Upload 19 files

README.md

@@ -1,3 +1,208 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: meta-llama/Llama-2-7b
 ---
+
+# 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
+
+
+### Framework versions
+
+
+- PEFT 0.6.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f5e1f6b4f1d0f96c14aec0a124ee6867902f1e2e939e2565a045e4da47b831
+size 16822989

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8444677690e53ddb99a8f6f895cccb85ace8b6f385b55c7d5e85a62949984f
+size 33661637

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8251d8f2b0fc0cd0c0d56e2beb546eb9d3b4156fea129e91f75ca4c14a2931fa
+size 21687

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8530960ee052ed37301950c215da1cc034198cfb1659240a9f775ee3f9243c29
+size 21687

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a99bc7161b8a3f49a75902cb67c3bec844650d768bf96d5f61c103978d23016
+size 21687

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779d33845dcd2509de12044f457f5df70d1c4456d7acbd2ae6dbf99df02e82b5
+size 21687

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7db5487a729d03070fa47b053aadb513c2a808e5f486449c82652e5d1f99abf
+size 21687

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29da6fca89711eeb0c506a92e0fbfbeed7c24a9eabb8067c33fd39f985560fa
+size 21687

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b9484dbf00daa2647852b1f6eb4c9ec993309824045af6768e41c4ae9580a9
+size 21687

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a842f826ca55e42c7ef2034d963b73cbdcac887f3512db1af34850e9f474be1
+size 21687

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce26047232a7fdc322fc0d9c90224b0fa0a830b4792d534b7ea0a4c861a5843
+size 627

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,1843 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.7007369822924607,
+  "eval_steps": 500,
+  "global_step": 1520000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9999270159623114e-05,
+      "loss": 0.1271,
+      "step": 5000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.999707892753202e-05,
+      "loss": 0.0859,
+      "step": 10000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9993426431557147e-05,
+      "loss": 0.0768,
+      "step": 15000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9988311715921104e-05,
+      "loss": 0.0727,
+      "step": 20000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9981738587426694e-05,
+      "loss": 0.0693,
+      "step": 25000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.997370216884145e-05,
+      "loss": 0.0677,
+      "step": 30000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9964207314440955e-05,
+      "loss": 0.0659,
+      "step": 35000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.995325311774524e-05,
+      "loss": 0.0657,
+      "step": 40000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.994084284853358e-05,
+      "loss": 0.0638,
+      "step": 45000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.992697226521413e-05,
+      "loss": 0.0623,
+      "step": 50000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.991164130374091e-05,
+      "loss": 0.0615,
+      "step": 55000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.9894856993903285e-05,
+      "loss": 0.0608,
+      "step": 60000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.987661739580889e-05,
+      "loss": 0.0604,
+      "step": 65000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.985691948992265e-05,
+      "loss": 0.0599,
+      "step": 70000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.983577230843278e-05,
+      "loss": 0.0591,
+      "step": 75000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.981317329262237e-05,
+      "loss": 0.0586,
+      "step": 80000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9789118806694247e-05,
+      "loss": 0.0587,
+      "step": 85000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.976361988048301e-05,
+      "loss": 0.0576,
+      "step": 90000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9736673337793535e-05,
+      "loss": 0.0576,
+      "step": 95000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.970828075385029e-05,
+      "loss": 0.0566,
+      "step": 100000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.967844378840947e-05,
+      "loss": 0.0567,
+      "step": 105000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.964715778300843e-05,
+      "loss": 0.0567,
+      "step": 110000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.961443708338981e-05,
+      "loss": 0.0568,
+      "step": 115000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.9580277488129266e-05,
+      "loss": 0.057,
+      "step": 120000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.954467372832107e-05,
+      "loss": 0.0551,
+      "step": 125000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.9507634576843017e-05,
+      "loss": 0.0549,
+      "step": 130000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.9469185717167566e-05,
+      "loss": 0.0563,
+      "step": 135000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.942928322246712e-05,
+      "loss": 0.0546,
+      "step": 140000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.938796049480949e-05,
+      "loss": 0.0538,
+      "step": 145000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.934520341515526e-05,
+      "loss": 0.0548,
+      "step": 150000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.930104056921508e-05,
+      "loss": 0.0541,
+      "step": 155000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.925543918835136e-05,
+      "loss": 0.0543,
+      "step": 160000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.920843842545973e-05,
+      "loss": 0.0538,
+      "step": 165000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.9160003406180696e-05,
+      "loss": 0.0539,
+      "step": 170000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.9110165603726345e-05,
+      "loss": 0.0536,
+      "step": 175000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.9058918384022446e-05,
+      "loss": 0.0537,
+      "step": 180000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.900625406738267e-05,
+      "loss": 0.0535,
+      "step": 185000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.895219680226333e-05,
+      "loss": 0.0527,
+      "step": 190000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.889673935433758e-05,
+      "loss": 0.0538,
+      "step": 195000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.8839896480432604e-05,
+      "loss": 0.0531,
+      "step": 200000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.878163695931812e-05,
+      "loss": 0.0527,
+      "step": 205000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.872198666951938e-05,
+      "loss": 0.0531,
+      "step": 210000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.8660961447879297e-05,
+      "loss": 0.0524,
+      "step": 215000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.859854044346287e-05,
+      "loss": 0.0527,
+      "step": 220000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.853475227851366e-05,
+      "loss": 0.0523,
+      "step": 225000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.8469588333473586e-05,
+      "loss": 0.0524,
+      "step": 230000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.8403052417656516e-05,
+      "loss": 0.0521,
+      "step": 235000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.833514842057813e-05,
+      "loss": 0.0518,
+      "step": 240000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.826586631633889e-05,
+      "loss": 0.052,
+      "step": 245000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.8195237873239866e-05,
+      "loss": 0.0525,
+      "step": 250000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.8123253497174505e-05,
+      "loss": 0.0514,
+      "step": 255000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.804991739616124e-05,
+      "loss": 0.0515,
+      "step": 260000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.7975233857236826e-05,
+      "loss": 0.0524,
+      "step": 265000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.789920724620569e-05,
+      "loss": 0.0506,
+      "step": 270000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.7821857620213536e-05,
+      "loss": 0.0513,
+      "step": 275000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.774314266334363e-05,
+      "loss": 0.0513,
+      "step": 280000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7663097669746146e-05,
+      "loss": 0.0512,
+      "step": 285000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.75817437300597e-05,
+      "loss": 0.0508,
+      "step": 290000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.749905304748714e-05,
+      "loss": 0.0515,
+      "step": 295000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.741504660273818e-05,
+      "loss": 0.0504,
+      "step": 300000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.732974650620106e-05,
+      "loss": 0.0504,
+      "step": 305000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.724315852930218e-05,
+      "loss": 0.0506,
+      "step": 310000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.715523536004309e-05,
+      "loss": 0.0496,
+      "step": 315000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.706605248838939e-05,
+      "loss": 0.0503,
+      "step": 320000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.697554374104222e-05,
+      "loss": 0.0504,
+      "step": 325000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.6883749846751347e-05,
+      "loss": 0.05,
+      "step": 330000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.679069491976989e-05,
+      "loss": 0.0497,
+      "step": 335000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.6696347165338586e-05,
+      "loss": 0.0503,
+      "step": 340000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.660074984524773e-05,
+      "loss": 0.0503,
+      "step": 345000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.650388980179216e-05,
+      "loss": 0.0493,
+      "step": 350000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.6405752940483196e-05,
+      "loss": 0.0503,
+      "step": 355000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.6306384260551005e-05,
+      "loss": 0.0502,
+      "step": 360000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.620577006509662e-05,
+      "loss": 0.0493,
+      "step": 365000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.6103916235762854e-05,
+      "loss": 0.05,
+      "step": 370000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.600082872665831e-05,
+      "loss": 0.0492,
+      "step": 375000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.589651356400925e-05,
+      "loss": 0.0499,
+      "step": 380000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5790976845807375e-05,
+      "loss": 0.0492,
+      "step": 385000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.568422474145333e-05,
+      "loss": 0.0496,
+      "step": 390000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.5576241769938385e-05,
+      "loss": 0.0496,
+      "step": 395000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.5467099406767963e-05,
+      "loss": 0.0491,
+      "step": 400000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.535671666878825e-05,
+      "loss": 0.0492,
+      "step": 405000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.52451883295289e-05,
+      "loss": 0.049,
+      "step": 410000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.513245430925934e-05,
+      "loss": 0.048,
+      "step": 415000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.5018543398343515e-05,
+      "loss": 0.0472,
+      "step": 420000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.4903415971499975e-05,
+      "loss": 0.0463,
+      "step": 425000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.47871708602701e-05,
+      "loss": 0.047,
+      "step": 430000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.46697926477584e-05,
+      "loss": 0.0472,
+      "step": 435000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.455119354756587e-05,
+      "loss": 0.0466,
+      "step": 440000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.443154687048235e-05,
+      "loss": 0.047,
+      "step": 445000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.4310692318277604e-05,
+      "loss": 0.047,
+      "step": 450000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.418870846171951e-05,
+      "loss": 0.047,
+      "step": 455000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.406562717238809e-05,
+      "loss": 0.0462,
+      "step": 460000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.394145631643063e-05,
+      "loss": 0.0471,
+      "step": 465000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.381615345463161e-05,
+      "loss": 0.0475,
+      "step": 470000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 4.368972524944734e-05,
+      "loss": 0.0467,
+      "step": 475000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.3562229672692154e-05,
+      "loss": 0.0467,
+      "step": 480000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.3433674830975235e-05,
+      "loss": 0.0463,
+      "step": 485000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 4.3303990737414704e-05,
+      "loss": 0.0463,
+      "step": 490000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 4.317326247486547e-05,
+      "loss": 0.0466,
+      "step": 495000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.304147185090266e-05,
+      "loss": 0.0463,
+      "step": 500000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.290859988496148e-05,
+      "loss": 0.0466,
+      "step": 505000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.277470750354905e-05,
+      "loss": 0.0461,
+      "step": 510000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.263980315969459e-05,
+      "loss": 0.0463,
+      "step": 515000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 4.250381343966794e-05,
+      "loss": 0.0463,
+      "step": 520000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.236680008297452e-05,
+      "loss": 0.0467,
+      "step": 525000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.222879881460605e-05,
+      "loss": 0.046,
+      "step": 530000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 4.2089790395700444e-05,
+      "loss": 0.0465,
+      "step": 535000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 4.194978295232646e-05,
+      "loss": 0.0471,
+      "step": 540000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.180875635941759e-05,
+      "loss": 0.046,
+      "step": 545000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.1666746777322316e-05,
+      "loss": 0.0463,
+      "step": 550000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.1523819909804684e-05,
+      "loss": 0.0464,
+      "step": 555000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.1379869705757123e-05,
+      "loss": 0.0462,
+      "step": 560000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.123501975940446e-05,
+      "loss": 0.0466,
+      "step": 565000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.108916259272307e-05,
+      "loss": 0.0462,
+      "step": 570000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.094239397826731e-05,
+      "loss": 0.0471,
+      "step": 575000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.079466376852837e-05,
+      "loss": 0.0456,
+      "step": 580000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.064606953152425e-05,
+      "loss": 0.0459,
+      "step": 585000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.049653102158943e-05,
+      "loss": 0.0464,
+      "step": 590000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 4.034608662496395e-05,
+      "loss": 0.0453,
+      "step": 595000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 4.019474513623393e-05,
+      "loss": 0.0466,
+      "step": 600000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 4.004248485601213e-05,
+      "loss": 0.046,
+      "step": 605000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.9889375601035114e-05,
+      "loss": 0.0454,
+      "step": 610000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.973536505734094e-05,
+      "loss": 0.0456,
+      "step": 615000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.958049277800142e-05,
+      "loss": 0.045,
+      "step": 620000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 3.94248302918014e-05,
+      "loss": 0.0452,
+      "step": 625000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.9268262097860184e-05,
+      "loss": 0.0458,
+      "step": 630000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.911089105446822e-05,
+      "loss": 0.0455,
+      "step": 635000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.895269512527556e-05,
+      "loss": 0.0453,
+      "step": 640000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 3.879368355800267e-05,
+      "loss": 0.0459,
+      "step": 645000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.863386564805006e-05,
+      "loss": 0.0458,
+      "step": 650000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 3.8473250737954924e-05,
+      "loss": 0.0452,
+      "step": 655000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.831181584524374e-05,
+      "loss": 0.046,
+      "step": 660000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.8149602467155784e-05,
+      "loss": 0.0454,
+      "step": 665000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.7986652769317283e-05,
+      "loss": 0.0454,
+      "step": 670000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.782291107551002e-05,
+      "loss": 0.0455,
+      "step": 675000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.7658452467105766e-05,
+      "loss": 0.0453,
+      "step": 680000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.7493287004972016e-05,
+      "loss": 0.0461,
+      "step": 685000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.7327324967260834e-05,
+      "loss": 0.045,
+      "step": 690000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.716067543266813e-05,
+      "loss": 0.0453,
+      "step": 695000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.6993281460825346e-05,
+      "loss": 0.0454,
+      "step": 700000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.682521980780319e-05,
+      "loss": 0.0455,
+      "step": 705000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.665646688334596e-05,
+      "loss": 0.0445,
+      "step": 710000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.648706652022939e-05,
+      "loss": 0.0448,
+      "step": 715000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.631692671937868e-05,
+      "loss": 0.0444,
+      "step": 720000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.6146125095823744e-05,
+      "loss": 0.0449,
+      "step": 725000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.597474036228449e-05,
+      "loss": 0.0453,
+      "step": 730000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.580264535204181e-05,
+      "loss": 0.0447,
+      "step": 735000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.562995320943442e-05,
+      "loss": 0.0441,
+      "step": 740000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.545660492947155e-05,
+      "loss": 0.0448,
+      "step": 745000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.52826799984853e-05,
+      "loss": 0.0442,
+      "step": 750000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.510818894752436e-05,
+      "loss": 0.044,
+      "step": 755000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.49330721388963e-05,
+      "loss": 0.044,
+      "step": 760000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.4757339457867414e-05,
+      "loss": 0.0444,
+      "step": 765000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.4581071484102234e-05,
+      "loss": 0.0435,
+      "step": 770000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.440424342594606e-05,
+      "loss": 0.0436,
+      "step": 775000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.4226865620304894e-05,
+      "loss": 0.0444,
+      "step": 780000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 3.404891278526875e-05,
+      "loss": 0.0442,
+      "step": 785000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.387046651852148e-05,
+      "loss": 0.0446,
+      "step": 790000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.369146584901852e-05,
+      "loss": 0.045,
+      "step": 795000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.3511992854912975e-05,
+      "loss": 0.044,
+      "step": 800000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.333205832954606e-05,
+      "loss": 0.0439,
+      "step": 805000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.315152846675856e-05,
+      "loss": 0.0447,
+      "step": 810000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.2970630450412766e-05,
+      "loss": 0.0439,
+      "step": 815000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.2789230337843214e-05,
+      "loss": 0.0438,
+      "step": 820000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 3.2607374887231645e-05,
+      "loss": 0.0414,
+      "step": 825000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 3.24251112477632e-05,
+      "loss": 0.0411,
+      "step": 830000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 3.22423405210557e-05,
+      "loss": 0.0409,
+      "step": 835000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 3.2059146256623924e-05,
+      "loss": 0.0403,
+      "step": 840000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 3.187561270645646e-05,
+      "loss": 0.0407,
+      "step": 845000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 3.169164053812308e-05,
+      "loss": 0.0406,
+      "step": 850000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 3.1507240268131666e-05,
+      "loss": 0.0412,
+      "step": 855000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 3.1322459449652304e-05,
+      "loss": 0.0406,
+      "step": 860000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 3.113734596258391e-05,
+      "loss": 0.0407,
+      "step": 865000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.095187370231551e-05,
+      "loss": 0.0406,
+      "step": 870000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.076605351107057e-05,
+      "loss": 0.0412,
+      "step": 875000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.057989625141167e-05,
+      "loss": 0.0407,
+      "step": 880000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.0393412805605544e-05,
+      "loss": 0.0414,
+      "step": 885000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.0206576669471674e-05,
+      "loss": 0.0409,
+      "step": 890000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.0019473514002417e-05,
+      "loss": 0.0411,
+      "step": 895000
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 2.983207693323402e-05,
+      "loss": 0.0405,
+      "step": 900000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 2.9644397881880708e-05,
+      "loss": 0.0409,
+      "step": 905000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.9456447331169147e-05,
+      "loss": 0.0408,
+      "step": 910000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.9268236268197174e-05,
+      "loss": 0.041,
+      "step": 915000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.90797756952915e-05,
+      "loss": 0.0413,
+      "step": 920000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.8891038851321416e-05,
+      "loss": 0.0412,
+      "step": 925000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.8702150101270274e-05,
+      "loss": 0.041,
+      "step": 930000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.8512969290515646e-05,
+      "loss": 0.0408,
+      "step": 935000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.832358303857603e-05,
+      "loss": 0.041,
+      "step": 940000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.8134040363313168e-05,
+      "loss": 0.0409,
+      "step": 945000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.7944276502291256e-05,
+      "loss": 0.041,
+      "step": 950000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.775437846896827e-05,
+      "loss": 0.04,
+      "step": 955000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.756435746426503e-05,
+      "loss": 0.04,
+      "step": 960000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.73741104713839e-05,
+      "loss": 0.0406,
+      "step": 965000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.718376273659552e-05,
+      "loss": 0.0401,
+      "step": 970000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.699332546709509e-05,
+      "loss": 0.0401,
+      "step": 975000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.680269543053059e-05,
+      "loss": 0.0391,
+      "step": 980000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.6612036299970488e-05,
+      "loss": 0.0402,
+      "step": 985000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.6421168424917686e-05,
+      "loss": 0.0403,
+      "step": 990000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.623033199888022e-05,
+      "loss": 0.0401,
+      "step": 995000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.6039385468590504e-05,
+      "loss": 0.0396,
+      "step": 1000000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.5848339956464096e-05,
+      "loss": 0.0398,
+      "step": 1005000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.5657283063641474e-05,
+      "loss": 0.0401,
+      "step": 1010000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.5466225985224508e-05,
+      "loss": 0.04,
+      "step": 1015000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2.5275103421570534e-05,
+      "loss": 0.0398,
+      "step": 1020000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5083926532199688e-05,
+      "loss": 0.0398,
+      "step": 1025000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 2.4892821222247636e-05,
+      "loss": 0.04,
+      "step": 1030000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 2.4701607451032485e-05,
+      "loss": 0.0402,
+      "step": 1035000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.4510525847347732e-05,
+      "loss": 0.0398,
+      "step": 1040000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 2.4319434615660547e-05,
+      "loss": 0.0404,
+      "step": 1045000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.4128383168046513e-05,
+      "loss": 0.0402,
+      "step": 1050000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.3937306253792384e-05,
+      "loss": 0.0397,
+      "step": 1055000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.3746367903542062e-05,
+      "loss": 0.0402,
+      "step": 1060000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.355550283734671e-05,
+      "loss": 0.0393,
+      "step": 1065000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.3364684050478952e-05,
+      "loss": 0.0397,
+      "step": 1070000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.3173999040117696e-05,
+      "loss": 0.0394,
+      "step": 1075000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.29834207729988e-05,
+      "loss": 0.039,
+      "step": 1080000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.2792922295048335e-05,
+      "loss": 0.0393,
+      "step": 1085000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.2602629024425966e-05,
+      "loss": 0.039,
+      "step": 1090000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.2412437803062146e-05,
+      "loss": 0.0394,
+      "step": 1095000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.2222359836495102e-05,
+      "loss": 0.0389,
+      "step": 1100000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.2032520255937674e-05,
+      "loss": 0.0392,
+      "step": 1105000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.1842816139163587e-05,
+      "loss": 0.039,
+      "step": 1110000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.1653258683231724e-05,
+      "loss": 0.0392,
+      "step": 1115000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.1463934806956023e-05,
+      "loss": 0.039,
+      "step": 1120000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.1274817639807107e-05,
+      "loss": 0.0393,
+      "step": 1125000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.1085918237080158e-05,
+      "loss": 0.0393,
+      "step": 1130000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.0897285366938386e-05,
+      "loss": 0.0389,
+      "step": 1135000
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.0708816881777654e-05,
+      "loss": 0.0386,
+      "step": 1140000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.052059934835373e-05,
+      "loss": 0.0387,
+      "step": 1145000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.0332718917197323e-05,
+      "loss": 0.0387,
+      "step": 1150000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.0145036181854185e-05,
+      "loss": 0.0386,
+      "step": 1155000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.9957712284869015e-05,
+      "loss": 0.0388,
+      "step": 1160000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.9770645630812195e-05,
+      "loss": 0.0385,
+      "step": 1165000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.958384733531826e-05,
+      "loss": 0.0387,
+      "step": 1170000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.939744032341169e-05,
+      "loss": 0.038,
+      "step": 1175000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.921132348667458e-05,
+      "loss": 0.0389,
+      "step": 1180000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.9025545040833008e-05,
+      "loss": 0.0388,
+      "step": 1185000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.8840078780999552e-05,
+      "loss": 0.0383,
+      "step": 1190000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.8655009750029695e-05,
+      "loss": 0.0388,
+      "step": 1195000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.8470311630602035e-05,
+      "loss": 0.0379,
+      "step": 1200000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.8285995219685757e-05,
+      "loss": 0.0378,
+      "step": 1205000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.8102071291936395e-05,
+      "loss": 0.0381,
+      "step": 1210000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.7918587276844793e-05,
+      "loss": 0.0382,
+      "step": 1215000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.7735443869214267e-05,
+      "loss": 0.0385,
+      "step": 1220000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.7552725298494208e-05,
+      "loss": 0.038,
+      "step": 1225000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.7370515089505386e-05,
+      "loss": 0.0381,
+      "step": 1230000
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 1.718875070180597e-05,
+      "loss": 0.0362,
+      "step": 1235000
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 1.7007370282692398e-05,
+      "loss": 0.0339,
+      "step": 1240000
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.682649342119219e-05,
+      "loss": 0.0349,
+      "step": 1245000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.664609436151844e-05,
+      "loss": 0.0345,
+      "step": 1250000
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.6466183649328544e-05,
+      "loss": 0.0348,
+      "step": 1255000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.628673595562077e-05,
+      "loss": 0.0346,
+      "step": 1260000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.6107833563524666e-05,
+      "loss": 0.0348,
+      "step": 1265000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 1.5929450984231475e-05,
+      "loss": 0.0341,
+      "step": 1270000
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 1.575159864552045e-05,
+      "loss": 0.0346,
+      "step": 1275000
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 1.5574286944174337e-05,
+      "loss": 0.0348,
+      "step": 1280000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 1.5397526245371656e-05,
+      "loss": 0.0347,
+      "step": 1285000
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 1.5221362079222911e-05,
+      "loss": 0.0346,
+      "step": 1290000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 1.5045699154455748e-05,
+      "loss": 0.035,
+      "step": 1295000
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.4870653329234462e-05,
+      "loss": 0.0343,
+      "step": 1300000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 1.469619963913822e-05,
+      "loss": 0.0344,
+      "step": 1305000
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.4522348282273651e-05,
+      "loss": 0.0346,
+      "step": 1310000
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 1.434910942153659e-05,
+      "loss": 0.0341,
+      "step": 1315000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.4176493184017924e-05,
+      "loss": 0.0338,
+      "step": 1320000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.4004509660411627e-05,
+      "loss": 0.0345,
+      "step": 1325000
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.3833134687545127e-05,
+      "loss": 0.0343,
+      "step": 1330000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 1.3662480932190311e-05,
+      "loss": 0.0341,
+      "step": 1335000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.3492421770010699e-05,
+      "loss": 0.0336,
+      "step": 1340000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.3323069396041015e-05,
+      "loss": 0.0343,
+      "step": 1345000
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.3154399624907232e-05,
+      "loss": 0.0342,
+      "step": 1350000
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 1.2986422316603203e-05,
+      "loss": 0.0346,
+      "step": 1355000
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 1.2819147290643238e-05,
+      "loss": 0.0341,
+      "step": 1360000
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 1.2652584325488027e-05,
+      "loss": 0.0339,
+      "step": 1365000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.2486743157973069e-05,
+      "loss": 0.0342,
+      "step": 1370000
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 1.2321666444080471e-05,
+      "loss": 0.0344,
+      "step": 1375000
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 1.2157264951667166e-05,
+      "loss": 0.0338,
+      "step": 1380000
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 1.1993647173310798e-05,
+      "loss": 0.0338,
+      "step": 1385000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 1.183078971233793e-05,
+      "loss": 0.0334,
+      "step": 1390000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 1.1668669736135962e-05,
+      "loss": 0.0347,
+      "step": 1395000
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.1507361582461623e-05,
+      "loss": 0.034,
+      "step": 1400000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.134684217315512e-05,
+      "loss": 0.0332,
+      "step": 1405000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.1187089015206759e-05,
+      "loss": 0.0336,
+      "step": 1410000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.1028175361103207e-05,
+      "loss": 0.0332,
+      "step": 1415000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.0870078463341248e-05,
+      "loss": 0.0336,
+      "step": 1420000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 1.0712838947388687e-05,
+      "loss": 0.0334,
+      "step": 1425000
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.0556371856281719e-05,
+      "loss": 0.0338,
+      "step": 1430000
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.0400780485452265e-05,
+      "loss": 0.0337,
+      "step": 1435000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.0246042546828628e-05,
+      "loss": 0.0335,
+      "step": 1440000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.009216708598616e-05,
+      "loss": 0.0332,
+      "step": 1445000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 9.939163098082024e-06,
+      "loss": 0.0324,
+      "step": 1450000
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 9.787039527329362e-06,
+      "loss": 0.0333,
+      "step": 1455000
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 9.635805266474399e-06,
+      "loss": 0.0333,
+      "step": 1460000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 9.485439167479077e-06,
+      "loss": 0.0335,
+      "step": 1465000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 9.335980372105996e-06,
+      "loss": 0.0333,
+      "step": 1470000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 9.187496865476697e-06,
+      "loss": 0.033,
+      "step": 1475000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 9.03987847348179e-06,
+      "loss": 0.033,
+      "step": 1480000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 8.893222690812272e-06,
+      "loss": 0.033,
+      "step": 1485000
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 8.747537527998633e-06,
+      "loss": 0.0331,
+      "step": 1490000
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 8.602773192648179e-06,
+      "loss": 0.0329,
+      "step": 1495000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 8.45893872011418e-06,
+      "loss": 0.0329,
+      "step": 1500000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 8.316100063601678e-06,
+      "loss": 0.0323,
+      "step": 1505000
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 8.174208418379433e-06,
+      "loss": 0.0329,
+      "step": 1510000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 8.03332884679727e-06,
+      "loss": 0.033,
+      "step": 1515000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 7.893441102454437e-06,
+      "loss": 0.0328,
+      "step": 1520000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 2053645,
+  "num_train_epochs": 5,
+  "save_steps": 40000,
+  "total_flos": 3.8313184144529346e+20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b185236dc2edc30b6945cb152bfbb24dbbabad40b3512123a9712cc64576d14f
+size 4283