Upload folder using huggingface_hub

README.md

@@ -0,0 +1,94 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5703
+
+## 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: 0.0004
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8756        | 0.06  | 20   | 0.7111          |
+| 0.9058        | 0.11  | 40   | 0.6764          |
+| 0.7526        | 0.17  | 60   | 0.6669          |
+| 0.6926        | 0.23  | 80   | 0.6363          |
+| 0.6731        | 0.28  | 100  | 0.6187          |
+| 0.647         | 0.34  | 120  | 0.6162          |
+| 0.6219        | 0.4   | 140  | 0.6041          |
+| 0.5781        | 0.45  | 160  | 0.5937          |
+| 0.6346        | 0.51  | 180  | 0.6006          |
+| 0.7663        | 0.57  | 200  | 0.5926          |
+| 0.5864        | 0.62  | 220  | 0.5866          |
+| 0.5943        | 0.68  | 240  | 0.5756          |
+| 0.5029        | 0.74  | 260  | 0.5733          |
+| 0.5482        | 0.79  | 280  | 0.5712          |
+| 0.5413        | 0.85  | 300  | 0.5820          |
+| 0.657         | 0.91  | 320  | 0.5696          |
+| 0.506         | 0.96  | 340  | 0.5839          |
+| 0.4804        | 1.02  | 360  | 0.5803          |
+| 0.5095        | 1.08  | 380  | 0.5974          |
+| 0.4404        | 1.13  | 400  | 0.5746          |
+| 0.3869        | 1.19  | 420  | 0.5740          |
+| 0.4129        | 1.25  | 440  | 0.5777          |
+| 0.4209        | 1.3   | 460  | 0.5825          |
+| 0.4014        | 1.36  | 480  | 0.5742          |
+| 0.3333        | 1.42  | 500  | 0.5851          |
+| 0.5041        | 1.47  | 520  | 0.5798          |
+| 0.5528        | 1.53  | 540  | 0.5631          |
+| 0.4372        | 1.59  | 560  | 0.5747          |
+| 0.3901        | 1.64  | 580  | 0.5625          |
+| 0.5271        | 1.7   | 600  | 0.5746          |
+| 0.4283        | 1.76  | 620  | 0.5662          |
+| 0.4336        | 1.81  | 640  | 0.5652          |
+| 0.3534        | 1.87  | 660  | 0.5697          |
+| 0.4728        | 1.93  | 680  | 0.5713          |
+| 0.5159        | 1.98  | 700  | 0.5703          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c54b4128d3990ad30d82d6e66838a8bd6bc36e4432c3f624f2c7aa1421f118
+size 160069389

checkpoint-353/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-353/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-353/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d229b772492f04317dc1ee247837801c7d10438db8bd57b5ad7857d60c429a
+size 160069389

checkpoint-353/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641724849660ac23ff00668bd48b2c1e0973e6869fafbd2d8ec8c904af23f26a
+size 320084485

checkpoint-353/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f93f102eaaaf175492fdb02a3c11f5b20ccd2940751ff92eb1e904824636842
+size 14575

checkpoint-353/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107742fc191734e42517b7ae0045017bb6bbac30ff33e6000caec822697c5c96
+size 627

checkpoint-353/trainer_state.json

@@ -0,0 +1,2273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9994691205096443,
+  "eval_steps": 20,
+  "global_step": 353,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.9795,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.2944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 4.0746,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 4.1905,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 4.4667,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.4e-05,
+      "loss": 4.8488,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 4.1473,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.7834,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.6e-05,
+      "loss": 3.2778,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 3.1975,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.7504,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8e-05,
+      "loss": 2.5047,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 2.3366,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 2.1348,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6e-05,
+      "loss": 1.6171,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.2901,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.1358,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.2e-05,
+      "loss": 0.9456,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.6e-05,
+      "loss": 0.8864,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8e-05,
+      "loss": 0.8756,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.7110548615455627,
+      "eval_runtime": 29.5129,
+      "eval_samples_per_second": 55.196,
+      "eval_steps_per_second": 55.196,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.4e-05,
+      "loss": 0.8825,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.822,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.8001,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.6e-05,
+      "loss": 0.8978,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001,
+      "loss": 0.8214,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.8012,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.9169,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.8436,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000116,
+      "loss": 0.738,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00012,
+      "loss": 0.8238,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000124,
+      "loss": 0.85,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.8292,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000132,
+      "loss": 0.8739,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.8456,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00014,
+      "loss": 0.7558,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000144,
+      "loss": 0.6982,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000148,
+      "loss": 0.7985,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000152,
+      "loss": 0.7995,
+      "step": 38
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5988,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00016,
+      "loss": 0.9058,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.6764179468154907,
+      "eval_runtime": 29.6679,
+      "eval_samples_per_second": 54.908,
+      "eval_steps_per_second": 54.908,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000164,
+      "loss": 0.8351,
+      "step": 41
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000168,
+      "loss": 0.8182,
+      "step": 42
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000172,
+      "loss": 0.8694,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.7743,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018,
+      "loss": 0.7448,
+      "step": 45
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.8416,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000188,
+      "loss": 0.7496,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000192,
+      "loss": 0.7353,
+      "step": 48
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000196,
+      "loss": 0.9026,
+      "step": 49
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002,
+      "loss": 0.8415,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.7606,
+      "step": 51
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.743,
+      "step": 52
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.7478,
+      "step": 53
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.6924,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.9163,
+      "step": 55
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.7332,
+      "step": 56
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.7678,
+      "step": 57
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000232,
+      "loss": 0.7561,
+      "step": 58
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000236,
+      "loss": 0.8494,
+      "step": 59
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00024,
+      "loss": 0.7526,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.6668684482574463,
+      "eval_runtime": 29.5308,
+      "eval_samples_per_second": 55.163,
+      "eval_steps_per_second": 55.163,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000244,
+      "loss": 0.7944,
+      "step": 61
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000248,
+      "loss": 0.7107,
+      "step": 62
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000252,
+      "loss": 0.7443,
+      "step": 63
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.7802,
+      "step": 64
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.6785,
+      "step": 65
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000264,
+      "loss": 0.7853,
+      "step": 66
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000268,
+      "loss": 0.8059,
+      "step": 67
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6702,
+      "step": 68
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000276,
+      "loss": 0.7784,
+      "step": 69
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00028,
+      "loss": 0.7447,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000284,
+      "loss": 0.6466,
+      "step": 71
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000288,
+      "loss": 0.6549,
+      "step": 72
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000292,
+      "loss": 0.6841,
+      "step": 73
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000296,
+      "loss": 0.6441,
+      "step": 74
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.6777,
+      "step": 75
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000304,
+      "loss": 0.7301,
+      "step": 76
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000308,
+      "loss": 0.692,
+      "step": 77
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.7697,
+      "step": 78
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6374,
+      "step": 79
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00032,
+      "loss": 0.6926,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.6363404989242554,
+      "eval_runtime": 29.5123,
+      "eval_samples_per_second": 55.197,
+      "eval_steps_per_second": 55.197,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000324,
+      "loss": 0.7258,
+      "step": 81
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000328,
+      "loss": 0.6556,
+      "step": 82
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000332,
+      "loss": 0.6122,
+      "step": 83
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000336,
+      "loss": 0.6915,
+      "step": 84
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00034,
+      "loss": 0.7711,
+      "step": 85
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000344,
+      "loss": 0.6637,
+      "step": 86
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000348,
+      "loss": 0.635,
+      "step": 87
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.648,
+      "step": 88
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6904,
+      "step": 89
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036,
+      "loss": 0.7026,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000364,
+      "loss": 0.6285,
+      "step": 91
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.6239,
+      "step": 92
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.6897,
+      "step": 93
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000376,
+      "loss": 0.6162,
+      "step": 94
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00038,
+      "loss": 0.6414,
+      "step": 95
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000384,
+      "loss": 0.637,
+      "step": 96
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000388,
+      "loss": 0.7453,
+      "step": 97
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000392,
+      "loss": 0.6462,
+      "step": 98
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.6717,
+      "step": 99
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004,
+      "loss": 0.6731,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.6186901926994324,
+      "eval_runtime": 29.5468,
+      "eval_samples_per_second": 55.133,
+      "eval_steps_per_second": 55.133,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00039999731246874025,
+      "loss": 0.6801,
+      "step": 101
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003999892499471893,
+      "loss": 0.6285,
+      "step": 102
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00039997581265202993,
+      "loss": 0.6436,
+      "step": 103
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003999570009443936,
+      "loss": 0.7124,
+      "step": 104
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039993281532985087,
+      "loss": 0.6157,
+      "step": 105
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039990325645839766,
+      "loss": 0.6532,
+      "step": 106
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003998683251244379,
+      "loss": 0.6072,
+      "step": 107
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003998280222667621,
+      "loss": 0.6871,
+      "step": 108
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039978234896852216,
+      "loss": 0.6139,
+      "step": 109
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003997313064572023,
+      "loss": 0.7056,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003996748961045859,
+      "loss": 0.5983,
+      "step": 111
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003996131194267189,
+      "loss": 0.5374,
+      "step": 112
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039954597808386874,
+      "loss": 0.6804,
+      "step": 113
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039947347388048,
+      "loss": 0.6254,
+      "step": 114
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039939560876512585,
+      "loss": 0.7221,
+      "step": 115
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003993123848304556,
+      "loss": 0.6417,
+      "step": 116
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003992238043131386,
+      "loss": 0.4836,
+      "step": 117
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003991298695938038,
+      "loss": 0.6186,
+      "step": 118
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003990305831969761,
+      "loss": 0.6362,
+      "step": 119
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039892594779100866,
+      "loss": 0.647,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.6162068843841553,
+      "eval_runtime": 29.5244,
+      "eval_samples_per_second": 55.175,
+      "eval_steps_per_second": 55.175,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003988159661880105,
+      "loss": 0.5818,
+      "step": 121
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003987006413437718,
+      "loss": 0.6267,
+      "step": 122
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039857997635768365,
+      "loss": 0.5502,
+      "step": 123
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039845397447265535,
+      "loss": 0.6438,
+      "step": 124
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039832263907502684,
+      "loss": 0.6472,
+      "step": 125
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003981859736944781,
+      "loss": 0.6834,
+      "step": 126
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039804398200393395,
+      "loss": 0.6091,
+      "step": 127
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003978966678194653,
+      "loss": 0.58,
+      "step": 128
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039774403510018714,
+      "loss": 0.5988,
+      "step": 129
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003975860879481514,
+      "loss": 0.6177,
+      "step": 130
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039742283060823706,
+      "loss": 0.5535,
+      "step": 131
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003972542674680364,
+      "loss": 0.7208,
+      "step": 132
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003970804030577363,
+      "loss": 0.626,
+      "step": 133
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003969012420499972,
+      "loss": 0.5747,
+      "step": 134
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039671678925982723,
+      "loss": 0.5567,
+      "step": 135
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039652704964445275,
+      "loss": 0.6814,
+      "step": 136
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039633202830318526,
+      "loss": 0.5917,
+      "step": 137
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003961317304772842,
+      "loss": 0.5793,
+      "step": 138
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039592616154981633,
+      "loss": 0.6533,
+      "step": 139
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039571532704551083,
+      "loss": 0.6219,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.6040534377098083,
+      "eval_runtime": 29.5629,
+      "eval_samples_per_second": 55.103,
+      "eval_steps_per_second": 55.103,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003954992326306109,
+      "loss": 0.5167,
+      "step": 141
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039527788411272143,
+      "loss": 0.6516,
+      "step": 142
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039505128744065314,
+      "loss": 0.607,
+      "step": 143
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003948194487042623,
+      "loss": 0.6482,
+      "step": 144
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003945823741342875,
+      "loss": 0.6133,
+      "step": 145
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003943400701021819,
+      "loss": 0.5582,
+      "step": 146
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039409254311994216,
+      "loss": 0.5985,
+      "step": 147
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039383979983993327,
+      "loss": 0.5648,
+      "step": 148
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935818470547098,
+      "loss": 0.5884,
+      "step": 149
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039331869169683363,
+      "loss": 0.5948,
+      "step": 150
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003930503408386871,
+      "loss": 0.5532,
+      "step": 151
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277680169228364,
+      "loss": 0.6034,
+      "step": 152
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003924980816090731,
+      "loss": 0.6522,
+      "step": 153
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003922141880797449,
+      "loss": 0.6142,
+      "step": 154
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003919251287340265,
+      "loss": 0.5816,
+      "step": 155
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000391630911340478,
+      "loss": 0.5686,
+      "step": 156
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039133154380628394,
+      "loss": 0.6053,
+      "step": 157
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003910270341770404,
+      "loss": 0.7025,
+      "step": 158
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039071739063653875,
+      "loss": 0.5625,
+      "step": 159
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039040262150654597,
+      "loss": 0.5781,
+      "step": 160
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.593679666519165,
+      "eval_runtime": 29.5229,
+      "eval_samples_per_second": 55.178,
+      "eval_steps_per_second": 55.178,
+      "step": 160
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039008273524658094,
+      "loss": 0.603,
+      "step": 161
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003897577404536867,
+      "loss": 0.5789,
+      "step": 162
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00038942764586220006,
+      "loss": 0.6881,
+      "step": 163
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00038909246034351624,
+      "loss": 0.6034,
+      "step": 164
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00038875219290585093,
+      "loss": 0.5881,
+      "step": 165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003884068526939978,
+      "loss": 0.6318,
+      "step": 166
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00038805644898908307,
+      "loss": 0.5383,
+      "step": 167
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003877009912083159,
+      "loss": 0.5284,
+      "step": 168
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038734048890473507,
+      "loss": 0.5723,
+      "step": 169
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038697495176695274,
+      "loss": 0.6311,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038660438961889387,
+      "loss": 0.6043,
+      "step": 171
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038622881241953195,
+      "loss": 0.5023,
+      "step": 172
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003858482302626216,
+      "loss": 0.566,
+      "step": 173
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003854626533764273,
+      "loss": 0.5677,
+      "step": 174
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038507209212344833,
+      "loss": 0.6342,
+      "step": 175
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038467655700014054,
+      "loss": 0.6095,
+      "step": 176
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003842760586366339,
+      "loss": 0.6715,
+      "step": 177
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038387060779644725,
+      "loss": 0.5173,
+      "step": 178
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00038346021537619866,
+      "loss": 0.6155,
+      "step": 179
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003830448924053126,
+      "loss": 0.6346,
+      "step": 180
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.6006138324737549,
+      "eval_runtime": 29.5105,
+      "eval_samples_per_second": 55.201,
+      "eval_steps_per_second": 55.201,
+      "step": 180
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00038262465004572377,
+      "loss": 0.7549,
+      "step": 181
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000382199499591577,
+      "loss": 0.5214,
+      "step": 182
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038176945246892367,
+      "loss": 0.5625,
+      "step": 183
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003813345202354145,
+      "loss": 0.5267,
+      "step": 184
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003808947145799894,
+      "loss": 0.6413,
+      "step": 185
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003804500473225627,
+      "loss": 0.4987,
+      "step": 186
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038000053041370603,
+      "loss": 0.6235,
+      "step": 187
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003795461759343268,
+      "loss": 0.5331,
+      "step": 188
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003790869960953437,
+      "loss": 0.6096,
+      "step": 189
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003786230032373583,
+      "loss": 0.5872,
+      "step": 190
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00037815420983032397,
+      "loss": 0.6665,
+      "step": 191
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003776806284732098,
+      "loss": 0.7373,
+      "step": 192
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037720227189366295,
+      "loss": 0.5193,
+      "step": 193
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037671915294766606,
+      "loss": 0.5335,
+      "step": 194
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037623128461919175,
+      "loss": 0.5148,
+      "step": 195
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037573868001985377,
+      "loss": 0.5961,
+      "step": 196
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003752413523885549,
+      "loss": 0.5421,
+      "step": 197
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00037473931509113056,
+      "loss": 0.6177,
+      "step": 198
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003742325816199901,
+      "loss": 0.6656,
+      "step": 199
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037372116559375397,
+      "loss": 0.7663,
+      "step": 200
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.5926464200019836,
+      "eval_runtime": 29.5066,
+      "eval_samples_per_second": 55.208,
+      "eval_steps_per_second": 55.208,
+      "step": 200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037320508075688776,
+      "loss": 0.6667,
+      "step": 201
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037268434097933274,
+      "loss": 0.587,
+      "step": 202
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003721589602561332,
+      "loss": 0.5747,
+      "step": 203
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003716289527070604,
+      "loss": 0.557,
+      "step": 204
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003710943325762328,
+      "loss": 0.5724,
+      "step": 205
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00037055511423173356,
+      "loss": 0.6036,
+      "step": 206
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003700113121652243,
+      "loss": 0.6007,
+      "step": 207
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003694629409915555,
+      "loss": 0.6895,
+      "step": 208
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00036891001544837393,
+      "loss": 0.6642,
+      "step": 209
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003683525503957263,
+      "loss": 0.7124,
+      "step": 210
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00036779056081566024,
+      "loss": 0.52,
+      "step": 211
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00036722406181182143,
+      "loss": 0.6133,
+      "step": 212
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003666530686090475,
+      "loss": 0.5487,
+      "step": 213
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003660775965529595,
+      "loss": 0.5686,
+      "step": 214
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003654976611095487,
+      "loss": 0.4951,
+      "step": 215
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003649132778647615,
+      "loss": 0.5794,
+      "step": 216
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00036432446252408014,
+      "loss": 0.4965,
+      "step": 217
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003637312309121011,
+      "loss": 0.6146,
+      "step": 218
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00036313359897210935,
+      "loss": 0.5697,
+      "step": 219
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00036253158276565006,
+      "loss": 0.5864,
+      "step": 220
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.5865967273712158,
+      "eval_runtime": 29.5042,
+      "eval_samples_per_second": 55.212,
+      "eval_steps_per_second": 55.212,
+      "step": 220
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000361925198472097,
+      "loss": 0.4863,
+      "step": 221
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00036131446238821767,
+      "loss": 0.5185,
+      "step": 222
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00036069939092773514,
+      "loss": 0.5846,
+      "step": 223
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003600800006208872,
+      "loss": 0.5416,
+      "step": 224
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00035945630811398205,
+      "loss": 0.5783,
+      "step": 225
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003588283301689507,
+      "loss": 0.7388,
+      "step": 226
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003581960836628968,
+      "loss": 0.7164,
+      "step": 227
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003575595855876427,
+      "loss": 0.5729,
+      "step": 228
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003569188530492732,
+      "loss": 0.5475,
+      "step": 229
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003562739032676756,
+      "loss": 0.6107,
+      "step": 230
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00035562475357607694,
+      "loss": 0.5441,
+      "step": 231
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000354971421420578,
+      "loss": 0.6148,
+      "step": 232
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003543139243596847,
+      "loss": 0.5864,
+      "step": 233
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00035365228006383614,
+      "loss": 0.5044,
+      "step": 234
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00035298650631492956,
+      "loss": 0.4947,
+      "step": 235
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003523166210058426,
+      "loss": 0.5524,
+      "step": 236
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003516426421399523,
+      "loss": 0.5434,
+      "step": 237
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00035096458783065145,
+      "loss": 0.6695,
+      "step": 238
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003502824763008615,
+      "loss": 0.6813,
+      "step": 239
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00034959632588254304,
+      "loss": 0.5943,
+      "step": 240
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.5755711793899536,
+      "eval_runtime": 29.5,
+      "eval_samples_per_second": 55.22,
+      "eval_steps_per_second": 55.22,
+      "step": 240
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000348906155016203,
+      "loss": 0.5239,
+      "step": 241
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003482119822503994,
+      "loss": 0.5347,
+      "step": 242
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000347513826241242,
+      "loss": 0.5513,
+      "step": 243
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003468117057518921,
+      "loss": 0.6988,
+      "step": 244
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000346105639652057,
+      "loss": 0.5591,
+      "step": 245
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00034539564691748407,
+      "loss": 0.5305,
+      "step": 246
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00034468174662944995,
+      "loss": 0.5492,
+      "step": 247
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003439639579742481,
+      "loss": 0.5907,
+      "step": 248
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034324230024267285,
+      "loss": 0.5596,
+      "step": 249
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034251679282950144,
+      "loss": 0.6163,
+      "step": 250
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034178745523297233,
+      "loss": 0.7016,
+      "step": 251
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003410543070542615,
+      "loss": 0.734,
+      "step": 252
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00034031736799695537,
+      "loss": 0.6601,
+      "step": 253
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003395766578665215,
+      "loss": 0.5738,
+      "step": 254
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00033883219656977615,
+      "loss": 0.5691,
+      "step": 255
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003380840041143494,
+      "loss": 0.4958,
+      "step": 256
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003373321006081474,
+      "loss": 0.4613,
+      "step": 257
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00033657650625881183,
+      "loss": 0.5939,
+      "step": 258
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003358172413731772,
+      "loss": 0.6093,
+      "step": 259
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033505432635672457,
+      "loss": 0.5029,
+      "step": 260
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.5733422040939331,
+      "eval_runtime": 29.5698,
+      "eval_samples_per_second": 55.09,
+      "eval_steps_per_second": 55.09,
+      "step": 260
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003342877817130334,
+      "loss": 0.6983,
+      "step": 261
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033351762804323073,
+      "loss": 0.5567,
+      "step": 262
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003327438860454372,
+      "loss": 0.5081,
+      "step": 263
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00033196657651421066,
+      "loss": 0.5475,
+      "step": 264
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000331185720339988,
+      "loss": 0.5527,
+      "step": 265
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003304013385085229,
+      "loss": 0.5244,
+      "step": 266
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003296134521003222,
+      "loss": 0.6156,
+      "step": 267
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003288220822900796,
+      "loss": 0.5203,
+      "step": 268
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00032802725034610593,
+      "loss": 0.5844,
+      "step": 269
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003272289776297583,
+      "loss": 0.6262,
+      "step": 270
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003264272855948653,
+      "loss": 0.552,
+      "step": 271
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003256221957871512,
+      "loss": 0.5817,
+      "step": 272
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003248137298436561,
+      "loss": 0.4906,
+      "step": 273
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00032400190949215507,
+      "loss": 0.4638,
+      "step": 274
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003231867565505737,
+      "loss": 0.532,
+      "step": 275
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003223682929264022,
+      "loss": 0.572,
+      "step": 276
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003215465406161064,
+      "loss": 0.6238,
+      "step": 277
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003207215217045363,
+      "loss": 0.5751,
+      "step": 278
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003198932583643332,
+      "loss": 0.5688,
+      "step": 279
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003190617728553332,
+      "loss": 0.5482,
+      "step": 280
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.5711647272109985,
+      "eval_runtime": 29.618,
+      "eval_samples_per_second": 55.0,
+      "eval_steps_per_second": 55.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003182270875239694,
+      "loss": 0.6118,
+      "step": 281
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003173892248026708,
+      "loss": 0.5704,
+      "step": 282
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003165482072092602,
+      "loss": 0.6117,
+      "step": 283
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00031570405734634814,
+      "loss": 0.5798,
+      "step": 284
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003148567979007261,
+      "loss": 0.5585,
+      "step": 285
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00031400645164275653,
+      "loss": 0.6552,
+      "step": 286
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000313153041425761,
+      "loss": 0.5421,
+      "step": 287
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003122965901854058,
+      "loss": 0.497,
+      "step": 288
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003114371209390857,
+      "loss": 0.5207,
+      "step": 289
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00031057465678530543,
+      "loss": 0.5028,
+      "step": 290
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003097092209030588,
+      "loss": 0.4905,
+      "step": 291
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003088408365512055,
+      "loss": 0.6156,
+      "step": 292
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00030796952706784646,
+      "loss": 0.5414,
+      "step": 293
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003070953158696967,
+      "loss": 0.4219,
+      "step": 294
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00030621822645145506,
+      "loss": 0.6778,
+      "step": 295
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000305338282385174,
+      "loss": 0.5173,
+      "step": 296
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00030445550731962546,
+      "loss": 0.5959,
+      "step": 297
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003035699249796651,
+      "loss": 0.6535,
+      "step": 298
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003026815591655953,
+      "loss": 0.6306,
+      "step": 299
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00030179043375252486,
+      "loss": 0.5413,
+      "step": 300
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.5820406675338745,
+      "eval_runtime": 29.5338,
+      "eval_samples_per_second": 55.157,
+      "eval_steps_per_second": 55.157,
+      "step": 300
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.000300896572689728,
+      "loss": 0.5046,
+      "step": 301
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.6131,
+      "step": 302
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029910073977901236,
+      "loss": 0.4598,
+      "step": 303
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029819881619466443,
+      "loss": 0.5017,
+      "step": 304
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029729425348643467,
+      "loss": 0.6571,
+      "step": 305
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029638707596472855,
+      "loss": 0.577,
+      "step": 306
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029547730801022544,
+      "loss": 0.5014,
+      "step": 307
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029456497407322365,
+      "loss": 0.4571,
+      "step": 308
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002936500986729829,
+      "loss": 0.5818,
+      "step": 309
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002927327063970655,
+      "loss": 0.5138,
+      "step": 310
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00029181282190067574,
+      "loss": 0.5927,
+      "step": 311
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00029089046990599685,
+      "loss": 0.5297,
+      "step": 312
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002899656752015272,
+      "loss": 0.5693,
+      "step": 313
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002890384626414134,
+      "loss": 0.5579,
+      "step": 314
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.000288108857144783,
+      "loss": 0.6165,
+      "step": 315
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00028717688369507425,
+      "loss": 0.4311,
+      "step": 316
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00028624256733936486,
+      "loss": 0.5919,
+      "step": 317
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002853059331876991,
+      "loss": 0.6499,
+      "step": 318
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002843670064124125,
+      "loss": 0.5486,
+      "step": 319
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002834258122474556,
+      "loss": 0.657,
+      "step": 320
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 0.5696084499359131,
+      "eval_runtime": 29.5183,
+      "eval_samples_per_second": 55.186,
+      "eval_steps_per_second": 55.186,
+      "step": 320
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002824823759877159,
+      "loss": 0.6218,
+      "step": 321
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00028153672298833775,
+      "loss": 0.4651,
+      "step": 322
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002805888786640412,
+      "loss": 0.5388,
+      "step": 323
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027963886848843863,
+      "loss": 0.4579,
+      "step": 324
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027868671799335053,
+      "loss": 0.6092,
+      "step": 325
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027773245276811905,
+      "loss": 0.711,
+      "step": 326
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027677609845892055,
+      "loss": 0.6601,
+      "step": 327
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002758176807680759,
+      "loss": 0.4271,
+      "step": 328
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027485722545336023,
+      "loss": 0.5561,
+      "step": 329
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027389475832731035,
+      "loss": 0.4772,
+      "step": 330
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00027293030525653105,
+      "loss": 0.56,
+      "step": 331
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002719638921610002,
+      "loss": 0.5905,
+      "step": 332
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002709955450133718,
+      "loss": 0.4981,
+      "step": 333
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002700252898382781,
+      "loss": 0.5701,
+      "step": 334
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002690531527116304,
+      "loss": 0.4725,
+      "step": 335
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00026807915975991765,
+      "loss": 0.5022,
+      "step": 336
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.000267103337159505,
+      "loss": 0.4953,
+      "step": 337
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002661257111359299,
+      "loss": 0.5762,
+      "step": 338
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002651463079631973,
+      "loss": 0.6713,
+      "step": 339
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00026416515396307353,
+      "loss": 0.506,
+      "step": 340
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5838707685470581,
+      "eval_runtime": 29.495,
+      "eval_samples_per_second": 55.23,
+      "eval_steps_per_second": 55.23,
+      "step": 340
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002631822755043793,
+      "loss": 0.5368,
+      "step": 341
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00026219769900228014,
+      "loss": 0.5509,
+      "step": 342
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002612114509175775,
+      "loss": 0.5365,
+      "step": 343
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002602235577559969,
+      "loss": 0.6527,
+      "step": 344
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002592340460674759,
+      "loss": 0.4975,
+      "step": 345
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00025824294244545045,
+      "loss": 0.6552,
+      "step": 346
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00025725027352614015,
+      "loss": 0.5523,
+      "step": 347
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00025625606598783256,
+      "loss": 0.6078,
+      "step": 348
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002552603465501661,
+      "loss": 0.4592,
+      "step": 349
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002542631419734118,
+      "loss": 0.587,
+      "step": 350
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00025326447905775446,
+      "loss": 0.5689,
+      "step": 351
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025226438464257217,
+      "loss": 0.4961,
+      "step": 352
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025126288560571483,
+      "loss": 0.4735,
+      "step": 353
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 706,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 9.231730747386102e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-353/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc29491a898700f15de2024fec703fbc3c0e47ff2a1808b6210d1914f87ee43
+size 4475

checkpoint-706/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-706/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-706/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c54b4128d3990ad30d82d6e66838a8bd6bc36e4432c3f624f2c7aa1421f118
+size 160069389

checkpoint-706/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8908522491fda83ea1584925a4b68602dde08aa0654af93dca92100e8add7e2e
+size 320084485

checkpoint-706/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39a6df6dbabc0651eb45454d0c57729e47a211c8689d8ae2ee43a00d90bf501
+size 14575

checkpoint-706/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6c545a34f8af97ab455a0b9974ed9cbf507668d9682a06a4e369c63d136974
+size 627

checkpoint-706/trainer_state.json

@@ -0,0 +1,4535 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9989382410192886,
+  "eval_steps": 20,
+  "global_step": 706,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.9795,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.2944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 4.0746,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 4.1905,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 4.4667,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.4e-05,
+      "loss": 4.8488,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 4.1473,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.7834,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.6e-05,
+      "loss": 3.2778,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 3.1975,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.7504,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8e-05,
+      "loss": 2.5047,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 2.3366,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 2.1348,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6e-05,
+      "loss": 1.6171,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.2901,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.1358,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.2e-05,
+      "loss": 0.9456,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.6e-05,
+      "loss": 0.8864,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8e-05,
+      "loss": 0.8756,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.7110548615455627,
+      "eval_runtime": 29.5129,
+      "eval_samples_per_second": 55.196,
+      "eval_steps_per_second": 55.196,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.4e-05,
+      "loss": 0.8825,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.822,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.8001,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.6e-05,
+      "loss": 0.8978,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001,
+      "loss": 0.8214,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.8012,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.9169,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.8436,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000116,
+      "loss": 0.738,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00012,
+      "loss": 0.8238,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000124,
+      "loss": 0.85,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.8292,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000132,
+      "loss": 0.8739,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.8456,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00014,
+      "loss": 0.7558,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000144,
+      "loss": 0.6982,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000148,
+      "loss": 0.7985,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000152,
+      "loss": 0.7995,
+      "step": 38
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5988,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00016,
+      "loss": 0.9058,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.6764179468154907,
+      "eval_runtime": 29.6679,
+      "eval_samples_per_second": 54.908,
+      "eval_steps_per_second": 54.908,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000164,
+      "loss": 0.8351,
+      "step": 41
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000168,
+      "loss": 0.8182,
+      "step": 42
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000172,
+      "loss": 0.8694,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.7743,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018,
+      "loss": 0.7448,
+      "step": 45
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.8416,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000188,
+      "loss": 0.7496,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000192,
+      "loss": 0.7353,
+      "step": 48
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000196,
+      "loss": 0.9026,
+      "step": 49
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002,
+      "loss": 0.8415,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.7606,
+      "step": 51
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.743,
+      "step": 52
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.7478,
+      "step": 53
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.6924,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.9163,
+      "step": 55
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.7332,
+      "step": 56
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.7678,
+      "step": 57
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000232,
+      "loss": 0.7561,
+      "step": 58
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000236,
+      "loss": 0.8494,
+      "step": 59
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00024,
+      "loss": 0.7526,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.6668684482574463,
+      "eval_runtime": 29.5308,
+      "eval_samples_per_second": 55.163,
+      "eval_steps_per_second": 55.163,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000244,
+      "loss": 0.7944,
+      "step": 61
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000248,
+      "loss": 0.7107,
+      "step": 62
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000252,
+      "loss": 0.7443,
+      "step": 63
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.7802,
+      "step": 64
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.6785,
+      "step": 65
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000264,
+      "loss": 0.7853,
+      "step": 66
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000268,
+      "loss": 0.8059,
+      "step": 67
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.6702,
+      "step": 68
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000276,
+      "loss": 0.7784,
+      "step": 69
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00028,
+      "loss": 0.7447,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000284,
+      "loss": 0.6466,
+      "step": 71
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000288,
+      "loss": 0.6549,
+      "step": 72
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000292,
+      "loss": 0.6841,
+      "step": 73
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000296,
+      "loss": 0.6441,
+      "step": 74
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.6777,
+      "step": 75
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000304,
+      "loss": 0.7301,
+      "step": 76
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000308,
+      "loss": 0.692,
+      "step": 77
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.7697,
+      "step": 78
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.6374,
+      "step": 79
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00032,
+      "loss": 0.6926,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.6363404989242554,
+      "eval_runtime": 29.5123,
+      "eval_samples_per_second": 55.197,
+      "eval_steps_per_second": 55.197,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000324,
+      "loss": 0.7258,
+      "step": 81
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000328,
+      "loss": 0.6556,
+      "step": 82
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000332,
+      "loss": 0.6122,
+      "step": 83
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000336,
+      "loss": 0.6915,
+      "step": 84
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00034,
+      "loss": 0.7711,
+      "step": 85
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000344,
+      "loss": 0.6637,
+      "step": 86
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000348,
+      "loss": 0.635,
+      "step": 87
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.648,
+      "step": 88
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6904,
+      "step": 89
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036,
+      "loss": 0.7026,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000364,
+      "loss": 0.6285,
+      "step": 91
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.6239,
+      "step": 92
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.6897,
+      "step": 93
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000376,
+      "loss": 0.6162,
+      "step": 94
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00038,
+      "loss": 0.6414,
+      "step": 95
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000384,
+      "loss": 0.637,
+      "step": 96
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000388,
+      "loss": 0.7453,
+      "step": 97
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000392,
+      "loss": 0.6462,
+      "step": 98
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.6717,
+      "step": 99
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004,
+      "loss": 0.6731,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.6186901926994324,
+      "eval_runtime": 29.5468,
+      "eval_samples_per_second": 55.133,
+      "eval_steps_per_second": 55.133,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00039999731246874025,
+      "loss": 0.6801,
+      "step": 101
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003999892499471893,
+      "loss": 0.6285,
+      "step": 102
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00039997581265202993,
+      "loss": 0.6436,
+      "step": 103
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003999570009443936,
+      "loss": 0.7124,
+      "step": 104
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039993281532985087,
+      "loss": 0.6157,
+      "step": 105
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00039990325645839766,
+      "loss": 0.6532,
+      "step": 106
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003998683251244379,
+      "loss": 0.6072,
+      "step": 107
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003998280222667621,
+      "loss": 0.6871,
+      "step": 108
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00039978234896852216,
+      "loss": 0.6139,
+      "step": 109
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003997313064572023,
+      "loss": 0.7056,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003996748961045859,
+      "loss": 0.5983,
+      "step": 111
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003996131194267189,
+      "loss": 0.5374,
+      "step": 112
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039954597808386874,
+      "loss": 0.6804,
+      "step": 113
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00039947347388048,
+      "loss": 0.6254,
+      "step": 114
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00039939560876512585,
+      "loss": 0.7221,
+      "step": 115
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003993123848304556,
+      "loss": 0.6417,
+      "step": 116
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003992238043131386,
+      "loss": 0.4836,
+      "step": 117
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003991298695938038,
+      "loss": 0.6186,
+      "step": 118
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003990305831969761,
+      "loss": 0.6362,
+      "step": 119
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00039892594779100866,
+      "loss": 0.647,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.6162068843841553,
+      "eval_runtime": 29.5244,
+      "eval_samples_per_second": 55.175,
+      "eval_steps_per_second": 55.175,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003988159661880105,
+      "loss": 0.5818,
+      "step": 121
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003987006413437718,
+      "loss": 0.6267,
+      "step": 122
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039857997635768365,
+      "loss": 0.5502,
+      "step": 123
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039845397447265535,
+      "loss": 0.6438,
+      "step": 124
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00039832263907502684,
+      "loss": 0.6472,
+      "step": 125
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003981859736944781,
+      "loss": 0.6834,
+      "step": 126
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00039804398200393395,
+      "loss": 0.6091,
+      "step": 127
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003978966678194653,
+      "loss": 0.58,
+      "step": 128
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039774403510018714,
+      "loss": 0.5988,
+      "step": 129
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003975860879481514,
+      "loss": 0.6177,
+      "step": 130
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00039742283060823706,
+      "loss": 0.5535,
+      "step": 131
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003972542674680364,
+      "loss": 0.7208,
+      "step": 132
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003970804030577363,
+      "loss": 0.626,
+      "step": 133
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003969012420499972,
+      "loss": 0.5747,
+      "step": 134
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00039671678925982723,
+      "loss": 0.5567,
+      "step": 135
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039652704964445275,
+      "loss": 0.6814,
+      "step": 136
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039633202830318526,
+      "loss": 0.5917,
+      "step": 137
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003961317304772842,
+      "loss": 0.5793,
+      "step": 138
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00039592616154981633,
+      "loss": 0.6533,
+      "step": 139
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039571532704551083,
+      "loss": 0.6219,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.6040534377098083,
+      "eval_runtime": 29.5629,
+      "eval_samples_per_second": 55.103,
+      "eval_steps_per_second": 55.103,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003954992326306109,
+      "loss": 0.5167,
+      "step": 141
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039527788411272143,
+      "loss": 0.6516,
+      "step": 142
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00039505128744065314,
+      "loss": 0.607,
+      "step": 143
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003948194487042623,
+      "loss": 0.6482,
+      "step": 144
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003945823741342875,
+      "loss": 0.6133,
+      "step": 145
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003943400701021819,
+      "loss": 0.5582,
+      "step": 146
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039409254311994216,
+      "loss": 0.5985,
+      "step": 147
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039383979983993327,
+      "loss": 0.5648,
+      "step": 148
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003935818470547098,
+      "loss": 0.5884,
+      "step": 149
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00039331869169683363,
+      "loss": 0.5948,
+      "step": 150
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003930503408386871,
+      "loss": 0.5532,
+      "step": 151
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00039277680169228364,
+      "loss": 0.6034,
+      "step": 152
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003924980816090731,
+      "loss": 0.6522,
+      "step": 153
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003922141880797449,
+      "loss": 0.6142,
+      "step": 154
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003919251287340265,
+      "loss": 0.5816,
+      "step": 155
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000391630911340478,
+      "loss": 0.5686,
+      "step": 156
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00039133154380628394,
+      "loss": 0.6053,
+      "step": 157
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003910270341770404,
+      "loss": 0.7025,
+      "step": 158
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039071739063653875,
+      "loss": 0.5625,
+      "step": 159
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00039040262150654597,
+      "loss": 0.5781,
+      "step": 160
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.593679666519165,
+      "eval_runtime": 29.5229,
+      "eval_samples_per_second": 55.178,
+      "eval_steps_per_second": 55.178,
+      "step": 160
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00039008273524658094,
+      "loss": 0.603,
+      "step": 161
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003897577404536867,
+      "loss": 0.5789,
+      "step": 162
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00038942764586220006,
+      "loss": 0.6881,
+      "step": 163
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00038909246034351624,
+      "loss": 0.6034,
+      "step": 164
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00038875219290585093,
+      "loss": 0.5881,
+      "step": 165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003884068526939978,
+      "loss": 0.6318,
+      "step": 166
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00038805644898908307,
+      "loss": 0.5383,
+      "step": 167
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003877009912083159,
+      "loss": 0.5284,
+      "step": 168
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038734048890473507,
+      "loss": 0.5723,
+      "step": 169
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038697495176695274,
+      "loss": 0.6311,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00038660438961889387,
+      "loss": 0.6043,
+      "step": 171
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00038622881241953195,
+      "loss": 0.5023,
+      "step": 172
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003858482302626216,
+      "loss": 0.566,
+      "step": 173
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003854626533764273,
+      "loss": 0.5677,
+      "step": 174
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038507209212344833,
+      "loss": 0.6342,
+      "step": 175
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038467655700014054,
+      "loss": 0.6095,
+      "step": 176
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003842760586366339,
+      "loss": 0.6715,
+      "step": 177
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00038387060779644725,
+      "loss": 0.5173,
+      "step": 178
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00038346021537619866,
+      "loss": 0.6155,
+      "step": 179
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003830448924053126,
+      "loss": 0.6346,
+      "step": 180
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.6006138324737549,
+      "eval_runtime": 29.5105,
+      "eval_samples_per_second": 55.201,
+      "eval_steps_per_second": 55.201,
+      "step": 180
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00038262465004572377,
+      "loss": 0.7549,
+      "step": 181
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000382199499591577,
+      "loss": 0.5214,
+      "step": 182
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00038176945246892367,
+      "loss": 0.5625,
+      "step": 183
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003813345202354145,
+      "loss": 0.5267,
+      "step": 184
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003808947145799894,
+      "loss": 0.6413,
+      "step": 185
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003804500473225627,
+      "loss": 0.4987,
+      "step": 186
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00038000053041370603,
+      "loss": 0.6235,
+      "step": 187
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003795461759343268,
+      "loss": 0.5331,
+      "step": 188
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003790869960953437,
+      "loss": 0.6096,
+      "step": 189
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003786230032373583,
+      "loss": 0.5872,
+      "step": 190
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00037815420983032397,
+      "loss": 0.6665,
+      "step": 191
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003776806284732098,
+      "loss": 0.7373,
+      "step": 192
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037720227189366295,
+      "loss": 0.5193,
+      "step": 193
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037671915294766606,
+      "loss": 0.5335,
+      "step": 194
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037623128461919175,
+      "loss": 0.5148,
+      "step": 195
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00037573868001985377,
+      "loss": 0.5961,
+      "step": 196
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003752413523885549,
+      "loss": 0.5421,
+      "step": 197
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00037473931509113056,
+      "loss": 0.6177,
+      "step": 198
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003742325816199901,
+      "loss": 0.6656,
+      "step": 199
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037372116559375397,
+      "loss": 0.7663,
+      "step": 200
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.5926464200019836,
+      "eval_runtime": 29.5066,
+      "eval_samples_per_second": 55.208,
+      "eval_steps_per_second": 55.208,
+      "step": 200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037320508075688776,
+      "loss": 0.6667,
+      "step": 201
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00037268434097933274,
+      "loss": 0.587,
+      "step": 202
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003721589602561332,
+      "loss": 0.5747,
+      "step": 203
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003716289527070604,
+      "loss": 0.557,
+      "step": 204
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003710943325762328,
+      "loss": 0.5724,
+      "step": 205
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00037055511423173356,
+      "loss": 0.6036,
+      "step": 206
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003700113121652243,
+      "loss": 0.6007,
+      "step": 207
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003694629409915555,
+      "loss": 0.6895,
+      "step": 208
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00036891001544837393,
+      "loss": 0.6642,
+      "step": 209
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003683525503957263,
+      "loss": 0.7124,
+      "step": 210
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00036779056081566024,
+      "loss": 0.52,
+      "step": 211
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00036722406181182143,
+      "loss": 0.6133,
+      "step": 212
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003666530686090475,
+      "loss": 0.5487,
+      "step": 213
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003660775965529595,
+      "loss": 0.5686,
+      "step": 214
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003654976611095487,
+      "loss": 0.4951,
+      "step": 215
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003649132778647615,
+      "loss": 0.5794,
+      "step": 216
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00036432446252408014,
+      "loss": 0.4965,
+      "step": 217
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003637312309121011,
+      "loss": 0.6146,
+      "step": 218
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00036313359897210935,
+      "loss": 0.5697,
+      "step": 219
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00036253158276565006,
+      "loss": 0.5864,
+      "step": 220
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.5865967273712158,
+      "eval_runtime": 29.5042,
+      "eval_samples_per_second": 55.212,
+      "eval_steps_per_second": 55.212,
+      "step": 220
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000361925198472097,
+      "loss": 0.4863,
+      "step": 221
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00036131446238821767,
+      "loss": 0.5185,
+      "step": 222
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00036069939092773514,
+      "loss": 0.5846,
+      "step": 223
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003600800006208872,
+      "loss": 0.5416,
+      "step": 224
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00035945630811398205,
+      "loss": 0.5783,
+      "step": 225
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003588283301689507,
+      "loss": 0.7388,
+      "step": 226
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003581960836628968,
+      "loss": 0.7164,
+      "step": 227
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003575595855876427,
+      "loss": 0.5729,
+      "step": 228
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003569188530492732,
+      "loss": 0.5475,
+      "step": 229
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003562739032676756,
+      "loss": 0.6107,
+      "step": 230
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00035562475357607694,
+      "loss": 0.5441,
+      "step": 231
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000354971421420578,
+      "loss": 0.6148,
+      "step": 232
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003543139243596847,
+      "loss": 0.5864,
+      "step": 233
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00035365228006383614,
+      "loss": 0.5044,
+      "step": 234
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00035298650631492956,
+      "loss": 0.4947,
+      "step": 235
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003523166210058426,
+      "loss": 0.5524,
+      "step": 236
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003516426421399523,
+      "loss": 0.5434,
+      "step": 237
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00035096458783065145,
+      "loss": 0.6695,
+      "step": 238
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003502824763008615,
+      "loss": 0.6813,
+      "step": 239
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00034959632588254304,
+      "loss": 0.5943,
+      "step": 240
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.5755711793899536,
+      "eval_runtime": 29.5,
+      "eval_samples_per_second": 55.22,
+      "eval_steps_per_second": 55.22,
+      "step": 240
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000348906155016203,
+      "loss": 0.5239,
+      "step": 241
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003482119822503994,
+      "loss": 0.5347,
+      "step": 242
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000347513826241242,
+      "loss": 0.5513,
+      "step": 243
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003468117057518921,
+      "loss": 0.6988,
+      "step": 244
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000346105639652057,
+      "loss": 0.5591,
+      "step": 245
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00034539564691748407,
+      "loss": 0.5305,
+      "step": 246
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00034468174662944995,
+      "loss": 0.5492,
+      "step": 247
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003439639579742481,
+      "loss": 0.5907,
+      "step": 248
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034324230024267285,
+      "loss": 0.5596,
+      "step": 249
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034251679282950144,
+      "loss": 0.6163,
+      "step": 250
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00034178745523297233,
+      "loss": 0.7016,
+      "step": 251
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003410543070542615,
+      "loss": 0.734,
+      "step": 252
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00034031736799695537,
+      "loss": 0.6601,
+      "step": 253
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003395766578665215,
+      "loss": 0.5738,
+      "step": 254
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00033883219656977615,
+      "loss": 0.5691,
+      "step": 255
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003380840041143494,
+      "loss": 0.4958,
+      "step": 256
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003373321006081474,
+      "loss": 0.4613,
+      "step": 257
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00033657650625881183,
+      "loss": 0.5939,
+      "step": 258
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003358172413731772,
+      "loss": 0.6093,
+      "step": 259
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033505432635672457,
+      "loss": 0.5029,
+      "step": 260
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.5733422040939331,
+      "eval_runtime": 29.5698,
+      "eval_samples_per_second": 55.09,
+      "eval_steps_per_second": 55.09,
+      "step": 260
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003342877817130334,
+      "loss": 0.6983,
+      "step": 261
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033351762804323073,
+      "loss": 0.5567,
+      "step": 262
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003327438860454372,
+      "loss": 0.5081,
+      "step": 263
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00033196657651421066,
+      "loss": 0.5475,
+      "step": 264
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000331185720339988,
+      "loss": 0.5527,
+      "step": 265
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003304013385085229,
+      "loss": 0.5244,
+      "step": 266
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003296134521003222,
+      "loss": 0.6156,
+      "step": 267
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003288220822900796,
+      "loss": 0.5203,
+      "step": 268
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00032802725034610593,
+      "loss": 0.5844,
+      "step": 269
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003272289776297583,
+      "loss": 0.6262,
+      "step": 270
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003264272855948653,
+      "loss": 0.552,
+      "step": 271
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003256221957871512,
+      "loss": 0.5817,
+      "step": 272
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003248137298436561,
+      "loss": 0.4906,
+      "step": 273
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00032400190949215507,
+      "loss": 0.4638,
+      "step": 274
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003231867565505737,
+      "loss": 0.532,
+      "step": 275
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003223682929264022,
+      "loss": 0.572,
+      "step": 276
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003215465406161064,
+      "loss": 0.6238,
+      "step": 277
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003207215217045363,
+      "loss": 0.5751,
+      "step": 278
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003198932583643332,
+      "loss": 0.5688,
+      "step": 279
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003190617728553332,
+      "loss": 0.5482,
+      "step": 280
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.5711647272109985,
+      "eval_runtime": 29.618,
+      "eval_samples_per_second": 55.0,
+      "eval_steps_per_second": 55.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003182270875239694,
+      "loss": 0.6118,
+      "step": 281
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003173892248026708,
+      "loss": 0.5704,
+      "step": 282
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003165482072092602,
+      "loss": 0.6117,
+      "step": 283
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00031570405734634814,
+      "loss": 0.5798,
+      "step": 284
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003148567979007261,
+      "loss": 0.5585,
+      "step": 285
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00031400645164275653,
+      "loss": 0.6552,
+      "step": 286
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000313153041425761,
+      "loss": 0.5421,
+      "step": 287
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003122965901854058,
+      "loss": 0.497,
+      "step": 288
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003114371209390857,
+      "loss": 0.5207,
+      "step": 289
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00031057465678530543,
+      "loss": 0.5028,
+      "step": 290
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003097092209030588,
+      "loss": 0.4905,
+      "step": 291
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003088408365512055,
+      "loss": 0.6156,
+      "step": 292
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00030796952706784646,
+      "loss": 0.5414,
+      "step": 293
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003070953158696967,
+      "loss": 0.4219,
+      "step": 294
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00030621822645145506,
+      "loss": 0.6778,
+      "step": 295
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000305338282385174,
+      "loss": 0.5173,
+      "step": 296
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00030445550731962546,
+      "loss": 0.5959,
+      "step": 297
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003035699249796651,
+      "loss": 0.6535,
+      "step": 298
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003026815591655953,
+      "loss": 0.6306,
+      "step": 299
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00030179043375252486,
+      "loss": 0.5413,
+      "step": 300
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.5820406675338745,
+      "eval_runtime": 29.5338,
+      "eval_samples_per_second": 55.157,
+      "eval_steps_per_second": 55.157,
+      "step": 300
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.000300896572689728,
+      "loss": 0.5046,
+      "step": 301
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.6131,
+      "step": 302
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029910073977901236,
+      "loss": 0.4598,
+      "step": 303
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029819881619466443,
+      "loss": 0.5017,
+      "step": 304
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029729425348643467,
+      "loss": 0.6571,
+      "step": 305
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029638707596472855,
+      "loss": 0.577,
+      "step": 306
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029547730801022544,
+      "loss": 0.5014,
+      "step": 307
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029456497407322365,
+      "loss": 0.4571,
+      "step": 308
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002936500986729829,
+      "loss": 0.5818,
+      "step": 309
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002927327063970655,
+      "loss": 0.5138,
+      "step": 310
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00029181282190067574,
+      "loss": 0.5927,
+      "step": 311
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00029089046990599685,
+      "loss": 0.5297,
+      "step": 312
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002899656752015272,
+      "loss": 0.5693,
+      "step": 313
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002890384626414134,
+      "loss": 0.5579,
+      "step": 314
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.000288108857144783,
+      "loss": 0.6165,
+      "step": 315
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00028717688369507425,
+      "loss": 0.4311,
+      "step": 316
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00028624256733936486,
+      "loss": 0.5919,
+      "step": 317
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002853059331876991,
+      "loss": 0.6499,
+      "step": 318
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002843670064124125,
+      "loss": 0.5486,
+      "step": 319
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002834258122474556,
+      "loss": 0.657,
+      "step": 320
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 0.5696084499359131,
+      "eval_runtime": 29.5183,
+      "eval_samples_per_second": 55.186,
+      "eval_steps_per_second": 55.186,
+      "step": 320
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002824823759877159,
+      "loss": 0.6218,
+      "step": 321
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00028153672298833775,
+      "loss": 0.4651,
+      "step": 322
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002805888786640412,
+      "loss": 0.5388,
+      "step": 323
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027963886848843863,
+      "loss": 0.4579,
+      "step": 324
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027868671799335053,
+      "loss": 0.6092,
+      "step": 325
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00027773245276811905,
+      "loss": 0.711,
+      "step": 326
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027677609845892055,
+      "loss": 0.6601,
+      "step": 327
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002758176807680759,
+      "loss": 0.4271,
+      "step": 328
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027485722545336023,
+      "loss": 0.5561,
+      "step": 329
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00027389475832731035,
+      "loss": 0.4772,
+      "step": 330
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00027293030525653105,
+      "loss": 0.56,
+      "step": 331
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002719638921610002,
+      "loss": 0.5905,
+      "step": 332
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002709955450133718,
+      "loss": 0.4981,
+      "step": 333
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002700252898382781,
+      "loss": 0.5701,
+      "step": 334
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002690531527116304,
+      "loss": 0.4725,
+      "step": 335
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00026807915975991765,
+      "loss": 0.5022,
+      "step": 336
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.000267103337159505,
+      "loss": 0.4953,
+      "step": 337
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002661257111359299,
+      "loss": 0.5762,
+      "step": 338
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002651463079631973,
+      "loss": 0.6713,
+      "step": 339
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00026416515396307353,
+      "loss": 0.506,
+      "step": 340
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5838707685470581,
+      "eval_runtime": 29.495,
+      "eval_samples_per_second": 55.23,
+      "eval_steps_per_second": 55.23,
+      "step": 340
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002631822755043793,
+      "loss": 0.5368,
+      "step": 341
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00026219769900228014,
+      "loss": 0.5509,
+      "step": 342
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002612114509175775,
+      "loss": 0.5365,
+      "step": 343
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002602235577559969,
+      "loss": 0.6527,
+      "step": 344
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002592340460674759,
+      "loss": 0.4975,
+      "step": 345
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00025824294244545045,
+      "loss": 0.6552,
+      "step": 346
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00025725027352614015,
+      "loss": 0.5523,
+      "step": 347
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00025625606598783256,
+      "loss": 0.6078,
+      "step": 348
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002552603465501661,
+      "loss": 0.4592,
+      "step": 349
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002542631419734118,
+      "loss": 0.587,
+      "step": 350
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00025326447905775446,
+      "loss": 0.5689,
+      "step": 351
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025226438464257217,
+      "loss": 0.4961,
+      "step": 352
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025126288560571483,
+      "loss": 0.4735,
+      "step": 353
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025026000886278223,
+      "loss": 0.5387,
+      "step": 354
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00024925578136640033,
+      "loss": 0.5427,
+      "step": 355
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002482502301054969,
+      "loss": 0.5362,
+      "step": 356
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002472433821045765,
+      "loss": 0.5619,
+      "step": 357
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000246235264422994,
+      "loss": 0.4473,
+      "step": 358
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002452259041542269,
+      "loss": 0.4934,
+      "step": 359
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002442153284251484,
+      "loss": 0.4804,
+      "step": 360
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.5803248882293701,
+      "eval_runtime": 29.5222,
+      "eval_samples_per_second": 55.179,
+      "eval_steps_per_second": 55.179,
+      "step": 360
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00024320356439529674,
+      "loss": 0.5928,
+      "step": 361
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00024219063925614664,
+      "loss": 0.5542,
+      "step": 362
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00024117658023037791,
+      "loss": 0.4748,
+      "step": 363
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002401614145711437,
+      "loss": 0.4946,
+      "step": 364
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00023914516956133862,
+      "loss": 0.4455,
+      "step": 365
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002381278725128649,
+      "loss": 0.4165,
+      "step": 366
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002371095507658987,
+      "loss": 0.4976,
+      "step": 367
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00023609023168815526,
+      "loss": 0.4858,
+      "step": 368
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00023506994267415358,
+      "loss": 0.5761,
+      "step": 369
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00023404871114447975,
+      "loss": 0.46,
+      "step": 370
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00023302656454505033,
+      "loss": 0.3988,
+      "step": 371
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00023200353034637483,
+      "loss": 0.6341,
+      "step": 372
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00023097963604281697,
+      "loss": 0.4849,
+      "step": 373
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00022995490915185633,
+      "loss": 0.4287,
+      "step": 374
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00022892937721334842,
+      "loss": 0.3591,
+      "step": 375
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00022790306778878465,
+      "loss": 0.454,
+      "step": 376
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022687600846055164,
+      "loss": 0.4785,
+      "step": 377
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002258482268311898,
+      "loss": 0.4696,
+      "step": 378
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022481975052265188,
+      "loss": 0.4635,
+      "step": 379
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002237906071755601,
+      "loss": 0.5095,
+      "step": 380
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.5974432229995728,
+      "eval_runtime": 29.5049,
+      "eval_samples_per_second": 55.211,
+      "eval_steps_per_second": 55.211,
+      "step": 380
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00022276082444846353,
+      "loss": 0.4766,
+      "step": 381
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002217304300170949,
+      "loss": 0.5072,
+      "step": 382
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00022069945157362675,
+      "loss": 0.5265,
+      "step": 383
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00021966791682592697,
+      "loss": 0.4095,
+      "step": 384
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00021863585349681436,
+      "loss": 0.3976,
+      "step": 385
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00021760328932331349,
+      "loss": 0.4774,
+      "step": 386
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00021657025205590923,
+      "loss": 0.3426,
+      "step": 387
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002155367694578013,
+      "loss": 0.4508,
+      "step": 388
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00021450286930415735,
+      "loss": 0.5369,
+      "step": 389
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002134685793813673,
+      "loss": 0.4261,
+      "step": 390
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00021243392748629614,
+      "loss": 0.5256,
+      "step": 391
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00021139894142553693,
+      "loss": 0.3956,
+      "step": 392
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002103636490146637,
+      "loss": 0.4001,
+      "step": 393
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00020932807807748352,
+      "loss": 0.6379,
+      "step": 394
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0002082922564452891,
+      "loss": 0.4611,
+      "step": 395
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00020725621195611052,
+      "loss": 0.5071,
+      "step": 396
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0002062199724539674,
+      "loss": 0.4864,
+      "step": 397
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00020518356578812022,
+      "loss": 0.4323,
+      "step": 398
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00020414701981232215,
+      "loss": 0.5897,
+      "step": 399
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002031103623840702,
+      "loss": 0.4404,
+      "step": 400
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 0.574560284614563,
+      "eval_runtime": 29.5518,
+      "eval_samples_per_second": 55.124,
+      "eval_steps_per_second": 55.124,
+      "step": 400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002020736213638569,
+      "loss": 0.4287,
+      "step": 401
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002010368246144213,
+      "loss": 0.5213,
+      "step": 402
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 0.405,
+      "step": 403
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00019896317538557878,
+      "loss": 0.4283,
+      "step": 404
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001979263786361431,
+      "loss": 0.4649,
+      "step": 405
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00019688963761592981,
+      "loss": 0.6243,
+      "step": 406
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00019585298018767798,
+      "loss": 0.4704,
+      "step": 407
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00019481643421187978,
+      "loss": 0.4266,
+      "step": 408
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00019378002754603265,
+      "loss": 0.4229,
+      "step": 409
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00019274378804388952,
+      "loss": 0.3718,
+      "step": 410
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00019170774355471094,
+      "loss": 0.4005,
+      "step": 411
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001906719219225165,
+      "loss": 0.4458,
+      "step": 412
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00018963635098533633,
+      "loss": 0.4691,
+      "step": 413
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00018860105857446306,
+      "loss": 0.5098,
+      "step": 414
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001875660725137039,
+      "loss": 0.4538,
+      "step": 415
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00018653142061863273,
+      "loss": 0.5558,
+      "step": 416
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00018549713069584276,
+      "loss": 0.6011,
+      "step": 417
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00018446323054219875,
+      "loss": 0.3524,
+      "step": 418
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00018342974794409079,
+      "loss": 0.5304,
+      "step": 419
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00018239671067668661,
+      "loss": 0.3869,
+      "step": 420
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.5739707350730896,
+      "eval_runtime": 29.5087,
+      "eval_samples_per_second": 55.204,
+      "eval_steps_per_second": 55.204,
+      "step": 420
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001813641465031857,
+      "loss": 0.4354,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00018033208317407308,
+      "loss": 0.4195,
+      "step": 422
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001793005484263733,
+      "loss": 0.6035,
+      "step": 423
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00017826956998290508,
+      "loss": 0.4244,
+      "step": 424
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00017723917555153654,
+      "loss": 0.4614,
+      "step": 425
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00017620939282444003,
+      "loss": 0.4522,
+      "step": 426
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00017518024947734814,
+      "loss": 0.459,
+      "step": 427
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00017415177316881022,
+      "loss": 0.4259,
+      "step": 428
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00017312399153944846,
+      "loss": 0.4132,
+      "step": 429
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00017209693221121542,
+      "loss": 0.402,
+      "step": 430
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00017107062278665165,
+      "loss": 0.4812,
+      "step": 431
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00017004509084814372,
+      "loss": 0.3626,
+      "step": 432
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00016902036395718305,
+      "loss": 0.4885,
+      "step": 433
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00016799646965362524,
+      "loss": 0.5113,
+      "step": 434
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00016697343545494974,
+      "loss": 0.5277,
+      "step": 435
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00016595128885552027,
+      "loss": 0.5086,
+      "step": 436
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00016493005732584647,
+      "loss": 0.3616,
+      "step": 437
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00016390976831184476,
+      "loss": 0.599,
+      "step": 438
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00016289044923410134,
+      "loss": 0.3622,
+      "step": 439
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00016187212748713519,
+      "loss": 0.4129,
+      "step": 440
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.5777345895767212,
+      "eval_runtime": 29.5678,
+      "eval_samples_per_second": 55.094,
+      "eval_steps_per_second": 55.094,
+      "step": 440
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00016085483043866143,
+      "loss": 0.3741,
+      "step": 441
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015983858542885634,
+      "loss": 0.508,
+      "step": 442
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015882341976962216,
+      "loss": 0.4585,
+      "step": 443
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001578093607438534,
+      "loss": 0.4852,
+      "step": 444
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015679643560470336,
+      "loss": 0.5091,
+      "step": 445
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015578467157485165,
+      "loss": 0.5604,
+      "step": 446
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001547740958457731,
+      "loss": 0.5011,
+      "step": 447
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015376473557700613,
+      "loss": 0.5016,
+      "step": 448
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001527566178954235,
+      "loss": 0.4144,
+      "step": 449
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015174976989450314,
+      "loss": 0.4511,
+      "step": 450
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00015074421863359974,
+      "loss": 0.4535,
+      "step": 451
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001497399911372178,
+      "loss": 0.4065,
+      "step": 452
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001487371143942852,
+      "loss": 0.6148,
+      "step": 453
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014773561535742793,
+      "loss": 0.5625,
+      "step": 454
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014673552094224553,
+      "loss": 0.3462,
+      "step": 455
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014573685802658824,
+      "loss": 0.5958,
+      "step": 456
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014473965344983397,
+      "loss": 0.4676,
+      "step": 457
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014374393401216746,
+      "loss": 0.5282,
+      "step": 458
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001427497264738599,
+      "loss": 0.4669,
+      "step": 459
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014175705755454962,
+      "loss": 0.4209,
+      "step": 460
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.5824912786483765,
+      "eval_runtime": 29.5128,
+      "eval_samples_per_second": 55.196,
+      "eval_steps_per_second": 55.196,
+      "step": 460
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014076595393252412,
+      "loss": 0.5164,
+      "step": 461
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013977644224400312,
+      "loss": 0.4663,
+      "step": 462
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013878854908242256,
+      "loss": 0.4182,
+      "step": 463
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013780230099771988,
+      "loss": 0.525,
+      "step": 464
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001368177244956208,
+      "loss": 0.4229,
+      "step": 465
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001358348460369265,
+      "loss": 0.5392,
+      "step": 466
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013485369203680283,
+      "loss": 0.436,
+      "step": 467
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013387428886407014,
+      "loss": 0.4743,
+      "step": 468
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013289666284049503,
+      "loss": 0.4443,
+      "step": 469
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001319208402400824,
+      "loss": 0.4095,
+      "step": 470
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013094684728836962,
+      "loss": 0.4275,
+      "step": 471
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00012997471016172187,
+      "loss": 0.5256,
+      "step": 472
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001290044549866283,
+      "loss": 0.5106,
+      "step": 473
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001280361078389998,
+      "loss": 0.5659,
+      "step": 474
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.000127069694743469,
+      "loss": 0.5246,
+      "step": 475
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00012610524167268975,
+      "loss": 0.4125,
+      "step": 476
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001251427745466398,
+      "loss": 0.647,
+      "step": 477
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00012418231923192415,
+      "loss": 0.4888,
+      "step": 478
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00012322390154107952,
+      "loss": 0.4619,
+      "step": 479
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00012226754723188097,
+      "loss": 0.4014,
+      "step": 480
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.5741853713989258,
+      "eval_runtime": 29.4992,
+      "eval_samples_per_second": 55.222,
+      "eval_steps_per_second": 55.222,
+      "step": 480
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00012131328200664955,
+      "loss": 0.3622,
+      "step": 481
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001203611315115615,
+      "loss": 0.4422,
+      "step": 482
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00011941112133595882,
+      "loss": 0.5294,
+      "step": 483
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00011846327701166226,
+      "loss": 0.583,
+      "step": 484
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00011751762401228414,
+      "loss": 0.4461,
+      "step": 485
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00011657418775254436,
+      "loss": 0.427,
+      "step": 486
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00011563299358758757,
+      "loss": 0.5413,
+      "step": 487
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.000114694066812301,
+      "loss": 0.4541,
+      "step": 488
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00011375743266063508,
+      "loss": 0.5347,
+      "step": 489
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00011282311630492579,
+      "loss": 0.5056,
+      "step": 490
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00011189114285521705,
+      "loss": 0.5073,
+      "step": 491
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001109615373585866,
+      "loss": 0.4864,
+      "step": 492
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00011003432479847284,
+      "loss": 0.5461,
+      "step": 493
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00010910953009400323,
+      "loss": 0.4275,
+      "step": 494
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00010818717809932435,
+      "loss": 0.4805,
+      "step": 495
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001072672936029345,
+      "loss": 0.4679,
+      "step": 496
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001063499013270172,
+      "loss": 0.3686,
+      "step": 497
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00010543502592677646,
+      "loss": 0.5115,
+      "step": 498
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00010452269198977456,
+      "loss": 0.3532,
+      "step": 499
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00010361292403527154,
+      "loss": 0.3333,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 0.5851367712020874,
+      "eval_runtime": 29.5774,
+      "eval_samples_per_second": 55.076,
+      "eval_steps_per_second": 55.076,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00010270574651356541,
+      "loss": 0.4008,
+      "step": 501
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00010180118380533559,
+      "loss": 0.5154,
+      "step": 502
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00010089926022098767,
+      "loss": 0.4936,
+      "step": 503
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00010000000000000005,
+      "loss": 0.3771,
+      "step": 504
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.910342731027206e-05,
+      "loss": 0.4883,
+      "step": 505
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.820956624747513e-05,
+      "loss": 0.4783,
+      "step": 506
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.731844083440478e-05,
+      "loss": 0.3825,
+      "step": 507
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.643007502033493e-05,
+      "loss": 0.4128,
+      "step": 508
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.554449268037464e-05,
+      "loss": 0.3869,
+      "step": 509
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.466171761482602e-05,
+      "loss": 0.4742,
+      "step": 510
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.378177354854498e-05,
+      "loss": 0.4733,
+      "step": 511
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.290468413030342e-05,
+      "loss": 0.4182,
+      "step": 512
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.203047293215349e-05,
+      "loss": 0.3875,
+      "step": 513
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.115916344879451e-05,
+      "loss": 0.4561,
+      "step": 514
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.029077909694128e-05,
+      "loss": 0.4582,
+      "step": 515
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.942534321469463e-05,
+      "loss": 0.3878,
+      "step": 516
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.856287906091434e-05,
+      "loss": 0.4842,
+      "step": 517
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.770340981459424e-05,
+      "loss": 0.4127,
+      "step": 518
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.684695857423906e-05,
+      "loss": 0.343,
+      "step": 519
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.599354835724347e-05,
+      "loss": 0.5041,
+      "step": 520
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.5797593593597412,
+      "eval_runtime": 29.4998,
+      "eval_samples_per_second": 55.221,
+      "eval_steps_per_second": 55.221,
+      "step": 520
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.514320209927392e-05,
+      "loss": 0.4945,
+      "step": 521
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.429594265365193e-05,
+      "loss": 0.4627,
+      "step": 522
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.345179279073982e-05,
+      "loss": 0.4855,
+      "step": 523
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.261077519732914e-05,
+      "loss": 0.4253,
+      "step": 524
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.177291247603068e-05,
+      "loss": 0.5328,
+      "step": 525
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.093822714466686e-05,
+      "loss": 0.5276,
+      "step": 526
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.01067416356668e-05,
+      "loss": 0.5293,
+      "step": 527
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.927847829546374e-05,
+      "loss": 0.5709,
+      "step": 528
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.845345938389372e-05,
+      "loss": 0.3874,
+      "step": 529
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.763170707359781e-05,
+      "loss": 0.6164,
+      "step": 530
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.68132434494263e-05,
+      "loss": 0.4348,
+      "step": 531
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.5998090507845e-05,
+      "loss": 0.4215,
+      "step": 532
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.518627015634392e-05,
+      "loss": 0.4744,
+      "step": 533
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.437780421284883e-05,
+      "loss": 0.4775,
+      "step": 534
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.357271440513473e-05,
+      "loss": 0.5049,
+      "step": 535
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.277102237024178e-05,
+      "loss": 0.4757,
+      "step": 536
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.197274965389413e-05,
+      "loss": 0.4429,
+      "step": 537
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.117791770992047e-05,
+      "loss": 0.4628,
+      "step": 538
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.038654789967776e-05,
+      "loss": 0.5186,
+      "step": 539
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.959866149147716e-05,
+      "loss": 0.5528,
+      "step": 540
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.5631201267242432,
+      "eval_runtime": 29.5533,
+      "eval_samples_per_second": 55.121,
+      "eval_steps_per_second": 55.121,
+      "step": 540
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.881427966001202e-05,
+      "loss": 0.4201,
+      "step": 541
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.803342348578938e-05,
+      "loss": 0.3929,
+      "step": 542
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.72561139545629e-05,
+      "loss": 0.5163,
+      "step": 543
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.648237195676928e-05,
+      "loss": 0.4811,
+      "step": 544
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.571221828696664e-05,
+      "loss": 0.5658,
+      "step": 545
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.494567364327549e-05,
+      "loss": 0.5507,
+      "step": 546
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.418275862682286e-05,
+      "loss": 0.4629,
+      "step": 547
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.342349374118817e-05,
+      "loss": 0.4757,
+      "step": 548
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.266789939185265e-05,
+      "loss": 0.3063,
+      "step": 549
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.191599588565067e-05,
+      "loss": 0.3894,
+      "step": 550
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.116780343022393e-05,
+      "loss": 0.4114,
+      "step": 551
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.042334213347856e-05,
+      "loss": 0.399,
+      "step": 552
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.9682632003044695e-05,
+      "loss": 0.4437,
+      "step": 553
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.8945692945738596e-05,
+      "loss": 0.4709,
+      "step": 554
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.821254476702767e-05,
+      "loss": 0.4779,
+      "step": 555
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.748320717049862e-05,
+      "loss": 0.4662,
+      "step": 556
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.6757699757327257e-05,
+      "loss": 0.4706,
+      "step": 557
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.603604202575199e-05,
+      "loss": 0.5546,
+      "step": 558
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.531825337055005e-05,
+      "loss": 0.4415,
+      "step": 559
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.460435308251597e-05,
+      "loss": 0.4372,
+      "step": 560
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 0.5746860504150391,
+      "eval_runtime": 29.5006,
+      "eval_samples_per_second": 55.219,
+      "eval_steps_per_second": 55.219,
+      "step": 560
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.3894360347943016e-05,
+      "loss": 0.4186,
+      "step": 561
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.318829424810796e-05,
+      "loss": 0.4436,
+      "step": 562
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.2486173758758e-05,
+      "loss": 0.3979,
+      "step": 563
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.178801774960065e-05,
+      "loss": 0.3732,
+      "step": 564
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.109384498379699e-05,
+      "loss": 0.3469,
+      "step": 565
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.040367411745701e-05,
+      "loss": 0.4271,
+      "step": 566
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.971752369913856e-05,
+      "loss": 0.4189,
+      "step": 567
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.903541216934864e-05,
+      "loss": 0.5201,
+      "step": 568
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.835735786004774e-05,
+      "loss": 0.4036,
+      "step": 569
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.768337899415749e-05,
+      "loss": 0.5698,
+      "step": 570
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.7013493685070484e-05,
+      "loss": 0.4032,
+      "step": 571
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.634771993616389e-05,
+      "loss": 0.4928,
+      "step": 572
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.568607564031535e-05,
+      "loss": 0.3489,
+      "step": 573
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.502857857942204e-05,
+      "loss": 0.506,
+      "step": 574
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.4375246423923125e-05,
+      "loss": 0.3895,
+      "step": 575
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.3726096732324415e-05,
+      "loss": 0.4829,
+      "step": 576
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.3081146950726804e-05,
+      "loss": 0.4555,
+      "step": 577
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.2440414412357376e-05,
+      "loss": 0.5311,
+      "step": 578
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.1803916337103275e-05,
+      "loss": 0.398,
+      "step": 579
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.11716698310493e-05,
+      "loss": 0.3901,
+      "step": 580
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 0.5625116229057312,
+      "eval_runtime": 29.4983,
+      "eval_samples_per_second": 55.224,
+      "eval_steps_per_second": 55.224,
+      "step": 580
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.054369188601796e-05,
+      "loss": 0.3709,
+      "step": 581
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.991999937911282e-05,
+      "loss": 0.3773,
+      "step": 582
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.930060907226485e-05,
+      "loss": 0.502,
+      "step": 583
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.8685537611782355e-05,
+      "loss": 0.5624,
+      "step": 584
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.807480152790302e-05,
+      "loss": 0.5273,
+      "step": 585
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.7468417234349976e-05,
+      "loss": 0.3771,
+      "step": 586
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.686640102789067e-05,
+      "loss": 0.3751,
+      "step": 587
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.6268769087898956e-05,
+      "loss": 0.4526,
+      "step": 588
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.567553747591988e-05,
+      "loss": 0.335,
+      "step": 589
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.508672213523854e-05,
+      "loss": 0.4781,
+      "step": 590
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.4502338890451315e-05,
+      "loss": 0.3673,
+      "step": 591
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.39224034470405e-05,
+      "loss": 0.4073,
+      "step": 592
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.3346931390952464e-05,
+      "loss": 0.4014,
+      "step": 593
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.277593818817863e-05,
+      "loss": 0.4375,
+      "step": 594
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.2209439184339804e-05,
+      "loss": 0.4856,
+      "step": 595
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.164744960427373e-05,
+      "loss": 0.5534,
+      "step": 596
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.1089984551626106e-05,
+      "loss": 0.3766,
+      "step": 597
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.053705900844452e-05,
+      "loss": 0.541,
+      "step": 598
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.9988687834775707e-05,
+      "loss": 0.3937,
+      "step": 599
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.9444885768266427e-05,
+      "loss": 0.5271,
+      "step": 600
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.5745556950569153,
+      "eval_runtime": 29.5072,
+      "eval_samples_per_second": 55.207,
+      "eval_steps_per_second": 55.207,
+      "step": 600
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.8905667423767256e-05,
+      "loss": 0.4961,
+      "step": 601
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.8371047292939645e-05,
+      "loss": 0.306,
+      "step": 602
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.7841039743866848e-05,
+      "loss": 0.4234,
+      "step": 603
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.7315659020667307e-05,
+      "loss": 0.4259,
+      "step": 604
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 0.5458,
+      "step": 605
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.6278834406246054e-05,
+      "loss": 0.4212,
+      "step": 606
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.576741838000991e-05,
+      "loss": 0.445,
+      "step": 607
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.526068490886946e-05,
+      "loss": 0.4042,
+      "step": 608
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.4758647611445152e-05,
+      "loss": 0.4857,
+      "step": 609
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.4261319980146292e-05,
+      "loss": 0.4402,
+      "step": 610
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.3768715380808316e-05,
+      "loss": 0.4056,
+      "step": 611
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.3280847052333976e-05,
+      "loss": 0.4577,
+      "step": 612
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.279772810633707e-05,
+      "loss": 0.3902,
+      "step": 613
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.2319371526790223e-05,
+      "loss": 0.4658,
+      "step": 614
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.1845790169676074e-05,
+      "loss": 0.3919,
+      "step": 615
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.137699676264171e-05,
+      "loss": 0.4294,
+      "step": 616
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.091300390465638e-05,
+      "loss": 0.3718,
+      "step": 617
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0453824065673222e-05,
+      "loss": 0.5159,
+      "step": 618
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.9999469586293996e-05,
+      "loss": 0.4383,
+      "step": 619
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.9549952677437354e-05,
+      "loss": 0.4283,
+      "step": 620
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.566196084022522,
+      "eval_runtime": 29.5086,
+      "eval_samples_per_second": 55.204,
+      "eval_steps_per_second": 55.204,
+      "step": 620
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.9105285420010598e-05,
+      "loss": 0.3683,
+      "step": 621
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8665479764585503e-05,
+      "loss": 0.424,
+      "step": 622
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8230547531076403e-05,
+      "loss": 0.4972,
+      "step": 623
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7800500408423028e-05,
+      "loss": 0.3295,
+      "step": 624
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7375349954276233e-05,
+      "loss": 0.4563,
+      "step": 625
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.695510759468746e-05,
+      "loss": 0.3215,
+      "step": 626
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.653978462380139e-05,
+      "loss": 0.5377,
+      "step": 627
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.6129392203552717e-05,
+      "loss": 0.5608,
+      "step": 628
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.5723941363366102e-05,
+      "loss": 0.4279,
+      "step": 629
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.5323442999859505e-05,
+      "loss": 0.4503,
+      "step": 630
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.4927907876551716e-05,
+      "loss": 0.3723,
+      "step": 631
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.4537346623572757e-05,
+      "loss": 0.4459,
+      "step": 632
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.415176973737844e-05,
+      "loss": 0.5126,
+      "step": 633
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.3771187580468115e-05,
+      "loss": 0.4712,
+      "step": 634
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.3395610381106171e-05,
+      "loss": 0.4301,
+      "step": 635
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.3025048233047266e-05,
+      "loss": 0.4497,
+      "step": 636
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.2659511095264997e-05,
+      "loss": 0.6653,
+      "step": 637
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.2299008791684174e-05,
+      "loss": 0.4751,
+      "step": 638
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1943551010916887e-05,
+      "loss": 0.4593,
+      "step": 639
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1593147306002183e-05,
+      "loss": 0.4336,
+      "step": 640
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.5652015209197998,
+      "eval_runtime": 29.5541,
+      "eval_samples_per_second": 55.119,
+      "eval_steps_per_second": 55.119,
+      "step": 640
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1247807094149098e-05,
+      "loss": 0.3976,
+      "step": 641
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0907539656483745e-05,
+      "loss": 0.4607,
+      "step": 642
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0572354137799978e-05,
+      "loss": 0.3328,
+      "step": 643
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0242259546313327e-05,
+      "loss": 0.3834,
+      "step": 644
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.91726475341912e-06,
+      "loss": 0.3841,
+      "step": 645
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.597378493454013e-06,
+      "loss": 0.4061,
+      "step": 646
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.282609363461281e-06,
+      "loss": 0.5084,
+      "step": 647
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.972965822959678e-06,
+      "loss": 0.4186,
+      "step": 648
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.668456193716057e-06,
+      "loss": 0.4335,
+      "step": 649
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.369088659522018e-06,
+      "loss": 0.4099,
+      "step": 650
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.074871265973572e-06,
+      "loss": 0.4574,
+      "step": 651
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.785811920255093e-06,
+      "loss": 0.3767,
+      "step": 652
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.501918390926932e-06,
+      "loss": 0.4218,
+      "step": 653
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.223198307716428e-06,
+      "loss": 0.4847,
+      "step": 654
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.949659161312871e-06,
+      "loss": 0.3806,
+      "step": 655
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.6813083031664005e-06,
+      "loss": 0.467,
+      "step": 656
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.418152945290224e-06,
+      "loss": 0.4087,
+      "step": 657
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.1602001600667755e-06,
+      "loss": 0.5307,
+      "step": 658
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.907456880057871e-06,
+      "loss": 0.3665,
+      "step": 659
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.659929897818095e-06,
+      "loss": 0.3534,
+      "step": 660
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.5697055459022522,
+      "eval_runtime": 29.5456,
+      "eval_samples_per_second": 55.135,
+      "eval_steps_per_second": 55.135,
+      "step": 660
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.417625865712506e-06,
+      "loss": 0.4096,
+      "step": 661
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.180551295737734e-06,
+      "loss": 0.3822,
+      "step": 662
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.9487125593469244e-06,
+      "loss": 0.4499,
+      "step": 663
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.7221158872786e-06,
+      "loss": 0.4191,
+      "step": 664
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.500767369389158e-06,
+      "loss": 0.4676,
+      "step": 665
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.284672954489177e-06,
+      "loss": 0.379,
+      "step": 666
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.073838450183654e-06,
+      "loss": 0.4382,
+      "step": 667
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.8682695227158174e-06,
+      "loss": 0.3908,
+      "step": 668
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.667971696814787e-06,
+      "loss": 0.4563,
+      "step": 669
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.4729503555472663e-06,
+      "loss": 0.4164,
+      "step": 670
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.2832107401727928e-06,
+      "loss": 0.361,
+      "step": 671
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.0987579500028062e-06,
+      "loss": 0.4599,
+      "step": 672
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.919596942263736e-06,
+      "loss": 0.4045,
+      "step": 673
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.7457325319636408e-06,
+      "loss": 0.4345,
+      "step": 674
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.5771693917629345e-06,
+      "loss": 0.5191,
+      "step": 675
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.4139120518486657e-06,
+      "loss": 0.444,
+      "step": 676
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.2559648998128792e-06,
+      "loss": 0.4587,
+      "step": 677
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.1033321805346896e-06,
+      "loss": 0.4841,
+      "step": 678
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9560179960661283e-06,
+      "loss": 0.3539,
+      "step": 679
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.8140263055219209e-06,
+      "loss": 0.4728,
+      "step": 680
+    },
+    {
+      "epoch": 1.93,
+      "eval_loss": 0.5713478922843933,
+      "eval_runtime": 29.5401,
+      "eval_samples_per_second": 55.145,
+      "eval_steps_per_second": 55.145,
+      "step": 680
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.6773609249731703e-06,
+      "loss": 0.5651,
+      "step": 681
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.5460255273447077e-06,
+      "loss": 0.5959,
+      "step": 682
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.4200236423163704e-06,
+      "loss": 0.5015,
+      "step": 683
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2993586562282112e-06,
+      "loss": 0.5174,
+      "step": 684
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.1840338119894822e-06,
+      "loss": 0.3708,
+      "step": 685
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0740522089913941e-06,
+      "loss": 0.4129,
+      "step": 686
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.694168030239148e-07,
+      "loss": 0.4747,
+      "step": 687
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 8.701304061962789e-07,
+      "loss": 0.3967,
+      "step": 688
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.761956868614473e-07,
+      "loss": 0.3929,
+      "step": 689
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.876151695443867e-07,
+      "loss": 0.4657,
+      "step": 690
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.043912348741465e-07,
+      "loss": 0.4274,
+      "step": 691
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.265261195200211e-07,
+      "loss": 0.5102,
+      "step": 692
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.5402191613130864e-07,
+      "loss": 0.4686,
+      "step": 693
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.8688057328113425e-07,
+      "loss": 0.397,
+      "step": 694
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.251038954140917e-07,
+      "loss": 0.4532,
+      "step": 695
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.6869354279770444e-07,
+      "loss": 0.3698,
+      "step": 696
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.1765103147783905e-07,
+      "loss": 0.4519,
+      "step": 697
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.7197773323791577e-07,
+      "loss": 0.4861,
+      "step": 698
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3167487556213775e-07,
+      "loss": 0.5166,
+      "step": 699
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 9.67435416023843e-08,
+      "loss": 0.5159,
+      "step": 700
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.5703364014625549,
+      "eval_runtime": 29.5151,
+      "eval_samples_per_second": 55.192,
+      "eval_steps_per_second": 55.192,
+      "step": 700
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.718467014918962e-08,
+      "loss": 0.3659,
+      "step": 701
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 4.299905560642969e-08,
+      "loss": 0.4171,
+      "step": 702
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.418734797009492e-08,
+      "loss": 0.3435,
+      "step": 703
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.075005281070407e-08,
+      "loss": 0.5624,
+      "step": 704
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6875312597374193e-09,
+      "loss": 0.4061,
+      "step": 705
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.3871,
+      "step": 706
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 706,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.8453659621743657e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-706/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc29491a898700f15de2024fec703fbc3c0e47ff2a1808b6210d1914f87ee43
+size 4475

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}