commit from cp400

README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-chat-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]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## 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 0.6.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d575312196cad8b27f8126c5cd8ab94d70152f5aab4a32476bd79cbd442abbe0
+size 80013120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6c1778038a67d0e25990e97182baca5a99869cd7bd11a4da10e61e7d05b527
+size 40570772

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb5af75cbb7702914d14c3eae35b3e95c4740f5af20e550edf9c4327f4f11ec
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44cd6af8be2bf07dffefe3fd8b4a71ea5dcc016e9ba568489db94f1fa71b011
+size 1064

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_config.json

@@ -0,0 +1,40 @@
+{
+  "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>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2499 @@
+{
+  "best_metric": 1.3731473684310913,
+  "best_model_checkpoint": "outputs_llama-2/checkpoint-400",
+  "epoch": 0.6170458927882762,
+  "eval_steps": 40,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 3.4868,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 3.7961,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6e-05,
+      "loss": 3.9088,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 3.4984,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 3.2276,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012,
+      "loss": 3.0655,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014,
+      "loss": 3.3618,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016,
+      "loss": 2.7163,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018,
+      "loss": 2.5164,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 2.4623,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019968652037617558,
+      "loss": 2.5072,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001993730407523511,
+      "loss": 2.3718,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019905956112852667,
+      "loss": 1.9166,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001987460815047022,
+      "loss": 1.8158,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019843260188087775,
+      "loss": 1.6101,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001981191222570533,
+      "loss": 1.7501,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019780564263322884,
+      "loss": 1.8495,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001974921630094044,
+      "loss": 1.7858,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019717868338557995,
+      "loss": 1.511,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001968652037617555,
+      "loss": 1.3787,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019655172413793104,
+      "loss": 1.8197,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001962382445141066,
+      "loss": 1.4238,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019592476489028212,
+      "loss": 1.6311,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001956112852664577,
+      "loss": 1.7413,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019529780564263324,
+      "loss": 1.6356,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019498432601880878,
+      "loss": 1.5826,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019467084639498435,
+      "loss": 1.3187,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019435736677115987,
+      "loss": 1.9504,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019404388714733544,
+      "loss": 1.5303,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019373040752351098,
+      "loss": 1.9262,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019341692789968652,
+      "loss": 1.3492,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001931034482758621,
+      "loss": 1.5133,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001927899686520376,
+      "loss": 1.7638,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019247648902821318,
+      "loss": 1.4146,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019216300940438872,
+      "loss": 2.0048,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019184952978056427,
+      "loss": 1.1199,
+      "step": 36
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001915360501567398,
+      "loss": 1.5077,
+      "step": 37
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019122257053291538,
+      "loss": 1.8042,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 1.3575,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019059561128526647,
+      "loss": 1.6653,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.4491230249404907,
+      "eval_runtime": 866.4575,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000190282131661442,
+      "loss": 1.0084,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00018996865203761755,
+      "loss": 1.841,
+      "step": 42
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00018965517241379312,
+      "loss": 1.5954,
+      "step": 43
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00018934169278996866,
+      "loss": 1.4138,
+      "step": 44
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001890282131661442,
+      "loss": 1.6798,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00018871473354231978,
+      "loss": 1.2323,
+      "step": 46
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001884012539184953,
+      "loss": 1.1051,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00018808777429467086,
+      "loss": 1.2045,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001877742946708464,
+      "loss": 1.7915,
+      "step": 49
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00018746081504702195,
+      "loss": 1.5733,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00018714733542319752,
+      "loss": 1.1321,
+      "step": 51
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00018683385579937304,
+      "loss": 1.5533,
+      "step": 52
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001865203761755486,
+      "loss": 1.6388,
+      "step": 53
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00018620689655172415,
+      "loss": 1.7207,
+      "step": 54
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001858934169278997,
+      "loss": 1.6191,
+      "step": 55
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018557993730407524,
+      "loss": 1.1936,
+      "step": 56
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001852664576802508,
+      "loss": 0.8021,
+      "step": 57
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018495297805642635,
+      "loss": 1.6352,
+      "step": 58
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001846394984326019,
+      "loss": 1.3609,
+      "step": 59
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018432601880877744,
+      "loss": 1.1234,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00018401253918495298,
+      "loss": 1.4164,
+      "step": 61
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018369905956112855,
+      "loss": 1.2983,
+      "step": 62
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018338557993730406,
+      "loss": 1.6532,
+      "step": 63
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018307210031347963,
+      "loss": 0.8675,
+      "step": 64
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018275862068965518,
+      "loss": 1.3623,
+      "step": 65
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018244514106583072,
+      "loss": 1.7138,
+      "step": 66
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001821316614420063,
+      "loss": 1.6071,
+      "step": 67
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 1.3497,
+      "step": 68
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018150470219435738,
+      "loss": 1.7226,
+      "step": 69
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018119122257053292,
+      "loss": 1.5776,
+      "step": 70
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018087774294670846,
+      "loss": 1.4415,
+      "step": 71
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018056426332288403,
+      "loss": 1.3818,
+      "step": 72
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018025078369905958,
+      "loss": 1.14,
+      "step": 73
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00017993730407523512,
+      "loss": 1.1541,
+      "step": 74
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017962382445141066,
+      "loss": 1.4013,
+      "step": 75
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001793103448275862,
+      "loss": 2.0154,
+      "step": 76
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017899686520376175,
+      "loss": 1.4794,
+      "step": 77
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017868338557993732,
+      "loss": 1.4989,
+      "step": 78
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017836990595611286,
+      "loss": 1.6,
+      "step": 79
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001780564263322884,
+      "loss": 1.3883,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4160501956939697,
+      "eval_runtime": 865.4029,
+      "eval_samples_per_second": 1.161,
+      "eval_steps_per_second": 1.161,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00017774294670846398,
+      "loss": 1.0814,
+      "step": 81
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001774294670846395,
+      "loss": 1.4005,
+      "step": 82
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00017711598746081506,
+      "loss": 1.576,
+      "step": 83
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001768025078369906,
+      "loss": 1.6388,
+      "step": 84
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00017648902821316615,
+      "loss": 1.3295,
+      "step": 85
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00017617554858934172,
+      "loss": 1.7523,
+      "step": 86
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00017586206896551723,
+      "loss": 1.7137,
+      "step": 87
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001755485893416928,
+      "loss": 1.3514,
+      "step": 88
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017523510971786835,
+      "loss": 1.5445,
+      "step": 89
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001749216300940439,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017460815047021943,
+      "loss": 1.4337,
+      "step": 91
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000174294670846395,
+      "loss": 1.572,
+      "step": 92
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017398119122257055,
+      "loss": 1.3782,
+      "step": 93
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001736677115987461,
+      "loss": 1.3746,
+      "step": 94
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017335423197492163,
+      "loss": 1.5409,
+      "step": 95
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017304075235109718,
+      "loss": 1.5832,
+      "step": 96
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 1.3129,
+      "step": 97
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 1.3966,
+      "step": 98
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017210031347962383,
+      "loss": 1.7874,
+      "step": 99
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001717868338557994,
+      "loss": 1.0902,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017147335423197492,
+      "loss": 1.617,
+      "step": 101
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001711598746081505,
+      "loss": 1.2597,
+      "step": 102
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017084639498432603,
+      "loss": 1.5788,
+      "step": 103
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017053291536050158,
+      "loss": 1.3218,
+      "step": 104
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017021943573667712,
+      "loss": 1.3153,
+      "step": 105
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00016990595611285266,
+      "loss": 1.2564,
+      "step": 106
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016959247648902823,
+      "loss": 1.8,
+      "step": 107
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016927899686520377,
+      "loss": 1.3895,
+      "step": 108
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016896551724137932,
+      "loss": 1.3897,
+      "step": 109
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016865203761755486,
+      "loss": 1.4656,
+      "step": 110
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001683385579937304,
+      "loss": 0.7588,
+      "step": 111
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016802507836990597,
+      "loss": 0.9988,
+      "step": 112
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00016771159874608152,
+      "loss": 1.8016,
+      "step": 113
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00016739811912225706,
+      "loss": 1.5793,
+      "step": 114
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001670846394984326,
+      "loss": 1.5504,
+      "step": 115
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00016677115987460817,
+      "loss": 1.3969,
+      "step": 116
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001664576802507837,
+      "loss": 1.0452,
+      "step": 117
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00016614420062695926,
+      "loss": 1.7136,
+      "step": 118
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001658307210031348,
+      "loss": 1.6306,
+      "step": 119
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00016551724137931035,
+      "loss": 1.2302,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.4042863845825195,
+      "eval_runtime": 866.713,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00016520376175548592,
+      "loss": 1.6392,
+      "step": 121
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00016489028213166143,
+      "loss": 1.7501,
+      "step": 122
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000164576802507837,
+      "loss": 1.3811,
+      "step": 123
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00016426332288401255,
+      "loss": 1.2695,
+      "step": 124
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001639498432601881,
+      "loss": 1.0973,
+      "step": 125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.2281,
+      "step": 126
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001633228840125392,
+      "loss": 1.8312,
+      "step": 127
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016300940438871475,
+      "loss": 1.2764,
+      "step": 128
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001626959247648903,
+      "loss": 1.3624,
+      "step": 129
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016238244514106583,
+      "loss": 1.2449,
+      "step": 130
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016206896551724137,
+      "loss": 1.2079,
+      "step": 131
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016175548589341694,
+      "loss": 1.0546,
+      "step": 132
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001614420062695925,
+      "loss": 1.1052,
+      "step": 133
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016112852664576803,
+      "loss": 1.789,
+      "step": 134
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001608150470219436,
+      "loss": 1.357,
+      "step": 135
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016050156739811912,
+      "loss": 1.6354,
+      "step": 136
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001601880877742947,
+      "loss": 1.4717,
+      "step": 137
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015987460815047023,
+      "loss": 1.7371,
+      "step": 138
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015956112852664577,
+      "loss": 1.5482,
+      "step": 139
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015924764890282134,
+      "loss": 1.202,
+      "step": 140
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015893416927899686,
+      "loss": 1.1362,
+      "step": 141
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015862068965517243,
+      "loss": 1.2072,
+      "step": 142
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015830721003134797,
+      "loss": 1.5035,
+      "step": 143
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015799373040752352,
+      "loss": 1.6734,
+      "step": 144
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00015768025078369906,
+      "loss": 1.3708,
+      "step": 145
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001573667711598746,
+      "loss": 1.3016,
+      "step": 146
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015705329153605017,
+      "loss": 0.6789,
+      "step": 147
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015673981191222572,
+      "loss": 1.2877,
+      "step": 148
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015642633228840126,
+      "loss": 1.3416,
+      "step": 149
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001561128526645768,
+      "loss": 1.1312,
+      "step": 150
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015579937304075237,
+      "loss": 1.2825,
+      "step": 151
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001554858934169279,
+      "loss": 0.9458,
+      "step": 152
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015517241379310346,
+      "loss": 1.4786,
+      "step": 153
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000154858934169279,
+      "loss": 1.734,
+      "step": 154
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 1.302,
+      "step": 155
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015423197492163011,
+      "loss": 1.3067,
+      "step": 156
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015391849529780563,
+      "loss": 1.2758,
+      "step": 157
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001536050156739812,
+      "loss": 0.4271,
+      "step": 158
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015329153605015674,
+      "loss": 1.3511,
+      "step": 159
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001529780564263323,
+      "loss": 1.2637,
+      "step": 160
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.3989219665527344,
+      "eval_runtime": 866.2996,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 160
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015266457680250786,
+      "loss": 1.2459,
+      "step": 161
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001523510971786834,
+      "loss": 1.1139,
+      "step": 162
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015203761755485894,
+      "loss": 1.7787,
+      "step": 163
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015172413793103449,
+      "loss": 1.8546,
+      "step": 164
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015141065830721003,
+      "loss": 1.3567,
+      "step": 165
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015109717868338557,
+      "loss": 1.1376,
+      "step": 166
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015078369905956114,
+      "loss": 1.2866,
+      "step": 167
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015047021943573669,
+      "loss": 1.1168,
+      "step": 168
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015015673981191223,
+      "loss": 1.3957,
+      "step": 169
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001498432601880878,
+      "loss": 1.4531,
+      "step": 170
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00014952978056426332,
+      "loss": 1.3238,
+      "step": 171
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014921630094043889,
+      "loss": 1.2166,
+      "step": 172
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014890282131661443,
+      "loss": 1.5402,
+      "step": 173
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014858934169278997,
+      "loss": 1.6967,
+      "step": 174
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014827586206896554,
+      "loss": 1.6176,
+      "step": 175
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014796238244514106,
+      "loss": 1.3383,
+      "step": 176
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014764890282131663,
+      "loss": 1.4409,
+      "step": 177
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00014733542319749217,
+      "loss": 1.2145,
+      "step": 178
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00014702194357366771,
+      "loss": 1.7027,
+      "step": 179
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00014670846394984328,
+      "loss": 1.5586,
+      "step": 180
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001463949843260188,
+      "loss": 1.3585,
+      "step": 181
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00014608150470219437,
+      "loss": 1.4356,
+      "step": 182
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001457680250783699,
+      "loss": 1.202,
+      "step": 183
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.4999,
+      "step": 184
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000145141065830721,
+      "loss": 1.8095,
+      "step": 185
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00014482758620689657,
+      "loss": 1.1945,
+      "step": 186
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001445141065830721,
+      "loss": 1.2339,
+      "step": 187
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00014420062695924766,
+      "loss": 1.8472,
+      "step": 188
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001438871473354232,
+      "loss": 0.9892,
+      "step": 189
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00014357366771159874,
+      "loss": 1.1517,
+      "step": 190
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001432601880877743,
+      "loss": 1.4252,
+      "step": 191
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014294670846394983,
+      "loss": 1.5793,
+      "step": 192
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001426332288401254,
+      "loss": 1.6862,
+      "step": 193
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014231974921630097,
+      "loss": 1.2111,
+      "step": 194
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014200626959247648,
+      "loss": 1.5163,
+      "step": 195
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014169278996865206,
+      "loss": 1.4963,
+      "step": 196
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001413793103448276,
+      "loss": 1.906,
+      "step": 197
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014106583072100314,
+      "loss": 1.4359,
+      "step": 198
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014075235109717868,
+      "loss": 1.4324,
+      "step": 199
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014043887147335423,
+      "loss": 1.513,
+      "step": 200
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 1.3920646905899048,
+      "eval_runtime": 866.473,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001401253918495298,
+      "loss": 1.2709,
+      "step": 201
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013981191222570534,
+      "loss": 1.4844,
+      "step": 202
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013949843260188088,
+      "loss": 1.4832,
+      "step": 203
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013918495297805643,
+      "loss": 1.6388,
+      "step": 204
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000138871473354232,
+      "loss": 0.7068,
+      "step": 205
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001385579937304075,
+      "loss": 1.4712,
+      "step": 206
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00013824451410658308,
+      "loss": 1.4861,
+      "step": 207
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 1.0516,
+      "step": 208
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00013761755485893417,
+      "loss": 1.7038,
+      "step": 209
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00013730407523510974,
+      "loss": 1.5841,
+      "step": 210
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013699059561128526,
+      "loss": 1.7073,
+      "step": 211
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013667711598746083,
+      "loss": 1.1921,
+      "step": 212
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 1.4323,
+      "step": 213
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001360501567398119,
+      "loss": 1.6943,
+      "step": 214
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013573667711598748,
+      "loss": 1.1724,
+      "step": 215
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013542319749216303,
+      "loss": 1.6194,
+      "step": 216
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00013510971786833857,
+      "loss": 1.1307,
+      "step": 217
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001347962382445141,
+      "loss": 0.9491,
+      "step": 218
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013448275862068965,
+      "loss": 1.4941,
+      "step": 219
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001341692789968652,
+      "loss": 1.519,
+      "step": 220
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013385579937304077,
+      "loss": 1.2309,
+      "step": 221
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001335423197492163,
+      "loss": 1.7851,
+      "step": 222
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013322884012539185,
+      "loss": 1.2136,
+      "step": 223
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001329153605015674,
+      "loss": 1.4588,
+      "step": 224
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013260188087774294,
+      "loss": 1.1362,
+      "step": 225
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001322884012539185,
+      "loss": 1.3981,
+      "step": 226
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013197492163009403,
+      "loss": 1.417,
+      "step": 227
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001316614420062696,
+      "loss": 1.3526,
+      "step": 228
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013134796238244517,
+      "loss": 1.3844,
+      "step": 229
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013103448275862068,
+      "loss": 1.1524,
+      "step": 230
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00013072100313479625,
+      "loss": 1.46,
+      "step": 231
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001304075235109718,
+      "loss": 1.4659,
+      "step": 232
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00013009404388714734,
+      "loss": 0.9684,
+      "step": 233
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001297805642633229,
+      "loss": 1.4079,
+      "step": 234
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00012946708463949843,
+      "loss": 1.5447,
+      "step": 235
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.000129153605015674,
+      "loss": 1.4095,
+      "step": 236
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012884012539184954,
+      "loss": 1.4073,
+      "step": 237
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012852664576802508,
+      "loss": 1.2867,
+      "step": 238
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012821316614420062,
+      "loss": 1.7357,
+      "step": 239
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001278996865203762,
+      "loss": 1.4032,
+      "step": 240
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 1.386928915977478,
+      "eval_runtime": 866.195,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 240
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012758620689655174,
+      "loss": 1.4204,
+      "step": 241
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 1.1404,
+      "step": 242
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00012695924764890282,
+      "loss": 1.7556,
+      "step": 243
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00012664576802507837,
+      "loss": 1.1598,
+      "step": 244
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00012633228840125394,
+      "loss": 1.6847,
+      "step": 245
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00012601880877742945,
+      "loss": 0.9023,
+      "step": 246
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00012570532915360502,
+      "loss": 1.7739,
+      "step": 247
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001253918495297806,
+      "loss": 1.2681,
+      "step": 248
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001250783699059561,
+      "loss": 1.5614,
+      "step": 249
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012476489028213168,
+      "loss": 1.7507,
+      "step": 250
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012445141065830722,
+      "loss": 1.205,
+      "step": 251
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012413793103448277,
+      "loss": 1.0752,
+      "step": 252
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001238244514106583,
+      "loss": 1.6259,
+      "step": 253
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012351097178683385,
+      "loss": 1.2839,
+      "step": 254
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012319749216300942,
+      "loss": 1.5367,
+      "step": 255
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012288401253918497,
+      "loss": 1.3161,
+      "step": 256
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001225705329153605,
+      "loss": 1.5973,
+      "step": 257
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012225705329153605,
+      "loss": 1.3614,
+      "step": 258
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012194357366771161,
+      "loss": 0.9446,
+      "step": 259
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012163009404388714,
+      "loss": 1.3996,
+      "step": 260
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012131661442006271,
+      "loss": 1.4435,
+      "step": 261
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012100313479623827,
+      "loss": 1.059,
+      "step": 262
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001206896551724138,
+      "loss": 1.1291,
+      "step": 263
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00012037617554858935,
+      "loss": 1.4702,
+      "step": 264
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001200626959247649,
+      "loss": 1.3586,
+      "step": 265
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011974921630094045,
+      "loss": 1.6694,
+      "step": 266
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011943573667711598,
+      "loss": 1.2642,
+      "step": 267
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00011912225705329154,
+      "loss": 1.1625,
+      "step": 268
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001188087774294671,
+      "loss": 1.6103,
+      "step": 269
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011849529780564264,
+      "loss": 1.3178,
+      "step": 270
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 1.3575,
+      "step": 271
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011786833855799372,
+      "loss": 1.4692,
+      "step": 272
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001175548589341693,
+      "loss": 1.7414,
+      "step": 273
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011724137931034482,
+      "loss": 1.6938,
+      "step": 274
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00011692789968652038,
+      "loss": 1.9068,
+      "step": 275
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011661442006269594,
+      "loss": 1.6176,
+      "step": 276
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011630094043887148,
+      "loss": 1.5824,
+      "step": 277
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011598746081504704,
+      "loss": 1.5442,
+      "step": 278
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011567398119122257,
+      "loss": 1.322,
+      "step": 279
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011536050156739812,
+      "loss": 1.6088,
+      "step": 280
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.3828775882720947,
+      "eval_runtime": 866.9525,
+      "eval_samples_per_second": 1.159,
+      "eval_steps_per_second": 1.159,
+      "step": 280
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011504702194357367,
+      "loss": 1.2647,
+      "step": 281
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011473354231974922,
+      "loss": 1.6157,
+      "step": 282
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011442006269592478,
+      "loss": 1.6007,
+      "step": 283
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011410658307210031,
+      "loss": 1.7898,
+      "step": 284
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011379310344827588,
+      "loss": 1.2325,
+      "step": 285
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011347962382445141,
+      "loss": 1.2579,
+      "step": 286
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011316614420062696,
+      "loss": 1.3584,
+      "step": 287
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011285266457680251,
+      "loss": 1.3461,
+      "step": 288
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011253918495297806,
+      "loss": 1.1491,
+      "step": 289
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011222570532915362,
+      "loss": 1.4842,
+      "step": 290
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011191222570532915,
+      "loss": 1.1456,
+      "step": 291
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011159874608150471,
+      "loss": 1.1362,
+      "step": 292
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011128526645768025,
+      "loss": 1.591,
+      "step": 293
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001109717868338558,
+      "loss": 1.5453,
+      "step": 294
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011065830721003134,
+      "loss": 1.6698,
+      "step": 295
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001103448275862069,
+      "loss": 1.9426,
+      "step": 296
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011003134796238246,
+      "loss": 1.4073,
+      "step": 297
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010971786833855799,
+      "loss": 0.9123,
+      "step": 298
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010940438871473355,
+      "loss": 1.6831,
+      "step": 299
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.294,
+      "step": 300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010877742946708465,
+      "loss": 1.5178,
+      "step": 301
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001084639498432602,
+      "loss": 1.2052,
+      "step": 302
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010815047021943574,
+      "loss": 1.1377,
+      "step": 303
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010783699059561129,
+      "loss": 1.6875,
+      "step": 304
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010752351097178684,
+      "loss": 1.1238,
+      "step": 305
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010721003134796239,
+      "loss": 1.0325,
+      "step": 306
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010689655172413792,
+      "loss": 0.9661,
+      "step": 307
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010658307210031349,
+      "loss": 1.1979,
+      "step": 308
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010626959247648905,
+      "loss": 1.2015,
+      "step": 309
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010595611285266458,
+      "loss": 1.6322,
+      "step": 310
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010564263322884013,
+      "loss": 1.3118,
+      "step": 311
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010532915360501568,
+      "loss": 1.5565,
+      "step": 312
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010501567398119123,
+      "loss": 0.8889,
+      "step": 313
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010470219435736676,
+      "loss": 0.983,
+      "step": 314
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010438871473354232,
+      "loss": 1.3105,
+      "step": 315
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010407523510971788,
+      "loss": 1.2417,
+      "step": 316
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010376175548589342,
+      "loss": 1.1782,
+      "step": 317
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 1.5382,
+      "step": 318
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010313479623824452,
+      "loss": 1.3938,
+      "step": 319
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010282131661442008,
+      "loss": 0.9485,
+      "step": 320
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.3797812461853027,
+      "eval_runtime": 866.3779,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 320
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001025078369905956,
+      "loss": 1.5318,
+      "step": 321
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010219435736677116,
+      "loss": 1.5941,
+      "step": 322
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010188087774294672,
+      "loss": 1.5669,
+      "step": 323
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010156739811912226,
+      "loss": 1.409,
+      "step": 324
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010125391849529782,
+      "loss": 1.5028,
+      "step": 325
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010094043887147335,
+      "loss": 1.2918,
+      "step": 326
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001006269592476489,
+      "loss": 1.5101,
+      "step": 327
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010031347962382445,
+      "loss": 1.2542,
+      "step": 328
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001,
+      "loss": 1.3369,
+      "step": 329
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.968652037617555e-05,
+      "loss": 1.3911,
+      "step": 330
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.93730407523511e-05,
+      "loss": 1.3189,
+      "step": 331
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.905956112852665e-05,
+      "loss": 1.1879,
+      "step": 332
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.87460815047022e-05,
+      "loss": 1.4755,
+      "step": 333
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.843260188087775e-05,
+      "loss": 0.8884,
+      "step": 334
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.81191222570533e-05,
+      "loss": 1.4322,
+      "step": 335
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.780564263322885e-05,
+      "loss": 1.2872,
+      "step": 336
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.749216300940439e-05,
+      "loss": 1.717,
+      "step": 337
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.717868338557993e-05,
+      "loss": 1.4597,
+      "step": 338
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.686520376175549e-05,
+      "loss": 1.3438,
+      "step": 339
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 1.0354,
+      "step": 340
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.623824451410659e-05,
+      "loss": 1.8091,
+      "step": 341
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.592476489028213e-05,
+      "loss": 1.4617,
+      "step": 342
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.561128526645769e-05,
+      "loss": 1.4417,
+      "step": 343
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.529780564263323e-05,
+      "loss": 1.0994,
+      "step": 344
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.498432601880878e-05,
+      "loss": 1.1481,
+      "step": 345
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.467084639498433e-05,
+      "loss": 1.0104,
+      "step": 346
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.435736677115989e-05,
+      "loss": 1.0098,
+      "step": 347
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.404388714733543e-05,
+      "loss": 1.9093,
+      "step": 348
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.373040752351098e-05,
+      "loss": 0.9269,
+      "step": 349
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.341692789968652e-05,
+      "loss": 0.606,
+      "step": 350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.310344827586207e-05,
+      "loss": 1.5762,
+      "step": 351
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.278996865203762e-05,
+      "loss": 1.1424,
+      "step": 352
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.247648902821317e-05,
+      "loss": 1.6305,
+      "step": 353
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.216300940438872e-05,
+      "loss": 1.1738,
+      "step": 354
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.184952978056427e-05,
+      "loss": 0.973,
+      "step": 355
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.153605015673982e-05,
+      "loss": 1.4229,
+      "step": 356
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.122257053291536e-05,
+      "loss": 1.3226,
+      "step": 357
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 1.6308,
+      "step": 358
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.059561128526646e-05,
+      "loss": 1.5685,
+      "step": 359
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.028213166144202e-05,
+      "loss": 1.5146,
+      "step": 360
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.3761860132217407,
+      "eval_runtime": 866.1927,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 360
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.996865203761756e-05,
+      "loss": 1.333,
+      "step": 361
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 1.4217,
+      "step": 362
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.934169278996866e-05,
+      "loss": 1.2831,
+      "step": 363
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.90282131661442e-05,
+      "loss": 1.4965,
+      "step": 364
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.871473354231975e-05,
+      "loss": 1.5408,
+      "step": 365
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.84012539184953e-05,
+      "loss": 1.3491,
+      "step": 366
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.808777429467086e-05,
+      "loss": 1.2511,
+      "step": 367
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.77742946708464e-05,
+      "loss": 1.7709,
+      "step": 368
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.746081504702195e-05,
+      "loss": 1.4589,
+      "step": 369
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.71473354231975e-05,
+      "loss": 1.2527,
+      "step": 370
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.683385579937305e-05,
+      "loss": 1.483,
+      "step": 371
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.652037617554859e-05,
+      "loss": 1.0561,
+      "step": 372
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.620689655172413e-05,
+      "loss": 1.52,
+      "step": 373
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.58934169278997e-05,
+      "loss": 1.6113,
+      "step": 374
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.557993730407524e-05,
+      "loss": 1.6251,
+      "step": 375
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.526645768025079e-05,
+      "loss": 1.1801,
+      "step": 376
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.495297805642633e-05,
+      "loss": 1.2712,
+      "step": 377
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.463949843260189e-05,
+      "loss": 1.3207,
+      "step": 378
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.432601880877743e-05,
+      "loss": 1.7274,
+      "step": 379
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.401253918495299e-05,
+      "loss": 0.8838,
+      "step": 380
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.369905956112853e-05,
+      "loss": 1.5105,
+      "step": 381
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.338557993730409e-05,
+      "loss": 1.4059,
+      "step": 382
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.307210031347963e-05,
+      "loss": 1.4178,
+      "step": 383
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 1.513,
+      "step": 384
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.244514106583072e-05,
+      "loss": 0.773,
+      "step": 385
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.213166144200627e-05,
+      "loss": 1.5264,
+      "step": 386
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 1.2271,
+      "step": 387
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.150470219435737e-05,
+      "loss": 1.8335,
+      "step": 388
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.119122257053292e-05,
+      "loss": 1.333,
+      "step": 389
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.087774294670847e-05,
+      "loss": 1.0521,
+      "step": 390
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.056426332288402e-05,
+      "loss": 1.6083,
+      "step": 391
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.025078369905956e-05,
+      "loss": 1.3099,
+      "step": 392
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.993730407523512e-05,
+      "loss": 1.3217,
+      "step": 393
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.962382445141067e-05,
+      "loss": 1.5504,
+      "step": 394
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.931034482758621e-05,
+      "loss": 1.2699,
+      "step": 395
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.899686520376176e-05,
+      "loss": 0.8664,
+      "step": 396
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.86833855799373e-05,
+      "loss": 1.6929,
+      "step": 397
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.836990595611286e-05,
+      "loss": 1.2003,
+      "step": 398
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.80564263322884e-05,
+      "loss": 1.6811,
+      "step": 399
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.774294670846394e-05,
+      "loss": 1.6352,
+      "step": 400
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.3731473684310913,
+      "eval_runtime": 866.2054,
+      "eval_samples_per_second": 1.16,
+      "eval_steps_per_second": 1.16,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 648,
+  "num_train_epochs": 1,
+  "save_steps": 40,
+  "total_flos": 1.9141431690264576e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b8440b8d8e7bf2870506a7bf59a8cd8408e545cedbc53d234193e070ae3e4e
+size 4536