commit 253b5294123490e414ab6ff7ba12c8908ac8e8e8 Author: ModelHub XC Date: Sun May 17 06:33:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: oumi-ai/HallOumi-8B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..df1e34a --- /dev/null +++ b/README.md @@ -0,0 +1,160 @@ +--- +library_name: transformers +license: cc-by-nc-4.0 +datasets: +- oumi-ai/oumi-anli-subset +- oumi-ai/oumi-c2d-d2c-subset +- oumi-ai/oumi-synthetic-claims +- oumi-ai/oumi-synthetic-document-claims +language: +- en +base_model: +- meta-llama/Llama-3.1-8B-Instruct +--- + +[![oumi logo](https://oumi.ai/logo_lockup_black.svg)](https://github.com/oumi-ai/oumi) +[![Made with Oumi](https://badgen.net/badge/Made%20with/Oumi/%23085CFF?icon=https%3A%2F%2Foumi.ai%2Flogo_dark.svg)](https://github.com/oumi-ai/oumi) + +[![Documentation](https://img.shields.io/badge/Documentation-oumi-blue.svg)](https://oumi.ai/docs/en/latest/index.html) +[![Blog](https://img.shields.io/badge/Blog-oumi-blue.svg)](https://oumi.ai/blog) +[![Discord](https://img.shields.io/discord/1286348126797430814?label=Discord)](https://discord.gg/oumi) + +# oumi-ai/HallOumi-8B + + + +Introducing **HallOumi-8B**, a **SOTA hallucination detection model**, outperforming DeepSeek R1, OpenAI o1, Google Gemini 1.5 Pro, and Claude Sonnet 3.5 at only **8 billion parameters!** + +Give HallOumi a try now! + +* Demo: https://oumi.ai/halloumi-demo +* Github: https://github.com/oumi-ai/oumi/tree/main/configs/projects/halloumi + +| Model | Macro F1 Score | Open? | Model Size | +| --------------------- | -------------- | ----------------- | ---------- | +| **HallOumi-8B** | **77.2% ± 2.2%** | Truly Open Source | 8B | +| Claude Sonnet 3.5 | 69.6% ± 2.8% | Closed | ?? | +| OpenAI o1-preview | 65.9% ± 2.3% | Closed | ?? | +| DeepSeek R1 | 61.6% ± 2.5% | Open Weights | 671B | +| Llama 3.1 405B | 58.8% ± 2.4% | Open Weights | 405B | +| Google Gemini 1.5 Pro | 48.2% ± 1.8% | Closed | ?? | + +**HallOumi**, the hallucination detection model built with Oumi, is a system built specifically to enable per-sentence verification of any content (either AI or human-generated) with **sentence-level citations** and **human-readable explanations.** +For example, when given one or more context documents, as well as an AI-generated summary, HallOumi goes through every claim being made in the summary and identifies: +* A determination whether that particular statement is **supported or unsupported** by the provided context combined with a **confidence score**. +* The **relevant context sentences** associated with that claim to facilitate human review. +* An **explanation** describing why a particular claim is supported or unsupported to boost human review accuracy. Some hallucinations may be nuanced and hard for humans to catch without help. + +## Hallucinations +Hallucinations are often cited as the most important issue with being able to deploy generative models in numerous commercial and personal applications, and for good reason: + +* [Lawyers sanctioned for briefing where ChatGPT cited 6 fictitious cases](https://www.reuters.com/legal/new-york-lawyers-sanctioned-using-fake-chatgpt-cases-legal-brief-2023-06-22/) +* [Air Canada required to honor refund policy made up by its AI support chatbot](https://www.wired.com/story/air-canada-chatbot-refund-policy/) +* [AI suggesting users should make glue pizza and eat rocks](https://www.bbc.com/news/articles/cd11gzejgz4o) + +It ultimately comes down to an issue of **trust** — generative models are trained to produce outputs which are **probabilistically likely**, but not necessarily **true**. +While such tools are useful in the right hands, being unable to trust them prevents AI from being adopted more broadly, +where it can be utilized safely and responsibly. + +## Building Trust with Verifiability +To be able to begin trusting AI systems, we have to be able to verify their outputs. To verify, we specifically mean that we need to: + +* Understand the **truthfulness** of a particular statement produced by any model. +* Understand what **information supports that statement’s truth** (or lack thereof). +* Have **full traceability** connecting the statement to that information. + +Missing any one of these aspects results in a system that cannot be verified and therefore cannot be trusted. +However, this is not enough, as we have to be capable of doing these things in a way that is **meticulous**, **scalable**, and **human-readable**. +With explanations, confidence scores, and citations, all at an affordable model size, HallOumi takes us towards a more grounded, trustworthy future for AI. + +- **Developed by:** [Oumi AI](https://oumi.ai/) +- **Model type:** Small Language Model +- **Language(s) (NLP):** English +- **License:** [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.en) (due to ANLI data falling under the same license) +- **Finetuned from model:** [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) +- **Demo:** [HallOumi Demo](https://oumi.ai/halloumi-demo) + +--- + +## Uses + + +Use to verify claims/detect hallucinations in scenarios where a known source of truth is available. + +Demo: https://oumi.ai/halloumi-demo + +Example prompt: +``` +EXAMPLE_CONTEXT = """<|context|><|s1|><|s2|>""" +EXAMPLE_REQUEST = """<|request|>""" +EXAMPLE_RESPONSE = """<|response|><|r1|><|r2|>""" + +messages = [ + {'role': 'user', 'content': f"{EXAMPLE_CONTEXT}{EXAMPLE_REQUEST}{EXAMPLE_RESPONSE}", +] +``` + +## Out-of-Scope Use + + +Smaller LLMs have limited capabilities and should be used with caution. Avoid using this model for purposes outside of claim verification. + +## Bias, Risks, and Limitations + + +This model was finetuned with Llama-3.1-405B-Instruct data on top of a Llama-3.1-8B-Instruct model, so any biases or risks associated with those models may be present. + +## Training Details + +### Training Data + + +Training data: +- [oumi-ai/oumi-synthetic-document-claims](https://huggingface.co/datasets/oumi-ai/oumi-synthetic-document-claims) +- [oumi-ai/oumi-synthetic-claims](https://huggingface.co/datasets/oumi-ai/oumi-synthetic-claims) +- [oumi-ai/oumi-anli-subset](https://huggingface.co/datasets/oumi-ai/oumi-anli-subset) +- [oumi-ai/oumi-c2d-d2c-subset](https://huggingface.co/datasets/oumi-ai/oumi-c2d-d2c-subset) + +### Training Procedure + + +For information on training, see https://oumi.ai/halloumi + +## Evaluation + + +Follow along with our notebook on how to evaluate hallucination with HallOumi and other popular models: + +https://github.com/oumi-ai/oumi/blob/main/configs/projects/halloumi/halloumi_eval_notebook.ipynb + +## Environmental Impact + + + +- **Hardware Type:** H100 +- **Hours used:** 32 (4 * 8 GPUs) +- **Cloud Provider:** Google Cloud Platform +- **Compute Region:** us-east5 +- **Carbon Emitted:** 2.8 kg + +## Citation + + + +``` +@misc{oumiHalloumi8B, + author = {Jeremy Greer, Konstantinos Aisopos, Panos Achlioptas, Michael Schuler, Oussama Elachqar, Emmanouil Koukoumidis}, + title = {HallOumi-8B}, + month = {March}, + year = {2025}, + url = {https://huggingface.co/oumi-ai/HallOumi-8B} +} + +@software{oumi2025, + author = {Oumi Community}, + title = {Oumi: an Open, End-to-end Platform for Building Large Foundation Models}, + month = {January}, + year = {2025}, + url = {https://github.com/oumi-ai/oumi} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..67a0a34 --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.2", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b18d16b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.45.2" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..061595d --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31543f50c3ef003f9db92a323cf4bf63e54f7c458f2d94ebc66a6d614109273 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..bfaab88 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6f9f382645280ed2d9949c34ea60e1adadb6e0a20dd4a4882c0c7af2997c21 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..2730884 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7ea6774ddb98c20d66483ca25cc676093b75e55b4bc41e267c001b8d7d36fa +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..3a9cd0d --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2da2641a5e986fc8b74e803dbccba8991dee287f17f288021a3e1d9e5114f00 +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0fd8120 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3c1d049 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6f102fc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 8192, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..348135c --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1021 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 50, + "global_step": 485, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008247422680412371, + "grad_norm": 16.75, + "learning_rate": 6.666666666666667e-06, + "loss": 0.8829, + "num_input_tokens_seen": 1413808, + "step": 4 + }, + { + "epoch": 0.016494845360824743, + "grad_norm": 3.90625, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.4033, + "num_input_tokens_seen": 2866496, + "step": 8 + }, + { + "epoch": 0.024742268041237112, + "grad_norm": 5.0, + "learning_rate": 2e-05, + "loss": 0.2755, + "num_input_tokens_seen": 4305104, + "step": 12 + }, + { + "epoch": 0.032989690721649485, + "grad_norm": 2.453125, + "learning_rate": 2.6666666666666667e-05, + "loss": 0.2531, + "num_input_tokens_seen": 5594128, + "step": 16 + }, + { + "epoch": 0.041237113402061855, + "grad_norm": 1.484375, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.2585, + "num_input_tokens_seen": 6683376, + "step": 20 + }, + { + "epoch": 0.049484536082474224, + "grad_norm": 1.328125, + "learning_rate": 4e-05, + "loss": 0.2308, + "num_input_tokens_seen": 8030336, + "step": 24 + }, + { + "epoch": 0.0577319587628866, + "grad_norm": 1.3671875, + "learning_rate": 3.9992569962849926e-05, + "loss": 0.2221, + "num_input_tokens_seen": 9395728, + "step": 28 + }, + { + "epoch": 0.06597938144329897, + "grad_norm": 1.3125, + "learning_rate": 3.99702853719449e-05, + "loss": 0.2259, + "num_input_tokens_seen": 10689344, + "step": 32 + }, + { + "epoch": 0.07422680412371134, + "grad_norm": 1.234375, + "learning_rate": 3.9933162784818745e-05, + "loss": 0.2201, + "num_input_tokens_seen": 11936704, + "step": 36 + }, + { + "epoch": 0.08247422680412371, + "grad_norm": 1.359375, + "learning_rate": 3.988122978369162e-05, + "loss": 0.2242, + "num_input_tokens_seen": 13217248, + "step": 40 + }, + { + "epoch": 0.09072164948453608, + "grad_norm": 1.203125, + "learning_rate": 3.981452495497628e-05, + "loss": 0.2213, + "num_input_tokens_seen": 14587328, + "step": 44 + }, + { + "epoch": 0.09896907216494845, + "grad_norm": 1.0859375, + "learning_rate": 3.973309786060829e-05, + "loss": 0.1958, + "num_input_tokens_seen": 15976464, + "step": 48 + }, + { + "epoch": 0.10721649484536082, + "grad_norm": 1.09375, + "learning_rate": 3.963700900122124e-05, + "loss": 0.2136, + "num_input_tokens_seen": 17262576, + "step": 52 + }, + { + "epoch": 0.1154639175257732, + "grad_norm": 1.03125, + "learning_rate": 3.952632977119465e-05, + "loss": 0.2059, + "num_input_tokens_seen": 18801264, + "step": 56 + }, + { + "epoch": 0.12371134020618557, + "grad_norm": 1.0859375, + "learning_rate": 3.9401142405607594e-05, + "loss": 0.197, + "num_input_tokens_seen": 20158000, + "step": 60 + }, + { + "epoch": 0.13195876288659794, + "grad_norm": 1.2109375, + "learning_rate": 3.9261539919137776e-05, + "loss": 0.2273, + "num_input_tokens_seen": 21322240, + "step": 64 + }, + { + "epoch": 0.1402061855670103, + "grad_norm": 0.98828125, + "learning_rate": 3.9107626036951266e-05, + "loss": 0.1971, + "num_input_tokens_seen": 22631360, + "step": 68 + }, + { + "epoch": 0.14845360824742268, + "grad_norm": 1.125, + "learning_rate": 3.8939515117634326e-05, + "loss": 0.2194, + "num_input_tokens_seen": 23848496, + "step": 72 + }, + { + "epoch": 0.15670103092783505, + "grad_norm": 1.1953125, + "learning_rate": 3.875733206822452e-05, + "loss": 0.2215, + "num_input_tokens_seen": 25148336, + "step": 76 + }, + { + "epoch": 0.16494845360824742, + "grad_norm": 1.203125, + "learning_rate": 3.8561212251404406e-05, + "loss": 0.1989, + "num_input_tokens_seen": 26427264, + "step": 80 + }, + { + "epoch": 0.1731958762886598, + "grad_norm": 1.203125, + "learning_rate": 3.835130138492644e-05, + "loss": 0.2072, + "num_input_tokens_seen": 27833024, + "step": 84 + }, + { + "epoch": 0.18144329896907216, + "grad_norm": 1.1171875, + "learning_rate": 3.812775543334425e-05, + "loss": 0.2013, + "num_input_tokens_seen": 29273008, + "step": 88 + }, + { + "epoch": 0.18969072164948453, + "grad_norm": 1.1484375, + "learning_rate": 3.789074049213033e-05, + "loss": 0.2119, + "num_input_tokens_seen": 30628416, + "step": 92 + }, + { + "epoch": 0.1979381443298969, + "grad_norm": 1.1328125, + "learning_rate": 3.7640432664266514e-05, + "loss": 0.2213, + "num_input_tokens_seen": 31861856, + "step": 96 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 1.0859375, + "learning_rate": 3.737701792939881e-05, + "loss": 0.2102, + "num_input_tokens_seen": 33121072, + "step": 100 + }, + { + "epoch": 0.21443298969072164, + "grad_norm": 1.0859375, + "learning_rate": 3.7100692005653796e-05, + "loss": 0.2052, + "num_input_tokens_seen": 34464560, + "step": 104 + }, + { + "epoch": 0.22268041237113403, + "grad_norm": 1.09375, + "learning_rate": 3.681166020421938e-05, + "loss": 0.1942, + "num_input_tokens_seen": 35918800, + "step": 108 + }, + { + "epoch": 0.2309278350515464, + "grad_norm": 1.0546875, + "learning_rate": 3.6510137276797786e-05, + "loss": 0.1946, + "num_input_tokens_seen": 37267616, + "step": 112 + }, + { + "epoch": 0.23917525773195877, + "grad_norm": 1.078125, + "learning_rate": 3.6196347256044236e-05, + "loss": 0.2263, + "num_input_tokens_seen": 38542608, + "step": 116 + }, + { + "epoch": 0.24742268041237114, + "grad_norm": 1.015625, + "learning_rate": 3.5870523289109886e-05, + "loss": 0.2102, + "num_input_tokens_seen": 39934016, + "step": 120 + }, + { + "epoch": 0.2556701030927835, + "grad_norm": 1.0390625, + "learning_rate": 3.553290746441261e-05, + "loss": 0.2084, + "num_input_tokens_seen": 41070080, + "step": 124 + }, + { + "epoch": 0.2639175257731959, + "grad_norm": 1.0390625, + "learning_rate": 3.5183750631764406e-05, + "loss": 0.1939, + "num_input_tokens_seen": 42375696, + "step": 128 + }, + { + "epoch": 0.2721649484536082, + "grad_norm": 1.0390625, + "learning_rate": 3.4823312215989046e-05, + "loss": 0.2027, + "num_input_tokens_seen": 43648368, + "step": 132 + }, + { + "epoch": 0.2804123711340206, + "grad_norm": 1.03125, + "learning_rate": 3.445186002416849e-05, + "loss": 0.2093, + "num_input_tokens_seen": 44952352, + "step": 136 + }, + { + "epoch": 0.28865979381443296, + "grad_norm": 1.1484375, + "learning_rate": 3.4069670046661197e-05, + "loss": 0.1887, + "num_input_tokens_seen": 46407584, + "step": 140 + }, + { + "epoch": 0.29690721649484536, + "grad_norm": 1.1015625, + "learning_rate": 3.3677026252040306e-05, + "loss": 0.2109, + "num_input_tokens_seen": 47649744, + "step": 144 + }, + { + "epoch": 0.30515463917525776, + "grad_norm": 0.98046875, + "learning_rate": 3.327422037610389e-05, + "loss": 0.2072, + "num_input_tokens_seen": 49014464, + "step": 148 + }, + { + "epoch": 0.3134020618556701, + "grad_norm": 0.97265625, + "learning_rate": 3.286155170511419e-05, + "loss": 0.2046, + "num_input_tokens_seen": 50443616, + "step": 152 + }, + { + "epoch": 0.3216494845360825, + "grad_norm": 1.1328125, + "learning_rate": 3.2439326853426824e-05, + "loss": 0.211, + "num_input_tokens_seen": 51801328, + "step": 156 + }, + { + "epoch": 0.32989690721649484, + "grad_norm": 0.9765625, + "learning_rate": 3.200785953567517e-05, + "loss": 0.1977, + "num_input_tokens_seen": 53112944, + "step": 160 + }, + { + "epoch": 0.33814432989690724, + "grad_norm": 1.03125, + "learning_rate": 3.156747033367922e-05, + "loss": 0.2001, + "num_input_tokens_seen": 54444256, + "step": 164 + }, + { + "epoch": 0.3463917525773196, + "grad_norm": 1.046875, + "learning_rate": 3.1118486458252094e-05, + "loss": 0.2, + "num_input_tokens_seen": 55882912, + "step": 168 + }, + { + "epoch": 0.354639175257732, + "grad_norm": 1.0234375, + "learning_rate": 3.0661241506081236e-05, + "loss": 0.1997, + "num_input_tokens_seen": 57157872, + "step": 172 + }, + { + "epoch": 0.3628865979381443, + "grad_norm": 1.0078125, + "learning_rate": 3.019607521186475e-05, + "loss": 0.2085, + "num_input_tokens_seen": 58474160, + "step": 176 + }, + { + "epoch": 0.3711340206185567, + "grad_norm": 1.0859375, + "learning_rate": 2.972333319588736e-05, + "loss": 0.2093, + "num_input_tokens_seen": 59687904, + "step": 180 + }, + { + "epoch": 0.37938144329896906, + "grad_norm": 0.99609375, + "learning_rate": 2.9243366707223165e-05, + "loss": 0.1963, + "num_input_tokens_seen": 61006320, + "step": 184 + }, + { + "epoch": 0.38762886597938145, + "grad_norm": 0.98828125, + "learning_rate": 2.875653236275632e-05, + "loss": 0.2001, + "num_input_tokens_seen": 62265552, + "step": 188 + }, + { + "epoch": 0.3958762886597938, + "grad_norm": 0.9609375, + "learning_rate": 2.8263191882213362e-05, + "loss": 0.1948, + "num_input_tokens_seen": 63682384, + "step": 192 + }, + { + "epoch": 0.4041237113402062, + "grad_norm": 0.953125, + "learning_rate": 2.7763711819404098e-05, + "loss": 0.2048, + "num_input_tokens_seen": 64848160, + "step": 196 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.98046875, + "learning_rate": 2.7258463289870764e-05, + "loss": 0.192, + "num_input_tokens_seen": 66278032, + "step": 200 + }, + { + "epoch": 0.42061855670103093, + "grad_norm": 0.80859375, + "learning_rate": 2.6747821695147806e-05, + "loss": 0.1933, + "num_input_tokens_seen": 67686560, + "step": 204 + }, + { + "epoch": 0.4288659793814433, + "grad_norm": 1.0703125, + "learning_rate": 2.623216644383715e-05, + "loss": 0.2094, + "num_input_tokens_seen": 68863776, + "step": 208 + }, + { + "epoch": 0.43711340206185567, + "grad_norm": 1.0859375, + "learning_rate": 2.5711880669706172e-05, + "loss": 0.1964, + "num_input_tokens_seen": 70186224, + "step": 212 + }, + { + "epoch": 0.44536082474226807, + "grad_norm": 0.9765625, + "learning_rate": 2.5187350947017918e-05, + "loss": 0.2042, + "num_input_tokens_seen": 71498112, + "step": 216 + }, + { + "epoch": 0.4536082474226804, + "grad_norm": 0.89453125, + "learning_rate": 2.4658967003304986e-05, + "loss": 0.1908, + "num_input_tokens_seen": 72880736, + "step": 220 + }, + { + "epoch": 0.4618556701030928, + "grad_norm": 1.0, + "learning_rate": 2.4127121429800498e-05, + "loss": 0.187, + "num_input_tokens_seen": 74122048, + "step": 224 + }, + { + "epoch": 0.47010309278350515, + "grad_norm": 0.9296875, + "learning_rate": 2.3592209389741372e-05, + "loss": 0.1778, + "num_input_tokens_seen": 75602400, + "step": 228 + }, + { + "epoch": 0.47835051546391755, + "grad_norm": 1.0546875, + "learning_rate": 2.30546283247606e-05, + "loss": 0.207, + "num_input_tokens_seen": 76746240, + "step": 232 + }, + { + "epoch": 0.4865979381443299, + "grad_norm": 0.984375, + "learning_rate": 2.251477765958655e-05, + "loss": 0.1911, + "num_input_tokens_seen": 78209744, + "step": 236 + }, + { + "epoch": 0.4948453608247423, + "grad_norm": 1.125, + "learning_rate": 2.1973058505269007e-05, + "loss": 0.1935, + "num_input_tokens_seen": 79494896, + "step": 240 + }, + { + "epoch": 0.5030927835051546, + "grad_norm": 1.0546875, + "learning_rate": 2.1429873361152124e-05, + "loss": 0.1977, + "num_input_tokens_seen": 80721808, + "step": 244 + }, + { + "epoch": 0.511340206185567, + "grad_norm": 0.96875, + "learning_rate": 2.088562581581592e-05, + "loss": 0.1956, + "num_input_tokens_seen": 81918944, + "step": 248 + }, + { + "epoch": 0.5195876288659794, + "grad_norm": 1.125, + "learning_rate": 2.0340720247208447e-05, + "loss": 0.1912, + "num_input_tokens_seen": 83184064, + "step": 252 + }, + { + "epoch": 0.5278350515463918, + "grad_norm": 1.03125, + "learning_rate": 1.9795561522191523e-05, + "loss": 0.1843, + "num_input_tokens_seen": 84574976, + "step": 256 + }, + { + "epoch": 0.5360824742268041, + "grad_norm": 1.0078125, + "learning_rate": 1.9250554695723107e-05, + "loss": 0.1942, + "num_input_tokens_seen": 85844768, + "step": 260 + }, + { + "epoch": 0.5443298969072164, + "grad_norm": 0.9765625, + "learning_rate": 1.8706104709899964e-05, + "loss": 0.1922, + "num_input_tokens_seen": 87245056, + "step": 264 + }, + { + "epoch": 0.5525773195876289, + "grad_norm": 1.0234375, + "learning_rate": 1.816261609308419e-05, + "loss": 0.182, + "num_input_tokens_seen": 88603792, + "step": 268 + }, + { + "epoch": 0.5608247422680412, + "grad_norm": 0.90625, + "learning_rate": 1.7620492659337155e-05, + "loss": 0.1879, + "num_input_tokens_seen": 90054816, + "step": 272 + }, + { + "epoch": 0.5690721649484536, + "grad_norm": 0.9453125, + "learning_rate": 1.7080137208384122e-05, + "loss": 0.1809, + "num_input_tokens_seen": 91432912, + "step": 276 + }, + { + "epoch": 0.5773195876288659, + "grad_norm": 0.921875, + "learning_rate": 1.6541951226332565e-05, + "loss": 0.1735, + "num_input_tokens_seen": 92795296, + "step": 280 + }, + { + "epoch": 0.5855670103092784, + "grad_norm": 0.9296875, + "learning_rate": 1.600633458736653e-05, + "loss": 0.1915, + "num_input_tokens_seen": 94071744, + "step": 284 + }, + { + "epoch": 0.5938144329896907, + "grad_norm": 0.94921875, + "learning_rate": 1.5473685256638572e-05, + "loss": 0.1895, + "num_input_tokens_seen": 95342096, + "step": 288 + }, + { + "epoch": 0.6020618556701031, + "grad_norm": 0.98828125, + "learning_rate": 1.4944398994580232e-05, + "loss": 0.1869, + "num_input_tokens_seen": 96569312, + "step": 292 + }, + { + "epoch": 0.6103092783505155, + "grad_norm": 1.03125, + "learning_rate": 1.4418869062850514e-05, + "loss": 0.2004, + "num_input_tokens_seen": 97849216, + "step": 296 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.93359375, + "learning_rate": 1.3897485932141042e-05, + "loss": 0.1865, + "num_input_tokens_seen": 99083488, + "step": 300 + }, + { + "epoch": 0.6268041237113402, + "grad_norm": 0.91796875, + "learning_rate": 1.3380636992054878e-05, + "loss": 0.1769, + "num_input_tokens_seen": 100566624, + "step": 304 + }, + { + "epoch": 0.6350515463917525, + "grad_norm": 0.86328125, + "learning_rate": 1.2868706263274602e-05, + "loss": 0.1969, + "num_input_tokens_seen": 101823872, + "step": 308 + }, + { + "epoch": 0.643298969072165, + "grad_norm": 0.96484375, + "learning_rate": 1.236207411223353e-05, + "loss": 0.1767, + "num_input_tokens_seen": 103284176, + "step": 312 + }, + { + "epoch": 0.6515463917525773, + "grad_norm": 0.83984375, + "learning_rate": 1.1861116968502015e-05, + "loss": 0.1799, + "num_input_tokens_seen": 104567360, + "step": 316 + }, + { + "epoch": 0.6597938144329897, + "grad_norm": 0.92578125, + "learning_rate": 1.136620704509892e-05, + "loss": 0.1856, + "num_input_tokens_seen": 105872848, + "step": 320 + }, + { + "epoch": 0.668041237113402, + "grad_norm": 0.86328125, + "learning_rate": 1.087771206193593e-05, + "loss": 0.1791, + "num_input_tokens_seen": 107217232, + "step": 324 + }, + { + "epoch": 0.6762886597938145, + "grad_norm": 0.9609375, + "learning_rate": 1.0395994972600285e-05, + "loss": 0.1806, + "num_input_tokens_seen": 108626976, + "step": 328 + }, + { + "epoch": 0.6845360824742268, + "grad_norm": 0.9609375, + "learning_rate": 9.921413694678959e-06, + "loss": 0.2018, + "num_input_tokens_seen": 109754000, + "step": 332 + }, + { + "epoch": 0.6927835051546392, + "grad_norm": 0.94921875, + "learning_rate": 9.454320843824512e-06, + "loss": 0.1848, + "num_input_tokens_seen": 111026592, + "step": 336 + }, + { + "epoch": 0.7010309278350515, + "grad_norm": 0.96484375, + "learning_rate": 8.995063471760377e-06, + "loss": 0.1885, + "num_input_tokens_seen": 112287760, + "step": 340 + }, + { + "epoch": 0.709278350515464, + "grad_norm": 0.98828125, + "learning_rate": 8.543982808420156e-06, + "loss": 0.1838, + "num_input_tokens_seen": 113634128, + "step": 344 + }, + { + "epoch": 0.7175257731958763, + "grad_norm": 0.984375, + "learning_rate": 8.101414008412469e-06, + "loss": 0.1842, + "num_input_tokens_seen": 114949760, + "step": 348 + }, + { + "epoch": 0.7257731958762886, + "grad_norm": 0.96484375, + "learning_rate": 7.667685901999875e-06, + "loss": 0.1935, + "num_input_tokens_seen": 116223648, + "step": 352 + }, + { + "epoch": 0.734020618556701, + "grad_norm": 0.86328125, + "learning_rate": 7.24312075077674e-06, + "loss": 0.1866, + "num_input_tokens_seen": 117618112, + "step": 356 + }, + { + "epoch": 0.7422680412371134, + "grad_norm": 0.875, + "learning_rate": 6.828034008227678e-06, + "loss": 0.1751, + "num_input_tokens_seen": 119000256, + "step": 360 + }, + { + "epoch": 0.7505154639175258, + "grad_norm": 0.9765625, + "learning_rate": 6.422734085344464e-06, + "loss": 0.1796, + "num_input_tokens_seen": 120232672, + "step": 364 + }, + { + "epoch": 0.7587628865979381, + "grad_norm": 0.83984375, + "learning_rate": 6.027522121475482e-06, + "loss": 0.1783, + "num_input_tokens_seen": 121499376, + "step": 368 + }, + { + "epoch": 0.7670103092783506, + "grad_norm": 0.95703125, + "learning_rate": 5.642691760578116e-06, + "loss": 0.1856, + "num_input_tokens_seen": 122791312, + "step": 372 + }, + { + "epoch": 0.7752577319587629, + "grad_norm": 0.85546875, + "learning_rate": 5.268528933040147e-06, + "loss": 0.1674, + "num_input_tokens_seen": 124261040, + "step": 376 + }, + { + "epoch": 0.7835051546391752, + "grad_norm": 0.82421875, + "learning_rate": 4.905311643232464e-06, + "loss": 0.1773, + "num_input_tokens_seen": 125708848, + "step": 380 + }, + { + "epoch": 0.7917525773195876, + "grad_norm": 0.9375, + "learning_rate": 4.553309762950739e-06, + "loss": 0.1905, + "num_input_tokens_seen": 126865712, + "step": 384 + }, + { + "epoch": 0.8, + "grad_norm": 0.99609375, + "learning_rate": 4.212784830899725e-06, + "loss": 0.1793, + "num_input_tokens_seen": 128157040, + "step": 388 + }, + { + "epoch": 0.8082474226804124, + "grad_norm": 0.84375, + "learning_rate": 3.8839898583689725e-06, + "loss": 0.1812, + "num_input_tokens_seen": 129465312, + "step": 392 + }, + { + "epoch": 0.8164948453608247, + "grad_norm": 0.890625, + "learning_rate": 3.567169141244562e-06, + "loss": 0.1813, + "num_input_tokens_seen": 130665504, + "step": 396 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.92578125, + "learning_rate": 3.262558078496301e-06, + "loss": 0.1727, + "num_input_tokens_seen": 132002896, + "step": 400 + }, + { + "epoch": 0.8329896907216495, + "grad_norm": 0.8828125, + "learning_rate": 2.9703829972754407e-06, + "loss": 0.1858, + "num_input_tokens_seen": 133415088, + "step": 404 + }, + { + "epoch": 0.8412371134020619, + "grad_norm": 0.90234375, + "learning_rate": 2.69086098475277e-06, + "loss": 0.1707, + "num_input_tokens_seen": 134815184, + "step": 408 + }, + { + "epoch": 0.8494845360824742, + "grad_norm": 0.97265625, + "learning_rate": 2.4241997268220096e-06, + "loss": 0.1822, + "num_input_tokens_seen": 136261472, + "step": 412 + }, + { + "epoch": 0.8577319587628865, + "grad_norm": 0.98828125, + "learning_rate": 2.1705973537884615e-06, + "loss": 0.1809, + "num_input_tokens_seen": 137429504, + "step": 416 + }, + { + "epoch": 0.865979381443299, + "grad_norm": 0.9375, + "learning_rate": 1.9302422931574183e-06, + "loss": 0.1885, + "num_input_tokens_seen": 138708544, + "step": 420 + }, + { + "epoch": 0.8742268041237113, + "grad_norm": 0.83984375, + "learning_rate": 1.7033131296318473e-06, + "loss": 0.1687, + "num_input_tokens_seen": 140033024, + "step": 424 + }, + { + "epoch": 0.8824742268041237, + "grad_norm": 0.859375, + "learning_rate": 1.4899784724232968e-06, + "loss": 0.1748, + "num_input_tokens_seen": 141348192, + "step": 428 + }, + { + "epoch": 0.8907216494845361, + "grad_norm": 0.859375, + "learning_rate": 1.2903968299746094e-06, + "loss": 0.1716, + "num_input_tokens_seen": 142800048, + "step": 432 + }, + { + "epoch": 0.8989690721649485, + "grad_norm": 0.94140625, + "learning_rate": 1.104716492187574e-06, + "loss": 0.1841, + "num_input_tokens_seen": 144156592, + "step": 436 + }, + { + "epoch": 0.9072164948453608, + "grad_norm": 0.984375, + "learning_rate": 9.330754202429726e-07, + "loss": 0.1855, + "num_input_tokens_seen": 145334944, + "step": 440 + }, + { + "epoch": 0.9154639175257732, + "grad_norm": 1.0625, + "learning_rate": 7.756011440948996e-07, + "loss": 0.1895, + "num_input_tokens_seen": 146529728, + "step": 444 + }, + { + "epoch": 0.9237113402061856, + "grad_norm": 1.03125, + "learning_rate": 6.324106677155573e-07, + "loss": 0.1841, + "num_input_tokens_seen": 147823952, + "step": 448 + }, + { + "epoch": 0.931958762886598, + "grad_norm": 0.88671875, + "learning_rate": 5.036103821608485e-07, + "loss": 0.1838, + "num_input_tokens_seen": 149194048, + "step": 452 + }, + { + "epoch": 0.9402061855670103, + "grad_norm": 0.83984375, + "learning_rate": 3.892959865214363e-07, + "loss": 0.1773, + "num_input_tokens_seen": 150529248, + "step": 456 + }, + { + "epoch": 0.9484536082474226, + "grad_norm": 1.1640625, + "learning_rate": 2.8955241681795534e-07, + "loss": 0.1863, + "num_input_tokens_seen": 151864336, + "step": 460 + }, + { + "epoch": 0.9567010309278351, + "grad_norm": 0.765625, + "learning_rate": 2.044537828932458e-07, + "loss": 0.1803, + "num_input_tokens_seen": 153203872, + "step": 464 + }, + { + "epoch": 0.9649484536082474, + "grad_norm": 0.8828125, + "learning_rate": 1.3406331334845813e-07, + "loss": 0.1869, + "num_input_tokens_seen": 154513568, + "step": 468 + }, + { + "epoch": 0.9731958762886598, + "grad_norm": 0.8046875, + "learning_rate": 7.843330856396103e-08, + "loss": 0.1818, + "num_input_tokens_seen": 155739584, + "step": 472 + }, + { + "epoch": 0.9814432989690721, + "grad_norm": 0.89453125, + "learning_rate": 3.760510183997701e-08, + "loss": 0.1826, + "num_input_tokens_seen": 157087344, + "step": 476 + }, + { + "epoch": 0.9896907216494846, + "grad_norm": 0.8984375, + "learning_rate": 1.160902868577951e-08, + "loss": 0.1905, + "num_input_tokens_seen": 158352288, + "step": 480 + }, + { + "epoch": 0.9979381443298969, + "grad_norm": 0.86328125, + "learning_rate": 4.64404280295927e-10, + "loss": 0.1794, + "num_input_tokens_seen": 159671536, + "step": 484 + }, + { + "epoch": 1.0, + "eval_loss": 0.09546061605215073, + "eval_runtime": 83.6615, + "eval_samples_per_second": 12.419, + "eval_steps_per_second": 0.394, + "num_input_tokens_seen": 160044208, + "step": 485 + }, + { + "epoch": 1.0, + "num_input_tokens_seen": 160044208, + "step": 485, + "total_flos": 9.013493089079132e+17, + "train_loss": 0.20329311268845784, + "train_runtime": 14400.7959, + "train_samples_per_second": 4.305, + "train_steps_per_second": 0.034, + "train_tokens_per_second": 1385.946 + } + ], + "logging_steps": 4, + "max_steps": 485, + "num_input_tokens_seen": 160044208, + "num_train_epochs": 1, + "save_steps": 0, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": false, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.013493089079132e+17, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +}