Upload folder using huggingface_hub

README.md

@@ -1,3 +1,135 @@
 ---
-license: unknown
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openlm-research/open_llama_3b_v2
+model-index:
+- name: qlora-out
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: openlm-research/open_llama_3b_v2
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: mhenrichsen/alpaca_2k_test
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: qlora
+lora_model_dir:
+sequence_len: 1024
+sample_packing: true
+lora_r: 8
+lora_alpha: 32
+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:
+output_dir: ./qlora-out
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 1
+optimizer: paged_adamw_32bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0002
+train_on_inputs: false
+group_by_length: false
+bf16: false
+fp16: true
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+evals_per_epoch: 4
+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
+
+This model is a fine-tuned version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1111
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2567        | 0.0   | 1    | 1.3469          |
+| 1.1726        | 0.25  | 108  | 1.1364          |
+| 1.1127        | 0.5   | 216  | 1.1218          |
+| 1.4125        | 0.75  | 324  | 1.1111          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu118
+- 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": "openlm-research/open_llama_3b_v2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "q_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:ccf142125200178b356f5c8155d5cda381199f5a4a65c57e12b5f4d620d0e8b2
+size 50982842

checkpoint-426/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openlm-research/open_llama_3b_v2
+---
+
+# 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-426/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-426/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce4df400276b9bb85c8b5652df91fc4dc175942c248be0295291b2bf2fea145
+size 50899792

checkpoint-426/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04efe59c057b5eb22955678a7dea73d5e3962c182a728f2dee473809bf87d741
+size 101919290

checkpoint-426/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0934a275afd2ca8de2510163d4a35672cc3dc20689a0fdd64a24060afa543cd
+size 14244

checkpoint-426/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fca02f23aa183f137360b6f00ec0358b364aebd03cc5dd5fdcc96a563d6326e
+size 1064

checkpoint-426/trainer_state.json

@@ -0,0 +1,3035 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 107,
+  "global_step": 426,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.8714431524276733,
+      "learning_rate": 1e-05,
+      "loss": 1.2567,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.3469438552856445,
+      "eval_runtime": 4.3863,
+      "eval_samples_per_second": 22.798,
+      "eval_steps_per_second": 22.798,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.7777996063232422,
+      "learning_rate": 2e-05,
+      "loss": 1.3328,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.0336275100708008,
+      "learning_rate": 3e-05,
+      "loss": 1.6576,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.3582738637924194,
+      "learning_rate": 4e-05,
+      "loss": 1.5508,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.6695992946624756,
+      "learning_rate": 5e-05,
+      "loss": 1.4342,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.0930147171020508,
+      "learning_rate": 6e-05,
+      "loss": 1.2685,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.9392880201339722,
+      "learning_rate": 7e-05,
+      "loss": 1.4734,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8906668424606323,
+      "learning_rate": 8e-05,
+      "loss": 1.4075,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8587246537208557,
+      "learning_rate": 9e-05,
+      "loss": 1.2863,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7436723113059998,
+      "learning_rate": 0.0001,
+      "loss": 1.1445,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8591585159301758,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.4687,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7763879299163818,
+      "learning_rate": 0.00012,
+      "loss": 0.9762,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.2800297737121582,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.5181,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0263522863388062,
+      "learning_rate": 0.00014,
+      "loss": 1.1558,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.0572967529296875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2756,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.368507981300354,
+      "learning_rate": 0.00016,
+      "loss": 1.3266,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0468926429748535,
+      "learning_rate": 0.00017,
+      "loss": 1.2975,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.040204405784607,
+      "learning_rate": 0.00018,
+      "loss": 1.324,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8548620939254761,
+      "learning_rate": 0.00019,
+      "loss": 1.205,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.705979824066162,
+      "learning_rate": 0.0002,
+      "loss": 1.1952,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.4010071754455566,
+      "learning_rate": 0.00019999700625010443,
+      "loss": 1.2281,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.3646819591522217,
+      "learning_rate": 0.0001999880251796685,
+      "loss": 1.3212,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.4444034099578857,
+      "learning_rate": 0.00019997305732643374,
+      "loss": 1.5903,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.1282485723495483,
+      "learning_rate": 0.00019995210358660038,
+      "loss": 1.3088,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9718368649482727,
+      "learning_rate": 0.00019992516521477352,
+      "loss": 1.3159,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0601626634597778,
+      "learning_rate": 0.00019989224382388813,
+      "loss": 1.2509,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9524707794189453,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 1.1984,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.9859796166419983,
+      "learning_rate": 0.00019980846022772978,
+      "loss": 1.0488,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.991126537322998,
+      "learning_rate": 0.00019975760303899952,
+      "loss": 1.3518,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3073846101760864,
+      "learning_rate": 0.0001997007728639956,
+      "loss": 1.255,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.9164822697639465,
+      "learning_rate": 0.0001996379731054247,
+      "loss": 1.1597,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2679331302642822,
+      "learning_rate": 0.00019956920752342225,
+      "loss": 1.1824,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0039063692092896,
+      "learning_rate": 0.00019949448023532726,
+      "loss": 1.0098,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0025910139083862,
+      "learning_rate": 0.00019941379571543596,
+      "loss": 1.1948,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3439923524856567,
+      "learning_rate": 0.00019932715879473386,
+      "loss": 1.5832,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0501818656921387,
+      "learning_rate": 0.00019923457466060636,
+      "loss": 0.971,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9802983999252319,
+      "learning_rate": 0.00019913604885652832,
+      "loss": 1.1861,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.611431360244751,
+      "learning_rate": 0.00019903158728173205,
+      "loss": 1.7258,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9659163951873779,
+      "learning_rate": 0.00019892119619085413,
+      "loss": 1.5085,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.2181308269500732,
+      "learning_rate": 0.00019880488219356087,
+      "loss": 1.1304,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9131419062614441,
+      "learning_rate": 0.00019868265225415265,
+      "loss": 1.2439,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9594250917434692,
+      "learning_rate": 0.00019855451369114676,
+      "loss": 1.2214,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.870884120464325,
+      "learning_rate": 0.0001984204741768395,
+      "loss": 1.5281,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9542310833930969,
+      "learning_rate": 0.00019828054173684644,
+      "loss": 1.1095,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8289800882339478,
+      "learning_rate": 0.00019813472474962217,
+      "loss": 1.089,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.0782636404037476,
+      "learning_rate": 0.00019798303194595846,
+      "loss": 1.2353,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.2055485248565674,
+      "learning_rate": 0.00019782547240846166,
+      "loss": 1.3402,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8603373169898987,
+      "learning_rate": 0.00019766205557100868,
+      "loss": 0.9598,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.043985366821289,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.3912,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.0970604419708252,
+      "learning_rate": 0.00019731768948468549,
+      "loss": 1.0194,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.174673318862915,
+      "learning_rate": 0.00019713676085473397,
+      "loss": 1.3042,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1205767393112183,
+      "learning_rate": 0.00019695001616142915,
+      "loss": 1.1749,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.2218433618545532,
+      "learning_rate": 0.00019675746658610917,
+      "loss": 1.251,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.140669345855713,
+      "learning_rate": 0.0001965591236576794,
+      "loss": 0.8802,
+      "step": 54
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7591732144355774,
+      "learning_rate": 0.0001963549992519223,
+      "loss": 1.2334,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.1725890636444092,
+      "learning_rate": 0.00019614510559078625,
+      "loss": 1.42,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.2042464017868042,
+      "learning_rate": 0.00019592945524165374,
+      "loss": 1.3263,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8648535013198853,
+      "learning_rate": 0.00019570806111658898,
+      "loss": 1.1415,
+      "step": 58
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9207460284233093,
+      "learning_rate": 0.0001954809364715648,
+      "loss": 1.0684,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8753947019577026,
+      "learning_rate": 0.00019524809490566877,
+      "loss": 1.3649,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9168523550033569,
+      "learning_rate": 0.00019500955036028922,
+      "loss": 0.5982,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.8507192730903625,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 1.254,
+      "step": 62
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.3870004415512085,
+      "learning_rate": 0.00019451540980310676,
+      "loss": 1.3797,
+      "step": 63
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7783665657043457,
+      "learning_rate": 0.0001942598433779687,
+      "loss": 0.9461,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.0121338367462158,
+      "learning_rate": 0.00019399863314490526,
+      "loss": 1.1174,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9875881671905518,
+      "learning_rate": 0.00019373179474387858,
+      "loss": 1.0404,
+      "step": 66
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1349287033081055,
+      "learning_rate": 0.0001934593441518374,
+      "loss": 1.0543,
+      "step": 67
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8213971257209778,
+      "learning_rate": 0.00019318129768176032,
+      "loss": 1.1827,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9462853670120239,
+      "learning_rate": 0.00019289767198167916,
+      "loss": 1.1625,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7908749580383301,
+      "learning_rate": 0.0001926084840336821,
+      "loss": 1.1092,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.9556800127029419,
+      "learning_rate": 0.00019231375115289696,
+      "loss": 1.3066,
+      "step": 71
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8883413672447205,
+      "learning_rate": 0.00019201349098645434,
+      "loss": 1.3062,
+      "step": 72
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.524029016494751,
+      "learning_rate": 0.00019170772151243107,
+      "loss": 1.1556,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8292478322982788,
+      "learning_rate": 0.0001913964610387738,
+      "loss": 0.7053,
+      "step": 74
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0171422958374023,
+      "learning_rate": 0.00019107972820220267,
+      "loss": 1.0826,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8275893926620483,
+      "learning_rate": 0.00019075754196709572,
+      "loss": 1.0433,
+      "step": 76
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0667102336883545,
+      "learning_rate": 0.00019042992162435302,
+      "loss": 1.1481,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0348743200302124,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.0743,
+      "step": 78
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.5982255339622498,
+      "learning_rate": 0.00018975845740522244,
+      "loss": 0.631,
+      "step": 79
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8770480751991272,
+      "learning_rate": 0.0001894146537327533,
+      "loss": 1.4117,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8862263560295105,
+      "learning_rate": 0.00018906549635807861,
+      "loss": 1.0361,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.9842098355293274,
+      "learning_rate": 0.00018871100618699554,
+      "loss": 1.1199,
+      "step": 82
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.0639700889587402,
+      "learning_rate": 0.0001883512044446023,
+      "loss": 1.4317,
+      "step": 83
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7691718339920044,
+      "learning_rate": 0.00018798611267402746,
+      "loss": 1.0549,
+      "step": 84
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8742901682853699,
+      "learning_rate": 0.00018761575273514003,
+      "loss": 0.8672,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8506189584732056,
+      "learning_rate": 0.00018724014680324057,
+      "loss": 1.0504,
+      "step": 86
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7364802956581116,
+      "learning_rate": 0.0001868593173677335,
+      "loss": 1.0435,
+      "step": 87
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.8765585422515869,
+      "learning_rate": 0.00018647328723078038,
+      "loss": 1.0099,
+      "step": 88
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.8263121247291565,
+      "learning_rate": 0.000186082079505935,
+      "loss": 1.1974,
+      "step": 89
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.8597404956817627,
+      "learning_rate": 0.00018568571761675893,
+      "loss": 1.2945,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.7249889373779297,
+      "learning_rate": 0.00018528422529541952,
+      "loss": 1.0435,
+      "step": 91
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.049282193183899,
+      "learning_rate": 0.0001848776265812687,
+      "loss": 1.1469,
+      "step": 92
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.4928953647613525,
+      "learning_rate": 0.0001844659458194036,
+      "loss": 1.3791,
+      "step": 93
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7761886119842529,
+      "learning_rate": 0.00018404920765920896,
+      "loss": 1.0154,
+      "step": 94
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.8695176243782043,
+      "learning_rate": 0.00018362743705288125,
+      "loss": 1.0702,
+      "step": 95
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0606937408447266,
+      "learning_rate": 0.00018320065925393468,
+      "loss": 1.1018,
+      "step": 96
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7747076749801636,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 0.8738,
+      "step": 97
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8261910676956177,
+      "learning_rate": 0.00018233218458973984,
+      "loss": 0.8859,
+      "step": 98
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1293946504592896,
+      "learning_rate": 0.00018189053972441025,
+      "loss": 1.312,
+      "step": 99
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8352298140525818,
+      "learning_rate": 0.00018144399166318572,
+      "loss": 1.3228,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0237839221954346,
+      "learning_rate": 0.0001809925671431304,
+      "loss": 1.0928,
+      "step": 101
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0794199705123901,
+      "learning_rate": 0.00018053629319328662,
+      "loss": 1.5585,
+      "step": 102
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7404956221580505,
+      "learning_rate": 0.00018007519713305605,
+      "loss": 1.1547,
+      "step": 103
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.2856953144073486,
+      "learning_rate": 0.00017960930657056438,
+      "loss": 1.2913,
+      "step": 104
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8910708427429199,
+      "learning_rate": 0.00017913864940100808,
+      "loss": 1.2172,
+      "step": 105
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9663183689117432,
+      "learning_rate": 0.00017866325380498416,
+      "loss": 0.9437,
+      "step": 106
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8983346223831177,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.9997,
+      "step": 107
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.1364588737487793,
+      "eval_runtime": 4.5016,
+      "eval_samples_per_second": 22.215,
+      "eval_steps_per_second": 22.215,
+      "step": 107
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.853449285030365,
+      "learning_rate": 0.0001776983614727838,
+      "loss": 1.1704,
+      "step": 108
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8785815238952637,
+      "learning_rate": 0.00017720892250953373,
+      "loss": 1.0636,
+      "step": 109
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8658995628356934,
+      "learning_rate": 0.00017671486066220965,
+      "loss": 1.0887,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8114773035049438,
+      "learning_rate": 0.00017621620551276366,
+      "loss": 1.2346,
+      "step": 111
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1983680725097656,
+      "learning_rate": 0.00017571298691817177,
+      "loss": 1.2172,
+      "step": 112
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5358327627182007,
+      "learning_rate": 0.00017520523500864625,
+      "loss": 0.4534,
+      "step": 113
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.9793819189071655,
+      "learning_rate": 0.0001746929801858317,
+      "loss": 1.3169,
+      "step": 114
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.7807549834251404,
+      "learning_rate": 0.00017417625312098452,
+      "loss": 1.0365,
+      "step": 115
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.8590349555015564,
+      "learning_rate": 0.0001736550847531366,
+      "loss": 1.1361,
+      "step": 116
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.042572021484375,
+      "learning_rate": 0.00017312950628724295,
+      "loss": 1.2348,
+      "step": 117
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2039955854415894,
+      "learning_rate": 0.0001725995491923131,
+      "loss": 1.1588,
+      "step": 118
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8001018166542053,
+      "learning_rate": 0.00017206524519952697,
+      "loss": 1.1131,
+      "step": 119
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8552284836769104,
+      "learning_rate": 0.00017152662630033505,
+      "loss": 1.0416,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.942588210105896,
+      "learning_rate": 0.00017098372474454277,
+      "loss": 0.7409,
+      "step": 121
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.8172719478607178,
+      "learning_rate": 0.00017043657303837963,
+      "loss": 1.1068,
+      "step": 122
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9123536944389343,
+      "learning_rate": 0.000169885203942553,
+      "loss": 1.3195,
+      "step": 123
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9618800282478333,
+      "learning_rate": 0.0001693296504702862,
+      "loss": 1.3815,
+      "step": 124
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9613810181617737,
+      "learning_rate": 0.00016876994588534234,
+      "loss": 1.4028,
+      "step": 125
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.7111766934394836,
+      "learning_rate": 0.00016820612370003221,
+      "loss": 0.8176,
+      "step": 126
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.6110447645187378,
+      "learning_rate": 0.000167638217673208,
+      "loss": 0.5987,
+      "step": 127
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9880752563476562,
+      "learning_rate": 0.00016706626180824186,
+      "loss": 1.1301,
+      "step": 128
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8844457268714905,
+      "learning_rate": 0.00016649029035099,
+      "loss": 1.0207,
+      "step": 129
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8161391615867615,
+      "learning_rate": 0.0001659103377877423,
+      "loss": 1.2918,
+      "step": 130
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.9053208231925964,
+      "learning_rate": 0.0001653264388431572,
+      "loss": 1.3093,
+      "step": 131
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7560325264930725,
+      "learning_rate": 0.00016473862847818277,
+      "loss": 1.0332,
+      "step": 132
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.1370497941970825,
+      "learning_rate": 0.00016414694188796345,
+      "loss": 1.3015,
+      "step": 133
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.789828896522522,
+      "learning_rate": 0.00016355141449973256,
+      "loss": 0.9216,
+      "step": 134
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0295219421386719,
+      "learning_rate": 0.0001629520819706912,
+      "loss": 1.2367,
+      "step": 135
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0790351629257202,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.0194,
+      "step": 136
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0458263158798218,
+      "learning_rate": 0.0001617421452559971,
+      "loss": 1.4242,
+      "step": 137
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8485111594200134,
+      "learning_rate": 0.0001611316135153026,
+      "loss": 1.0657,
+      "step": 138
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2946741580963135,
+      "learning_rate": 0.00016051742151937655,
+      "loss": 1.1067,
+      "step": 139
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.676237165927887,
+      "learning_rate": 0.0001598996060429634,
+      "loss": 0.9243,
+      "step": 140
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.8740692734718323,
+      "learning_rate": 0.00015927820407776353,
+      "loss": 1.1059,
+      "step": 141
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.0768831968307495,
+      "learning_rate": 0.0001586532528302183,
+      "loss": 1.1538,
+      "step": 142
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.8637721538543701,
+      "learning_rate": 0.00015802478971928242,
+      "loss": 1.2217,
+      "step": 143
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9076741337776184,
+      "learning_rate": 0.0001573928523741832,
+      "loss": 1.0969,
+      "step": 144
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0173722505569458,
+      "learning_rate": 0.00015675747863216801,
+      "loss": 1.2173,
+      "step": 145
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0093746185302734,
+      "learning_rate": 0.00015611870653623825,
+      "loss": 1.0805,
+      "step": 146
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.9120362401008606,
+      "learning_rate": 0.00015547657433287183,
+      "loss": 0.8473,
+      "step": 147
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.9144474267959595,
+      "learning_rate": 0.0001548311204697331,
+      "loss": 1.4245,
+      "step": 148
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.2324213981628418,
+      "learning_rate": 0.00015418238359337077,
+      "loss": 1.1003,
+      "step": 149
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.0838642120361328,
+      "learning_rate": 0.00015353040254690393,
+      "loss": 1.3472,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1831884384155273,
+      "learning_rate": 0.0001528752163676964,
+      "loss": 1.3466,
+      "step": 151
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.8773367404937744,
+      "learning_rate": 0.00015221686428501928,
+      "loss": 1.6197,
+      "step": 152
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0825533866882324,
+      "learning_rate": 0.00015155538571770218,
+      "loss": 1.4016,
+      "step": 153
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7868863940238953,
+      "learning_rate": 0.0001508908202717729,
+      "loss": 1.4014,
+      "step": 154
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.9290267825126648,
+      "learning_rate": 0.00015022320773808612,
+      "loss": 1.16,
+      "step": 155
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.9752824902534485,
+      "learning_rate": 0.00014955258808994096,
+      "loss": 1.1949,
+      "step": 156
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.876549243927002,
+      "learning_rate": 0.00014887900148068735,
+      "loss": 1.2258,
+      "step": 157
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6399539113044739,
+      "learning_rate": 0.0001482024882413222,
+      "loss": 0.8452,
+      "step": 158
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6850602030754089,
+      "learning_rate": 0.00014752308887807427,
+      "loss": 0.8122,
+      "step": 159
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7485994696617126,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.9129,
+      "step": 160
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7684512734413147,
+      "learning_rate": 0.00014615579466644292,
+      "loss": 1.1828,
+      "step": 161
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1462233066558838,
+      "learning_rate": 0.00014546798168479756,
+      "loss": 1.067,
+      "step": 162
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7982854843139648,
+      "learning_rate": 0.00014477744630784378,
+      "loss": 0.7413,
+      "step": 163
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.8392084836959839,
+      "learning_rate": 0.00014408422988138584,
+      "loss": 0.8734,
+      "step": 164
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.0327231884002686,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 1.37,
+      "step": 165
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.7807676196098328,
+      "learning_rate": 0.00014268992006332846,
+      "loss": 1.0077,
+      "step": 166
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.7953339219093323,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 1.1208,
+      "step": 167
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.3525584936141968,
+      "learning_rate": 0.0001412853861628166,
+      "loss": 1.0539,
+      "step": 168
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9052585363388062,
+      "learning_rate": 0.0001405793902071964,
+      "loss": 1.2677,
+      "step": 169
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9520561099052429,
+      "learning_rate": 0.00013987096456067236,
+      "loss": 1.3438,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3817763328552246,
+      "learning_rate": 0.00013916015164022852,
+      "loss": 1.128,
+      "step": 171
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0267670154571533,
+      "learning_rate": 0.00013844699400578696,
+      "loss": 1.201,
+      "step": 172
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.2591007947921753,
+      "learning_rate": 0.00013773153435765964,
+      "loss": 1.2994,
+      "step": 173
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0140405893325806,
+      "learning_rate": 0.00013701381553399145,
+      "loss": 1.3077,
+      "step": 174
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.9484094977378845,
+      "learning_rate": 0.00013629388050819547,
+      "loss": 1.3431,
+      "step": 175
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.057604193687439,
+      "learning_rate": 0.00013557177238637986,
+      "loss": 1.235,
+      "step": 176
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1387184858322144,
+      "learning_rate": 0.00013484753440476692,
+      "loss": 1.3051,
+      "step": 177
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7856025695800781,
+      "learning_rate": 0.00013412120992710425,
+      "loss": 0.8797,
+      "step": 178
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.8861658573150635,
+      "learning_rate": 0.00013339284244206847,
+      "loss": 1.008,
+      "step": 179
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.06355619430542,
+      "learning_rate": 0.00013266247556066122,
+      "loss": 1.4541,
+      "step": 180
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.9280688762664795,
+      "learning_rate": 0.000131930153013598,
+      "loss": 1.1963,
+      "step": 181
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.9036038517951965,
+      "learning_rate": 0.0001311959186486898,
+      "loss": 0.9803,
+      "step": 182
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.7766662240028381,
+      "learning_rate": 0.0001304598164282176,
+      "loss": 1.1155,
+      "step": 183
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.0177185535430908,
+      "learning_rate": 0.00012972189042630044,
+      "loss": 0.9596,
+      "step": 184
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.9740273952484131,
+      "learning_rate": 0.00012898218482625606,
+      "loss": 1.3439,
+      "step": 185
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.7388937473297119,
+      "learning_rate": 0.0001282407439179557,
+      "loss": 1.2573,
+      "step": 186
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.952064037322998,
+      "learning_rate": 0.0001274976120951723,
+      "loss": 1.2573,
+      "step": 187
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.849350094795227,
+      "learning_rate": 0.00012675283385292212,
+      "loss": 1.2124,
+      "step": 188
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.9224015474319458,
+      "learning_rate": 0.00012600645378480082,
+      "loss": 1.1693,
+      "step": 189
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8120655417442322,
+      "learning_rate": 0.00012525851658031352,
+      "loss": 1.1117,
+      "step": 190
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.793065071105957,
+      "learning_rate": 0.0001245090670221987,
+      "loss": 1.4568,
+      "step": 191
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8071841597557068,
+      "learning_rate": 0.00012375814998374712,
+      "loss": 1.1733,
+      "step": 192
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.0794304609298706,
+      "learning_rate": 0.00012300581042611492,
+      "loss": 0.997,
+      "step": 193
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7968724370002747,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 1.0403,
+      "step": 194
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0258793830871582,
+      "learning_rate": 0.00012149704402110243,
+      "loss": 1.4506,
+      "step": 195
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7685389518737793,
+      "learning_rate": 0.00012074070751110751,
+      "loss": 0.9257,
+      "step": 196
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9771597385406494,
+      "learning_rate": 0.00011998312915129371,
+      "loss": 0.9478,
+      "step": 197
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.8616073727607727,
+      "learning_rate": 0.0001192243543016637,
+      "loss": 1.2277,
+      "step": 198
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.6608029007911682,
+      "learning_rate": 0.00011846442839386003,
+      "loss": 0.7004,
+      "step": 199
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2879540920257568,
+      "learning_rate": 0.00011770339692844483,
+      "loss": 1.3485,
+      "step": 200
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.8453806638717651,
+      "learning_rate": 0.00011694130547217554,
+      "loss": 1.0356,
+      "step": 201
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.0563206672668457,
+      "learning_rate": 0.0001161781996552765,
+      "loss": 0.9449,
+      "step": 202
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1731258630752563,
+      "learning_rate": 0.00011541412516870684,
+      "loss": 1.1213,
+      "step": 203
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9057393074035645,
+      "learning_rate": 0.00011464912776142494,
+      "loss": 1.1281,
+      "step": 204
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8910503387451172,
+      "learning_rate": 0.00011388325323764888,
+      "loss": 1.3129,
+      "step": 205
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.099128484725952,
+      "learning_rate": 0.00011311654745411425,
+      "loss": 1.4921,
+      "step": 206
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.8299047946929932,
+      "learning_rate": 0.00011234905631732819,
+      "loss": 1.1755,
+      "step": 207
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.8262067437171936,
+      "learning_rate": 0.00011158082578082089,
+      "loss": 1.0692,
+      "step": 208
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.9301685690879822,
+      "learning_rate": 0.00011081190184239419,
+      "loss": 1.2959,
+      "step": 209
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.7783687114715576,
+      "learning_rate": 0.00011004233054136725,
+      "loss": 1.0235,
+      "step": 210
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8740360140800476,
+      "learning_rate": 0.00010927215795582012,
+      "loss": 1.2894,
+      "step": 211
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9843310117721558,
+      "learning_rate": 0.00010850143019983474,
+      "loss": 0.891,
+      "step": 212
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0247008800506592,
+      "learning_rate": 0.0001077301934207339,
+      "loss": 1.4805,
+      "step": 213
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8254871368408203,
+      "learning_rate": 0.00010695849379631813,
+      "loss": 1.0905,
+      "step": 214
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.122007131576538,
+      "eval_runtime": 4.6129,
+      "eval_samples_per_second": 21.678,
+      "eval_steps_per_second": 21.678,
+      "step": 214
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9306489825248718,
+      "learning_rate": 0.00010618637753210085,
+      "loss": 1.1526,
+      "step": 215
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.9931721091270447,
+      "learning_rate": 0.00010541389085854176,
+      "loss": 1.1198,
+      "step": 216
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.9121679663658142,
+      "learning_rate": 0.00010464108002827882,
+      "loss": 0.9779,
+      "step": 217
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.091155767440796,
+      "learning_rate": 0.00010386799131335889,
+      "loss": 1.2817,
+      "step": 218
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.9759095907211304,
+      "learning_rate": 0.00010309467100246713,
+      "loss": 1.1902,
+      "step": 219
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0254298448562622,
+      "learning_rate": 0.00010232116539815558,
+      "loss": 1.0221,
+      "step": 220
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0925480127334595,
+      "learning_rate": 0.00010154752081407066,
+      "loss": 1.142,
+      "step": 221
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7804872989654541,
+      "learning_rate": 0.00010077378357218021,
+      "loss": 1.1341,
+      "step": 222
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0329289436340332,
+      "learning_rate": 0.0001,
+      "loss": 1.0699,
+      "step": 223
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.8126528859138489,
+      "learning_rate": 9.92262164278198e-05,
+      "loss": 1.2582,
+      "step": 224
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.8940727710723877,
+      "learning_rate": 9.845247918592937e-05,
+      "loss": 0.948,
+      "step": 225
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.9005630016326904,
+      "learning_rate": 9.767883460184443e-05,
+      "loss": 1.1758,
+      "step": 226
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.8826602697372437,
+      "learning_rate": 9.69053289975329e-05,
+      "loss": 1.0277,
+      "step": 227
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.7822252511978149,
+      "learning_rate": 9.613200868664112e-05,
+      "loss": 0.9718,
+      "step": 228
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8417437076568604,
+      "learning_rate": 9.53589199717212e-05,
+      "loss": 1.3759,
+      "step": 229
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.801726758480072,
+      "learning_rate": 9.458610914145826e-05,
+      "loss": 1.2302,
+      "step": 230
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.7820351123809814,
+      "learning_rate": 9.381362246789917e-05,
+      "loss": 0.9784,
+      "step": 231
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8511584401130676,
+      "learning_rate": 9.304150620368188e-05,
+      "loss": 1.2409,
+      "step": 232
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.9426187872886658,
+      "learning_rate": 9.226980657926614e-05,
+      "loss": 1.1604,
+      "step": 233
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.171368956565857,
+      "learning_rate": 9.149856980016529e-05,
+      "loss": 0.836,
+      "step": 234
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.8709436058998108,
+      "learning_rate": 9.072784204417995e-05,
+      "loss": 1.1157,
+      "step": 235
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.933211088180542,
+      "learning_rate": 8.995766945863277e-05,
+      "loss": 1.3549,
+      "step": 236
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.7886441349983215,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 1.1515,
+      "step": 237
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.747288167476654,
+      "learning_rate": 8.841917421917912e-05,
+      "loss": 0.9248,
+      "step": 238
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8038252592086792,
+      "learning_rate": 8.765094368267186e-05,
+      "loss": 0.8667,
+      "step": 239
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.7888665795326233,
+      "learning_rate": 8.688345254588578e-05,
+      "loss": 1.0537,
+      "step": 240
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.094549536705017,
+      "learning_rate": 8.611674676235115e-05,
+      "loss": 1.1782,
+      "step": 241
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.7410706281661987,
+      "learning_rate": 8.535087223857508e-05,
+      "loss": 1.029,
+      "step": 242
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8244362473487854,
+      "learning_rate": 8.458587483129316e-05,
+      "loss": 1.0919,
+      "step": 243
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8174493312835693,
+      "learning_rate": 8.382180034472353e-05,
+      "loss": 1.2227,
+      "step": 244
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.7158798575401306,
+      "learning_rate": 8.305869452782446e-05,
+      "loss": 1.109,
+      "step": 245
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.8245162963867188,
+      "learning_rate": 8.229660307155518e-05,
+      "loss": 1.2469,
+      "step": 246
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.8199716806411743,
+      "learning_rate": 8.153557160613998e-05,
+      "loss": 1.2334,
+      "step": 247
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.8087395429611206,
+      "learning_rate": 8.077564569833632e-05,
+      "loss": 0.8122,
+      "step": 248
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9640026688575745,
+      "learning_rate": 8.00168708487063e-05,
+      "loss": 0.8892,
+      "step": 249
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.9019801616668701,
+      "learning_rate": 7.92592924888925e-05,
+      "loss": 1.1128,
+      "step": 250
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.920712947845459,
+      "learning_rate": 7.85029559788976e-05,
+      "loss": 1.0292,
+      "step": 251
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.7551796436309814,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.9783,
+      "step": 252
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.01247239112854,
+      "learning_rate": 7.699418957388512e-05,
+      "loss": 1.2214,
+      "step": 253
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6323232650756836,
+      "learning_rate": 7.624185001625292e-05,
+      "loss": 0.5998,
+      "step": 254
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7825503945350647,
+      "learning_rate": 7.549093297780132e-05,
+      "loss": 1.0062,
+      "step": 255
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7228556275367737,
+      "learning_rate": 7.474148341968652e-05,
+      "loss": 0.6876,
+      "step": 256
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.272310495376587,
+      "learning_rate": 7.39935462151992e-05,
+      "loss": 1.042,
+      "step": 257
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.1196962594985962,
+      "learning_rate": 7.324716614707793e-05,
+      "loss": 1.1608,
+      "step": 258
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.7413707971572876,
+      "learning_rate": 7.250238790482773e-05,
+      "loss": 0.9734,
+      "step": 259
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.2565113306045532,
+      "learning_rate": 7.175925608204428e-05,
+      "loss": 1.3064,
+      "step": 260
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.789618968963623,
+      "learning_rate": 7.101781517374398e-05,
+      "loss": 1.3269,
+      "step": 261
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.8871381878852844,
+      "learning_rate": 7.027810957369957e-05,
+      "loss": 0.86,
+      "step": 262
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9494991302490234,
+      "learning_rate": 6.954018357178241e-05,
+      "loss": 1.1312,
+      "step": 263
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9433842897415161,
+      "learning_rate": 6.880408135131022e-05,
+      "loss": 1.4065,
+      "step": 264
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0069125890731812,
+      "learning_rate": 6.806984698640202e-05,
+      "loss": 1.1966,
+      "step": 265
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6543261408805847,
+      "learning_rate": 6.733752443933878e-05,
+      "loss": 0.7893,
+      "step": 266
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.6551367044448853,
+      "learning_rate": 6.660715755793154e-05,
+      "loss": 1.4264,
+      "step": 267
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.6854212284088135,
+      "learning_rate": 6.587879007289576e-05,
+      "loss": 0.7446,
+      "step": 268
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.9157115817070007,
+      "learning_rate": 6.515246559523312e-05,
+      "loss": 1.2289,
+      "step": 269
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.8367937207221985,
+      "learning_rate": 6.442822761362015e-05,
+      "loss": 1.1291,
+      "step": 270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.9523156881332397,
+      "learning_rate": 6.370611949180457e-05,
+      "loss": 1.2549,
+      "step": 271
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8018501400947571,
+      "learning_rate": 6.298618446600856e-05,
+      "loss": 1.2464,
+      "step": 272
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0242061614990234,
+      "learning_rate": 6.22684656423404e-05,
+      "loss": 1.114,
+      "step": 273
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0759499073028564,
+      "learning_rate": 6.155300599421306e-05,
+      "loss": 0.866,
+      "step": 274
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.7727057337760925,
+      "learning_rate": 6.0839848359771536e-05,
+      "loss": 0.9828,
+      "step": 275
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8630977869033813,
+      "learning_rate": 6.012903543932766e-05,
+      "loss": 1.2963,
+      "step": 276
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.1302142143249512,
+      "learning_rate": 5.9420609792803604e-05,
+      "loss": 1.2394,
+      "step": 277
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.905367374420166,
+      "learning_rate": 5.871461383718344e-05,
+      "loss": 1.3546,
+      "step": 278
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8619841933250427,
+      "learning_rate": 5.801108984397354e-05,
+      "loss": 1.1971,
+      "step": 279
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.7877105474472046,
+      "learning_rate": 5.7310079936671545e-05,
+      "loss": 1.1946,
+      "step": 280
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8128871917724609,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 0.9827,
+      "step": 281
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8880854845046997,
+      "learning_rate": 5.59157701186142e-05,
+      "loss": 0.9885,
+      "step": 282
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8349465727806091,
+      "learning_rate": 5.522255369215622e-05,
+      "loss": 1.2848,
+      "step": 283
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8847686648368835,
+      "learning_rate": 5.453201831520245e-05,
+      "loss": 1.1092,
+      "step": 284
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.9228406548500061,
+      "learning_rate": 5.38442053335571e-05,
+      "loss": 1.1529,
+      "step": 285
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.9547788500785828,
+      "learning_rate": 5.3159155930021e-05,
+      "loss": 1.2343,
+      "step": 286
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0922831296920776,
+      "learning_rate": 5.247691112192577e-05,
+      "loss": 1.296,
+      "step": 287
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9485066533088684,
+      "learning_rate": 5.179751175867784e-05,
+      "loss": 0.9976,
+      "step": 288
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.7523879408836365,
+      "learning_rate": 5.112099851931265e-05,
+      "loss": 0.9032,
+      "step": 289
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0466837882995605,
+      "learning_rate": 5.044741191005908e-05,
+      "loss": 1.4829,
+      "step": 290
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9014366269111633,
+      "learning_rate": 4.9776792261913896e-05,
+      "loss": 1.0843,
+      "step": 291
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9814268946647644,
+      "learning_rate": 4.910917972822713e-05,
+      "loss": 1.1762,
+      "step": 292
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8316671252250671,
+      "learning_rate": 4.844461428229782e-05,
+      "loss": 1.146,
+      "step": 293
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9291322827339172,
+      "learning_rate": 4.7783135714980744e-05,
+      "loss": 1.0792,
+      "step": 294
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.015356421470642,
+      "learning_rate": 4.712478363230362e-05,
+      "loss": 1.4492,
+      "step": 295
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8872371315956116,
+      "learning_rate": 4.646959745309609e-05,
+      "loss": 0.8613,
+      "step": 296
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0304248332977295,
+      "learning_rate": 4.581761640662927e-05,
+      "loss": 1.1013,
+      "step": 297
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.793870210647583,
+      "learning_rate": 4.516887953026691e-05,
+      "loss": 0.8556,
+      "step": 298
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.7005939483642578,
+      "learning_rate": 4.452342566712818e-05,
+      "loss": 0.9191,
+      "step": 299
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0646456480026245,
+      "learning_rate": 4.388129346376178e-05,
+      "loss": 1.4374,
+      "step": 300
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9402028322219849,
+      "learning_rate": 4.3242521367832015e-05,
+      "loss": 1.0451,
+      "step": 301
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.8696098327636719,
+      "learning_rate": 4.260714762581677e-05,
+      "loss": 1.1377,
+      "step": 302
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9871663451194763,
+      "learning_rate": 4.197521028071765e-05,
+      "loss": 1.2126,
+      "step": 303
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9076434969902039,
+      "learning_rate": 4.13467471697817e-05,
+      "loss": 1.0153,
+      "step": 304
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8657947778701782,
+      "learning_rate": 4.0721795922236496e-05,
+      "loss": 1.1835,
+      "step": 305
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.6072056293487549,
+      "learning_rate": 4.010039395703664e-05,
+      "loss": 1.2517,
+      "step": 306
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.8781859874725342,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 1.2192,
+      "step": 307
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6578808426856995,
+      "learning_rate": 3.8868386484697417e-05,
+      "loss": 0.9224,
+      "step": 308
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9013091921806335,
+      "learning_rate": 3.825785474400291e-05,
+      "loss": 1.0601,
+      "step": 309
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9491739869117737,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 1.1021,
+      "step": 310
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.0723105669021606,
+      "learning_rate": 3.7047918029308815e-05,
+      "loss": 1.3365,
+      "step": 311
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9843062162399292,
+      "learning_rate": 3.6448585500267485e-05,
+      "loss": 1.1171,
+      "step": 312
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9364001750946045,
+      "learning_rate": 3.5853058112036596e-05,
+      "loss": 1.3634,
+      "step": 313
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.677176833152771,
+      "learning_rate": 3.5261371521817244e-05,
+      "loss": 0.8549,
+      "step": 314
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0187640190124512,
+      "learning_rate": 3.467356115684284e-05,
+      "loss": 1.055,
+      "step": 315
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.9334242939949036,
+      "learning_rate": 3.408966221225773e-05,
+      "loss": 1.1827,
+      "step": 316
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0158796310424805,
+      "learning_rate": 3.350970964900998e-05,
+      "loss": 1.4149,
+      "step": 317
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7531949877738953,
+      "learning_rate": 3.293373819175816e-05,
+      "loss": 1.0654,
+      "step": 318
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7838178277015686,
+      "learning_rate": 3.236178232679202e-05,
+      "loss": 0.9998,
+      "step": 319
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.8562126755714417,
+      "learning_rate": 3.1793876299967816e-05,
+      "loss": 1.116,
+      "step": 320
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.0082615613937378,
+      "learning_rate": 3.123005411465766e-05,
+      "loss": 1.323,
+      "step": 321
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.110154628753662,
+      "eval_runtime": 4.6829,
+      "eval_samples_per_second": 21.354,
+      "eval_steps_per_second": 21.354,
+      "step": 321
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9480220675468445,
+      "learning_rate": 3.0670349529713816e-05,
+      "loss": 1.0395,
+      "step": 322
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1284518241882324,
+      "learning_rate": 3.0114796057447026e-05,
+      "loss": 1.4027,
+      "step": 323
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0139000415802002,
+      "learning_rate": 2.9563426961620367e-05,
+      "loss": 1.4189,
+      "step": 324
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7573887705802917,
+      "learning_rate": 2.901627525545726e-05,
+      "loss": 0.8434,
+      "step": 325
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8869838714599609,
+      "learning_rate": 2.8473373699664997e-05,
+      "loss": 1.2955,
+      "step": 326
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8555613160133362,
+      "learning_rate": 2.793475480047303e-05,
+      "loss": 1.1054,
+      "step": 327
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.042114019393921,
+      "learning_rate": 2.7400450807686938e-05,
+      "loss": 1.5567,
+      "step": 328
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9764856100082397,
+      "learning_rate": 2.687049371275705e-05,
+      "loss": 1.1184,
+      "step": 329
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8084841370582581,
+      "learning_rate": 2.6344915246863412e-05,
+      "loss": 1.1947,
+      "step": 330
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.7911667823791504,
+      "learning_rate": 2.582374687901553e-05,
+      "loss": 1.1807,
+      "step": 331
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0174006223678589,
+      "learning_rate": 2.5307019814168342e-05,
+      "loss": 1.5032,
+      "step": 332
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9718097448348999,
+      "learning_rate": 2.4794764991353748e-05,
+      "loss": 1.4613,
+      "step": 333
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9452516436576843,
+      "learning_rate": 2.4287013081828257e-05,
+      "loss": 0.857,
+      "step": 334
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.7970743179321289,
+      "learning_rate": 2.3783794487236365e-05,
+      "loss": 1.1569,
+      "step": 335
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.4133670330047607,
+      "learning_rate": 2.328513933779034e-05,
+      "loss": 1.135,
+      "step": 336
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2680160999298096,
+      "learning_rate": 2.2791077490466262e-05,
+      "loss": 1.3429,
+      "step": 337
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9616788625717163,
+      "learning_rate": 2.2301638527216194e-05,
+      "loss": 1.05,
+      "step": 338
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2440178394317627,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 1.1399,
+      "step": 339
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8922715187072754,
+      "learning_rate": 2.1336746195015846e-05,
+      "loss": 1.2397,
+      "step": 340
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8706962466239929,
+      "learning_rate": 2.0861350598991945e-05,
+      "loss": 1.2491,
+      "step": 341
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7499839663505554,
+      "learning_rate": 2.0390693429435627e-05,
+      "loss": 0.9789,
+      "step": 342
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8695294260978699,
+      "learning_rate": 1.992480286694397e-05,
+      "loss": 1.1003,
+      "step": 343
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0640183687210083,
+      "learning_rate": 1.946370680671341e-05,
+      "loss": 1.3413,
+      "step": 344
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0847088098526,
+      "learning_rate": 1.90074328568696e-05,
+      "loss": 1.7681,
+      "step": 345
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.7911257147789001,
+      "learning_rate": 1.85560083368143e-05,
+      "loss": 1.1384,
+      "step": 346
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.995191752910614,
+      "learning_rate": 1.8109460275589773e-05,
+      "loss": 1.0634,
+      "step": 347
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8777083158493042,
+      "learning_rate": 1.766781541026018e-05,
+      "loss": 1.1154,
+      "step": 348
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.470664381980896,
+      "learning_rate": 1.7231100184310956e-05,
+      "loss": 1.5478,
+      "step": 349
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8574717044830322,
+      "learning_rate": 1.679934074606533e-05,
+      "loss": 1.2001,
+      "step": 350
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8735147714614868,
+      "learning_rate": 1.6372562947118763e-05,
+      "loss": 1.3081,
+      "step": 351
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.6728559136390686,
+      "learning_rate": 1.5950792340791043e-05,
+      "loss": 0.9461,
+      "step": 352
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1059622764587402,
+      "learning_rate": 1.5534054180596415e-05,
+      "loss": 1.1666,
+      "step": 353
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.9656254053115845,
+      "learning_rate": 1.5122373418731306e-05,
+      "loss": 1.3456,
+      "step": 354
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.7049956321716309,
+      "learning_rate": 1.4715774704580453e-05,
+      "loss": 1.1051,
+      "step": 355
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8989938497543335,
+      "learning_rate": 1.4314282383241096e-05,
+      "loss": 1.0213,
+      "step": 356
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7486435770988464,
+      "learning_rate": 1.3917920494065029e-05,
+      "loss": 1.1314,
+      "step": 357
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9318729639053345,
+      "learning_rate": 1.3526712769219618e-05,
+      "loss": 1.4529,
+      "step": 358
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8596606850624084,
+      "learning_rate": 1.3140682632266543e-05,
+      "loss": 0.9848,
+      "step": 359
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9519713521003723,
+      "learning_rate": 1.2759853196759453e-05,
+      "loss": 1.3027,
+      "step": 360
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.1047871112823486,
+      "learning_rate": 1.2384247264859972e-05,
+      "loss": 1.3237,
+      "step": 361
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.7814332246780396,
+      "learning_rate": 1.201388732597255e-05,
+      "loss": 0.9958,
+      "step": 362
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9286463260650635,
+      "learning_rate": 1.1648795555397719e-05,
+      "loss": 1.2046,
+      "step": 363
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.4703665971755981,
+      "learning_rate": 1.1288993813004467e-05,
+      "loss": 1.3091,
+      "step": 364
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2573424577713013,
+      "learning_rate": 1.0934503641921402e-05,
+      "loss": 2.7786,
+      "step": 365
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7916259169578552,
+      "learning_rate": 1.0585346267246743e-05,
+      "loss": 1.1154,
+      "step": 366
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2563278675079346,
+      "learning_rate": 1.0241542594777576e-05,
+      "loss": 1.3654,
+      "step": 367
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7537509202957153,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 1.1905,
+      "step": 368
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.7813998460769653,
+      "learning_rate": 9.570078375647006e-06,
+      "loss": 1.1525,
+      "step": 369
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.1447442770004272,
+      "learning_rate": 9.242458032904311e-06,
+      "loss": 1.0021,
+      "step": 370
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.9054378867149353,
+      "learning_rate": 8.92027179779732e-06,
+      "loss": 1.0541,
+      "step": 371
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.138863444328308,
+      "learning_rate": 8.603538961226232e-06,
+      "loss": 1.0078,
+      "step": 372
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8442170023918152,
+      "learning_rate": 8.29227848756895e-06,
+      "loss": 0.9012,
+      "step": 373
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8788736462593079,
+      "learning_rate": 7.986509013545673e-06,
+      "loss": 1.1114,
+      "step": 374
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.021142840385437,
+      "learning_rate": 7.686248847103072e-06,
+      "loss": 1.1777,
+      "step": 375
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9009897708892822,
+      "learning_rate": 7.3915159663179075e-06,
+      "loss": 1.2008,
+      "step": 376
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9428213834762573,
+      "learning_rate": 7.102328018320858e-06,
+      "loss": 1.1237,
+      "step": 377
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.8773625493049622,
+      "learning_rate": 6.818702318239689e-06,
+      "loss": 1.3511,
+      "step": 378
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.087082028388977,
+      "learning_rate": 6.540655848162602e-06,
+      "loss": 1.3119,
+      "step": 379
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.8091554045677185,
+      "learning_rate": 6.268205256121396e-06,
+      "loss": 1.0414,
+      "step": 380
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.856467604637146,
+      "learning_rate": 6.001366855094748e-06,
+      "loss": 1.1321,
+      "step": 381
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9399726390838623,
+      "learning_rate": 5.7401566220313005e-06,
+      "loss": 1.1264,
+      "step": 382
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9808714985847473,
+      "learning_rate": 5.484590196893247e-06,
+      "loss": 1.2507,
+      "step": 383
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8338817358016968,
+      "learning_rate": 5.2346828817197655e-06,
+      "loss": 1.176,
+      "step": 384
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.076346755027771,
+      "learning_rate": 4.990449639710815e-06,
+      "loss": 1.4701,
+      "step": 385
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3114168643951416,
+      "learning_rate": 4.7519050943312325e-06,
+      "loss": 1.1993,
+      "step": 386
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.383102536201477,
+      "learning_rate": 4.5190635284352075e-06,
+      "loss": 1.0222,
+      "step": 387
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.7202867865562439,
+      "learning_rate": 4.291938883411007e-06,
+      "loss": 0.4224,
+      "step": 388
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.7904449105262756,
+      "learning_rate": 4.070544758346273e-06,
+      "loss": 1.1798,
+      "step": 389
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8682311177253723,
+      "learning_rate": 3.85489440921376e-06,
+      "loss": 1.1389,
+      "step": 390
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.9757256507873535,
+      "learning_rate": 3.6450007480777093e-06,
+      "loss": 1.3057,
+      "step": 391
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8438984751701355,
+      "learning_rate": 3.440876342320609e-06,
+      "loss": 1.0613,
+      "step": 392
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0326892137527466,
+      "learning_rate": 3.2425334138908583e-06,
+      "loss": 0.987,
+      "step": 393
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.9625622630119324,
+      "learning_rate": 3.049983838570858e-06,
+      "loss": 0.7992,
+      "step": 394
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.869756817817688,
+      "learning_rate": 2.863239145266028e-06,
+      "loss": 1.2917,
+      "step": 395
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0128636360168457,
+      "learning_rate": 2.682310515314512e-06,
+      "loss": 1.0237,
+      "step": 396
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.8120230436325073,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 0.8368,
+      "step": 397
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.8616847395896912,
+      "learning_rate": 2.3379444289913342e-06,
+      "loss": 1.0892,
+      "step": 398
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1150074005126953,
+      "learning_rate": 2.174527591538367e-06,
+      "loss": 1.3495,
+      "step": 399
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.0317437648773193,
+      "learning_rate": 2.016968054041546e-06,
+      "loss": 1.6286,
+      "step": 400
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9908115267753601,
+      "learning_rate": 1.8652752503778404e-06,
+      "loss": 1.215,
+      "step": 401
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9031442999839783,
+      "learning_rate": 1.7194582631535617e-06,
+      "loss": 0.8664,
+      "step": 402
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.7035516500473022,
+      "learning_rate": 1.5795258231605103e-06,
+      "loss": 0.7614,
+      "step": 403
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8984954357147217,
+      "learning_rate": 1.4454863088532388e-06,
+      "loss": 1.0593,
+      "step": 404
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.2464302778244019,
+      "learning_rate": 1.317347745847386e-06,
+      "loss": 1.2341,
+      "step": 405
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8292190432548523,
+      "learning_rate": 1.19511780643915e-06,
+      "loss": 1.1548,
+      "step": 406
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1433041095733643,
+      "learning_rate": 1.0788038091458897e-06,
+      "loss": 1.2587,
+      "step": 407
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8059953451156616,
+      "learning_rate": 9.684127182679526e-07,
+      "loss": 1.0997,
+      "step": 408
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8124595880508423,
+      "learning_rate": 8.639511434716863e-07,
+      "loss": 1.2506,
+      "step": 409
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9550383687019348,
+      "learning_rate": 7.654253393936439e-07,
+      "loss": 1.1916,
+      "step": 410
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9518684148788452,
+      "learning_rate": 6.728412052661504e-07,
+      "loss": 1.4701,
+      "step": 411
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.8674444556236267,
+      "learning_rate": 5.862042845640403e-07,
+      "loss": 1.14,
+      "step": 412
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.854787290096283,
+      "learning_rate": 5.055197646727572e-07,
+      "loss": 1.1427,
+      "step": 413
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.0092004537582397,
+      "learning_rate": 4.307924765777682e-07,
+      "loss": 1.1285,
+      "step": 414
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.8621972799301147,
+      "learning_rate": 3.620268945752847e-07,
+      "loss": 1.2702,
+      "step": 415
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9072843194007874,
+      "learning_rate": 2.9922713600439854e-07,
+      "loss": 1.6336,
+      "step": 416
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7977897524833679,
+      "learning_rate": 2.423969610005017e-07,
+      "loss": 0.7256,
+      "step": 417
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1193830966949463,
+      "learning_rate": 1.915397722702217e-07,
+      "loss": 1.2789,
+      "step": 418
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7878805994987488,
+      "learning_rate": 1.4665861488761813e-07,
+      "loss": 1.1138,
+      "step": 419
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.3625191450119019,
+      "learning_rate": 1.0775617611189503e-07,
+      "loss": 0.964,
+      "step": 420
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9271944165229797,
+      "learning_rate": 7.483478522649634e-08,
+      "loss": 1.1211,
+      "step": 421
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8852077722549438,
+      "learning_rate": 4.789641339963957e-08,
+      "loss": 1.2948,
+      "step": 422
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8668275475502014,
+      "learning_rate": 2.6942673566265897e-08,
+      "loss": 1.2833,
+      "step": 423
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8821643590927124,
+      "learning_rate": 1.1974820331517312e-08,
+      "loss": 1.407,
+      "step": 424
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8318036198616028,
+      "learning_rate": 2.9937498955745493e-09,
+      "loss": 1.0075,
+      "step": 425
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.788590669631958,
+      "learning_rate": 0.0,
+      "loss": 0.8834,
+      "step": 426
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 426,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 7754585188270080.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-426/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a470c9bc65ff1c7aee513b4815676c03d5364fde308e102b0462e5888662c1e9
+size 5624

checkpoint-431/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openlm-research/open_llama_3b_v2
+---
+
+# 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-431/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-431/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32977da3155fa1c57dd8bf5fc9256904b8b90451cc9de27ba75597e146638674
+size 50899792

checkpoint-431/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3312dd5154a684f6f2100945a99d002db2a33343abd6cc6b55978f8820af3c24
+size 101919290

checkpoint-431/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b506d602a9aceef7a87ef4665405abfeeaf3645bcf975dd29d0787810ce9a177
+size 14244

checkpoint-431/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f73a16ac262980457d80b6b9e4834ebbf9e3ee06ac2280222318fcdf9e15a8
+size 1064

checkpoint-431/trainer_state.json

@@ -0,0 +1,3070 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 108,
+  "global_step": 431,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.949445366859436,
+      "learning_rate": 1e-05,
+      "loss": 1.2567,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.3469438552856445,
+      "eval_runtime": 4.4705,
+      "eval_samples_per_second": 22.369,
+      "eval_steps_per_second": 22.369,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.8507896065711975,
+      "learning_rate": 2e-05,
+      "loss": 1.3328,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.1072367429733276,
+      "learning_rate": 3e-05,
+      "loss": 1.6567,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.519516944885254,
+      "learning_rate": 4e-05,
+      "loss": 1.5499,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.7287861704826355,
+      "learning_rate": 5e-05,
+      "loss": 1.4337,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.2137192487716675,
+      "learning_rate": 6e-05,
+      "loss": 1.2657,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.0216978788375854,
+      "learning_rate": 7e-05,
+      "loss": 1.4715,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.9651184678077698,
+      "learning_rate": 8e-05,
+      "loss": 1.4058,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8699764609336853,
+      "learning_rate": 9e-05,
+      "loss": 1.2822,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7840852737426758,
+      "learning_rate": 0.0001,
+      "loss": 1.1426,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8829829692840576,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.4651,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8318219184875488,
+      "learning_rate": 0.00012,
+      "loss": 0.9747,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.346136450767517,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.5122,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0932445526123047,
+      "learning_rate": 0.00014,
+      "loss": 1.1516,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.2486791610717773,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2722,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.446858286857605,
+      "learning_rate": 0.00016,
+      "loss": 1.3268,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0801032781600952,
+      "learning_rate": 0.00017,
+      "loss": 1.2944,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0723249912261963,
+      "learning_rate": 0.00018,
+      "loss": 1.3235,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8839237093925476,
+      "learning_rate": 0.00019,
+      "loss": 1.203,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.7870981693267822,
+      "learning_rate": 0.0002,
+      "loss": 1.1922,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.437753438949585,
+      "learning_rate": 0.00019999707864731247,
+      "loss": 1.2289,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.4064440727233887,
+      "learning_rate": 0.00019998831475993593,
+      "loss": 1.3205,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.4990166425704956,
+      "learning_rate": 0.00019997370884991842,
+      "loss": 1.5893,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.1783679723739624,
+      "learning_rate": 0.0001999532617706403,
+      "loss": 1.3094,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0205744504928589,
+      "learning_rate": 0.00019992697471676413,
+      "loss": 1.3151,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0935940742492676,
+      "learning_rate": 0.00019989484922416502,
+      "loss": 1.2537,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9904759526252747,
+      "learning_rate": 0.0001998568871698409,
+      "loss": 1.1985,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0003483295440674,
+      "learning_rate": 0.00019981309077180272,
+      "loss": 1.0457,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.023276448249817,
+      "learning_rate": 0.00019976346258894503,
+      "loss": 1.3524,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3426311016082764,
+      "learning_rate": 0.00019970800552089623,
+      "loss": 1.2572,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.9393813014030457,
+      "learning_rate": 0.00019964672280784954,
+      "loss": 1.1576,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3142485618591309,
+      "learning_rate": 0.00019957961803037326,
+      "loss": 1.1848,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0402196645736694,
+      "learning_rate": 0.00019950669510920184,
+      "loss": 1.0087,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0158718824386597,
+      "learning_rate": 0.0001994279583050067,
+      "loss": 1.1926,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3834636211395264,
+      "learning_rate": 0.00019934341221814739,
+      "loss": 1.5813,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0681791305541992,
+      "learning_rate": 0.0001992530617884026,
+      "loss": 0.9701,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.0147560834884644,
+      "learning_rate": 0.00019915691229468178,
+      "loss": 1.1877,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.6721752882003784,
+      "learning_rate": 0.00019905496935471658,
+      "loss": 1.7297,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9919783473014832,
+      "learning_rate": 0.0001989472389247326,
+      "loss": 1.509,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.2846685647964478,
+      "learning_rate": 0.00019883372729910152,
+      "loss": 1.1308,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9084304571151733,
+      "learning_rate": 0.0001987144411099731,
+      "loss": 1.2434,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9819477200508118,
+      "learning_rate": 0.000198589387326888,
+      "loss": 1.2231,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.907674252986908,
+      "learning_rate": 0.00019845857325637031,
+      "loss": 1.527,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9865033030509949,
+      "learning_rate": 0.00019832200654150076,
+      "loss": 1.1143,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8477481007575989,
+      "learning_rate": 0.0001981796951614701,
+      "loss": 1.0935,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.0751707553863525,
+      "learning_rate": 0.00019803164743111302,
+      "loss": 1.2345,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.212093472480774,
+      "learning_rate": 0.00019787787200042223,
+      "loss": 1.3429,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8709837794303894,
+      "learning_rate": 0.00019771837785404305,
+      "loss": 0.9622,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.0572818517684937,
+      "learning_rate": 0.00019755317431074859,
+      "loss": 1.3914,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1103079319000244,
+      "learning_rate": 0.0001973822710228951,
+      "loss": 1.018,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1869310140609741,
+      "learning_rate": 0.00019720567797585817,
+      "loss": 1.3041,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1007969379425049,
+      "learning_rate": 0.0001970234054874493,
+      "loss": 1.1729,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.2385724782943726,
+      "learning_rate": 0.0001968354642073129,
+      "loss": 1.2543,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.1716569662094116,
+      "learning_rate": 0.00019664186511630433,
+      "loss": 0.883,
+      "step": 54
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7648707032203674,
+      "learning_rate": 0.000196442619525848,
+      "loss": 1.2307,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.192175030708313,
+      "learning_rate": 0.00019623773907727682,
+      "loss": 1.4194,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.2176754474639893,
+      "learning_rate": 0.0001960272357411517,
+      "loss": 1.3297,
+      "step": 57
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.8858970999717712,
+      "learning_rate": 0.0001958111218165624,
+      "loss": 1.1429,
+      "step": 58
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9252458214759827,
+      "learning_rate": 0.00019558940993040885,
+      "loss": 1.0657,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9035778045654297,
+      "learning_rate": 0.00019536211303666323,
+      "loss": 1.3623,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9124057292938232,
+      "learning_rate": 0.00019512924441561348,
+      "loss": 0.599,
+      "step": 61
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8610370755195618,
+      "learning_rate": 0.00019489081767308698,
+      "loss": 1.2562,
+      "step": 62
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.4054765701293945,
+      "learning_rate": 0.00019464684673965583,
+      "loss": 1.3822,
+      "step": 63
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7933898568153381,
+      "learning_rate": 0.0001943973458698229,
+      "loss": 0.9506,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.028634786605835,
+      "learning_rate": 0.00019414232964118892,
+      "loss": 1.1164,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9996744990348816,
+      "learning_rate": 0.00019388181295360078,
+      "loss": 1.0456,
+      "step": 66
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1415095329284668,
+      "learning_rate": 0.00019361581102828095,
+      "loss": 1.0508,
+      "step": 67
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8323081731796265,
+      "learning_rate": 0.0001933443394069383,
+      "loss": 1.1819,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.990214467048645,
+      "learning_rate": 0.00019306741395085976,
+      "loss": 1.1623,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8008455038070679,
+      "learning_rate": 0.0001927850508399839,
+      "loss": 1.1096,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9952508807182312,
+      "learning_rate": 0.00019249726657195532,
+      "loss": 1.3074,
+      "step": 71
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.9121832251548767,
+      "learning_rate": 0.00019220407796116098,
+      "loss": 1.309,
+      "step": 72
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.5662074089050293,
+      "learning_rate": 0.00019190550213774756,
+      "loss": 1.1578,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8138138055801392,
+      "learning_rate": 0.00019160155654662076,
+      "loss": 0.7039,
+      "step": 74
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.0473222732543945,
+      "learning_rate": 0.00019129225894642593,
+      "loss": 1.0794,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8314051032066345,
+      "learning_rate": 0.00019097762740851061,
+      "loss": 1.0441,
+      "step": 76
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0878669023513794,
+      "learning_rate": 0.0001906576803158686,
+      "loss": 1.1507,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.021689534187317,
+      "learning_rate": 0.0001903324363620659,
+      "loss": 1.0724,
+      "step": 78
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6085835695266724,
+      "learning_rate": 0.0001900019145501484,
+      "loss": 0.6315,
+      "step": 79
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8956215381622314,
+      "learning_rate": 0.0001896661341915318,
+      "loss": 1.4115,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.9094576239585876,
+      "learning_rate": 0.0001893251149048732,
+      "loss": 1.0351,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.9838559627532959,
+      "learning_rate": 0.00018897887661492474,
+      "loss": 1.1197,
+      "step": 82
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.0802074670791626,
+      "learning_rate": 0.00018862743955136966,
+      "loss": 1.4306,
+      "step": 83
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.7728214263916016,
+      "learning_rate": 0.0001882708242476401,
+      "loss": 1.0561,
+      "step": 84
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8827099800109863,
+      "learning_rate": 0.00018790905153971758,
+      "loss": 0.8641,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9011664390563965,
+      "learning_rate": 0.00018754214256491562,
+      "loss": 1.0551,
+      "step": 86
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7555330991744995,
+      "learning_rate": 0.00018717011876064453,
+      "loss": 1.0437,
+      "step": 87
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.902161180973053,
+      "learning_rate": 0.0001867930018631592,
+      "loss": 1.0091,
+      "step": 88
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.8388335704803467,
+      "learning_rate": 0.00018641081390628877,
+      "loss": 1.1971,
+      "step": 89
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.9152207374572754,
+      "learning_rate": 0.00018602357722014964,
+      "loss": 1.2934,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.7390096783638,
+      "learning_rate": 0.00018563131442984044,
+      "loss": 1.0418,
+      "step": 91
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.054923176765442,
+      "learning_rate": 0.00018523404845412027,
+      "loss": 1.1483,
+      "step": 92
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.5307762622833252,
+      "learning_rate": 0.0001848318025040697,
+      "loss": 1.3822,
+      "step": 93
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7944795489311218,
+      "learning_rate": 0.00018442460008173445,
+      "loss": 1.0146,
+      "step": 94
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.9003429412841797,
+      "learning_rate": 0.0001840124649787524,
+      "loss": 1.062,
+      "step": 95
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.0946155786514282,
+      "learning_rate": 0.0001835954212749632,
+      "loss": 1.1054,
+      "step": 96
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7898225784301758,
+      "learning_rate": 0.0001831734933370019,
+      "loss": 0.875,
+      "step": 97
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8385939598083496,
+      "learning_rate": 0.0001827467058168748,
+      "loss": 0.8868,
+      "step": 98
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.122320294380188,
+      "learning_rate": 0.00018231508365051922,
+      "loss": 1.3118,
+      "step": 99
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8597874641418457,
+      "learning_rate": 0.0001818786520563467,
+      "loss": 1.3222,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0316661596298218,
+      "learning_rate": 0.00018143743653376942,
+      "loss": 1.0929,
+      "step": 101
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0938916206359863,
+      "learning_rate": 0.0001809914628617105,
+      "loss": 1.5598,
+      "step": 102
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7412592768669128,
+      "learning_rate": 0.00018054075709709756,
+      "loss": 1.1524,
+      "step": 103
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.286882758140564,
+      "learning_rate": 0.00018008534557334064,
+      "loss": 1.2891,
+      "step": 104
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8679689168930054,
+      "learning_rate": 0.00017962525489879325,
+      "loss": 1.2164,
+      "step": 105
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9576878547668457,
+      "learning_rate": 0.00017916051195519797,
+      "loss": 0.9446,
+      "step": 106
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8837612867355347,
+      "learning_rate": 0.00017869114389611575,
+      "loss": 0.9996,
+      "step": 107
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.86222243309021,
+      "learning_rate": 0.0001782171781453394,
+      "loss": 1.1726,
+      "step": 108
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.1363587379455566,
+      "eval_runtime": 4.5587,
+      "eval_samples_per_second": 21.936,
+      "eval_steps_per_second": 21.936,
+      "step": 108
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8856573104858398,
+      "learning_rate": 0.00017773864239529132,
+      "loss": 1.0635,
+      "step": 109
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8627833127975464,
+      "learning_rate": 0.0001772555646054055,
+      "loss": 1.0891,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8263021111488342,
+      "learning_rate": 0.00017676797300049393,
+      "loss": 1.2359,
+      "step": 111
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1909066438674927,
+      "learning_rate": 0.00017627589606909755,
+      "loss": 1.2198,
+      "step": 112
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5449989438056946,
+      "learning_rate": 0.00017577936256182167,
+      "loss": 0.4532,
+      "step": 113
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9954172968864441,
+      "learning_rate": 0.0001752784014896562,
+      "loss": 1.3172,
+      "step": 114
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.8009255528450012,
+      "learning_rate": 0.00017477304212228057,
+      "loss": 1.0376,
+      "step": 115
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.8513997793197632,
+      "learning_rate": 0.0001742633139863538,
+      "loss": 1.1343,
+      "step": 116
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0654432773590088,
+      "learning_rate": 0.00017374924686378905,
+      "loss": 1.2319,
+      "step": 117
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.2617158889770508,
+      "learning_rate": 0.0001732308707900137,
+      "loss": 1.1578,
+      "step": 118
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8207240104675293,
+      "learning_rate": 0.0001727082160522145,
+      "loss": 1.114,
+      "step": 119
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.868678629398346,
+      "learning_rate": 0.0001721813131875679,
+      "loss": 1.0403,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9377112984657288,
+      "learning_rate": 0.00017165019298145585,
+      "loss": 0.7393,
+      "step": 121
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.8332670331001282,
+      "learning_rate": 0.00017111488646566727,
+      "loss": 1.1088,
+      "step": 122
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9136579036712646,
+      "learning_rate": 0.00017057542491658468,
+      "loss": 1.3177,
+      "step": 123
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9743526577949524,
+      "learning_rate": 0.000170031839853357,
+      "loss": 1.3773,
+      "step": 124
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.9520983099937439,
+      "learning_rate": 0.00016948416303605795,
+      "loss": 1.4045,
+      "step": 125
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.7437195181846619,
+      "learning_rate": 0.0001689324264638304,
+      "loss": 0.8205,
+      "step": 126
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.6287678480148315,
+      "learning_rate": 0.00016837666237301663,
+      "loss": 0.5968,
+      "step": 127
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0181548595428467,
+      "learning_rate": 0.00016781690323527511,
+      "loss": 1.1309,
+      "step": 128
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8763456344604492,
+      "learning_rate": 0.00016725318175568306,
+      "loss": 1.0159,
+      "step": 129
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8480902314186096,
+      "learning_rate": 0.00016668553087082567,
+      "loss": 1.2932,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.916015088558197,
+      "learning_rate": 0.0001661139837468717,
+      "loss": 1.3086,
+      "step": 131
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7846031188964844,
+      "learning_rate": 0.00016553857377763566,
+      "loss": 1.0314,
+      "step": 132
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.1489626169204712,
+      "learning_rate": 0.0001649593345826268,
+      "loss": 1.2978,
+      "step": 133
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8068945407867432,
+      "learning_rate": 0.00016437630000508464,
+      "loss": 0.9223,
+      "step": 134
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.0491584539413452,
+      "learning_rate": 0.00016378950411000183,
+      "loss": 1.2362,
+      "step": 135
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.104225516319275,
+      "learning_rate": 0.00016319898118213365,
+      "loss": 1.0196,
+      "step": 136
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0593640804290771,
+      "learning_rate": 0.00016260476572399496,
+      "loss": 1.419,
+      "step": 137
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8832619190216064,
+      "learning_rate": 0.00016200689245384424,
+      "loss": 1.0647,
+      "step": 138
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3387718200683594,
+      "learning_rate": 0.00016140539630365522,
+      "loss": 1.1116,
+      "step": 139
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.6814751625061035,
+      "learning_rate": 0.00016080031241707578,
+      "loss": 0.9274,
+      "step": 140
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.8765230774879456,
+      "learning_rate": 0.0001601916761473747,
+      "loss": 1.1033,
+      "step": 141
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.081540584564209,
+      "learning_rate": 0.00015957952305537597,
+      "loss": 1.1593,
+      "step": 142
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.8593389391899109,
+      "learning_rate": 0.00015896388890738127,
+      "loss": 1.2165,
+      "step": 143
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.9136074185371399,
+      "learning_rate": 0.00015834480967308003,
+      "loss": 1.094,
+      "step": 144
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0166850090026855,
+      "learning_rate": 0.00015772232152344795,
+      "loss": 1.2198,
+      "step": 145
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0423035621643066,
+      "learning_rate": 0.0001570964608286336,
+      "loss": 1.0797,
+      "step": 146
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9270806908607483,
+      "learning_rate": 0.00015646726415583344,
+      "loss": 0.8472,
+      "step": 147
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9399263858795166,
+      "learning_rate": 0.0001558347682671553,
+      "loss": 1.4304,
+      "step": 148
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.2435301542282104,
+      "learning_rate": 0.00015519901011747044,
+      "loss": 1.1031,
+      "step": 149
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.124361276626587,
+      "learning_rate": 0.00015456002685225448,
+      "loss": 1.3516,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.2383774518966675,
+      "learning_rate": 0.00015391785580541698,
+      "loss": 1.3462,
+      "step": 151
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.9090824723243713,
+      "learning_rate": 0.0001532725344971202,
+      "loss": 1.6209,
+      "step": 152
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1137770414352417,
+      "learning_rate": 0.0001526241006315869,
+      "loss": 1.4041,
+      "step": 153
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.809044599533081,
+      "learning_rate": 0.00015197259209489747,
+      "loss": 1.4031,
+      "step": 154
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.97702956199646,
+      "learning_rate": 0.00015131804695277612,
+      "loss": 1.163,
+      "step": 155
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0018224716186523,
+      "learning_rate": 0.00015066050344836706,
+      "loss": 1.1896,
+      "step": 156
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.9001697301864624,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2266,
+      "step": 157
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.64654141664505,
+      "learning_rate": 0.0001493365751989454,
+      "loss": 0.8407,
+      "step": 158
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.7076368927955627,
+      "learning_rate": 0.0001486702678071598,
+      "loss": 0.8155,
+      "step": 159
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.7560897469520569,
+      "learning_rate": 0.00014800111675502094,
+      "loss": 0.9128,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.7732242941856384,
+      "learning_rate": 0.00014732916113905335,
+      "loss": 1.1847,
+      "step": 161
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.138899326324463,
+      "learning_rate": 0.0001466544402196439,
+      "loss": 1.0657,
+      "step": 162
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.8294484615325928,
+      "learning_rate": 0.00014597699341874806,
+      "loss": 0.744,
+      "step": 163
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.8406904339790344,
+      "learning_rate": 0.00014529686031758643,
+      "loss": 0.8743,
+      "step": 164
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0488048791885376,
+      "learning_rate": 0.00014461408065433227,
+      "loss": 1.3688,
+      "step": 165
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.792988121509552,
+      "learning_rate": 0.00014392869432178971,
+      "loss": 1.0099,
+      "step": 166
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.7955910563468933,
+      "learning_rate": 0.00014324074136506284,
+      "loss": 1.1211,
+      "step": 167
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.3699181079864502,
+      "learning_rate": 0.00014255026197921596,
+      "loss": 1.0631,
+      "step": 168
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9223146438598633,
+      "learning_rate": 0.00014185729650692533,
+      "loss": 1.2675,
+      "step": 169
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9542146325111389,
+      "learning_rate": 0.0001411618854361218,
+      "loss": 1.346,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.376379370689392,
+      "learning_rate": 0.00014046406939762545,
+      "loss": 1.1186,
+      "step": 171
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0217031240463257,
+      "learning_rate": 0.0001397638891627714,
+      "loss": 1.2027,
+      "step": 172
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2267695665359497,
+      "learning_rate": 0.00013906138564102793,
+      "loss": 1.2938,
+      "step": 173
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0638290643692017,
+      "learning_rate": 0.00013835659987760605,
+      "loss": 1.3085,
+      "step": 174
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0052992105484009,
+      "learning_rate": 0.0001376495730510614,
+      "loss": 1.3518,
+      "step": 175
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.084850788116455,
+      "learning_rate": 0.0001369403464708884,
+      "loss": 1.2305,
+      "step": 176
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.1039252281188965,
+      "learning_rate": 0.00013622896157510658,
+      "loss": 1.2994,
+      "step": 177
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.8094058632850647,
+      "learning_rate": 0.00013551545992783947,
+      "loss": 0.8855,
+      "step": 178
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.8836209774017334,
+      "learning_rate": 0.0001347998832168862,
+      "loss": 1.0082,
+      "step": 179
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.0846760272979736,
+      "learning_rate": 0.0001340822732512857,
+      "loss": 1.4665,
+      "step": 180
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.9249682426452637,
+      "learning_rate": 0.00013336267195887398,
+      "loss": 1.1938,
+      "step": 181
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.9154543876647949,
+      "learning_rate": 0.00013264112138383445,
+      "loss": 0.9821,
+      "step": 182
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.7893356084823608,
+      "learning_rate": 0.00013191766368424133,
+      "loss": 1.1116,
+      "step": 183
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.035430669784546,
+      "learning_rate": 0.00013119234112959655,
+      "loss": 0.9664,
+      "step": 184
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.9736204147338867,
+      "learning_rate": 0.00013046519609836,
+      "loss": 1.3514,
+      "step": 185
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.7362933158874512,
+      "learning_rate": 0.00012973627107547346,
+      "loss": 1.2597,
+      "step": 186
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.9524862170219421,
+      "learning_rate": 0.0001290056086498785,
+      "loss": 1.2517,
+      "step": 187
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.8574633598327637,
+      "learning_rate": 0.00012827325151202782,
+      "loss": 1.2107,
+      "step": 188
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.9051613807678223,
+      "learning_rate": 0.00012753924245139135,
+      "loss": 1.1696,
+      "step": 189
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.8226101398468018,
+      "learning_rate": 0.00012680362435395595,
+      "loss": 1.1115,
+      "step": 190
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8252354860305786,
+      "learning_rate": 0.00012606644019971968,
+      "loss": 1.4651,
+      "step": 191
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.7974991202354431,
+      "learning_rate": 0.00012532773306018076,
+      "loss": 1.1674,
+      "step": 192
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1095021963119507,
+      "learning_rate": 0.00012458754609582097,
+      "loss": 1.0023,
+      "step": 193
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8103540539741516,
+      "learning_rate": 0.00012384592255358385,
+      "loss": 1.0422,
+      "step": 194
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.0317672491073608,
+      "learning_rate": 0.00012310290576434795,
+      "loss": 1.4481,
+      "step": 195
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.7659044861793518,
+      "learning_rate": 0.00012235853914039515,
+      "loss": 0.9214,
+      "step": 196
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9760628938674927,
+      "learning_rate": 0.00012161286617287419,
+      "loss": 0.9451,
+      "step": 197
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.8639245629310608,
+      "learning_rate": 0.00012086593042925964,
+      "loss": 1.228,
+      "step": 198
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.679837703704834,
+      "learning_rate": 0.00012011777555080638,
+      "loss": 0.7013,
+      "step": 199
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3544727563858032,
+      "learning_rate": 0.00011936844524999966,
+      "loss": 1.3484,
+      "step": 200
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.8588854670524597,
+      "learning_rate": 0.00011861798330800125,
+      "loss": 1.038,
+      "step": 201
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.042388916015625,
+      "learning_rate": 0.00011786643357209136,
+      "loss": 0.9381,
+      "step": 202
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2419315576553345,
+      "learning_rate": 0.00011711383995310681,
+      "loss": 1.1239,
+      "step": 203
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.9067419767379761,
+      "learning_rate": 0.00011636024642287546,
+      "loss": 1.1281,
+      "step": 204
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.892392635345459,
+      "learning_rate": 0.00011560569701164697,
+      "loss": 1.3182,
+      "step": 205
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.165024518966675,
+      "learning_rate": 0.00011485023580552039,
+      "loss": 1.4994,
+      "step": 206
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8466215133666992,
+      "learning_rate": 0.00011409390694386817,
+      "loss": 1.1808,
+      "step": 207
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.8418644666671753,
+      "learning_rate": 0.00011333675461675739,
+      "loss": 1.073,
+      "step": 208
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9302152395248413,
+      "learning_rate": 0.00011257882306236775,
+      "loss": 1.3006,
+      "step": 209
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.7823472023010254,
+      "learning_rate": 0.00011182015656440692,
+      "loss": 1.022,
+      "step": 210
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.8613569736480713,
+      "learning_rate": 0.00011106079944952317,
+      "loss": 1.2908,
+      "step": 211
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0009961128234863,
+      "learning_rate": 0.00011030079608471544,
+      "loss": 0.8989,
+      "step": 212
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0519012212753296,
+      "learning_rate": 0.00010954019087474124,
+      "loss": 1.4786,
+      "step": 213
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8396223187446594,
+      "learning_rate": 0.00010877902825952197,
+      "loss": 1.0932,
+      "step": 214
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9197802543640137,
+      "learning_rate": 0.00010801735271154669,
+      "loss": 1.1499,
+      "step": 215
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.992536187171936,
+      "learning_rate": 0.00010725520873327361,
+      "loss": 1.1127,
+      "step": 216
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.1217732429504395,
+      "eval_runtime": 4.53,
+      "eval_samples_per_second": 22.075,
+      "eval_steps_per_second": 22.075,
+      "step": 216
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9117234349250793,
+      "learning_rate": 0.00010649264085452988,
+      "loss": 0.9796,
+      "step": 217
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.1023670434951782,
+      "learning_rate": 0.00010572969362990998,
+      "loss": 1.279,
+      "step": 218
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.9863465428352356,
+      "learning_rate": 0.0001049664116361724,
+      "loss": 1.1939,
+      "step": 219
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.0204691886901855,
+      "learning_rate": 0.0001042028394696352,
+      "loss": 1.0306,
+      "step": 220
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.0943104028701782,
+      "learning_rate": 0.00010343902174357039,
+      "loss": 1.1368,
+      "step": 221
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7969679832458496,
+      "learning_rate": 0.00010267500308559732,
+      "loss": 1.1307,
+      "step": 222
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0134028196334839,
+      "learning_rate": 0.0001019108281350752,
+      "loss": 1.0659,
+      "step": 223
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8264066576957703,
+      "learning_rate": 0.0001011465415404949,
+      "loss": 1.2561,
+      "step": 224
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8983911871910095,
+      "learning_rate": 0.0001003821879568704,
+      "loss": 0.9493,
+      "step": 225
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.9019614458084106,
+      "learning_rate": 9.96178120431296e-05,
+      "loss": 1.176,
+      "step": 226
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.8894824385643005,
+      "learning_rate": 9.88534584595051e-05,
+      "loss": 1.031,
+      "step": 227
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.7906700372695923,
+      "learning_rate": 9.80891718649248e-05,
+      "loss": 0.9673,
+      "step": 228
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.851535439491272,
+      "learning_rate": 9.732499691440266e-05,
+      "loss": 1.3752,
+      "step": 229
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.811988115310669,
+      "learning_rate": 9.656097825642961e-05,
+      "loss": 1.2275,
+      "step": 230
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.7805109620094299,
+      "learning_rate": 9.579716053036479e-05,
+      "loss": 0.9749,
+      "step": 231
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8648375272750854,
+      "learning_rate": 9.503358836382761e-05,
+      "loss": 1.2433,
+      "step": 232
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.9555246233940125,
+      "learning_rate": 9.427030637009003e-05,
+      "loss": 1.1633,
+      "step": 233
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1394392251968384,
+      "learning_rate": 9.35073591454701e-05,
+      "loss": 0.8344,
+      "step": 234
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.8720835447311401,
+      "learning_rate": 9.274479126672641e-05,
+      "loss": 1.1096,
+      "step": 235
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.9399293661117554,
+      "learning_rate": 9.198264728845332e-05,
+      "loss": 1.3523,
+      "step": 236
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.7978518009185791,
+      "learning_rate": 9.122097174047805e-05,
+      "loss": 1.1517,
+      "step": 237
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.7624977231025696,
+      "learning_rate": 9.045980912525879e-05,
+      "loss": 0.9275,
+      "step": 238
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.8147649765014648,
+      "learning_rate": 8.969920391528458e-05,
+      "loss": 0.8636,
+      "step": 239
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.785790205001831,
+      "learning_rate": 8.893920055047686e-05,
+      "loss": 1.0534,
+      "step": 240
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.125995397567749,
+      "learning_rate": 8.81798434355931e-05,
+      "loss": 1.1807,
+      "step": 241
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.7521439790725708,
+      "learning_rate": 8.742117693763227e-05,
+      "loss": 1.0305,
+      "step": 242
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8274433016777039,
+      "learning_rate": 8.666324538324264e-05,
+      "loss": 1.085,
+      "step": 243
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8147134780883789,
+      "learning_rate": 8.590609305613184e-05,
+      "loss": 1.2264,
+      "step": 244
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.7244744896888733,
+      "learning_rate": 8.514976419447964e-05,
+      "loss": 1.1086,
+      "step": 245
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8199812769889832,
+      "learning_rate": 8.439430298835304e-05,
+      "loss": 1.2493,
+      "step": 246
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8318966031074524,
+      "learning_rate": 8.363975357712457e-05,
+      "loss": 1.2299,
+      "step": 247
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.7832856178283691,
+      "learning_rate": 8.28861600468932e-05,
+      "loss": 0.8078,
+      "step": 248
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9130321741104126,
+      "learning_rate": 8.213356642790867e-05,
+      "loss": 0.8836,
+      "step": 249
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9047381281852722,
+      "learning_rate": 8.138201669199879e-05,
+      "loss": 1.1093,
+      "step": 250
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9429170489311218,
+      "learning_rate": 8.063155475000037e-05,
+      "loss": 1.0342,
+      "step": 251
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.768521785736084,
+      "learning_rate": 7.988222444919364e-05,
+      "loss": 0.9746,
+      "step": 252
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0032973289489746,
+      "learning_rate": 7.913406957074037e-05,
+      "loss": 1.2174,
+      "step": 253
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6308262944221497,
+      "learning_rate": 7.838713382712583e-05,
+      "loss": 0.6023,
+      "step": 254
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.7773599028587341,
+      "learning_rate": 7.76414608596049e-05,
+      "loss": 1.0076,
+      "step": 255
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.7157078385353088,
+      "learning_rate": 7.68970942356521e-05,
+      "loss": 0.6884,
+      "step": 256
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2393338680267334,
+      "learning_rate": 7.615407744641619e-05,
+      "loss": 1.0305,
+      "step": 257
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0994664430618286,
+      "learning_rate": 7.541245390417906e-05,
+      "loss": 1.1654,
+      "step": 258
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7427523732185364,
+      "learning_rate": 7.467226693981925e-05,
+      "loss": 0.9712,
+      "step": 259
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2756493091583252,
+      "learning_rate": 7.393355980028039e-05,
+      "loss": 1.3114,
+      "step": 260
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.793830394744873,
+      "learning_rate": 7.319637564604412e-05,
+      "loss": 1.3208,
+      "step": 261
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9040703773498535,
+      "learning_rate": 7.246075754860868e-05,
+      "loss": 0.8639,
+      "step": 262
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9407386183738708,
+      "learning_rate": 7.172674848797219e-05,
+      "loss": 1.1326,
+      "step": 263
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9421854019165039,
+      "learning_rate": 7.099439135012153e-05,
+      "loss": 1.4087,
+      "step": 264
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.994733452796936,
+      "learning_rate": 7.026372892452653e-05,
+      "loss": 1.1922,
+      "step": 265
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6622300744056702,
+      "learning_rate": 6.953480390164e-05,
+      "loss": 0.7856,
+      "step": 266
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.657450556755066,
+      "learning_rate": 6.880765887040343e-05,
+      "loss": 1.4286,
+      "step": 267
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6856554746627808,
+      "learning_rate": 6.808233631575867e-05,
+      "loss": 0.747,
+      "step": 268
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9431721568107605,
+      "learning_rate": 6.735887861616556e-05,
+      "loss": 1.2292,
+      "step": 269
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.8753611445426941,
+      "learning_rate": 6.663732804112603e-05,
+      "loss": 1.131,
+      "step": 270
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.9430322051048279,
+      "learning_rate": 6.591772674871434e-05,
+      "loss": 1.2531,
+      "step": 271
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.8063769936561584,
+      "learning_rate": 6.520011678311382e-05,
+      "loss": 1.2419,
+      "step": 272
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.0588343143463135,
+      "learning_rate": 6.448454007216054e-05,
+      "loss": 1.1127,
+      "step": 273
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0695732831954956,
+      "learning_rate": 6.377103842489343e-05,
+      "loss": 0.8653,
+      "step": 274
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.7874151468276978,
+      "learning_rate": 6.305965352911161e-05,
+      "loss": 0.9848,
+      "step": 275
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8761109709739685,
+      "learning_rate": 6.235042694893862e-05,
+      "loss": 1.2929,
+      "step": 276
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.125989317893982,
+      "learning_rate": 6.164340012239396e-05,
+      "loss": 1.2386,
+      "step": 277
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.9087582230567932,
+      "learning_rate": 6.093861435897208e-05,
+      "loss": 1.3605,
+      "step": 278
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8747795224189758,
+      "learning_rate": 6.02361108372286e-05,
+      "loss": 1.1958,
+      "step": 279
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.795741617679596,
+      "learning_rate": 5.953593060237457e-05,
+      "loss": 1.1931,
+      "step": 280
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8389732241630554,
+      "learning_rate": 5.883811456387821e-05,
+      "loss": 0.9892,
+      "step": 281
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8712977766990662,
+      "learning_rate": 5.8142703493074714e-05,
+      "loss": 0.9848,
+      "step": 282
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8444830179214478,
+      "learning_rate": 5.7449738020784085e-05,
+      "loss": 1.2844,
+      "step": 283
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8620829582214355,
+      "learning_rate": 5.675925863493721e-05,
+      "loss": 1.1073,
+      "step": 284
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.9305702447891235,
+      "learning_rate": 5.607130567821031e-05,
+      "loss": 1.1492,
+      "step": 285
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.95172119140625,
+      "learning_rate": 5.5385919345667715e-05,
+      "loss": 1.2335,
+      "step": 286
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0538924932479858,
+      "learning_rate": 5.4703139682413586e-05,
+      "loss": 1.291,
+      "step": 287
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.932868480682373,
+      "learning_rate": 5.402300658125197e-05,
+      "loss": 0.9993,
+      "step": 288
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.7361299991607666,
+      "learning_rate": 5.334555978035609e-05,
+      "loss": 0.9007,
+      "step": 289
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.9995474219322205,
+      "learning_rate": 5.267083886094668e-05,
+      "loss": 1.4761,
+      "step": 290
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9075713753700256,
+      "learning_rate": 5.199888324497907e-05,
+      "loss": 1.0876,
+      "step": 291
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9964917898178101,
+      "learning_rate": 5.132973219284023e-05,
+      "loss": 1.1724,
+      "step": 292
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8188440203666687,
+      "learning_rate": 5.0663424801054595e-05,
+      "loss": 1.1436,
+      "step": 293
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.9193772077560425,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.0768,
+      "step": 294
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0195751190185547,
+      "learning_rate": 4.9339496551632944e-05,
+      "loss": 1.449,
+      "step": 295
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8990641236305237,
+      "learning_rate": 4.8681953047223914e-05,
+      "loss": 0.8608,
+      "step": 296
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.022701621055603,
+      "learning_rate": 4.8027407905102585e-05,
+      "loss": 1.1053,
+      "step": 297
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.807485818862915,
+      "learning_rate": 4.73758993684131e-05,
+      "loss": 0.8525,
+      "step": 298
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.7073543667793274,
+      "learning_rate": 4.672746550287985e-05,
+      "loss": 0.9197,
+      "step": 299
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0731732845306396,
+      "learning_rate": 4.6082144194583056e-05,
+      "loss": 1.4369,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9274147152900696,
+      "learning_rate": 4.543997314774553e-05,
+      "loss": 1.0458,
+      "step": 301
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.8712925910949707,
+      "learning_rate": 4.4800989882529574e-05,
+      "loss": 1.1399,
+      "step": 302
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.997308075428009,
+      "learning_rate": 4.41652317328447e-05,
+      "loss": 1.2134,
+      "step": 303
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9169958233833313,
+      "learning_rate": 4.3532735844166574e-05,
+      "loss": 1.0142,
+      "step": 304
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.8785117864608765,
+      "learning_rate": 4.2903539171366393e-05,
+      "loss": 1.1855,
+      "step": 305
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.609159231185913,
+      "learning_rate": 4.227767847655205e-05,
+      "loss": 1.2509,
+      "step": 306
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.8807599544525146,
+      "learning_rate": 4.165519032691998e-05,
+      "loss": 1.2177,
+      "step": 307
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.6682782173156738,
+      "learning_rate": 4.1036111092618725e-05,
+      "loss": 0.9244,
+      "step": 308
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9000231027603149,
+      "learning_rate": 4.042047694462404e-05,
+      "loss": 1.0608,
+      "step": 309
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9451295137405396,
+      "learning_rate": 3.9808323852625316e-05,
+      "loss": 1.1026,
+      "step": 310
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0684716701507568,
+      "learning_rate": 3.919968758292425e-05,
+      "loss": 1.3358,
+      "step": 311
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.977093517780304,
+      "learning_rate": 3.859460369634479e-05,
+      "loss": 1.1094,
+      "step": 312
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9359922409057617,
+      "learning_rate": 3.799310754615578e-05,
+      "loss": 1.3639,
+      "step": 313
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.6790077090263367,
+      "learning_rate": 3.7395234276005087e-05,
+      "loss": 0.8584,
+      "step": 314
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.010183572769165,
+      "learning_rate": 3.6801018817866375e-05,
+      "loss": 1.0515,
+      "step": 315
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9452493786811829,
+      "learning_rate": 3.62104958899982e-05,
+      "loss": 1.1822,
+      "step": 316
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0171464681625366,
+      "learning_rate": 3.562369999491536e-05,
+      "loss": 1.4204,
+      "step": 317
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7657376527786255,
+      "learning_rate": 3.504066541737323e-05,
+      "loss": 1.0697,
+      "step": 318
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7902315258979797,
+      "learning_rate": 3.4461426222364336e-05,
+      "loss": 1.0003,
+      "step": 319
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8496732115745544,
+      "learning_rate": 3.3886016253128326e-05,
+      "loss": 1.1138,
+      "step": 320
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0020195245742798,
+      "learning_rate": 3.3314469129174364e-05,
+      "loss": 1.327,
+      "step": 321
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9500836133956909,
+      "learning_rate": 3.2746818244316956e-05,
+      "loss": 1.0384,
+      "step": 322
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.075058102607727,
+      "learning_rate": 3.2183096764724915e-05,
+      "loss": 1.3979,
+      "step": 323
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9950640201568604,
+      "learning_rate": 3.16233376269834e-05,
+      "loss": 1.4125,
+      "step": 324
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.1111160516738892,
+      "eval_runtime": 4.6774,
+      "eval_samples_per_second": 21.379,
+      "eval_steps_per_second": 21.379,
+      "step": 324
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7793411016464233,
+      "learning_rate": 3.106757353616966e-05,
+      "loss": 0.8381,
+      "step": 325
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8830385804176331,
+      "learning_rate": 3.0515836963942056e-05,
+      "loss": 1.2964,
+      "step": 326
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8861040472984314,
+      "learning_rate": 2.9968160146643022e-05,
+      "loss": 1.0995,
+      "step": 327
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.053879976272583,
+      "learning_rate": 2.9424575083415362e-05,
+      "loss": 1.5488,
+      "step": 328
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9933589100837708,
+      "learning_rate": 2.888511353433274e-05,
+      "loss": 1.118,
+      "step": 329
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8043419718742371,
+      "learning_rate": 2.8349807018544174e-05,
+      "loss": 1.1957,
+      "step": 330
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.7816306352615356,
+      "learning_rate": 2.7818686812432136e-05,
+      "loss": 1.1842,
+      "step": 331
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.0237221717834473,
+      "learning_rate": 2.7291783947785543e-05,
+      "loss": 1.5032,
+      "step": 332
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9819310903549194,
+      "learning_rate": 2.6769129209986322e-05,
+      "loss": 1.463,
+      "step": 333
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9578650593757629,
+      "learning_rate": 2.6250753136210983e-05,
+      "loss": 0.8582,
+      "step": 334
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.7909988760948181,
+      "learning_rate": 2.5736686013646228e-05,
+      "loss": 1.1534,
+      "step": 335
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4216173887252808,
+      "learning_rate": 2.5226957877719436e-05,
+      "loss": 1.1382,
+      "step": 336
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.25717294216156,
+      "learning_rate": 2.4721598510343858e-05,
+      "loss": 1.3448,
+      "step": 337
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9537882804870605,
+      "learning_rate": 2.4220637438178317e-05,
+      "loss": 1.0524,
+      "step": 338
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2170014381408691,
+      "learning_rate": 2.372410393090243e-05,
+      "loss": 1.1399,
+      "step": 339
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9083089232444763,
+      "learning_rate": 2.3232026999506062e-05,
+      "loss": 1.2474,
+      "step": 340
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.8763582706451416,
+      "learning_rate": 2.2744435394594497e-05,
+      "loss": 1.2537,
+      "step": 341
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.7505499720573425,
+      "learning_rate": 2.22613576047087e-05,
+      "loss": 0.9797,
+      "step": 342
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8739334940910339,
+      "learning_rate": 2.1782821854660606e-05,
+      "loss": 1.1039,
+      "step": 343
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0695990324020386,
+      "learning_rate": 2.130885610388428e-05,
+      "loss": 1.3357,
+      "step": 344
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0684748888015747,
+      "learning_rate": 2.0839488044802036e-05,
+      "loss": 1.7609,
+      "step": 345
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7981250286102295,
+      "learning_rate": 2.037474510120676e-05,
+      "loss": 1.1366,
+      "step": 346
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.9911528825759888,
+      "learning_rate": 1.9914654426659374e-05,
+      "loss": 1.0673,
+      "step": 347
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.893088698387146,
+      "learning_rate": 1.945924290290242e-05,
+      "loss": 1.1137,
+      "step": 348
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.5035367012023926,
+      "learning_rate": 1.9008537138289527e-05,
+      "loss": 1.5564,
+      "step": 349
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8571119904518127,
+      "learning_rate": 1.8562563466230576e-05,
+      "loss": 1.2024,
+      "step": 350
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8839694261550903,
+      "learning_rate": 1.8121347943653332e-05,
+      "loss": 1.3072,
+      "step": 351
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6712371706962585,
+      "learning_rate": 1.7684916349480794e-05,
+      "loss": 0.9432,
+      "step": 352
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0981756448745728,
+      "learning_rate": 1.7253294183125223e-05,
+      "loss": 1.1677,
+      "step": 353
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9684164524078369,
+      "learning_rate": 1.6826506662998097e-05,
+      "loss": 1.347,
+      "step": 354
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7216952443122864,
+      "learning_rate": 1.64045787250368e-05,
+      "loss": 1.11,
+      "step": 355
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.8955852389335632,
+      "learning_rate": 1.5987535021247667e-05,
+      "loss": 1.0251,
+      "step": 356
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.7568878531455994,
+      "learning_rate": 1.5575399918265542e-05,
+      "loss": 1.1329,
+      "step": 357
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.9345647692680359,
+      "learning_rate": 1.5168197495930315e-05,
+      "loss": 1.4607,
+      "step": 358
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.8495572209358215,
+      "learning_rate": 1.476595154587973e-05,
+      "loss": 0.9832,
+      "step": 359
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9725989103317261,
+      "learning_rate": 1.436868557015959e-05,
+      "loss": 1.2982,
+      "step": 360
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.1222511529922485,
+      "learning_rate": 1.3976422779850384e-05,
+      "loss": 1.3227,
+      "step": 361
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7948237657546997,
+      "learning_rate": 1.3589186093711226e-05,
+      "loss": 1.0005,
+      "step": 362
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9465959668159485,
+      "learning_rate": 1.3206998136840831e-05,
+      "loss": 1.2083,
+      "step": 363
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4611457586288452,
+      "learning_rate": 1.2829881239355468e-05,
+      "loss": 1.3059,
+      "step": 364
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2416762113571167,
+      "learning_rate": 1.2457857435084408e-05,
+      "loss": 2.7802,
+      "step": 365
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.7987867593765259,
+      "learning_rate": 1.2090948460282414e-05,
+      "loss": 1.1166,
+      "step": 366
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2761002779006958,
+      "learning_rate": 1.1729175752359922e-05,
+      "loss": 1.3666,
+      "step": 367
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.7645698189735413,
+      "learning_rate": 1.1372560448630376e-05,
+      "loss": 1.1899,
+      "step": 368
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7835568785667419,
+      "learning_rate": 1.102112338507526e-05,
+      "loss": 1.1535,
+      "step": 369
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.1104003190994263,
+      "learning_rate": 1.067488509512683e-05,
+      "loss": 0.9926,
+      "step": 370
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9154466986656189,
+      "learning_rate": 1.0333865808468202e-05,
+      "loss": 1.0499,
+      "step": 371
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.0990214347839355,
+      "learning_rate": 9.998085449851635e-06,
+      "loss": 1.0088,
+      "step": 372
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.8231632113456726,
+      "learning_rate": 9.667563637934129e-06,
+      "loss": 0.8993,
+      "step": 373
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.8902583122253418,
+      "learning_rate": 9.342319684131395e-06,
+      "loss": 1.1143,
+      "step": 374
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0287319421768188,
+      "learning_rate": 9.02237259148938e-06,
+      "loss": 1.1727,
+      "step": 375
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.8908065557479858,
+      "learning_rate": 8.70774105357407e-06,
+      "loss": 1.1978,
+      "step": 376
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.9575155377388,
+      "learning_rate": 8.398443453379267e-06,
+      "loss": 1.1231,
+      "step": 377
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8669496774673462,
+      "learning_rate": 8.094497862252471e-06,
+      "loss": 1.3489,
+      "step": 378
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0810797214508057,
+      "learning_rate": 7.795922038839032e-06,
+      "loss": 1.314,
+      "step": 379
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8104758262634277,
+      "learning_rate": 7.502733428044683e-06,
+      "loss": 1.0355,
+      "step": 380
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8727629780769348,
+      "learning_rate": 7.214949160016115e-06,
+      "loss": 1.1318,
+      "step": 381
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.9471575021743774,
+      "learning_rate": 6.932586049140255e-06,
+      "loss": 1.1269,
+      "step": 382
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.0069880485534668,
+      "learning_rate": 6.655660593061719e-06,
+      "loss": 1.256,
+      "step": 383
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.8442095518112183,
+      "learning_rate": 6.384188971719052e-06,
+      "loss": 1.1764,
+      "step": 384
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1151554584503174,
+      "learning_rate": 6.11818704639926e-06,
+      "loss": 1.4769,
+      "step": 385
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3000290393829346,
+      "learning_rate": 5.857670358811096e-06,
+      "loss": 1.2021,
+      "step": 386
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.4002149105072021,
+      "learning_rate": 5.6026541301771095e-06,
+      "loss": 1.0293,
+      "step": 387
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7477453947067261,
+      "learning_rate": 5.353153260344179e-06,
+      "loss": 0.4222,
+      "step": 388
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.772838294506073,
+      "learning_rate": 5.109182326913054e-06,
+      "loss": 1.1792,
+      "step": 389
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8639078140258789,
+      "learning_rate": 4.870755584386544e-06,
+      "loss": 1.1377,
+      "step": 390
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0017356872558594,
+      "learning_rate": 4.63788696333678e-06,
+      "loss": 1.3083,
+      "step": 391
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.8512603044509888,
+      "learning_rate": 4.410590069591192e-06,
+      "loss": 1.0622,
+      "step": 392
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0194518566131592,
+      "learning_rate": 4.188878183437594e-06,
+      "loss": 0.9805,
+      "step": 393
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.9389981627464294,
+      "learning_rate": 3.972764258848305e-06,
+      "loss": 0.8029,
+      "step": 394
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8767827749252319,
+      "learning_rate": 3.7622609227231818e-06,
+      "loss": 1.2896,
+      "step": 395
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.057941198348999,
+      "learning_rate": 3.5573804741519833e-06,
+      "loss": 1.0284,
+      "step": 396
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8057636618614197,
+      "learning_rate": 3.3581348836956738e-06,
+      "loss": 0.8359,
+      "step": 397
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8794740438461304,
+      "learning_rate": 3.1645357926870955e-06,
+      "loss": 1.0901,
+      "step": 398
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.1350359916687012,
+      "learning_rate": 2.9765945125507235e-06,
+      "loss": 1.3476,
+      "step": 399
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0273802280426025,
+      "learning_rate": 2.7943220241418377e-06,
+      "loss": 1.633,
+      "step": 400
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0018689632415771,
+      "learning_rate": 2.6177289771049274e-06,
+      "loss": 1.2149,
+      "step": 401
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.8840231895446777,
+      "learning_rate": 2.4468256892514417e-06,
+      "loss": 0.8715,
+      "step": 402
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7019383907318115,
+      "learning_rate": 2.281622145956952e-06,
+      "loss": 0.7569,
+      "step": 403
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8953691124916077,
+      "learning_rate": 2.122127999577783e-06,
+      "loss": 1.0571,
+      "step": 404
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.2523472309112549,
+      "learning_rate": 1.9683525688869773e-06,
+      "loss": 1.2324,
+      "step": 405
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8265737891197205,
+      "learning_rate": 1.8203048385299181e-06,
+      "loss": 1.1572,
+      "step": 406
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1475375890731812,
+      "learning_rate": 1.6779934584992718e-06,
+      "loss": 1.252,
+      "step": 407
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8161171078681946,
+      "learning_rate": 1.5414267436297037e-06,
+      "loss": 1.0995,
+      "step": 408
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.7946155071258545,
+      "learning_rate": 1.4106126731119996e-06,
+      "loss": 1.2478,
+      "step": 409
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.9553078413009644,
+      "learning_rate": 1.2855588900269056e-06,
+      "loss": 1.197,
+      "step": 410
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.9659767150878906,
+      "learning_rate": 1.1662727008984964e-06,
+      "loss": 1.4687,
+      "step": 411
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8661131262779236,
+      "learning_rate": 1.0527610752673944e-06,
+      "loss": 1.1361,
+      "step": 412
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8412200212478638,
+      "learning_rate": 9.450306452834179e-07,
+      "loss": 1.1367,
+      "step": 413
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0240707397460938,
+      "learning_rate": 8.430877053182129e-07,
+      "loss": 1.1314,
+      "step": 414
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8636841177940369,
+      "learning_rate": 7.469382115974032e-07,
+      "loss": 1.2735,
+      "step": 415
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9078946709632874,
+      "learning_rate": 6.565877818526245e-07,
+      "loss": 1.6363,
+      "step": 416
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.7889100313186646,
+      "learning_rate": 5.72041694993286e-07,
+      "loss": 0.7248,
+      "step": 417
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.1223846673965454,
+      "learning_rate": 4.933048907981741e-07,
+      "loss": 1.2877,
+      "step": 418
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.796015202999115,
+      "learning_rate": 4.203819696267486e-07,
+      "loss": 1.1152,
+      "step": 419
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3147443532943726,
+      "learning_rate": 3.532771921504696e-07,
+      "loss": 0.964,
+      "step": 420
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9248856902122498,
+      "learning_rate": 2.919944791037632e-07,
+      "loss": 1.1183,
+      "step": 421
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9096655249595642,
+      "learning_rate": 2.3653741105499338e-07,
+      "loss": 1.2962,
+      "step": 422
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.8650621175765991,
+      "learning_rate": 1.8690922819727398e-07,
+      "loss": 1.2811,
+      "step": 423
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.8937092423439026,
+      "learning_rate": 1.4311283015910893e-07,
+      "loss": 1.4072,
+      "step": 424
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8139075040817261,
+      "learning_rate": 1.0515077583498344e-07,
+      "loss": 1.0015,
+      "step": 425
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.7907817959785461,
+      "learning_rate": 7.302528323589464e-08,
+      "loss": 0.8809,
+      "step": 426
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8603721261024475,
+      "learning_rate": 4.6738229359732935e-08,
+      "loss": 0.9924,
+      "step": 427
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.7711588740348816,
+      "learning_rate": 2.6291150081603212e-08,
+      "loss": 1.1624,
+      "step": 428
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9995566010475159,
+      "learning_rate": 1.168524006410765e-08,
+      "loss": 1.2978,
+      "step": 429
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2378227710723877,
+      "learning_rate": 2.921352687534906e-09,
+      "loss": 0.9902,
+      "step": 430
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.906247079372406,
+      "learning_rate": 0.0,
+      "loss": 1.1797,
+      "step": 431
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 431,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 7839152706846720.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-431/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6130444794cf1785095c2c4fa31cbd8f6699b43f19794a00a7cc54396d426369
+size 5624

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "openlm-research/open_llama_3b_v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "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-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

runs/Mar10_13-35-56_b36d25534b8d/events.out.tfevents.1710077756.b36d25534b8d.44.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1efac7496f86c2861ae1231484b40bb2fa64784a49d0c542960b762415ae59
+size 96628

runs/Mar10_14-03-24_b36d25534b8d/events.out.tfevents.1710079405.b36d25534b8d.238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac9f4f40a2a672e77ce37acf10c7b944f624812467016802b60c0a39a620356
+size 97683

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}