commit 4160615f2bb0965bc49e8e5bee43900be23a1aac
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Mon Aug 31 22:54:13 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Josephgflowers/Qllama-tiny-5B-test-1
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..d2fc868
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,51 @@
+*.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
+
+merges.txt filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+vocab.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..7819c51
--- /dev/null
+++ b/README.md
@@ -0,0 +1,7 @@
+---
+license: mit
+---
+Llamafyd version of Qwen .5B further fine tuned on wiki, math, science, and chat datasets.
+Based on Cinder data.
+
+ As well as Cinder character specific data, a mix of RAG generated Q and A of world knowledge, STEM topics, and Cinder Character data. I suplimented the Cinder character with an abreviated Samantha dataset edited for Cinder and removed a lot of the negative responses. Model Overview Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration.
\ No newline at end of file
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..409be9f
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..638de03
--- /dev/null
+++ b/config.json
@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/home/joe/Downloads/q/text1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
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..5aa5095
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.41.0.dev0"
+}
diff --git a/merges.txt b/merges.txt
new file mode 100644
index 0000000..80c1a19
--- /dev/null
+++ b/merges.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..09e2d1a
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1b30ba884df4dedd6da09af4ef04baab4c2dadf7e39b0b4386e28843f09da1
+size 928059544
diff --git a/optimizer.pt b/optimizer.pt
new file mode 100644
index 0000000..608fcc9
--- /dev/null
+++ b/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ff35046a640a98ab07af04b3047af6b7033db4a355715805564024560fa57d
+size 3324282
diff --git a/rng_state.pth b/rng_state.pth
new file mode 100644
index 0000000..93a5222
--- /dev/null
+++ b/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/scheduler.pt b/scheduler.pt
new file mode 100644
index 0000000..9d1369b
--- /dev/null
+++ b/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87651c24ec0dcadf88273129cd2a759815e228b28ec29398402170415bee441
+size 1064
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..2c53454
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..f9d83c4
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1
+size 7028043
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..1016cc4
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..a916cde
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1293 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 18053,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005539245554755442,
+      "grad_norm": 1.546007513999939,
+      "learning_rate": 4.972580734503961e-05,
+      "loss": 1.2806,
+      "step": 100
+    },
+    {
+      "epoch": 0.011078491109510884,
+      "grad_norm": 1.6162946224212646,
+      "learning_rate": 4.945161469007921e-05,
+      "loss": 1.2654,
+      "step": 200
+    },
+    {
+      "epoch": 0.016617736664266327,
+      "grad_norm": 2.059379816055298,
+      "learning_rate": 4.917465241234144e-05,
+      "loss": 1.2231,
+      "step": 300
+    },
+    {
+      "epoch": 0.022156982219021768,
+      "grad_norm": 1.6531622409820557,
+      "learning_rate": 4.890045975738105e-05,
+      "loss": 1.2161,
+      "step": 400
+    },
+    {
+      "epoch": 0.027696227773777213,
+      "grad_norm": 1.57131028175354,
+      "learning_rate": 4.8623497479643274e-05,
+      "loss": 1.1963,
+      "step": 500
+    },
+    {
+      "epoch": 0.033235473328532654,
+      "grad_norm": 1.4883884191513062,
+      "learning_rate": 4.83465352019055e-05,
+      "loss": 1.1716,
+      "step": 600
+    },
+    {
+      "epoch": 0.038774718883288095,
+      "grad_norm": 1.4190359115600586,
+      "learning_rate": 4.806957292416773e-05,
+      "loss": 1.1969,
+      "step": 700
+    },
+    {
+      "epoch": 0.044313964438043536,
+      "grad_norm": 1.6759884357452393,
+      "learning_rate": 4.779261064642996e-05,
+      "loss": 1.179,
+      "step": 800
+    },
+    {
+      "epoch": 0.04985320999279898,
+      "grad_norm": 1.4575251340866089,
+      "learning_rate": 4.7515648368692186e-05,
+      "loss": 1.1543,
+      "step": 900
+    },
+    {
+      "epoch": 0.055392455547554426,
+      "grad_norm": 1.4753471612930298,
+      "learning_rate": 4.723868609095441e-05,
+      "loss": 1.1502,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06093170110230987,
+      "grad_norm": 1.660173773765564,
+      "learning_rate": 4.696172381321664e-05,
+      "loss": 1.1231,
+      "step": 1100
+    },
+    {
+      "epoch": 0.06647094665706531,
+      "grad_norm": 1.5432391166687012,
+      "learning_rate": 4.668476153547887e-05,
+      "loss": 1.1036,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07201019221182076,
+      "grad_norm": 1.3922276496887207,
+      "learning_rate": 4.64077992577411e-05,
+      "loss": 1.1286,
+      "step": 1300
+    },
+    {
+      "epoch": 0.07754943776657619,
+      "grad_norm": 1.361965298652649,
+      "learning_rate": 4.613083698000333e-05,
+      "loss": 1.1039,
+      "step": 1400
+    },
+    {
+      "epoch": 0.08308868332133164,
+      "grad_norm": 1.3993804454803467,
+      "learning_rate": 4.585387470226555e-05,
+      "loss": 1.1166,
+      "step": 1500
+    },
+    {
+      "epoch": 0.08862792887608707,
+      "grad_norm": 1.5207942724227905,
+      "learning_rate": 4.557691242452778e-05,
+      "loss": 1.1079,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09416717443084252,
+      "grad_norm": 1.6368706226348877,
+      "learning_rate": 4.529995014679001e-05,
+      "loss": 1.1103,
+      "step": 1700
+    },
+    {
+      "epoch": 0.09970641998559795,
+      "grad_norm": 1.4837383031845093,
+      "learning_rate": 4.5022987869052236e-05,
+      "loss": 1.1003,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1052456655403534,
+      "grad_norm": 1.483654499053955,
+      "learning_rate": 4.474602559131447e-05,
+      "loss": 1.0686,
+      "step": 1900
+    },
+    {
+      "epoch": 0.11078491109510885,
+      "grad_norm": 1.776803731918335,
+      "learning_rate": 4.446906331357669e-05,
+      "loss": 1.0892,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11632415664986429,
+      "grad_norm": 1.6472382545471191,
+      "learning_rate": 4.419210103583892e-05,
+      "loss": 1.0892,
+      "step": 2100
+    },
+    {
+      "epoch": 0.12186340220461973,
+      "grad_norm": 1.4846845865249634,
+      "learning_rate": 4.391513875810115e-05,
+      "loss": 1.0421,
+      "step": 2200
+    },
+    {
+      "epoch": 0.12740264775937518,
+      "grad_norm": 1.4608880281448364,
+      "learning_rate": 4.3638176480363375e-05,
+      "loss": 1.0578,
+      "step": 2300
+    },
+    {
+      "epoch": 0.13294189331413062,
+      "grad_norm": 1.515207052230835,
+      "learning_rate": 4.336121420262561e-05,
+      "loss": 1.0652,
+      "step": 2400
+    },
+    {
+      "epoch": 0.13848113886888605,
+      "grad_norm": 1.5072288513183594,
+      "learning_rate": 4.308425192488783e-05,
+      "loss": 1.0855,
+      "step": 2500
+    },
+    {
+      "epoch": 0.1440203844236415,
+      "grad_norm": 1.4887125492095947,
+      "learning_rate": 4.281005926992744e-05,
+      "loss": 1.0739,
+      "step": 2600
+    },
+    {
+      "epoch": 0.14955962997839695,
+      "grad_norm": 1.3779743909835815,
+      "learning_rate": 4.2533096992189665e-05,
+      "loss": 1.0558,
+      "step": 2700
+    },
+    {
+      "epoch": 0.15509887553315238,
+      "grad_norm": 1.4754050970077515,
+      "learning_rate": 4.22561347144519e-05,
+      "loss": 1.0458,
+      "step": 2800
+    },
+    {
+      "epoch": 0.16063812108790781,
+      "grad_norm": 1.3826239109039307,
+      "learning_rate": 4.197917243671412e-05,
+      "loss": 1.0416,
+      "step": 2900
+    },
+    {
+      "epoch": 0.16617736664266328,
+      "grad_norm": 1.3614164590835571,
+      "learning_rate": 4.170221015897635e-05,
+      "loss": 1.0405,
+      "step": 3000
+    },
+    {
+      "epoch": 0.1717166121974187,
+      "grad_norm": 1.8164361715316772,
+      "learning_rate": 4.142524788123858e-05,
+      "loss": 1.0464,
+      "step": 3100
+    },
+    {
+      "epoch": 0.17725585775217415,
+      "grad_norm": 1.497776746749878,
+      "learning_rate": 4.11482856035008e-05,
+      "loss": 1.0242,
+      "step": 3200
+    },
+    {
+      "epoch": 0.1827951033069296,
+      "grad_norm": 1.5668854713439941,
+      "learning_rate": 4.0871323325763036e-05,
+      "loss": 1.0444,
+      "step": 3300
+    },
+    {
+      "epoch": 0.18833434886168504,
+      "grad_norm": 1.3012648820877075,
+      "learning_rate": 4.0594361048025256e-05,
+      "loss": 1.019,
+      "step": 3400
+    },
+    {
+      "epoch": 0.19387359441644048,
+      "grad_norm": 1.4110270738601685,
+      "learning_rate": 4.031739877028749e-05,
+      "loss": 1.031,
+      "step": 3500
+    },
+    {
+      "epoch": 0.1994128399711959,
+      "grad_norm": 1.7231452465057373,
+      "learning_rate": 4.0040436492549715e-05,
+      "loss": 1.0458,
+      "step": 3600
+    },
+    {
+      "epoch": 0.20495208552595137,
+      "grad_norm": 1.5503065586090088,
+      "learning_rate": 3.976347421481195e-05,
+      "loss": 1.0141,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2104913310807068,
+      "grad_norm": 1.3918309211730957,
+      "learning_rate": 3.9486511937074175e-05,
+      "loss": 1.0169,
+      "step": 3800
+    },
+    {
+      "epoch": 0.21603057663546224,
+      "grad_norm": 1.4343814849853516,
+      "learning_rate": 3.9209549659336394e-05,
+      "loss": 1.0247,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2215698221902177,
+      "grad_norm": 1.4719725847244263,
+      "learning_rate": 3.893258738159863e-05,
+      "loss": 1.0043,
+      "step": 4000
+    },
+    {
+      "epoch": 0.22710906774497314,
+      "grad_norm": 1.3622781038284302,
+      "learning_rate": 3.8655625103860854e-05,
+      "loss": 1.0282,
+      "step": 4100
+    },
+    {
+      "epoch": 0.23264831329972857,
+      "grad_norm": 1.5316309928894043,
+      "learning_rate": 3.837866282612309e-05,
+      "loss": 1.0034,
+      "step": 4200
+    },
+    {
+      "epoch": 0.23818755885448403,
+      "grad_norm": 1.3682796955108643,
+      "learning_rate": 3.8104470171162684e-05,
+      "loss": 1.0456,
+      "step": 4300
+    },
+    {
+      "epoch": 0.24372680440923947,
+      "grad_norm": 1.4921820163726807,
+      "learning_rate": 3.782750789342492e-05,
+      "loss": 1.0166,
+      "step": 4400
+    },
+    {
+      "epoch": 0.2492660499639949,
+      "grad_norm": 1.4957038164138794,
+      "learning_rate": 3.7550545615687143e-05,
+      "loss": 1.0079,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25480529551875036,
+      "grad_norm": 1.5265921354293823,
+      "learning_rate": 3.7273583337949377e-05,
+      "loss": 1.0297,
+      "step": 4600
+    },
+    {
+      "epoch": 0.2603445410735058,
+      "grad_norm": 1.4102026224136353,
+      "learning_rate": 3.69966210602116e-05,
+      "loss": 0.978,
+      "step": 4700
+    },
+    {
+      "epoch": 0.26588378662826123,
+      "grad_norm": 1.3901424407958984,
+      "learning_rate": 3.671965878247383e-05,
+      "loss": 1.0043,
+      "step": 4800
+    },
+    {
+      "epoch": 0.27142303218301667,
+      "grad_norm": 1.4173741340637207,
+      "learning_rate": 3.6442696504736056e-05,
+      "loss": 0.9725,
+      "step": 4900
+    },
+    {
+      "epoch": 0.2769622777377721,
+      "grad_norm": 1.2784532308578491,
+      "learning_rate": 3.616573422699828e-05,
+      "loss": 0.9876,
+      "step": 5000
+    },
+    {
+      "epoch": 0.28250152329252753,
+      "grad_norm": 1.4648102521896362,
+      "learning_rate": 3.5888771949260515e-05,
+      "loss": 0.9715,
+      "step": 5100
+    },
+    {
+      "epoch": 0.288040768847283,
+      "grad_norm": 1.410418152809143,
+      "learning_rate": 3.561180967152274e-05,
+      "loss": 1.0037,
+      "step": 5200
+    },
+    {
+      "epoch": 0.29358001440203846,
+      "grad_norm": 1.6049284934997559,
+      "learning_rate": 3.533484739378497e-05,
+      "loss": 0.9674,
+      "step": 5300
+    },
+    {
+      "epoch": 0.2991192599567939,
+      "grad_norm": 1.3856281042099,
+      "learning_rate": 3.5057885116047194e-05,
+      "loss": 0.9927,
+      "step": 5400
+    },
+    {
+      "epoch": 0.3046585055115493,
+      "grad_norm": 1.485903024673462,
+      "learning_rate": 3.478092283830943e-05,
+      "loss": 0.9421,
+      "step": 5500
+    },
+    {
+      "epoch": 0.31019775106630476,
+      "grad_norm": 1.2787377834320068,
+      "learning_rate": 3.4503960560571654e-05,
+      "loss": 0.9697,
+      "step": 5600
+    },
+    {
+      "epoch": 0.3157369966210602,
+      "grad_norm": 1.4596630334854126,
+      "learning_rate": 3.422699828283388e-05,
+      "loss": 0.9743,
+      "step": 5700
+    },
+    {
+      "epoch": 0.32127624217581563,
+      "grad_norm": 1.6178170442581177,
+      "learning_rate": 3.3950036005096106e-05,
+      "loss": 0.979,
+      "step": 5800
+    },
+    {
+      "epoch": 0.3268154877305711,
+      "grad_norm": 1.5128576755523682,
+      "learning_rate": 3.367307372735833e-05,
+      "loss": 0.9507,
+      "step": 5900
+    },
+    {
+      "epoch": 0.33235473328532655,
+      "grad_norm": 1.4769525527954102,
+      "learning_rate": 3.3396111449620566e-05,
+      "loss": 0.9651,
+      "step": 6000
+    },
+    {
+      "epoch": 0.337893978840082,
+      "grad_norm": 1.3777639865875244,
+      "learning_rate": 3.311914917188279e-05,
+      "loss": 0.9747,
+      "step": 6100
+    },
+    {
+      "epoch": 0.3434332243948374,
+      "grad_norm": 1.492494821548462,
+      "learning_rate": 3.284218689414502e-05,
+      "loss": 0.9858,
+      "step": 6200
+    },
+    {
+      "epoch": 0.34897246994959286,
+      "grad_norm": 1.282101035118103,
+      "learning_rate": 3.2565224616407245e-05,
+      "loss": 0.9761,
+      "step": 6300
+    },
+    {
+      "epoch": 0.3545117155043483,
+      "grad_norm": 1.3632028102874756,
+      "learning_rate": 3.228826233866947e-05,
+      "loss": 0.958,
+      "step": 6400
+    },
+    {
+      "epoch": 0.3600509610591037,
+      "grad_norm": 1.4041866064071655,
+      "learning_rate": 3.2011300060931704e-05,
+      "loss": 0.9772,
+      "step": 6500
+    },
+    {
+      "epoch": 0.3655902066138592,
+      "grad_norm": 1.3332486152648926,
+      "learning_rate": 3.173433778319393e-05,
+      "loss": 0.9669,
+      "step": 6600
+    },
+    {
+      "epoch": 0.37112945216861465,
+      "grad_norm": 1.3557853698730469,
+      "learning_rate": 3.145737550545616e-05,
+      "loss": 0.9431,
+      "step": 6700
+    },
+    {
+      "epoch": 0.3766686977233701,
+      "grad_norm": 1.311341404914856,
+      "learning_rate": 3.118041322771838e-05,
+      "loss": 0.9675,
+      "step": 6800
+    },
+    {
+      "epoch": 0.3822079432781255,
+      "grad_norm": 1.3420363664627075,
+      "learning_rate": 3.0903450949980616e-05,
+      "loss": 0.9443,
+      "step": 6900
+    },
+    {
+      "epoch": 0.38774718883288095,
+      "grad_norm": 1.5872620344161987,
+      "learning_rate": 3.062648867224284e-05,
+      "loss": 0.9534,
+      "step": 7000
+    },
+    {
+      "epoch": 0.3932864343876364,
+      "grad_norm": 1.5827562808990479,
+      "learning_rate": 3.035229601728245e-05,
+      "loss": 0.9618,
+      "step": 7100
+    },
+    {
+      "epoch": 0.3988256799423918,
+      "grad_norm": 1.4099847078323364,
+      "learning_rate": 3.0075333739544676e-05,
+      "loss": 0.94,
+      "step": 7200
+    },
+    {
+      "epoch": 0.4043649254971473,
+      "grad_norm": 1.6116340160369873,
+      "learning_rate": 2.97983714618069e-05,
+      "loss": 0.9461,
+      "step": 7300
+    },
+    {
+      "epoch": 0.40990417105190274,
+      "grad_norm": 1.3645659685134888,
+      "learning_rate": 2.9521409184069133e-05,
+      "loss": 0.9427,
+      "step": 7400
+    },
+    {
+      "epoch": 0.4154434166066582,
+      "grad_norm": 1.7124513387680054,
+      "learning_rate": 2.924444690633136e-05,
+      "loss": 0.9431,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4209826621614136,
+      "grad_norm": 1.47300124168396,
+      "learning_rate": 2.896748462859359e-05,
+      "loss": 0.94,
+      "step": 7600
+    },
+    {
+      "epoch": 0.42652190771616905,
+      "grad_norm": 1.4425369501113892,
+      "learning_rate": 2.8690522350855815e-05,
+      "loss": 0.9439,
+      "step": 7700
+    },
+    {
+      "epoch": 0.4320611532709245,
+      "grad_norm": 1.1862937211990356,
+      "learning_rate": 2.8413560073118045e-05,
+      "loss": 0.9429,
+      "step": 7800
+    },
+    {
+      "epoch": 0.4376003988256799,
+      "grad_norm": 1.3416625261306763,
+      "learning_rate": 2.813659779538027e-05,
+      "loss": 0.9228,
+      "step": 7900
+    },
+    {
+      "epoch": 0.4431396443804354,
+      "grad_norm": 1.4095027446746826,
+      "learning_rate": 2.7859635517642497e-05,
+      "loss": 0.9477,
+      "step": 8000
+    },
+    {
+      "epoch": 0.44867888993519084,
+      "grad_norm": 1.3794485330581665,
+      "learning_rate": 2.7582673239904727e-05,
+      "loss": 0.9234,
+      "step": 8100
+    },
+    {
+      "epoch": 0.4542181354899463,
+      "grad_norm": 1.638173222541809,
+      "learning_rate": 2.7305710962166953e-05,
+      "loss": 0.9239,
+      "step": 8200
+    },
+    {
+      "epoch": 0.4597573810447017,
+      "grad_norm": 1.4151724576950073,
+      "learning_rate": 2.7028748684429183e-05,
+      "loss": 0.9488,
+      "step": 8300
+    },
+    {
+      "epoch": 0.46529662659945714,
+      "grad_norm": 1.4664607048034668,
+      "learning_rate": 2.675178640669141e-05,
+      "loss": 0.9281,
+      "step": 8400
+    },
+    {
+      "epoch": 0.4708358721542126,
+      "grad_norm": 1.4272499084472656,
+      "learning_rate": 2.647482412895364e-05,
+      "loss": 0.9252,
+      "step": 8500
+    },
+    {
+      "epoch": 0.47637511770896807,
+      "grad_norm": 1.380058765411377,
+      "learning_rate": 2.6197861851215866e-05,
+      "loss": 0.9067,
+      "step": 8600
+    },
+    {
+      "epoch": 0.4819143632637235,
+      "grad_norm": 1.385686993598938,
+      "learning_rate": 2.5920899573478092e-05,
+      "loss": 0.921,
+      "step": 8700
+    },
+    {
+      "epoch": 0.48745360881847893,
+      "grad_norm": 1.4072484970092773,
+      "learning_rate": 2.5643937295740322e-05,
+      "loss": 0.9134,
+      "step": 8800
+    },
+    {
+      "epoch": 0.49299285437323437,
+      "grad_norm": 1.5359854698181152,
+      "learning_rate": 2.5366975018002548e-05,
+      "loss": 0.9355,
+      "step": 8900
+    },
+    {
+      "epoch": 0.4985320999279898,
+      "grad_norm": 1.3707598447799683,
+      "learning_rate": 2.5090012740264778e-05,
+      "loss": 0.932,
+      "step": 9000
+    },
+    {
+      "epoch": 0.5040713454827452,
+      "grad_norm": 1.4937622547149658,
+      "learning_rate": 2.4815820085304385e-05,
+      "loss": 0.929,
+      "step": 9100
+    },
+    {
+      "epoch": 0.5096105910375007,
+      "grad_norm": 1.4973763227462769,
+      "learning_rate": 2.4538857807566608e-05,
+      "loss": 0.9313,
+      "step": 9200
+    },
+    {
+      "epoch": 0.5151498365922561,
+      "grad_norm": 1.3731300830841064,
+      "learning_rate": 2.4261895529828838e-05,
+      "loss": 0.8977,
+      "step": 9300
+    },
+    {
+      "epoch": 0.5206890821470116,
+      "grad_norm": 1.5620144605636597,
+      "learning_rate": 2.3984933252091064e-05,
+      "loss": 0.9255,
+      "step": 9400
+    },
+    {
+      "epoch": 0.526228327701767,
+      "grad_norm": 1.4226034879684448,
+      "learning_rate": 2.3707970974353294e-05,
+      "loss": 0.8994,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5317675732565225,
+      "grad_norm": 1.3993937969207764,
+      "learning_rate": 2.3431008696615524e-05,
+      "loss": 0.9212,
+      "step": 9600
+    },
+    {
+      "epoch": 0.537306818811278,
+      "grad_norm": 1.4125133752822876,
+      "learning_rate": 2.315404641887775e-05,
+      "loss": 0.9072,
+      "step": 9700
+    },
+    {
+      "epoch": 0.5428460643660333,
+      "grad_norm": 1.2466013431549072,
+      "learning_rate": 2.287708414113998e-05,
+      "loss": 0.9155,
+      "step": 9800
+    },
+    {
+      "epoch": 0.5483853099207888,
+      "grad_norm": 1.319427251815796,
+      "learning_rate": 2.2600121863402206e-05,
+      "loss": 0.8968,
+      "step": 9900
+    },
+    {
+      "epoch": 0.5539245554755442,
+      "grad_norm": 1.5401791334152222,
+      "learning_rate": 2.2323159585664432e-05,
+      "loss": 0.9146,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5594638010302997,
+      "grad_norm": 1.2928884029388428,
+      "learning_rate": 2.2046197307926662e-05,
+      "loss": 0.8996,
+      "step": 10100
+    },
+    {
+      "epoch": 0.5650030465850551,
+      "grad_norm": 1.5264612436294556,
+      "learning_rate": 2.176923503018889e-05,
+      "loss": 0.8889,
+      "step": 10200
+    },
+    {
+      "epoch": 0.5705422921398106,
+      "grad_norm": 1.5760724544525146,
+      "learning_rate": 2.1492272752451118e-05,
+      "loss": 0.8978,
+      "step": 10300
+    },
+    {
+      "epoch": 0.576081537694566,
+      "grad_norm": 1.414896845817566,
+      "learning_rate": 2.1215310474713345e-05,
+      "loss": 0.8989,
+      "step": 10400
+    },
+    {
+      "epoch": 0.5816207832493214,
+      "grad_norm": 1.422662377357483,
+      "learning_rate": 2.0938348196975574e-05,
+      "loss": 0.8695,
+      "step": 10500
+    },
+    {
+      "epoch": 0.5871600288040769,
+      "grad_norm": 1.6162989139556885,
+      "learning_rate": 2.06613859192378e-05,
+      "loss": 0.9017,
+      "step": 10600
+    },
+    {
+      "epoch": 0.5926992743588323,
+      "grad_norm": 1.537391185760498,
+      "learning_rate": 2.0384423641500027e-05,
+      "loss": 0.8946,
+      "step": 10700
+    },
+    {
+      "epoch": 0.5982385199135878,
+      "grad_norm": 1.3381567001342773,
+      "learning_rate": 2.0107461363762257e-05,
+      "loss": 0.8901,
+      "step": 10800
+    },
+    {
+      "epoch": 0.6037777654683432,
+      "grad_norm": 1.3765337467193604,
+      "learning_rate": 1.9830499086024483e-05,
+      "loss": 0.8872,
+      "step": 10900
+    },
+    {
+      "epoch": 0.6093170110230987,
+      "grad_norm": 1.5019334554672241,
+      "learning_rate": 1.9553536808286713e-05,
+      "loss": 0.8688,
+      "step": 11000
+    },
+    {
+      "epoch": 0.6148562565778541,
+      "grad_norm": 1.5896552801132202,
+      "learning_rate": 1.9276574530548943e-05,
+      "loss": 0.8863,
+      "step": 11100
+    },
+    {
+      "epoch": 0.6203955021326095,
+      "grad_norm": 1.481461524963379,
+      "learning_rate": 1.899961225281117e-05,
+      "loss": 0.8735,
+      "step": 11200
+    },
+    {
+      "epoch": 0.625934747687365,
+      "grad_norm": 1.5073565244674683,
+      "learning_rate": 1.8722649975073395e-05,
+      "loss": 0.8929,
+      "step": 11300
+    },
+    {
+      "epoch": 0.6314739932421204,
+      "grad_norm": 1.3693833351135254,
+      "learning_rate": 1.844568769733562e-05,
+      "loss": 0.8478,
+      "step": 11400
+    },
+    {
+      "epoch": 0.6370132387968759,
+      "grad_norm": 1.481180191040039,
+      "learning_rate": 1.816872541959785e-05,
+      "loss": 0.8784,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6425524843516313,
+      "grad_norm": 1.5158451795578003,
+      "learning_rate": 1.789176314186008e-05,
+      "loss": 0.8697,
+      "step": 11600
+    },
+    {
+      "epoch": 0.6480917299063867,
+      "grad_norm": 1.4979525804519653,
+      "learning_rate": 1.7614800864122307e-05,
+      "loss": 0.9006,
+      "step": 11700
+    },
+    {
+      "epoch": 0.6536309754611422,
+      "grad_norm": 1.3702558279037476,
+      "learning_rate": 1.7337838586384537e-05,
+      "loss": 0.8745,
+      "step": 11800
+    },
+    {
+      "epoch": 0.6591702210158976,
+      "grad_norm": 1.298034429550171,
+      "learning_rate": 1.7060876308646763e-05,
+      "loss": 0.8719,
+      "step": 11900
+    },
+    {
+      "epoch": 0.6647094665706531,
+      "grad_norm": 1.3086830377578735,
+      "learning_rate": 1.678668365368637e-05,
+      "loss": 0.8478,
+      "step": 12000
+    },
+    {
+      "epoch": 0.6702487121254085,
+      "grad_norm": 1.4746365547180176,
+      "learning_rate": 1.6509721375948597e-05,
+      "loss": 0.8843,
+      "step": 12100
+    },
+    {
+      "epoch": 0.675787957680164,
+      "grad_norm": 1.503086805343628,
+      "learning_rate": 1.6232759098210827e-05,
+      "loss": 0.8948,
+      "step": 12200
+    },
+    {
+      "epoch": 0.6813272032349194,
+      "grad_norm": 1.4060204029083252,
+      "learning_rate": 1.595579682047305e-05,
+      "loss": 0.8695,
+      "step": 12300
+    },
+    {
+      "epoch": 0.6868664487896748,
+      "grad_norm": 1.5291565656661987,
+      "learning_rate": 1.568160416551266e-05,
+      "loss": 0.9056,
+      "step": 12400
+    },
+    {
+      "epoch": 0.6924056943444303,
+      "grad_norm": 1.3221312761306763,
+      "learning_rate": 1.5404641887774887e-05,
+      "loss": 0.8651,
+      "step": 12500
+    },
+    {
+      "epoch": 0.6979449398991857,
+      "grad_norm": 1.5272188186645508,
+      "learning_rate": 1.5127679610037113e-05,
+      "loss": 0.8725,
+      "step": 12600
+    },
+    {
+      "epoch": 0.7034841854539412,
+      "grad_norm": 1.4335006475448608,
+      "learning_rate": 1.4850717332299341e-05,
+      "loss": 0.8663,
+      "step": 12700
+    },
+    {
+      "epoch": 0.7090234310086966,
+      "grad_norm": 1.321509838104248,
+      "learning_rate": 1.457375505456157e-05,
+      "loss": 0.8565,
+      "step": 12800
+    },
+    {
+      "epoch": 0.7145626765634521,
+      "grad_norm": 1.3843624591827393,
+      "learning_rate": 1.4296792776823797e-05,
+      "loss": 0.8614,
+      "step": 12900
+    },
+    {
+      "epoch": 0.7201019221182074,
+      "grad_norm": 1.3091601133346558,
+      "learning_rate": 1.4019830499086025e-05,
+      "loss": 0.8538,
+      "step": 13000
+    },
+    {
+      "epoch": 0.7256411676729629,
+      "grad_norm": 1.5815715789794922,
+      "learning_rate": 1.3742868221348253e-05,
+      "loss": 0.8624,
+      "step": 13100
+    },
+    {
+      "epoch": 0.7311804132277184,
+      "grad_norm": 1.6078437566757202,
+      "learning_rate": 1.346590594361048e-05,
+      "loss": 0.8405,
+      "step": 13200
+    },
+    {
+      "epoch": 0.7367196587824738,
+      "grad_norm": 1.446047306060791,
+      "learning_rate": 1.3188943665872708e-05,
+      "loss": 0.8445,
+      "step": 13300
+    },
+    {
+      "epoch": 0.7422589043372293,
+      "grad_norm": 1.207653284072876,
+      "learning_rate": 1.2911981388134936e-05,
+      "loss": 0.8431,
+      "step": 13400
+    },
+    {
+      "epoch": 0.7477981498919847,
+      "grad_norm": 1.3394980430603027,
+      "learning_rate": 1.2635019110397164e-05,
+      "loss": 0.868,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7533373954467402,
+      "grad_norm": 1.549267053604126,
+      "learning_rate": 1.2358056832659392e-05,
+      "loss": 0.8604,
+      "step": 13600
+    },
+    {
+      "epoch": 0.7588766410014955,
+      "grad_norm": 1.3387057781219482,
+      "learning_rate": 1.2081094554921622e-05,
+      "loss": 0.8563,
+      "step": 13700
+    },
+    {
+      "epoch": 0.764415886556251,
+      "grad_norm": 1.3845041990280151,
+      "learning_rate": 1.1804132277183848e-05,
+      "loss": 0.8365,
+      "step": 13800
+    },
+    {
+      "epoch": 0.7699551321110065,
+      "grad_norm": 1.4750843048095703,
+      "learning_rate": 1.1527169999446076e-05,
+      "loss": 0.8322,
+      "step": 13900
+    },
+    {
+      "epoch": 0.7754943776657619,
+      "grad_norm": 1.4781407117843628,
+      "learning_rate": 1.1250207721708304e-05,
+      "loss": 0.8696,
+      "step": 14000
+    },
+    {
+      "epoch": 0.7810336232205174,
+      "grad_norm": 1.5403274297714233,
+      "learning_rate": 1.0973245443970532e-05,
+      "loss": 0.8381,
+      "step": 14100
+    },
+    {
+      "epoch": 0.7865728687752728,
+      "grad_norm": 1.4403986930847168,
+      "learning_rate": 1.069628316623276e-05,
+      "loss": 0.8341,
+      "step": 14200
+    },
+    {
+      "epoch": 0.7921121143300283,
+      "grad_norm": 1.509552001953125,
+      "learning_rate": 1.0419320888494988e-05,
+      "loss": 0.8689,
+      "step": 14300
+    },
+    {
+      "epoch": 0.7976513598847836,
+      "grad_norm": 1.567030668258667,
+      "learning_rate": 1.0142358610757214e-05,
+      "loss": 0.8496,
+      "step": 14400
+    },
+    {
+      "epoch": 0.8031906054395391,
+      "grad_norm": 1.4610817432403564,
+      "learning_rate": 9.865396333019443e-06,
+      "loss": 0.8694,
+      "step": 14500
+    },
+    {
+      "epoch": 0.8087298509942946,
+      "grad_norm": 1.4665472507476807,
+      "learning_rate": 9.58843405528167e-06,
+      "loss": 0.843,
+      "step": 14600
+    },
+    {
+      "epoch": 0.81426909654905,
+      "grad_norm": 1.45100998878479,
+      "learning_rate": 9.3114717775439e-06,
+      "loss": 0.8529,
+      "step": 14700
+    },
+    {
+      "epoch": 0.8198083421038055,
+      "grad_norm": 1.4459706544876099,
+      "learning_rate": 9.034509499806127e-06,
+      "loss": 0.8251,
+      "step": 14800
+    },
+    {
+      "epoch": 0.8253475876585609,
+      "grad_norm": 1.408592700958252,
+      "learning_rate": 8.757547222068355e-06,
+      "loss": 0.858,
+      "step": 14900
+    },
+    {
+      "epoch": 0.8308868332133164,
+      "grad_norm": 1.4576612710952759,
+      "learning_rate": 8.480584944330583e-06,
+      "loss": 0.8294,
+      "step": 15000
+    },
+    {
+      "epoch": 0.8364260787680717,
+      "grad_norm": 1.4453418254852295,
+      "learning_rate": 8.203622666592809e-06,
+      "loss": 0.8421,
+      "step": 15100
+    },
+    {
+      "epoch": 0.8419653243228272,
+      "grad_norm": 1.4345848560333252,
+      "learning_rate": 7.926660388855039e-06,
+      "loss": 0.8338,
+      "step": 15200
+    },
+    {
+      "epoch": 0.8475045698775827,
+      "grad_norm": 1.4117823839187622,
+      "learning_rate": 7.649698111117267e-06,
+      "loss": 0.8494,
+      "step": 15300
+    },
+    {
+      "epoch": 0.8530438154323381,
+      "grad_norm": 1.7380582094192505,
+      "learning_rate": 7.372735833379495e-06,
+      "loss": 0.831,
+      "step": 15400
+    },
+    {
+      "epoch": 0.8585830609870936,
+      "grad_norm": 1.372897744178772,
+      "learning_rate": 7.095773555641721e-06,
+      "loss": 0.8201,
+      "step": 15500
+    },
+    {
+      "epoch": 0.864122306541849,
+      "grad_norm": 1.482770562171936,
+      "learning_rate": 6.81881127790395e-06,
+      "loss": 0.8221,
+      "step": 15600
+    },
+    {
+      "epoch": 0.8696615520966045,
+      "grad_norm": 1.394877314567566,
+      "learning_rate": 6.541849000166178e-06,
+      "loss": 0.8441,
+      "step": 15700
+    },
+    {
+      "epoch": 0.8752007976513598,
+      "grad_norm": 1.4818041324615479,
+      "learning_rate": 6.264886722428405e-06,
+      "loss": 0.843,
+      "step": 15800
+    },
+    {
+      "epoch": 0.8807400432061153,
+      "grad_norm": 1.8270115852355957,
+      "learning_rate": 5.9879244446906334e-06,
+      "loss": 0.851,
+      "step": 15900
+    },
+    {
+      "epoch": 0.8862792887608708,
+      "grad_norm": 1.4031203985214233,
+      "learning_rate": 5.7109621669528615e-06,
+      "loss": 0.8515,
+      "step": 16000
+    },
+    {
+      "epoch": 0.8918185343156262,
+      "grad_norm": 1.5000931024551392,
+      "learning_rate": 5.4339998892150895e-06,
+      "loss": 0.819,
+      "step": 16100
+    },
+    {
+      "epoch": 0.8973577798703817,
+      "grad_norm": 1.4219608306884766,
+      "learning_rate": 5.1570376114773176e-06,
+      "loss": 0.8528,
+      "step": 16200
+    },
+    {
+      "epoch": 0.9028970254251371,
+      "grad_norm": 1.6713409423828125,
+      "learning_rate": 4.880075333739545e-06,
+      "loss": 0.8253,
+      "step": 16300
+    },
+    {
+      "epoch": 0.9084362709798925,
+      "grad_norm": 1.642972707748413,
+      "learning_rate": 4.603113056001773e-06,
+      "loss": 0.8199,
+      "step": 16400
+    },
+    {
+      "epoch": 0.913975516534648,
+      "grad_norm": 1.4362276792526245,
+      "learning_rate": 4.328920401041378e-06,
+      "loss": 0.8186,
+      "step": 16500
+    },
+    {
+      "epoch": 0.9195147620894034,
+      "grad_norm": 1.387813925743103,
+      "learning_rate": 4.051958123303606e-06,
+      "loss": 0.8447,
+      "step": 16600
+    },
+    {
+      "epoch": 0.9250540076441589,
+      "grad_norm": 1.7197731733322144,
+      "learning_rate": 3.774995845565834e-06,
+      "loss": 0.8416,
+      "step": 16700
+    },
+    {
+      "epoch": 0.9305932531989143,
+      "grad_norm": 1.4148505926132202,
+      "learning_rate": 3.498033567828062e-06,
+      "loss": 0.8388,
+      "step": 16800
+    },
+    {
+      "epoch": 0.9361324987536698,
+      "grad_norm": 1.5057902336120605,
+      "learning_rate": 3.2210712900902897e-06,
+      "loss": 0.8141,
+      "step": 16900
+    },
+    {
+      "epoch": 0.9416717443084252,
+      "grad_norm": 1.6533297300338745,
+      "learning_rate": 2.9441090123525177e-06,
+      "loss": 0.8131,
+      "step": 17000
+    },
+    {
+      "epoch": 0.9472109898631806,
+      "grad_norm": 1.550384759902954,
+      "learning_rate": 2.6671467346147458e-06,
+      "loss": 0.8474,
+      "step": 17100
+    },
+    {
+      "epoch": 0.9527502354179361,
+      "grad_norm": 1.3930208683013916,
+      "learning_rate": 2.3901844568769734e-06,
+      "loss": 0.8252,
+      "step": 17200
+    },
+    {
+      "epoch": 0.9582894809726915,
+      "grad_norm": 1.534490704536438,
+      "learning_rate": 2.1132221791392014e-06,
+      "loss": 0.8333,
+      "step": 17300
+    },
+    {
+      "epoch": 0.963828726527447,
+      "grad_norm": 1.496036171913147,
+      "learning_rate": 1.836259901401429e-06,
+      "loss": 0.8452,
+      "step": 17400
+    },
+    {
+      "epoch": 0.9693679720822024,
+      "grad_norm": 1.4429802894592285,
+      "learning_rate": 1.559297623663657e-06,
+      "loss": 0.8368,
+      "step": 17500
+    },
+    {
+      "epoch": 0.9749072176369579,
+      "grad_norm": 1.4180331230163574,
+      "learning_rate": 1.282335345925885e-06,
+      "loss": 0.8139,
+      "step": 17600
+    },
+    {
+      "epoch": 0.9804464631917132,
+      "grad_norm": 1.423274278640747,
+      "learning_rate": 1.005373068188113e-06,
+      "loss": 0.809,
+      "step": 17700
+    },
+    {
+      "epoch": 0.9859857087464687,
+      "grad_norm": 1.4893913269042969,
+      "learning_rate": 7.284107904503407e-07,
+      "loss": 0.8271,
+      "step": 17800
+    },
+    {
+      "epoch": 0.9915249543012242,
+      "grad_norm": 1.5484572649002075,
+      "learning_rate": 4.5144851271256857e-07,
+      "loss": 0.8409,
+      "step": 17900
+    },
+    {
+      "epoch": 0.9970641998559796,
+      "grad_norm": 1.423147439956665,
+      "learning_rate": 1.7448623497479645e-07,
+      "loss": 0.8285,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 18053,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 18053,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.47361101474431e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..bd5a9ab
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc002492ebea20ff538f4e511bdeddeb8af4cd81f31240f552feb26de6c0d0a6
+size 5048
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..6c49fc6
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833