Upload model livekit/turn-detector from revision v0.3.0-intl

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+# Only track large .json files in specific files
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,6 @@
+# Ignore common system files
+.DS_Store
+Thumbs.db
+
+# Ignore personal notes
+update_model_steps.sh

LICENSE

@@ -0,0 +1,115 @@
+LIVEKIT MODEL LICENSE AGREEMENT
+
+1. Introduction
+
+   LiveKit Incorporated ("LiveKit") is making available its proprietary models for
+   use pursuant to the terms and conditions of this Agreement. As further
+   described below, you may use these LiveKit models freely but can only use them
+   together with the LiveKit Agents framework. You cannot use the LiveKit models
+   on a standalone basis or with any other frameworks.
+
+   BY CLICKING "I ACCEPT," OR BY DOWNLOADING, INSTALLING, OR OTHERWISE ACCESSING
+   OR USING THE LIVEKIT MATERIALS, YOU AGREE THAT YOU HAVE READ AND UNDERSTOOD,
+   AND, AS A CONDITION TO YOUR USE OF THE LIVEKIT MATERIALS, YOU AGREE TO BE
+   BOUND BY, THE FOLLOWING TERMS AND CONDITIONS.
+
+2. Definitions
+
+   "Agreement" means this LiveKit Model License Agreement.
+
+   "Documentation" means the specifications, manuals, and documentation
+   accompanying any LiveKit Model and distributed by LiveKit.
+
+   "Licensee" or "you" means the individual or entity agreeing to be bound by
+   this Agreement.
+
+   "LiveKit Agents" means the proprietary LiveKit software framework for building
+   real-time multimodal AI applications with programmable backend participants.
+
+   "LiveKit Materials" means, collectively, the LiveKit Models and Documentation.
+
+   "LiveKit Model" means any of LiveKit's proprietary software models or
+   algorithms, including machine-learning software code, model weights,
+   inference-enabling software code, training-enabling software code, and
+   fine-tuning enabling software code. Any derivative works of a LiveKit Model,
+   whether developed by LiveKit, you, or any third party, will be deemed the
+   "LiveKit Model" for the purposes of this Agreement.
+
+3. License Rights
+
+   Right to Use LiveKit Materials. Subject to the terms and conditions of this
+   Agreement, including the requirements of Section 3.b, LiveKit grants you a
+   nonexclusive, nontransferable, worldwide, royalty-free license under LiveKit's
+   intellectual property rights to use, reproduce, distribute, copy, and create
+   derivative works of the LiveKit Materials.
+
+   Limitation on Use. As a condition to your use of the LiveKit Materials, you
+   agree: (i) not to use any LiveKit Models on a standalone basis or with any
+   frameworks other than LiveKit Agents; (ii) not to use any LiveKit Materials or
+   any output from, or results of using, LiveKit Models (including any derivative
+   works thereof) to improve or otherwise develop any other models that are not
+   LiveKit Models; or (iii) distribute or otherwise make available the LiveKit
+   Materials (including any derivative works thereof) except (x) pursuant to the
+   terms of this Agreement, and (y) you reproduce the above copyright notice.
+
+4. Intellectual Property
+
+   The LiveKit Materials are owned by LiveKit and its licensors. Except for the
+   rights granted to you under this Agreement, all rights are reserved and no
+   other express or implied rights are granted.
+
+   You will own any derivative works that you created from the LiveKit Materials,
+   subject to the terms of this Agreement.
+
+5. Disclaimer
+
+   UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, LIVEKIT PROVIDES
+   THE LIVEKIT MATERIALS, AND ANY OUTPUT OR RESULTS THEREFROM, ON AN "AS IS"
+   BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED,
+   INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE,
+   NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
+   ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
+   REDISTRIBUTING THE LIVEKIT MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
+   USE OF THE LIVEKIT MATERIALS AND ANY OUTPUT AND RESULTS.
+
+6. Limitation of Liability
+
+   IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE),
+   CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW (SUCH AS DELIBERATE
+   AND GROSSLY NEGLIGENT ACTS) OR AGREED TO IN WRITING, WILL LIVEKIT BE LIABLE TO
+   YOU FOR INDIRECT DAMAGES, INCLUDING ANY SPECIAL, INCIDENTAL, OR CONSEQUENTIAL
+   DAMAGES OF ANY CHARACTER ARISING AS A RESULT OF THIS AGREEMENT OR OUT OF THE
+   USE OR INABILITY TO USE THE LIVEKIT MATERIALS OR ANY OUTPUT OR RESULTS
+   THEREFROM (INCLUDING BUT NOT LIMITED TO DAMAGES FOR LOSS OF GOODWILL, WORK
+   STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL
+   DAMAGES OR LOSSES), EVEN IF LIVEKIT HAS BEEN ADVISED OF THE POSSIBILITY OF
+   SUCH DAMAGES.
+
+7. Trademarks
+
+   This Agreement does not grant permission to use the trade names, trademarks,
+   service marks, or product names of LiveKit, except as required for reasonable
+   and customary use in describing the origin of the LiveKit Materials.
+
+8. Term and Termination
+
+   The term of this Agreement commences upon your acceptance of this Agreement
+   and continues in effect until you cease using the LiveKit Materials or it is
+   terminated by either party (on immediate written notice to the other party).
+   This Agreement will automatically terminate if you breach any of its terms.
+   Upon termination, you must immediately cease all use of the LiveKit Materials.
+   Sections 4, 5, 6, and 9 will survive termination.
+
+9. Governing Law and Venue
+
+   This Agreement is subject to the laws of the State of California, without
+   regard to its conflict of laws principles. The UN Convention on Contracts for
+   the International Sale of Goods does not apply to this Agreement. The courts
+   located in San Francisco, California, have exclusive jurisdiction for any
+   dispute arising out of this Agreement.
+
++ + + +
+
+Last Updated: November 25, 2024
+
+

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# 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. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **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]

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct_pruned",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 1216,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.3"
+}

languages.json

@@ -0,0 +1,142 @@
+{
+    "hi":{
+        "tpr":0.9941,
+        "tnr":0.936,
+        "threshold":0.0220999997
+    },
+    "hindi":{
+        "tpr":0.9941,
+        "tnr":0.936,
+        "threshold":0.0220999997
+    },
+    "korean":{
+        "tpr":0.9932,
+        "tnr":0.887,
+        "threshold":0.0055999998
+    },
+    "ko":{
+        "tpr":0.9932,
+        "tnr":0.887,
+        "threshold":0.0055999998
+    },
+    "french":{
+        "tpr":0.993,
+        "tnr":0.8494,
+        "threshold":0.0091000004
+    },
+    "fr":{
+        "tpr":0.993,
+        "tnr":0.8494,
+        "threshold":0.0091000004
+    },
+    "portuguese":{
+        "tpr":0.9935,
+        "tnr":0.8275,
+        "threshold":0.0074
+    },
+    "pt":{
+        "tpr":0.9935,
+        "tnr":0.8275,
+        "threshold":0.0074
+    },
+    "indonesian":{
+        "tpr":0.993,
+        "tnr":0.8032,
+        "threshold":0.0077999998
+    },
+    "id":{
+        "tpr":0.993,
+        "tnr":0.8032,
+        "threshold":0.0077999998
+    },
+    "ru":{
+        "tpr":0.9933,
+        "tnr":0.8017,
+        "threshold":0.0024000001
+    },
+    "russian":{
+        "tpr":0.9933,
+        "tnr":0.8017,
+        "threshold":0.0024000001
+    },
+    "english":{
+        "tpr":0.9934,
+        "tnr":0.8016,
+        "threshold":0.0049000001
+    },
+    "en":{
+        "tpr":0.9934,
+        "tnr":0.8016,
+        "threshold":0.0049000001
+    },
+    "zh":{
+        "tpr":0.9931,
+        "tnr":0.7996,
+        "threshold":0.0038999999
+    },
+    "chinese":{
+        "tpr":0.9931,
+        "tnr":0.7996,
+        "threshold":0.0038999999
+    },
+    "ja":{
+        "tpr":0.993,
+        "tnr":0.7982,
+        "threshold":0.0027000001
+    },
+    "japanese":{
+        "tpr":0.993,
+        "tnr":0.7982,
+        "threshold":0.0027000001
+    },
+    "it":{
+        "tpr":0.993,
+        "tnr":0.7976,
+        "threshold":0.0060999999
+    },
+    "italian":{
+        "tpr":0.993,
+        "tnr":0.7976,
+        "threshold":0.0060999999
+    },
+    "es":{
+        "tpr":0.9931,
+        "tnr":0.7967,
+        "threshold":0.0035999999
+    },
+    "spanish":{
+        "tpr":0.9931,
+        "tnr":0.7967,
+        "threshold":0.0035999999
+    },
+    "de":{
+        "tpr":0.9931,
+        "tnr":0.7755,
+        "threshold":0.0046999999
+    },
+    "german":{
+        "tpr":0.9931,
+        "tnr":0.7755,
+        "threshold":0.0046999999
+    },
+    "tr":{
+        "tpr":0.9934,
+        "tnr":0.743,
+        "threshold":0.0034
+    },
+    "turkish":{
+        "tpr":0.9934,
+        "tnr":0.743,
+        "threshold":0.0034
+    },
+    "nl":{
+        "tpr":0.9932,
+        "tnr":0.7337,
+        "threshold":0.0026
+    },
+    "dutch":{
+        "tpr":0.9932,
+        "tnr":0.7337,
+        "threshold":0.0026
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc14a5bb854c5da7b650d4fa104dbb074fcd6ca28d9868d96aa123f99ae2d94
+size 517418272

onnx/model_q8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb517791184b05c659371092f20cf2e2a09407decd318f996f9ea159df3b166
+size 396312785

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64eb36ca66060e66d883312782e939e1292b3375c2bbdbdd18e7257fc0ba9de
+size 1035007435

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f70f09d3cb910592b4d2344caae1568a9b5043377429849d732244fbeec9cb
+size 14391

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588490afe995435560a63cecc7fcfbda7ae66e87863035b7c3c1f3d9a638454a
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2163 @@
+{
+  "best_metric": 0.7931236608249025,
+  "best_model_checkpoint": "./models/checkpoint-1500",
+  "epoch": 1.0053619302949062,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003351206434316354,
+      "grad_norm": 248.0,
+      "learning_rate": 5e-06,
+      "loss": 12.9737,
+      "step": 5
+    },
+    {
+      "epoch": 0.006702412868632708,
+      "grad_norm": 205.0,
+      "learning_rate": 1e-05,
+      "loss": 12.2905,
+      "step": 10
+    },
+    {
+      "epoch": 0.010053619302949061,
+      "grad_norm": 78.5,
+      "learning_rate": 1.5e-05,
+      "loss": 10.8747,
+      "step": 15
+    },
+    {
+      "epoch": 0.013404825737265416,
+      "grad_norm": 45.25,
+      "learning_rate": 2e-05,
+      "loss": 9.7048,
+      "step": 20
+    },
+    {
+      "epoch": 0.01675603217158177,
+      "grad_norm": 35.0,
+      "learning_rate": 2.5e-05,
+      "loss": 8.8715,
+      "step": 25
+    },
+    {
+      "epoch": 0.020107238605898123,
+      "grad_norm": 30.0,
+      "learning_rate": 3e-05,
+      "loss": 8.1936,
+      "step": 30
+    },
+    {
+      "epoch": 0.023458445040214475,
+      "grad_norm": 29.5,
+      "learning_rate": 3.5e-05,
+      "loss": 7.5312,
+      "step": 35
+    },
+    {
+      "epoch": 0.02680965147453083,
+      "grad_norm": 35.75,
+      "learning_rate": 4e-05,
+      "loss": 6.9812,
+      "step": 40
+    },
+    {
+      "epoch": 0.030160857908847184,
+      "grad_norm": 47.75,
+      "learning_rate": 4.5e-05,
+      "loss": 6.2436,
+      "step": 45
+    },
+    {
+      "epoch": 0.03351206434316354,
+      "grad_norm": 25.125,
+      "learning_rate": 5e-05,
+      "loss": 5.7614,
+      "step": 50
+    },
+    {
+      "epoch": 0.03686327077747989,
+      "grad_norm": 19.625,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.6177,
+      "step": 55
+    },
+    {
+      "epoch": 0.040214477211796246,
+      "grad_norm": 13.5625,
+      "learning_rate": 6e-05,
+      "loss": 5.3004,
+      "step": 60
+    },
+    {
+      "epoch": 0.0435656836461126,
+      "grad_norm": 21.375,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 4.9812,
+      "step": 65
+    },
+    {
+      "epoch": 0.04691689008042895,
+      "grad_norm": 14.6875,
+      "learning_rate": 7e-05,
+      "loss": 4.827,
+      "step": 70
+    },
+    {
+      "epoch": 0.05026809651474531,
+      "grad_norm": 15.6875,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 4.4671,
+      "step": 75
+    },
+    {
+      "epoch": 0.05361930294906166,
+      "grad_norm": 13.4375,
+      "learning_rate": 8e-05,
+      "loss": 4.5079,
+      "step": 80
+    },
+    {
+      "epoch": 0.05697050938337802,
+      "grad_norm": 15.8125,
+      "learning_rate": 8.5e-05,
+      "loss": 4.2763,
+      "step": 85
+    },
+    {
+      "epoch": 0.06032171581769437,
+      "grad_norm": 18.625,
+      "learning_rate": 9e-05,
+      "loss": 4.1637,
+      "step": 90
+    },
+    {
+      "epoch": 0.06367292225201072,
+      "grad_norm": 15.125,
+      "learning_rate": 9.5e-05,
+      "loss": 4.0087,
+      "step": 95
+    },
+    {
+      "epoch": 0.06702412868632708,
+      "grad_norm": 12.875,
+      "learning_rate": 0.0001,
+      "loss": 3.9387,
+      "step": 100
+    },
+    {
+      "epoch": 0.07037533512064344,
+      "grad_norm": 14.0,
+      "learning_rate": 0.000105,
+      "loss": 3.9187,
+      "step": 105
+    },
+    {
+      "epoch": 0.07372654155495978,
+      "grad_norm": 12.0,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 3.808,
+      "step": 110
+    },
+    {
+      "epoch": 0.07707774798927614,
+      "grad_norm": 12.1875,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 3.6024,
+      "step": 115
+    },
+    {
+      "epoch": 0.08042895442359249,
+      "grad_norm": 11.4375,
+      "learning_rate": 0.00012,
+      "loss": 3.6723,
+      "step": 120
+    },
+    {
+      "epoch": 0.08378016085790885,
+      "grad_norm": 11.5625,
+      "learning_rate": 0.000125,
+      "loss": 3.5476,
+      "step": 125
+    },
+    {
+      "epoch": 0.0871313672922252,
+      "grad_norm": 11.0,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 3.4838,
+      "step": 130
+    },
+    {
+      "epoch": 0.09048257372654156,
+      "grad_norm": 10.375,
+      "learning_rate": 0.00013500000000000003,
+      "loss": 3.5531,
+      "step": 135
+    },
+    {
+      "epoch": 0.0938337801608579,
+      "grad_norm": 11.75,
+      "learning_rate": 0.00014,
+      "loss": 3.4721,
+      "step": 140
+    },
+    {
+      "epoch": 0.09718498659517426,
+      "grad_norm": 11.75,
+      "learning_rate": 0.000145,
+      "loss": 3.4215,
+      "step": 145
+    },
+    {
+      "epoch": 0.10053619302949061,
+      "grad_norm": 11.5,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.5449,
+      "step": 150
+    },
+    {
+      "epoch": 0.10388739946380697,
+      "grad_norm": 19.0,
+      "learning_rate": 0.000155,
+      "loss": 3.3309,
+      "step": 155
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 10.0,
+      "learning_rate": 0.00016,
+      "loss": 3.3066,
+      "step": 160
+    },
+    {
+      "epoch": 0.11058981233243968,
+      "grad_norm": 13.25,
+      "learning_rate": 0.000165,
+      "loss": 3.3844,
+      "step": 165
+    },
+    {
+      "epoch": 0.11394101876675604,
+      "grad_norm": 10.5625,
+      "learning_rate": 0.00017,
+      "loss": 3.2758,
+      "step": 170
+    },
+    {
+      "epoch": 0.11729222520107238,
+      "grad_norm": 10.75,
+      "learning_rate": 0.000175,
+      "loss": 3.4125,
+      "step": 175
+    },
+    {
+      "epoch": 0.12064343163538874,
+      "grad_norm": 10.0,
+      "learning_rate": 0.00018,
+      "loss": 3.0847,
+      "step": 180
+    },
+    {
+      "epoch": 0.1239946380697051,
+      "grad_norm": 23.5,
+      "learning_rate": 0.00018500000000000002,
+      "loss": 3.1467,
+      "step": 185
+    },
+    {
+      "epoch": 0.12734584450402145,
+      "grad_norm": 8.0625,
+      "learning_rate": 0.00019,
+      "loss": 3.1672,
+      "step": 190
+    },
+    {
+      "epoch": 0.1306970509383378,
+      "grad_norm": 7.21875,
+      "learning_rate": 0.000195,
+      "loss": 3.2039,
+      "step": 195
+    },
+    {
+      "epoch": 0.13404825737265416,
+      "grad_norm": 6.71875,
+      "learning_rate": 0.0002,
+      "loss": 3.2238,
+      "step": 200
+    },
+    {
+      "epoch": 0.13739946380697052,
+      "grad_norm": 8.0625,
+      "learning_rate": 0.00019999619230641713,
+      "loss": 3.1889,
+      "step": 205
+    },
+    {
+      "epoch": 0.14075067024128687,
+      "grad_norm": 13.4375,
+      "learning_rate": 0.00019998476951563915,
+      "loss": 3.1551,
+      "step": 210
+    },
+    {
+      "epoch": 0.14410187667560323,
+      "grad_norm": 11.0,
+      "learning_rate": 0.00019996573249755572,
+      "loss": 3.1229,
+      "step": 215
+    },
+    {
+      "epoch": 0.14745308310991956,
+      "grad_norm": 8.375,
+      "learning_rate": 0.0001999390827019096,
+      "loss": 3.0822,
+      "step": 220
+    },
+    {
+      "epoch": 0.15080428954423591,
+      "grad_norm": 7.875,
+      "learning_rate": 0.0001999048221581858,
+      "loss": 2.9755,
+      "step": 225
+    },
+    {
+      "epoch": 0.15415549597855227,
+      "grad_norm": 8.5,
+      "learning_rate": 0.0001998629534754574,
+      "loss": 3.0043,
+      "step": 230
+    },
+    {
+      "epoch": 0.15750670241286863,
+      "grad_norm": 9.0625,
+      "learning_rate": 0.0001998134798421867,
+      "loss": 2.9992,
+      "step": 235
+    },
+    {
+      "epoch": 0.16085790884718498,
+      "grad_norm": 13.4375,
+      "learning_rate": 0.00019975640502598244,
+      "loss": 3.0183,
+      "step": 240
+    },
+    {
+      "epoch": 0.16420911528150134,
+      "grad_norm": 10.875,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 3.004,
+      "step": 245
+    },
+    {
+      "epoch": 0.1675603217158177,
+      "grad_norm": 7.75,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 3.0863,
+      "step": 250
+    },
+    {
+      "epoch": 0.17091152815013405,
+      "grad_norm": 7.71875,
+      "learning_rate": 0.00019953961983671788,
+      "loss": 2.7425,
+      "step": 255
+    },
+    {
+      "epoch": 0.1742627345844504,
+      "grad_norm": 9.5625,
+      "learning_rate": 0.00019945218953682734,
+      "loss": 3.0072,
+      "step": 260
+    },
+    {
+      "epoch": 0.17761394101876676,
+      "grad_norm": 7.96875,
+      "learning_rate": 0.00019935718556765876,
+      "loss": 2.9687,
+      "step": 265
+    },
+    {
+      "epoch": 0.18096514745308312,
+      "grad_norm": 8.8125,
+      "learning_rate": 0.00019925461516413223,
+      "loss": 2.9539,
+      "step": 270
+    },
+    {
+      "epoch": 0.18431635388739948,
+      "grad_norm": 7.46875,
+      "learning_rate": 0.00019914448613738106,
+      "loss": 2.8877,
+      "step": 275
+    },
+    {
+      "epoch": 0.1876675603217158,
+      "grad_norm": 5.65625,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 2.8264,
+      "step": 280
+    },
+    {
+      "epoch": 0.19101876675603216,
+      "grad_norm": 6.375,
+      "learning_rate": 0.0001989015863361917,
+      "loss": 2.8201,
+      "step": 285
+    },
+    {
+      "epoch": 0.19436997319034852,
+      "grad_norm": 6.09375,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 2.8141,
+      "step": 290
+    },
+    {
+      "epoch": 0.19772117962466487,
+      "grad_norm": 7.0,
+      "learning_rate": 0.00019862856015372317,
+      "loss": 2.9018,
+      "step": 295
+    },
+    {
+      "epoch": 0.20107238605898123,
+      "grad_norm": 6.34375,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 2.8597,
+      "step": 300
+    },
+    {
+      "epoch": 0.20442359249329758,
+      "grad_norm": 8.9375,
+      "learning_rate": 0.0001983254907563955,
+      "loss": 2.8288,
+      "step": 305
+    },
+    {
+      "epoch": 0.20777479892761394,
+      "grad_norm": 21.375,
+      "learning_rate": 0.00019816271834476642,
+      "loss": 2.8927,
+      "step": 310
+    },
+    {
+      "epoch": 0.2111260053619303,
+      "grad_norm": 9.9375,
+      "learning_rate": 0.00019799247046208297,
+      "loss": 2.6922,
+      "step": 315
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 6.21875,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.9288,
+      "step": 320
+    },
+    {
+      "epoch": 0.217828418230563,
+      "grad_norm": 4.84375,
+      "learning_rate": 0.00019762960071199333,
+      "loss": 2.7749,
+      "step": 325
+    },
+    {
+      "epoch": 0.22117962466487937,
+      "grad_norm": 6.28125,
+      "learning_rate": 0.00019743700647852354,
+      "loss": 2.725,
+      "step": 330
+    },
+    {
+      "epoch": 0.22453083109919572,
+      "grad_norm": 11.8125,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 2.9425,
+      "step": 335
+    },
+    {
+      "epoch": 0.22788203753351208,
+      "grad_norm": 6.9375,
+      "learning_rate": 0.00019702957262759965,
+      "loss": 2.744,
+      "step": 340
+    },
+    {
+      "epoch": 0.2312332439678284,
+      "grad_norm": 5.0625,
+      "learning_rate": 0.0001968147640378108,
+      "loss": 2.6849,
+      "step": 345
+    },
+    {
+      "epoch": 0.23458445040214476,
+      "grad_norm": 5.9375,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 2.9359,
+      "step": 350
+    },
+    {
+      "epoch": 0.23793565683646112,
+      "grad_norm": 8.0,
+      "learning_rate": 0.0001963630453208623,
+      "loss": 2.7998,
+      "step": 355
+    },
+    {
+      "epoch": 0.24128686327077747,
+      "grad_norm": 4.4375,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 2.6601,
+      "step": 360
+    },
+    {
+      "epoch": 0.24463806970509383,
+      "grad_norm": 5.1875,
+      "learning_rate": 0.0001958819734868193,
+      "loss": 2.6936,
+      "step": 365
+    },
+    {
+      "epoch": 0.2479892761394102,
+      "grad_norm": 5.25,
+      "learning_rate": 0.00019563047559630357,
+      "loss": 2.7705,
+      "step": 370
+    },
+    {
+      "epoch": 0.25134048257372654,
+      "grad_norm": 5.96875,
+      "learning_rate": 0.0001953716950748227,
+      "loss": 2.8504,
+      "step": 375
+    },
+    {
+      "epoch": 0.2546916890080429,
+      "grad_norm": 5.78125,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.5577,
+      "step": 380
+    },
+    {
+      "epoch": 0.25804289544235925,
+      "grad_norm": 5.5,
+      "learning_rate": 0.00019483236552061994,
+      "loss": 2.7717,
+      "step": 385
+    },
+    {
+      "epoch": 0.2613941018766756,
+      "grad_norm": 4.8125,
+      "learning_rate": 0.0001945518575599317,
+      "loss": 2.6139,
+      "step": 390
+    },
+    {
+      "epoch": 0.26474530831099197,
+      "grad_norm": 60.75,
+      "learning_rate": 0.00019426414910921787,
+      "loss": 2.7684,
+      "step": 395
+    },
+    {
+      "epoch": 0.2680965147453083,
+      "grad_norm": 4.53125,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 2.6009,
+      "step": 400
+    },
+    {
+      "epoch": 0.2714477211796247,
+      "grad_norm": 5.28125,
+      "learning_rate": 0.00019366721892483978,
+      "loss": 2.6487,
+      "step": 405
+    },
+    {
+      "epoch": 0.27479892761394104,
+      "grad_norm": 4.625,
+      "learning_rate": 0.00019335804264972018,
+      "loss": 2.5787,
+      "step": 410
+    },
+    {
+      "epoch": 0.2781501340482574,
+      "grad_norm": 4.78125,
+      "learning_rate": 0.00019304175679820247,
+      "loss": 2.5201,
+      "step": 415
+    },
+    {
+      "epoch": 0.28150134048257375,
+      "grad_norm": 4.5,
+      "learning_rate": 0.00019271838545667876,
+      "loss": 2.575,
+      "step": 420
+    },
+    {
+      "epoch": 0.2848525469168901,
+      "grad_norm": 10.4375,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 2.4937,
+      "step": 425
+    },
+    {
+      "epoch": 0.28820375335120646,
+      "grad_norm": 14.5625,
+      "learning_rate": 0.00019205048534524406,
+      "loss": 2.6559,
+      "step": 430
+    },
+    {
+      "epoch": 0.2915549597855228,
+      "grad_norm": 4.28125,
+      "learning_rate": 0.0001917060074385124,
+      "loss": 2.529,
+      "step": 435
+    },
+    {
+      "epoch": 0.2949061662198391,
+      "grad_norm": 4.125,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.6327,
+      "step": 440
+    },
+    {
+      "epoch": 0.2982573726541555,
+      "grad_norm": 4.96875,
+      "learning_rate": 0.00019099612708765434,
+      "loss": 2.6676,
+      "step": 445
+    },
+    {
+      "epoch": 0.30160857908847183,
+      "grad_norm": 4.84375,
+      "learning_rate": 0.000190630778703665,
+      "loss": 2.531,
+      "step": 450
+    },
+    {
+      "epoch": 0.3049597855227882,
+      "grad_norm": 4.40625,
+      "learning_rate": 0.00019025852843498607,
+      "loss": 2.586,
+      "step": 455
+    },
+    {
+      "epoch": 0.30831099195710454,
+      "grad_norm": 4.1875,
+      "learning_rate": 0.0001898794046299167,
+      "loss": 2.6193,
+      "step": 460
+    },
+    {
+      "epoch": 0.3116621983914209,
+      "grad_norm": 4.375,
+      "learning_rate": 0.00018949343616020252,
+      "loss": 2.5805,
+      "step": 465
+    },
+    {
+      "epoch": 0.31501340482573725,
+      "grad_norm": 4.1875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 2.6252,
+      "step": 470
+    },
+    {
+      "epoch": 0.3183646112600536,
+      "grad_norm": 3.9375,
+      "learning_rate": 0.00018870108331782217,
+      "loss": 2.5582,
+      "step": 475
+    },
+    {
+      "epoch": 0.32171581769436997,
+      "grad_norm": 4.90625,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 2.6244,
+      "step": 480
+    },
+    {
+      "epoch": 0.3250670241286863,
+      "grad_norm": 31.375,
+      "learning_rate": 0.00018788171126619653,
+      "loss": 2.651,
+      "step": 485
+    },
+    {
+      "epoch": 0.3284182305630027,
+      "grad_norm": 4.5,
+      "learning_rate": 0.00018746197071393958,
+      "loss": 2.5153,
+      "step": 490
+    },
+    {
+      "epoch": 0.33176943699731903,
+      "grad_norm": 4.15625,
+      "learning_rate": 0.00018703556959398998,
+      "loss": 2.6416,
+      "step": 495
+    },
+    {
+      "epoch": 0.3351206434316354,
+      "grad_norm": 4.90625,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.5965,
+      "step": 500
+    },
+    {
+      "epoch": 0.3351206434316354,
+      "eval_128_ap": 0.6946773245581791,
+      "eval_128_auc": 0.9680845837539295,
+      "eval_128_loss": 2.086740016937256,
+      "eval_128_runtime": 19.4102,
+      "eval_128_samples_per_second": 20.608,
+      "eval_128_steps_per_second": 5.152,
+      "step": 500
+    },
+    {
+      "epoch": 0.33847184986595175,
+      "grad_norm": 4.4375,
+      "learning_rate": 0.00018616291604415258,
+      "loss": 2.435,
+      "step": 505
+    },
+    {
+      "epoch": 0.3418230563002681,
+      "grad_norm": 4.875,
+      "learning_rate": 0.00018571673007021123,
+      "loss": 2.5466,
+      "step": 510
+    },
+    {
+      "epoch": 0.34517426273458446,
+      "grad_norm": 3.875,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 2.6,
+      "step": 515
+    },
+    {
+      "epoch": 0.3485254691689008,
+      "grad_norm": 6.34375,
+      "learning_rate": 0.0001848048096156426,
+      "loss": 2.4788,
+      "step": 520
+    },
+    {
+      "epoch": 0.35187667560321717,
+      "grad_norm": 4.0625,
+      "learning_rate": 0.0001843391445812886,
+      "loss": 2.4897,
+      "step": 525
+    },
+    {
+      "epoch": 0.3552278820375335,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.00018386705679454242,
+      "loss": 2.3744,
+      "step": 530
+    },
+    {
+      "epoch": 0.3585790884718499,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.00018338858220671682,
+      "loss": 2.5395,
+      "step": 535
+    },
+    {
+      "epoch": 0.36193029490616624,
+      "grad_norm": 4.28125,
+      "learning_rate": 0.00018290375725550417,
+      "loss": 2.4539,
+      "step": 540
+    },
+    {
+      "epoch": 0.3652815013404826,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.00018241261886220154,
+      "loss": 2.4642,
+      "step": 545
+    },
+    {
+      "epoch": 0.36863270777479895,
+      "grad_norm": 5.03125,
+      "learning_rate": 0.0001819152044288992,
+      "loss": 2.5463,
+      "step": 550
+    },
+    {
+      "epoch": 0.3719839142091153,
+      "grad_norm": 3.921875,
+      "learning_rate": 0.00018141155183563193,
+      "loss": 2.4316,
+      "step": 555
+    },
+    {
+      "epoch": 0.3753351206434316,
+      "grad_norm": 6.3125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.4111,
+      "step": 560
+    },
+    {
+      "epoch": 0.37868632707774796,
+      "grad_norm": 4.84375,
+      "learning_rate": 0.00018038568606172173,
+      "loss": 2.5699,
+      "step": 565
+    },
+    {
+      "epoch": 0.3820375335120643,
+      "grad_norm": 4.40625,
+      "learning_rate": 0.00017986355100472928,
+      "loss": 2.3959,
+      "step": 570
+    },
+    {
+      "epoch": 0.3853887399463807,
+      "grad_norm": 4.34375,
+      "learning_rate": 0.00017933533402912354,
+      "loss": 2.4525,
+      "step": 575
+    },
+    {
+      "epoch": 0.38873994638069703,
+      "grad_norm": 4.375,
+      "learning_rate": 0.00017880107536067218,
+      "loss": 2.5208,
+      "step": 580
+    },
+    {
+      "epoch": 0.3920911528150134,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.0001782608156852414,
+      "loss": 2.482,
+      "step": 585
+    },
+    {
+      "epoch": 0.39544235924932974,
+      "grad_norm": 4.375,
+      "learning_rate": 0.0001777145961456971,
+      "loss": 2.4212,
+      "step": 590
+    },
+    {
+      "epoch": 0.3987935656836461,
+      "grad_norm": 4.4375,
+      "learning_rate": 0.00017716245833877201,
+      "loss": 2.4238,
+      "step": 595
+    },
+    {
+      "epoch": 0.40214477211796246,
+      "grad_norm": 4.90625,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 2.4752,
+      "step": 600
+    },
+    {
+      "epoch": 0.4054959785522788,
+      "grad_norm": 4.15625,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 2.4592,
+      "step": 605
+    },
+    {
+      "epoch": 0.40884718498659517,
+      "grad_norm": 4.0625,
+      "learning_rate": 0.00017547095802227723,
+      "loss": 2.3419,
+      "step": 610
+    },
+    {
+      "epoch": 0.4121983914209115,
+      "grad_norm": 3.75,
+      "learning_rate": 0.00017489557207890023,
+      "loss": 2.4173,
+      "step": 615
+    },
+    {
+      "epoch": 0.4155495978552279,
+      "grad_norm": 4.3125,
+      "learning_rate": 0.00017431448254773944,
+      "loss": 2.4782,
+      "step": 620
+    },
+    {
+      "epoch": 0.41890080428954424,
+      "grad_norm": 4.96875,
+      "learning_rate": 0.0001737277336810124,
+      "loss": 2.4608,
+      "step": 625
+    },
+    {
+      "epoch": 0.4222520107238606,
+      "grad_norm": 3.453125,
+      "learning_rate": 0.00017313537016191706,
+      "loss": 2.3687,
+      "step": 630
+    },
+    {
+      "epoch": 0.42560321715817695,
+      "grad_norm": 4.0,
+      "learning_rate": 0.00017253743710122878,
+      "loss": 2.5249,
+      "step": 635
+    },
+    {
+      "epoch": 0.4289544235924933,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.0001719339800338651,
+      "loss": 2.3771,
+      "step": 640
+    },
+    {
+      "epoch": 0.43230563002680966,
+      "grad_norm": 3.90625,
+      "learning_rate": 0.00017132504491541818,
+      "loss": 2.5041,
+      "step": 645
+    },
+    {
+      "epoch": 0.435656836461126,
+      "grad_norm": 3.53125,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.2476,
+      "step": 650
+    },
+    {
+      "epoch": 0.4390080428954424,
+      "grad_norm": 4.3125,
+      "learning_rate": 0.0001700909264299851,
+      "loss": 2.4838,
+      "step": 655
+    },
+    {
+      "epoch": 0.44235924932975873,
+      "grad_norm": 3.421875,
+      "learning_rate": 0.00016946583704589973,
+      "loss": 2.3025,
+      "step": 660
+    },
+    {
+      "epoch": 0.4457104557640751,
+      "grad_norm": 6.125,
+      "learning_rate": 0.0001688354575693754,
+      "loss": 2.3728,
+      "step": 665
+    },
+    {
+      "epoch": 0.44906166219839144,
+      "grad_norm": 3.578125,
+      "learning_rate": 0.00016819983600624986,
+      "loss": 2.3742,
+      "step": 670
+    },
+    {
+      "epoch": 0.4524128686327078,
+      "grad_norm": 3.8125,
+      "learning_rate": 0.00016755902076156604,
+      "loss": 2.5019,
+      "step": 675
+    },
+    {
+      "epoch": 0.45576407506702415,
+      "grad_norm": 6.09375,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.4063,
+      "step": 680
+    },
+    {
+      "epoch": 0.45911528150134046,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.00016626200482157378,
+      "loss": 2.3548,
+      "step": 685
+    },
+    {
+      "epoch": 0.4624664879356568,
+      "grad_norm": 4.375,
+      "learning_rate": 0.00016560590289905073,
+      "loss": 2.3674,
+      "step": 690
+    },
+    {
+      "epoch": 0.46581769436997317,
+      "grad_norm": 3.859375,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 2.3071,
+      "step": 695
+    },
+    {
+      "epoch": 0.4691689008042895,
+      "grad_norm": 3.71875,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 2.3699,
+      "step": 700
+    },
+    {
+      "epoch": 0.4725201072386059,
+      "grad_norm": 3.859375,
+      "learning_rate": 0.0001636078220277764,
+      "loss": 2.2788,
+      "step": 705
+    },
+    {
+      "epoch": 0.47587131367292224,
+      "grad_norm": 3.546875,
+      "learning_rate": 0.00016293203910498376,
+      "loss": 2.2637,
+      "step": 710
+    },
+    {
+      "epoch": 0.4792225201072386,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.00016225146366376198,
+      "loss": 2.3791,
+      "step": 715
+    },
+    {
+      "epoch": 0.48257372654155495,
+      "grad_norm": 3.46875,
+      "learning_rate": 0.00016156614753256584,
+      "loss": 2.2704,
+      "step": 720
+    },
+    {
+      "epoch": 0.4859249329758713,
+      "grad_norm": 6.21875,
+      "learning_rate": 0.00016087614290087208,
+      "loss": 2.3598,
+      "step": 725
+    },
+    {
+      "epoch": 0.48927613941018766,
+      "grad_norm": 3.671875,
+      "learning_rate": 0.00016018150231520483,
+      "loss": 2.4334,
+      "step": 730
+    },
+    {
+      "epoch": 0.492627345844504,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.00015948227867513415,
+      "loss": 2.434,
+      "step": 735
+    },
+    {
+      "epoch": 0.4959785522788204,
+      "grad_norm": 3.640625,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 2.3569,
+      "step": 740
+    },
+    {
+      "epoch": 0.49932975871313673,
+      "grad_norm": 3.6875,
+      "learning_rate": 0.00015807029557109398,
+      "loss": 2.3909,
+      "step": 745
+    },
+    {
+      "epoch": 0.5026809651474531,
+      "grad_norm": 3.765625,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 2.3255,
+      "step": 750
+    },
+    {
+      "epoch": 0.5060321715817694,
+      "grad_norm": 3.421875,
+      "learning_rate": 0.00015664062369248328,
+      "loss": 2.2162,
+      "step": 755
+    },
+    {
+      "epoch": 0.5093833780160858,
+      "grad_norm": 4.4375,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 2.2311,
+      "step": 760
+    },
+    {
+      "epoch": 0.5127345844504021,
+      "grad_norm": 12.0625,
+      "learning_rate": 0.0001551936985312058,
+      "loss": 2.2553,
+      "step": 765
+    },
+    {
+      "epoch": 0.5160857908847185,
+      "grad_norm": 3.90625,
+      "learning_rate": 0.0001544639035015027,
+      "loss": 2.3287,
+      "step": 770
+    },
+    {
+      "epoch": 0.5194369973190348,
+      "grad_norm": 3.484375,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 2.3142,
+      "step": 775
+    },
+    {
+      "epoch": 0.5227882037533512,
+      "grad_norm": 3.375,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 2.3647,
+      "step": 780
+    },
+    {
+      "epoch": 0.5261394101876675,
+      "grad_norm": 4.1875,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 2.2755,
+      "step": 785
+    },
+    {
+      "epoch": 0.5294906166219839,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.00015150380749100545,
+      "loss": 2.1969,
+      "step": 790
+    },
+    {
+      "epoch": 0.5328418230563002,
+      "grad_norm": 3.46875,
+      "learning_rate": 0.00015075383629607042,
+      "loss": 2.3177,
+      "step": 795
+    },
+    {
+      "epoch": 0.5361930294906166,
+      "grad_norm": 3.875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.2585,
+      "step": 800
+    },
+    {
+      "epoch": 0.539544235924933,
+      "grad_norm": 3.8125,
+      "learning_rate": 0.00014924235601034672,
+      "loss": 2.3202,
+      "step": 805
+    },
+    {
+      "epoch": 0.5428954423592494,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.00014848096202463372,
+      "loss": 2.2391,
+      "step": 810
+    },
+    {
+      "epoch": 0.5462466487935657,
+      "grad_norm": 4.15625,
+      "learning_rate": 0.00014771587602596084,
+      "loss": 2.1343,
+      "step": 815
+    },
+    {
+      "epoch": 0.5495978552278821,
+      "grad_norm": 3.203125,
+      "learning_rate": 0.00014694715627858908,
+      "loss": 2.2725,
+      "step": 820
+    },
+    {
+      "epoch": 0.5529490616621984,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 2.1359,
+      "step": 825
+    },
+    {
+      "epoch": 0.5563002680965148,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 2.081,
+      "step": 830
+    },
+    {
+      "epoch": 0.5596514745308311,
+      "grad_norm": 3.15625,
+      "learning_rate": 0.00014461978131098088,
+      "loss": 2.1051,
+      "step": 835
+    },
+    {
+      "epoch": 0.5630026809651475,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00014383711467890774,
+      "loss": 2.1229,
+      "step": 840
+    },
+    {
+      "epoch": 0.5663538873994638,
+      "grad_norm": 4.09375,
+      "learning_rate": 0.00014305110968082952,
+      "loss": 2.2683,
+      "step": 845
+    },
+    {
+      "epoch": 0.5697050938337802,
+      "grad_norm": 3.484375,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 2.1467,
+      "step": 850
+    },
+    {
+      "epoch": 0.5730563002680965,
+      "grad_norm": 3.640625,
+      "learning_rate": 0.00014146932426562392,
+      "loss": 2.1038,
+      "step": 855
+    },
+    {
+      "epoch": 0.5764075067024129,
+      "grad_norm": 3.390625,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 2.3725,
+      "step": 860
+    },
+    {
+      "epoch": 0.5797587131367292,
+      "grad_norm": 5.125,
+      "learning_rate": 0.00013987490689252463,
+      "loss": 2.1452,
+      "step": 865
+    },
+    {
+      "epoch": 0.5831099195710456,
+      "grad_norm": 3.421875,
+      "learning_rate": 0.00013907311284892736,
+      "loss": 2.1279,
+      "step": 870
+    },
+    {
+      "epoch": 0.5864611260053619,
+      "grad_norm": 3.265625,
+      "learning_rate": 0.000138268343236509,
+      "loss": 2.2028,
+      "step": 875
+    },
+    {
+      "epoch": 0.5898123324396782,
+      "grad_norm": 3.546875,
+      "learning_rate": 0.00013746065934159123,
+      "loss": 2.2621,
+      "step": 880
+    },
+    {
+      "epoch": 0.5931635388739946,
+      "grad_norm": 3.40625,
+      "learning_rate": 0.00013665012267242974,
+      "loss": 2.3162,
+      "step": 885
+    },
+    {
+      "epoch": 0.596514745308311,
+      "grad_norm": 3.3125,
+      "learning_rate": 0.00013583679495453,
+      "loss": 2.2635,
+      "step": 890
+    },
+    {
+      "epoch": 0.5998659517426274,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.00013502073812594675,
+      "loss": 2.2185,
+      "step": 895
+    },
+    {
+      "epoch": 0.6032171581769437,
+      "grad_norm": 3.40625,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 2.1357,
+      "step": 900
+    },
+    {
+      "epoch": 0.6065683646112601,
+      "grad_norm": 3.875,
+      "learning_rate": 0.0001333806859233771,
+      "loss": 2.1906,
+      "step": 905
+    },
+    {
+      "epoch": 0.6099195710455764,
+      "grad_norm": 3.578125,
+      "learning_rate": 0.00013255681544571568,
+      "loss": 2.1371,
+      "step": 910
+    },
+    {
+      "epoch": 0.6132707774798928,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00013173046564050924,
+      "loss": 2.1377,
+      "step": 915
+    },
+    {
+      "epoch": 0.6166219839142091,
+      "grad_norm": 3.078125,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1863,
+      "step": 920
+    },
+    {
+      "epoch": 0.6199731903485255,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 2.1153,
+      "step": 925
+    },
+    {
+      "epoch": 0.6233243967828418,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00012923717047227368,
+      "loss": 2.1994,
+      "step": 930
+    },
+    {
+      "epoch": 0.6266756032171582,
+      "grad_norm": 3.203125,
+      "learning_rate": 0.00012840153447039228,
+      "loss": 2.205,
+      "step": 935
+    },
+    {
+      "epoch": 0.6300268096514745,
+      "grad_norm": 3.46875,
+      "learning_rate": 0.0001275637355816999,
+      "loss": 2.1964,
+      "step": 940
+    },
+    {
+      "epoch": 0.6333780160857909,
+      "grad_norm": 3.625,
+      "learning_rate": 0.00012672383760782568,
+      "loss": 2.1978,
+      "step": 945
+    },
+    {
+      "epoch": 0.6367292225201072,
+      "grad_norm": 3.171875,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 2.1862,
+      "step": 950
+    },
+    {
+      "epoch": 0.6400804289544236,
+      "grad_norm": 3.296875,
+      "learning_rate": 0.00012503800040544416,
+      "loss": 2.1544,
+      "step": 955
+    },
+    {
+      "epoch": 0.6434316353887399,
+      "grad_norm": 3.46875,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 2.1247,
+      "step": 960
+    },
+    {
+      "epoch": 0.6467828418230563,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 2.132,
+      "step": 965
+    },
+    {
+      "epoch": 0.6501340482573726,
+      "grad_norm": 3.5,
+      "learning_rate": 0.0001224951054343865,
+      "loss": 2.0192,
+      "step": 970
+    },
+    {
+      "epoch": 0.653485254691689,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 2.0863,
+      "step": 975
+    },
+    {
+      "epoch": 0.6568364611260054,
+      "grad_norm": 3.234375,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 2.162,
+      "step": 980
+    },
+    {
+      "epoch": 0.6601876675603218,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.00011993679344171973,
+      "loss": 2.2546,
+      "step": 985
+    },
+    {
+      "epoch": 0.6635388739946381,
+      "grad_norm": 3.640625,
+      "learning_rate": 0.00011908089953765449,
+      "loss": 2.1244,
+      "step": 990
+    },
+    {
+      "epoch": 0.6668900804289544,
+      "grad_norm": 3.515625,
+      "learning_rate": 0.00011822355254921478,
+      "loss": 2.1339,
+      "step": 995
+    },
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 5.46875,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.1744,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6702412868632708,
+      "eval_128_ap": 0.7636418814117207,
+      "eval_128_auc": 0.9774185615872945,
+      "eval_128_loss": 1.7800103425979614,
+      "eval_128_runtime": 21.8273,
+      "eval_128_samples_per_second": 18.326,
+      "eval_128_steps_per_second": 4.581,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6735924932975871,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.00011650476058606777,
+      "loss": 1.9784,
+      "step": 1005
+    },
+    {
+      "epoch": 0.6769436997319035,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.9891,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6802949061662198,
+      "grad_norm": 3.8125,
+      "learning_rate": 0.00011478094111296109,
+      "loss": 2.0137,
+      "step": 1015
+    },
+    {
+      "epoch": 0.6836461126005362,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.00011391731009600654,
+      "loss": 2.0556,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6869973190348525,
+      "grad_norm": 3.140625,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 2.0577,
+      "step": 1025
+    },
+    {
+      "epoch": 0.6903485254691689,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00011218693434051475,
+      "loss": 2.0269,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6936997319034852,
+      "grad_norm": 3.28125,
+      "learning_rate": 0.0001113203213767907,
+      "loss": 2.0982,
+      "step": 1035
+    },
+    {
+      "epoch": 0.6970509383378016,
+      "grad_norm": 3.28125,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.1156,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7004021447721179,
+      "grad_norm": 3.140625,
+      "learning_rate": 0.00010958457525202241,
+      "loss": 2.0988,
+      "step": 1045
+    },
+    {
+      "epoch": 0.7037533512064343,
+      "grad_norm": 3.40625,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 2.0687,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7071045576407506,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 2.0488,
+      "step": 1055
+    },
+    {
+      "epoch": 0.710455764075067,
+      "grad_norm": 3.390625,
+      "learning_rate": 0.00010697564737441252,
+      "loss": 2.1562,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7138069705093834,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00010610485395348571,
+      "loss": 2.0119,
+      "step": 1065
+    },
+    {
+      "epoch": 0.7171581769436998,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.0001052335956242944,
+      "loss": 2.0686,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7205093833780161,
+      "grad_norm": 3.65625,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 2.0053,
+      "step": 1075
+    },
+    {
+      "epoch": 0.7238605898123325,
+      "grad_norm": 3.15625,
+      "learning_rate": 0.00010348994967025012,
+      "loss": 2.0279,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7272117962466488,
+      "grad_norm": 3.3125,
+      "learning_rate": 0.00010261769483078733,
+      "loss": 2.2239,
+      "step": 1085
+    },
+    {
+      "epoch": 0.7305630026809652,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00010174524064372837,
+      "loss": 2.0663,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7339142091152815,
+      "grad_norm": 3.25,
+      "learning_rate": 0.0001008726535498374,
+      "loss": 2.1292,
+      "step": 1095
+    },
+    {
+      "epoch": 0.7372654155495979,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0001,
+      "loss": 2.0677,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7406166219839142,
+      "grad_norm": 3.109375,
+      "learning_rate": 9.912734645016263e-05,
+      "loss": 1.9551,
+      "step": 1105
+    },
+    {
+      "epoch": 0.7439678284182306,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.825475935627165e-05,
+      "loss": 2.0803,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7473190348525469,
+      "grad_norm": 3.25,
+      "learning_rate": 9.73823051692127e-05,
+      "loss": 2.114,
+      "step": 1115
+    },
+    {
+      "epoch": 0.7506702412868632,
+      "grad_norm": 3.0625,
+      "learning_rate": 9.651005032974994e-05,
+      "loss": 2.0298,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7540214477211796,
+      "grad_norm": 3.203125,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 2.15,
+      "step": 1125
+    },
+    {
+      "epoch": 0.7573726541554959,
+      "grad_norm": 3.359375,
+      "learning_rate": 9.476640437570562e-05,
+      "loss": 2.0435,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7607238605898123,
+      "grad_norm": 3.140625,
+      "learning_rate": 9.38951460465143e-05,
+      "loss": 2.0872,
+      "step": 1135
+    },
+    {
+      "epoch": 0.7640750670241286,
+      "grad_norm": 3.421875,
+      "learning_rate": 9.302435262558747e-05,
+      "loss": 1.981,
+      "step": 1140
+    },
+    {
+      "epoch": 0.767426273458445,
+      "grad_norm": 2.796875,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 1.9386,
+      "step": 1145
+    },
+    {
+      "epoch": 0.7707774798927614,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 2.0754,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7741286863270778,
+      "grad_norm": 3.234375,
+      "learning_rate": 9.04154247479776e-05,
+      "loss": 2.0129,
+      "step": 1155
+    },
+    {
+      "epoch": 0.7774798927613941,
+      "grad_norm": 3.328125,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.099,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7808310991957105,
+      "grad_norm": 3.171875,
+      "learning_rate": 8.867967862320934e-05,
+      "loss": 2.055,
+      "step": 1165
+    },
+    {
+      "epoch": 0.7841823056300268,
+      "grad_norm": 3.109375,
+      "learning_rate": 8.781306565948528e-05,
+      "loss": 1.9264,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7875335120643432,
+      "grad_norm": 3.359375,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.9382,
+      "step": 1175
+    },
+    {
+      "epoch": 0.7908847184986595,
+      "grad_norm": 3.5625,
+      "learning_rate": 8.608268990399349e-05,
+      "loss": 1.9913,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7942359249329759,
+      "grad_norm": 3.390625,
+      "learning_rate": 8.521905888703893e-05,
+      "loss": 2.2202,
+      "step": 1185
+    },
+    {
+      "epoch": 0.7975871313672922,
+      "grad_norm": 3.296875,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9226,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8009383378016086,
+      "grad_norm": 3.375,
+      "learning_rate": 8.349523941393224e-05,
+      "loss": 1.9842,
+      "step": 1195
+    },
+    {
+      "epoch": 0.8042895442359249,
+      "grad_norm": 3.109375,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 2.0414,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8076407506702413,
+      "grad_norm": 3.375,
+      "learning_rate": 8.177644745078526e-05,
+      "loss": 1.9747,
+      "step": 1205
+    },
+    {
+      "epoch": 0.8109919571045576,
+      "grad_norm": 3.1875,
+      "learning_rate": 8.091910046234552e-05,
+      "loss": 2.1483,
+      "step": 1210
+    },
+    {
+      "epoch": 0.814343163538874,
+      "grad_norm": 3.046875,
+      "learning_rate": 8.00632065582803e-05,
+      "loss": 2.003,
+      "step": 1215
+    },
+    {
+      "epoch": 0.8176943699731903,
+      "grad_norm": 3.4375,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 1.9795,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8210455764075067,
+      "grad_norm": 4.46875,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 1.9079,
+      "step": 1225
+    },
+    {
+      "epoch": 0.824396782841823,
+      "grad_norm": 3.046875,
+      "learning_rate": 7.750489456561352e-05,
+      "loss": 1.9086,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8277479892761395,
+      "grad_norm": 3.1875,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 2.138,
+      "step": 1235
+    },
+    {
+      "epoch": 0.8310991957104558,
+      "grad_norm": 3.125,
+      "learning_rate": 7.580781044003324e-05,
+      "loss": 1.9724,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8344504021447721,
+      "grad_norm": 3.265625,
+      "learning_rate": 7.496199959455584e-05,
+      "loss": 2.0067,
+      "step": 1245
+    },
+    {
+      "epoch": 0.8378016085790885,
+      "grad_norm": 3.359375,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.9761,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8411528150134048,
+      "grad_norm": 3.265625,
+      "learning_rate": 7.327616239217431e-05,
+      "loss": 1.9118,
+      "step": 1255
+    },
+    {
+      "epoch": 0.8445040214477212,
+      "grad_norm": 2.96875,
+      "learning_rate": 7.243626441830009e-05,
+      "loss": 1.992,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8478552278820375,
+      "grad_norm": 3.109375,
+      "learning_rate": 7.159846552960774e-05,
+      "loss": 1.9095,
+      "step": 1265
+    },
+    {
+      "epoch": 0.8512064343163539,
+      "grad_norm": 3.0625,
+      "learning_rate": 7.076282952772633e-05,
+      "loss": 1.9637,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8545576407506702,
+      "grad_norm": 3.265625,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 1.9976,
+      "step": 1275
+    },
+    {
+      "epoch": 0.8579088471849866,
+      "grad_norm": 3.203125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.0146,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8612600536193029,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.826953435949081e-05,
+      "loss": 1.9493,
+      "step": 1285
+    },
+    {
+      "epoch": 0.8646112600536193,
+      "grad_norm": 3.25,
+      "learning_rate": 6.744318455428436e-05,
+      "loss": 2.0348,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8679624664879356,
+      "grad_norm": 3.09375,
+      "learning_rate": 6.661931407662292e-05,
+      "loss": 1.9574,
+      "step": 1295
+    },
+    {
+      "epoch": 0.871313672922252,
+      "grad_norm": 3.234375,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 2.023,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8746648793565683,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.497926187405326e-05,
+      "loss": 1.9266,
+      "step": 1305
+    },
+    {
+      "epoch": 0.8780160857908847,
+      "grad_norm": 3.078125,
+      "learning_rate": 6.416320504546997e-05,
+      "loss": 1.9451,
+      "step": 1310
+    },
+    {
+      "epoch": 0.881367292225201,
+      "grad_norm": 3.296875,
+      "learning_rate": 6.334987732757029e-05,
+      "loss": 2.0478,
+      "step": 1315
+    },
+    {
+      "epoch": 0.8847184986595175,
+      "grad_norm": 3.15625,
+      "learning_rate": 6.25393406584088e-05,
+      "loss": 2.0049,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8880697050938338,
+      "grad_norm": 3.15625,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.9374,
+      "step": 1325
+    },
+    {
+      "epoch": 0.8914209115281502,
+      "grad_norm": 3.140625,
+      "learning_rate": 6.092688715107264e-05,
+      "loss": 1.9352,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8947721179624665,
+      "grad_norm": 3.203125,
+      "learning_rate": 6.012509310747538e-05,
+      "loss": 1.8953,
+      "step": 1335
+    },
+    {
+      "epoch": 0.8981233243967829,
+      "grad_norm": 3.25,
+      "learning_rate": 5.9326335692419995e-05,
+      "loss": 2.0176,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9014745308310992,
+      "grad_norm": 3.203125,
+      "learning_rate": 5.853067573437612e-05,
+      "loss": 1.9532,
+      "step": 1345
+    },
+    {
+      "epoch": 0.9048257372654156,
+      "grad_norm": 3.03125,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 1.9968,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9081769436997319,
+      "grad_norm": 3.0625,
+      "learning_rate": 5.694889031917047e-05,
+      "loss": 2.0223,
+      "step": 1355
+    },
+    {
+      "epoch": 0.9115281501340483,
+      "grad_norm": 3.0625,
+      "learning_rate": 5.616288532109225e-05,
+      "loss": 1.8986,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9148793565683646,
+      "grad_norm": 3.109375,
+      "learning_rate": 5.5380218689019125e-05,
+      "loss": 1.8947,
+      "step": 1365
+    },
+    {
+      "epoch": 0.9182305630026809,
+      "grad_norm": 2.9375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 2.0307,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9215817694369973,
+      "grad_norm": 2.859375,
+      "learning_rate": 5.3825138676496624e-05,
+      "loss": 1.8391,
+      "step": 1375
+    },
+    {
+      "epoch": 0.9249329758713136,
+      "grad_norm": 3.078125,
+      "learning_rate": 5.305284372141095e-05,
+      "loss": 1.9281,
+      "step": 1380
+    },
+    {
+      "epoch": 0.92828418230563,
+      "grad_norm": 3.03125,
+      "learning_rate": 5.2284123974039154e-05,
+      "loss": 2.0512,
+      "step": 1385
+    },
+    {
+      "epoch": 0.9316353887399463,
+      "grad_norm": 3.171875,
+      "learning_rate": 5.15190379753663e-05,
+      "loss": 1.9567,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9349865951742627,
+      "grad_norm": 3.125,
+      "learning_rate": 5.07576439896533e-05,
+      "loss": 1.864,
+      "step": 1395
+    },
+    {
+      "epoch": 0.938337801608579,
+      "grad_norm": 3.296875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.9016,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9416890080428955,
+      "grad_norm": 3.28125,
+      "learning_rate": 4.924616370392961e-05,
+      "loss": 2.0128,
+      "step": 1405
+    },
+    {
+      "epoch": 0.9450402144772118,
+      "grad_norm": 2.8125,
+      "learning_rate": 4.8496192508994576e-05,
+      "loss": 2.0419,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9483914209115282,
+      "grad_norm": 3.03125,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 1.964,
+      "step": 1415
+    },
+    {
+      "epoch": 0.9517426273458445,
+      "grad_norm": 3.0625,
+      "learning_rate": 4.700807357667952e-05,
+      "loss": 1.9684,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9550938337801609,
+      "grad_norm": 3.265625,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 1.9713,
+      "step": 1425
+    },
+    {
+      "epoch": 0.9584450402144772,
+      "grad_norm": 3.015625,
+      "learning_rate": 4.553609649849728e-05,
+      "loss": 1.8728,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9617962466487936,
+      "grad_norm": 3.28125,
+      "learning_rate": 4.480630146879419e-05,
+      "loss": 1.8794,
+      "step": 1435
+    },
+    {
+      "epoch": 0.9651474530831099,
+      "grad_norm": 3.296875,
+      "learning_rate": 4.4080709652925336e-05,
+      "loss": 2.017,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9684986595174263,
+      "grad_norm": 3.140625,
+      "learning_rate": 4.335937630751674e-05,
+      "loss": 1.9458,
+      "step": 1445
+    },
+    {
+      "epoch": 0.9718498659517426,
+      "grad_norm": 3.09375,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 2.0505,
+      "step": 1450
+    },
+    {
+      "epoch": 0.975201072386059,
+      "grad_norm": 3.21875,
+      "learning_rate": 4.1929704428906026e-05,
+      "loss": 1.9101,
+      "step": 1455
+    },
+    {
+      "epoch": 0.9785522788203753,
+      "grad_norm": 3.078125,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.8192,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9819034852546917,
+      "grad_norm": 3.0,
+      "learning_rate": 4.0517721324865884e-05,
+      "loss": 1.9514,
+      "step": 1465
+    },
+    {
+      "epoch": 0.985254691689008,
+      "grad_norm": 3.3125,
+      "learning_rate": 3.981849768479517e-05,
+      "loss": 1.9101,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9886058981233244,
+      "grad_norm": 2.96875,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.8583,
+      "step": 1475
+    },
+    {
+      "epoch": 0.9919571045576407,
+      "grad_norm": 3.078125,
+      "learning_rate": 3.843385246743417e-05,
+      "loss": 1.8693,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9953083109919572,
+      "grad_norm": 3.109375,
+      "learning_rate": 3.774853633623806e-05,
+      "loss": 1.952,
+      "step": 1485
+    },
+    {
+      "epoch": 0.9986595174262735,
+      "grad_norm": 2.9375,
+      "learning_rate": 3.7067960895016275e-05,
+      "loss": 1.9502,
+      "step": 1490
+    },
+    {
+      "epoch": 1.0020107238605898,
+      "grad_norm": 4.1875,
+      "learning_rate": 3.6392177972223594e-05,
+      "loss": 1.7212,
+      "step": 1495
+    },
+    {
+      "epoch": 1.0053619302949062,
+      "grad_norm": 2.96875,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.6225,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0053619302949062,
+      "eval_128_ap": 0.7931236608249025,
+      "eval_128_auc": 0.9804633885794023,
+      "eval_128_loss": 1.6620492935180664,
+      "eval_128_runtime": 20.588,
+      "eval_128_samples_per_second": 19.429,
+      "eval_128_steps_per_second": 4.857,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4517613999095808.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b401459a110bcfbc0ae993f2040677ba421d24a5acfed8807cbdd6a9c04c026b
+size 5969