Upload 8 files

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.7.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2205ede55070eb384bceec5c6becf3d53bfb8a6c9c3bda218aefeb3f9f2ca5
+size 33571624

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 512,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1830 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.4673,
+      "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4e-05,
+      "loss": 0.4921,
+      "step": 2
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 6e-05,
+      "loss": 0.513,
+      "step": 3
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8e-05,
+      "loss": 0.4494,
+      "step": 4
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001,
+      "loss": 0.3777,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00012,
+      "loss": 0.3692,
+      "step": 6
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00014,
+      "loss": 0.3899,
+      "step": 7
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016,
+      "loss": 0.3349,
+      "step": 8
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00018,
+      "loss": 0.3956,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.417,
+      "step": 10
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00019999413227831132,
+      "loss": 0.3352,
+      "step": 11
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00019997652980184843,
+      "loss": 0.3709,
+      "step": 12
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00019994719463633997,
+      "loss": 0.3868,
+      "step": 13
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001999061302243977,
+      "loss": 0.3771,
+      "step": 14
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 0.2788,
+      "step": 15
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00019978883431348845,
+      "loss": 0.2897,
+      "step": 16
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0001997126165797167,
+      "loss": 0.2225,
+      "step": 17
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00019962469712828614,
+      "loss": 0.2778,
+      "step": 18
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0001995250862769342,
+      "loss": 0.2976,
+      "step": 19
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00019941379571543596,
+      "loss": 0.3287,
+      "step": 20
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00019929083850423225,
+      "loss": 0.2585,
+      "step": 21
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00019915622907289694,
+      "loss": 0.2322,
+      "step": 22
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00019900998321844367,
+      "loss": 0.2285,
+      "step": 23
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00019885211810347184,
+      "loss": 0.3068,
+      "step": 24
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00019868265225415265,
+      "loss": 0.184,
+      "step": 25
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00019850160555805486,
+      "loss": 0.2525,
+      "step": 26
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.000198308999261811,
+      "loss": 0.2629,
+      "step": 27
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.00019810485596862392,
+      "loss": 0.2774,
+      "step": 28
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00019788919963561422,
+      "loss": 0.2102,
+      "step": 29
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00019766205557100868,
+      "loss": 0.169,
+      "step": 30
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00019742345043117045,
+      "loss": 0.246,
+      "step": 31
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.00019717341221747056,
+      "loss": 0.233,
+      "step": 32
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.00019691197027300205,
+      "loss": 0.1728,
+      "step": 33
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.00019663915527913625,
+      "loss": 0.1657,
+      "step": 34
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0001963549992519223,
+      "loss": 0.1968,
+      "step": 35
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00019605953553832988,
+      "loss": 0.1797,
+      "step": 36
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.00019575279881233577,
+      "loss": 0.1904,
+      "step": 37
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00019543482507085482,
+      "loss": 0.2162,
+      "step": 38
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.1524,
+      "step": 39
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 0.1587,
+      "step": 40
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 0.00019441386147691335,
+      "loss": 0.1774,
+      "step": 41
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 0.0001940513259502924,
+      "loss": 0.1352,
+      "step": 42
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.0001936777530835689,
+      "loss": 0.1913,
+      "step": 43
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0001932931867171751,
+      "loss": 0.1578,
+      "step": 44
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00019289767198167916,
+      "loss": 0.2396,
+      "step": 45
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.0001924912552924889,
+      "loss": 0.095,
+      "step": 46
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 0.00019207398434440478,
+      "loss": 0.1376,
+      "step": 47
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 0.00019164590810602262,
+      "loss": 0.1483,
+      "step": 48
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.000191207076813987,
+      "loss": 0.1417,
+      "step": 49
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00019075754196709572,
+      "loss": 0.1373,
+      "step": 50
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 0.00019029735632025618,
+      "loss": 0.1883,
+      "step": 51
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.00018982657387829445,
+      "loss": 0.1106,
+      "step": 52
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.00018934524988961738,
+      "loss": 0.1231,
+      "step": 53
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 0.00018885344083972914,
+      "loss": 0.1112,
+      "step": 54
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.0001883512044446023,
+      "loss": 0.11,
+      "step": 55
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 0.00018783859964390464,
+      "loss": 0.1028,
+      "step": 56
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 0.0001873156865940823,
+      "loss": 0.1243,
+      "step": 57
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 0.00018678252666130013,
+      "loss": 0.1259,
+      "step": 58
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 0.0001862391824142402,
+      "loss": 0.1002,
+      "step": 59
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00018568571761675893,
+      "loss": 0.1718,
+      "step": 60
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.00018512219722040425,
+      "loss": 0.0951,
+      "step": 61
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.0001845486873567932,
+      "loss": 0.1086,
+      "step": 62
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 0.00018396525532985108,
+      "loss": 0.1299,
+      "step": 63
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.00018337196960791302,
+      "loss": 0.0888,
+      "step": 64
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 0.1316,
+      "step": 65
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 0.00018215611672609317,
+      "loss": 0.0862,
+      "step": 66
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 0.00018153369225193782,
+      "loss": 0.103,
+      "step": 67
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0748,
+      "step": 68
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 0.00018026021244992287,
+      "loss": 0.1113,
+      "step": 69
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00017960930657056438,
+      "loss": 0.0869,
+      "step": 70
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 0.0001789490581861102,
+      "loss": 0.0785,
+      "step": 71
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 0.00017827954477963557,
+      "loss": 0.0865,
+      "step": 72
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 0.0001776008449215073,
+      "loss": 0.0883,
+      "step": 73
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 0.0001769130382601629,
+      "loss": 0.093,
+      "step": 74
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.00017621620551276366,
+      "loss": 0.0576,
+      "step": 75
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 0.00017551042845572208,
+      "loss": 0.0695,
+      "step": 76
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 0.00017479578991510508,
+      "loss": 0.0664,
+      "step": 77
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 0.00017407237375691392,
+      "loss": 0.0609,
+      "step": 78
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 0.00017334026487724225,
+      "loss": 0.0686,
+      "step": 79
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0001725995491923131,
+      "loss": 0.1042,
+      "step": 80
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.00017185031362839626,
+      "loss": 0.055,
+      "step": 81
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 0.00017109264611160708,
+      "loss": 0.1005,
+      "step": 82
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 0.000170326635557588,
+      "loss": 0.0553,
+      "step": 83
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 0.00016955237186107387,
+      "loss": 0.0384,
+      "step": 84
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 0.00016876994588534234,
+      "loss": 0.0468,
+      "step": 85
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 0.0001679794494515508,
+      "loss": 0.0491,
+      "step": 86
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 0.00016718097532796063,
+      "loss": 0.0564,
+      "step": 87
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 0.00016637461721905045,
+      "loss": 0.0525,
+      "step": 88
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 0.0001655604697545196,
+      "loss": 0.0433,
+      "step": 89
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00016473862847818277,
+      "loss": 0.0525,
+      "step": 90
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 0.0001639091898367576,
+      "loss": 0.0422,
+      "step": 91
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 0.00016307225116854622,
+      "loss": 0.0319,
+      "step": 92
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 0.00016222791069201207,
+      "loss": 0.032,
+      "step": 93
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 0.00016137626749425377,
+      "loss": 0.0341,
+      "step": 94
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.00016051742151937655,
+      "loss": 0.0618,
+      "step": 95
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 0.00015965147355676343,
+      "loss": 0.0346,
+      "step": 96
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0387,
+      "step": 97
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.0001578986789811849,
+      "loss": 0.0453,
+      "step": 98
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 0.00015701203806643433,
+      "loss": 0.0313,
+      "step": 99
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00015611870653623825,
+      "loss": 0.0352,
+      "step": 100
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 0.00015521878922701246,
+      "loss": 0.0449,
+      "step": 101
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 0.00015431239174804328,
+      "loss": 0.0309,
+      "step": 102
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 0.00015339962046909364,
+      "loss": 0.0164,
+      "step": 103
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 0.00015248058250792008,
+      "loss": 0.0248,
+      "step": 104
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 0.00015155538571770218,
+      "loss": 0.0236,
+      "step": 105
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 0.0001506241386743854,
+      "loss": 0.023,
+      "step": 106
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 0.00014968695066393923,
+      "loss": 0.0203,
+      "step": 107
+    },
+    {
+      "epoch": 10.8,
+      "learning_rate": 0.00014874393166953192,
+      "loss": 0.0175,
+      "step": 108
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 0.00014779519235862365,
+      "loss": 0.024,
+      "step": 109
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.0385,
+      "step": 110
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 0.0001458809988006011,
+      "loss": 0.0117,
+      "step": 111
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 0.00014491576919258792,
+      "loss": 0.0188,
+      "step": 112
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 0.00014394526851991364,
+      "loss": 0.0198,
+      "step": 113
+    },
+    {
+      "epoch": 11.4,
+      "learning_rate": 0.0001429696106751352,
+      "loss": 0.0255,
+      "step": 114
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 0.0143,
+      "step": 115
+    },
+    {
+      "epoch": 11.6,
+      "learning_rate": 0.0001410032820521416,
+      "loss": 0.0218,
+      "step": 116
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 0.00014001284203130868,
+      "loss": 0.0213,
+      "step": 117
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 0.00013901770632605547,
+      "loss": 0.011,
+      "step": 118
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.0001380179917199692,
+      "loss": 0.0175,
+      "step": 119
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.00013701381553399145,
+      "loss": 0.0135,
+      "step": 120
+    },
+    {
+      "epoch": 12.1,
+      "learning_rate": 0.0001360052956126499,
+      "loss": 0.0114,
+      "step": 121
+    },
+    {
+      "epoch": 12.2,
+      "learning_rate": 0.00013499255031022885,
+      "loss": 0.0109,
+      "step": 122
+    },
+    {
+      "epoch": 12.3,
+      "learning_rate": 0.00013397569847687984,
+      "loss": 0.0119,
+      "step": 123
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 0.00013295485944467405,
+      "loss": 0.0074,
+      "step": 124
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.000131930153013598,
+      "loss": 0.0193,
+      "step": 125
+    },
+    {
+      "epoch": 12.6,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0175,
+      "step": 126
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 0.00012986961940995138,
+      "loss": 0.0112,
+      "step": 127
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 0.0001288340340501351,
+      "loss": 0.0192,
+      "step": 128
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 0.00012779506488857945,
+      "loss": 0.0113,
+      "step": 129
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.00012675283385292212,
+      "loss": 0.0075,
+      "step": 130
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 0.00012570746325359607,
+      "loss": 0.0054,
+      "step": 131
+    },
+    {
+      "epoch": 13.2,
+      "learning_rate": 0.00012465907576947622,
+      "loss": 0.0125,
+      "step": 132
+    },
+    {
+      "epoch": 13.3,
+      "learning_rate": 0.000123607794433482,
+      "loss": 0.0063,
+      "step": 133
+    },
+    {
+      "epoch": 13.4,
+      "learning_rate": 0.00012255374261813944,
+      "loss": 0.0087,
+      "step": 134
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 0.00012149704402110243,
+      "loss": 0.0093,
+      "step": 135
+    },
+    {
+      "epoch": 13.6,
+      "learning_rate": 0.0001204378226506365,
+      "loss": 0.0118,
+      "step": 136
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 0.00011937620281106585,
+      "loss": 0.0106,
+      "step": 137
+    },
+    {
+      "epoch": 13.8,
+      "learning_rate": 0.00011831230908818563,
+      "loss": 0.0164,
+      "step": 138
+    },
+    {
+      "epoch": 13.9,
+      "learning_rate": 0.00011724626633464127,
+      "loss": 0.0085,
+      "step": 139
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.0001161781996552765,
+      "loss": 0.0074,
+      "step": 140
+    },
+    {
+      "epoch": 14.1,
+      "learning_rate": 0.00011510823439245169,
+      "loss": 0.0036,
+      "step": 141
+    },
+    {
+      "epoch": 14.2,
+      "learning_rate": 0.00011403649611133444,
+      "loss": 0.0101,
+      "step": 142
+    },
+    {
+      "epoch": 14.3,
+      "learning_rate": 0.00011296311058516389,
+      "loss": 0.0072,
+      "step": 143
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 0.00011188820378049065,
+      "loss": 0.0094,
+      "step": 144
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 0.00011081190184239419,
+      "loss": 0.0063,
+      "step": 145
+    },
+    {
+      "epoch": 14.6,
+      "learning_rate": 0.00010973433107967902,
+      "loss": 0.0125,
+      "step": 146
+    },
+    {
+      "epoch": 14.7,
+      "learning_rate": 0.00010865561795005177,
+      "loss": 0.0047,
+      "step": 147
+    },
+    {
+      "epoch": 14.8,
+      "learning_rate": 0.00010757588904528106,
+      "loss": 0.0048,
+      "step": 148
+    },
+    {
+      "epoch": 14.9,
+      "learning_rate": 0.00010649527107634108,
+      "loss": 0.0037,
+      "step": 149
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.00010541389085854176,
+      "loss": 0.0048,
+      "step": 150
+    },
+    {
+      "epoch": 15.1,
+      "learning_rate": 0.00010433187529664623,
+      "loss": 0.0057,
+      "step": 151
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 0.00010324935136997806,
+      "loss": 0.0062,
+      "step": 152
+    },
+    {
+      "epoch": 15.3,
+      "learning_rate": 0.00010216644611751975,
+      "loss": 0.0056,
+      "step": 153
+    },
+    {
+      "epoch": 15.4,
+      "learning_rate": 0.000101083286623004,
+      "loss": 0.0055,
+      "step": 154
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 0.0001,
+      "loss": 0.0039,
+      "step": 155
+    },
+    {
+      "epoch": 15.6,
+      "learning_rate": 9.891671337699602e-05,
+      "loss": 0.004,
+      "step": 156
+    },
+    {
+      "epoch": 15.7,
+      "learning_rate": 9.783355388248027e-05,
+      "loss": 0.004,
+      "step": 157
+    },
+    {
+      "epoch": 15.8,
+      "learning_rate": 9.675064863002196e-05,
+      "loss": 0.0024,
+      "step": 158
+    },
+    {
+      "epoch": 15.9,
+      "learning_rate": 9.56681247033538e-05,
+      "loss": 0.0069,
+      "step": 159
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 9.458610914145826e-05,
+      "loss": 0.0027,
+      "step": 160
+    },
+    {
+      "epoch": 16.1,
+      "learning_rate": 9.350472892365892e-05,
+      "loss": 0.0036,
+      "step": 161
+    },
+    {
+      "epoch": 16.2,
+      "learning_rate": 9.242411095471897e-05,
+      "loss": 0.0024,
+      "step": 162
+    },
+    {
+      "epoch": 16.3,
+      "learning_rate": 9.134438204994824e-05,
+      "loss": 0.002,
+      "step": 163
+    },
+    {
+      "epoch": 16.4,
+      "learning_rate": 9.026566892032105e-05,
+      "loss": 0.0052,
+      "step": 164
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 0.0029,
+      "step": 165
+    },
+    {
+      "epoch": 16.6,
+      "learning_rate": 8.811179621950936e-05,
+      "loss": 0.0032,
+      "step": 166
+    },
+    {
+      "epoch": 16.7,
+      "learning_rate": 8.703688941483616e-05,
+      "loss": 0.0025,
+      "step": 167
+    },
+    {
+      "epoch": 16.8,
+      "learning_rate": 8.596350388866558e-05,
+      "loss": 0.0044,
+      "step": 168
+    },
+    {
+      "epoch": 16.9,
+      "learning_rate": 8.489176560754834e-05,
+      "loss": 0.0034,
+      "step": 169
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 8.382180034472353e-05,
+      "loss": 0.0042,
+      "step": 170
+    },
+    {
+      "epoch": 17.1,
+      "learning_rate": 8.275373366535877e-05,
+      "loss": 0.0031,
+      "step": 171
+    },
+    {
+      "epoch": 17.2,
+      "learning_rate": 8.168769091181438e-05,
+      "loss": 0.0024,
+      "step": 172
+    },
+    {
+      "epoch": 17.3,
+      "learning_rate": 8.062379718893417e-05,
+      "loss": 0.0037,
+      "step": 173
+    },
+    {
+      "epoch": 17.4,
+      "learning_rate": 7.956217734936353e-05,
+      "loss": 0.0014,
+      "step": 174
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 7.85029559788976e-05,
+      "loss": 0.0023,
+      "step": 175
+    },
+    {
+      "epoch": 17.6,
+      "learning_rate": 7.744625738186059e-05,
+      "loss": 0.0019,
+      "step": 176
+    },
+    {
+      "epoch": 17.7,
+      "learning_rate": 7.639220556651799e-05,
+      "loss": 0.0016,
+      "step": 177
+    },
+    {
+      "epoch": 17.8,
+      "learning_rate": 7.534092423052381e-05,
+      "loss": 0.0027,
+      "step": 178
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 7.42925367464039e-05,
+      "loss": 0.0018,
+      "step": 179
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 7.324716614707793e-05,
+      "loss": 0.002,
+      "step": 180
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 7.220493511142059e-05,
+      "loss": 0.002,
+      "step": 181
+    },
+    {
+      "epoch": 18.2,
+      "learning_rate": 7.116596594986494e-05,
+      "loss": 0.0009,
+      "step": 182
+    },
+    {
+      "epoch": 18.3,
+      "learning_rate": 7.013038059004866e-05,
+      "loss": 0.0013,
+      "step": 183
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0022,
+      "step": 184
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 6.806984698640202e-05,
+      "loss": 0.0017,
+      "step": 185
+    },
+    {
+      "epoch": 18.6,
+      "learning_rate": 6.704514055532598e-05,
+      "loss": 0.0026,
+      "step": 186
+    },
+    {
+      "epoch": 18.7,
+      "learning_rate": 6.602430152312017e-05,
+      "loss": 0.0017,
+      "step": 187
+    },
+    {
+      "epoch": 18.8,
+      "learning_rate": 6.500744968977116e-05,
+      "loss": 0.002,
+      "step": 188
+    },
+    {
+      "epoch": 18.9,
+      "learning_rate": 6.399470438735014e-05,
+      "loss": 0.001,
+      "step": 189
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 6.298618446600856e-05,
+      "loss": 0.0013,
+      "step": 190
+    },
+    {
+      "epoch": 19.1,
+      "learning_rate": 6.19820082800308e-05,
+      "loss": 0.0014,
+      "step": 191
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 6.0982293673944544e-05,
+      "loss": 0.0008,
+      "step": 192
+    },
+    {
+      "epoch": 19.3,
+      "learning_rate": 5.9987157968691344e-05,
+      "loss": 0.0009,
+      "step": 193
+    },
+    {
+      "epoch": 19.4,
+      "learning_rate": 5.899671794785839e-05,
+      "loss": 0.0007,
+      "step": 194
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 5.801108984397354e-05,
+      "loss": 0.0011,
+      "step": 195
+    },
+    {
+      "epoch": 19.6,
+      "learning_rate": 5.703038932486484e-05,
+      "loss": 0.0011,
+      "step": 196
+    },
+    {
+      "epoch": 19.7,
+      "learning_rate": 5.605473148008638e-05,
+      "loss": 0.002,
+      "step": 197
+    },
+    {
+      "epoch": 19.8,
+      "learning_rate": 5.5084230807412126e-05,
+      "loss": 0.0012,
+      "step": 198
+    },
+    {
+      "epoch": 19.9,
+      "learning_rate": 5.411900119939895e-05,
+      "loss": 0.0015,
+      "step": 199
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 5.3159155930021e-05,
+      "loss": 0.0021,
+      "step": 200
+    },
+    {
+      "epoch": 20.1,
+      "learning_rate": 5.2204807641376354e-05,
+      "loss": 0.0011,
+      "step": 201
+    },
+    {
+      "epoch": 20.2,
+      "learning_rate": 5.12560683304681e-05,
+      "loss": 0.0018,
+      "step": 202
+    },
+    {
+      "epoch": 20.3,
+      "learning_rate": 5.03130493360608e-05,
+      "loss": 0.0015,
+      "step": 203
+    },
+    {
+      "epoch": 20.4,
+      "learning_rate": 4.9375861325614606e-05,
+      "loss": 0.0011,
+      "step": 204
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 4.844461428229782e-05,
+      "loss": 0.0007,
+      "step": 205
+    },
+    {
+      "epoch": 20.6,
+      "learning_rate": 4.751941749207995e-05,
+      "loss": 0.0006,
+      "step": 206
+    },
+    {
+      "epoch": 20.7,
+      "learning_rate": 4.660037953090639e-05,
+      "loss": 0.0008,
+      "step": 207
+    },
+    {
+      "epoch": 20.8,
+      "learning_rate": 4.5687608251956714e-05,
+      "loss": 0.0013,
+      "step": 208
+    },
+    {
+      "epoch": 20.9,
+      "learning_rate": 4.4781210772987514e-05,
+      "loss": 0.0008,
+      "step": 209
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 4.388129346376178e-05,
+      "loss": 0.0012,
+      "step": 210
+    },
+    {
+      "epoch": 21.1,
+      "learning_rate": 4.298796193356566e-05,
+      "loss": 0.0012,
+      "step": 211
+    },
+    {
+      "epoch": 21.2,
+      "learning_rate": 4.210132101881516e-05,
+      "loss": 0.0009,
+      "step": 212
+    },
+    {
+      "epoch": 21.3,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0007,
+      "step": 213
+    },
+    {
+      "epoch": 21.4,
+      "learning_rate": 4.034852644323661e-05,
+      "loss": 0.0012,
+      "step": 214
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 3.94825784806235e-05,
+      "loss": 0.0013,
+      "step": 215
+    },
+    {
+      "epoch": 21.6,
+      "learning_rate": 3.862373250574626e-05,
+      "loss": 0.0009,
+      "step": 216
+    },
+    {
+      "epoch": 21.7,
+      "learning_rate": 3.7772089307987936e-05,
+      "loss": 0.0008,
+      "step": 217
+    },
+    {
+      "epoch": 21.8,
+      "learning_rate": 3.6927748831453836e-05,
+      "loss": 0.0009,
+      "step": 218
+    },
+    {
+      "epoch": 21.9,
+      "learning_rate": 3.6090810163242416e-05,
+      "loss": 0.0006,
+      "step": 219
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 3.526137152181723e-05,
+      "loss": 0.0009,
+      "step": 220
+    },
+    {
+      "epoch": 22.1,
+      "learning_rate": 3.44395302454804e-05,
+      "loss": 0.0009,
+      "step": 221
+    },
+    {
+      "epoch": 22.2,
+      "learning_rate": 3.362538278094957e-05,
+      "loss": 0.0012,
+      "step": 222
+    },
+    {
+      "epoch": 22.3,
+      "learning_rate": 3.28190246720394e-05,
+      "loss": 0.0005,
+      "step": 223
+    },
+    {
+      "epoch": 22.4,
+      "learning_rate": 3.202055054844921e-05,
+      "loss": 0.001,
+      "step": 224
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 3.123005411465766e-05,
+      "loss": 0.0007,
+      "step": 225
+    },
+    {
+      "epoch": 22.6,
+      "learning_rate": 3.0447628138926156e-05,
+      "loss": 0.0012,
+      "step": 226
+    },
+    {
+      "epoch": 22.7,
+      "learning_rate": 2.9673364442412e-05,
+      "loss": 0.0011,
+      "step": 227
+    },
+    {
+      "epoch": 22.8,
+      "learning_rate": 2.890735388839295e-05,
+      "loss": 0.0009,
+      "step": 228
+    },
+    {
+      "epoch": 22.9,
+      "learning_rate": 2.8149686371603767e-05,
+      "loss": 0.0005,
+      "step": 229
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 2.7400450807686952e-05,
+      "loss": 0.0007,
+      "step": 230
+    },
+    {
+      "epoch": 23.1,
+      "learning_rate": 2.665973512275778e-05,
+      "loss": 0.0008,
+      "step": 231
+    },
+    {
+      "epoch": 23.2,
+      "learning_rate": 2.59276262430861e-05,
+      "loss": 0.0007,
+      "step": 232
+    },
+    {
+      "epoch": 23.3,
+      "learning_rate": 2.520421008489493e-05,
+      "loss": 0.0007,
+      "step": 233
+    },
+    {
+      "epoch": 23.4,
+      "learning_rate": 2.4489571544277955e-05,
+      "loss": 0.0005,
+      "step": 234
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 2.3783794487236365e-05,
+      "loss": 0.0007,
+      "step": 235
+    },
+    {
+      "epoch": 23.6,
+      "learning_rate": 2.308696173983711e-05,
+      "loss": 0.0013,
+      "step": 236
+    },
+    {
+      "epoch": 23.7,
+      "learning_rate": 2.2399155078492708e-05,
+      "loss": 0.0012,
+      "step": 237
+    },
+    {
+      "epoch": 23.8,
+      "learning_rate": 2.1720455220364444e-05,
+      "loss": 0.0006,
+      "step": 238
+    },
+    {
+      "epoch": 23.9,
+      "learning_rate": 2.1050941813889836e-05,
+      "loss": 0.0012,
+      "step": 239
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.0390693429435627e-05,
+      "loss": 0.0005,
+      "step": 240
+    },
+    {
+      "epoch": 24.1,
+      "learning_rate": 1.9739787550077116e-05,
+      "loss": 0.0007,
+      "step": 241
+    },
+    {
+      "epoch": 24.2,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0006,
+      "step": 242
+    },
+    {
+      "epoch": 24.3,
+      "learning_rate": 1.8466307748062205e-05,
+      "loss": 0.0015,
+      "step": 243
+    },
+    {
+      "epoch": 24.4,
+      "learning_rate": 1.784388327390687e-05,
+      "loss": 0.0008,
+      "step": 244
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 1.7231100184310956e-05,
+      "loss": 0.0008,
+      "step": 245
+    },
+    {
+      "epoch": 24.6,
+      "learning_rate": 1.6628030392087e-05,
+      "loss": 0.0006,
+      "step": 246
+    },
+    {
+      "epoch": 24.7,
+      "learning_rate": 1.6034744670148972e-05,
+      "loss": 0.0005,
+      "step": 247
+    },
+    {
+      "epoch": 24.8,
+      "learning_rate": 1.5451312643206827e-05,
+      "loss": 0.0011,
+      "step": 248
+    },
+    {
+      "epoch": 24.9,
+      "learning_rate": 1.4877802779595762e-05,
+      "loss": 0.0005,
+      "step": 249
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 1.4314282383241096e-05,
+      "loss": 0.0008,
+      "step": 250
+    },
+    {
+      "epoch": 25.1,
+      "learning_rate": 1.376081758575981e-05,
+      "loss": 0.0006,
+      "step": 251
+    },
+    {
+      "epoch": 25.2,
+      "learning_rate": 1.3217473338699859e-05,
+      "loss": 0.0005,
+      "step": 252
+    },
+    {
+      "epoch": 25.3,
+      "learning_rate": 1.2684313405917703e-05,
+      "loss": 0.0007,
+      "step": 253
+    },
+    {
+      "epoch": 25.4,
+      "learning_rate": 1.2161400356095375e-05,
+      "loss": 0.0006,
+      "step": 254
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 1.1648795555397707e-05,
+      "loss": 0.0006,
+      "step": 255
+    },
+    {
+      "epoch": 25.6,
+      "learning_rate": 1.1146559160270875e-05,
+      "loss": 0.0007,
+      "step": 256
+    },
+    {
+      "epoch": 25.7,
+      "learning_rate": 1.0654750110382628e-05,
+      "loss": 0.0005,
+      "step": 257
+    },
+    {
+      "epoch": 25.8,
+      "learning_rate": 1.0173426121705576e-05,
+      "loss": 0.0017,
+      "step": 258
+    },
+    {
+      "epoch": 25.9,
+      "learning_rate": 9.702643679743817e-06,
+      "loss": 0.0011,
+      "step": 259
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 9.242458032904311e-06,
+      "loss": 0.0005,
+      "step": 260
+    },
+    {
+      "epoch": 26.1,
+      "learning_rate": 8.792923186013024e-06,
+      "loss": 0.001,
+      "step": 261
+    },
+    {
+      "epoch": 26.2,
+      "learning_rate": 8.354091893977401e-06,
+      "loss": 0.0005,
+      "step": 262
+    },
+    {
+      "epoch": 26.3,
+      "learning_rate": 7.926015655595254e-06,
+      "loss": 0.0007,
+      "step": 263
+    },
+    {
+      "epoch": 26.4,
+      "learning_rate": 7.508744707511117e-06,
+      "loss": 0.0012,
+      "step": 264
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 7.102328018320858e-06,
+      "loss": 0.0005,
+      "step": 265
+    },
+    {
+      "epoch": 26.6,
+      "learning_rate": 6.70681328282492e-06,
+      "loss": 0.001,
+      "step": 266
+    },
+    {
+      "epoch": 26.7,
+      "learning_rate": 6.322246916431107e-06,
+      "loss": 0.0005,
+      "step": 267
+    },
+    {
+      "epoch": 26.8,
+      "learning_rate": 5.948674049707603e-06,
+      "loss": 0.0005,
+      "step": 268
+    },
+    {
+      "epoch": 26.9,
+      "learning_rate": 5.58613852308667e-06,
+      "loss": 0.0011,
+      "step": 269
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 5.2346828817197655e-06,
+      "loss": 0.0004,
+      "step": 270
+    },
+    {
+      "epoch": 27.1,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0008,
+      "step": 271
+    },
+    {
+      "epoch": 27.2,
+      "learning_rate": 4.565174929145188e-06,
+      "loss": 0.0007,
+      "step": 272
+    },
+    {
+      "epoch": 27.3,
+      "learning_rate": 4.247201187664218e-06,
+      "loss": 0.0009,
+      "step": 273
+    },
+    {
+      "epoch": 27.4,
+      "learning_rate": 3.940464461670135e-06,
+      "loss": 0.0015,
+      "step": 274
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 3.6450007480777093e-06,
+      "loss": 0.0004,
+      "step": 275
+    },
+    {
+      "epoch": 27.6,
+      "learning_rate": 3.360844720863765e-06,
+      "loss": 0.0005,
+      "step": 276
+    },
+    {
+      "epoch": 27.7,
+      "learning_rate": 3.0880297269979653e-06,
+      "loss": 0.001,
+      "step": 277
+    },
+    {
+      "epoch": 27.8,
+      "learning_rate": 2.826587782529444e-06,
+      "loss": 0.0006,
+      "step": 278
+    },
+    {
+      "epoch": 27.9,
+      "learning_rate": 2.576549568829578e-06,
+      "loss": 0.0005,
+      "step": 279
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 2.3379444289913342e-06,
+      "loss": 0.0005,
+      "step": 280
+    },
+    {
+      "epoch": 28.1,
+      "learning_rate": 2.110800364385812e-06,
+      "loss": 0.0005,
+      "step": 281
+    },
+    {
+      "epoch": 28.2,
+      "learning_rate": 1.8951440313760837e-06,
+      "loss": 0.0011,
+      "step": 282
+    },
+    {
+      "epoch": 28.3,
+      "learning_rate": 1.6910007381890081e-06,
+      "loss": 0.0013,
+      "step": 283
+    },
+    {
+      "epoch": 28.4,
+      "learning_rate": 1.4983944419451613e-06,
+      "loss": 0.0005,
+      "step": 284
+    },
+    {
+      "epoch": 28.5,
+      "learning_rate": 1.317347745847386e-06,
+      "loss": 0.0004,
+      "step": 285
+    },
+    {
+      "epoch": 28.6,
+      "learning_rate": 1.1478818965281911e-06,
+      "loss": 0.0007,
+      "step": 286
+    },
+    {
+      "epoch": 28.7,
+      "learning_rate": 9.900167815563465e-07,
+      "loss": 0.0006,
+      "step": 287
+    },
+    {
+      "epoch": 28.8,
+      "learning_rate": 8.437709271030603e-07,
+      "loss": 0.0009,
+      "step": 288
+    },
+    {
+      "epoch": 28.9,
+      "learning_rate": 7.091614957677517e-07,
+      "loss": 0.0006,
+      "step": 289
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 5.862042845640403e-07,
+      "loss": 0.0006,
+      "step": 290
+    },
+    {
+      "epoch": 29.1,
+      "learning_rate": 4.7491372306580627e-07,
+      "loss": 0.0007,
+      "step": 291
+    },
+    {
+      "epoch": 29.2,
+      "learning_rate": 3.7530287171387843e-07,
+      "loss": 0.0005,
+      "step": 292
+    },
+    {
+      "epoch": 29.3,
+      "learning_rate": 2.873834202833159e-07,
+      "loss": 0.0005,
+      "step": 293
+    },
+    {
+      "epoch": 29.4,
+      "learning_rate": 2.1116568651156076e-07,
+      "loss": 0.0011,
+      "step": 294
+    },
+    {
+      "epoch": 29.5,
+      "learning_rate": 1.4665861488761813e-07,
+      "loss": 0.0009,
+      "step": 295
+    },
+    {
+      "epoch": 29.6,
+      "learning_rate": 9.386977560232879e-08,
+      "loss": 0.0007,
+      "step": 296
+    },
+    {
+      "epoch": 29.7,
+      "learning_rate": 5.2805363660046734e-08,
+      "loss": 0.0004,
+      "step": 297
+    },
+    {
+      "epoch": 29.8,
+      "learning_rate": 2.347019815158724e-08,
+      "loss": 0.0007,
+      "step": 298
+    },
+    {
+      "epoch": 29.9,
+      "learning_rate": 5.867721688690431e-09,
+      "loss": 0.0005,
+      "step": 299
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.0,
+      "loss": 0.0012,
+      "step": 300
+    },
+    {
+      "epoch": 30.0,
+      "step": 300,
+      "total_flos": 4.8779437400064e+16,
+      "train_loss": 0.06055552892871977,
+      "train_runtime": 2678.0048,
+      "train_samples_per_second": 0.896,
+      "train_steps_per_second": 0.112
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 4.8779437400064e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd1ff2662ea6e1ce9f61c06a04042e811d727cda68688c9974ca81b2da642b1
+size 4728