate": 0.00010638101267246283,
+      "loss": 5.4864,
+      "step": 256
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.141561985015869,
+      "eval_runtime": 117.9745,
+      "eval_samples_per_second": 14.368,
+      "eval_steps_per_second": 2.06,
+      "step": 256
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 256,
+  "total_flos": 1.8895499024347955e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-256/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e6a8e7b42c6d0fb444438c2b307f3df9d33555640360e342822219fc0d61dd
+size 5624

checkpoint-512/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: JY623/KoSOLAR-v2.0
+---
+
+# 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 0.9.0

checkpoint-512/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "JY623/KoSOLAR-v2.0",
+  "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",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-512/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026b4b01d6c8d0f64be12250de7235ff6b68844ea37fc9d7ec27cffd41294ca1
+size 503407240

checkpoint-512/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30923eddaeef757dc977bf16020a90165a352919020f588bbf847f692144f769
+size 1007047506

checkpoint-512/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aca24750f48200a87ade3859b2ab99820630d3bbd75498550c4e4491bb28ae3
+size 15728

checkpoint-512/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a229a9978fb8b0fde58150b3e0f2464e90e90726231250ef4798e390729452ce
+size 15728

checkpoint-512/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ccc60a3c39cf97130f52ba6dd040950e7cefcbae22607df50f8d3065197298
+size 15728

checkpoint-512/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf6d92dba06a976529e5e7f6dea3a26793b929ae2237542a621e0c8fa4ebfbc
+size 15728

checkpoint-512/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b468fb3f5d5a8b9b6f263c5e91a161c96aa60826fff094f4e57334d3a2e68c
+size 15728

checkpoint-512/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366cdc406945d1e0e09173a4043bf03d54694775bd9d544bc9ae8e989eed1f1d
+size 15728

checkpoint-512/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90412299ca2827f92e036dbe5599cf5b0a30f7ff6f4574b5875cd9f38b53c722
+size 15728

checkpoint-512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998c68294c0641c309afd5886c0764953f86fe35026abbefbad217062c3ece3e
+size 1064

checkpoint-512/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-512/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-512/trainer_state.json

@@ -0,0 +1,3677 @@
+{
+  "best_metric": 5.141561985015869,
+  "best_model_checkpoint": "./qlora-out/v1.2/checkpoint-256",
+  "epoch": 1.9853515625,
+  "eval_steps": 64,
+  "global_step": 512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.009024755097925663,
+      "learning_rate": 1e-05,
+      "loss": 13.4775,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 13.432984352111816,
+      "eval_runtime": 117.1907,
+      "eval_samples_per_second": 14.464,
+      "eval_steps_per_second": 2.074,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.008986919187009335,
+      "learning_rate": 2e-05,
+      "loss": 13.4709,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.008954666554927826,
+      "learning_rate": 3e-05,
+      "loss": 13.4803,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.009628714993596077,
+      "learning_rate": 4e-05,
+      "loss": 13.4636,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.010959964245557785,
+      "learning_rate": 5e-05,
+      "loss": 13.435,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.01327170804142952,
+      "learning_rate": 6e-05,
+      "loss": 13.4603,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.016410112380981445,
+      "learning_rate": 7e-05,
+      "loss": 13.459,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.020337102934718132,
+      "learning_rate": 8e-05,
+      "loss": 13.4504,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.025200409814715385,
+      "learning_rate": 9e-05,
+      "loss": 13.4827,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.03093448095023632,
+      "learning_rate": 0.0001,
+      "loss": 13.441,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.03790152817964554,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 13.4603,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.04524616152048111,
+      "learning_rate": 0.00012,
+      "loss": 13.4387,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.054408054798841476,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 13.4697,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.06374166905879974,
+      "learning_rate": 0.00014,
+      "loss": 13.4468,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.07343802601099014,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 13.3862,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.08400653302669525,
+      "learning_rate": 0.00016,
+      "loss": 13.3262,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.09511911123991013,
+      "learning_rate": 0.00017,
+      "loss": 13.2573,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.10723020881414413,
+      "learning_rate": 0.00018,
+      "loss": 13.2185,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.12024787068367004,
+      "learning_rate": 0.00019,
+      "loss": 13.1834,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.13525475561618805,
+      "learning_rate": 0.0002,
+      "loss": 13.1029,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.14704181253910065,
+      "learning_rate": 0.0001999979613716069,
+      "loss": 13.0303,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16100184619426727,
+      "learning_rate": 0.00019999184556954776,
+      "loss": 12.9015,
+      "step": 22
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.17425554990768433,
+      "learning_rate": 0.00019998165284317945,
+      "loss": 12.8389,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.18788361549377441,
+      "learning_rate": 0.00019996738360808565,
+      "loss": 12.7146,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.20275714993476868,
+      "learning_rate": 0.00019994903844605972,
+      "loss": 12.5686,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.21356578171253204,
+      "learning_rate": 0.000199926618105081,
+      "loss": 12.4685,
+      "step": 26
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2230716049671173,
+      "learning_rate": 0.0001999001234992844,
+      "loss": 12.33,
+      "step": 27
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2376524955034256,
+      "learning_rate": 0.000199869555708923,
+      "loss": 12.1648,
+      "step": 28
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2519569396972656,
+      "learning_rate": 0.0001998349159803241,
+      "loss": 12.0116,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.257049024105072,
+      "learning_rate": 0.00019979620572583846,
+      "loss": 11.8535,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.27328285574913025,
+      "learning_rate": 0.00019975342652378246,
+      "loss": 11.6906,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2857399880886078,
+      "learning_rate": 0.00019970658011837404,
+      "loss": 11.4716,
+      "step": 32
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2988531291484833,
+      "learning_rate": 0.0001996556684196615,
+      "loss": 11.3095,
+      "step": 33
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.316837877035141,
+      "learning_rate": 0.00019960069350344548,
+      "loss": 11.0641,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3310101628303528,
+      "learning_rate": 0.0001995416576111945,
+      "loss": 10.8383,
+      "step": 35
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3369371294975281,
+      "learning_rate": 0.00019947856314995349,
+      "loss": 10.6568,
+      "step": 36
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3535173535346985,
+      "learning_rate": 0.00019941141269224564,
+      "loss": 10.3978,
+      "step": 37
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3756394684314728,
+      "learning_rate": 0.0001993402089759675,
+      "loss": 10.1159,
+      "step": 38
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.38187795877456665,
+      "learning_rate": 0.00019926495490427753,
+      "loss": 9.879,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.39641591906547546,
+      "learning_rate": 0.0001991856535454774,
+      "loss": 9.5833,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.40500307083129883,
+      "learning_rate": 0.00019910230813288712,
+      "loss": 9.3309,
+      "step": 41
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.42996540665626526,
+      "learning_rate": 0.00019901492206471325,
+      "loss": 8.8893,
+      "step": 42
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.41511279344558716,
+      "learning_rate": 0.00019892349890391015,
+      "loss": 8.597,
+      "step": 43
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.35860675573349,
+      "learning_rate": 0.00019882804237803488,
+      "loss": 8.4768,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3302132785320282,
+      "learning_rate": 0.00019872855637909504,
+      "loss": 8.3176,
+      "step": 45
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.43532317876815796,
+      "learning_rate": 0.00019862504496339037,
+      "loss": 8.1118,
+      "step": 46
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6842054724693298,
+      "learning_rate": 0.000198517512351347,
+      "loss": 8.1977,
+      "step": 47
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8128633499145508,
+      "learning_rate": 0.0001984059629273457,
+      "loss": 8.1527,
+      "step": 48
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8130613565444946,
+      "learning_rate": 0.00019829040123954297,
+      "loss": 8.0821,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7518128752708435,
+      "learning_rate": 0.00019817083199968552,
+      "loss": 7.8393,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5997517108917236,
+      "learning_rate": 0.00019804726008291828,
+      "loss": 7.557,
+      "step": 51
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.42999598383903503,
+      "learning_rate": 0.00019791969052758562,
+      "loss": 7.5165,
+      "step": 52
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.3002629578113556,
+      "learning_rate": 0.00019778812853502592,
+      "loss": 7.3037,
+      "step": 53
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.24435582756996155,
+      "learning_rate": 0.00019765257946935944,
+      "loss": 7.3316,
+      "step": 54
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2515851855278015,
+      "learning_rate": 0.00019751304885726967,
+      "loss": 7.1767,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2763000726699829,
+      "learning_rate": 0.00019736954238777792,
+      "loss": 7.0993,
+      "step": 56
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2830991744995117,
+      "learning_rate": 0.00019722206591201146,
+      "loss": 7.1805,
+      "step": 57
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.30122554302215576,
+      "learning_rate": 0.00019707062544296498,
+      "loss": 7.0762,
+      "step": 58
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.3070628046989441,
+      "learning_rate": 0.0001969152271552552,
+      "loss": 7.1017,
+      "step": 59
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.30436331033706665,
+      "learning_rate": 0.00019675587738486936,
+      "loss": 7.3221,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2854003608226776,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 6.9803,
+      "step": 61
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.27880895137786865,
+      "learning_rate": 0.0001964253495453141,
+      "loss": 6.7288,
+      "step": 62
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2640041410923004,
+      "learning_rate": 0.00019625418495261343,
+      "loss": 6.8195,
+      "step": 63
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2415798306465149,
+      "learning_rate": 0.00019607909582962477,
+      "loss": 6.9219,
+      "step": 64
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 6.202152252197266,
+      "eval_runtime": 118.0179,
+      "eval_samples_per_second": 14.362,
+      "eval_steps_per_second": 2.059,
+      "step": 64
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.18691398203372955,
+      "learning_rate": 0.0001959000893151813,
+      "loss": 6.6136,
+      "step": 65
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.15952067077159882,
+      "learning_rate": 0.00019571717270783828,
+      "loss": 6.4341,
+      "step": 66
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14711293578147888,
+      "learning_rate": 0.00019553035346557543,
+      "loss": 6.414,
+      "step": 67
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1670265942811966,
+      "learning_rate": 0.00019533963920549306,
+      "loss": 6.4894,
+      "step": 68
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2034294307231903,
+      "learning_rate": 0.00019514503770350127,
+      "loss": 6.3448,
+      "step": 69
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.22955259680747986,
+      "learning_rate": 0.00019494655689400293,
+      "loss": 6.3133,
+      "step": 70
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2635420262813568,
+      "learning_rate": 0.00019474420486957042,
+      "loss": 6.3256,
+      "step": 71
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.26006290316581726,
+      "learning_rate": 0.00019453798988061535,
+      "loss": 6.4601,
+      "step": 72
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.22863267362117767,
+      "learning_rate": 0.0001943279203350523,
+      "loss": 6.1397,
+      "step": 73
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.18543188273906708,
+      "learning_rate": 0.00019411400479795617,
+      "loss": 6.5625,
+      "step": 74
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.14754259586334229,
+      "learning_rate": 0.00019389625199121263,
+      "loss": 6.2912,
+      "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12668511271476746,
+      "learning_rate": 0.00019367467079316279,
+      "loss": 6.2679,
+      "step": 76
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1176210567355156,
+      "learning_rate": 0.0001934492702382411,
+      "loss": 6.2426,
+      "step": 77
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12420424073934555,
+      "learning_rate": 0.00019322005951660697,
+      "loss": 6.3293,
+      "step": 78
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1415456086397171,
+      "learning_rate": 0.00019298704797377013,
+      "loss": 6.0938,
+      "step": 79
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1544170081615448,
+      "learning_rate": 0.0001927502451102095,
+      "loss": 6.1926,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14980632066726685,
+      "learning_rate": 0.00019250966058098588,
+      "loss": 6.1425,
+      "step": 81
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13148672878742218,
+      "learning_rate": 0.00019226530419534833,
+      "loss": 6.0866,
+      "step": 82
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14052827656269073,
+      "learning_rate": 0.00019201718591633417,
+      "loss": 6.1682,
+      "step": 83
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1245439425110817,
+      "learning_rate": 0.0001917653158603628,
+      "loss": 6.0281,
+      "step": 84
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1110084131360054,
+      "learning_rate": 0.00019150970429682314,
+      "loss": 6.0577,
+      "step": 85
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.08920083940029144,
+      "learning_rate": 0.000191250361647655,
+      "loss": 6.0772,
+      "step": 86
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.09026093780994415,
+      "learning_rate": 0.0001909872984869242,
+      "loss": 6.2326,
+      "step": 87
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.11133856326341629,
+      "learning_rate": 0.00019072052554039122,
+      "loss": 5.8261,
+      "step": 88
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.11304065585136414,
+      "learning_rate": 0.00019045005368507418,
+      "loss": 6.3169,
+      "step": 89
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.10704243183135986,
+      "learning_rate": 0.00019017589394880515,
+      "loss": 5.9967,
+      "step": 90
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1576884537935257,
+      "learning_rate": 0.0001898980575097806,
+      "loss": 5.7186,
+      "step": 91
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.12191645801067352,
+      "learning_rate": 0.00018961655569610557,
+      "loss": 5.8001,
+      "step": 92
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1100529134273529,
+      "learning_rate": 0.00018933139998533188,
+      "loss": 5.9882,
+      "step": 93
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.10520044714212418,
+      "learning_rate": 0.00018904260200399006,
+      "loss": 5.8127,
+      "step": 94
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.08245933800935745,
+      "learning_rate": 0.00018875017352711545,
+      "loss": 6.0165,
+      "step": 95
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.07817509770393372,
+      "learning_rate": 0.00018845412647776794,
+      "loss": 5.9087,
+      "step": 96
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.07296270877122879,
+      "learning_rate": 0.00018815447292654596,
+      "loss": 5.8837,
+      "step": 97
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.077950619161129,
+      "learning_rate": 0.00018785122509109426,
+      "loss": 5.9915,
+      "step": 98
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.09345076233148575,
+      "learning_rate": 0.00018754439533560574,
+      "loss": 5.9908,
+      "step": 99
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.10249783098697662,
+      "learning_rate": 0.00018723399617031751,
+      "loss": 6.0887,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.11731438338756561,
+      "learning_rate": 0.00018692004025100054,
+      "loss": 6.0414,
+      "step": 101
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.06663200259208679,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 5.881,
+      "step": 102
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07221497595310211,
+      "learning_rate": 0.00018628150949793261,
+      "loss": 5.6574,
+      "step": 103
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.061096612364053726,
+      "learning_rate": 0.00018595696069872013,
+      "loss": 5.8519,
+      "step": 104
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.06478705257177353,
+      "learning_rate": 0.00018562890721349434,
+      "loss": 5.7816,
+      "step": 105
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.06368556618690491,
+      "learning_rate": 0.00018529736241783824,
+      "loss": 5.872,
+      "step": 106
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07194569706916809,
+      "learning_rate": 0.00018496233982968457,
+      "loss": 5.9662,
+      "step": 107
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07953158766031265,
+      "learning_rate": 0.00018462385310876443,
+      "loss": 5.783,
+      "step": 108
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.06713347882032394,
+      "learning_rate": 0.00018428191605605068,
+      "loss": 5.8917,
+      "step": 109
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.06519600003957748,
+      "learning_rate": 0.000183936542613195,
+      "loss": 5.797,
+      "step": 110
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0615142360329628,
+      "learning_rate": 0.00018358774686195954,
+      "loss": 5.8417,
+      "step": 111
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.07100021839141846,
+      "learning_rate": 0.00018323554302364272,
+      "loss": 5.6852,
+      "step": 112
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.08909253031015396,
+      "learning_rate": 0.00018287994545849946,
+      "loss": 5.7358,
+      "step": 113
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.052479445934295654,
+      "learning_rate": 0.00018252096866515558,
+      "loss": 5.7226,
+      "step": 114
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.05653544142842293,
+      "learning_rate": 0.00018215862728001677,
+      "loss": 5.6749,
+      "step": 115
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.07588440924882889,
+      "learning_rate": 0.00018179293607667178,
+      "loss": 5.7824,
+      "step": 116
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.05357549712061882,
+      "learning_rate": 0.00018142390996528994,
+      "loss": 5.6497,
+      "step": 117
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.07835177332162857,
+      "learning_rate": 0.0001810515639920135,
+      "loss": 5.823,
+      "step": 118
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.05335072800517082,
+      "learning_rate": 0.00018067591333834383,
+      "loss": 5.6614,
+      "step": 119
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0556107759475708,
+      "learning_rate": 0.00018029697332052277,
+      "loss": 5.735,
+      "step": 120
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.05811074376106262,
+      "learning_rate": 0.0001799147593889079,
+      "loss": 5.5866,
+      "step": 121
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06357719749212265,
+      "learning_rate": 0.00017952928712734268,
+      "loss": 5.6589,
+      "step": 122
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.07032563537359238,
+      "learning_rate": 0.000179140572252521,
+      "loss": 5.5309,
+      "step": 123
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06277754157781601,
+      "learning_rate": 0.00017874863061334657,
+      "loss": 5.6021,
+      "step": 124
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.0650109127163887,
+      "learning_rate": 0.00017835347819028643,
+      "loss": 5.7339,
+      "step": 125
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.07425089180469513,
+      "learning_rate": 0.00017795513109471954,
+      "loss": 5.5569,
+      "step": 126
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.05482316017150879,
+      "learning_rate": 0.0001775536055682799,
+      "loss": 5.7093,
+      "step": 127
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.04600892961025238,
+      "learning_rate": 0.0001771489179821943,
+      "loss": 5.5416,
+      "step": 128
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 5.278008937835693,
+      "eval_runtime": 118.0858,
+      "eval_samples_per_second": 14.354,
+      "eval_steps_per_second": 2.058,
+      "step": 128
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.046527788043022156,
+      "learning_rate": 0.0001767410848366148,
+      "loss": 5.61,
+      "step": 129
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.050605978816747665,
+      "learning_rate": 0.000176330122759946,
+      "loss": 5.4324,
+      "step": 130
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.04772460088133812,
+      "learning_rate": 0.00017591604850816705,
+      "loss": 5.5366,
+      "step": 131
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.06192879006266594,
+      "learning_rate": 0.00017549887896414851,
+      "loss": 5.6139,
+      "step": 132
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1338934600353241,
+      "learning_rate": 0.0001750786311369639,
+      "loss": 5.7635,
+      "step": 133
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.07604615390300751,
+      "learning_rate": 0.00017465532216119625,
+      "loss": 5.8955,
+      "step": 134
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.050154052674770355,
+      "learning_rate": 0.00017422896929623959,
+      "loss": 5.5455,
+      "step": 135
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.057466309517621994,
+      "learning_rate": 0.00017379958992559493,
+      "loss": 5.7089,
+      "step": 136
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.055996015667915344,
+      "learning_rate": 0.00017336720155616185,
+      "loss": 5.6818,
+      "step": 137
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.07138606905937195,
+      "learning_rate": 0.0001729318218175245,
+      "loss": 5.6629,
+      "step": 138
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.07406231015920639,
+      "learning_rate": 0.0001724934684612328,
+      "loss": 5.5892,
+      "step": 139
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06853732466697693,
+      "learning_rate": 0.0001720521593600787,
+      "loss": 5.4891,
+      "step": 140
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.04835648089647293,
+      "learning_rate": 0.00017160791250736752,
+      "loss": 5.5121,
+      "step": 141
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.05019184201955795,
+      "learning_rate": 0.00017116074601618417,
+      "loss": 5.7229,
+      "step": 142
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04837877303361893,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.7613,
+      "step": 143
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.04546854645013809,
+      "learning_rate": 0.00017025772716520323,
+      "loss": 5.5808,
+      "step": 144
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.053208645433187485,
+      "learning_rate": 0.000169801911623803,
+      "loss": 5.5359,
+      "step": 145
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.04370814561843872,
+      "learning_rate": 0.00016934325007922417,
+      "loss": 5.6874,
+      "step": 146
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.03918847441673279,
+      "learning_rate": 0.00016888176123227577,
+      "loss": 5.4949,
+      "step": 147
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.07932115346193314,
+      "learning_rate": 0.00016841746389904304,
+      "loss": 5.8311,
+      "step": 148
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.049384649842977524,
+      "learning_rate": 0.00016795037701012057,
+      "loss": 5.763,
+      "step": 149
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.04727654159069061,
+      "learning_rate": 0.00016748051960984022,
+      "loss": 5.7183,
+      "step": 150
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.04280374199151993,
+      "learning_rate": 0.00016700791085549473,
+      "loss": 5.4721,
+      "step": 151
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.08193852752447128,
+      "learning_rate": 0.00016653257001655652,
+      "loss": 5.4723,
+      "step": 152
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.058386653661727905,
+      "learning_rate": 0.00016605451647389236,
+      "loss": 5.5226,
+      "step": 153
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.05409287288784981,
+      "learning_rate": 0.00016557376971897266,
+      "loss": 5.7237,
+      "step": 154
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.03722846135497093,
+      "learning_rate": 0.00016509034935307715,
+      "loss": 5.6341,
+      "step": 155
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.07390096038579941,
+      "learning_rate": 0.00016460427508649546,
+      "loss": 5.7795,
+      "step": 156
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.038613855838775635,
+      "learning_rate": 0.00016411556673772364,
+      "loss": 5.4934,
+      "step": 157
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.052825428545475006,
+      "learning_rate": 0.00016362424423265598,
+      "loss": 5.3813,
+      "step": 158
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.035356536507606506,
+      "learning_rate": 0.00016313032760377271,
+      "loss": 5.5633,
+      "step": 159
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.038892149925231934,
+      "learning_rate": 0.00016263383698932306,
+      "loss": 5.4557,
+      "step": 160
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.043012477457523346,
+      "learning_rate": 0.00016213479263250434,
+      "loss": 5.4882,
+      "step": 161
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.03944695368409157,
+      "learning_rate": 0.00016163321488063637,
+      "loss": 5.5918,
+      "step": 162
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06338631361722946,
+      "learning_rate": 0.00016112912418433218,
+      "loss": 5.5623,
+      "step": 163
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.047581642866134644,
+      "learning_rate": 0.0001606225410966638,
+      "loss": 5.6071,
+      "step": 164
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.035596996545791626,
+      "learning_rate": 0.00016011348627232463,
+      "loss": 5.4562,
+      "step": 165
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.041574880480766296,
+      "learning_rate": 0.000159601980466787,
+      "loss": 5.5685,
+      "step": 166
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.07232942432165146,
+      "learning_rate": 0.00015908804453545607,
+      "loss": 5.6704,
+      "step": 167
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04852332919836044,
+      "learning_rate": 0.00015857169943281948,
+      "loss": 5.3836,
+      "step": 168
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04303191974759102,
+      "learning_rate": 0.000158052966211593,
+      "loss": 5.5911,
+      "step": 169
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.04516925662755966,
+      "learning_rate": 0.00015753186602186209,
+      "loss": 5.532,
+      "step": 170
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.05235312879085541,
+      "learning_rate": 0.00015700842011021955,
+      "loss": 5.6902,
+      "step": 171
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.04326900467276573,
+      "learning_rate": 0.00015648264981889934,
+      "loss": 5.6425,
+      "step": 172
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.04079822823405266,
+      "learning_rate": 0.00015595457658490643,
+      "loss": 5.619,
+      "step": 173
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0557156540453434,
+      "learning_rate": 0.0001554242219391425,
+      "loss": 5.352,
+      "step": 174
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.06979982554912567,
+      "learning_rate": 0.00015489160750552832,
+      "loss": 5.7106,
+      "step": 175
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.05179354175925255,
+      "learning_rate": 0.00015435675500012212,
+      "loss": 5.7409,
+      "step": 176
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.04983863607048988,
+      "learning_rate": 0.0001538196862302339,
+      "loss": 5.6446,
+      "step": 177
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.040575865656137466,
+      "learning_rate": 0.00015328042309353657,
+      "loss": 5.6534,
+      "step": 178
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0419522225856781,
+      "learning_rate": 0.00015273898757717293,
+      "loss": 5.7551,
+      "step": 179
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0641922652721405,
+      "learning_rate": 0.00015219540175685938,
+      "loss": 5.6773,
+      "step": 180
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.07758746296167374,
+      "learning_rate": 0.00015164968779598557,
+      "loss": 5.3518,
+      "step": 181
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.036839358508586884,
+      "learning_rate": 0.00015110186794471103,
+      "loss": 5.6357,
+      "step": 182
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.03718819469213486,
+      "learning_rate": 0.00015055196453905788,
+      "loss": 5.5973,
+      "step": 183
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.04714547097682953,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.5771,
+      "step": 184
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.04743782430887222,
+      "learning_rate": 0.00014944599683254902,
+      "loss": 5.5583,
+      "step": 185
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.03646031394600868,
+      "learning_rate": 0.0001488899776248367,
+      "loss": 5.5805,
+      "step": 186
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.03820512071251869,
+      "learning_rate": 0.00014833196504719388,
+      "loss": 5.6603,
+      "step": 187
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0345190055668354,
+      "learning_rate": 0.0001477719818512263,
+      "loss": 5.5955,
+      "step": 188
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.04769587889313698,
+      "learning_rate": 0.00014721005086888676,
+      "loss": 5.6999,
+      "step": 189
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0692368894815445,
+      "learning_rate": 0.00014664619501154443,
+      "loss": 5.4506,
+      "step": 190
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03599226102232933,
+      "learning_rate": 0.0001460804372690505,
+      "loss": 5.4122,
+      "step": 191
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03820048272609711,
+      "learning_rate": 0.0001455128007088009,
+      "loss": 5.4282,
+      "step": 192
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 5.192940711975098,
+      "eval_runtime": 118.1006,
+      "eval_samples_per_second": 14.352,
+      "eval_steps_per_second": 2.058,
+      "step": 192
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03974439203739166,
+      "learning_rate": 0.0001449433084747958,
+      "loss": 5.4563,
+      "step": 193
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.034280966967344284,
+      "learning_rate": 0.00014437198378669598,
+      "loss": 5.4544,
+      "step": 194
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.048673514276742935,
+      "learning_rate": 0.00014379884993887606,
+      "loss": 5.5972,
+      "step": 195
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.0692707970738411,
+      "learning_rate": 0.00014322393029947468,
+      "loss": 5.6211,
+      "step": 196
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.04898356273770332,
+      "learning_rate": 0.000142647248309442,
+      "loss": 5.3995,
+      "step": 197
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.058041736483573914,
+      "learning_rate": 0.0001420688274815834,
+      "loss": 5.4633,
+      "step": 198
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.036273758858442307,
+      "learning_rate": 0.0001414886913996015,
+      "loss": 5.5174,
+      "step": 199
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.08915985375642776,
+      "learning_rate": 0.00014090686371713402,
+      "loss": 5.7644,
+      "step": 200
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.03881510719656944,
+      "learning_rate": 0.00014032336815678956,
+      "loss": 5.3306,
+      "step": 201
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.03407745435833931,
+      "learning_rate": 0.00013973822850918055,
+      "loss": 5.3793,
+      "step": 202
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.04425397515296936,
+      "learning_rate": 0.00013915146863195291,
+      "loss": 5.5079,
+      "step": 203
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03599456697702408,
+      "learning_rate": 0.0001385631124488136,
+      "loss": 5.6079,
+      "step": 204
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06741538643836975,
+      "learning_rate": 0.00013797318394855496,
+      "loss": 5.4523,
+      "step": 205
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.04686039686203003,
+      "learning_rate": 0.00013738170718407687,
+      "loss": 5.3534,
+      "step": 206
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.03939492255449295,
+      "learning_rate": 0.00013678870627140585,
+      "loss": 5.39,
+      "step": 207
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.03362642973661423,
+      "learning_rate": 0.00013619420538871178,
+      "loss": 5.4704,
+      "step": 208
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.04307378828525543,
+      "learning_rate": 0.00013559822877532232,
+      "loss": 5.3642,
+      "step": 209
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.05713765695691109,
+      "learning_rate": 0.00013500080073073435,
+      "loss": 5.6962,
+      "step": 210
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0568612739443779,
+      "learning_rate": 0.0001344019456136234,
+      "loss": 5.6521,
+      "step": 211
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.03639932721853256,
+      "learning_rate": 0.00013380168784085027,
+      "loss": 5.4487,
+      "step": 212
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.03534509986639023,
+      "learning_rate": 0.00013320005188646587,
+      "loss": 5.4749,
+      "step": 213
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.03920762613415718,
+      "learning_rate": 0.00013259706228071285,
+      "loss": 5.5691,
+      "step": 214
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0338614359498024,
+      "learning_rate": 0.00013199274360902588,
+      "loss": 5.4251,
+      "step": 215
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.04901224374771118,
+      "learning_rate": 0.0001313871205110291,
+      "loss": 5.6354,
+      "step": 216
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.042758435010910034,
+      "learning_rate": 0.00013078021767953124,
+      "loss": 5.5125,
+      "step": 217
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.035222314298152924,
+      "learning_rate": 0.00013017205985951926,
+      "loss": 5.4903,
+      "step": 218
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.06844358146190643,
+      "learning_rate": 0.0001295626718471491,
+      "loss": 5.6841,
+      "step": 219
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.033597927540540695,
+      "learning_rate": 0.00012895207848873487,
+      "loss": 5.3933,
+      "step": 220
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.05063093453645706,
+      "learning_rate": 0.0001283403046797357,
+      "loss": 5.4618,
+      "step": 221
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.03585563227534294,
+      "learning_rate": 0.0001277273753637408,
+      "loss": 5.4886,
+      "step": 222
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.04604891687631607,
+      "learning_rate": 0.00012711331553145222,
+      "loss": 5.67,
+      "step": 223
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.034121155738830566,
+      "learning_rate": 0.0001264981502196662,
+      "loss": 5.4705,
+      "step": 224
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.04434522986412048,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 5.4958,
+      "step": 225
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.030158868059515953,
+      "learning_rate": 0.00012526460352912995,
+      "loss": 5.5153,
+      "step": 226
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0346997007727623,
+      "learning_rate": 0.00012464627244524593,
+      "loss": 5.5369,
+      "step": 227
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.08054299652576447,
+      "learning_rate": 0.00012402693646954607,
+      "loss": 5.8509,
+      "step": 228
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.05208098143339157,
+      "learning_rate": 0.0001234066208539485,
+      "loss": 5.3976,
+      "step": 229
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.062221452593803406,
+      "learning_rate": 0.00012278535089031378,
+      "loss": 5.2981,
+      "step": 230
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.040150679647922516,
+      "learning_rate": 0.0001221631519094136,
+      "loss": 5.6089,
+      "step": 231
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.05412865802645683,
+      "learning_rate": 0.00012154004927989815,
+      "loss": 5.4375,
+      "step": 232
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.038796316832304,
+      "learning_rate": 0.00012091606840726169,
+      "loss": 5.5065,
+      "step": 233
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0440991073846817,
+      "learning_rate": 0.00012029123473280668,
+      "loss": 5.522,
+      "step": 234
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.054540976881980896,
+      "learning_rate": 0.00011966557373260654,
+      "loss": 5.3513,
+      "step": 235
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.04210669547319412,
+      "learning_rate": 0.00011903911091646684,
+      "loss": 5.5149,
+      "step": 236
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.05175742134451866,
+      "learning_rate": 0.00011841187182688526,
+      "loss": 5.4831,
+      "step": 237
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.04814860597252846,
+      "learning_rate": 0.00011778388203801018,
+      "loss": 5.441,
+      "step": 238
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.03201444074511528,
+      "learning_rate": 0.00011715516715459785,
+      "loss": 5.3987,
+      "step": 239
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.036201510578393936,
+      "learning_rate": 0.0001165257528109685,
+      "loss": 5.4906,
+      "step": 240
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.062432534992694855,
+      "learning_rate": 0.00011589566466996123,
+      "loss": 5.5572,
+      "step": 241
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.03997960314154625,
+      "learning_rate": 0.00011526492842188745,
+      "loss": 5.3745,
+      "step": 242
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.06984079629182816,
+      "learning_rate": 0.00011463356978348371,
+      "loss": 5.4129,
+      "step": 243
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07232825458049774,
+      "learning_rate": 0.00011400161449686293,
+      "loss": 5.518,
+      "step": 244
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.06185632199048996,
+      "learning_rate": 0.00011336908832846484,
+      "loss": 5.6377,
+      "step": 245
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.033329036086797714,
+      "learning_rate": 0.0001127360170680057,
+      "loss": 5.4242,
+      "step": 246
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.03494875878095627,
+      "learning_rate": 0.00011210242652742631,
+      "loss": 5.3739,
+      "step": 247
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.03172081336379051,
+      "learning_rate": 0.00011146834253984006,
+      "loss": 5.4698,
+      "step": 248
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.04552210494875908,
+      "learning_rate": 0.00011083379095847932,
+      "loss": 5.5625,
+      "step": 249
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.051661595702171326,
+      "learning_rate": 0.00011019879765564153,
+      "loss": 5.3063,
+      "step": 250
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.04173550382256508,
+      "learning_rate": 0.00010956338852163424,
+      "loss": 5.4449,
+      "step": 251
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.036143746227025986,
+      "learning_rate": 0.00010892758946371944,
+      "loss": 5.4327,
+      "step": 252
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.054287999868392944,
+      "learning_rate": 0.00010829142640505738,
+      "loss": 5.6596,
+      "step": 253
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.0568251796066761,
+      "learning_rate": 0.0001076549252836496,
+      "loss": 5.3534,
+      "step": 254
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.05703786015510559,
+      "learning_rate": 0.00010701811205128113,
+      "loss": 5.2521,
+      "step": 255
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03435615077614784,
+      "learning_rate": 0.00010638101267246283,
+      "loss": 5.4864,
+      "step": 256
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.141561985015869,
+      "eval_runtime": 117.9745,
+      "eval_samples_per_second": 14.368,
+      "eval_steps_per_second": 2.06,
+      "step": 256
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03892118111252785,
+      "learning_rate": 0.00010574365312337235,
+      "loss": 5.5171,
+      "step": 257
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.03254527598619461,
+      "learning_rate": 0.00010510605939079505,
+      "loss": 5.4599,
+      "step": 258
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.04460343345999718,
+      "learning_rate": 0.00010446825747106479,
+      "loss": 5.5515,
+      "step": 259
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.038897812366485596,
+      "learning_rate": 0.00010383027336900355,
+      "loss": 5.3123,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03247852250933647,
+      "learning_rate": 0.00010319213309686144,
+      "loss": 5.4907,
+      "step": 261
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.05617564916610718,
+      "learning_rate": 0.00010255386267325602,
+      "loss": 5.4376,
+      "step": 262
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.02894892543554306,
+      "learning_rate": 0.00010191548812211142,
+      "loss": 5.4439,
+      "step": 263
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.037546053528785706,
+      "learning_rate": 0.00010127703547159739,
+      "loss": 5.3931,
+      "step": 264
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.09106461703777313,
+      "learning_rate": 0.00010063853075306793,
+      "loss": 5.6589,
+      "step": 265
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.03836290165781975,
+      "learning_rate": 0.0001,
+      "loss": 5.4115,
+      "step": 266
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.05548371374607086,
+      "learning_rate": 9.93614692469321e-05,
+      "loss": 5.4327,
+      "step": 267
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.03244495019316673,
+      "learning_rate": 9.872296452840264e-05,
+      "loss": 5.446,
+      "step": 268
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.048196546733379364,
+      "learning_rate": 9.808451187788859e-05,
+      "loss": 5.4429,
+      "step": 269
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.043303292244672775,
+      "learning_rate": 9.744613732674401e-05,
+      "loss": 5.3831,
+      "step": 270
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.029421547427773476,
+      "learning_rate": 9.68078669031386e-05,
+      "loss": 5.445,
+      "step": 271
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.052507225424051285,
+      "learning_rate": 9.616972663099647e-05,
+      "loss": 5.6058,
+      "step": 272
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.07338947057723999,
+      "learning_rate": 9.553174252893522e-05,
+      "loss": 5.6714,
+      "step": 273
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.04616468399763107,
+      "learning_rate": 9.489394060920496e-05,
+      "loss": 5.3734,
+      "step": 274
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.036514170467853546,
+      "learning_rate": 9.425634687662768e-05,
+      "loss": 5.4143,
+      "step": 275
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.05710041895508766,
+      "learning_rate": 9.361898732753716e-05,
+      "loss": 5.3507,
+      "step": 276
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.04608845338225365,
+      "learning_rate": 9.298188794871888e-05,
+      "loss": 5.7134,
+      "step": 277
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.033140767365694046,
+      "learning_rate": 9.234507471635043e-05,
+      "loss": 5.5013,
+      "step": 278
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.053405869752168655,
+      "learning_rate": 9.170857359494264e-05,
+      "loss": 5.6759,
+      "step": 279
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.05170680209994316,
+      "learning_rate": 9.107241053628059e-05,
+      "loss": 5.3689,
+      "step": 280
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.03882214426994324,
+      "learning_rate": 9.043661147836578e-05,
+      "loss": 5.3795,
+      "step": 281
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.052860137075185776,
+      "learning_rate": 8.980120234435849e-05,
+      "loss": 5.5302,
+      "step": 282
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.06640254706144333,
+      "learning_rate": 8.916620904152069e-05,
+      "loss": 5.5381,
+      "step": 283
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.043861739337444305,
+      "learning_rate": 8.853165746015997e-05,
+      "loss": 5.5606,
+      "step": 284
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.03182082995772362,
+      "learning_rate": 8.789757347257372e-05,
+      "loss": 5.4734,
+      "step": 285
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.05194887891411781,
+      "learning_rate": 8.726398293199434e-05,
+      "loss": 5.6236,
+      "step": 286
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.034338489174842834,
+      "learning_rate": 8.663091167153516e-05,
+      "loss": 5.4019,
+      "step": 287
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.05889330431818962,
+      "learning_rate": 8.599838550313713e-05,
+      "loss": 5.4263,
+      "step": 288
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.04128503426909447,
+      "learning_rate": 8.53664302165163e-05,
+      "loss": 5.4715,
+      "step": 289
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.0485406368970871,
+      "learning_rate": 8.473507157811254e-05,
+      "loss": 5.284,
+      "step": 290
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.030397815629839897,
+      "learning_rate": 8.410433533003881e-05,
+      "loss": 5.4436,
+      "step": 291
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.04625779017806053,
+      "learning_rate": 8.347424718903151e-05,
+      "loss": 5.4165,
+      "step": 292
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.086111880838871,
+      "learning_rate": 8.284483284540216e-05,
+      "loss": 5.5681,
+      "step": 293
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.08673430234193802,
+      "learning_rate": 8.221611796198985e-05,
+      "loss": 5.2608,
+      "step": 294
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.09690722823143005,
+      "learning_rate": 8.158812817311475e-05,
+      "loss": 5.8206,
+      "step": 295
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.07265935838222504,
+      "learning_rate": 8.096088908353315e-05,
+      "loss": 5.1928,
+      "step": 296
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.07043205946683884,
+      "learning_rate": 8.033442626739347e-05,
+      "loss": 5.618,
+      "step": 297
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.03906979411840439,
+      "learning_rate": 7.970876526719333e-05,
+      "loss": 5.5603,
+      "step": 298
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.056637875735759735,
+      "learning_rate": 7.908393159273836e-05,
+      "loss": 5.3759,
+      "step": 299
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.04319996014237404,
+      "learning_rate": 7.845995072010188e-05,
+      "loss": 5.4196,
+      "step": 300
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.0478227362036705,
+      "learning_rate": 7.783684809058642e-05,
+      "loss": 5.32,
+      "step": 301
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.04370150342583656,
+      "learning_rate": 7.721464910968627e-05,
+      "loss": 5.3773,
+      "step": 302
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.05833783373236656,
+      "learning_rate": 7.659337914605151e-05,
+      "loss": 5.6629,
+      "step": 303
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.047900766134262085,
+      "learning_rate": 7.597306353045393e-05,
+      "loss": 5.3259,
+      "step": 304
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.03448645770549774,
+      "learning_rate": 7.535372755475411e-05,
+      "loss": 5.3499,
+      "step": 305
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.05190582945942879,
+      "learning_rate": 7.473539647087007e-05,
+      "loss": 5.4548,
+      "step": 306
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.08470705896615982,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 5.8594,
+      "step": 307
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.026675831526517868,
+      "learning_rate": 7.350184978033386e-05,
+      "loss": 5.4803,
+      "step": 308
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.027785539627075195,
+      "learning_rate": 7.28866844685478e-05,
+      "loss": 5.5096,
+      "step": 309
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.045870471745729446,
+      "learning_rate": 7.22726246362592e-05,
+      "loss": 5.3877,
+      "step": 310
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.03886491432785988,
+      "learning_rate": 7.16596953202643e-05,
+      "loss": 5.3928,
+      "step": 311
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.039413053542375565,
+      "learning_rate": 7.104792151126515e-05,
+      "loss": 5.4992,
+      "step": 312
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.03315013647079468,
+      "learning_rate": 7.043732815285091e-05,
+      "loss": 5.5056,
+      "step": 313
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.04284488782286644,
+      "learning_rate": 6.982794014048077e-05,
+      "loss": 5.5894,
+      "step": 314
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.041594624519348145,
+      "learning_rate": 6.921978232046877e-05,
+      "loss": 5.3632,
+      "step": 315
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.044996097683906555,
+      "learning_rate": 6.861287948897091e-05,
+      "loss": 5.4832,
+      "step": 316
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.04162047058343887,
+      "learning_rate": 6.800725639097411e-05,
+      "loss": 5.4092,
+      "step": 317
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.08886846899986267,
+      "learning_rate": 6.740293771928716e-05,
+      "loss": 5.2591,
+      "step": 318
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.07054431736469269,
+      "learning_rate": 6.679994811353418e-05,
+      "loss": 5.2832,
+      "step": 319
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.03775365650653839,
+      "learning_rate": 6.619831215914974e-05,
+      "loss": 5.2877,
+      "step": 320
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 5.144121170043945,
+      "eval_runtime": 117.9665,
+      "eval_samples_per_second": 14.368,
+      "eval_steps_per_second": 2.06,
+      "step": 320
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.05343703180551529,
+      "learning_rate": 6.559805438637663e-05,
+      "loss": 5.3204,
+      "step": 321
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.05394141003489494,
+      "learning_rate": 6.499919926926566e-05,
+      "loss": 5.3675,
+      "step": 322
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.028001869097352028,
+      "learning_rate": 6.440177122467769e-05,
+      "loss": 5.4041,
+      "step": 323
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.04468236118555069,
+      "learning_rate": 6.380579461128819e-05,
+      "loss": 5.4149,
+      "step": 324
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.10019981861114502,
+      "learning_rate": 6.321129372859418e-05,
+      "loss": 5.6874,
+      "step": 325
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.04705387353897095,
+      "learning_rate": 6.261829281592314e-05,
+      "loss": 5.4054,
+      "step": 326
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.036189932376146317,
+      "learning_rate": 6.202681605144502e-05,
+      "loss": 5.2958,
+      "step": 327
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.05683156102895737,
+      "learning_rate": 6.143688755118646e-05,
+      "loss": 5.5621,
+      "step": 328
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.09604857116937637,
+      "learning_rate": 6.0848531368047115e-05,
+      "loss": 5.5285,
+      "step": 329
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.04301217570900917,
+      "learning_rate": 6.026177149081948e-05,
+      "loss": 5.3762,
+      "step": 330
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.036191683262586594,
+      "learning_rate": 5.967663184321047e-05,
+      "loss": 5.3144,
+      "step": 331
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.0407772958278656,
+      "learning_rate": 5.909313628286601e-05,
+      "loss": 5.3912,
+      "step": 332
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.03703505918383598,
+      "learning_rate": 5.851130860039851e-05,
+      "loss": 5.3716,
+      "step": 333
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.03205498680472374,
+      "learning_rate": 5.793117251841659e-05,
+      "loss": 5.3783,
+      "step": 334
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.031054235994815826,
+      "learning_rate": 5.735275169055803e-05,
+      "loss": 5.428,
+      "step": 335
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.04683557152748108,
+      "learning_rate": 5.677606970052529e-05,
+      "loss": 5.3454,
+      "step": 336
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0369766429066658,
+      "learning_rate": 5.620115006112396e-05,
+      "loss": 5.5212,
+      "step": 337
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.03676708787679672,
+      "learning_rate": 5.5628016213304025e-05,
+      "loss": 5.5202,
+      "step": 338
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.03692242130637169,
+      "learning_rate": 5.505669152520425e-05,
+      "loss": 5.3962,
+      "step": 339
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.03632184490561485,
+      "learning_rate": 5.448719929119915e-05,
+      "loss": 5.4719,
+      "step": 340
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.03401057794690132,
+      "learning_rate": 5.3919562730949515e-05,
+      "loss": 5.4735,
+      "step": 341
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.03179492428898811,
+      "learning_rate": 5.335380498845559e-05,
+      "loss": 5.4301,
+      "step": 342
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.05031324550509453,
+      "learning_rate": 5.278994913111326e-05,
+      "loss": 5.5902,
+      "step": 343
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.037076130509376526,
+      "learning_rate": 5.222801814877369e-05,
+      "loss": 5.3786,
+      "step": 344
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.05723627656698227,
+      "learning_rate": 5.1668034952806146e-05,
+      "loss": 5.7038,
+      "step": 345
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.035133399069309235,
+      "learning_rate": 5.111002237516334e-05,
+      "loss": 5.4535,
+      "step": 346
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.06996971368789673,
+      "learning_rate": 5.055400316745096e-05,
+      "loss": 5.726,
+      "step": 347
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.0424312986433506,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.3156,
+      "step": 348
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.05643362179398537,
+      "learning_rate": 4.9448035460942144e-05,
+      "loss": 5.3829,
+      "step": 349
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.0284893736243248,
+      "learning_rate": 4.889813205528895e-05,
+      "loss": 5.6425,
+      "step": 350
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.06052859500050545,
+      "learning_rate": 4.835031220401447e-05,
+      "loss": 5.3397,
+      "step": 351
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.06666272133588791,
+      "learning_rate": 4.7804598243140666e-05,
+      "loss": 5.6796,
+      "step": 352
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.03461989015340805,
+      "learning_rate": 4.726101242282708e-05,
+      "loss": 5.538,
+      "step": 353
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.052791792899370193,
+      "learning_rate": 4.671957690646345e-05,
+      "loss": 5.4114,
+      "step": 354
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.06576182693243027,
+      "learning_rate": 4.6180313769766105e-05,
+      "loss": 5.4554,
+      "step": 355
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.043472375720739365,
+      "learning_rate": 4.56432449998779e-05,
+      "loss": 5.4107,
+      "step": 356
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.03615492582321167,
+      "learning_rate": 4.5108392494471686e-05,
+      "loss": 5.4123,
+      "step": 357
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.05690396949648857,
+      "learning_rate": 4.457577806085754e-05,
+      "loss": 5.6233,
+      "step": 358
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.060359589755535126,
+      "learning_rate": 4.40454234150936e-05,
+      "loss": 5.6305,
+      "step": 359
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.05274466052651405,
+      "learning_rate": 4.351735018110066e-05,
+      "loss": 5.5135,
+      "step": 360
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.03002074547111988,
+      "learning_rate": 4.299157988978048e-05,
+      "loss": 5.4805,
+      "step": 361
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.037866391241550446,
+      "learning_rate": 4.2468133978137945e-05,
+      "loss": 5.381,
+      "step": 362
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.03351390361785889,
+      "learning_rate": 4.1947033788407005e-05,
+      "loss": 5.5211,
+      "step": 363
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.04190673679113388,
+      "learning_rate": 4.142830056718052e-05,
+      "loss": 5.425,
+      "step": 364
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.03094741329550743,
+      "learning_rate": 4.0911955464543986e-05,
+      "loss": 5.3775,
+      "step": 365
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.0317833349108696,
+      "learning_rate": 4.0398019533213014e-05,
+      "loss": 5.4909,
+      "step": 366
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.05673886463046074,
+      "learning_rate": 3.988651372767538e-05,
+      "loss": 5.4684,
+      "step": 367
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.06641435623168945,
+      "learning_rate": 3.937745890333623e-05,
+      "loss": 5.316,
+      "step": 368
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.029901282861828804,
+      "learning_rate": 3.887087581566784e-05,
+      "loss": 5.3482,
+      "step": 369
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.04485533386468887,
+      "learning_rate": 3.8366785119363624e-05,
+      "loss": 5.4514,
+      "step": 370
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.038150250911712646,
+      "learning_rate": 3.786520736749572e-05,
+      "loss": 5.403,
+      "step": 371
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.034878868609666824,
+      "learning_rate": 3.736616301067694e-05,
+      "loss": 5.451,
+      "step": 372
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.05571235716342926,
+      "learning_rate": 3.686967239622728e-05,
+      "loss": 5.2992,
+      "step": 373
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.03623438999056816,
+      "learning_rate": 3.637575576734404e-05,
+      "loss": 5.4354,
+      "step": 374
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.040699999779462814,
+      "learning_rate": 3.5884433262276375e-05,
+      "loss": 5.5793,
+      "step": 375
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.0567522794008255,
+      "learning_rate": 3.5395724913504545e-05,
+      "loss": 5.5866,
+      "step": 376
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.06090893968939781,
+      "learning_rate": 3.4909650646922896e-05,
+      "loss": 5.4413,
+      "step": 377
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.03806202486157417,
+      "learning_rate": 3.442623028102737e-05,
+      "loss": 5.4202,
+      "step": 378
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.03735024482011795,
+      "learning_rate": 3.394548352610767e-05,
+      "loss": 5.4923,
+      "step": 379
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.05218209698796272,
+      "learning_rate": 3.346742998344348e-05,
+      "loss": 5.3634,
+      "step": 380
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.03788035362958908,
+      "learning_rate": 3.299208914450532e-05,
+      "loss": 5.4613,
+      "step": 381
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.038459401577711105,
+      "learning_rate": 3.2519480390159806e-05,
+      "loss": 5.5289,
+      "step": 382
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.03371362388134003,
+      "learning_rate": 3.204962298987945e-05,
+      "loss": 5.4143,
+      "step": 383
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.1352624148130417,
+      "learning_rate": 3.158253610095697e-05,
+      "loss": 5.1731,
+      "step": 384
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 5.14132833480835,
+      "eval_runtime": 117.9188,
+      "eval_samples_per_second": 14.374,
+      "eval_steps_per_second": 2.061,
+      "step": 384
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.033526431769132614,
+      "learning_rate": 3.111823876772426e-05,
+      "loss": 5.5211,
+      "step": 385
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.05555104464292526,
+      "learning_rate": 3.065674992077584e-05,
+      "loss": 5.7138,
+      "step": 386
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.037323616445064545,
+      "learning_rate": 3.019808837619704e-05,
+      "loss": 5.4475,
+      "step": 387
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.028331860899925232,
+      "learning_rate": 2.9742272834796813e-05,
+      "loss": 5.3551,
+      "step": 388
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.02999243512749672,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 5.3843,
+      "step": 389
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.029440969228744507,
+      "learning_rate": 2.883925398381585e-05,
+      "loss": 5.3457,
+      "step": 390
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.043180134147405624,
+      "learning_rate": 2.8392087492632502e-05,
+      "loss": 5.3563,
+      "step": 391
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.06036212667822838,
+      "learning_rate": 2.794784063992131e-05,
+      "loss": 5.3512,
+      "step": 392
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.08311715722084045,
+      "learning_rate": 2.7506531538767212e-05,
+      "loss": 5.6404,
+      "step": 393
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.046528592705726624,
+      "learning_rate": 2.706817818247551e-05,
+      "loss": 5.3849,
+      "step": 394
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.05664818361401558,
+      "learning_rate": 2.6632798443838147e-05,
+      "loss": 5.6102,
+      "step": 395
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.041858069598674774,
+      "learning_rate": 2.620041007440508e-05,
+      "loss": 5.4059,
+      "step": 396
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.051613613963127136,
+      "learning_rate": 2.5771030703760434e-05,
+      "loss": 5.6078,
+      "step": 397
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.03705097734928131,
+      "learning_rate": 2.5344677838803733e-05,
+      "loss": 5.3332,
+      "step": 398
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.0435323491692543,
+      "learning_rate": 2.492136886303611e-05,
+      "loss": 5.4705,
+      "step": 399
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.043584998697042465,
+      "learning_rate": 2.4501121035851492e-05,
+      "loss": 5.4051,
+      "step": 400
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.054206427186727524,
+      "learning_rate": 2.4083951491832945e-05,
+      "loss": 5.6382,
+      "step": 401
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.04840492084622383,
+      "learning_rate": 2.366987724005404e-05,
+      "loss": 5.4019,
+      "step": 402
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.028504041954874992,
+      "learning_rate": 2.325891516338523e-05,
+      "loss": 5.3931,
+      "step": 403
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.04800885543227196,
+      "learning_rate": 2.2851082017805703e-05,
+      "loss": 5.5231,
+      "step": 404
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.033465560525655746,
+      "learning_rate": 2.244639443172013e-05,
+      "loss": 5.379,
+      "step": 405
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.030162468552589417,
+      "learning_rate": 2.20448689052805e-05,
+      "loss": 5.3633,
+      "step": 406
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.09385357797145844,
+      "learning_rate": 2.164652180971358e-05,
+      "loss": 5.3651,
+      "step": 407
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.04510626196861267,
+      "learning_rate": 2.1251369386653454e-05,
+      "loss": 5.4746,
+      "step": 408
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.039704885333776474,
+      "learning_rate": 2.085942774747901e-05,
+      "loss": 5.4849,
+      "step": 409
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.03505348786711693,
+      "learning_rate": 2.047071287265735e-05,
+      "loss": 5.4485,
+      "step": 410
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.03931122273206711,
+      "learning_rate": 2.0085240611092138e-05,
+      "loss": 5.375,
+      "step": 411
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.03462689369916916,
+      "learning_rate": 1.9703026679477256e-05,
+      "loss": 5.5718,
+      "step": 412
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.035479288548231125,
+      "learning_rate": 1.932408666165617e-05,
+      "loss": 5.5952,
+      "step": 413
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.030520660802721977,
+      "learning_rate": 1.8948436007986546e-05,
+      "loss": 5.4703,
+      "step": 414
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.11821933090686798,
+      "learning_rate": 1.857609003471007e-05,
+      "loss": 5.5369,
+      "step": 415
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.05747751519083977,
+      "learning_rate": 1.8207063923328237e-05,
+      "loss": 5.6542,
+      "step": 416
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.0752585232257843,
+      "learning_rate": 1.7841372719983228e-05,
+      "loss": 5.5633,
+      "step": 417
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.078254833817482,
+      "learning_rate": 1.747903133484442e-05,
+      "loss": 5.7038,
+      "step": 418
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.0734933391213417,
+      "learning_rate": 1.7120054541500553e-05,
+      "loss": 5.2323,
+      "step": 419
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.03491882234811783,
+      "learning_rate": 1.676445697635728e-05,
+      "loss": 5.523,
+      "step": 420
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.08193439245223999,
+      "learning_rate": 1.6412253138040468e-05,
+      "loss": 5.2352,
+      "step": 421
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.03526321053504944,
+      "learning_rate": 1.6063457386805004e-05,
+      "loss": 5.5528,
+      "step": 422
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.03471006825566292,
+      "learning_rate": 1.5718083943949337e-05,
+      "loss": 5.5334,
+      "step": 423
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.0470704585313797,
+      "learning_rate": 1.5376146891235598e-05,
+      "loss": 5.6915,
+      "step": 424
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.05606949329376221,
+      "learning_rate": 1.503766017031547e-05,
+      "loss": 5.5933,
+      "step": 425
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.04725959151983261,
+      "learning_rate": 1.470263758216176e-05,
+      "loss": 5.4065,
+      "step": 426
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.053547605872154236,
+      "learning_rate": 1.4371092786505669e-05,
+      "loss": 5.5144,
+      "step": 427
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.05385226011276245,
+      "learning_rate": 1.4043039301279903e-05,
+      "loss": 5.6636,
+      "step": 428
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.032404594123363495,
+      "learning_rate": 1.3718490502067394e-05,
+      "loss": 5.4314,
+      "step": 429
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.038287803530693054,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 5.4867,
+      "step": 430
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.09523623436689377,
+      "learning_rate": 1.3079959748999493e-05,
+      "loss": 5.2526,
+      "step": 431
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.03632797673344612,
+      "learning_rate": 1.2766003829682505e-05,
+      "loss": 5.4288,
+      "step": 432
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.047736331820487976,
+      "learning_rate": 1.2455604664394249e-05,
+      "loss": 5.5558,
+      "step": 433
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.04540436714887619,
+      "learning_rate": 1.214877490890578e-05,
+      "loss": 5.2932,
+      "step": 434
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.039823420345783234,
+      "learning_rate": 1.1845527073454044e-05,
+      "loss": 5.3759,
+      "step": 435
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.06641686707735062,
+      "learning_rate": 1.1545873522232053e-05,
+      "loss": 5.3121,
+      "step": 436
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.05735361576080322,
+      "learning_rate": 1.1249826472884572e-05,
+      "loss": 5.3518,
+      "step": 437
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.058835744857788086,
+      "learning_rate": 1.0957397996009933e-05,
+      "loss": 5.3926,
+      "step": 438
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.07455369085073471,
+      "learning_rate": 1.0668600014668129e-05,
+      "loss": 5.3992,
+      "step": 439
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.09594876319169998,
+      "learning_rate": 1.0383444303894452e-05,
+      "loss": 5.4881,
+      "step": 440
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.06567229330539703,
+      "learning_rate": 1.0101942490219418e-05,
+      "loss": 5.496,
+      "step": 441
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.0464106909930706,
+      "learning_rate": 9.824106051194859e-06,
+      "loss": 5.3197,
+      "step": 442
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.041425399482250214,
+      "learning_rate": 9.549946314925839e-06,
+      "loss": 5.5576,
+      "step": 443
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.07320866733789444,
+      "learning_rate": 9.279474459608805e-06,
+      "loss": 5.2278,
+      "step": 444
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.06431550532579422,
+      "learning_rate": 9.012701513075839e-06,
+      "loss": 5.7271,
+      "step": 445
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.04593539610505104,
+      "learning_rate": 8.749638352345002e-06,
+      "loss": 5.4862,
+      "step": 446
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.04739491268992424,
+      "learning_rate": 8.490295703176877e-06,
+      "loss": 5.5574,
+      "step": 447
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.07719334214925766,
+      "learning_rate": 8.234684139637205e-06,
+      "loss": 5.6221,
+      "step": 448
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 5.140613555908203,
+      "eval_runtime": 118.0618,
+      "eval_samples_per_second": 14.357,
+      "eval_steps_per_second": 2.058,
+      "step": 448
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.041309550404548645,
+      "learning_rate": 7.982814083665824e-06,
+      "loss": 5.5653,
+      "step": 449
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.04140365868806839,
+      "learning_rate": 7.734695804651693e-06,
+      "loss": 5.4939,
+      "step": 450
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.06422597914934158,
+      "learning_rate": 7.490339419014147e-06,
+      "loss": 5.4952,
+      "step": 451
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.03446926176548004,
+      "learning_rate": 7.249754889790539e-06,
+      "loss": 5.5574,
+      "step": 452
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.03944532573223114,
+      "learning_rate": 7.0129520262298905e-06,
+      "loss": 5.3908,
+      "step": 453
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.03682417795062065,
+      "learning_rate": 6.779940483393032e-06,
+      "loss": 5.4036,
+      "step": 454
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.04823753237724304,
+      "learning_rate": 6.5507297617589005e-06,
+      "loss": 5.5624,
+      "step": 455
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.04815137758851051,
+      "learning_rate": 6.325329206837216e-06,
+      "loss": 5.3947,
+      "step": 456
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.034516386687755585,
+      "learning_rate": 6.10374800878738e-06,
+      "loss": 5.4647,
+      "step": 457
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.05057673528790474,
+      "learning_rate": 5.885995202043848e-06,
+      "loss": 5.3745,
+      "step": 458
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.05802900716662407,
+      "learning_rate": 5.672079664947683e-06,
+      "loss": 5.3907,
+      "step": 459
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.06572411209344864,
+      "learning_rate": 5.462010119384664e-06,
+      "loss": 5.5531,
+      "step": 460
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.07992907613515854,
+      "learning_rate": 5.255795130429575e-06,
+      "loss": 5.6433,
+      "step": 461
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.04272537678480148,
+      "learning_rate": 5.0534431059970685e-06,
+      "loss": 5.2467,
+      "step": 462
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.05195242911577225,
+      "learning_rate": 4.854962296498767e-06,
+      "loss": 5.4404,
+      "step": 463
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.08947974443435669,
+      "learning_rate": 4.660360794506946e-06,
+      "loss": 5.7227,
+      "step": 464
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.04164132848381996,
+      "learning_rate": 4.469646534424587e-06,
+      "loss": 5.4453,
+      "step": 465
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.04136288911104202,
+      "learning_rate": 4.2828272921617615e-06,
+      "loss": 5.2939,
+      "step": 466
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.028134597465395927,
+      "learning_rate": 4.099910684818698e-06,
+      "loss": 5.4966,
+      "step": 467
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.02709069848060608,
+      "learning_rate": 3.9209041703752395e-06,
+      "loss": 5.4437,
+      "step": 468
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.028078071773052216,
+      "learning_rate": 3.7458150473865806e-06,
+      "loss": 5.3869,
+      "step": 469
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.035699162632226944,
+      "learning_rate": 3.5746504546859018e-06,
+      "loss": 5.4277,
+      "step": 470
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.03117111697793007,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 5.4876,
+      "step": 471
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.07179710268974304,
+      "learning_rate": 3.2441226151306404e-06,
+      "loss": 5.2674,
+      "step": 472
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.07368176430463791,
+      "learning_rate": 3.08477284474481e-06,
+      "loss": 5.6495,
+      "step": 473
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.06733419746160507,
+      "learning_rate": 2.929374557035036e-06,
+      "loss": 5.6539,
+      "step": 474
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.03158855438232422,
+      "learning_rate": 2.7779340879885317e-06,
+      "loss": 5.5043,
+      "step": 475
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.0531897209584713,
+      "learning_rate": 2.6304576122221035e-06,
+      "loss": 5.3542,
+      "step": 476
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.06829779595136642,
+      "learning_rate": 2.486951142730354e-06,
+      "loss": 5.482,
+      "step": 477
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0455712154507637,
+      "learning_rate": 2.347420530640565e-06,
+      "loss": 5.3337,
+      "step": 478
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.056621916592121124,
+      "learning_rate": 2.211871464974091e-06,
+      "loss": 5.6204,
+      "step": 479
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.03741488978266716,
+      "learning_rate": 2.080309472414388e-06,
+      "loss": 5.5323,
+      "step": 480
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.03577736020088196,
+      "learning_rate": 1.9527399170817474e-06,
+      "loss": 5.5698,
+      "step": 481
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.06947164237499237,
+      "learning_rate": 1.8291680003145073e-06,
+      "loss": 5.376,
+      "step": 482
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.03131519630551338,
+      "learning_rate": 1.709598760457043e-06,
+      "loss": 5.4888,
+      "step": 483
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.07330077886581421,
+      "learning_rate": 1.5940370726542863e-06,
+      "loss": 5.2317,
+      "step": 484
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.043250925838947296,
+      "learning_rate": 1.482487648653008e-06,
+      "loss": 5.4134,
+      "step": 485
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.029981188476085663,
+      "learning_rate": 1.3749550366096597e-06,
+      "loss": 5.5351,
+      "step": 486
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.06865333765745163,
+      "learning_rate": 1.2714436209049663e-06,
+      "loss": 5.2031,
+      "step": 487
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.05455838516354561,
+      "learning_rate": 1.1719576219651585e-06,
+      "loss": 5.4211,
+      "step": 488
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.05349655821919441,
+      "learning_rate": 1.0765010960898547e-06,
+      "loss": 5.6215,
+      "step": 489
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.04323553293943405,
+      "learning_rate": 9.85077935286749e-07,
+      "loss": 5.4167,
+      "step": 490
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.0579364188015461,
+      "learning_rate": 8.97691867112882e-07,
+      "loss": 5.417,
+      "step": 491
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.034214384853839874,
+      "learning_rate": 8.143464545226298e-07,
+      "loss": 5.433,
+      "step": 492
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.06100679188966751,
+      "learning_rate": 7.350450957224863e-07,
+      "loss": 5.5141,
+      "step": 493
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.03651317209005356,
+      "learning_rate": 6.597910240324967e-07,
+      "loss": 5.3889,
+      "step": 494
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.06660210341215134,
+      "learning_rate": 5.885873077543847e-07,
+      "loss": 5.7303,
+      "step": 495
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.045400649309158325,
+      "learning_rate": 5.214368500465305e-07,
+      "loss": 5.2787,
+      "step": 496
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.09726037085056305,
+      "learning_rate": 4.583423888055105e-07,
+      "loss": 5.2564,
+      "step": 497
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.04204811528325081,
+      "learning_rate": 3.99306496554519e-07,
+      "loss": 5.469,
+      "step": 498
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.04836532101035118,
+      "learning_rate": 3.4433158033850833e-07,
+      "loss": 5.3378,
+      "step": 499
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.046665653586387634,
+      "learning_rate": 2.934198816259559e-07,
+      "loss": 5.2861,
+      "step": 500
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.03299957513809204,
+      "learning_rate": 2.4657347621755975e-07,
+      "loss": 5.416,
+      "step": 501
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.05182642117142677,
+      "learning_rate": 2.037942741615617e-07,
+      "loss": 5.3701,
+      "step": 502
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.05335336923599243,
+      "learning_rate": 1.6508401967588739e-07,
+      "loss": 5.5008,
+      "step": 503
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.04429781809449196,
+      "learning_rate": 1.3044429107700318e-07,
+      "loss": 5.5158,
+      "step": 504
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.040103472769260406,
+      "learning_rate": 9.987650071561216e-08,
+      "loss": 5.4417,
+      "step": 505
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.061163704842329025,
+      "learning_rate": 7.338189491900016e-08,
+      "loss": 5.3255,
+      "step": 506
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.02699468657374382,
+      "learning_rate": 5.096155394028745e-08,
+      "loss": 5.3667,
+      "step": 507
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.03286271169781685,
+      "learning_rate": 3.2616391914364054e-08,
+      "loss": 5.4115,
+      "step": 508
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.05289580672979355,
+      "learning_rate": 1.834715682056398e-08,
+      "loss": 5.5861,
+      "step": 509
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.05315104126930237,
+      "learning_rate": 8.15443045226738e-09,
+      "loss": 5.6414,
+      "step": 510
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.048052575439214706,
+      "learning_rate": 2.038628393097319e-09,
+      "loss": 5.491,
+      "step": 511
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.03549593687057495,
+      "learning_rate": 0.0,
+      "loss": 5.3737,
+      "step": 512
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 5.141936302185059,
+      "eval_runtime": 118.0207,
+      "eval_samples_per_second": 14.362,
+      "eval_steps_per_second": 2.059,
+      "step": 512
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 256,
+  "total_flos": 3.779099804869591e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e6a8e7b42c6d0fb444438c2b307f3df9d33555640360e342822219fc0d61dd
+size 5624

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "JY623/KoSOLAR-v2.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "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": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

runs/Mar26_00-22-15_ginger/events.out.tfevents.1711412537.ginger.170386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473bd5c79802ef726a57dff38c6ba5804080b682d2850224079d72ee87a68131
+size 116229

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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}