Upload folder using huggingface_hub

README.md

@@ -0,0 +1,160 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: openlm-research/open_llama_7b_v2
+tags:
+- generated_from_trainer
+datasets:
+- train_dataset.jsonl
+model-index:
+- name: outputs/open_llama_7b_v2_explain_contracts
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.6.0`
+```yaml
+base_model: openlm-research/open_llama_7b_v2
+# optionally might have model_type or tokenizer_type
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: train_dataset.jsonl
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.1
+adapter: lora
+lora_model_dir:
+sequence_len: 1024
+sample_packing: false
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./outputs/open_llama_7b_v2_explain_contracts
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+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:
+s2_attention:
+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>
+
+# outputs/open_llama_7b_v2_explain_contracts
+
+This model is a fine-tuned version of [openlm-research/open_llama_7b_v2](https://huggingface.co/openlm-research/open_llama_7b_v2) on the train_dataset.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6394
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0718        | 0.0049 | 1    | 0.9605          |
+| 0.7756        | 0.2512 | 51   | 0.6831          |
+| 0.7316        | 0.5025 | 102  | 0.6300          |
+| 0.5161        | 0.7537 | 153  | 0.5952          |
+| 0.2465        | 1.0049 | 204  | 0.5775          |
+| 0.3408        | 1.2562 | 255  | 0.5715          |
+| 0.5834        | 1.5074 | 306  | 0.5610          |
+| 0.4347        | 1.7586 | 357  | 0.5540          |
+| 0.272         | 2.0099 | 408  | 0.5428          |
+| 0.2509        | 2.2611 | 459  | 0.5885          |
+| 0.2044        | 2.5123 | 510  | 0.5848          |
+| 0.4006        | 2.7635 | 561  | 0.5771          |
+| 0.2471        | 3.0148 | 612  | 0.5739          |
+| 0.0865        | 3.2660 | 663  | 0.6318          |
+| 0.1475        | 3.5172 | 714  | 0.6396          |
+| 0.3631        | 3.7685 | 765  | 0.6394          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b_v2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_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 sha256:38e60d3476758fa95293b2a3747e66bb16d13999ffc4eaaa3cb60a4d418f866e
+size 80115210

checkpoint-203/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_7b_v2
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-203/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b_v2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-203/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4021c85db51eb39453538e4a6e559d95fcf78ae45f521c5de716d83087cba88e
+size 80013120

checkpoint-203/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5f133bdbe52e7b6f455a3c5d3751e1449afa2b4b2b609f6f7342a6118e4da0
+size 41119636

checkpoint-203/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

checkpoint-203/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493650b039a9bed7e27fdf9325273123719714152714d719f76287852f98eade
+size 1064

checkpoint-203/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
+  }
+}

checkpoint-203/tokenizer.model

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

checkpoint-203/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}

checkpoint-203/trainer_state.json

@@ -0,0 +1,1486 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 51,
+  "global_step": 203,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0049261083743842365,
+      "grad_norm": 0.15764524042606354,
+      "learning_rate": 1e-05,
+      "loss": 1.0718,
+      "step": 1
+    },
+    {
+      "epoch": 0.0049261083743842365,
+      "eval_loss": 0.9604623317718506,
+      "eval_runtime": 11.0685,
+      "eval_samples_per_second": 4.066,
+      "eval_steps_per_second": 2.078,
+      "step": 1
+    },
+    {
+      "epoch": 0.009852216748768473,
+      "grad_norm": 0.17232584953308105,
+      "learning_rate": 2e-05,
+      "loss": 1.0695,
+      "step": 2
+    },
+    {
+      "epoch": 0.014778325123152709,
+      "grad_norm": 0.17787113785743713,
+      "learning_rate": 3e-05,
+      "loss": 0.9787,
+      "step": 3
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.18442076444625854,
+      "learning_rate": 4e-05,
+      "loss": 1.0556,
+      "step": 4
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.1500977873802185,
+      "learning_rate": 5e-05,
+      "loss": 0.8182,
+      "step": 5
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.1790969967842102,
+      "learning_rate": 6e-05,
+      "loss": 0.8186,
+      "step": 6
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.17189474403858185,
+      "learning_rate": 7e-05,
+      "loss": 0.9289,
+      "step": 7
+    },
+    {
+      "epoch": 0.03940886699507389,
+      "grad_norm": 0.21660089492797852,
+      "learning_rate": 8e-05,
+      "loss": 1.1689,
+      "step": 8
+    },
+    {
+      "epoch": 0.04433497536945813,
+      "grad_norm": 0.202072873711586,
+      "learning_rate": 9e-05,
+      "loss": 0.8433,
+      "step": 9
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 0.20105081796646118,
+      "learning_rate": 0.0001,
+      "loss": 1.1257,
+      "step": 10
+    },
+    {
+      "epoch": 0.054187192118226604,
+      "grad_norm": 0.23838526010513306,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.9087,
+      "step": 11
+    },
+    {
+      "epoch": 0.059113300492610835,
+      "grad_norm": 0.28929364681243896,
+      "learning_rate": 0.00012,
+      "loss": 1.0844,
+      "step": 12
+    },
+    {
+      "epoch": 0.06403940886699508,
+      "grad_norm": 0.26252612471580505,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.8561,
+      "step": 13
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.30341705679893494,
+      "learning_rate": 0.00014,
+      "loss": 0.9649,
+      "step": 14
+    },
+    {
+      "epoch": 0.07389162561576355,
+      "grad_norm": 0.35611552000045776,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1053,
+      "step": 15
+    },
+    {
+      "epoch": 0.07881773399014778,
+      "grad_norm": 0.2868112027645111,
+      "learning_rate": 0.00016,
+      "loss": 0.7479,
+      "step": 16
+    },
+    {
+      "epoch": 0.08374384236453201,
+      "grad_norm": 0.3906789720058441,
+      "learning_rate": 0.00017,
+      "loss": 0.887,
+      "step": 17
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 0.34518149495124817,
+      "learning_rate": 0.00018,
+      "loss": 0.6395,
+      "step": 18
+    },
+    {
+      "epoch": 0.09359605911330049,
+      "grad_norm": 0.43788307905197144,
+      "learning_rate": 0.00019,
+      "loss": 0.8385,
+      "step": 19
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.5314550399780273,
+      "learning_rate": 0.0002,
+      "loss": 0.8561,
+      "step": 20
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.5479442477226257,
+      "learning_rate": 0.00019999921328248872,
+      "loss": 0.9136,
+      "step": 21
+    },
+    {
+      "epoch": 0.10837438423645321,
+      "grad_norm": 0.46753960847854614,
+      "learning_rate": 0.0001999968531423333,
+      "loss": 0.8868,
+      "step": 22
+    },
+    {
+      "epoch": 0.11330049261083744,
+      "grad_norm": 0.5541612505912781,
+      "learning_rate": 0.00019999291961666908,
+      "loss": 1.0887,
+      "step": 23
+    },
+    {
+      "epoch": 0.11822660098522167,
+      "grad_norm": 0.5009401440620422,
+      "learning_rate": 0.00019998741276738754,
+      "loss": 0.7118,
+      "step": 24
+    },
+    {
+      "epoch": 0.12315270935960591,
+      "grad_norm": 0.5104517936706543,
+      "learning_rate": 0.00019998033268113526,
+      "loss": 0.8755,
+      "step": 25
+    },
+    {
+      "epoch": 0.12807881773399016,
+      "grad_norm": 0.46783849596977234,
+      "learning_rate": 0.0001999716794693129,
+      "loss": 0.745,
+      "step": 26
+    },
+    {
+      "epoch": 0.1330049261083744,
+      "grad_norm": 0.4237991273403168,
+      "learning_rate": 0.00019996145326807313,
+      "loss": 0.9907,
+      "step": 27
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.482265442609787,
+      "learning_rate": 0.00019994965423831854,
+      "loss": 0.8543,
+      "step": 28
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.3490796387195587,
+      "learning_rate": 0.0001999362825656992,
+      "loss": 0.5405,
+      "step": 29
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 0.450983464717865,
+      "learning_rate": 0.00019992133846060968,
+      "loss": 0.7886,
+      "step": 30
+    },
+    {
+      "epoch": 0.15270935960591134,
+      "grad_norm": 0.46920955181121826,
+      "learning_rate": 0.0001999048221581858,
+      "loss": 0.7652,
+      "step": 31
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "grad_norm": 0.4696129858493805,
+      "learning_rate": 0.0001998867339183008,
+      "loss": 0.8397,
+      "step": 32
+    },
+    {
+      "epoch": 0.1625615763546798,
+      "grad_norm": 0.4254930317401886,
+      "learning_rate": 0.00019986707402556145,
+      "loss": 0.7488,
+      "step": 33
+    },
+    {
+      "epoch": 0.16748768472906403,
+      "grad_norm": 0.45232057571411133,
+      "learning_rate": 0.0001998458427893033,
+      "loss": 0.6505,
+      "step": 34
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.4483110308647156,
+      "learning_rate": 0.00019982304054358614,
+      "loss": 0.7754,
+      "step": 35
+    },
+    {
+      "epoch": 0.17733990147783252,
+      "grad_norm": 0.40316057205200195,
+      "learning_rate": 0.00019979866764718843,
+      "loss": 0.5503,
+      "step": 36
+    },
+    {
+      "epoch": 0.18226600985221675,
+      "grad_norm": 0.40666651725769043,
+      "learning_rate": 0.0001997727244836019,
+      "loss": 0.5926,
+      "step": 37
+    },
+    {
+      "epoch": 0.18719211822660098,
+      "grad_norm": 0.44321340322494507,
+      "learning_rate": 0.00019974521146102537,
+      "loss": 0.7276,
+      "step": 38
+    },
+    {
+      "epoch": 0.1921182266009852,
+      "grad_norm": 0.38087835907936096,
+      "learning_rate": 0.00019971612901235832,
+      "loss": 0.6578,
+      "step": 39
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.479129433631897,
+      "learning_rate": 0.00019968547759519425,
+      "loss": 0.7137,
+      "step": 40
+    },
+    {
+      "epoch": 0.2019704433497537,
+      "grad_norm": 0.5175262689590454,
+      "learning_rate": 0.00019965325769181325,
+      "loss": 0.9117,
+      "step": 41
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.3792617619037628,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 0.5606,
+      "step": 42
+    },
+    {
+      "epoch": 0.21182266009852216,
+      "grad_norm": 0.4176344573497772,
+      "learning_rate": 0.0001995841144789086,
+      "loss": 0.687,
+      "step": 43
+    },
+    {
+      "epoch": 0.21674876847290642,
+      "grad_norm": 0.37092089653015137,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 0.5669,
+      "step": 44
+    },
+    {
+      "epoch": 0.22167487684729065,
+      "grad_norm": 0.45256292819976807,
+      "learning_rate": 0.00019950870372532138,
+      "loss": 0.9317,
+      "step": 45
+    },
+    {
+      "epoch": 0.22660098522167488,
+      "grad_norm": 0.47242656350135803,
+      "learning_rate": 0.00019946864948853935,
+      "loss": 0.5439,
+      "step": 46
+    },
+    {
+      "epoch": 0.2315270935960591,
+      "grad_norm": 0.5142560601234436,
+      "learning_rate": 0.00019942703017718975,
+      "loss": 0.8644,
+      "step": 47
+    },
+    {
+      "epoch": 0.23645320197044334,
+      "grad_norm": 0.553180456161499,
+      "learning_rate": 0.00019938384644612543,
+      "loss": 0.8806,
+      "step": 48
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.43755683302879333,
+      "learning_rate": 0.00019933909897481433,
+      "loss": 0.8555,
+      "step": 49
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 0.4272922873497009,
+      "learning_rate": 0.00019929278846732884,
+      "loss": 0.4278,
+      "step": 50
+    },
+    {
+      "epoch": 0.2512315270935961,
+      "grad_norm": 0.5655816197395325,
+      "learning_rate": 0.0001992449156523347,
+      "loss": 0.7756,
+      "step": 51
+    },
+    {
+      "epoch": 0.2512315270935961,
+      "eval_loss": 0.6830816268920898,
+      "eval_runtime": 11.0415,
+      "eval_samples_per_second": 4.076,
+      "eval_steps_per_second": 2.083,
+      "step": 51
+    },
+    {
+      "epoch": 0.2561576354679803,
+      "grad_norm": 0.435141384601593,
+      "learning_rate": 0.00019919548128307954,
+      "loss": 0.6849,
+      "step": 52
+    },
+    {
+      "epoch": 0.26108374384236455,
+      "grad_norm": 0.49647849798202515,
+      "learning_rate": 0.00019914448613738106,
+      "loss": 0.5521,
+      "step": 53
+    },
+    {
+      "epoch": 0.2660098522167488,
+      "grad_norm": 0.4620106518268585,
+      "learning_rate": 0.0001990919310176147,
+      "loss": 0.563,
+      "step": 54
+    },
+    {
+      "epoch": 0.270935960591133,
+      "grad_norm": 0.461224764585495,
+      "learning_rate": 0.00019903781675070117,
+      "loss": 0.603,
+      "step": 55
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.4303002953529358,
+      "learning_rate": 0.0001989821441880933,
+      "loss": 0.6271,
+      "step": 56
+    },
+    {
+      "epoch": 0.28078817733990147,
+      "grad_norm": 0.46398401260375977,
+      "learning_rate": 0.00019892491420576261,
+      "loss": 0.5245,
+      "step": 57
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.4930243492126465,
+      "learning_rate": 0.00019886612770418578,
+      "loss": 0.6301,
+      "step": 58
+    },
+    {
+      "epoch": 0.29064039408866993,
+      "grad_norm": 0.47263646125793457,
+      "learning_rate": 0.00019880578560833016,
+      "loss": 0.6773,
+      "step": 59
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.40455955266952515,
+      "learning_rate": 0.00019874388886763944,
+      "loss": 0.4478,
+      "step": 60
+    },
+    {
+      "epoch": 0.30049261083743845,
+      "grad_norm": 0.587720513343811,
+      "learning_rate": 0.00019868043845601863,
+      "loss": 0.8783,
+      "step": 61
+    },
+    {
+      "epoch": 0.3054187192118227,
+      "grad_norm": 0.5045145153999329,
+      "learning_rate": 0.00019861543537181867,
+      "loss": 0.6364,
+      "step": 62
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.5762777328491211,
+      "learning_rate": 0.00019854888063782088,
+      "loss": 1.0393,
+      "step": 63
+    },
+    {
+      "epoch": 0.31527093596059114,
+      "grad_norm": 0.5282868146896362,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7865,
+      "step": 64
+    },
+    {
+      "epoch": 0.32019704433497537,
+      "grad_norm": 0.5349370241165161,
+      "learning_rate": 0.0001984111204336116,
+      "loss": 0.7984,
+      "step": 65
+    },
+    {
+      "epoch": 0.3251231527093596,
+      "grad_norm": 0.4982023239135742,
+      "learning_rate": 0.0001983399171309674,
+      "loss": 0.8803,
+      "step": 66
+    },
+    {
+      "epoch": 0.33004926108374383,
+      "grad_norm": 0.467535138130188,
+      "learning_rate": 0.00019826716651362585,
+      "loss": 0.6774,
+      "step": 67
+    },
+    {
+      "epoch": 0.33497536945812806,
+      "grad_norm": 0.36764436960220337,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 0.4467,
+      "step": 68
+    },
+    {
+      "epoch": 0.3399014778325123,
+      "grad_norm": 0.4941648840904236,
+      "learning_rate": 0.00019811702793791355,
+      "loss": 0.6345,
+      "step": 69
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.5048440098762512,
+      "learning_rate": 0.0001980396423418757,
+      "loss": 0.641,
+      "step": 70
+    },
+    {
+      "epoch": 0.3497536945812808,
+      "grad_norm": 0.5182650685310364,
+      "learning_rate": 0.00019796071415576925,
+      "loss": 0.6989,
+      "step": 71
+    },
+    {
+      "epoch": 0.35467980295566504,
+      "grad_norm": 0.504978358745575,
+      "learning_rate": 0.00019788024462147788,
+      "loss": 0.7198,
+      "step": 72
+    },
+    {
+      "epoch": 0.35960591133004927,
+      "grad_norm": 0.5767678022384644,
+      "learning_rate": 0.00019779823500513745,
+      "loss": 0.9102,
+      "step": 73
+    },
+    {
+      "epoch": 0.3645320197044335,
+      "grad_norm": 0.5125048756599426,
+      "learning_rate": 0.00019771468659711595,
+      "loss": 0.6646,
+      "step": 74
+    },
+    {
+      "epoch": 0.3694581280788177,
+      "grad_norm": 0.4948768615722656,
+      "learning_rate": 0.00019762960071199333,
+      "loss": 0.7312,
+      "step": 75
+    },
+    {
+      "epoch": 0.37438423645320196,
+      "grad_norm": 0.45587611198425293,
+      "learning_rate": 0.00019754297868854073,
+      "loss": 0.6778,
+      "step": 76
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.49900615215301514,
+      "learning_rate": 0.0001974548218896993,
+      "loss": 0.724,
+      "step": 77
+    },
+    {
+      "epoch": 0.3842364532019704,
+      "grad_norm": 0.533632755279541,
+      "learning_rate": 0.00019736513170255911,
+      "loss": 0.5307,
+      "step": 78
+    },
+    {
+      "epoch": 0.3891625615763547,
+      "grad_norm": 0.5380002856254578,
+      "learning_rate": 0.0001972739095383369,
+      "loss": 0.725,
+      "step": 79
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.6754060983657837,
+      "learning_rate": 0.00019718115683235417,
+      "loss": 1.04,
+      "step": 80
+    },
+    {
+      "epoch": 0.39901477832512317,
+      "grad_norm": 0.674319326877594,
+      "learning_rate": 0.0001970868750440145,
+      "loss": 0.9026,
+      "step": 81
+    },
+    {
+      "epoch": 0.4039408866995074,
+      "grad_norm": 0.5251882672309875,
+      "learning_rate": 0.0001969910656567805,
+      "loss": 0.615,
+      "step": 82
+    },
+    {
+      "epoch": 0.4088669950738916,
+      "grad_norm": 0.5495942831039429,
+      "learning_rate": 0.00019689373017815073,
+      "loss": 0.7116,
+      "step": 83
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.4467202425003052,
+      "learning_rate": 0.00019679487013963564,
+      "loss": 0.4405,
+      "step": 84
+    },
+    {
+      "epoch": 0.4187192118226601,
+      "grad_norm": 0.4973738491535187,
+      "learning_rate": 0.0001966944870967337,
+      "loss": 0.6288,
+      "step": 85
+    },
+    {
+      "epoch": 0.4236453201970443,
+      "grad_norm": 0.5494425892829895,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.8375,
+      "step": 86
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.6044692397117615,
+      "learning_rate": 0.0001964891583395557,
+      "loss": 0.8642,
+      "step": 87
+    },
+    {
+      "epoch": 0.43349753694581283,
+      "grad_norm": 0.6321963667869568,
+      "learning_rate": 0.00019638421585599423,
+      "loss": 0.6427,
+      "step": 88
+    },
+    {
+      "epoch": 0.43842364532019706,
+      "grad_norm": 0.591774046421051,
+      "learning_rate": 0.0001962777568294242,
+      "loss": 0.812,
+      "step": 89
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 0.4774153232574463,
+      "learning_rate": 0.0001961697829349093,
+      "loss": 0.6251,
+      "step": 90
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.3739103674888611,
+      "learning_rate": 0.00019606029587134854,
+      "loss": 0.4022,
+      "step": 91
+    },
+    {
+      "epoch": 0.45320197044334976,
+      "grad_norm": 0.33491694927215576,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 0.3867,
+      "step": 92
+    },
+    {
+      "epoch": 0.458128078817734,
+      "grad_norm": 0.5062631964683533,
+      "learning_rate": 0.00019583678915170233,
+      "loss": 0.691,
+      "step": 93
+    },
+    {
+      "epoch": 0.4630541871921182,
+      "grad_norm": 0.44269800186157227,
+      "learning_rate": 0.00019572277301234986,
+      "loss": 0.5816,
+      "step": 94
+    },
+    {
+      "epoch": 0.46798029556650245,
+      "grad_norm": 0.5803526639938354,
+      "learning_rate": 0.00019560725073736226,
+      "loss": 0.9605,
+      "step": 95
+    },
+    {
+      "epoch": 0.4729064039408867,
+      "grad_norm": 0.4676986038684845,
+      "learning_rate": 0.0001954902241444074,
+      "loss": 0.4847,
+      "step": 96
+    },
+    {
+      "epoch": 0.47783251231527096,
+      "grad_norm": 0.4004145860671997,
+      "learning_rate": 0.0001953716950748227,
+      "loss": 0.5009,
+      "step": 97
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.4633149206638336,
+      "learning_rate": 0.00019525166539358606,
+      "loss": 0.6022,
+      "step": 98
+    },
+    {
+      "epoch": 0.4876847290640394,
+      "grad_norm": 0.5013838410377502,
+      "learning_rate": 0.00019513013698928652,
+      "loss": 0.5579,
+      "step": 99
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.42055630683898926,
+      "learning_rate": 0.00019500711177409454,
+      "loss": 0.6106,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975369458128079,
+      "grad_norm": 0.5310317873954773,
+      "learning_rate": 0.00019488259168373197,
+      "loss": 0.5404,
+      "step": 101
+    },
+    {
+      "epoch": 0.5024630541871922,
+      "grad_norm": 0.5370813012123108,
+      "learning_rate": 0.0001947565786774415,
+      "loss": 0.7316,
+      "step": 102
+    },
+    {
+      "epoch": 0.5024630541871922,
+      "eval_loss": 0.6300095319747925,
+      "eval_runtime": 11.037,
+      "eval_samples_per_second": 4.077,
+      "eval_steps_per_second": 2.084,
+      "step": 102
+    },
+    {
+      "epoch": 0.5073891625615764,
+      "grad_norm": 0.6000672578811646,
+      "learning_rate": 0.0001946290747379559,
+      "loss": 0.8484,
+      "step": 103
+    },
+    {
+      "epoch": 0.5123152709359606,
+      "grad_norm": 0.5001861453056335,
+      "learning_rate": 0.00019450008187146684,
+      "loss": 0.475,
+      "step": 104
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.4290579557418823,
+      "learning_rate": 0.00019436960210759326,
+      "loss": 0.4866,
+      "step": 105
+    },
+    {
+      "epoch": 0.5221674876847291,
+      "grad_norm": 0.6716535091400146,
+      "learning_rate": 0.0001942376374993494,
+      "loss": 0.8152,
+      "step": 106
+    },
+    {
+      "epoch": 0.5270935960591133,
+      "grad_norm": 0.4558948874473572,
+      "learning_rate": 0.00019410419012311268,
+      "loss": 0.5321,
+      "step": 107
+    },
+    {
+      "epoch": 0.5320197044334976,
+      "grad_norm": 0.5225330591201782,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.5838,
+      "step": 108
+    },
+    {
+      "epoch": 0.5369458128078818,
+      "grad_norm": 0.5035777688026428,
+      "learning_rate": 0.00019383285548878898,
+      "loss": 0.5303,
+      "step": 109
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 0.4841632544994354,
+      "learning_rate": 0.0001936949724999762,
+      "loss": 0.5958,
+      "step": 110
+    },
+    {
+      "epoch": 0.5467980295566502,
+      "grad_norm": 0.5300568342208862,
+      "learning_rate": 0.00019355561528165165,
+      "loss": 0.5823,
+      "step": 111
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.4645020067691803,
+      "learning_rate": 0.00019341478602651069,
+      "loss": 0.5323,
+      "step": 112
+    },
+    {
+      "epoch": 0.5566502463054187,
+      "grad_norm": 0.5558884143829346,
+      "learning_rate": 0.0001932724869504101,
+      "loss": 0.7341,
+      "step": 113
+    },
+    {
+      "epoch": 0.5615763546798029,
+      "grad_norm": 0.5705283284187317,
+      "learning_rate": 0.00019312872029233339,
+      "loss": 0.617,
+      "step": 114
+    },
+    {
+      "epoch": 0.5665024630541872,
+      "grad_norm": 0.48577770590782166,
+      "learning_rate": 0.0001929834883143555,
+      "loss": 0.7458,
+      "step": 115
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.5642262101173401,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 0.8641,
+      "step": 116
+    },
+    {
+      "epoch": 0.5763546798029556,
+      "grad_norm": 0.4224662780761719,
+      "learning_rate": 0.00019268863756223938,
+      "loss": 0.5858,
+      "step": 117
+    },
+    {
+      "epoch": 0.5812807881773399,
+      "grad_norm": 0.5003111958503723,
+      "learning_rate": 0.0001925390234273861,
+      "loss": 0.6534,
+      "step": 118
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.39336368441581726,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.4173,
+      "step": 119
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.5101594924926758,
+      "learning_rate": 0.00019223542941045817,
+      "loss": 0.7547,
+      "step": 120
+    },
+    {
+      "epoch": 0.5960591133004927,
+      "grad_norm": 0.5837039351463318,
+      "learning_rate": 0.00019208145430523805,
+      "loss": 0.6629,
+      "step": 121
+    },
+    {
+      "epoch": 0.6009852216748769,
+      "grad_norm": 0.44756221771240234,
+      "learning_rate": 0.00019192603035816656,
+      "loss": 0.5471,
+      "step": 122
+    },
+    {
+      "epoch": 0.6059113300492611,
+      "grad_norm": 0.46749138832092285,
+      "learning_rate": 0.00019176916001473857,
+      "loss": 0.5808,
+      "step": 123
+    },
+    {
+      "epoch": 0.6108374384236454,
+      "grad_norm": 0.5669186115264893,
+      "learning_rate": 0.00019161084574320696,
+      "loss": 0.6666,
+      "step": 124
+    },
+    {
+      "epoch": 0.6157635467980296,
+      "grad_norm": 0.39391183853149414,
+      "learning_rate": 0.00019145109003454396,
+      "loss": 0.4012,
+      "step": 125
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.597058892250061,
+      "learning_rate": 0.00019128989540240178,
+      "loss": 0.5815,
+      "step": 126
+    },
+    {
+      "epoch": 0.625615763546798,
+      "grad_norm": 0.42727410793304443,
+      "learning_rate": 0.00019112726438307327,
+      "loss": 0.543,
+      "step": 127
+    },
+    {
+      "epoch": 0.6305418719211823,
+      "grad_norm": 0.4960153102874756,
+      "learning_rate": 0.00019096319953545185,
+      "loss": 0.8382,
+      "step": 128
+    },
+    {
+      "epoch": 0.6354679802955665,
+      "grad_norm": 0.5167288780212402,
+      "learning_rate": 0.00019079770344099126,
+      "loss": 0.6161,
+      "step": 129
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 0.43096935749053955,
+      "learning_rate": 0.000190630778703665,
+      "loss": 0.446,
+      "step": 130
+    },
+    {
+      "epoch": 0.645320197044335,
+      "grad_norm": 0.48677173256874084,
+      "learning_rate": 0.00019046242794992538,
+      "loss": 0.5953,
+      "step": 131
+    },
+    {
+      "epoch": 0.6502463054187192,
+      "grad_norm": 0.43192002177238464,
+      "learning_rate": 0.00019029265382866214,
+      "loss": 0.6484,
+      "step": 132
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.4542531669139862,
+      "learning_rate": 0.00019012145901116072,
+      "loss": 0.6714,
+      "step": 133
+    },
+    {
+      "epoch": 0.6600985221674877,
+      "grad_norm": 0.5044397115707397,
+      "learning_rate": 0.00018994884619106031,
+      "loss": 0.5707,
+      "step": 134
+    },
+    {
+      "epoch": 0.6650246305418719,
+      "grad_norm": 0.5109909772872925,
+      "learning_rate": 0.00018977481808431156,
+      "loss": 0.5733,
+      "step": 135
+    },
+    {
+      "epoch": 0.6699507389162561,
+      "grad_norm": 0.408963680267334,
+      "learning_rate": 0.00018959937742913359,
+      "loss": 0.4026,
+      "step": 136
+    },
+    {
+      "epoch": 0.6748768472906403,
+      "grad_norm": 0.4982157051563263,
+      "learning_rate": 0.00018942252698597113,
+      "loss": 0.5858,
+      "step": 137
+    },
+    {
+      "epoch": 0.6798029556650246,
+      "grad_norm": 0.43446001410484314,
+      "learning_rate": 0.000189244269537451,
+      "loss": 0.399,
+      "step": 138
+    },
+    {
+      "epoch": 0.6847290640394089,
+      "grad_norm": 0.563456118106842,
+      "learning_rate": 0.0001890646078883383,
+      "loss": 0.609,
+      "step": 139
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.5484267473220825,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 0.6773,
+      "step": 140
+    },
+    {
+      "epoch": 0.6945812807881774,
+      "grad_norm": 0.3881613314151764,
+      "learning_rate": 0.00018870108331782217,
+      "loss": 0.4737,
+      "step": 141
+    },
+    {
+      "epoch": 0.6995073891625616,
+      "grad_norm": 0.45160579681396484,
+      "learning_rate": 0.00018851722611624164,
+      "loss": 0.4898,
+      "step": 142
+    },
+    {
+      "epoch": 0.7044334975369458,
+      "grad_norm": 0.43751001358032227,
+      "learning_rate": 0.0001883319761536244,
+      "loss": 0.4106,
+      "step": 143
+    },
+    {
+      "epoch": 0.7093596059113301,
+      "grad_norm": 0.4221664369106293,
+      "learning_rate": 0.00018814533634475822,
+      "loss": 0.7008,
+      "step": 144
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.4563562572002411,
+      "learning_rate": 0.00018795730962629917,
+      "loss": 0.5083,
+      "step": 145
+    },
+    {
+      "epoch": 0.7192118226600985,
+      "grad_norm": 0.43079623579978943,
+      "learning_rate": 0.00018776789895672558,
+      "loss": 0.5056,
+      "step": 146
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.536952793598175,
+      "learning_rate": 0.00018757710731629116,
+      "loss": 0.7533,
+      "step": 147
+    },
+    {
+      "epoch": 0.729064039408867,
+      "grad_norm": 0.507958710193634,
+      "learning_rate": 0.00018738493770697852,
+      "loss": 0.6007,
+      "step": 148
+    },
+    {
+      "epoch": 0.7339901477832512,
+      "grad_norm": 0.5080809593200684,
+      "learning_rate": 0.00018719139315245148,
+      "loss": 0.6368,
+      "step": 149
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.43527957797050476,
+      "learning_rate": 0.0001869964766980079,
+      "loss": 0.6269,
+      "step": 150
+    },
+    {
+      "epoch": 0.7438423645320197,
+      "grad_norm": 0.5668943524360657,
+      "learning_rate": 0.00018680019141053156,
+      "loss": 0.6683,
+      "step": 151
+    },
+    {
+      "epoch": 0.7487684729064039,
+      "grad_norm": 0.4798513352870941,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.6075,
+      "step": 152
+    },
+    {
+      "epoch": 0.7536945812807881,
+      "grad_norm": 0.4836024045944214,
+      "learning_rate": 0.0001864035267116554,
+      "loss": 0.5161,
+      "step": 153
+    },
+    {
+      "epoch": 0.7536945812807881,
+      "eval_loss": 0.5951735377311707,
+      "eval_runtime": 11.0583,
+      "eval_samples_per_second": 4.069,
+      "eval_steps_per_second": 2.08,
+      "step": 153
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.4657806158065796,
+      "learning_rate": 0.00018620315354151695,
+      "loss": 0.5469,
+      "step": 154
+    },
+    {
+      "epoch": 0.7635467980295566,
+      "grad_norm": 0.4219043254852295,
+      "learning_rate": 0.00018600142402077006,
+      "loss": 0.389,
+      "step": 155
+    },
+    {
+      "epoch": 0.7684729064039408,
+      "grad_norm": 0.42991775274276733,
+      "learning_rate": 0.00018579834132349772,
+      "loss": 0.4041,
+      "step": 156
+    },
+    {
+      "epoch": 0.7733990147783252,
+      "grad_norm": 0.4750354290008545,
+      "learning_rate": 0.00018559390864507418,
+      "loss": 0.4167,
+      "step": 157
+    },
+    {
+      "epoch": 0.7783251231527094,
+      "grad_norm": 0.470115065574646,
+      "learning_rate": 0.0001853881292021148,
+      "loss": 0.5946,
+      "step": 158
+    },
+    {
+      "epoch": 0.7832512315270936,
+      "grad_norm": 0.4590957462787628,
+      "learning_rate": 0.00018518100623242547,
+      "loss": 0.3899,
+      "step": 159
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.6609347462654114,
+      "learning_rate": 0.00018497254299495146,
+      "loss": 0.7092,
+      "step": 160
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.687901496887207,
+      "learning_rate": 0.00018476274276972636,
+      "loss": 0.97,
+      "step": 161
+    },
+    {
+      "epoch": 0.7980295566502463,
+      "grad_norm": 0.49742093682289124,
+      "learning_rate": 0.00018455160885782045,
+      "loss": 0.8148,
+      "step": 162
+    },
+    {
+      "epoch": 0.8029556650246306,
+      "grad_norm": 0.4497315585613251,
+      "learning_rate": 0.0001843391445812886,
+      "loss": 0.383,
+      "step": 163
+    },
+    {
+      "epoch": 0.8078817733990148,
+      "grad_norm": 0.6029507517814636,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 0.6391,
+      "step": 164
+    },
+    {
+      "epoch": 0.812807881773399,
+      "grad_norm": 0.48474130034446716,
+      "learning_rate": 0.00018391023832717624,
+      "loss": 0.655,
+      "step": 165
+    },
+    {
+      "epoch": 0.8177339901477833,
+      "grad_norm": 0.3837825059890747,
+      "learning_rate": 0.00018369380309815698,
+      "loss": 0.5073,
+      "step": 166
+    },
+    {
+      "epoch": 0.8226600985221675,
+      "grad_norm": 0.5352115035057068,
+      "learning_rate": 0.00018347605100152802,
+      "loss": 0.8059,
+      "step": 167
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.37411192059516907,
+      "learning_rate": 0.00018325698546347715,
+      "loss": 0.3482,
+      "step": 168
+    },
+    {
+      "epoch": 0.8325123152709359,
+      "grad_norm": 0.5351614952087402,
+      "learning_rate": 0.00018303660993085826,
+      "loss": 0.8118,
+      "step": 169
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 0.516040027141571,
+      "learning_rate": 0.00018281492787113708,
+      "loss": 0.8158,
+      "step": 170
+    },
+    {
+      "epoch": 0.8423645320197044,
+      "grad_norm": 0.5002651214599609,
+      "learning_rate": 0.0001825919427723369,
+      "loss": 0.5554,
+      "step": 171
+    },
+    {
+      "epoch": 0.8472906403940886,
+      "grad_norm": 0.5356642007827759,
+      "learning_rate": 0.0001823676581429833,
+      "loss": 0.4798,
+      "step": 172
+    },
+    {
+      "epoch": 0.8522167487684729,
+      "grad_norm": 0.5253735184669495,
+      "learning_rate": 0.00018214207751204918,
+      "loss": 0.6372,
+      "step": 173
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.4893580675125122,
+      "learning_rate": 0.0001819152044288992,
+      "loss": 0.6477,
+      "step": 174
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.5049504041671753,
+      "learning_rate": 0.0001816870424632339,
+      "loss": 0.6475,
+      "step": 175
+    },
+    {
+      "epoch": 0.8669950738916257,
+      "grad_norm": 0.4409392476081848,
+      "learning_rate": 0.00018145759520503358,
+      "loss": 0.4051,
+      "step": 176
+    },
+    {
+      "epoch": 0.8719211822660099,
+      "grad_norm": 0.49714887142181396,
+      "learning_rate": 0.00018122686626450174,
+      "loss": 0.581,
+      "step": 177
+    },
+    {
+      "epoch": 0.8768472906403941,
+      "grad_norm": 0.4551338851451874,
+      "learning_rate": 0.00018099485927200836,
+      "loss": 0.54,
+      "step": 178
+    },
+    {
+      "epoch": 0.8817733990147784,
+      "grad_norm": 0.4689117670059204,
+      "learning_rate": 0.00018076157787803268,
+      "loss": 0.4337,
+      "step": 179
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.3948321044445038,
+      "learning_rate": 0.00018052702575310588,
+      "loss": 0.3073,
+      "step": 180
+    },
+    {
+      "epoch": 0.8916256157635468,
+      "grad_norm": 0.5096619129180908,
+      "learning_rate": 0.0001802912065877532,
+      "loss": 0.6153,
+      "step": 181
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.49955296516418457,
+      "learning_rate": 0.00018005412409243606,
+      "loss": 0.6417,
+      "step": 182
+    },
+    {
+      "epoch": 0.9014778325123153,
+      "grad_norm": 0.5724025964736938,
+      "learning_rate": 0.0001798157819974934,
+      "loss": 0.524,
+      "step": 183
+    },
+    {
+      "epoch": 0.9064039408866995,
+      "grad_norm": 0.573061466217041,
+      "learning_rate": 0.00017957618405308324,
+      "loss": 0.5929,
+      "step": 184
+    },
+    {
+      "epoch": 0.9113300492610837,
+      "grad_norm": 0.5818294882774353,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 0.6464,
+      "step": 185
+    },
+    {
+      "epoch": 0.916256157635468,
+      "grad_norm": 0.5145869851112366,
+      "learning_rate": 0.00017909323571523294,
+      "loss": 0.6867,
+      "step": 186
+    },
+    {
+      "epoch": 0.9211822660098522,
+      "grad_norm": 0.4173225462436676,
+      "learning_rate": 0.0001788498929206711,
+      "loss": 0.3869,
+      "step": 187
+    },
+    {
+      "epoch": 0.9261083743842364,
+      "grad_norm": 0.4742754101753235,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 0.6324,
+      "step": 188
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.4032367765903473,
+      "learning_rate": 0.00017835948922441755,
+      "loss": 0.3317,
+      "step": 189
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 0.5449414253234863,
+      "learning_rate": 0.00017811243603890934,
+      "loss": 0.6642,
+      "step": 190
+    },
+    {
+      "epoch": 0.9408866995073891,
+      "grad_norm": 0.3662044405937195,
+      "learning_rate": 0.00017786415380497553,
+      "loss": 0.4073,
+      "step": 191
+    },
+    {
+      "epoch": 0.9458128078817734,
+      "grad_norm": 0.5382059812545776,
+      "learning_rate": 0.0001776146464291757,
+      "loss": 1.0491,
+      "step": 192
+    },
+    {
+      "epoch": 0.9507389162561576,
+      "grad_norm": 0.406678169965744,
+      "learning_rate": 0.0001773639178373463,
+      "loss": 0.5818,
+      "step": 193
+    },
+    {
+      "epoch": 0.9556650246305419,
+      "grad_norm": 0.44329485297203064,
+      "learning_rate": 0.00017711197197453878,
+      "loss": 0.3998,
+      "step": 194
+    },
+    {
+      "epoch": 0.9605911330049262,
+      "grad_norm": 0.5197709798812866,
+      "learning_rate": 0.0001768588128049576,
+      "loss": 0.7085,
+      "step": 195
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.4579933285713196,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.5236,
+      "step": 196
+    },
+    {
+      "epoch": 0.9704433497536946,
+      "grad_norm": 0.5653615593910217,
+      "learning_rate": 0.00017634887049768237,
+      "loss": 0.7925,
+      "step": 197
+    },
+    {
+      "epoch": 0.9753694581280788,
+      "grad_norm": 0.46353796124458313,
+      "learning_rate": 0.00017609209538359917,
+      "loss": 0.4271,
+      "step": 198
+    },
+    {
+      "epoch": 0.9802955665024631,
+      "grad_norm": 0.5367504358291626,
+      "learning_rate": 0.00017583412300983776,
+      "loss": 0.5715,
+      "step": 199
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.470466673374176,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 0.3894,
+      "step": 200
+    },
+    {
+      "epoch": 0.9901477832512315,
+      "grad_norm": 0.6407225728034973,
+      "learning_rate": 0.00017531460273816532,
+      "loss": 0.6297,
+      "step": 201
+    },
+    {
+      "epoch": 0.9950738916256158,
+      "grad_norm": 0.44787856936454773,
+      "learning_rate": 0.00017505306301456822,
+      "loss": 0.4496,
+      "step": 202
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431913018226624,
+      "learning_rate": 0.0001747903423797921,
+      "loss": 0.4843,
+      "step": 203
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 812,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 203,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.058455441781555e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-203/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bf012787e91b667ff263fbb8cf29a77de7813ddb5a7593e1b3ff73159f5131
+size 6392

checkpoint-406/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_7b_v2
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-406/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b_v2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-406/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63d1127c7a19c867f425475908fdaf04a3878b477ceeff69c3504ac8328d567
+size 80013120

checkpoint-406/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e74f74766ae0ccf8f8e749e79917eb8f486c54cb93d875e51220d8f82ac899
+size 41120084

checkpoint-406/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+size 14244

checkpoint-406/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8275d8789703ca084468efdcc23dbf2888ef4bac867a45f55e20cd93d91bd239
+size 1064

checkpoint-406/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
+  }
+}

checkpoint-406/tokenizer.model

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

checkpoint-406/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}

checkpoint-406/trainer_state.json

@@ -0,0 +1,2939 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 51,
+  "global_step": 406,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0049261083743842365,
+      "grad_norm": 0.15764524042606354,
+      "learning_rate": 1e-05,
+      "loss": 1.0718,
+      "step": 1
+    },
+    {
+      "epoch": 0.0049261083743842365,
+      "eval_loss": 0.9604623317718506,
+      "eval_runtime": 11.0685,
+      "eval_samples_per_second": 4.066,
+      "eval_steps_per_second": 2.078,
+      "step": 1
+    },
+    {
+      "epoch": 0.009852216748768473,
+      "grad_norm": 0.17232584953308105,
+      "learning_rate": 2e-05,
+      "loss": 1.0695,
+      "step": 2
+    },
+    {
+      "epoch": 0.014778325123152709,
+      "grad_norm": 0.17787113785743713,
+      "learning_rate": 3e-05,
+      "loss": 0.9787,
+      "step": 3
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.18442076444625854,
+      "learning_rate": 4e-05,
+      "loss": 1.0556,
+      "step": 4
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.1500977873802185,
+      "learning_rate": 5e-05,
+      "loss": 0.8182,
+      "step": 5
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.1790969967842102,
+      "learning_rate": 6e-05,
+      "loss": 0.8186,
+      "step": 6
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.17189474403858185,
+      "learning_rate": 7e-05,
+      "loss": 0.9289,
+      "step": 7
+    },
+    {
+      "epoch": 0.03940886699507389,
+      "grad_norm": 0.21660089492797852,
+      "learning_rate": 8e-05,
+      "loss": 1.1689,
+      "step": 8
+    },
+    {
+      "epoch": 0.04433497536945813,
+      "grad_norm": 0.202072873711586,
+      "learning_rate": 9e-05,
+      "loss": 0.8433,
+      "step": 9
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 0.20105081796646118,
+      "learning_rate": 0.0001,
+      "loss": 1.1257,
+      "step": 10
+    },
+    {
+      "epoch": 0.054187192118226604,
+      "grad_norm": 0.23838526010513306,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.9087,
+      "step": 11
+    },
+    {
+      "epoch": 0.059113300492610835,
+      "grad_norm": 0.28929364681243896,
+      "learning_rate": 0.00012,
+      "loss": 1.0844,
+      "step": 12
+    },
+    {
+      "epoch": 0.06403940886699508,
+      "grad_norm": 0.26252612471580505,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.8561,
+      "step": 13
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.30341705679893494,
+      "learning_rate": 0.00014,
+      "loss": 0.9649,
+      "step": 14
+    },
+    {
+      "epoch": 0.07389162561576355,
+      "grad_norm": 0.35611552000045776,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1053,
+      "step": 15
+    },
+    {
+      "epoch": 0.07881773399014778,
+      "grad_norm": 0.2868112027645111,
+      "learning_rate": 0.00016,
+      "loss": 0.7479,
+      "step": 16
+    },
+    {
+      "epoch": 0.08374384236453201,
+      "grad_norm": 0.3906789720058441,
+      "learning_rate": 0.00017,
+      "loss": 0.887,
+      "step": 17
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 0.34518149495124817,
+      "learning_rate": 0.00018,
+      "loss": 0.6395,
+      "step": 18
+    },
+    {
+      "epoch": 0.09359605911330049,
+      "grad_norm": 0.43788307905197144,
+      "learning_rate": 0.00019,
+      "loss": 0.8385,
+      "step": 19
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.5314550399780273,
+      "learning_rate": 0.0002,
+      "loss": 0.8561,
+      "step": 20
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.5479442477226257,
+      "learning_rate": 0.00019999921328248872,
+      "loss": 0.9136,
+      "step": 21
+    },
+    {
+      "epoch": 0.10837438423645321,
+      "grad_norm": 0.46753960847854614,
+      "learning_rate": 0.0001999968531423333,
+      "loss": 0.8868,
+      "step": 22
+    },
+    {
+      "epoch": 0.11330049261083744,
+      "grad_norm": 0.5541612505912781,
+      "learning_rate": 0.00019999291961666908,
+      "loss": 1.0887,
+      "step": 23
+    },
+    {
+      "epoch": 0.11822660098522167,
+      "grad_norm": 0.5009401440620422,
+      "learning_rate": 0.00019998741276738754,
+      "loss": 0.7118,
+      "step": 24
+    },
+    {
+      "epoch": 0.12315270935960591,
+      "grad_norm": 0.5104517936706543,
+      "learning_rate": 0.00019998033268113526,
+      "loss": 0.8755,
+      "step": 25
+    },
+    {
+      "epoch": 0.12807881773399016,
+      "grad_norm": 0.46783849596977234,
+      "learning_rate": 0.0001999716794693129,
+      "loss": 0.745,
+      "step": 26
+    },
+    {
+      "epoch": 0.1330049261083744,
+      "grad_norm": 0.4237991273403168,
+      "learning_rate": 0.00019996145326807313,
+      "loss": 0.9907,
+      "step": 27
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.482265442609787,
+      "learning_rate": 0.00019994965423831854,
+      "loss": 0.8543,
+      "step": 28
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.3490796387195587,
+      "learning_rate": 0.0001999362825656992,
+      "loss": 0.5405,
+      "step": 29
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 0.450983464717865,
+      "learning_rate": 0.00019992133846060968,
+      "loss": 0.7886,
+      "step": 30
+    },
+    {
+      "epoch": 0.15270935960591134,
+      "grad_norm": 0.46920955181121826,
+      "learning_rate": 0.0001999048221581858,
+      "loss": 0.7652,
+      "step": 31
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "grad_norm": 0.4696129858493805,
+      "learning_rate": 0.0001998867339183008,
+      "loss": 0.8397,
+      "step": 32
+    },
+    {
+      "epoch": 0.1625615763546798,
+      "grad_norm": 0.4254930317401886,
+      "learning_rate": 0.00019986707402556145,
+      "loss": 0.7488,
+      "step": 33
+    },
+    {
+      "epoch": 0.16748768472906403,
+      "grad_norm": 0.45232057571411133,
+      "learning_rate": 0.0001998458427893033,
+      "loss": 0.6505,
+      "step": 34
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.4483110308647156,
+      "learning_rate": 0.00019982304054358614,
+      "loss": 0.7754,
+      "step": 35
+    },
+    {
+      "epoch": 0.17733990147783252,
+      "grad_norm": 0.40316057205200195,
+      "learning_rate": 0.00019979866764718843,
+      "loss": 0.5503,
+      "step": 36
+    },
+    {
+      "epoch": 0.18226600985221675,
+      "grad_norm": 0.40666651725769043,
+      "learning_rate": 0.0001997727244836019,
+      "loss": 0.5926,
+      "step": 37
+    },
+    {
+      "epoch": 0.18719211822660098,
+      "grad_norm": 0.44321340322494507,
+      "learning_rate": 0.00019974521146102537,
+      "loss": 0.7276,
+      "step": 38
+    },
+    {
+      "epoch": 0.1921182266009852,
+      "grad_norm": 0.38087835907936096,
+      "learning_rate": 0.00019971612901235832,
+      "loss": 0.6578,
+      "step": 39
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.479129433631897,
+      "learning_rate": 0.00019968547759519425,
+      "loss": 0.7137,
+      "step": 40
+    },
+    {
+      "epoch": 0.2019704433497537,
+      "grad_norm": 0.5175262689590454,
+      "learning_rate": 0.00019965325769181325,
+      "loss": 0.9117,
+      "step": 41
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.3792617619037628,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 0.5606,
+      "step": 42
+    },
+    {
+      "epoch": 0.21182266009852216,
+      "grad_norm": 0.4176344573497772,
+      "learning_rate": 0.0001995841144789086,
+      "loss": 0.687,
+      "step": 43
+    },
+    {
+      "epoch": 0.21674876847290642,
+      "grad_norm": 0.37092089653015137,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 0.5669,
+      "step": 44
+    },
+    {
+      "epoch": 0.22167487684729065,
+      "grad_norm": 0.45256292819976807,
+      "learning_rate": 0.00019950870372532138,
+      "loss": 0.9317,
+      "step": 45
+    },
+    {
+      "epoch": 0.22660098522167488,
+      "grad_norm": 0.47242656350135803,
+      "learning_rate": 0.00019946864948853935,
+      "loss": 0.5439,
+      "step": 46
+    },
+    {
+      "epoch": 0.2315270935960591,
+      "grad_norm": 0.5142560601234436,
+      "learning_rate": 0.00019942703017718975,
+      "loss": 0.8644,
+      "step": 47
+    },
+    {
+      "epoch": 0.23645320197044334,
+      "grad_norm": 0.553180456161499,
+      "learning_rate": 0.00019938384644612543,
+      "loss": 0.8806,
+      "step": 48
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.43755683302879333,
+      "learning_rate": 0.00019933909897481433,
+      "loss": 0.8555,
+      "step": 49
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 0.4272922873497009,
+      "learning_rate": 0.00019929278846732884,
+      "loss": 0.4278,
+      "step": 50
+    },
+    {
+      "epoch": 0.2512315270935961,
+      "grad_norm": 0.5655816197395325,
+      "learning_rate": 0.0001992449156523347,
+      "loss": 0.7756,
+      "step": 51
+    },
+    {
+      "epoch": 0.2512315270935961,
+      "eval_loss": 0.6830816268920898,
+      "eval_runtime": 11.0415,
+      "eval_samples_per_second": 4.076,
+      "eval_steps_per_second": 2.083,
+      "step": 51
+    },
+    {
+      "epoch": 0.2561576354679803,
+      "grad_norm": 0.435141384601593,
+      "learning_rate": 0.00019919548128307954,
+      "loss": 0.6849,
+      "step": 52
+    },
+    {
+      "epoch": 0.26108374384236455,
+      "grad_norm": 0.49647849798202515,
+      "learning_rate": 0.00019914448613738106,
+      "loss": 0.5521,
+      "step": 53
+    },
+    {
+      "epoch": 0.2660098522167488,
+      "grad_norm": 0.4620106518268585,
+      "learning_rate": 0.0001990919310176147,
+      "loss": 0.563,
+      "step": 54
+    },
+    {
+      "epoch": 0.270935960591133,
+      "grad_norm": 0.461224764585495,
+      "learning_rate": 0.00019903781675070117,
+      "loss": 0.603,
+      "step": 55
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.4303002953529358,
+      "learning_rate": 0.0001989821441880933,
+      "loss": 0.6271,
+      "step": 56
+    },
+    {
+      "epoch": 0.28078817733990147,
+      "grad_norm": 0.46398401260375977,
+      "learning_rate": 0.00019892491420576261,
+      "loss": 0.5245,
+      "step": 57
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.4930243492126465,
+      "learning_rate": 0.00019886612770418578,
+      "loss": 0.6301,
+      "step": 58
+    },
+    {
+      "epoch": 0.29064039408866993,
+      "grad_norm": 0.47263646125793457,
+      "learning_rate": 0.00019880578560833016,
+      "loss": 0.6773,
+      "step": 59
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.40455955266952515,
+      "learning_rate": 0.00019874388886763944,
+      "loss": 0.4478,
+      "step": 60
+    },
+    {
+      "epoch": 0.30049261083743845,
+      "grad_norm": 0.587720513343811,
+      "learning_rate": 0.00019868043845601863,
+      "loss": 0.8783,
+      "step": 61
+    },
+    {
+      "epoch": 0.3054187192118227,
+      "grad_norm": 0.5045145153999329,
+      "learning_rate": 0.00019861543537181867,
+      "loss": 0.6364,
+      "step": 62
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.5762777328491211,
+      "learning_rate": 0.00019854888063782088,
+      "loss": 1.0393,
+      "step": 63
+    },
+    {
+      "epoch": 0.31527093596059114,
+      "grad_norm": 0.5282868146896362,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7865,
+      "step": 64
+    },
+    {
+      "epoch": 0.32019704433497537,
+      "grad_norm": 0.5349370241165161,
+      "learning_rate": 0.0001984111204336116,
+      "loss": 0.7984,
+      "step": 65
+    },
+    {
+      "epoch": 0.3251231527093596,
+      "grad_norm": 0.4982023239135742,
+      "learning_rate": 0.0001983399171309674,
+      "loss": 0.8803,
+      "step": 66
+    },
+    {
+      "epoch": 0.33004926108374383,
+      "grad_norm": 0.467535138130188,
+      "learning_rate": 0.00019826716651362585,
+      "loss": 0.6774,
+      "step": 67
+    },
+    {
+      "epoch": 0.33497536945812806,
+      "grad_norm": 0.36764436960220337,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 0.4467,
+      "step": 68
+    },
+    {
+      "epoch": 0.3399014778325123,
+      "grad_norm": 0.4941648840904236,
+      "learning_rate": 0.00019811702793791355,
+      "loss": 0.6345,
+      "step": 69
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.5048440098762512,
+      "learning_rate": 0.0001980396423418757,
+      "loss": 0.641,
+      "step": 70
+    },
+    {
+      "epoch": 0.3497536945812808,
+      "grad_norm": 0.5182650685310364,
+      "learning_rate": 0.00019796071415576925,
+      "loss": 0.6989,
+      "step": 71
+    },
+    {
+      "epoch": 0.35467980295566504,
+      "grad_norm": 0.504978358745575,
+      "learning_rate": 0.00019788024462147788,
+      "loss": 0.7198,
+      "step": 72
+    },
+    {
+      "epoch": 0.35960591133004927,
+      "grad_norm": 0.5767678022384644,
+      "learning_rate": 0.00019779823500513745,
+      "loss": 0.9102,
+      "step": 73
+    },
+    {
+      "epoch": 0.3645320197044335,
+      "grad_norm": 0.5125048756599426,
+      "learning_rate": 0.00019771468659711595,
+      "loss": 0.6646,
+      "step": 74
+    },
+    {
+      "epoch": 0.3694581280788177,
+      "grad_norm": 0.4948768615722656,
+      "learning_rate": 0.00019762960071199333,
+      "loss": 0.7312,
+      "step": 75
+    },
+    {
+      "epoch": 0.37438423645320196,
+      "grad_norm": 0.45587611198425293,
+      "learning_rate": 0.00019754297868854073,
+      "loss": 0.6778,
+      "step": 76
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.49900615215301514,
+      "learning_rate": 0.0001974548218896993,
+      "loss": 0.724,
+      "step": 77
+    },
+    {
+      "epoch": 0.3842364532019704,
+      "grad_norm": 0.533632755279541,
+      "learning_rate": 0.00019736513170255911,
+      "loss": 0.5307,
+      "step": 78
+    },
+    {
+      "epoch": 0.3891625615763547,
+      "grad_norm": 0.5380002856254578,
+      "learning_rate": 0.0001972739095383369,
+      "loss": 0.725,
+      "step": 79
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.6754060983657837,
+      "learning_rate": 0.00019718115683235417,
+      "loss": 1.04,
+      "step": 80
+    },
+    {
+      "epoch": 0.39901477832512317,
+      "grad_norm": 0.674319326877594,
+      "learning_rate": 0.0001970868750440145,
+      "loss": 0.9026,
+      "step": 81
+    },
+    {
+      "epoch": 0.4039408866995074,
+      "grad_norm": 0.5251882672309875,
+      "learning_rate": 0.0001969910656567805,
+      "loss": 0.615,
+      "step": 82
+    },
+    {
+      "epoch": 0.4088669950738916,
+      "grad_norm": 0.5495942831039429,
+      "learning_rate": 0.00019689373017815073,
+      "loss": 0.7116,
+      "step": 83
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.4467202425003052,
+      "learning_rate": 0.00019679487013963564,
+      "loss": 0.4405,
+      "step": 84
+    },
+    {
+      "epoch": 0.4187192118226601,
+      "grad_norm": 0.4973738491535187,
+      "learning_rate": 0.0001966944870967337,
+      "loss": 0.6288,
+      "step": 85
+    },
+    {
+      "epoch": 0.4236453201970443,
+      "grad_norm": 0.5494425892829895,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.8375,
+      "step": 86
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.6044692397117615,
+      "learning_rate": 0.0001964891583395557,
+      "loss": 0.8642,
+      "step": 87
+    },
+    {
+      "epoch": 0.43349753694581283,
+      "grad_norm": 0.6321963667869568,
+      "learning_rate": 0.00019638421585599423,
+      "loss": 0.6427,
+      "step": 88
+    },
+    {
+      "epoch": 0.43842364532019706,
+      "grad_norm": 0.591774046421051,
+      "learning_rate": 0.0001962777568294242,
+      "loss": 0.812,
+      "step": 89
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 0.4774153232574463,
+      "learning_rate": 0.0001961697829349093,
+      "loss": 0.6251,
+      "step": 90
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.3739103674888611,
+      "learning_rate": 0.00019606029587134854,
+      "loss": 0.4022,
+      "step": 91
+    },
+    {
+      "epoch": 0.45320197044334976,
+      "grad_norm": 0.33491694927215576,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 0.3867,
+      "step": 92
+    },
+    {
+      "epoch": 0.458128078817734,
+      "grad_norm": 0.5062631964683533,
+      "learning_rate": 0.00019583678915170233,
+      "loss": 0.691,
+      "step": 93
+    },
+    {
+      "epoch": 0.4630541871921182,
+      "grad_norm": 0.44269800186157227,
+      "learning_rate": 0.00019572277301234986,
+      "loss": 0.5816,
+      "step": 94
+    },
+    {
+      "epoch": 0.46798029556650245,
+      "grad_norm": 0.5803526639938354,
+      "learning_rate": 0.00019560725073736226,
+      "loss": 0.9605,
+      "step": 95
+    },
+    {
+      "epoch": 0.4729064039408867,
+      "grad_norm": 0.4676986038684845,
+      "learning_rate": 0.0001954902241444074,
+      "loss": 0.4847,
+      "step": 96
+    },
+    {
+      "epoch": 0.47783251231527096,
+      "grad_norm": 0.4004145860671997,
+      "learning_rate": 0.0001953716950748227,
+      "loss": 0.5009,
+      "step": 97
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.4633149206638336,
+      "learning_rate": 0.00019525166539358606,
+      "loss": 0.6022,
+      "step": 98
+    },
+    {
+      "epoch": 0.4876847290640394,
+      "grad_norm": 0.5013838410377502,
+      "learning_rate": 0.00019513013698928652,
+      "loss": 0.5579,
+      "step": 99
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.42055630683898926,
+      "learning_rate": 0.00019500711177409454,
+      "loss": 0.6106,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975369458128079,
+      "grad_norm": 0.5310317873954773,
+      "learning_rate": 0.00019488259168373197,
+      "loss": 0.5404,
+      "step": 101
+    },
+    {
+      "epoch": 0.5024630541871922,
+      "grad_norm": 0.5370813012123108,
+      "learning_rate": 0.0001947565786774415,
+      "loss": 0.7316,
+      "step": 102
+    },
+    {
+      "epoch": 0.5024630541871922,
+      "eval_loss": 0.6300095319747925,
+      "eval_runtime": 11.037,
+      "eval_samples_per_second": 4.077,
+      "eval_steps_per_second": 2.084,
+      "step": 102
+    },
+    {
+      "epoch": 0.5073891625615764,
+      "grad_norm": 0.6000672578811646,
+      "learning_rate": 0.0001946290747379559,
+      "loss": 0.8484,
+      "step": 103
+    },
+    {
+      "epoch": 0.5123152709359606,
+      "grad_norm": 0.5001861453056335,
+      "learning_rate": 0.00019450008187146684,
+      "loss": 0.475,
+      "step": 104
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.4290579557418823,
+      "learning_rate": 0.00019436960210759326,
+      "loss": 0.4866,
+      "step": 105
+    },
+    {
+      "epoch": 0.5221674876847291,
+      "grad_norm": 0.6716535091400146,
+      "learning_rate": 0.0001942376374993494,
+      "loss": 0.8152,
+      "step": 106
+    },
+    {
+      "epoch": 0.5270935960591133,
+      "grad_norm": 0.4558948874473572,
+      "learning_rate": 0.00019410419012311268,
+      "loss": 0.5321,
+      "step": 107
+    },
+    {
+      "epoch": 0.5320197044334976,
+      "grad_norm": 0.5225330591201782,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.5838,
+      "step": 108
+    },
+    {
+      "epoch": 0.5369458128078818,
+      "grad_norm": 0.5035777688026428,
+      "learning_rate": 0.00019383285548878898,
+      "loss": 0.5303,
+      "step": 109
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 0.4841632544994354,
+      "learning_rate": 0.0001936949724999762,
+      "loss": 0.5958,
+      "step": 110
+    },
+    {
+      "epoch": 0.5467980295566502,
+      "grad_norm": 0.5300568342208862,
+      "learning_rate": 0.00019355561528165165,
+      "loss": 0.5823,
+      "step": 111
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.4645020067691803,
+      "learning_rate": 0.00019341478602651069,
+      "loss": 0.5323,
+      "step": 112
+    },
+    {
+      "epoch": 0.5566502463054187,
+      "grad_norm": 0.5558884143829346,
+      "learning_rate": 0.0001932724869504101,
+      "loss": 0.7341,
+      "step": 113
+    },
+    {
+      "epoch": 0.5615763546798029,
+      "grad_norm": 0.5705283284187317,
+      "learning_rate": 0.00019312872029233339,
+      "loss": 0.617,
+      "step": 114
+    },
+    {
+      "epoch": 0.5665024630541872,
+      "grad_norm": 0.48577770590782166,
+      "learning_rate": 0.0001929834883143555,
+      "loss": 0.7458,
+      "step": 115
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.5642262101173401,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 0.8641,
+      "step": 116
+    },
+    {
+      "epoch": 0.5763546798029556,
+      "grad_norm": 0.4224662780761719,
+      "learning_rate": 0.00019268863756223938,
+      "loss": 0.5858,
+      "step": 117
+    },
+    {
+      "epoch": 0.5812807881773399,
+      "grad_norm": 0.5003111958503723,
+      "learning_rate": 0.0001925390234273861,
+      "loss": 0.6534,
+      "step": 118
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.39336368441581726,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.4173,
+      "step": 119
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.5101594924926758,
+      "learning_rate": 0.00019223542941045817,
+      "loss": 0.7547,
+      "step": 120
+    },
+    {
+      "epoch": 0.5960591133004927,
+      "grad_norm": 0.5837039351463318,
+      "learning_rate": 0.00019208145430523805,
+      "loss": 0.6629,
+      "step": 121
+    },
+    {
+      "epoch": 0.6009852216748769,
+      "grad_norm": 0.44756221771240234,
+      "learning_rate": 0.00019192603035816656,
+      "loss": 0.5471,
+      "step": 122
+    },
+    {
+      "epoch": 0.6059113300492611,
+      "grad_norm": 0.46749138832092285,
+      "learning_rate": 0.00019176916001473857,
+      "loss": 0.5808,
+      "step": 123
+    },
+    {
+      "epoch": 0.6108374384236454,
+      "grad_norm": 0.5669186115264893,
+      "learning_rate": 0.00019161084574320696,
+      "loss": 0.6666,
+      "step": 124
+    },
+    {
+      "epoch": 0.6157635467980296,
+      "grad_norm": 0.39391183853149414,
+      "learning_rate": 0.00019145109003454396,
+      "loss": 0.4012,
+      "step": 125
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.597058892250061,
+      "learning_rate": 0.00019128989540240178,
+      "loss": 0.5815,
+      "step": 126
+    },
+    {
+      "epoch": 0.625615763546798,
+      "grad_norm": 0.42727410793304443,
+      "learning_rate": 0.00019112726438307327,
+      "loss": 0.543,
+      "step": 127
+    },
+    {
+      "epoch": 0.6305418719211823,
+      "grad_norm": 0.4960153102874756,
+      "learning_rate": 0.00019096319953545185,
+      "loss": 0.8382,
+      "step": 128
+    },
+    {
+      "epoch": 0.6354679802955665,
+      "grad_norm": 0.5167288780212402,
+      "learning_rate": 0.00019079770344099126,
+      "loss": 0.6161,
+      "step": 129
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 0.43096935749053955,
+      "learning_rate": 0.000190630778703665,
+      "loss": 0.446,
+      "step": 130
+    },
+    {
+      "epoch": 0.645320197044335,
+      "grad_norm": 0.48677173256874084,
+      "learning_rate": 0.00019046242794992538,
+      "loss": 0.5953,
+      "step": 131
+    },
+    {
+      "epoch": 0.6502463054187192,
+      "grad_norm": 0.43192002177238464,
+      "learning_rate": 0.00019029265382866214,
+      "loss": 0.6484,
+      "step": 132
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.4542531669139862,
+      "learning_rate": 0.00019012145901116072,
+      "loss": 0.6714,
+      "step": 133
+    },
+    {
+      "epoch": 0.6600985221674877,
+      "grad_norm": 0.5044397115707397,
+      "learning_rate": 0.00018994884619106031,
+      "loss": 0.5707,
+      "step": 134
+    },
+    {
+      "epoch": 0.6650246305418719,
+      "grad_norm": 0.5109909772872925,
+      "learning_rate": 0.00018977481808431156,
+      "loss": 0.5733,
+      "step": 135
+    },
+    {
+      "epoch": 0.6699507389162561,
+      "grad_norm": 0.408963680267334,
+      "learning_rate": 0.00018959937742913359,
+      "loss": 0.4026,
+      "step": 136
+    },
+    {
+      "epoch": 0.6748768472906403,
+      "grad_norm": 0.4982157051563263,
+      "learning_rate": 0.00018942252698597113,
+      "loss": 0.5858,
+      "step": 137
+    },
+    {
+      "epoch": 0.6798029556650246,
+      "grad_norm": 0.43446001410484314,
+      "learning_rate": 0.000189244269537451,
+      "loss": 0.399,
+      "step": 138
+    },
+    {
+      "epoch": 0.6847290640394089,
+      "grad_norm": 0.563456118106842,
+      "learning_rate": 0.0001890646078883383,
+      "loss": 0.609,
+      "step": 139
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.5484267473220825,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 0.6773,
+      "step": 140
+    },
+    {
+      "epoch": 0.6945812807881774,
+      "grad_norm": 0.3881613314151764,
+      "learning_rate": 0.00018870108331782217,
+      "loss": 0.4737,
+      "step": 141
+    },
+    {
+      "epoch": 0.6995073891625616,
+      "grad_norm": 0.45160579681396484,
+      "learning_rate": 0.00018851722611624164,
+      "loss": 0.4898,
+      "step": 142
+    },
+    {
+      "epoch": 0.7044334975369458,
+      "grad_norm": 0.43751001358032227,
+      "learning_rate": 0.0001883319761536244,
+      "loss": 0.4106,
+      "step": 143
+    },
+    {
+      "epoch": 0.7093596059113301,
+      "grad_norm": 0.4221664369106293,
+      "learning_rate": 0.00018814533634475822,
+      "loss": 0.7008,
+      "step": 144
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.4563562572002411,
+      "learning_rate": 0.00018795730962629917,
+      "loss": 0.5083,
+      "step": 145
+    },
+    {
+      "epoch": 0.7192118226600985,
+      "grad_norm": 0.43079623579978943,
+      "learning_rate": 0.00018776789895672558,
+      "loss": 0.5056,
+      "step": 146
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.536952793598175,
+      "learning_rate": 0.00018757710731629116,
+      "loss": 0.7533,
+      "step": 147
+    },
+    {
+      "epoch": 0.729064039408867,
+      "grad_norm": 0.507958710193634,
+      "learning_rate": 0.00018738493770697852,
+      "loss": 0.6007,
+      "step": 148
+    },
+    {
+      "epoch": 0.7339901477832512,
+      "grad_norm": 0.5080809593200684,
+      "learning_rate": 0.00018719139315245148,
+      "loss": 0.6368,
+      "step": 149
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.43527957797050476,
+      "learning_rate": 0.0001869964766980079,
+      "loss": 0.6269,
+      "step": 150
+    },
+    {
+      "epoch": 0.7438423645320197,
+      "grad_norm": 0.5668943524360657,
+      "learning_rate": 0.00018680019141053156,
+      "loss": 0.6683,
+      "step": 151
+    },
+    {
+      "epoch": 0.7487684729064039,
+      "grad_norm": 0.4798513352870941,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.6075,
+      "step": 152
+    },
+    {
+      "epoch": 0.7536945812807881,
+      "grad_norm": 0.4836024045944214,
+      "learning_rate": 0.0001864035267116554,
+      "loss": 0.5161,
+      "step": 153
+    },
+    {
+      "epoch": 0.7536945812807881,
+      "eval_loss": 0.5951735377311707,
+      "eval_runtime": 11.0583,
+      "eval_samples_per_second": 4.069,
+      "eval_steps_per_second": 2.08,
+      "step": 153
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.4657806158065796,
+      "learning_rate": 0.00018620315354151695,
+      "loss": 0.5469,
+      "step": 154
+    },
+    {
+      "epoch": 0.7635467980295566,
+      "grad_norm": 0.4219043254852295,
+      "learning_rate": 0.00018600142402077006,
+      "loss": 0.389,
+      "step": 155
+    },
+    {
+      "epoch": 0.7684729064039408,
+      "grad_norm": 0.42991775274276733,
+      "learning_rate": 0.00018579834132349772,
+      "loss": 0.4041,
+      "step": 156
+    },
+    {
+      "epoch": 0.7733990147783252,
+      "grad_norm": 0.4750354290008545,
+      "learning_rate": 0.00018559390864507418,
+      "loss": 0.4167,
+      "step": 157
+    },
+    {
+      "epoch": 0.7783251231527094,
+      "grad_norm": 0.470115065574646,
+      "learning_rate": 0.0001853881292021148,
+      "loss": 0.5946,
+      "step": 158
+    },
+    {
+      "epoch": 0.7832512315270936,
+      "grad_norm": 0.4590957462787628,
+      "learning_rate": 0.00018518100623242547,
+      "loss": 0.3899,
+      "step": 159
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.6609347462654114,
+      "learning_rate": 0.00018497254299495146,
+      "loss": 0.7092,
+      "step": 160
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.687901496887207,
+      "learning_rate": 0.00018476274276972636,
+      "loss": 0.97,
+      "step": 161
+    },
+    {
+      "epoch": 0.7980295566502463,
+      "grad_norm": 0.49742093682289124,
+      "learning_rate": 0.00018455160885782045,
+      "loss": 0.8148,
+      "step": 162
+    },
+    {
+      "epoch": 0.8029556650246306,
+      "grad_norm": 0.4497315585613251,
+      "learning_rate": 0.0001843391445812886,
+      "loss": 0.383,
+      "step": 163
+    },
+    {
+      "epoch": 0.8078817733990148,
+      "grad_norm": 0.6029507517814636,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 0.6391,
+      "step": 164
+    },
+    {
+      "epoch": 0.812807881773399,
+      "grad_norm": 0.48474130034446716,
+      "learning_rate": 0.00018391023832717624,
+      "loss": 0.655,
+      "step": 165
+    },
+    {
+      "epoch": 0.8177339901477833,
+      "grad_norm": 0.3837825059890747,
+      "learning_rate": 0.00018369380309815698,
+      "loss": 0.5073,
+      "step": 166
+    },
+    {
+      "epoch": 0.8226600985221675,
+      "grad_norm": 0.5352115035057068,
+      "learning_rate": 0.00018347605100152802,
+      "loss": 0.8059,
+      "step": 167
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.37411192059516907,
+      "learning_rate": 0.00018325698546347715,
+      "loss": 0.3482,
+      "step": 168
+    },
+    {
+      "epoch": 0.8325123152709359,
+      "grad_norm": 0.5351614952087402,
+      "learning_rate": 0.00018303660993085826,
+      "loss": 0.8118,
+      "step": 169
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 0.516040027141571,
+      "learning_rate": 0.00018281492787113708,
+      "loss": 0.8158,
+      "step": 170
+    },
+    {
+      "epoch": 0.8423645320197044,
+      "grad_norm": 0.5002651214599609,
+      "learning_rate": 0.0001825919427723369,
+      "loss": 0.5554,
+      "step": 171
+    },
+    {
+      "epoch": 0.8472906403940886,
+      "grad_norm": 0.5356642007827759,
+      "learning_rate": 0.0001823676581429833,
+      "loss": 0.4798,
+      "step": 172
+    },
+    {
+      "epoch": 0.8522167487684729,
+      "grad_norm": 0.5253735184669495,
+      "learning_rate": 0.00018214207751204918,
+      "loss": 0.6372,
+      "step": 173
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.4893580675125122,
+      "learning_rate": 0.0001819152044288992,
+      "loss": 0.6477,
+      "step": 174
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.5049504041671753,
+      "learning_rate": 0.0001816870424632339,
+      "loss": 0.6475,
+      "step": 175
+    },
+    {
+      "epoch": 0.8669950738916257,
+      "grad_norm": 0.4409392476081848,
+      "learning_rate": 0.00018145759520503358,
+      "loss": 0.4051,
+      "step": 176
+    },
+    {
+      "epoch": 0.8719211822660099,
+      "grad_norm": 0.49714887142181396,
+      "learning_rate": 0.00018122686626450174,
+      "loss": 0.581,
+      "step": 177
+    },
+    {
+      "epoch": 0.8768472906403941,
+      "grad_norm": 0.4551338851451874,
+      "learning_rate": 0.00018099485927200836,
+      "loss": 0.54,
+      "step": 178
+    },
+    {
+      "epoch": 0.8817733990147784,
+      "grad_norm": 0.4689117670059204,
+      "learning_rate": 0.00018076157787803268,
+      "loss": 0.4337,
+      "step": 179
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.3948321044445038,
+      "learning_rate": 0.00018052702575310588,
+      "loss": 0.3073,
+      "step": 180
+    },
+    {
+      "epoch": 0.8916256157635468,
+      "grad_norm": 0.5096619129180908,
+      "learning_rate": 0.0001802912065877532,
+      "loss": 0.6153,
+      "step": 181
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.49955296516418457,
+      "learning_rate": 0.00018005412409243606,
+      "loss": 0.6417,
+      "step": 182
+    },
+    {
+      "epoch": 0.9014778325123153,
+      "grad_norm": 0.5724025964736938,
+      "learning_rate": 0.0001798157819974934,
+      "loss": 0.524,
+      "step": 183
+    },
+    {
+      "epoch": 0.9064039408866995,
+      "grad_norm": 0.573061466217041,
+      "learning_rate": 0.00017957618405308324,
+      "loss": 0.5929,
+      "step": 184
+    },
+    {
+      "epoch": 0.9113300492610837,
+      "grad_norm": 0.5818294882774353,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 0.6464,
+      "step": 185
+    },
+    {
+      "epoch": 0.916256157635468,
+      "grad_norm": 0.5145869851112366,
+      "learning_rate": 0.00017909323571523294,
+      "loss": 0.6867,
+      "step": 186
+    },
+    {
+      "epoch": 0.9211822660098522,
+      "grad_norm": 0.4173225462436676,
+      "learning_rate": 0.0001788498929206711,
+      "loss": 0.3869,
+      "step": 187
+    },
+    {
+      "epoch": 0.9261083743842364,
+      "grad_norm": 0.4742754101753235,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 0.6324,
+      "step": 188
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.4032367765903473,
+      "learning_rate": 0.00017835948922441755,
+      "loss": 0.3317,
+      "step": 189
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 0.5449414253234863,
+      "learning_rate": 0.00017811243603890934,
+      "loss": 0.6642,
+      "step": 190
+    },
+    {
+      "epoch": 0.9408866995073891,
+      "grad_norm": 0.3662044405937195,
+      "learning_rate": 0.00017786415380497553,
+      "loss": 0.4073,
+      "step": 191
+    },
+    {
+      "epoch": 0.9458128078817734,
+      "grad_norm": 0.5382059812545776,
+      "learning_rate": 0.0001776146464291757,
+      "loss": 1.0491,
+      "step": 192
+    },
+    {
+      "epoch": 0.9507389162561576,
+      "grad_norm": 0.406678169965744,
+      "learning_rate": 0.0001773639178373463,
+      "loss": 0.5818,
+      "step": 193
+    },
+    {
+      "epoch": 0.9556650246305419,
+      "grad_norm": 0.44329485297203064,
+      "learning_rate": 0.00017711197197453878,
+      "loss": 0.3998,
+      "step": 194
+    },
+    {
+      "epoch": 0.9605911330049262,
+      "grad_norm": 0.5197709798812866,
+      "learning_rate": 0.0001768588128049576,
+      "loss": 0.7085,
+      "step": 195
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.4579933285713196,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.5236,
+      "step": 196
+    },
+    {
+      "epoch": 0.9704433497536946,
+      "grad_norm": 0.5653615593910217,
+      "learning_rate": 0.00017634887049768237,
+      "loss": 0.7925,
+      "step": 197
+    },
+    {
+      "epoch": 0.9753694581280788,
+      "grad_norm": 0.46353796124458313,
+      "learning_rate": 0.00017609209538359917,
+      "loss": 0.4271,
+      "step": 198
+    },
+    {
+      "epoch": 0.9802955665024631,
+      "grad_norm": 0.5367504358291626,
+      "learning_rate": 0.00017583412300983776,
+      "loss": 0.5715,
+      "step": 199
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.470466673374176,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 0.3894,
+      "step": 200
+    },
+    {
+      "epoch": 0.9901477832512315,
+      "grad_norm": 0.6407225728034973,
+      "learning_rate": 0.00017531460273816532,
+      "loss": 0.6297,
+      "step": 201
+    },
+    {
+      "epoch": 0.9950738916256158,
+      "grad_norm": 0.44787856936454773,
+      "learning_rate": 0.00017505306301456822,
+      "loss": 0.4496,
+      "step": 202
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431913018226624,
+      "learning_rate": 0.0001747903423797921,
+      "loss": 0.4843,
+      "step": 203
+    },
+    {
+      "epoch": 1.0049261083743843,
+      "grad_norm": 0.3732824921607971,
+      "learning_rate": 0.0001745264449675755,
+      "loss": 0.2465,
+      "step": 204
+    },
+    {
+      "epoch": 1.0049261083743843,
+      "eval_loss": 0.5774902701377869,
+      "eval_runtime": 11.086,
+      "eval_samples_per_second": 4.059,
+      "eval_steps_per_second": 2.075,
+      "step": 204
+    },
+    {
+      "epoch": 1.0098522167487685,
+      "grad_norm": 0.4518275558948517,
+      "learning_rate": 0.00017426137493017265,
+      "loss": 0.3676,
+      "step": 205
+    },
+    {
+      "epoch": 1.0147783251231528,
+      "grad_norm": 0.41071954369544983,
+      "learning_rate": 0.0001739951364382884,
+      "loss": 0.4175,
+      "step": 206
+    },
+    {
+      "epoch": 1.019704433497537,
+      "grad_norm": 0.6320828199386597,
+      "learning_rate": 0.0001737277336810124,
+      "loss": 0.6605,
+      "step": 207
+    },
+    {
+      "epoch": 1.0246305418719213,
+      "grad_norm": 0.5452926158905029,
+      "learning_rate": 0.00017345917086575332,
+      "loss": 0.5126,
+      "step": 208
+    },
+    {
+      "epoch": 1.0295566502463054,
+      "grad_norm": 0.5548157691955566,
+      "learning_rate": 0.00017318945221817255,
+      "loss": 0.4749,
+      "step": 209
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.6151676774024963,
+      "learning_rate": 0.00017291858198211773,
+      "loss": 0.52,
+      "step": 210
+    },
+    {
+      "epoch": 1.0394088669950738,
+      "grad_norm": 0.5246535539627075,
+      "learning_rate": 0.00017264656441955603,
+      "loss": 0.5984,
+      "step": 211
+    },
+    {
+      "epoch": 1.0443349753694582,
+      "grad_norm": 0.5412974953651428,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 0.4845,
+      "step": 212
+    },
+    {
+      "epoch": 1.0492610837438423,
+      "grad_norm": 0.4644743502140045,
+      "learning_rate": 0.00017209910445297542,
+      "loss": 0.4952,
+      "step": 213
+    },
+    {
+      "epoch": 1.0541871921182266,
+      "grad_norm": 0.5570724010467529,
+      "learning_rate": 0.00017182367066288342,
+      "loss": 0.4349,
+      "step": 214
+    },
+    {
+      "epoch": 1.0591133004926108,
+      "grad_norm": 0.602289617061615,
+      "learning_rate": 0.00017154710677400265,
+      "loss": 0.5497,
+      "step": 215
+    },
+    {
+      "epoch": 1.064039408866995,
+      "grad_norm": 0.577187180519104,
+      "learning_rate": 0.00017126941713788632,
+      "loss": 0.4701,
+      "step": 216
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.5879427194595337,
+      "learning_rate": 0.00017099060612380028,
+      "loss": 0.5623,
+      "step": 217
+    },
+    {
+      "epoch": 1.0738916256157636,
+      "grad_norm": 0.6489105224609375,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.609,
+      "step": 218
+    },
+    {
+      "epoch": 1.0788177339901477,
+      "grad_norm": 0.6771227717399597,
+      "learning_rate": 0.00017042963752693502,
+      "loss": 0.5906,
+      "step": 219
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.617244303226471,
+      "learning_rate": 0.00017014748877063214,
+      "loss": 0.4835,
+      "step": 220
+    },
+    {
+      "epoch": 1.0886699507389164,
+      "grad_norm": 0.7694700360298157,
+      "learning_rate": 0.00016986423628917346,
+      "loss": 0.6549,
+      "step": 221
+    },
+    {
+      "epoch": 1.0935960591133005,
+      "grad_norm": 0.45222944021224976,
+      "learning_rate": 0.00016957988453935276,
+      "loss": 0.3017,
+      "step": 222
+    },
+    {
+      "epoch": 1.0985221674876848,
+      "grad_norm": 0.6281430125236511,
+      "learning_rate": 0.00016929443799526002,
+      "loss": 0.4617,
+      "step": 223
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.5648610591888428,
+      "learning_rate": 0.00016900790114821122,
+      "loss": 0.4349,
+      "step": 224
+    },
+    {
+      "epoch": 1.1083743842364533,
+      "grad_norm": 0.590632975101471,
+      "learning_rate": 0.00016872027850667735,
+      "loss": 0.4623,
+      "step": 225
+    },
+    {
+      "epoch": 1.1133004926108374,
+      "grad_norm": 0.4984714686870575,
+      "learning_rate": 0.00016843157459621384,
+      "loss": 0.2308,
+      "step": 226
+    },
+    {
+      "epoch": 1.1182266009852218,
+      "grad_norm": 0.47801119089126587,
+      "learning_rate": 0.00016814179395938913,
+      "loss": 0.3446,
+      "step": 227
+    },
+    {
+      "epoch": 1.1231527093596059,
+      "grad_norm": 0.6627326011657715,
+      "learning_rate": 0.00016785094115571322,
+      "loss": 0.575,
+      "step": 228
+    },
+    {
+      "epoch": 1.1280788177339902,
+      "grad_norm": 0.661377489566803,
+      "learning_rate": 0.00016755902076156604,
+      "loss": 0.6227,
+      "step": 229
+    },
+    {
+      "epoch": 1.1330049261083743,
+      "grad_norm": 0.5839930176734924,
+      "learning_rate": 0.00016726603737012529,
+      "loss": 0.4468,
+      "step": 230
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.660953164100647,
+      "learning_rate": 0.0001669719955912942,
+      "loss": 0.5003,
+      "step": 231
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.48201170563697815,
+      "learning_rate": 0.00016667690005162916,
+      "loss": 0.4768,
+      "step": 232
+    },
+    {
+      "epoch": 1.1477832512315271,
+      "grad_norm": 0.6323191523551941,
+      "learning_rate": 0.00016638075539426677,
+      "loss": 0.6227,
+      "step": 233
+    },
+    {
+      "epoch": 1.1527093596059113,
+      "grad_norm": 0.5048434138298035,
+      "learning_rate": 0.00016608356627885072,
+      "loss": 0.4082,
+      "step": 234
+    },
+    {
+      "epoch": 1.1576354679802956,
+      "grad_norm": 0.4962400496006012,
+      "learning_rate": 0.00016578533738145868,
+      "loss": 0.4486,
+      "step": 235
+    },
+    {
+      "epoch": 1.1625615763546797,
+      "grad_norm": 0.5392332077026367,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 0.3338,
+      "step": 236
+    },
+    {
+      "epoch": 1.167487684729064,
+      "grad_norm": 0.5738560557365417,
+      "learning_rate": 0.00016518577902678466,
+      "loss": 0.4169,
+      "step": 237
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.45562079548835754,
+      "learning_rate": 0.00016488445900316386,
+      "loss": 0.4418,
+      "step": 238
+    },
+    {
+      "epoch": 1.1773399014778325,
+      "grad_norm": 0.46458548307418823,
+      "learning_rate": 0.00016458211806474088,
+      "loss": 0.2972,
+      "step": 239
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.6105532646179199,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.625,
+      "step": 240
+    },
+    {
+      "epoch": 1.187192118226601,
+      "grad_norm": 0.6343269348144531,
+      "learning_rate": 0.00016397439248802984,
+      "loss": 0.4275,
+      "step": 241
+    },
+    {
+      "epoch": 1.1921182266009853,
+      "grad_norm": 0.5875888466835022,
+      "learning_rate": 0.00016366901741190882,
+      "loss": 0.3788,
+      "step": 242
+    },
+    {
+      "epoch": 1.1970443349753694,
+      "grad_norm": 0.5735545754432678,
+      "learning_rate": 0.00016336264054516933,
+      "loss": 0.4419,
+      "step": 243
+    },
+    {
+      "epoch": 1.2019704433497538,
+      "grad_norm": 0.7177073955535889,
+      "learning_rate": 0.00016305526670845226,
+      "loss": 0.726,
+      "step": 244
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.6101499199867249,
+      "learning_rate": 0.0001627469007380852,
+      "loss": 0.3365,
+      "step": 245
+    },
+    {
+      "epoch": 1.2118226600985222,
+      "grad_norm": 0.6157029271125793,
+      "learning_rate": 0.00016243754748600635,
+      "loss": 0.436,
+      "step": 246
+    },
+    {
+      "epoch": 1.2167487684729064,
+      "grad_norm": 0.7198493480682373,
+      "learning_rate": 0.00016212721181968812,
+      "loss": 0.6299,
+      "step": 247
+    },
+    {
+      "epoch": 1.2216748768472907,
+      "grad_norm": 0.6608026027679443,
+      "learning_rate": 0.00016181589862206052,
+      "loss": 0.5704,
+      "step": 248
+    },
+    {
+      "epoch": 1.2266009852216748,
+      "grad_norm": 0.5983904600143433,
+      "learning_rate": 0.0001615036127914345,
+      "loss": 0.4425,
+      "step": 249
+    },
+    {
+      "epoch": 1.2315270935960592,
+      "grad_norm": 0.5112388730049133,
+      "learning_rate": 0.00016119035924142466,
+      "loss": 0.4805,
+      "step": 250
+    },
+    {
+      "epoch": 1.2364532019704433,
+      "grad_norm": 0.6211384534835815,
+      "learning_rate": 0.00016087614290087208,
+      "loss": 0.5718,
+      "step": 251
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.6166737675666809,
+      "learning_rate": 0.00016056096871376667,
+      "loss": 0.5045,
+      "step": 252
+    },
+    {
+      "epoch": 1.2463054187192117,
+      "grad_norm": 0.5174737572669983,
+      "learning_rate": 0.00016024484163916952,
+      "loss": 0.2844,
+      "step": 253
+    },
+    {
+      "epoch": 1.251231527093596,
+      "grad_norm": 0.5628989338874817,
+      "learning_rate": 0.0001599277666511347,
+      "loss": 0.4168,
+      "step": 254
+    },
+    {
+      "epoch": 1.2561576354679804,
+      "grad_norm": 0.5588826537132263,
+      "learning_rate": 0.00015960974873863114,
+      "loss": 0.3408,
+      "step": 255
+    },
+    {
+      "epoch": 1.2561576354679804,
+      "eval_loss": 0.5714771747589111,
+      "eval_runtime": 11.1786,
+      "eval_samples_per_second": 4.026,
+      "eval_steps_per_second": 2.058,
+      "step": 255
+    },
+    {
+      "epoch": 1.2610837438423645,
+      "grad_norm": 0.47429361939430237,
+      "learning_rate": 0.00015929079290546408,
+      "loss": 0.3027,
+      "step": 256
+    },
+    {
+      "epoch": 1.2660098522167487,
+      "grad_norm": 0.7338742613792419,
+      "learning_rate": 0.0001589709041701962,
+      "loss": 0.5326,
+      "step": 257
+    },
+    {
+      "epoch": 1.270935960591133,
+      "grad_norm": 0.6908726096153259,
+      "learning_rate": 0.00015865008756606904,
+      "loss": 0.5045,
+      "step": 258
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.7498694658279419,
+      "learning_rate": 0.00015832834814092332,
+      "loss": 0.5976,
+      "step": 259
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 0.6521242260932922,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 0.552,
+      "step": 260
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.5835188031196594,
+      "learning_rate": 0.00015768212109145975,
+      "loss": 0.3854,
+      "step": 261
+    },
+    {
+      "epoch": 1.29064039408867,
+      "grad_norm": 0.4915793836116791,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 0.3531,
+      "step": 262
+    },
+    {
+      "epoch": 1.2955665024630543,
+      "grad_norm": 0.6469236612319946,
+      "learning_rate": 0.0001570322636934964,
+      "loss": 0.4179,
+      "step": 263
+    },
+    {
+      "epoch": 1.3004926108374384,
+      "grad_norm": 0.5294272899627686,
+      "learning_rate": 0.00015670598638627706,
+      "loss": 0.5197,
+      "step": 264
+    },
+    {
+      "epoch": 1.3054187192118227,
+      "grad_norm": 0.8104782700538635,
+      "learning_rate": 0.00015637881684720805,
+      "loss": 0.5919,
+      "step": 265
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.6078993082046509,
+      "learning_rate": 0.0001560507602240894,
+      "loss": 0.4743,
+      "step": 266
+    },
+    {
+      "epoch": 1.3152709359605912,
+      "grad_norm": 0.7405218482017517,
+      "learning_rate": 0.000155721821678679,
+      "loss": 0.5671,
+      "step": 267
+    },
+    {
+      "epoch": 1.3201970443349753,
+      "grad_norm": 0.7156871557235718,
+      "learning_rate": 0.00015539200638661104,
+      "loss": 0.5013,
+      "step": 268
+    },
+    {
+      "epoch": 1.3251231527093597,
+      "grad_norm": 0.6963270902633667,
+      "learning_rate": 0.0001550613195373149,
+      "loss": 0.7078,
+      "step": 269
+    },
+    {
+      "epoch": 1.3300492610837438,
+      "grad_norm": 0.6525111198425293,
+      "learning_rate": 0.00015472976633393326,
+      "loss": 0.3107,
+      "step": 270
+    },
+    {
+      "epoch": 1.3349753694581281,
+      "grad_norm": 0.7296736836433411,
+      "learning_rate": 0.00015439735199324032,
+      "loss": 0.416,
+      "step": 271
+    },
+    {
+      "epoch": 1.3399014778325122,
+      "grad_norm": 0.6551435589790344,
+      "learning_rate": 0.00015406408174555976,
+      "loss": 0.3226,
+      "step": 272
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.7207363843917847,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 0.5027,
+      "step": 273
+    },
+    {
+      "epoch": 1.3497536945812807,
+      "grad_norm": 0.7445921897888184,
+      "learning_rate": 0.00015339499451778364,
+      "loss": 0.4475,
+      "step": 274
+    },
+    {
+      "epoch": 1.354679802955665,
+      "grad_norm": 0.5955771803855896,
+      "learning_rate": 0.00015305918806534082,
+      "loss": 0.4876,
+      "step": 275
+    },
+    {
+      "epoch": 1.3596059113300494,
+      "grad_norm": 0.5247209072113037,
+      "learning_rate": 0.00015272254676105025,
+      "loss": 0.4293,
+      "step": 276
+    },
+    {
+      "epoch": 1.3645320197044335,
+      "grad_norm": 0.7054429054260254,
+      "learning_rate": 0.00015238507590174417,
+      "loss": 0.6231,
+      "step": 277
+    },
+    {
+      "epoch": 1.3694581280788176,
+      "grad_norm": 0.5251216292381287,
+      "learning_rate": 0.00015204678079730724,
+      "loss": 0.3443,
+      "step": 278
+    },
+    {
+      "epoch": 1.374384236453202,
+      "grad_norm": 0.6474141478538513,
+      "learning_rate": 0.0001517076667705931,
+      "loss": 0.4946,
+      "step": 279
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.654502272605896,
+      "learning_rate": 0.00015136773915734066,
+      "loss": 0.6073,
+      "step": 280
+    },
+    {
+      "epoch": 1.3842364532019704,
+      "grad_norm": 0.7839478850364685,
+      "learning_rate": 0.00015102700330609,
+      "loss": 0.5921,
+      "step": 281
+    },
+    {
+      "epoch": 1.3891625615763548,
+      "grad_norm": 0.6912551522254944,
+      "learning_rate": 0.0001506854645780983,
+      "loss": 0.4686,
+      "step": 282
+    },
+    {
+      "epoch": 1.3940886699507389,
+      "grad_norm": 0.6430887579917908,
+      "learning_rate": 0.0001503431283472556,
+      "loss": 0.5105,
+      "step": 283
+    },
+    {
+      "epoch": 1.3990147783251232,
+      "grad_norm": 0.5742291212081909,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4308,
+      "step": 284
+    },
+    {
+      "epoch": 1.4039408866995073,
+      "grad_norm": 0.5854840874671936,
+      "learning_rate": 0.00014965608493523313,
+      "loss": 0.3606,
+      "step": 285
+    },
+    {
+      "epoch": 1.4088669950738917,
+      "grad_norm": 0.6118752956390381,
+      "learning_rate": 0.00014931138856423502,
+      "loss": 0.4141,
+      "step": 286
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.6871208548545837,
+      "learning_rate": 0.00014896591631057912,
+      "loss": 0.4697,
+      "step": 287
+    },
+    {
+      "epoch": 1.4187192118226601,
+      "grad_norm": 0.7824487686157227,
+      "learning_rate": 0.00014861967361004687,
+      "loss": 0.653,
+      "step": 288
+    },
+    {
+      "epoch": 1.4236453201970443,
+      "grad_norm": 0.7655541300773621,
+      "learning_rate": 0.0001482726659105422,
+      "loss": 0.4795,
+      "step": 289
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.6854352951049805,
+      "learning_rate": 0.0001479248986720057,
+      "loss": 0.5587,
+      "step": 290
+    },
+    {
+      "epoch": 1.4334975369458127,
+      "grad_norm": 0.6824727058410645,
+      "learning_rate": 0.00014757637736632898,
+      "loss": 0.4207,
+      "step": 291
+    },
+    {
+      "epoch": 1.438423645320197,
+      "grad_norm": 0.654896080493927,
+      "learning_rate": 0.0001472271074772683,
+      "loss": 0.4777,
+      "step": 292
+    },
+    {
+      "epoch": 1.4433497536945814,
+      "grad_norm": 0.49683672189712524,
+      "learning_rate": 0.00014687709450035837,
+      "loss": 0.2947,
+      "step": 293
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.47079044580459595,
+      "learning_rate": 0.00014652634394282608,
+      "loss": 0.2836,
+      "step": 294
+    },
+    {
+      "epoch": 1.4532019704433496,
+      "grad_norm": 0.562249481678009,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 0.3707,
+      "step": 295
+    },
+    {
+      "epoch": 1.458128078817734,
+      "grad_norm": 0.5470603108406067,
+      "learning_rate": 0.00014582265217274104,
+      "loss": 0.411,
+      "step": 296
+    },
+    {
+      "epoch": 1.4630541871921183,
+      "grad_norm": 0.48108726739883423,
+      "learning_rate": 0.00014546972203232112,
+      "loss": 0.27,
+      "step": 297
+    },
+    {
+      "epoch": 1.4679802955665024,
+      "grad_norm": 0.6207696795463562,
+      "learning_rate": 0.0001451160764553701,
+      "loss": 0.5093,
+      "step": 298
+    },
+    {
+      "epoch": 1.4729064039408866,
+      "grad_norm": 0.6771376729011536,
+      "learning_rate": 0.00014476172100627127,
+      "loss": 0.5358,
+      "step": 299
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 0.6966915726661682,
+      "learning_rate": 0.00014440666126057744,
+      "loss": 0.5852,
+      "step": 300
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.6209229230880737,
+      "learning_rate": 0.00014405090280492295,
+      "loss": 0.4382,
+      "step": 301
+    },
+    {
+      "epoch": 1.4876847290640394,
+      "grad_norm": 0.742935061454773,
+      "learning_rate": 0.00014369445123693596,
+      "loss": 0.6076,
+      "step": 302
+    },
+    {
+      "epoch": 1.4926108374384237,
+      "grad_norm": 0.8368776440620422,
+      "learning_rate": 0.00014333731216515028,
+      "loss": 0.6199,
+      "step": 303
+    },
+    {
+      "epoch": 1.4975369458128078,
+      "grad_norm": 0.7391186952590942,
+      "learning_rate": 0.00014297949120891718,
+      "loss": 0.3661,
+      "step": 304
+    },
+    {
+      "epoch": 1.5024630541871922,
+      "grad_norm": 0.591601550579071,
+      "learning_rate": 0.00014262099399831683,
+      "loss": 0.4744,
+      "step": 305
+    },
+    {
+      "epoch": 1.5073891625615765,
+      "grad_norm": 0.6733282208442688,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 0.5834,
+      "step": 306
+    },
+    {
+      "epoch": 1.5073891625615765,
+      "eval_loss": 0.5610231757164001,
+      "eval_runtime": 11.3154,
+      "eval_samples_per_second": 3.977,
+      "eval_steps_per_second": 2.033,
+      "step": 306
+    },
+    {
+      "epoch": 1.5123152709359606,
+      "grad_norm": 0.5315914154052734,
+      "learning_rate": 0.00014190199338744887,
+      "loss": 0.2892,
+      "step": 307
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.6961568593978882,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 0.6031,
+      "step": 308
+    },
+    {
+      "epoch": 1.522167487684729,
+      "grad_norm": 0.44431206583976746,
+      "learning_rate": 0.00014118035558439808,
+      "loss": 0.3165,
+      "step": 309
+    },
+    {
+      "epoch": 1.5270935960591134,
+      "grad_norm": 0.5725176334381104,
+      "learning_rate": 0.00014081856192247033,
+      "loss": 0.3325,
+      "step": 310
+    },
+    {
+      "epoch": 1.5320197044334976,
+      "grad_norm": 0.48680877685546875,
+      "learning_rate": 0.0001404561260069935,
+      "loss": 0.3523,
+      "step": 311
+    },
+    {
+      "epoch": 1.5369458128078817,
+      "grad_norm": 0.6941611170768738,
+      "learning_rate": 0.00014009305354066137,
+      "loss": 0.6243,
+      "step": 312
+    },
+    {
+      "epoch": 1.541871921182266,
+      "grad_norm": 0.5704216957092285,
+      "learning_rate": 0.00013972935023618318,
+      "loss": 0.4025,
+      "step": 313
+    },
+    {
+      "epoch": 1.5467980295566504,
+      "grad_norm": 0.6456660032272339,
+      "learning_rate": 0.00013936502181619416,
+      "loss": 0.5085,
+      "step": 314
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.5849847197532654,
+      "learning_rate": 0.0001390000740131652,
+      "loss": 0.3853,
+      "step": 315
+    },
+    {
+      "epoch": 1.5566502463054186,
+      "grad_norm": 0.48363542556762695,
+      "learning_rate": 0.00013863451256931287,
+      "loss": 0.4199,
+      "step": 316
+    },
+    {
+      "epoch": 1.561576354679803,
+      "grad_norm": 0.5757195949554443,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.3624,
+      "step": 317
+    },
+    {
+      "epoch": 1.5665024630541873,
+      "grad_norm": 0.5957686305046082,
+      "learning_rate": 0.00013790157177619004,
+      "loss": 0.4201,
+      "step": 318
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.5736541748046875,
+      "learning_rate": 0.0001375342039592667,
+      "loss": 0.4718,
+      "step": 319
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 0.5630667805671692,
+      "learning_rate": 0.00013716624556603274,
+      "loss": 0.3789,
+      "step": 320
+    },
+    {
+      "epoch": 1.5812807881773399,
+      "grad_norm": 0.7546968460083008,
+      "learning_rate": 0.0001367977023860745,
+      "loss": 0.5795,
+      "step": 321
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.6928917765617371,
+      "learning_rate": 0.00013642858021817943,
+      "loss": 0.5271,
+      "step": 322
+    },
+    {
+      "epoch": 1.5911330049261085,
+      "grad_norm": 0.5510915517807007,
+      "learning_rate": 0.000136058884870245,
+      "loss": 0.4151,
+      "step": 323
+    },
+    {
+      "epoch": 1.5960591133004927,
+      "grad_norm": 0.7442372441291809,
+      "learning_rate": 0.00013568862215918717,
+      "loss": 0.5533,
+      "step": 324
+    },
+    {
+      "epoch": 1.6009852216748768,
+      "grad_norm": 0.7526097297668457,
+      "learning_rate": 0.0001353177979108493,
+      "loss": 0.5425,
+      "step": 325
+    },
+    {
+      "epoch": 1.6059113300492611,
+      "grad_norm": 0.6402207016944885,
+      "learning_rate": 0.00013494641795990986,
+      "loss": 0.6017,
+      "step": 326
+    },
+    {
+      "epoch": 1.6108374384236455,
+      "grad_norm": 0.7436459064483643,
+      "learning_rate": 0.00013457448814979109,
+      "loss": 0.5229,
+      "step": 327
+    },
+    {
+      "epoch": 1.6157635467980296,
+      "grad_norm": 0.6757021546363831,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.5225,
+      "step": 328
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.5550339818000793,
+      "learning_rate": 0.00013382900236887075,
+      "loss": 0.3526,
+      "step": 329
+    },
+    {
+      "epoch": 1.625615763546798,
+      "grad_norm": 0.6458706855773926,
+      "learning_rate": 0.00013345545812780353,
+      "loss": 0.3961,
+      "step": 330
+    },
+    {
+      "epoch": 1.6305418719211824,
+      "grad_norm": 0.5926823019981384,
+      "learning_rate": 0.0001330813874868412,
+      "loss": 0.3994,
+      "step": 331
+    },
+    {
+      "epoch": 1.6354679802955665,
+      "grad_norm": 0.6645280122756958,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 0.507,
+      "step": 332
+    },
+    {
+      "epoch": 1.6403940886699506,
+      "grad_norm": 0.7319492101669312,
+      "learning_rate": 0.0001323316905564549,
+      "loss": 0.603,
+      "step": 333
+    },
+    {
+      "epoch": 1.645320197044335,
+      "grad_norm": 0.6422541737556458,
+      "learning_rate": 0.00013195607606302501,
+      "loss": 0.3432,
+      "step": 334
+    },
+    {
+      "epoch": 1.6502463054187193,
+      "grad_norm": 0.6640862226486206,
+      "learning_rate": 0.0001315799587615025,
+      "loss": 0.509,
+      "step": 335
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.6828907132148743,
+      "learning_rate": 0.0001312033445698487,
+      "loss": 0.4412,
+      "step": 336
+    },
+    {
+      "epoch": 1.6600985221674875,
+      "grad_norm": 0.6668173670768738,
+      "learning_rate": 0.00013082623941384325,
+      "loss": 0.4453,
+      "step": 337
+    },
+    {
+      "epoch": 1.6650246305418719,
+      "grad_norm": 0.600563108921051,
+      "learning_rate": 0.0001304486492269907,
+      "loss": 0.3716,
+      "step": 338
+    },
+    {
+      "epoch": 1.6699507389162562,
+      "grad_norm": 0.6383490562438965,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 0.3624,
+      "step": 339
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.612424910068512,
+      "learning_rate": 0.0001296920375328275,
+      "loss": 0.3337,
+      "step": 340
+    },
+    {
+      "epoch": 1.6798029556650245,
+      "grad_norm": 0.6634405255317688,
+      "learning_rate": 0.0001293130279303102,
+      "loss": 0.4438,
+      "step": 341
+    },
+    {
+      "epoch": 1.6847290640394088,
+      "grad_norm": 0.6734313368797302,
+      "learning_rate": 0.0001289335571063453,
+      "loss": 0.4937,
+      "step": 342
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.72150719165802,
+      "learning_rate": 0.00012855363103165957,
+      "loss": 0.3999,
+      "step": 343
+    },
+    {
+      "epoch": 1.6945812807881775,
+      "grad_norm": 0.49467992782592773,
+      "learning_rate": 0.00012817325568414297,
+      "loss": 0.2655,
+      "step": 344
+    },
+    {
+      "epoch": 1.6995073891625616,
+      "grad_norm": 0.614782452583313,
+      "learning_rate": 0.00012779243704875444,
+      "loss": 0.3216,
+      "step": 345
+    },
+    {
+      "epoch": 1.7044334975369457,
+      "grad_norm": 0.6507689952850342,
+      "learning_rate": 0.00012741118111742777,
+      "loss": 0.4357,
+      "step": 346
+    },
+    {
+      "epoch": 1.70935960591133,
+      "grad_norm": 0.6325626969337463,
+      "learning_rate": 0.0001270294938889773,
+      "loss": 0.4469,
+      "step": 347
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.6168348789215088,
+      "learning_rate": 0.00012664738136900348,
+      "loss": 0.3397,
+      "step": 348
+    },
+    {
+      "epoch": 1.7192118226600985,
+      "grad_norm": 0.5866071581840515,
+      "learning_rate": 0.00012626484956979866,
+      "loss": 0.3869,
+      "step": 349
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.8230339288711548,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 0.7113,
+      "step": 350
+    },
+    {
+      "epoch": 1.729064039408867,
+      "grad_norm": 0.6938710808753967,
+      "learning_rate": 0.00012549855221575542,
+      "loss": 0.781,
+      "step": 351
+    },
+    {
+      "epoch": 1.7339901477832513,
+      "grad_norm": 0.5978900790214539,
+      "learning_rate": 0.0001251147987181079,
+      "loss": 0.4472,
+      "step": 352
+    },
+    {
+      "epoch": 1.7389162561576355,
+      "grad_norm": 0.6921452879905701,
+      "learning_rate": 0.00012473065005542155,
+      "loss": 0.5878,
+      "step": 353
+    },
+    {
+      "epoch": 1.7438423645320196,
+      "grad_norm": 0.5542033314704895,
+      "learning_rate": 0.0001243461122720259,
+      "loss": 0.2496,
+      "step": 354
+    },
+    {
+      "epoch": 1.748768472906404,
+      "grad_norm": 0.7317242622375488,
+      "learning_rate": 0.0001239611914183731,
+      "loss": 0.4469,
+      "step": 355
+    },
+    {
+      "epoch": 1.7536945812807883,
+      "grad_norm": 0.5736520290374756,
+      "learning_rate": 0.00012357589355094275,
+      "loss": 0.3918,
+      "step": 356
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.6014077663421631,
+      "learning_rate": 0.00012319022473214632,
+      "loss": 0.4347,
+      "step": 357
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "eval_loss": 0.5540220737457275,
+      "eval_runtime": 11.2551,
+      "eval_samples_per_second": 3.998,
+      "eval_steps_per_second": 2.044,
+      "step": 357
+    },
+    {
+      "epoch": 1.7635467980295565,
+      "grad_norm": 0.6542104482650757,
+      "learning_rate": 0.00012280419103023217,
+      "loss": 0.3577,
+      "step": 358
+    },
+    {
+      "epoch": 1.7684729064039408,
+      "grad_norm": 0.6519327759742737,
+      "learning_rate": 0.0001224177985191897,
+      "loss": 0.2853,
+      "step": 359
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 0.7503228187561035,
+      "learning_rate": 0.00012203105327865407,
+      "loss": 0.6344,
+      "step": 360
+    },
+    {
+      "epoch": 1.7783251231527095,
+      "grad_norm": 0.581355094909668,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 0.5612,
+      "step": 361
+    },
+    {
+      "epoch": 1.7832512315270936,
+      "grad_norm": 0.6459757685661316,
+      "learning_rate": 0.00012125652895529766,
+      "loss": 0.4864,
+      "step": 362
+    },
+    {
+      "epoch": 1.7881773399014778,
+      "grad_norm": 0.5689775943756104,
+      "learning_rate": 0.00012086876205911389,
+      "loss": 0.3458,
+      "step": 363
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.6334294080734253,
+      "learning_rate": 0.00012048066680651908,
+      "loss": 0.4945,
+      "step": 364
+    },
+    {
+      "epoch": 1.7980295566502464,
+      "grad_norm": 0.5965712666511536,
+      "learning_rate": 0.00012009224930393988,
+      "loss": 0.3278,
+      "step": 365
+    },
+    {
+      "epoch": 1.8029556650246306,
+      "grad_norm": 0.6973611116409302,
+      "learning_rate": 0.00011970351566287333,
+      "loss": 0.3529,
+      "step": 366
+    },
+    {
+      "epoch": 1.8078817733990147,
+      "grad_norm": 0.5669241547584534,
+      "learning_rate": 0.00011931447199979057,
+      "loss": 0.4718,
+      "step": 367
+    },
+    {
+      "epoch": 1.812807881773399,
+      "grad_norm": 0.6049864292144775,
+      "learning_rate": 0.00011892512443604102,
+      "loss": 0.2931,
+      "step": 368
+    },
+    {
+      "epoch": 1.8177339901477834,
+      "grad_norm": 0.5491435527801514,
+      "learning_rate": 0.00011853547909775553,
+      "loss": 0.287,
+      "step": 369
+    },
+    {
+      "epoch": 1.8226600985221675,
+      "grad_norm": 0.6700085997581482,
+      "learning_rate": 0.00011814554211575027,
+      "loss": 0.3676,
+      "step": 370
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.6265245079994202,
+      "learning_rate": 0.00011775531962543036,
+      "loss": 0.4745,
+      "step": 371
+    },
+    {
+      "epoch": 1.832512315270936,
+      "grad_norm": 0.6745122075080872,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.4044,
+      "step": 372
+    },
+    {
+      "epoch": 1.8374384236453203,
+      "grad_norm": 0.4890718460083008,
+      "learning_rate": 0.00011697404268383141,
+      "loss": 0.2473,
+      "step": 373
+    },
+    {
+      "epoch": 1.8423645320197044,
+      "grad_norm": 0.5244059562683105,
+      "learning_rate": 0.00011658300052543742,
+      "loss": 0.2308,
+      "step": 374
+    },
+    {
+      "epoch": 1.8472906403940885,
+      "grad_norm": 0.621101975440979,
+      "learning_rate": 0.00011619169744430538,
+      "loss": 0.3971,
+      "step": 375
+    },
+    {
+      "epoch": 1.8522167487684729,
+      "grad_norm": 0.5578574538230896,
+      "learning_rate": 0.000115800139597335,
+      "loss": 0.4145,
+      "step": 376
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.8010319471359253,
+      "learning_rate": 0.00011540833314543458,
+      "loss": 0.4975,
+      "step": 377
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.8334612250328064,
+      "learning_rate": 0.00011501628425342403,
+      "loss": 0.7582,
+      "step": 378
+    },
+    {
+      "epoch": 1.8669950738916257,
+      "grad_norm": 0.49707093834877014,
+      "learning_rate": 0.00011462399908993797,
+      "loss": 0.2228,
+      "step": 379
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 0.6417017579078674,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 0.3904,
+      "step": 380
+    },
+    {
+      "epoch": 1.8768472906403941,
+      "grad_norm": 0.4788695275783539,
+      "learning_rate": 0.0001138387446415683,
+      "loss": 0.2358,
+      "step": 381
+    },
+    {
+      "epoch": 1.8817733990147785,
+      "grad_norm": 0.7310598492622375,
+      "learning_rate": 0.00011344578771215319,
+      "loss": 0.5967,
+      "step": 382
+    },
+    {
+      "epoch": 1.8866995073891626,
+      "grad_norm": 0.5737311840057373,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 0.3213,
+      "step": 383
+    },
+    {
+      "epoch": 1.8916256157635467,
+      "grad_norm": 0.5912585258483887,
+      "learning_rate": 0.00011265924535737493,
+      "loss": 0.4226,
+      "step": 384
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.6237417459487915,
+      "learning_rate": 0.00011226567230774467,
+      "loss": 0.4841,
+      "step": 385
+    },
+    {
+      "epoch": 1.9014778325123154,
+      "grad_norm": 0.6014819741249084,
+      "learning_rate": 0.00011187190626573052,
+      "loss": 0.3386,
+      "step": 386
+    },
+    {
+      "epoch": 1.9064039408866995,
+      "grad_norm": 0.6071181297302246,
+      "learning_rate": 0.00011147795342698537,
+      "loss": 0.3899,
+      "step": 387
+    },
+    {
+      "epoch": 1.9113300492610836,
+      "grad_norm": 0.609453022480011,
+      "learning_rate": 0.00011108381999010111,
+      "loss": 0.4262,
+      "step": 388
+    },
+    {
+      "epoch": 1.916256157635468,
+      "grad_norm": 0.5656450986862183,
+      "learning_rate": 0.00011068951215651132,
+      "loss": 0.34,
+      "step": 389
+    },
+    {
+      "epoch": 1.9211822660098523,
+      "grad_norm": 0.6314427852630615,
+      "learning_rate": 0.00011029503613039346,
+      "loss": 0.4736,
+      "step": 390
+    },
+    {
+      "epoch": 1.9261083743842364,
+      "grad_norm": 0.7153500914573669,
+      "learning_rate": 0.00010990039811857156,
+      "loss": 0.559,
+      "step": 391
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.6263774633407593,
+      "learning_rate": 0.00010950560433041826,
+      "loss": 0.4973,
+      "step": 392
+    },
+    {
+      "epoch": 1.935960591133005,
+      "grad_norm": 0.6896617412567139,
+      "learning_rate": 0.00010911066097775735,
+      "loss": 0.4341,
+      "step": 393
+    },
+    {
+      "epoch": 1.9408866995073892,
+      "grad_norm": 0.636617124080658,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 0.3414,
+      "step": 394
+    },
+    {
+      "epoch": 1.9458128078817734,
+      "grad_norm": 0.6351125240325928,
+      "learning_rate": 0.00010832035043787625,
+      "loss": 0.4062,
+      "step": 395
+    },
+    {
+      "epoch": 1.9507389162561575,
+      "grad_norm": 0.7071142792701721,
+      "learning_rate": 0.00010792499568567884,
+      "loss": 0.4047,
+      "step": 396
+    },
+    {
+      "epoch": 1.9556650246305418,
+      "grad_norm": 0.5642038583755493,
+      "learning_rate": 0.00010752951623882382,
+      "loss": 0.3063,
+      "step": 397
+    },
+    {
+      "epoch": 1.9605911330049262,
+      "grad_norm": 0.6832185983657837,
+      "learning_rate": 0.00010713391831992323,
+      "loss": 0.4548,
+      "step": 398
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.7424250245094299,
+      "learning_rate": 0.00010673820815345334,
+      "loss": 0.4871,
+      "step": 399
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 0.6147627830505371,
+      "learning_rate": 0.00010634239196565646,
+      "loss": 0.4571,
+      "step": 400
+    },
+    {
+      "epoch": 1.9753694581280787,
+      "grad_norm": 0.6986880302429199,
+      "learning_rate": 0.00010594647598444312,
+      "loss": 0.5246,
+      "step": 401
+    },
+    {
+      "epoch": 1.980295566502463,
+      "grad_norm": 0.7610223889350891,
+      "learning_rate": 0.00010555046643929403,
+      "loss": 0.5115,
+      "step": 402
+    },
+    {
+      "epoch": 1.9852216748768474,
+      "grad_norm": 0.5143783688545227,
+      "learning_rate": 0.0001051543695611621,
+      "loss": 0.2487,
+      "step": 403
+    },
+    {
+      "epoch": 1.9901477832512315,
+      "grad_norm": 0.4890079200267792,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 0.2312,
+      "step": 404
+    },
+    {
+      "epoch": 1.9950738916256157,
+      "grad_norm": 0.6719345450401306,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 0.4527,
+      "step": 405
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8623074293136597,
+      "learning_rate": 0.00010396561725842124,
+      "loss": 0.765,
+      "step": 406
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 812,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 203,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.123527611927757e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-406/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bf012787e91b667ff263fbb8cf29a77de7813ddb5a7593e1b3ff73159f5131
+size 6392

checkpoint-609/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_7b_v2
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-609/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b_v2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-609/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667de80454a64b889a2abfd9ab440b26c7c198bb1f1ff8df54b9a7a017f96c13
+size 80013120

checkpoint-609/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd9be43710e040f0309e5dd00d6028257ac83fc90faa7f8773a9d136666c564
+size 41120084

checkpoint-609/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5328f04f222a66b45931d6bc246721e0747decf9d78d167903d0547a248f78f0
+size 14244

checkpoint-609/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a6f8d1291bcedaa612240eca9322bb271de106a736b44078bc91e8ae05762b
+size 1064

checkpoint-609/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
+  }
+}

checkpoint-609/tokenizer.model

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

checkpoint-609/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}

checkpoint-609/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bf012787e91b667ff263fbb8cf29a77de7813ddb5a7593e1b3ff73159f5131
+size 6392

checkpoint-812/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_7b_v2
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-812/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_7b_v2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-812/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7229b2312464e672dcc771b859a217bbab77a670e3828c2e6bef1a2d15ad0b
+size 80013120

checkpoint-812/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6c24391ca4eff4d8a69425f76f4a260596756888b2dd58d5a6e49fe726230c
+size 41120084

checkpoint-812/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afbf853352cfbcfea61884ff6a2ddcd2aee1ce8618589cf5b56912c1b160011
+size 14244

checkpoint-812/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d603d4c8eda6dea22ff5f0991aca0dd577d01c4290f425e0e8390c8c183a3b0b
+size 1064

checkpoint-812/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
+  }
+}

checkpoint-812/tokenizer.model

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

checkpoint-812/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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
+}

checkpoint-812/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bf012787e91b667ff263fbb8cf29a77de7813ddb5a7593e1b3ff73159f5131
+size 6392

config.json

@@ -0,0 +1,47 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "openlm-research/open_llama_7b_v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merged/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "openlm-research/open_llama_7b_v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merged/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}