commit 8eae555d0b5f69e74071aa098213b2bac623975c
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sun May 24 01:55:15 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: BEE-spoke-data/Mixtral-GQA-400m-v2
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..a6344aa
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..71781c1
--- /dev/null
+++ b/README.md
@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+language:
+- en
+---
+
+
+
+#  BEE-spoke-data/Mixtral-GQA-400m-v2
+
+
+
+
+## testing code
+
+```python
+# !pip install -U -q transformers datasets accelerate sentencepiece
+import pprint as pp
+from transformers import pipeline
+
+pipe = pipeline(
+    "text-generation",
+    model="BEE-spoke-data/Mixtral-GQA-400m-v2",
+    device_map="auto",
+)
+pipe.model.config.pad_token_id = pipe.model.config.eos_token_id
+
+prompt = "My favorite movie is Godfather because"
+
+res = pipe(
+    prompt,
+    max_new_tokens=256,
+    top_k=4,
+    penalty_alpha=0.6,
+    use_cache=True,
+    no_repeat_ngram_size=4,
+    repetition_penalty=1.1,
+    renormalize_logits=True,
+)
+pp.pprint(res[0])
+```
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..a33590d
--- /dev/null
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/workspace/axolotl/mixtral-smol-400-v2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..59cf3fd
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..07af250
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed8d25c13b5844e479e79e2bb6c1575e37cd14c850acb4fef3f0e64f666333c
+size 4274322736
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..72ecfee
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..8b443ef
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..3930c93
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..b5a7ba3
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1853 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.36951013513513514,
+  "eval_steps": 406,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_loss": 10.780741691589355,
+      "eval_runtime": 947.394,
+      "eval_samples_per_second": 79.833,
+      "eval_steps_per_second": 4.435,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.25e-05,
+      "loss": 10.7434,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.5e-05,
+      "loss": 9.9589,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.75e-05,
+      "loss": 8.6595,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9e-05,
+      "loss": 7.9676,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001125,
+      "loss": 7.4358,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.000135,
+      "loss": 7.1452,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015749999999999998,
+      "loss": 6.9396,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018,
+      "loss": 6.8089,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002025,
+      "loss": 6.6897,
+      "step": 45
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.000225,
+      "loss": 6.4553,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00022499913644577618,
+      "loss": 6.3166,
+      "step": 55
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002249965457963621,
+      "loss": 6.1718,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022499222809152964,
+      "loss": 6.0497,
+      "step": 65
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022498618339756446,
+      "loss": 5.9306,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022497841180726518,
+      "loss": 5.825,
+      "step": 75
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022496891343994188,
+      "loss": 5.7394,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022495768844141414,
+      "loss": 5.6247,
+      "step": 85
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.000224944736984009,
+      "loss": 5.5139,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00022493005926655827,
+      "loss": 5.3914,
+      "step": 95
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002249136555143953,
+      "loss": 5.369,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022489552597935173,
+      "loss": 5.3003,
+      "step": 105
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022487567093975358,
+      "loss": 5.2256,
+      "step": 110
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022485409070041688,
+      "loss": 5.141,
+      "step": 115
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022483078559264308,
+      "loss": 5.0825,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022480575597421393,
+      "loss": 5.0306,
+      "step": 125
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002247790022293861,
+      "loss": 4.9651,
+      "step": 130
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.000224750524768885,
+      "loss": 4.9608,
+      "step": 135
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022472032402989878,
+      "loss": 4.9164,
+      "step": 140
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00022468840047607143,
+      "loss": 4.8746,
+      "step": 145
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00022465475459749576,
+      "loss": 4.7804,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00022461938691070582,
+      "loss": 4.7936,
+      "step": 155
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000224582297958669,
+      "loss": 4.7272,
+      "step": 160
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00022454348831077767,
+      "loss": 4.7058,
+      "step": 165
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00022450295856284047,
+      "loss": 4.6486,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002244607093370731,
+      "loss": 4.6536,
+      "step": 175
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002244167412820889,
+      "loss": 4.5721,
+      "step": 180
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022437105507288872,
+      "loss": 4.5511,
+      "step": 185
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022432365141085068,
+      "loss": 4.4932,
+      "step": 190
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022427453102371933,
+      "loss": 4.5251,
+      "step": 195
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002242236946655946,
+      "loss": 4.4763,
+      "step": 200
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022417114311692,
+      "loss": 4.5116,
+      "step": 205
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022411687718447093,
+      "loss": 4.4102,
+      "step": 210
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022406089770134205,
+      "loss": 4.4343,
+      "step": 215
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00022400320552693452,
+      "loss": 4.4403,
+      "step": 220
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000223943801546943,
+      "loss": 4.4068,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0002238826866733418,
+      "loss": 4.3988,
+      "step": 230
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022381986184437112,
+      "loss": 4.3703,
+      "step": 235
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022375532802452238,
+      "loss": 4.303,
+      "step": 240
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022368908620452367,
+      "loss": 4.2979,
+      "step": 245
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022362113740132436,
+      "loss": 4.2974,
+      "step": 250
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022355148265807966,
+      "loss": 4.2652,
+      "step": 255
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00022348012304413426,
+      "loss": 4.203,
+      "step": 260
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022340705965500642,
+      "loss": 4.2045,
+      "step": 265
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022333229361237082,
+      "loss": 4.2342,
+      "step": 270
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022325582606404126,
+      "loss": 4.1869,
+      "step": 275
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022317765818395332,
+      "loss": 4.0939,
+      "step": 280
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022309779117214617,
+      "loss": 4.1401,
+      "step": 285
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022301622625474417,
+      "loss": 4.0744,
+      "step": 290
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00022293296468393808,
+      "loss": 4.0818,
+      "step": 295
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002228480077379657,
+      "loss": 4.029,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022276135672109258,
+      "loss": 4.0574,
+      "step": 305
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022267301296359155,
+      "loss": 4.0003,
+      "step": 310
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022258297782172258,
+      "loss": 4.0143,
+      "step": 315
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000222491252677712,
+      "loss": 3.9962,
+      "step": 320
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002223978389397311,
+      "loss": 3.9994,
+      "step": 325
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022230273804187456,
+      "loss": 3.9424,
+      "step": 330
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022220595144413854,
+      "loss": 3.9215,
+      "step": 335
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022210748063239815,
+      "loss": 3.9483,
+      "step": 340
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00022200732711838466,
+      "loss": 3.9037,
+      "step": 345
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00022190549243966234,
+      "loss": 3.8959,
+      "step": 350
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0002218019781596049,
+      "loss": 3.8066,
+      "step": 355
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00022169678586737127,
+      "loss": 3.8306,
+      "step": 360
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00022158991717788137,
+      "loss": 3.7961,
+      "step": 365
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00022148137373179146,
+      "loss": 3.7739,
+      "step": 370
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0002213711571954686,
+      "loss": 3.7727,
+      "step": 375
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00022125926926096538,
+      "loss": 3.7895,
+      "step": 380
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0002211457116459937,
+      "loss": 3.7839,
+      "step": 385
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022103048609389868,
+      "loss": 3.7261,
+      "step": 390
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022091359437363157,
+      "loss": 3.7129,
+      "step": 395
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022079503827972293,
+      "loss": 3.6765,
+      "step": 400
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002206748196322547,
+      "loss": 3.6463,
+      "step": 405
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 3.6351399421691895,
+      "eval_runtime": 955.1583,
+      "eval_samples_per_second": 79.184,
+      "eval_steps_per_second": 4.399,
+      "step": 406
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022055294027683266,
+      "loss": 3.6138,
+      "step": 410
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002204294020845578,
+      "loss": 3.6069,
+      "step": 415
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022030420695199774,
+      "loss": 3.5781,
+      "step": 420
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00022017735680115755,
+      "loss": 3.5925,
+      "step": 425
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00022004885357945026,
+      "loss": 3.6038,
+      "step": 430
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000219918699259667,
+      "loss": 3.5368,
+      "step": 435
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00021978689583994666,
+      "loss": 3.5982,
+      "step": 440
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00021965344534374522,
+      "loss": 3.5501,
+      "step": 445
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0002195183498198047,
+      "loss": 3.5315,
+      "step": 450
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00021938161134212177,
+      "loss": 3.5229,
+      "step": 455
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00021924323200991577,
+      "loss": 3.5106,
+      "step": 460
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00021910321394759662,
+      "loss": 3.4851,
+      "step": 465
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00021896155930473216,
+      "loss": 3.4405,
+      "step": 470
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00021881827025601504,
+      "loss": 3.5036,
+      "step": 475
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00021867334900122954,
+      "loss": 3.4158,
+      "step": 480
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002185267977652176,
+      "loss": 3.465,
+      "step": 485
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00021837861879784484,
+      "loss": 3.3843,
+      "step": 490
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002182288143739659,
+      "loss": 3.3678,
+      "step": 495
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00021807738679338953,
+      "loss": 3.4079,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002179243383808433,
+      "loss": 3.3826,
+      "step": 505
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021776967148593793,
+      "loss": 3.4016,
+      "step": 510
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021761338848313123,
+      "loss": 3.3715,
+      "step": 515
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0002174554917716916,
+      "loss": 3.4046,
+      "step": 520
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021729598377566122,
+      "loss": 3.3304,
+      "step": 525
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021713486694381875,
+      "loss": 3.3419,
+      "step": 530
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021697214374964195,
+      "loss": 3.3681,
+      "step": 535
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0002168078166912695,
+      "loss": 3.3012,
+      "step": 540
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00021664188829146277,
+      "loss": 3.3551,
+      "step": 545
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000216474361097567,
+      "loss": 3.2824,
+      "step": 550
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021630523768147218,
+      "loss": 3.3024,
+      "step": 555
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021613452063957379,
+      "loss": 3.2661,
+      "step": 560
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021596221259273266,
+      "loss": 3.2882,
+      "step": 565
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002157883161862348,
+      "loss": 3.3181,
+      "step": 570
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021561283408975097,
+      "loss": 3.2574,
+      "step": 575
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021543576899729543,
+      "loss": 3.2339,
+      "step": 580
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00021525712362718483,
+      "loss": 3.2554,
+      "step": 585
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021507690072199625,
+      "loss": 3.1892,
+      "step": 590
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021489510304852536,
+      "loss": 3.2946,
+      "step": 595
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021471173339774363,
+      "loss": 3.2303,
+      "step": 600
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021452679458475567,
+      "loss": 3.2891,
+      "step": 605
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021434028944875607,
+      "loss": 3.224,
+      "step": 610
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021415222085298573,
+      "loss": 3.2337,
+      "step": 615
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00021396259168468773,
+      "loss": 3.2158,
+      "step": 620
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002137714048550634,
+      "loss": 3.2126,
+      "step": 625
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002135786632992273,
+      "loss": 3.1934,
+      "step": 630
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021338436997616223,
+      "loss": 3.2051,
+      "step": 635
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021318852786867388,
+      "loss": 3.2667,
+      "step": 640
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021299113998334503,
+      "loss": 3.1956,
+      "step": 645
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021279220935048926,
+      "loss": 3.1771,
+      "step": 650
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002125917390241046,
+      "loss": 3.1467,
+      "step": 655
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021238973208182659,
+      "loss": 3.1788,
+      "step": 660
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00021218619162488095,
+      "loss": 3.1967,
+      "step": 665
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021198112077803607,
+      "loss": 3.149,
+      "step": 670
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021177452268955496,
+      "loss": 3.154,
+      "step": 675
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000211566400531147,
+      "loss": 3.1652,
+      "step": 680
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021135675749791924,
+      "loss": 3.1433,
+      "step": 685
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021114559680832722,
+      "loss": 3.1893,
+      "step": 690
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0002109329217041257,
+      "loss": 3.1788,
+      "step": 695
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021071873545031885,
+      "loss": 3.1549,
+      "step": 700
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021050304133511018,
+      "loss": 3.1294,
+      "step": 705
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00021028584266985186,
+      "loss": 3.1109,
+      "step": 710
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021006714278899415,
+      "loss": 3.1713,
+      "step": 715
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020984694505003402,
+      "loss": 3.1304,
+      "step": 720
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020962525283346376,
+      "loss": 3.1285,
+      "step": 725
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0002094020695427188,
+      "loss": 3.0582,
+      "step": 730
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020917739860412592,
+      "loss": 3.1063,
+      "step": 735
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020895124346685017,
+      "loss": 3.1309,
+      "step": 740
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020872360760284219,
+      "loss": 3.1125,
+      "step": 745
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0002084944945067849,
+      "loss": 3.1108,
+      "step": 750
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00020826390769603968,
+      "loss": 3.0765,
+      "step": 755
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00020803185071059267,
+      "loss": 3.0634,
+      "step": 760
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000207798327113,
+      "loss": 3.0993,
+      "step": 765
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0002075633404883336,
+      "loss": 3.1127,
+      "step": 770
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00020732689444412573,
+      "loss": 3.0502,
+      "step": 775
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0002070889926103138,
+      "loss": 3.0436,
+      "step": 780
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0002068496386391846,
+      "loss": 3.0305,
+      "step": 785
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0002066088362053184,
+      "loss": 3.0996,
+      "step": 790
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020636658900553213,
+      "loss": 3.0584,
+      "step": 795
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020612290075882296,
+      "loss": 3.0508,
+      "step": 800
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020587777520631126,
+      "loss": 3.0578,
+      "step": 805
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020563121611118286,
+      "loss": 3.0308,
+      "step": 810
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 3.0524611473083496,
+      "eval_runtime": 955.714,
+      "eval_samples_per_second": 79.138,
+      "eval_steps_per_second": 4.397,
+      "step": 812
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020538322725863146,
+      "loss": 3.122,
+      "step": 815
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020513381245580064,
+      "loss": 2.9886,
+      "step": 820
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020488297553172515,
+      "loss": 3.0606,
+      "step": 825
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00020463072033727225,
+      "loss": 2.993,
+      "step": 830
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020437705074508264,
+      "loss": 2.9999,
+      "step": 835
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020412197064951097,
+      "loss": 3.0143,
+      "step": 840
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000203865483966566,
+      "loss": 2.9886,
+      "step": 845
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020360759463385053,
+      "loss": 3.0219,
+      "step": 850
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020334830661050102,
+      "loss": 2.9888,
+      "step": 855
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020308762387712662,
+      "loss": 3.0271,
+      "step": 860
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020282555043574823,
+      "loss": 3.0063,
+      "step": 865
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00020256209030973708,
+      "loss": 3.0198,
+      "step": 870
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020229724754375266,
+      "loss": 3.0135,
+      "step": 875
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020203102620368113,
+      "loss": 3.0008,
+      "step": 880
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020176343037657242,
+      "loss": 3.0168,
+      "step": 885
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020149446417057782,
+      "loss": 3.042,
+      "step": 890
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020122413171488667,
+      "loss": 2.9954,
+      "step": 895
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00020095243715966316,
+      "loss": 3.0191,
+      "step": 900
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002006793846759825,
+      "loss": 3.0343,
+      "step": 905
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002004049784557669,
+      "loss": 2.9843,
+      "step": 910
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00020012922271172128,
+      "loss": 3.0263,
+      "step": 915
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019985212167726853,
+      "loss": 2.975,
+      "step": 920
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001995736796064845,
+      "loss": 2.9858,
+      "step": 925
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001992939007740328,
+      "loss": 2.9526,
+      "step": 930
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001990127894750991,
+      "loss": 2.971,
+      "step": 935
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019873035002532512,
+      "loss": 2.9635,
+      "step": 940
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019844658676074255,
+      "loss": 2.9807,
+      "step": 945
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001981615040377063,
+      "loss": 2.9822,
+      "step": 950
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019787510623282776,
+      "loss": 2.9552,
+      "step": 955
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019758739774290753,
+      "loss": 2.9877,
+      "step": 960
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019729838298486793,
+      "loss": 2.974,
+      "step": 965
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019700806639568524,
+      "loss": 2.9613,
+      "step": 970
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019671645243232155,
+      "loss": 2.9949,
+      "step": 975
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019642354557165633,
+      "loss": 2.9876,
+      "step": 980
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019612935031041768,
+      "loss": 2.9644,
+      "step": 985
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019583387116511335,
+      "loss": 2.9204,
+      "step": 990
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019553711267196136,
+      "loss": 2.9849,
+      "step": 995
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019523907938682038,
+      "loss": 2.9622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019493977588511978,
+      "loss": 2.9457,
+      "step": 1005
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001946392067617894,
+      "loss": 2.9558,
+      "step": 1010
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019433737663118898,
+      "loss": 2.9107,
+      "step": 1015
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001940342901270374,
+      "loss": 2.963,
+      "step": 1020
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019372995190234136,
+      "loss": 2.8945,
+      "step": 1025
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019342436662932416,
+      "loss": 2.9756,
+      "step": 1030
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019311753899935389,
+      "loss": 2.9392,
+      "step": 1035
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019280947372287132,
+      "loss": 2.9293,
+      "step": 1040
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019250017552931774,
+      "loss": 2.947,
+      "step": 1045
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019218964916706223,
+      "loss": 2.9317,
+      "step": 1050
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019187789940332882,
+      "loss": 2.8816,
+      "step": 1055
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001915649310241233,
+      "loss": 2.9644,
+      "step": 1060
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001912507488341597,
+      "loss": 2.9219,
+      "step": 1065
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019093535765678663,
+      "loss": 2.8983,
+      "step": 1070
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019061876233391313,
+      "loss": 2.8816,
+      "step": 1075
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019030096772593432,
+      "loss": 2.8844,
+      "step": 1080
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018998197871165692,
+      "loss": 2.9207,
+      "step": 1085
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018966180018822423,
+      "loss": 2.9553,
+      "step": 1090
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018934043707104098,
+      "loss": 2.893,
+      "step": 1095
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001890178942936979,
+      "loss": 2.9049,
+      "step": 1100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018869417680789587,
+      "loss": 2.8872,
+      "step": 1105
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018836928958337009,
+      "loss": 2.9219,
+      "step": 1110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018804323760781362,
+      "loss": 2.9005,
+      "step": 1115
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018771602588680083,
+      "loss": 2.8814,
+      "step": 1120
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018738765944371067,
+      "loss": 2.8915,
+      "step": 1125
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018705814331964945,
+      "loss": 2.8777,
+      "step": 1130
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001867274825733734,
+      "loss": 2.8821,
+      "step": 1135
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001863956822812112,
+      "loss": 2.8803,
+      "step": 1140
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018606274753698576,
+      "loss": 2.8787,
+      "step": 1145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018572868345193632,
+      "loss": 2.9365,
+      "step": 1150
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001853934951546398,
+      "loss": 2.8642,
+      "step": 1155
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018505718779093206,
+      "loss": 2.8333,
+      "step": 1160
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001847197665238291,
+      "loss": 2.9019,
+      "step": 1165
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018438123653344746,
+      "loss": 2.8726,
+      "step": 1170
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018404160301692504,
+      "loss": 2.8655,
+      "step": 1175
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018370087118834102,
+      "loss": 2.8639,
+      "step": 1180
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018335904627863605,
+      "loss": 2.8742,
+      "step": 1185
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018301613353553182,
+      "loss": 2.9013,
+      "step": 1190
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001826721382234505,
+      "loss": 2.9131,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000182327065623434,
+      "loss": 2.9068,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001819809210330627,
+      "loss": 2.9222,
+      "step": 1205
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001816337097663744,
+      "loss": 2.8718,
+      "step": 1210
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00018128543715378252,
+      "loss": 2.8504,
+      "step": 1215
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 2.8658618927001953,
+      "eval_runtime": 957.687,
+      "eval_samples_per_second": 78.975,
+      "eval_steps_per_second": 4.388,
+      "step": 1218
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00018093610854199438,
+      "loss": 2.8823,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00018058572929392902,
+      "loss": 2.8528,
+      "step": 1225
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000180234304788635,
+      "loss": 2.9415,
+      "step": 1230
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001798818404212077,
+      "loss": 2.8599,
+      "step": 1235
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017952834160270655,
+      "loss": 2.8218,
+      "step": 1240
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000179173813760072,
+      "loss": 2.8258,
+      "step": 1245
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017881826233604204,
+      "loss": 2.8397,
+      "step": 1250
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017846169278906888,
+      "loss": 2.8817,
+      "step": 1255
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017810411059323498,
+      "loss": 2.8424,
+      "step": 1260
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017774552123816904,
+      "loss": 2.845,
+      "step": 1265
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017738593022896177,
+      "loss": 2.8272,
+      "step": 1270
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017702534308608133,
+      "loss": 2.8452,
+      "step": 1275
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017666376534528866,
+      "loss": 2.8805,
+      "step": 1280
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017630120255755235,
+      "loss": 2.8824,
+      "step": 1285
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017593766028896357,
+      "loss": 2.8669,
+      "step": 1290
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001755731441206505,
+      "loss": 2.8883,
+      "step": 1295
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001752076596486927,
+      "loss": 2.813,
+      "step": 1300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001748412124840353,
+      "loss": 2.8275,
+      "step": 1305
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017447380825240264,
+      "loss": 2.8017,
+      "step": 1310
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017410545259421208,
+      "loss": 2.8368,
+      "step": 1315
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017373615116448736,
+      "loss": 2.8448,
+      "step": 1320
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017336590963277173,
+      "loss": 2.8353,
+      "step": 1325
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017299473368304102,
+      "loss": 2.8326,
+      "step": 1330
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017262262901361627,
+      "loss": 2.7981,
+      "step": 1335
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017224960133707627,
+      "loss": 2.828,
+      "step": 1340
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017187565638017,
+      "loss": 2.8209,
+      "step": 1345
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017150079988372842,
+      "loss": 2.8166,
+      "step": 1350
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001711250376025767,
+      "loss": 2.7783,
+      "step": 1355
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00017074837530544557,
+      "loss": 2.7564,
+      "step": 1360
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00017037081877488284,
+      "loss": 2.7957,
+      "step": 1365
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001699923738071648,
+      "loss": 2.8139,
+      "step": 1370
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016961304621220696,
+      "loss": 2.7938,
+      "step": 1375
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016923284181347506,
+      "loss": 2.8097,
+      "step": 1380
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016885176644789557,
+      "loss": 2.8043,
+      "step": 1385
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016846982596576614,
+      "loss": 2.7577,
+      "step": 1390
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001680870262306657,
+      "loss": 2.7921,
+      "step": 1395
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016770337311936456,
+      "loss": 2.7836,
+      "step": 1400
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00016731887252173408,
+      "loss": 2.7963,
+      "step": 1405
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001669335303406563,
+      "loss": 2.8547,
+      "step": 1410
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00016654735249193334,
+      "loss": 2.808,
+      "step": 1415
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00016616034490419648,
+      "loss": 2.7782,
+      "step": 1420
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00016577251351881532,
+      "loss": 2.76,
+      "step": 1425
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00016538386428980638,
+      "loss": 2.7957,
+      "step": 1430
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001649944031837418,
+      "loss": 2.819,
+      "step": 1435
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001646041361796578,
+      "loss": 2.7574,
+      "step": 1440
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016421306926896266,
+      "loss": 2.7939,
+      "step": 1445
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016382120845534497,
+      "loss": 2.7814,
+      "step": 1450
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016342855975468135,
+      "loss": 2.7271,
+      "step": 1455
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001630351291949442,
+      "loss": 2.8333,
+      "step": 1460
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001626409228161089,
+      "loss": 2.8128,
+      "step": 1465
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001622459466700615,
+      "loss": 2.7752,
+      "step": 1470
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016185020682050541,
+      "loss": 2.8474,
+      "step": 1475
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001614537093428685,
+      "loss": 2.8078,
+      "step": 1480
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016105646032420982,
+      "loss": 2.7696,
+      "step": 1485
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016065846586312617,
+      "loss": 2.8652,
+      "step": 1490
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001602597320696584,
+      "loss": 2.7888,
+      "step": 1495
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00015986026506519755,
+      "loss": 2.7349,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 4059,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.8026854820610048e+19,
+  "train_batch_size": 18,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..2e45346
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7338f8c5d7e5e87e4fe2f9db5fec5f4c807ae1d04e6511b11790439862115f76
+size 5240