commit b60fb3915425c3e74cf99fc632f04c9d6e82c3af
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Wed Jun 24 20:22:13 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Josephgflowers/TinyLlama-Cinder-Agent-v1
    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..6ff6bf3
--- /dev/null
+++ b/README.md
@@ -0,0 +1,67 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+base_model: Josephgflowers/TinyLlama-Cinder-Tiny-Agent
+model-index:
+- name: TinyLlama-Cinder-Agent-v1
+  results: []
+---
+The goal of this Model is to build a Tinyllama model that can be used for tool usage, RAG, take system instructions, and as a general assistant.
+
+This model is a fine-tuned version of [Josephgflowers/TinyLlama-Cinder-Tiny-Agent](https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Tiny-Agent).
+
+Special Thanks to https://nationtech.io/ for their generous sponorship in training this model.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6328952f798f8d122ce62a44/MbN_SXChmMxuHO8GjdUSc.png)
+
+This model is a fine-tuned version of [Josephgflowers/TinyLlama-3T-Cinder-v1.2](https://huggingface.co/Josephgflowers/TinyLlama-3T-Cinder-v1.2) on https://huggingface.co/datasets/Josephgflowers/agent_1.
+
+## Model description
+
+This models is trained for RAG, Summary, Function Calling and Tool usage. Trained off of Cinder. Cinder is a chatbot designed for chat about STEM topics, space adventure RP and storytelling.
+This model does well at the IFEval (following instuctions) for its size. It is great at summary and RAG. Due to the formatting of the Glaive function calling dataset the JSON
+output is not what I was expecting for doing regular JSON dumps but does follow their standard strictly.
+
+*********************************************
+10 X the original tinyllama model on GSM8K!!!
+*********************************************
+
+To do this I started with all the normal open math datasets EG Orca Math, All the Meta Math, camel AI math qa, ect and as many reasoning datasets as I could make or find.
+But what really made it go the extra mile was adding in TIGER-Lab/WebInstructSub along with all of the RAG and Summary data.
+So special thanks to TIGER-Lab. I found that as math perfomance improved so did the model's ability to handle extracting relevant data in RAG.
+
+### Help Here
+Like my work? Want to see more? Custom request? Message me on discord: joseph.flowers.ra Donate here: https://buymeacoffee.com/josephgflowers
+
+See https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Agent-Rag/blob/main/tinyllama_agent_cinder_txtai-rag.py 
+For usage example with wiki rag.
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Josephgflowers__TinyLlama-Cinder-Agent-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |39.17|
+|AI2 Reasoning Challenge (25-Shot)|34.90|
+|HellaSwag (10-Shot)              |53.87|
+|MMLU (5-Shot)                    |26.89|
+|TruthfulQA (0-shot)              |39.08|
+|Winogrande (5-shot)              |59.12|
+|GSM8k (5-shot)                   |21.15|
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Josephgflowers__TinyLlama-Cinder-Agent-v1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 5.82|
+|IFEval (0-Shot)    |26.70|
+|BBH (3-Shot)       | 3.80|
+|MATH Lvl 5 (4-Shot)| 0.38|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 2.23|
+|MMLU-PRO (5-shot)  | 1.79|
+
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..f6e2b97
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.955920022807249e+18,
+    "train_loss": 0.8700304180128008,
+    "train_runtime": 179145.9612,
+    "train_samples": 153863,
+    "train_samples_per_second": 0.859,
+    "train_steps_per_second": 0.072
+}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..1600c03
--- /dev/null
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Josephgflowers/TinyLlama-Cinder-Tiny-Agent",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
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..30b30ac
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..a950e00
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c86cd1858d9891e7cd52ccb63a868d208a7a0731b84df044c8506a2f0a7e1fb
+size 4400216536
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..492d4b2
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..5d592ae
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf467c9e0f536bda271283c6ef85eb1a943e3196b621c8a912d64953b205df83
+size 1842795
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..2343c72
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..f6e2b97
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.955920022807249e+18,
+    "train_loss": 0.8700304180128008,
+    "train_runtime": 179145.9612,
+    "train_samples": 153863,
+    "train_samples_per_second": 0.859,
+    "train_steps_per_second": 0.072
+}
\ No newline at end of file
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..715878f
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,938 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 12822,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007799095304944627,
+      "grad_norm": 63896.45703125,
+      "learning_rate": 4.961004523475277e-05,
+      "loss": 0.929,
+      "step": 100
+    },
+    {
+      "epoch": 0.015598190609889253,
+      "grad_norm": 79284.765625,
+      "learning_rate": 4.9220090469505544e-05,
+      "loss": 0.9281,
+      "step": 200
+    },
+    {
+      "epoch": 0.02339728591483388,
+      "grad_norm": 80169.203125,
+      "learning_rate": 4.883013570425831e-05,
+      "loss": 0.9385,
+      "step": 300
+    },
+    {
+      "epoch": 0.031196381219778507,
+      "grad_norm": 65649.6796875,
+      "learning_rate": 4.844018093901108e-05,
+      "loss": 0.9454,
+      "step": 400
+    },
+    {
+      "epoch": 0.038995476524723134,
+      "grad_norm": 82255.6953125,
+      "learning_rate": 4.805022617376384e-05,
+      "loss": 0.9368,
+      "step": 500
+    },
+    {
+      "epoch": 0.04679457182966776,
+      "grad_norm": 78376.4296875,
+      "learning_rate": 4.7660271408516614e-05,
+      "loss": 0.9318,
+      "step": 600
+    },
+    {
+      "epoch": 0.05459366713461238,
+      "grad_norm": 92200.078125,
+      "learning_rate": 4.7270316643269384e-05,
+      "loss": 0.9272,
+      "step": 700
+    },
+    {
+      "epoch": 0.06239276243955701,
+      "grad_norm": 88060.359375,
+      "learning_rate": 4.688036187802215e-05,
+      "loss": 0.9097,
+      "step": 800
+    },
+    {
+      "epoch": 0.07019185774450164,
+      "grad_norm": 76161.1796875,
+      "learning_rate": 4.649040711277492e-05,
+      "loss": 0.9475,
+      "step": 900
+    },
+    {
+      "epoch": 0.07799095304944627,
+      "grad_norm": 90524.1796875,
+      "learning_rate": 4.610045234752769e-05,
+      "loss": 0.9481,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08579004835439089,
+      "grad_norm": 100124.8359375,
+      "learning_rate": 4.571049758228046e-05,
+      "loss": 0.9333,
+      "step": 1100
+    },
+    {
+      "epoch": 0.09358914365933552,
+      "grad_norm": 65681.7734375,
+      "learning_rate": 4.5320542817033225e-05,
+      "loss": 0.9247,
+      "step": 1200
+    },
+    {
+      "epoch": 0.10138823896428015,
+      "grad_norm": 76333.234375,
+      "learning_rate": 4.4930588051785995e-05,
+      "loss": 0.9098,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10918733426922476,
+      "grad_norm": 77002.0703125,
+      "learning_rate": 4.4540633286538766e-05,
+      "loss": 0.9034,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1169864295741694,
+      "grad_norm": 72669.1875,
+      "learning_rate": 4.415067852129153e-05,
+      "loss": 0.9149,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12478552487911403,
+      "grad_norm": 71785.34375,
+      "learning_rate": 4.37607237560443e-05,
+      "loss": 0.9051,
+      "step": 1600
+    },
+    {
+      "epoch": 0.13258462018405864,
+      "grad_norm": 72728.5859375,
+      "learning_rate": 4.3370768990797065e-05,
+      "loss": 0.9268,
+      "step": 1700
+    },
+    {
+      "epoch": 0.14038371548900327,
+      "grad_norm": 69223.3203125,
+      "learning_rate": 4.2980814225549836e-05,
+      "loss": 0.9294,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1481828107939479,
+      "grad_norm": 62745.203125,
+      "learning_rate": 4.2590859460302607e-05,
+      "loss": 0.9038,
+      "step": 1900
+    },
+    {
+      "epoch": 0.15598190609889254,
+      "grad_norm": 79897.8671875,
+      "learning_rate": 4.220090469505538e-05,
+      "loss": 0.8994,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16378100140383717,
+      "grad_norm": 74131.546875,
+      "learning_rate": 4.181094992980815e-05,
+      "loss": 0.9144,
+      "step": 2100
+    },
+    {
+      "epoch": 0.17158009670878177,
+      "grad_norm": 67760.7109375,
+      "learning_rate": 4.142099516456091e-05,
+      "loss": 0.9285,
+      "step": 2200
+    },
+    {
+      "epoch": 0.1793791920137264,
+      "grad_norm": 78868.1484375,
+      "learning_rate": 4.103104039931368e-05,
+      "loss": 0.8973,
+      "step": 2300
+    },
+    {
+      "epoch": 0.18717828731867103,
+      "grad_norm": 71780.2109375,
+      "learning_rate": 4.064108563406645e-05,
+      "loss": 0.8961,
+      "step": 2400
+    },
+    {
+      "epoch": 0.19497738262361566,
+      "grad_norm": 77858.109375,
+      "learning_rate": 4.025113086881922e-05,
+      "loss": 0.9171,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2027764779285603,
+      "grad_norm": 70062.796875,
+      "learning_rate": 3.986117610357199e-05,
+      "loss": 0.8903,
+      "step": 2600
+    },
+    {
+      "epoch": 0.21057557323350493,
+      "grad_norm": 171091.046875,
+      "learning_rate": 3.947122133832475e-05,
+      "loss": 0.9061,
+      "step": 2700
+    },
+    {
+      "epoch": 0.21837466853844953,
+      "grad_norm": 84371.34375,
+      "learning_rate": 3.908126657307752e-05,
+      "loss": 0.9315,
+      "step": 2800
+    },
+    {
+      "epoch": 0.22617376384339416,
+      "grad_norm": 62273.2578125,
+      "learning_rate": 3.8691311807830294e-05,
+      "loss": 0.9115,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2339728591483388,
+      "grad_norm": 60464.15625,
+      "learning_rate": 3.8301357042583065e-05,
+      "loss": 0.8888,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24177195445328342,
+      "grad_norm": 67546.828125,
+      "learning_rate": 3.7911402277335836e-05,
+      "loss": 0.9031,
+      "step": 3100
+    },
+    {
+      "epoch": 0.24957104975822805,
+      "grad_norm": 75904.6328125,
+      "learning_rate": 3.75214475120886e-05,
+      "loss": 0.9146,
+      "step": 3200
+    },
+    {
+      "epoch": 0.2573701450631727,
+      "grad_norm": 81015.3828125,
+      "learning_rate": 3.713149274684137e-05,
+      "loss": 0.8935,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2651692403681173,
+      "grad_norm": 69763.3203125,
+      "learning_rate": 3.6741537981594134e-05,
+      "loss": 0.9129,
+      "step": 3400
+    },
+    {
+      "epoch": 0.27296833567306195,
+      "grad_norm": 68604.5,
+      "learning_rate": 3.6351583216346905e-05,
+      "loss": 0.8834,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28076743097800655,
+      "grad_norm": 66758.03125,
+      "learning_rate": 3.596162845109967e-05,
+      "loss": 0.8925,
+      "step": 3600
+    },
+    {
+      "epoch": 0.28856652628295115,
+      "grad_norm": 72424.8984375,
+      "learning_rate": 3.557167368585244e-05,
+      "loss": 0.915,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2963656215878958,
+      "grad_norm": 65904.9453125,
+      "learning_rate": 3.518171892060521e-05,
+      "loss": 0.8833,
+      "step": 3800
+    },
+    {
+      "epoch": 0.3041647168928404,
+      "grad_norm": 62548.9453125,
+      "learning_rate": 3.479176415535798e-05,
+      "loss": 0.8991,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3119638121977851,
+      "grad_norm": 85173.90625,
+      "learning_rate": 3.440180939011075e-05,
+      "loss": 0.9111,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3197629075027297,
+      "grad_norm": 65947.765625,
+      "learning_rate": 3.4011854624863516e-05,
+      "loss": 0.8774,
+      "step": 4100
+    },
+    {
+      "epoch": 0.32756200280767434,
+      "grad_norm": 69672.1875,
+      "learning_rate": 3.362189985961629e-05,
+      "loss": 0.8816,
+      "step": 4200
+    },
+    {
+      "epoch": 0.33536109811261894,
+      "grad_norm": 68125.9609375,
+      "learning_rate": 3.323194509436906e-05,
+      "loss": 0.8784,
+      "step": 4300
+    },
+    {
+      "epoch": 0.34316019341756354,
+      "grad_norm": 76767.6796875,
+      "learning_rate": 3.284199032912182e-05,
+      "loss": 0.899,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3509592887225082,
+      "grad_norm": 64417.96484375,
+      "learning_rate": 3.245203556387459e-05,
+      "loss": 0.8944,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3587583840274528,
+      "grad_norm": 62896.37109375,
+      "learning_rate": 3.206208079862736e-05,
+      "loss": 0.8745,
+      "step": 4600
+    },
+    {
+      "epoch": 0.36655747933239746,
+      "grad_norm": 58443.88671875,
+      "learning_rate": 3.167212603338013e-05,
+      "loss": 0.853,
+      "step": 4700
+    },
+    {
+      "epoch": 0.37435657463734207,
+      "grad_norm": 75019.8515625,
+      "learning_rate": 3.12821712681329e-05,
+      "loss": 0.8728,
+      "step": 4800
+    },
+    {
+      "epoch": 0.38215566994228667,
+      "grad_norm": 82645.0078125,
+      "learning_rate": 3.089221650288567e-05,
+      "loss": 0.8617,
+      "step": 4900
+    },
+    {
+      "epoch": 0.3899547652472313,
+      "grad_norm": 57014.08984375,
+      "learning_rate": 3.0502261737638436e-05,
+      "loss": 0.8566,
+      "step": 5000
+    },
+    {
+      "epoch": 0.39775386055217593,
+      "grad_norm": 71623.7578125,
+      "learning_rate": 3.01123069723912e-05,
+      "loss": 0.879,
+      "step": 5100
+    },
+    {
+      "epoch": 0.4055529558571206,
+      "grad_norm": 75911.140625,
+      "learning_rate": 2.972235220714397e-05,
+      "loss": 0.8889,
+      "step": 5200
+    },
+    {
+      "epoch": 0.4133520511620652,
+      "grad_norm": 69251.0703125,
+      "learning_rate": 2.9332397441896742e-05,
+      "loss": 0.8685,
+      "step": 5300
+    },
+    {
+      "epoch": 0.42115114646700985,
+      "grad_norm": 72434.6484375,
+      "learning_rate": 2.8942442676649513e-05,
+      "loss": 0.8895,
+      "step": 5400
+    },
+    {
+      "epoch": 0.42895024177195445,
+      "grad_norm": 69133.78125,
+      "learning_rate": 2.855248791140228e-05,
+      "loss": 0.8845,
+      "step": 5500
+    },
+    {
+      "epoch": 0.43674933707689906,
+      "grad_norm": 67216.6875,
+      "learning_rate": 2.8162533146155044e-05,
+      "loss": 0.8661,
+      "step": 5600
+    },
+    {
+      "epoch": 0.4445484323818437,
+      "grad_norm": 61408.3515625,
+      "learning_rate": 2.7772578380907815e-05,
+      "loss": 0.8743,
+      "step": 5700
+    },
+    {
+      "epoch": 0.4523475276867883,
+      "grad_norm": 66496.1640625,
+      "learning_rate": 2.7382623615660586e-05,
+      "loss": 0.8805,
+      "step": 5800
+    },
+    {
+      "epoch": 0.460146622991733,
+      "grad_norm": 62693.109375,
+      "learning_rate": 2.6992668850413357e-05,
+      "loss": 0.8634,
+      "step": 5900
+    },
+    {
+      "epoch": 0.4679457182966776,
+      "grad_norm": 77037.4140625,
+      "learning_rate": 2.660271408516612e-05,
+      "loss": 0.8834,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4757448136016222,
+      "grad_norm": 67157.15625,
+      "learning_rate": 2.6212759319918888e-05,
+      "loss": 0.8993,
+      "step": 6100
+    },
+    {
+      "epoch": 0.48354390890656684,
+      "grad_norm": 77155.8125,
+      "learning_rate": 2.582280455467166e-05,
+      "loss": 0.854,
+      "step": 6200
+    },
+    {
+      "epoch": 0.49134300421151145,
+      "grad_norm": 65097.22265625,
+      "learning_rate": 2.543284978942443e-05,
+      "loss": 0.8716,
+      "step": 6300
+    },
+    {
+      "epoch": 0.4991420995164561,
+      "grad_norm": 89373.515625,
+      "learning_rate": 2.50428950241772e-05,
+      "loss": 0.873,
+      "step": 6400
+    },
+    {
+      "epoch": 0.5069411948214008,
+      "grad_norm": 65231.74609375,
+      "learning_rate": 2.4652940258929964e-05,
+      "loss": 0.8698,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5147402901263454,
+      "grad_norm": 60228.23828125,
+      "learning_rate": 2.426298549368273e-05,
+      "loss": 0.8374,
+      "step": 6600
+    },
+    {
+      "epoch": 0.52253938543129,
+      "grad_norm": 73940.3125,
+      "learning_rate": 2.3873030728435502e-05,
+      "loss": 0.8669,
+      "step": 6700
+    },
+    {
+      "epoch": 0.5303384807362346,
+      "grad_norm": 80768.6953125,
+      "learning_rate": 2.3483075963188273e-05,
+      "loss": 0.8708,
+      "step": 6800
+    },
+    {
+      "epoch": 0.5381375760411792,
+      "grad_norm": 67096.984375,
+      "learning_rate": 2.309312119794104e-05,
+      "loss": 0.8797,
+      "step": 6900
+    },
+    {
+      "epoch": 0.5459366713461239,
+      "grad_norm": 56897.71875,
+      "learning_rate": 2.2703166432693808e-05,
+      "loss": 0.8728,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5537357666510685,
+      "grad_norm": 64982.1015625,
+      "learning_rate": 2.2313211667446575e-05,
+      "loss": 0.8735,
+      "step": 7100
+    },
+    {
+      "epoch": 0.5615348619560131,
+      "grad_norm": 62320.35546875,
+      "learning_rate": 2.1923256902199346e-05,
+      "loss": 0.8519,
+      "step": 7200
+    },
+    {
+      "epoch": 0.5693339572609577,
+      "grad_norm": 74915.2578125,
+      "learning_rate": 2.1533302136952117e-05,
+      "loss": 0.849,
+      "step": 7300
+    },
+    {
+      "epoch": 0.5771330525659023,
+      "grad_norm": 69091.40625,
+      "learning_rate": 2.1143347371704884e-05,
+      "loss": 0.8451,
+      "step": 7400
+    },
+    {
+      "epoch": 0.584932147870847,
+      "grad_norm": 75015.2109375,
+      "learning_rate": 2.0753392606457652e-05,
+      "loss": 0.8757,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5927312431757916,
+      "grad_norm": 59275.14453125,
+      "learning_rate": 2.036343784121042e-05,
+      "loss": 0.8657,
+      "step": 7600
+    },
+    {
+      "epoch": 0.6005303384807362,
+      "grad_norm": 64822.92578125,
+      "learning_rate": 1.997348307596319e-05,
+      "loss": 0.8555,
+      "step": 7700
+    },
+    {
+      "epoch": 0.6083294337856808,
+      "grad_norm": 63732.34765625,
+      "learning_rate": 1.9583528310715957e-05,
+      "loss": 0.8415,
+      "step": 7800
+    },
+    {
+      "epoch": 0.6161285290906254,
+      "grad_norm": 66452.859375,
+      "learning_rate": 1.9193573545468728e-05,
+      "loss": 0.8475,
+      "step": 7900
+    },
+    {
+      "epoch": 0.6239276243955701,
+      "grad_norm": 69227.2890625,
+      "learning_rate": 1.8803618780221496e-05,
+      "loss": 0.8333,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6317267197005147,
+      "grad_norm": 67040.7578125,
+      "learning_rate": 1.8413664014974263e-05,
+      "loss": 0.8317,
+      "step": 8100
+    },
+    {
+      "epoch": 0.6395258150054594,
+      "grad_norm": 74801.2734375,
+      "learning_rate": 1.8023709249727034e-05,
+      "loss": 0.8726,
+      "step": 8200
+    },
+    {
+      "epoch": 0.647324910310404,
+      "grad_norm": 63112.703125,
+      "learning_rate": 1.76337544844798e-05,
+      "loss": 0.8442,
+      "step": 8300
+    },
+    {
+      "epoch": 0.6551240056153487,
+      "grad_norm": 81685.2265625,
+      "learning_rate": 1.724379971923257e-05,
+      "loss": 0.8316,
+      "step": 8400
+    },
+    {
+      "epoch": 0.6629231009202933,
+      "grad_norm": 69446.4921875,
+      "learning_rate": 1.6853844953985336e-05,
+      "loss": 0.8391,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6707221962252379,
+      "grad_norm": 66903.671875,
+      "learning_rate": 1.6463890188738107e-05,
+      "loss": 0.8144,
+      "step": 8600
+    },
+    {
+      "epoch": 0.6785212915301825,
+      "grad_norm": 76092.6328125,
+      "learning_rate": 1.6073935423490877e-05,
+      "loss": 0.8441,
+      "step": 8700
+    },
+    {
+      "epoch": 0.6863203868351271,
+      "grad_norm": 71659.8515625,
+      "learning_rate": 1.5683980658243645e-05,
+      "loss": 0.8388,
+      "step": 8800
+    },
+    {
+      "epoch": 0.6941194821400718,
+      "grad_norm": 61097.1171875,
+      "learning_rate": 1.5294025892996412e-05,
+      "loss": 0.8383,
+      "step": 8900
+    },
+    {
+      "epoch": 0.7019185774450164,
+      "grad_norm": 60165.2734375,
+      "learning_rate": 1.4904071127749181e-05,
+      "loss": 0.8442,
+      "step": 9000
+    },
+    {
+      "epoch": 0.709717672749961,
+      "grad_norm": 71296.1171875,
+      "learning_rate": 1.451411636250195e-05,
+      "loss": 0.8537,
+      "step": 9100
+    },
+    {
+      "epoch": 0.7175167680549056,
+      "grad_norm": 67209.6328125,
+      "learning_rate": 1.4124161597254721e-05,
+      "loss": 0.8575,
+      "step": 9200
+    },
+    {
+      "epoch": 0.7253158633598502,
+      "grad_norm": 63280.3203125,
+      "learning_rate": 1.3734206832007487e-05,
+      "loss": 0.8358,
+      "step": 9300
+    },
+    {
+      "epoch": 0.7331149586647949,
+      "grad_norm": 69636.6875,
+      "learning_rate": 1.3344252066760258e-05,
+      "loss": 0.8475,
+      "step": 9400
+    },
+    {
+      "epoch": 0.7409140539697395,
+      "grad_norm": 68302.3828125,
+      "learning_rate": 1.2954297301513025e-05,
+      "loss": 0.8305,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7487131492746841,
+      "grad_norm": 68986.78125,
+      "learning_rate": 1.2564342536265794e-05,
+      "loss": 0.8667,
+      "step": 9600
+    },
+    {
+      "epoch": 0.7565122445796287,
+      "grad_norm": 69115.0546875,
+      "learning_rate": 1.2174387771018563e-05,
+      "loss": 0.8386,
+      "step": 9700
+    },
+    {
+      "epoch": 0.7643113398845733,
+      "grad_norm": 58786.73046875,
+      "learning_rate": 1.178443300577133e-05,
+      "loss": 0.8306,
+      "step": 9800
+    },
+    {
+      "epoch": 0.772110435189518,
+      "grad_norm": 75233.265625,
+      "learning_rate": 1.13944782405241e-05,
+      "loss": 0.8611,
+      "step": 9900
+    },
+    {
+      "epoch": 0.7799095304944627,
+      "grad_norm": 65838.609375,
+      "learning_rate": 1.1004523475276867e-05,
+      "loss": 0.8191,
+      "step": 10000
+    },
+    {
+      "epoch": 0.7877086257994073,
+      "grad_norm": 55231.33984375,
+      "learning_rate": 1.0614568710029638e-05,
+      "loss": 0.8551,
+      "step": 10100
+    },
+    {
+      "epoch": 0.7955077211043519,
+      "grad_norm": 63516.97265625,
+      "learning_rate": 1.0224613944782405e-05,
+      "loss": 0.8685,
+      "step": 10200
+    },
+    {
+      "epoch": 0.8033068164092966,
+      "grad_norm": 63661.3671875,
+      "learning_rate": 9.834659179535174e-06,
+      "loss": 0.8009,
+      "step": 10300
+    },
+    {
+      "epoch": 0.8111059117142412,
+      "grad_norm": 71024.375,
+      "learning_rate": 9.444704414287943e-06,
+      "loss": 0.8331,
+      "step": 10400
+    },
+    {
+      "epoch": 0.8189050070191858,
+      "grad_norm": 80821.6640625,
+      "learning_rate": 9.05474964904071e-06,
+      "loss": 0.8344,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8267041023241304,
+      "grad_norm": 61162.19140625,
+      "learning_rate": 8.66479488379348e-06,
+      "loss": 0.8454,
+      "step": 10600
+    },
+    {
+      "epoch": 0.834503197629075,
+      "grad_norm": 64971.5390625,
+      "learning_rate": 8.274840118546249e-06,
+      "loss": 0.8247,
+      "step": 10700
+    },
+    {
+      "epoch": 0.8423022929340197,
+      "grad_norm": 64816.95703125,
+      "learning_rate": 7.884885353299018e-06,
+      "loss": 0.8142,
+      "step": 10800
+    },
+    {
+      "epoch": 0.8501013882389643,
+      "grad_norm": 60450.6875,
+      "learning_rate": 7.494930588051786e-06,
+      "loss": 0.8128,
+      "step": 10900
+    },
+    {
+      "epoch": 0.8579004835439089,
+      "grad_norm": 71442.4375,
+      "learning_rate": 7.104975822804555e-06,
+      "loss": 0.8166,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8656995788488535,
+      "grad_norm": 76537.1875,
+      "learning_rate": 6.715021057557324e-06,
+      "loss": 0.852,
+      "step": 11100
+    },
+    {
+      "epoch": 0.8734986741537981,
+      "grad_norm": 65081.37890625,
+      "learning_rate": 6.325066292310092e-06,
+      "loss": 0.8394,
+      "step": 11200
+    },
+    {
+      "epoch": 0.8812977694587428,
+      "grad_norm": 73682.296875,
+      "learning_rate": 5.935111527062861e-06,
+      "loss": 0.8165,
+      "step": 11300
+    },
+    {
+      "epoch": 0.8890968647636874,
+      "grad_norm": 73644.78125,
+      "learning_rate": 5.54515676181563e-06,
+      "loss": 0.8312,
+      "step": 11400
+    },
+    {
+      "epoch": 0.896895960068632,
+      "grad_norm": 79621.890625,
+      "learning_rate": 5.155201996568398e-06,
+      "loss": 0.8404,
+      "step": 11500
+    },
+    {
+      "epoch": 0.9046950553735766,
+      "grad_norm": 56045.7734375,
+      "learning_rate": 4.7652472313211666e-06,
+      "loss": 0.8295,
+      "step": 11600
+    },
+    {
+      "epoch": 0.9124941506785212,
+      "grad_norm": 66463.71875,
+      "learning_rate": 4.375292466073936e-06,
+      "loss": 0.8256,
+      "step": 11700
+    },
+    {
+      "epoch": 0.920293245983466,
+      "grad_norm": 58425.23046875,
+      "learning_rate": 3.985337700826705e-06,
+      "loss": 0.8253,
+      "step": 11800
+    },
+    {
+      "epoch": 0.9280923412884106,
+      "grad_norm": 68089.9609375,
+      "learning_rate": 3.595382935579473e-06,
+      "loss": 0.8161,
+      "step": 11900
+    },
+    {
+      "epoch": 0.9358914365933552,
+      "grad_norm": 63161.6796875,
+      "learning_rate": 3.2054281703322412e-06,
+      "loss": 0.8322,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9436905318982998,
+      "grad_norm": 56655.69921875,
+      "learning_rate": 2.8154734050850103e-06,
+      "loss": 0.8117,
+      "step": 12100
+    },
+    {
+      "epoch": 0.9514896272032444,
+      "grad_norm": 72667.96875,
+      "learning_rate": 2.425518639837779e-06,
+      "loss": 0.8181,
+      "step": 12200
+    },
+    {
+      "epoch": 0.9592887225081891,
+      "grad_norm": 64209.17578125,
+      "learning_rate": 2.0355638745905476e-06,
+      "loss": 0.813,
+      "step": 12300
+    },
+    {
+      "epoch": 0.9670878178131337,
+      "grad_norm": 68720.7109375,
+      "learning_rate": 1.6456091093433163e-06,
+      "loss": 0.8343,
+      "step": 12400
+    },
+    {
+      "epoch": 0.9748869131180783,
+      "grad_norm": 62702.68359375,
+      "learning_rate": 1.255654344096085e-06,
+      "loss": 0.8156,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9826860084230229,
+      "grad_norm": 62949.0625,
+      "learning_rate": 8.656995788488536e-07,
+      "loss": 0.8343,
+      "step": 12600
+    },
+    {
+      "epoch": 0.9904851037279676,
+      "grad_norm": 64140.0703125,
+      "learning_rate": 4.757448136016222e-07,
+      "loss": 0.8189,
+      "step": 12700
+    },
+    {
+      "epoch": 0.9982841990329122,
+      "grad_norm": 72402.578125,
+      "learning_rate": 8.579004835439089e-08,
+      "loss": 0.823,
+      "step": 12800
+    },
+    {
+      "epoch": 1.0,
+      "step": 12822,
+      "total_flos": 1.955920022807249e+18,
+      "train_loss": 0.8700304180128008,
+      "train_runtime": 179145.9612,
+      "train_samples_per_second": 0.859,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 12822,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12822,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.955920022807249e+18,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..77835f4
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c44c38eb09a6b2599756766edbc167c8760d5ab86cbaedecff96098292537cf
+size 5112