Upload 9 files

LICENSE

@@ -0,0 +1,53 @@
+Tongyi Qianwen LICENSE AGREEMENT
+
+Tongyi Qianwen Release Date: August 23, 2023
+
+By clicking to agree or by using or distributing any portion or element of the Tongyi Qianwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This Tongyi Qianwen LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b. "We"(or "Us") shall mean Alibaba Cloud.
+    c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d. "Third Parties" shall mean individuals or legal entities that are not under common control with Us or You.
+    e. "Tongyi Qianwen" shall mean the large language models (including Qwen-VL model and Qwen-VL-Chat model), and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Us.
+    f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Tongyi Qianwen and Documentation (and any portion thereof) made available under this Agreement.
+    g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+2. Grant of Rights
+You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by Us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials.
+
+3. Redistribution
+You may reproduce and distribute copies of the Materials or derivative works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
+    b. You shall cause any modified files to carry prominent notices stating that You changed the files;
+    c. You shall retain in all copies of the Materials that You distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Tongyi Qianwen is licensed under the Tongyi Qianwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
+    d. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such derivative works as a whole, provided Your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
+
+4. Restrictions
+If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, You shall request a license from Us. You cannot exercise your rights under this Agreement without our express authorization.
+
+5. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
+    b. You can not use the Materials or any output therefrom to improve any other large language model (excluding Tongyi Qianwen or derivative works thereof).
+
+6. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for Us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of Us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against Us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licences granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+
+7. Disclaimer of Warranty and Limitation of Liability
+
+    a. We are not obligated to support, update, provide training for, or develop any further version of the Tongyi Qianwen Materials or to grant any license thereto.
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will defend, indemnify and hold harmless Us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+8. Survival and Termination.
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 7 and 9 shall survive the termination of this Agreement.
+
+9. Governing Law and Jurisdiction.
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.

README.md

@@ -1,3 +1,204 @@
 ---
-license: unknown
+library_name: peft
+base_model: Qwen/Qwen-VL-Chat
 ---
+
+# 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 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-VL-Chat",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "w2",
+    "attn.c_proj",
+    "w1"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8166d6394787d2b8bac1cf4eef06c3d67bfe8b7d87208ee21cfe17a2d7af3da
+size 224483018

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "Qwen/Qwen-VL-Chat--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 2048,
+  "padding_side": "right",
+  "tokenizer_class": "QWenTokenizer"
+}

trainer_state.json

@@ -0,0 +1,2338 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.943820224719101,
+  "eval_steps": 500,
+  "global_step": 385,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5e-06,
+      "loss": 2.3199,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-06,
+      "loss": 2.6164,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.7792,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 2.6204,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.999830024102874e-06,
+      "loss": 2.3813,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.99932010796822e-06,
+      "loss": 2.5856,
+      "step": 6
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.998470286265415e-06,
+      "loss": 2.3747,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.997280616774147e-06,
+      "loss": 2.5818,
+      "step": 8
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.995751180380468e-06,
+      "loss": 2.5867,
+      "step": 9
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.993882081071307e-06,
+      "loss": 2.2268,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.991673445927399e-06,
+      "loss": 2.6059,
+      "step": 11
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989125425114639e-06,
+      "loss": 2.0894,
+      "step": 12
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.986238191873874e-06,
+      "loss": 2.2201,
+      "step": 13
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.983011942509131e-06,
+      "loss": 2.316,
+      "step": 14
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.979446896374264e-06,
+      "loss": 2.6564,
+      "step": 15
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.975543295858035e-06,
+      "loss": 2.465,
+      "step": 16
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.971301406367644e-06,
+      "loss": 2.4582,
+      "step": 17
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.966721516310683e-06,
+      "loss": 2.2573,
+      "step": 18
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.961803937075516e-06,
+      "loss": 2.3717,
+      "step": 19
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.956549003010122e-06,
+      "loss": 2.6225,
+      "step": 20
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.950957071399357e-06,
+      "loss": 2.0773,
+      "step": 21
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.945028522440654e-06,
+      "loss": 2.2186,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.938763759218186e-06,
+      "loss": 2.7806,
+      "step": 23
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.93216320767545e-06,
+      "loss": 2.5508,
+      "step": 24
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.925227316586316e-06,
+      "loss": 2.2016,
+      "step": 25
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.917956557524511e-06,
+      "loss": 2.2435,
+      "step": 26
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.910351424831545e-06,
+      "loss": 2.5108,
+      "step": 27
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.902412435583127e-06,
+      "loss": 2.2933,
+      "step": 28
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.89414012955398e-06,
+      "loss": 2.1846,
+      "step": 29
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.885535069181163e-06,
+      "loss": 2.9822,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.876597839525814e-06,
+      "loss": 2.231,
+      "step": 31
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.867329048233387e-06,
+      "loss": 2.2585,
+      "step": 32
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.857729325492329e-06,
+      "loss": 2.3573,
+      "step": 33
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.847799323991234e-06,
+      "loss": 2.2582,
+      "step": 34
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.837539718874466e-06,
+      "loss": 2.2804,
+      "step": 35
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.826951207696258e-06,
+      "loss": 2.864,
+      "step": 36
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.816034510373287e-06,
+      "loss": 2.1242,
+      "step": 37
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.804790369135719e-06,
+      "loss": 2.2738,
+      "step": 38
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.793219548476754e-06,
+      "loss": 2.6035,
+      "step": 39
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.781322835100639e-06,
+      "loss": 2.1281,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.769101037869187e-06,
+      "loss": 2.392,
+      "step": 41
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.756554987746777e-06,
+      "loss": 2.2579,
+      "step": 42
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.743685537743856e-06,
+      "loss": 2.1741,
+      "step": 43
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.730493562858954e-06,
+      "loss": 2.2772,
+      "step": 44
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.716979960019173e-06,
+      "loss": 2.2809,
+      "step": 45
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.70314564801922e-06,
+      "loss": 2.3821,
+      "step": 46
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.688991567458934e-06,
+      "loss": 2.5027,
+      "step": 47
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.67451868067933e-06,
+      "loss": 2.3994,
+      "step": 48
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.659727971697173e-06,
+      "loss": 2.3403,
+      "step": 49
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.644620446138078e-06,
+      "loss": 2.2843,
+      "step": 50
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.629197131168125e-06,
+      "loss": 1.9102,
+      "step": 51
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.613459075424033e-06,
+      "loss": 2.0563,
+      "step": 52
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.597407348941865e-06,
+      "loss": 2.5812,
+      "step": 53
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.58104304308426e-06,
+      "loss": 2.0869,
+      "step": 54
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.564367270466247e-06,
+      "loss": 1.9037,
+      "step": 55
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.54738116487959e-06,
+      "loss": 2.3678,
+      "step": 56
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.530085881215705e-06,
+      "loss": 2.2848,
+      "step": 57
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.512482595387131e-06,
+      "loss": 2.0607,
+      "step": 58
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 9.494572504247593e-06,
+      "loss": 1.956,
+      "step": 59
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 9.476356825510613e-06,
+      "loss": 2.2119,
+      "step": 60
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.457836797666722e-06,
+      "loss": 2.2242,
+      "step": 61
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.439013679899263e-06,
+      "loss": 2.259,
+      "step": 62
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.419888751998768e-06,
+      "loss": 2.2482,
+      "step": 63
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.400463314275942e-06,
+      "loss": 2.0579,
+      "step": 64
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.380738687473274e-06,
+      "loss": 1.9384,
+      "step": 65
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.360716212675213e-06,
+      "loss": 2.1505,
+      "step": 66
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.340397251217009e-06,
+      "loss": 2.0986,
+      "step": 67
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.319783184592142e-06,
+      "loss": 2.3174,
+      "step": 68
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.298875414358399e-06,
+      "loss": 2.1534,
+      "step": 69
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.27767536204258e-06,
+      "loss": 2.1114,
+      "step": 70
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.256184469043852e-06,
+      "loss": 1.9863,
+      "step": 71
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.23440419653574e-06,
+      "loss": 2.137,
+      "step": 72
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.212336025366789e-06,
+      "loss": 2.225,
+      "step": 73
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.189981455959873e-06,
+      "loss": 2.0334,
+      "step": 74
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.167342008210191e-06,
+      "loss": 1.9056,
+      "step": 75
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.144419221381919e-06,
+      "loss": 2.144,
+      "step": 76
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.121214654003561e-06,
+      "loss": 1.8992,
+      "step": 77
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.097729883761977e-06,
+      "loss": 1.8587,
+      "step": 78
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.073966507395123e-06,
+      "loss": 2.5454,
+      "step": 79
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.049926140583487e-06,
+      "loss": 2.0381,
+      "step": 80
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.025610417840238e-06,
+      "loss": 2.0646,
+      "step": 81
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.001020992400086e-06,
+      "loss": 1.6412,
+      "step": 82
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.976159536106895e-06,
+      "loss": 1.9907,
+      "step": 83
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.951027739299996e-06,
+      "loss": 1.8317,
+      "step": 84
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.925627310699275e-06,
+      "loss": 2.1631,
+      "step": 85
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.899959977288988e-06,
+      "loss": 2.2149,
+      "step": 86
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.874027484200342e-06,
+      "loss": 2.2374,
+      "step": 87
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.847831594592851e-06,
+      "loss": 2.124,
+      "step": 88
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.821374089534446e-06,
+      "loss": 2.0088,
+      "step": 89
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.794656767880394e-06,
+      "loss": 2.1843,
+      "step": 90
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.767681446150977e-06,
+      "loss": 2.552,
+      "step": 91
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.740449958408006e-06,
+      "loss": 1.7471,
+      "step": 92
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 8.7129641561301e-06,
+      "loss": 1.9054,
+      "step": 93
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 8.68522590808682e-06,
+      "loss": 2.1348,
+      "step": 94
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 8.657237100211604e-06,
+      "loss": 2.0139,
+      "step": 95
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.628999635473547e-06,
+      "loss": 1.9181,
+      "step": 96
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8.600515433748003e-06,
+      "loss": 2.2683,
+      "step": 97
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.571786431686074e-06,
+      "loss": 1.7892,
+      "step": 98
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 8.542814582582917e-06,
+      "loss": 1.9259,
+      "step": 99
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 8.513601856244951e-06,
+      "loss": 1.9594,
+      "step": 100
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 8.484150238855921e-06,
+      "loss": 2.1425,
+      "step": 101
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 8.454461732841864e-06,
+      "loss": 2.1687,
+      "step": 102
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 8.424538356734957e-06,
+      "loss": 2.128,
+      "step": 103
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 8.394382145036277e-06,
+      "loss": 2.3052,
+      "step": 104
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 8.363995148077481e-06,
+      "loss": 2.1029,
+      "step": 105
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 8.333379431881398e-06,
+      "loss": 1.9932,
+      "step": 106
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 8.302537078021555e-06,
+      "loss": 1.9616,
+      "step": 107
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 8.271470183480664e-06,
+      "loss": 2.0529,
+      "step": 108
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 8.240180860508027e-06,
+      "loss": 1.8921,
+      "step": 109
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 8.208671236475945e-06,
+      "loss": 1.7787,
+      "step": 110
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.176943453735062e-06,
+      "loss": 2.0703,
+      "step": 111
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.144999669468714e-06,
+      "loss": 1.9988,
+      "step": 112
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.112842055546254e-06,
+      "loss": 1.8816,
+      "step": 113
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.080472798375392e-06,
+      "loss": 1.953,
+      "step": 114
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.04789409875354e-06,
+      "loss": 2.0868,
+      "step": 115
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.015108171718177e-06,
+      "loss": 2.2089,
+      "step": 116
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.982117246396246e-06,
+      "loss": 1.9521,
+      "step": 117
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.948923565852597e-06,
+      "loss": 2.2335,
+      "step": 118
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.915529386937486e-06,
+      "loss": 2.2536,
+      "step": 119
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.881936980133118e-06,
+      "loss": 1.6541,
+      "step": 120
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.848148629399287e-06,
+      "loss": 1.9498,
+      "step": 121
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 7.814166632018083e-06,
+      "loss": 2.3166,
+      "step": 122
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 7.779993298437704e-06,
+      "loss": 2.1169,
+      "step": 123
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 7.745630952115365e-06,
+      "loss": 2.1505,
+      "step": 124
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.711081929359316e-06,
+      "loss": 1.9007,
+      "step": 125
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.67634857917002e-06,
+      "loss": 2.1772,
+      "step": 126
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.641433263080418e-06,
+      "loss": 2.4341,
+      "step": 127
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.606338354995381e-06,
+      "loss": 1.7081,
+      "step": 128
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.571066241030302e-06,
+      "loss": 2.0402,
+      "step": 129
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 7.5356193193488655e-06,
+      "loss": 2.0681,
+      "step": 130
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.5562,
+      "step": 131
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 7.464210704754009e-06,
+      "loss": 1.7387,
+      "step": 132
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.4282538669379186e-06,
+      "loss": 2.1956,
+      "step": 133
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.3921319312700365e-06,
+      "loss": 2.0449,
+      "step": 134
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.355847353693729e-06,
+      "loss": 1.8579,
+      "step": 135
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.319402601210448e-06,
+      "loss": 2.0661,
+      "step": 136
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.282800151711991e-06,
+      "loss": 2.1408,
+      "step": 137
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.246042493812036e-06,
+      "loss": 1.729,
+      "step": 138
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.209132126676934e-06,
+      "loss": 2.3547,
+      "step": 139
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.172071559855792e-06,
+      "loss": 2.2959,
+      "step": 140
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.134863313109847e-06,
+      "loss": 2.3131,
+      "step": 141
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.097509916241145e-06,
+      "loss": 1.7705,
+      "step": 142
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.060013908920549e-06,
+      "loss": 1.6909,
+      "step": 143
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.022377840515047e-06,
+      "loss": 1.84,
+      "step": 144
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.984604269914437e-06,
+      "loss": 1.977,
+      "step": 145
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.94669576535734e-06,
+      "loss": 2.177,
+      "step": 146
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.908654904256584e-06,
+      "loss": 1.9606,
+      "step": 147
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.870484273023967e-06,
+      "loss": 2.0072,
+      "step": 148
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.832186466894402e-06,
+      "loss": 1.7583,
+      "step": 149
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.793764089749473e-06,
+      "loss": 1.8085,
+      "step": 150
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.755219753940389e-06,
+      "loss": 1.7839,
+      "step": 151
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.716556080110374e-06,
+      "loss": 1.9219,
+      "step": 152
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.677775697016484e-06,
+      "loss": 2.1836,
+      "step": 153
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.638881241350884e-06,
+      "loss": 1.964,
+      "step": 154
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.599875357561572e-06,
+      "loss": 1.8509,
+      "step": 155
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.560760697672583e-06,
+      "loss": 2.2632,
+      "step": 156
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.5215399211036815e-06,
+      "loss": 1.9777,
+      "step": 157
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 6.4822156944895375e-06,
+      "loss": 1.9851,
+      "step": 158
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.442790691498433e-06,
+      "loss": 2.204,
+      "step": 159
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 6.403267592650466e-06,
+      "loss": 1.7941,
+      "step": 160
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.363649085135311e-06,
+      "loss": 1.8559,
+      "step": 161
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 6.323937862629513e-06,
+      "loss": 1.9673,
+      "step": 162
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 6.2841366251133405e-06,
+      "loss": 1.883,
+      "step": 163
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 6.244248078687213e-06,
+      "loss": 1.9343,
+      "step": 164
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 6.204274935387716e-06,
+      "loss": 1.8082,
+      "step": 165
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 6.164219913003208e-06,
+      "loss": 1.9898,
+      "step": 166
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 6.124085734889034e-06,
+      "loss": 1.6458,
+      "step": 167
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 6.083875129782366e-06,
+      "loss": 2.0815,
+      "step": 168
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 6.043590831616677e-06,
+      "loss": 2.1997,
+      "step": 169
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 6.003235579335851e-06,
+      "loss": 2.1733,
+      "step": 170
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.962812116707977e-06,
+      "loss": 1.8058,
+      "step": 171
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 5.92232319213878e-06,
+      "loss": 2.1662,
+      "step": 172
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5.8817715584847744e-06,
+      "loss": 1.8951,
+      "step": 173
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 5.841159972866085e-06,
+      "loss": 1.9074,
+      "step": 174
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 5.800491196478989e-06,
+      "loss": 1.9271,
+      "step": 175
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 5.759767994408188e-06,
+      "loss": 1.9044,
+      "step": 176
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 5.718993135438803e-06,
+      "loss": 1.9798,
+      "step": 177
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 5.678169391868128e-06,
+      "loss": 1.9495,
+      "step": 178
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 5.637299539317141e-06,
+      "loss": 2.1539,
+      "step": 179
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 5.596386356541779e-06,
+      "loss": 2.0293,
+      "step": 180
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 5.555432625244024e-06,
+      "loss": 1.8224,
+      "step": 181
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.51444112988276e-06,
+      "loss": 1.6832,
+      "step": 182
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 5.473414657484468e-06,
+      "loss": 2.0847,
+      "step": 183
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 5.432355997453729e-06,
+      "loss": 2.0309,
+      "step": 184
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 5.391267941383572e-06,
+      "loss": 2.0406,
+      "step": 185
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 5.350153282865674e-06,
+      "loss": 1.7257,
+      "step": 186
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 5.309014817300422e-06,
+      "loss": 1.8888,
+      "step": 187
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 5.26785534170685e-06,
+      "loss": 1.8149,
+      "step": 188
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 5.226677654532476e-06,
+      "loss": 2.0397,
+      "step": 189
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.185484555463026e-06,
+      "loss": 2.1468,
+      "step": 190
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 5.1442788452320915e-06,
+      "loss": 2.1732,
+      "step": 191
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 5.1030633254306935e-06,
+      "loss": 2.2631,
+      "step": 192
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5.061840798316815e-06,
+      "loss": 1.9009,
+      "step": 193
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.020614066624868e-06,
+      "loss": 2.2187,
+      "step": 194
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 4.979385933375133e-06,
+      "loss": 1.6122,
+      "step": 195
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.9381592016831856e-06,
+      "loss": 1.5505,
+      "step": 196
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.896936674569309e-06,
+      "loss": 1.843,
+      "step": 197
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.85572115476791e-06,
+      "loss": 1.7565,
+      "step": 198
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.814515444536975e-06,
+      "loss": 1.8699,
+      "step": 199
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.773322345467525e-06,
+      "loss": 1.9872,
+      "step": 200
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 4.732144658293151e-06,
+      "loss": 1.9223,
+      "step": 201
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.690985182699581e-06,
+      "loss": 1.9225,
+      "step": 202
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.649846717134327e-06,
+      "loss": 1.8284,
+      "step": 203
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.6087320586164296e-06,
+      "loss": 1.8652,
+      "step": 204
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 4.567644002546273e-06,
+      "loss": 1.735,
+      "step": 205
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 4.526585342515533e-06,
+      "loss": 2.0562,
+      "step": 206
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 4.485558870117241e-06,
+      "loss": 2.0004,
+      "step": 207
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 4.444567374755978e-06,
+      "loss": 2.2094,
+      "step": 208
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.403613643458222e-06,
+      "loss": 1.9606,
+      "step": 209
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.362700460682861e-06,
+      "loss": 1.984,
+      "step": 210
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.321830608131872e-06,
+      "loss": 1.7363,
+      "step": 211
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.281006864561199e-06,
+      "loss": 1.9783,
+      "step": 212
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.240232005591816e-06,
+      "loss": 1.6583,
+      "step": 213
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.1995088035210126e-06,
+      "loss": 2.3748,
+      "step": 214
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.158840027133917e-06,
+      "loss": 2.0012,
+      "step": 215
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.1182284415152255e-06,
+      "loss": 1.6849,
+      "step": 216
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 4.077676807861221e-06,
+      "loss": 1.729,
+      "step": 217
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 4.037187883292027e-06,
+      "loss": 2.2028,
+      "step": 218
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.996764420664149e-06,
+      "loss": 1.9073,
+      "step": 219
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.956409168383325e-06,
+      "loss": 1.6662,
+      "step": 220
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 3.916124870217635e-06,
+      "loss": 1.9193,
+      "step": 221
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 3.875914265110967e-06,
+      "loss": 1.8654,
+      "step": 222
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 3.835780086996794e-06,
+      "loss": 1.9015,
+      "step": 223
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 3.7957250646122843e-06,
+      "loss": 1.9406,
+      "step": 224
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.755751921312788e-06,
+      "loss": 1.8809,
+      "step": 225
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.715863374886661e-06,
+      "loss": 1.8371,
+      "step": 226
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.6760621373704867e-06,
+      "loss": 2.0746,
+      "step": 227
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.636350914864689e-06,
+      "loss": 1.822,
+      "step": 228
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 3.5967324073495363e-06,
+      "loss": 1.7246,
+      "step": 229
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 3.5572093085015683e-06,
+      "loss": 1.6679,
+      "step": 230
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.5177843055104633e-06,
+      "loss": 1.8069,
+      "step": 231
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.4784600788963197e-06,
+      "loss": 1.9182,
+      "step": 232
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 3.4392393023274173e-06,
+      "loss": 1.6175,
+      "step": 233
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.4001246424384294e-06,
+      "loss": 1.8909,
+      "step": 234
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 3.361118758649116e-06,
+      "loss": 2.0512,
+      "step": 235
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 3.322224302983517e-06,
+      "loss": 1.8031,
+      "step": 236
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.2834439198896285e-06,
+      "loss": 1.8325,
+      "step": 237
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 3.2447802460596124e-06,
+      "loss": 1.9987,
+      "step": 238
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 3.206235910250529e-06,
+      "loss": 1.694,
+      "step": 239
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.167813533105598e-06,
+      "loss": 2.1121,
+      "step": 240
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 3.1295157269760347e-06,
+      "loss": 2.1676,
+      "step": 241
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.0913450957434177e-06,
+      "loss": 1.9139,
+      "step": 242
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 3.0533042346426612e-06,
+      "loss": 1.8614,
+      "step": 243
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 3.015395730085565e-06,
+      "loss": 1.9445,
+      "step": 244
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 2.9776221594849565e-06,
+      "loss": 2.1084,
+      "step": 245
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 2.9399860910794532e-06,
+      "loss": 1.9299,
+      "step": 246
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.902490083758856e-06,
+      "loss": 1.7569,
+      "step": 247
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 2.8651366868901543e-06,
+      "loss": 1.5915,
+      "step": 248
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 2.8279284401442085e-06,
+      "loss": 1.4711,
+      "step": 249
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 2.790867873323067e-06,
+      "loss": 1.7658,
+      "step": 250
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 2.753957506187964e-06,
+      "loss": 2.2383,
+      "step": 251
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 2.7171998482880093e-06,
+      "loss": 2.1103,
+      "step": 252
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.680597398789554e-06,
+      "loss": 1.9208,
+      "step": 253
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 2.6441526463062727e-06,
+      "loss": 1.9773,
+      "step": 254
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 2.607868068729966e-06,
+      "loss": 2.0155,
+      "step": 255
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 2.571746133062082e-06,
+      "loss": 1.8626,
+      "step": 256
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 2.5357892952459917e-06,
+      "loss": 1.764,
+      "step": 257
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 2.0152,
+      "step": 258
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 2.4643806806511344e-06,
+      "loss": 1.8742,
+      "step": 259
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 2.4289337589697e-06,
+      "loss": 2.0988,
+      "step": 260
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 2.3936616450046207e-06,
+      "loss": 1.9274,
+      "step": 261
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 2.3585667369195815e-06,
+      "loss": 1.5094,
+      "step": 262
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 2.32365142082998e-06,
+      "loss": 2.0823,
+      "step": 263
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 2.288918070640684e-06,
+      "loss": 1.6446,
+      "step": 264
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.254369047884639e-06,
+      "loss": 1.9535,
+      "step": 265
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 2.2200067015622986e-06,
+      "loss": 1.5839,
+      "step": 266
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 2.185833367981918e-06,
+      "loss": 1.7815,
+      "step": 267
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.1518513706007154e-06,
+      "loss": 1.4904,
+      "step": 268
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.118063019866884e-06,
+      "loss": 2.2307,
+      "step": 269
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.0844706130625146e-06,
+      "loss": 1.947,
+      "step": 270
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.0510764341474032e-06,
+      "loss": 2.2949,
+      "step": 271
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 2.0178827536037547e-06,
+      "loss": 1.7868,
+      "step": 272
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.9848918282818242e-06,
+      "loss": 1.663,
+      "step": 273
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.952105901246461e-06,
+      "loss": 1.7499,
+      "step": 274
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.9195272016246105e-06,
+      "loss": 1.938,
+      "step": 275
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 1.887157944453749e-06,
+      "loss": 2.0385,
+      "step": 276
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.855000330531289e-06,
+      "loss": 2.0374,
+      "step": 277
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 1.823056546264939e-06,
+      "loss": 1.7599,
+      "step": 278
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.7913287635240573e-06,
+      "loss": 2.1512,
+      "step": 279
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.7598191394919738e-06,
+      "loss": 1.8319,
+      "step": 280
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.7285298165193388e-06,
+      "loss": 1.7238,
+      "step": 281
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.697462921978446e-06,
+      "loss": 1.8568,
+      "step": 282
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.6666205681186032e-06,
+      "loss": 2.1115,
+      "step": 283
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.6360048519225197e-06,
+      "loss": 1.8881,
+      "step": 284
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.6056178549637248e-06,
+      "loss": 1.8789,
+      "step": 285
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.5754616432650443e-06,
+      "loss": 2.168,
+      "step": 286
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.5455382671581365e-06,
+      "loss": 1.9499,
+      "step": 287
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.5158497611440792e-06,
+      "loss": 2.0706,
+      "step": 288
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.48639814375505e-06,
+      "loss": 1.9817,
+      "step": 289
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.4571854174170847e-06,
+      "loss": 1.8163,
+      "step": 290
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.428213568313927e-06,
+      "loss": 1.785,
+      "step": 291
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.3994845662519985e-06,
+      "loss": 2.0604,
+      "step": 292
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 1.3710003645264559e-06,
+      "loss": 1.7002,
+      "step": 293
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.3427628997883957e-06,
+      "loss": 1.788,
+      "step": 294
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.3147740919131814e-06,
+      "loss": 1.5869,
+      "step": 295
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.2870358438699005e-06,
+      "loss": 1.6432,
+      "step": 296
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.2595500415919948e-06,
+      "loss": 1.9052,
+      "step": 297
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.232318553849023e-06,
+      "loss": 1.8955,
+      "step": 298
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.2053432321196085e-06,
+      "loss": 1.904,
+      "step": 299
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.1786259104655562e-06,
+      "loss": 2.0135,
+      "step": 300
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.1521684054071524e-06,
+      "loss": 1.8603,
+      "step": 301
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.1259725157996593e-06,
+      "loss": 1.7627,
+      "step": 302
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.1000400227110142e-06,
+      "loss": 1.6693,
+      "step": 303
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.0743726893007257e-06,
+      "loss": 1.779,
+      "step": 304
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.0489722607000052e-06,
+      "loss": 2.0575,
+      "step": 305
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 1.0238404638931077e-06,
+      "loss": 1.9037,
+      "step": 306
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 9.989790075999145e-07,
+      "loss": 1.9991,
+      "step": 307
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 9.743895821597638e-07,
+      "loss": 2.0821,
+      "step": 308
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 9.500738594165132e-07,
+      "loss": 1.9613,
+      "step": 309
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 9.260334926048787e-07,
+      "loss": 1.939,
+      "step": 310
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 9.022701162380259e-07,
+      "loss": 1.7692,
+      "step": 311
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 8.787853459964407e-07,
+      "loss": 2.0053,
+      "step": 312
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 8.555807786180814e-07,
+      "loss": 1.8909,
+      "step": 313
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 8.326579917898098e-07,
+      "loss": 1.8692,
+      "step": 314
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 8.100185440401276e-07,
+      "loss": 2.1948,
+      "step": 315
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 7.876639746332132e-07,
+      "loss": 2.2319,
+      "step": 316
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 7.655958034642619e-07,
+      "loss": 1.8725,
+      "step": 317
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 7.43815530956149e-07,
+      "loss": 1.5717,
+      "step": 318
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 7.223246379574206e-07,
+      "loss": 1.7549,
+      "step": 319
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 7.011245856416016e-07,
+      "loss": 2.0717,
+      "step": 320
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 6.802168154078586e-07,
+      "loss": 1.9039,
+      "step": 321
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 6.596027487829915e-07,
+      "loss": 2.0704,
+      "step": 322
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 6.392837873247876e-07,
+      "loss": 1.8727,
+      "step": 323
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 6.192613125267283e-07,
+      "loss": 1.8494,
+      "step": 324
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 5.995366857240592e-07,
+      "loss": 1.9835,
+      "step": 325
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 5.801112480012344e-07,
+      "loss": 2.0905,
+      "step": 326
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 5.609863201007382e-07,
+      "loss": 1.8491,
+      "step": 327
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 5.421632023332779e-07,
+      "loss": 1.6643,
+      "step": 328
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 5.236431744893883e-07,
+      "loss": 1.5409,
+      "step": 329
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 5.054274957524075e-07,
+      "loss": 1.6956,
+      "step": 330
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 4.875174046128684e-07,
+      "loss": 1.9333,
+      "step": 331
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 4.6991411878429593e-07,
+      "loss": 1.7577,
+      "step": 332
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 4.526188351204103e-07,
+      "loss": 2.0727,
+      "step": 333
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 4.3563272953375426e-07,
+      "loss": 1.8069,
+      "step": 334
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 4.1895695691574146e-07,
+      "loss": 2.0435,
+      "step": 335
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 4.025926510581357e-07,
+      "loss": 2.0467,
+      "step": 336
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 3.8654092457596714e-07,
+      "loss": 1.6247,
+      "step": 337
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 3.7080286883187713e-07,
+      "loss": 1.9954,
+      "step": 338
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 3.553795538619237e-07,
+      "loss": 2.255,
+      "step": 339
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 3.402720283028277e-07,
+      "loss": 1.9724,
+      "step": 340
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 3.2548131932067184e-07,
+      "loss": 1.9318,
+      "step": 341
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 3.110084325410667e-07,
+      "loss": 1.7369,
+      "step": 342
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.9685435198078095e-07,
+      "loss": 1.7993,
+      "step": 343
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 2.830200399808286e-07,
+      "loss": 1.9586,
+      "step": 344
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.6950643714104774e-07,
+      "loss": 1.6359,
+      "step": 345
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 2.563144622561453e-07,
+      "loss": 1.8904,
+      "step": 346
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 2.4344501225322557e-07,
+      "loss": 1.7661,
+      "step": 347
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 2.3089896213081553e-07,
+      "loss": 1.8997,
+      "step": 348
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 2.1867716489936297e-07,
+      "loss": 1.759,
+      "step": 349
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 2.0678045152324798e-07,
+      "loss": 1.7521,
+      "step": 350
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9520963086428258e-07,
+      "loss": 1.5358,
+      "step": 351
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.8396548962671456e-07,
+      "loss": 2.0727,
+      "step": 352
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.7304879230374328e-07,
+      "loss": 2.0473,
+      "step": 353
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 1.6246028112553603e-07,
+      "loss": 1.9068,
+      "step": 354
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 1.5220067600876686e-07,
+      "loss": 2.1523,
+      "step": 355
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 1.422706745076713e-07,
+      "loss": 1.9869,
+      "step": 356
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.3267095176661304e-07,
+      "loss": 2.0737,
+      "step": 357
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 1.2340216047418697e-07,
+      "loss": 1.9659,
+      "step": 358
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 1.1446493081883891e-07,
+      "loss": 1.4132,
+      "step": 359
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 1.0585987044602009e-07,
+      "loss": 1.7613,
+      "step": 360
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 9.758756441687333e-08,
+      "loss": 2.0321,
+      "step": 361
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 8.964857516845449e-08,
+      "loss": 2.1659,
+      "step": 362
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 8.204344247549067e-08,
+      "loss": 1.7783,
+      "step": 363
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 7.47726834136836e-08,
+      "loss": 1.8563,
+      "step": 364
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 6.783679232455043e-08,
+      "loss": 1.986,
+      "step": 365
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 6.123624078181512e-08,
+      "loss": 1.8735,
+      "step": 366
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 5.4971477559346286e-08,
+      "loss": 1.5537,
+      "step": 367
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 4.90429286006433e-08,
+      "loss": 1.857,
+      "step": 368
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 4.34509969898772e-08,
+      "loss": 1.673,
+      "step": 369
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 3.819606292448541e-08,
+      "loss": 1.9837,
+      "step": 370
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 3.327848368931907e-08,
+      "loss": 1.6531,
+      "step": 371
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 2.8698593632357496e-08,
+      "loss": 1.9188,
+      "step": 372
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.4456704141967437e-08,
+      "loss": 1.9565,
+      "step": 373
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.0553103625737813e-08,
+      "loss": 1.6245,
+      "step": 374
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 1.6988057490868736e-08,
+      "loss": 1.7511,
+      "step": 375
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 1.3761808126126486e-08,
+      "loss": 1.8122,
+      "step": 376
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 1.0874574885362809e-08,
+      "loss": 1.6269,
+      "step": 377
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 8.32655407260241e-09,
+      "loss": 2.0738,
+      "step": 378
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 6.117918928693623e-09,
+      "loss": 2.0557,
+      "step": 379
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 4.248819619533384e-09,
+      "loss": 1.8619,
+      "step": 380
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 2.7193832258537447e-09,
+      "loss": 2.2485,
+      "step": 381
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 1.5297137345843261e-09,
+      "loss": 1.9175,
+      "step": 382
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 6.798920317807601e-10,
+      "loss": 2.099,
+      "step": 383
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 1.6997589712575145e-10,
+      "loss": 2.1961,
+      "step": 384
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 0.0,
+      "loss": 2.2319,
+      "step": 385
+    },
+    {
+      "epoch": 4.94,
+      "step": 385,
+      "total_flos": 3.4617941689368576e+17,
+      "train_loss": 2.0085288332654283,
+      "train_runtime": 6983.5696,
+      "train_samples_per_second": 0.446,
+      "train_steps_per_second": 0.055
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 385,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "total_flos": 3.4617941689368576e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb47645631bf22babe12672e4f1d9372bee531bf4ede1c212d08b9c34cd82830
+size 4536