Upload 16 files

README.md

@@ -1,24 +1,57 @@
 ---
-license: mit
+license: other
+base_model: calm2-7b
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: noberai-main-6
+  results: []
 ---
-cyberAgent社のCalm-7Bに対し、高品質なウェブ小説、青空文庫で構成されたおよそ3GBの厳選データセットでファインチューニングを施したモデルです。
-以下の指示チューニングを活用し、生成される小説の方向性を調節することができます。
 
-    ###指示：\n\n[キーワード：異世界転移、ファンタジー、異世界、魔法、シリアス]\n\n###出力:\n
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-または、小説の題名や作者の名前を指定することもできます。
+# noberai-main-6
 
-    ###指示:\n\n[作品名:ウェストミンスター寺院], [作者:アーヴィングワシントン]\n\n###出力:\n
+This model is a fine-tuned version of [calm2-7b](https://huggingface.co/calm2-7b) on the super-jeneri-beta dataset.
 
+## Model description
 
-これらの指示は、各項目を空白にしても動作するように設計しています。少なくとも`[キーワード：]`とだけ書いておけば動作します。
+More information needed
 
-コンテキスト長3072
+## Intended uses & limitations
 
+More information needed
 
+## Training and evaluation data
 
+More information needed
 
+## Training procedure
 
-# 免責事項
+### Training hyperparameters
 
-作者である私は、このモデルの使用によって起こったいかなる問題の責任も負いません。
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.93,
+    "train_loss": 0.048051854148181763,
+    "train_runtime": 5063.5443,
+    "train_samples_per_second": 54.75,
+    "train_steps_per_second": 0.427
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "calm2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4858ea15b2bd273fead3640175401bc33f9d7f143293c924cc1d0fdaf750808a
+size 4985122120

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e696d9851eb0dffd043ae0db209349daaa205328bae8688ba5eb4ef153ed5f
+size 4991431432

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1166eff786b0f9cb133c0a71fe9ea22679b43cceb7cb13068a65af84973f47f
+size 4723000160

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f604669dbf371487ddad6c4900d678db81bd86bd510dccd9bd02d7ba89455a2
+size 532676736

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15232196608
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '###指示:\\n' + content + '\\n\\n###出力:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.93,
+    "train_loss": 0.048051854148181763,
+    "train_runtime": 5063.5443,
+    "train_samples_per_second": 54.75,
+    "train_steps_per_second": 0.427
+}

trainer_state.json

@@ -0,0 +1,2592 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.9274893960816,
+  "eval_steps": 500,
+  "global_step": 1832,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.30875682830810547,
+      "learning_rate": 1.5e-06,
+      "loss": 3.2648,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.2472837269306183,
+      "learning_rate": 3e-06,
+      "loss": 3.2957,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.27992337942123413,
+      "learning_rate": 4.5e-06,
+      "loss": 3.3082,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2051214873790741,
+      "learning_rate": 6e-06,
+      "loss": 3.2454,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.23398754000663757,
+      "learning_rate": 7.5e-06,
+      "loss": 3.2516,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.21358206868171692,
+      "learning_rate": 9e-06,
+      "loss": 3.2567,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2220185399055481,
+      "learning_rate": 1.05e-05,
+      "loss": 3.2233,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.1718285083770752,
+      "learning_rate": 1.2e-05,
+      "loss": 3.2189,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1586149036884308,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 3.2114,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1811351776123047,
+      "learning_rate": 1.5e-05,
+      "loss": 3.2512,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.14845654368400574,
+      "learning_rate": 1.65e-05,
+      "loss": 3.203,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1642150580883026,
+      "learning_rate": 1.8e-05,
+      "loss": 3.2081,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.14407196640968323,
+      "learning_rate": 1.95e-05,
+      "loss": 3.255,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.13313639163970947,
+      "learning_rate": 2.1e-05,
+      "loss": 3.2154,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.14706526696681976,
+      "learning_rate": 2.25e-05,
+      "loss": 3.2013,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14185847342014313,
+      "learning_rate": 2.4e-05,
+      "loss": 3.1885,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.14037567377090454,
+      "learning_rate": 2.55e-05,
+      "loss": 3.2362,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.14292936027050018,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 3.1896,
+      "step": 90
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1628720611333847,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 3.2099,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14814336597919464,
+      "learning_rate": 3e-05,
+      "loss": 3.2269,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.14351879060268402,
+      "learning_rate": 2.991448118586089e-05,
+      "loss": 3.1992,
+      "step": 105
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.14756764471530914,
+      "learning_rate": 2.982896237172178e-05,
+      "loss": 3.1756,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.1422564834356308,
+      "learning_rate": 2.9743443557582668e-05,
+      "loss": 3.1774,
+      "step": 115
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.13317522406578064,
+      "learning_rate": 2.9657924743443557e-05,
+      "loss": 3.1923,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.14658209681510925,
+      "learning_rate": 2.9572405929304446e-05,
+      "loss": 3.2007,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1425113081932068,
+      "learning_rate": 2.948688711516534e-05,
+      "loss": 3.1538,
+      "step": 130
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.13603942096233368,
+      "learning_rate": 2.9401368301026228e-05,
+      "loss": 3.1756,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.14405600726604462,
+      "learning_rate": 2.9315849486887117e-05,
+      "loss": 3.1855,
+      "step": 140
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.14144060015678406,
+      "learning_rate": 2.9230330672748006e-05,
+      "loss": 3.1821,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.13670259714126587,
+      "learning_rate": 2.9144811858608895e-05,
+      "loss": 3.1469,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.14555875957012177,
+      "learning_rate": 2.9059293044469784e-05,
+      "loss": 3.1334,
+      "step": 155
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14179597795009613,
+      "learning_rate": 2.8973774230330673e-05,
+      "loss": 3.1912,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.13467080891132355,
+      "learning_rate": 2.8888255416191563e-05,
+      "loss": 3.1573,
+      "step": 165
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1724693775177002,
+      "learning_rate": 2.880273660205245e-05,
+      "loss": 3.1717,
+      "step": 170
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1808375120162964,
+      "learning_rate": 2.871721778791334e-05,
+      "loss": 3.1606,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1484830379486084,
+      "learning_rate": 2.8631698973774233e-05,
+      "loss": 3.153,
+      "step": 180
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15217700600624084,
+      "learning_rate": 2.8546180159635122e-05,
+      "loss": 3.127,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.16882199048995972,
+      "learning_rate": 2.846066134549601e-05,
+      "loss": 3.1582,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1615631878376007,
+      "learning_rate": 2.83751425313569e-05,
+      "loss": 3.1462,
+      "step": 195
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.14329533278942108,
+      "learning_rate": 2.828962371721779e-05,
+      "loss": 3.1041,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.15113158524036407,
+      "learning_rate": 2.820410490307868e-05,
+      "loss": 3.184,
+      "step": 205
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1513780653476715,
+      "learning_rate": 2.8118586088939568e-05,
+      "loss": 3.1227,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.16015127301216125,
+      "learning_rate": 2.8033067274800457e-05,
+      "loss": 3.1548,
+      "step": 215
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.14768767356872559,
+      "learning_rate": 2.7947548460661346e-05,
+      "loss": 3.1377,
+      "step": 220
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.148753359913826,
+      "learning_rate": 2.7862029646522235e-05,
+      "loss": 3.162,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.17637503147125244,
+      "learning_rate": 2.7776510832383128e-05,
+      "loss": 3.1687,
+      "step": 230
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.13954448699951172,
+      "learning_rate": 2.7690992018244017e-05,
+      "loss": 3.1667,
+      "step": 235
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.14189836382865906,
+      "learning_rate": 2.7605473204104906e-05,
+      "loss": 3.1399,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1491958051919937,
+      "learning_rate": 2.7519954389965795e-05,
+      "loss": 3.1121,
+      "step": 245
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.14595240354537964,
+      "learning_rate": 2.7434435575826684e-05,
+      "loss": 3.1527,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.15809328854084015,
+      "learning_rate": 2.7348916761687573e-05,
+      "loss": 3.1609,
+      "step": 255
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.14767523109912872,
+      "learning_rate": 2.7263397947548462e-05,
+      "loss": 3.1475,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.15313534438610077,
+      "learning_rate": 2.717787913340935e-05,
+      "loss": 3.127,
+      "step": 265
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.15991611778736115,
+      "learning_rate": 2.7092360319270237e-05,
+      "loss": 3.1614,
+      "step": 270
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.14508678019046783,
+      "learning_rate": 2.700684150513113e-05,
+      "loss": 3.1323,
+      "step": 275
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.14730039238929749,
+      "learning_rate": 2.692132269099202e-05,
+      "loss": 3.1293,
+      "step": 280
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.14069867134094238,
+      "learning_rate": 2.6835803876852908e-05,
+      "loss": 3.1154,
+      "step": 285
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1483781933784485,
+      "learning_rate": 2.6750285062713797e-05,
+      "loss": 3.1513,
+      "step": 290
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.14479319751262665,
+      "learning_rate": 2.6664766248574686e-05,
+      "loss": 3.1129,
+      "step": 295
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.13547484576702118,
+      "learning_rate": 2.6579247434435575e-05,
+      "loss": 3.1569,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.14407330751419067,
+      "learning_rate": 2.6493728620296464e-05,
+      "loss": 3.1319,
+      "step": 305
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15453161299228668,
+      "learning_rate": 2.6408209806157353e-05,
+      "loss": 3.1203,
+      "step": 310
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.13878263533115387,
+      "learning_rate": 2.6322690992018242e-05,
+      "loss": 3.1042,
+      "step": 315
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.14512255787849426,
+      "learning_rate": 2.623717217787913e-05,
+      "loss": 3.0954,
+      "step": 320
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.15042366087436676,
+      "learning_rate": 2.615165336374002e-05,
+      "loss": 3.0634,
+      "step": 325
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.16962555050849915,
+      "learning_rate": 2.6066134549600913e-05,
+      "loss": 3.0815,
+      "step": 330
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.14756160974502563,
+      "learning_rate": 2.5980615735461802e-05,
+      "loss": 3.0923,
+      "step": 335
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.14769217371940613,
+      "learning_rate": 2.589509692132269e-05,
+      "loss": 3.0942,
+      "step": 340
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.15603114664554596,
+      "learning_rate": 2.580957810718358e-05,
+      "loss": 3.0863,
+      "step": 345
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.14204762876033783,
+      "learning_rate": 2.572405929304447e-05,
+      "loss": 3.0707,
+      "step": 350
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.1573951095342636,
+      "learning_rate": 2.563854047890536e-05,
+      "loss": 3.0755,
+      "step": 355
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.1641531139612198,
+      "learning_rate": 2.5553021664766248e-05,
+      "loss": 3.0549,
+      "step": 360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.16347742080688477,
+      "learning_rate": 2.5467502850627137e-05,
+      "loss": 3.0753,
+      "step": 365
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1477546989917755,
+      "learning_rate": 2.5381984036488026e-05,
+      "loss": 3.1141,
+      "step": 370
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.15331922471523285,
+      "learning_rate": 2.5296465222348915e-05,
+      "loss": 3.0359,
+      "step": 375
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.14977489411830902,
+      "learning_rate": 2.5210946408209808e-05,
+      "loss": 3.0921,
+      "step": 380
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.15610727667808533,
+      "learning_rate": 2.5125427594070697e-05,
+      "loss": 3.0766,
+      "step": 385
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.16113075613975525,
+      "learning_rate": 2.5039908779931586e-05,
+      "loss": 3.0792,
+      "step": 390
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.16325776278972626,
+      "learning_rate": 2.4954389965792475e-05,
+      "loss": 3.0633,
+      "step": 395
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.14828483760356903,
+      "learning_rate": 2.4868871151653364e-05,
+      "loss": 3.0537,
+      "step": 400
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.14972282946109772,
+      "learning_rate": 2.4783352337514253e-05,
+      "loss": 3.0487,
+      "step": 405
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.15230616927146912,
+      "learning_rate": 2.4697833523375142e-05,
+      "loss": 3.0619,
+      "step": 410
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.1488548368215561,
+      "learning_rate": 2.461231470923603e-05,
+      "loss": 3.0887,
+      "step": 415
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.17049625515937805,
+      "learning_rate": 2.452679589509692e-05,
+      "loss": 3.078,
+      "step": 420
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.1818585842847824,
+      "learning_rate": 2.444127708095781e-05,
+      "loss": 3.0933,
+      "step": 425
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.15089115500450134,
+      "learning_rate": 2.4355758266818702e-05,
+      "loss": 3.0542,
+      "step": 430
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.16785630583763123,
+      "learning_rate": 2.427023945267959e-05,
+      "loss": 3.0591,
+      "step": 435
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.15143312513828278,
+      "learning_rate": 2.418472063854048e-05,
+      "loss": 3.0896,
+      "step": 440
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.14978434145450592,
+      "learning_rate": 2.409920182440137e-05,
+      "loss": 3.0589,
+      "step": 445
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.16092675924301147,
+      "learning_rate": 2.401368301026226e-05,
+      "loss": 3.0444,
+      "step": 450
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.15623970329761505,
+      "learning_rate": 2.3928164196123148e-05,
+      "loss": 3.0959,
+      "step": 455
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.15813413262367249,
+      "learning_rate": 2.3842645381984037e-05,
+      "loss": 3.0444,
+      "step": 460
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.1623263657093048,
+      "learning_rate": 2.3757126567844926e-05,
+      "loss": 3.0753,
+      "step": 465
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.16919799149036407,
+      "learning_rate": 2.3671607753705815e-05,
+      "loss": 3.0481,
+      "step": 470
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.1622595638036728,
+      "learning_rate": 2.3586088939566704e-05,
+      "loss": 3.065,
+      "step": 475
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.15223100781440735,
+      "learning_rate": 2.3500570125427597e-05,
+      "loss": 3.0647,
+      "step": 480
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.1645466536283493,
+      "learning_rate": 2.3415051311288486e-05,
+      "loss": 3.0444,
+      "step": 485
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.14715692400932312,
+      "learning_rate": 2.3329532497149375e-05,
+      "loss": 3.0299,
+      "step": 490
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.17336295545101166,
+      "learning_rate": 2.3244013683010264e-05,
+      "loss": 3.071,
+      "step": 495
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.1599658727645874,
+      "learning_rate": 2.3158494868871153e-05,
+      "loss": 3.0644,
+      "step": 500
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.16342023015022278,
+      "learning_rate": 2.3072976054732042e-05,
+      "loss": 3.0447,
+      "step": 505
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.16088004410266876,
+      "learning_rate": 2.298745724059293e-05,
+      "loss": 3.0885,
+      "step": 510
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.15718434751033783,
+      "learning_rate": 2.290193842645382e-05,
+      "loss": 3.0667,
+      "step": 515
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.16234581172466278,
+      "learning_rate": 2.281641961231471e-05,
+      "loss": 3.0954,
+      "step": 520
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.15279100835323334,
+      "learning_rate": 2.27309007981756e-05,
+      "loss": 3.0609,
+      "step": 525
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.1524941623210907,
+      "learning_rate": 2.264538198403649e-05,
+      "loss": 3.0233,
+      "step": 530
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.15686309337615967,
+      "learning_rate": 2.255986316989738e-05,
+      "loss": 3.0486,
+      "step": 535
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.16973251104354858,
+      "learning_rate": 2.247434435575827e-05,
+      "loss": 3.036,
+      "step": 540
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.16990025341510773,
+      "learning_rate": 2.2388825541619158e-05,
+      "loss": 3.014,
+      "step": 545
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.17086321115493774,
+      "learning_rate": 2.2303306727480047e-05,
+      "loss": 3.0311,
+      "step": 550
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.15396995842456818,
+      "learning_rate": 2.2217787913340936e-05,
+      "loss": 3.0324,
+      "step": 555
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.16492833197116852,
+      "learning_rate": 2.2132269099201826e-05,
+      "loss": 3.0421,
+      "step": 560
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.15703165531158447,
+      "learning_rate": 2.2046750285062715e-05,
+      "loss": 3.0424,
+      "step": 565
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.17821280658245087,
+      "learning_rate": 2.1961231470923604e-05,
+      "loss": 3.0318,
+      "step": 570
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.1624838411808014,
+      "learning_rate": 2.1875712656784493e-05,
+      "loss": 3.0359,
+      "step": 575
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.16541211307048798,
+      "learning_rate": 2.1790193842645385e-05,
+      "loss": 3.0248,
+      "step": 580
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.17508499324321747,
+      "learning_rate": 2.1704675028506275e-05,
+      "loss": 3.0131,
+      "step": 585
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.1695563644170761,
+      "learning_rate": 2.1619156214367164e-05,
+      "loss": 3.0272,
+      "step": 590
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.17492899298667908,
+      "learning_rate": 2.1533637400228053e-05,
+      "loss": 3.0173,
+      "step": 595
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.1568179726600647,
+      "learning_rate": 2.1448118586088942e-05,
+      "loss": 3.0046,
+      "step": 600
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.15557514131069183,
+      "learning_rate": 2.136259977194983e-05,
+      "loss": 3.0124,
+      "step": 605
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.16714046895503998,
+      "learning_rate": 2.1277080957810717e-05,
+      "loss": 3.0674,
+      "step": 610
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.16147108376026154,
+      "learning_rate": 2.1191562143671606e-05,
+      "loss": 3.0534,
+      "step": 615
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20646385848522186,
+      "learning_rate": 2.1106043329532495e-05,
+      "loss": 3.0084,
+      "step": 620
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.18532122671604156,
+      "learning_rate": 2.1020524515393384e-05,
+      "loss": 3.0369,
+      "step": 625
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.17400296032428741,
+      "learning_rate": 2.0935005701254276e-05,
+      "loss": 2.9915,
+      "step": 630
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.17704206705093384,
+      "learning_rate": 2.0849486887115166e-05,
+      "loss": 2.9672,
+      "step": 635
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.17726150155067444,
+      "learning_rate": 2.0763968072976055e-05,
+      "loss": 3.0192,
+      "step": 640
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.190839946269989,
+      "learning_rate": 2.0678449258836944e-05,
+      "loss": 2.9942,
+      "step": 645
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.1717444211244583,
+      "learning_rate": 2.0592930444697833e-05,
+      "loss": 2.9427,
+      "step": 650
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.1715097725391388,
+      "learning_rate": 2.0507411630558722e-05,
+      "loss": 3.0079,
+      "step": 655
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.17741073668003082,
+      "learning_rate": 2.042189281641961e-05,
+      "loss": 2.9878,
+      "step": 660
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.16402089595794678,
+      "learning_rate": 2.03363740022805e-05,
+      "loss": 2.9606,
+      "step": 665
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.17002873122692108,
+      "learning_rate": 2.025085518814139e-05,
+      "loss": 2.9774,
+      "step": 670
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.17261062562465668,
+      "learning_rate": 2.016533637400228e-05,
+      "loss": 2.9691,
+      "step": 675
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.16659089922904968,
+      "learning_rate": 2.007981755986317e-05,
+      "loss": 2.9814,
+      "step": 680
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.181407630443573,
+      "learning_rate": 1.999429874572406e-05,
+      "loss": 2.9819,
+      "step": 685
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.18762464821338654,
+      "learning_rate": 1.990877993158495e-05,
+      "loss": 2.9845,
+      "step": 690
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.17215465009212494,
+      "learning_rate": 1.9823261117445838e-05,
+      "loss": 2.9697,
+      "step": 695
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.17270050942897797,
+      "learning_rate": 1.9737742303306727e-05,
+      "loss": 2.9408,
+      "step": 700
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.20069903135299683,
+      "learning_rate": 1.9652223489167616e-05,
+      "loss": 2.9579,
+      "step": 705
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.17869950830936432,
+      "learning_rate": 1.9566704675028506e-05,
+      "loss": 2.9771,
+      "step": 710
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.17995081841945648,
+      "learning_rate": 1.9481185860889395e-05,
+      "loss": 2.9371,
+      "step": 715
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.1739899218082428,
+      "learning_rate": 1.9395667046750284e-05,
+      "loss": 2.9447,
+      "step": 720
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.17162194848060608,
+      "learning_rate": 1.9310148232611173e-05,
+      "loss": 2.972,
+      "step": 725
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.17730017006397247,
+      "learning_rate": 1.9224629418472065e-05,
+      "loss": 2.9458,
+      "step": 730
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.18780378997325897,
+      "learning_rate": 1.9139110604332954e-05,
+      "loss": 2.9893,
+      "step": 735
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.17871220409870148,
+      "learning_rate": 1.9053591790193844e-05,
+      "loss": 3.0007,
+      "step": 740
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.16773036122322083,
+      "learning_rate": 1.8968072976054733e-05,
+      "loss": 2.9678,
+      "step": 745
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.1990986317396164,
+      "learning_rate": 1.8882554161915622e-05,
+      "loss": 2.9688,
+      "step": 750
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.16836166381835938,
+      "learning_rate": 1.879703534777651e-05,
+      "loss": 2.9485,
+      "step": 755
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.17354542016983032,
+      "learning_rate": 1.87115165336374e-05,
+      "loss": 2.9727,
+      "step": 760
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.17101739346981049,
+      "learning_rate": 1.862599771949829e-05,
+      "loss": 2.9571,
+      "step": 765
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.1743125468492508,
+      "learning_rate": 1.8540478905359178e-05,
+      "loss": 2.9398,
+      "step": 770
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.17796063423156738,
+      "learning_rate": 1.8454960091220067e-05,
+      "loss": 2.9513,
+      "step": 775
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.16847650706768036,
+      "learning_rate": 1.836944127708096e-05,
+      "loss": 2.9892,
+      "step": 780
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.18287205696105957,
+      "learning_rate": 1.828392246294185e-05,
+      "loss": 2.9718,
+      "step": 785
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.1805015206336975,
+      "learning_rate": 1.8198403648802738e-05,
+      "loss": 2.9718,
+      "step": 790
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.18497325479984283,
+      "learning_rate": 1.8112884834663627e-05,
+      "loss": 2.962,
+      "step": 795
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.17345541715621948,
+      "learning_rate": 1.8027366020524516e-05,
+      "loss": 3.0038,
+      "step": 800
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.19061264395713806,
+      "learning_rate": 1.7941847206385405e-05,
+      "loss": 2.9932,
+      "step": 805
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.17812280356884003,
+      "learning_rate": 1.7856328392246294e-05,
+      "loss": 2.9394,
+      "step": 810
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.184650257229805,
+      "learning_rate": 1.7770809578107184e-05,
+      "loss": 2.9747,
+      "step": 815
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.18826904892921448,
+      "learning_rate": 1.7685290763968073e-05,
+      "loss": 2.9636,
+      "step": 820
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.17561104893684387,
+      "learning_rate": 1.7599771949828962e-05,
+      "loss": 2.9477,
+      "step": 825
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.17117257416248322,
+      "learning_rate": 1.7514253135689854e-05,
+      "loss": 2.9691,
+      "step": 830
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.17985746264457703,
+      "learning_rate": 1.7428734321550743e-05,
+      "loss": 2.9648,
+      "step": 835
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.18568694591522217,
+      "learning_rate": 1.7343215507411632e-05,
+      "loss": 2.9571,
+      "step": 840
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.18761347234249115,
+      "learning_rate": 1.725769669327252e-05,
+      "loss": 2.928,
+      "step": 845
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.1732112318277359,
+      "learning_rate": 1.717217787913341e-05,
+      "loss": 2.9474,
+      "step": 850
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.1749856323003769,
+      "learning_rate": 1.70866590649943e-05,
+      "loss": 2.9514,
+      "step": 855
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.1849680095911026,
+      "learning_rate": 1.700114025085519e-05,
+      "loss": 2.9327,
+      "step": 860
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.17794924974441528,
+      "learning_rate": 1.6915621436716078e-05,
+      "loss": 2.9644,
+      "step": 865
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.18736787140369415,
+      "learning_rate": 1.6830102622576967e-05,
+      "loss": 2.9353,
+      "step": 870
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.1925778090953827,
+      "learning_rate": 1.6744583808437856e-05,
+      "loss": 2.9446,
+      "step": 875
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.21187719702720642,
+      "learning_rate": 1.665906499429875e-05,
+      "loss": 2.9451,
+      "step": 880
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.17500068247318268,
+      "learning_rate": 1.6573546180159638e-05,
+      "loss": 2.9715,
+      "step": 885
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.18147456645965576,
+      "learning_rate": 1.6488027366020527e-05,
+      "loss": 2.9393,
+      "step": 890
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.17849037051200867,
+      "learning_rate": 1.6402508551881416e-05,
+      "loss": 2.9391,
+      "step": 895
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.1820787936449051,
+      "learning_rate": 1.6316989737742305e-05,
+      "loss": 2.9692,
+      "step": 900
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.18852904438972473,
+      "learning_rate": 1.6231470923603194e-05,
+      "loss": 2.9525,
+      "step": 905
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.17656317353248596,
+      "learning_rate": 1.6145952109464083e-05,
+      "loss": 2.9816,
+      "step": 910
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.17851251363754272,
+      "learning_rate": 1.6060433295324972e-05,
+      "loss": 2.9253,
+      "step": 915
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.18870405852794647,
+      "learning_rate": 1.597491448118586e-05,
+      "loss": 2.938,
+      "step": 920
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.1780102699995041,
+      "learning_rate": 1.588939566704675e-05,
+      "loss": 2.9252,
+      "step": 925
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 0.1899801790714264,
+      "learning_rate": 1.5803876852907643e-05,
+      "loss": 2.9285,
+      "step": 930
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 0.19754503667354584,
+      "learning_rate": 1.5718358038768532e-05,
+      "loss": 2.8888,
+      "step": 935
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.17948701977729797,
+      "learning_rate": 1.563283922462942e-05,
+      "loss": 2.8812,
+      "step": 940
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.18633098900318146,
+      "learning_rate": 1.5547320410490307e-05,
+      "loss": 2.9063,
+      "step": 945
+    },
+    {
+      "epoch": 3.07,
+      "grad_norm": 0.1805902123451233,
+      "learning_rate": 1.5461801596351196e-05,
+      "loss": 2.8998,
+      "step": 950
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 0.19559837877750397,
+      "learning_rate": 1.5376282782212085e-05,
+      "loss": 2.8877,
+      "step": 955
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.1801781952381134,
+      "learning_rate": 1.5290763968072974e-05,
+      "loss": 2.9265,
+      "step": 960
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.18338532745838165,
+      "learning_rate": 1.5205245153933865e-05,
+      "loss": 2.9025,
+      "step": 965
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 0.1971079260110855,
+      "learning_rate": 1.5119726339794754e-05,
+      "loss": 2.8788,
+      "step": 970
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.19317658245563507,
+      "learning_rate": 1.5034207525655643e-05,
+      "loss": 2.9048,
+      "step": 975
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 0.2028065323829651,
+      "learning_rate": 1.4948688711516534e-05,
+      "loss": 2.9021,
+      "step": 980
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 0.19364020228385925,
+      "learning_rate": 1.4863169897377423e-05,
+      "loss": 2.8742,
+      "step": 985
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.19389031827449799,
+      "learning_rate": 1.4777651083238314e-05,
+      "loss": 2.8769,
+      "step": 990
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 0.18738117814064026,
+      "learning_rate": 1.4692132269099203e-05,
+      "loss": 2.8896,
+      "step": 995
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 0.19338880479335785,
+      "learning_rate": 1.4606613454960092e-05,
+      "loss": 2.9101,
+      "step": 1000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.211032897233963,
+      "learning_rate": 1.4521094640820981e-05,
+      "loss": 2.8706,
+      "step": 1005
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 0.19349248707294464,
+      "learning_rate": 1.443557582668187e-05,
+      "loss": 2.8723,
+      "step": 1010
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 0.18660078942775726,
+      "learning_rate": 1.4350057012542761e-05,
+      "loss": 2.859,
+      "step": 1015
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.20884543657302856,
+      "learning_rate": 1.426453819840365e-05,
+      "loss": 2.9178,
+      "step": 1020
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 0.19792766869068146,
+      "learning_rate": 1.417901938426454e-05,
+      "loss": 2.8876,
+      "step": 1025
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 0.18087029457092285,
+      "learning_rate": 1.4093500570125427e-05,
+      "loss": 2.8858,
+      "step": 1030
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 0.20698681473731995,
+      "learning_rate": 1.4007981755986316e-05,
+      "loss": 2.8902,
+      "step": 1035
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.19386625289916992,
+      "learning_rate": 1.3922462941847207e-05,
+      "loss": 2.9174,
+      "step": 1040
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 0.19532999396324158,
+      "learning_rate": 1.3836944127708096e-05,
+      "loss": 2.8899,
+      "step": 1045
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 0.19565771520137787,
+      "learning_rate": 1.3751425313568985e-05,
+      "loss": 2.8784,
+      "step": 1050
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 0.193053737282753,
+      "learning_rate": 1.3665906499429874e-05,
+      "loss": 2.8943,
+      "step": 1055
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 0.1953536421060562,
+      "learning_rate": 1.3580387685290763e-05,
+      "loss": 2.8789,
+      "step": 1060
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.19460298120975494,
+      "learning_rate": 1.3494868871151654e-05,
+      "loss": 2.869,
+      "step": 1065
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 0.21567782759666443,
+      "learning_rate": 1.3409350057012543e-05,
+      "loss": 2.8993,
+      "step": 1070
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 0.20107676088809967,
+      "learning_rate": 1.3323831242873432e-05,
+      "loss": 2.8874,
+      "step": 1075
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 0.20253504812717438,
+      "learning_rate": 1.3238312428734321e-05,
+      "loss": 2.8715,
+      "step": 1080
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.203015998005867,
+      "learning_rate": 1.315279361459521e-05,
+      "loss": 2.8761,
+      "step": 1085
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.18808282911777496,
+      "learning_rate": 1.3067274800456101e-05,
+      "loss": 2.9125,
+      "step": 1090
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 0.20760120451450348,
+      "learning_rate": 1.298175598631699e-05,
+      "loss": 2.9097,
+      "step": 1095
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 0.2105015069246292,
+      "learning_rate": 1.289623717217788e-05,
+      "loss": 2.8776,
+      "step": 1100
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 0.19079047441482544,
+      "learning_rate": 1.2810718358038769e-05,
+      "loss": 2.8638,
+      "step": 1105
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 0.18677778542041779,
+      "learning_rate": 1.2725199543899658e-05,
+      "loss": 2.8611,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.19675646722316742,
+      "learning_rate": 1.2639680729760549e-05,
+      "loss": 2.8915,
+      "step": 1115
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 0.18953052163124084,
+      "learning_rate": 1.2554161915621438e-05,
+      "loss": 2.8717,
+      "step": 1120
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.19209244847297668,
+      "learning_rate": 1.2468643101482327e-05,
+      "loss": 2.8872,
+      "step": 1125
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.1874540001153946,
+      "learning_rate": 1.2383124287343216e-05,
+      "loss": 2.8752,
+      "step": 1130
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 0.19191692769527435,
+      "learning_rate": 1.2297605473204105e-05,
+      "loss": 2.874,
+      "step": 1135
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.19061529636383057,
+      "learning_rate": 1.2212086659064996e-05,
+      "loss": 2.8571,
+      "step": 1140
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.20083603262901306,
+      "learning_rate": 1.2126567844925885e-05,
+      "loss": 2.8681,
+      "step": 1145
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 0.20946206152439117,
+      "learning_rate": 1.2041049030786774e-05,
+      "loss": 2.8843,
+      "step": 1150
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 0.20480531454086304,
+      "learning_rate": 1.1955530216647663e-05,
+      "loss": 2.888,
+      "step": 1155
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.19144266843795776,
+      "learning_rate": 1.1870011402508552e-05,
+      "loss": 2.8637,
+      "step": 1160
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.20213666558265686,
+      "learning_rate": 1.1784492588369441e-05,
+      "loss": 2.8995,
+      "step": 1165
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 0.18854743242263794,
+      "learning_rate": 1.1698973774230332e-05,
+      "loss": 2.8914,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.19319185614585876,
+      "learning_rate": 1.1613454960091221e-05,
+      "loss": 2.8919,
+      "step": 1175
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 0.20369315147399902,
+      "learning_rate": 1.152793614595211e-05,
+      "loss": 2.8563,
+      "step": 1180
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 0.19648641347885132,
+      "learning_rate": 1.1442417331813e-05,
+      "loss": 2.8929,
+      "step": 1185
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.20386841893196106,
+      "learning_rate": 1.1356898517673888e-05,
+      "loss": 2.8548,
+      "step": 1190
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 0.19758112728595734,
+      "learning_rate": 1.127137970353478e-05,
+      "loss": 2.8811,
+      "step": 1195
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.21303939819335938,
+      "learning_rate": 1.1185860889395667e-05,
+      "loss": 2.879,
+      "step": 1200
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.1993599683046341,
+      "learning_rate": 1.1100342075256556e-05,
+      "loss": 2.8718,
+      "step": 1205
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 0.20202603936195374,
+      "learning_rate": 1.1014823261117445e-05,
+      "loss": 2.8337,
+      "step": 1210
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.20566709339618683,
+      "learning_rate": 1.0929304446978336e-05,
+      "loss": 2.8658,
+      "step": 1215
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 0.18417729437351227,
+      "learning_rate": 1.0843785632839225e-05,
+      "loss": 2.853,
+      "step": 1220
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.19506323337554932,
+      "learning_rate": 1.0758266818700114e-05,
+      "loss": 2.84,
+      "step": 1225
+    },
+    {
+      "epoch": 3.97,
+      "grad_norm": 0.20047935843467712,
+      "learning_rate": 1.0672748004561003e-05,
+      "loss": 2.8488,
+      "step": 1230
+    },
+    {
+      "epoch": 3.99,
+      "grad_norm": 0.187282994389534,
+      "learning_rate": 1.0587229190421892e-05,
+      "loss": 2.84,
+      "step": 1235
+    },
+    {
+      "epoch": 4.01,
+      "grad_norm": 0.19961225986480713,
+      "learning_rate": 1.0501710376282783e-05,
+      "loss": 2.873,
+      "step": 1240
+    },
+    {
+      "epoch": 4.02,
+      "grad_norm": 0.20117315649986267,
+      "learning_rate": 1.0416191562143672e-05,
+      "loss": 2.8046,
+      "step": 1245
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 0.19239380955696106,
+      "learning_rate": 1.0330672748004561e-05,
+      "loss": 2.8576,
+      "step": 1250
+    },
+    {
+      "epoch": 4.06,
+      "grad_norm": 0.19857007265090942,
+      "learning_rate": 1.024515393386545e-05,
+      "loss": 2.8165,
+      "step": 1255
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 0.2090427130460739,
+      "learning_rate": 1.015963511972634e-05,
+      "loss": 2.8076,
+      "step": 1260
+    },
+    {
+      "epoch": 4.09,
+      "grad_norm": 0.1895773708820343,
+      "learning_rate": 1.0074116305587228e-05,
+      "loss": 2.792,
+      "step": 1265
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 0.20731306076049805,
+      "learning_rate": 9.98859749144812e-06,
+      "loss": 2.8121,
+      "step": 1270
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.19480618834495544,
+      "learning_rate": 9.903078677309008e-06,
+      "loss": 2.8261,
+      "step": 1275
+    },
+    {
+      "epoch": 4.14,
+      "grad_norm": 0.1925288587808609,
+      "learning_rate": 9.817559863169897e-06,
+      "loss": 2.8131,
+      "step": 1280
+    },
+    {
+      "epoch": 4.15,
+      "grad_norm": 0.21479365229606628,
+      "learning_rate": 9.732041049030787e-06,
+      "loss": 2.8021,
+      "step": 1285
+    },
+    {
+      "epoch": 4.17,
+      "grad_norm": 0.19130577147006989,
+      "learning_rate": 9.646522234891676e-06,
+      "loss": 2.8115,
+      "step": 1290
+    },
+    {
+      "epoch": 4.19,
+      "grad_norm": 0.22513242065906525,
+      "learning_rate": 9.561003420752566e-06,
+      "loss": 2.8134,
+      "step": 1295
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.204105406999588,
+      "learning_rate": 9.475484606613456e-06,
+      "loss": 2.8208,
+      "step": 1300
+    },
+    {
+      "epoch": 4.22,
+      "grad_norm": 0.2156701236963272,
+      "learning_rate": 9.389965792474345e-06,
+      "loss": 2.8246,
+      "step": 1305
+    },
+    {
+      "epoch": 4.23,
+      "grad_norm": 0.2150842398405075,
+      "learning_rate": 9.304446978335234e-06,
+      "loss": 2.8054,
+      "step": 1310
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.19922739267349243,
+      "learning_rate": 9.218928164196123e-06,
+      "loss": 2.7994,
+      "step": 1315
+    },
+    {
+      "epoch": 4.27,
+      "grad_norm": 0.20415738224983215,
+      "learning_rate": 9.133409350057014e-06,
+      "loss": 2.7762,
+      "step": 1320
+    },
+    {
+      "epoch": 4.28,
+      "grad_norm": 0.21822912991046906,
+      "learning_rate": 9.047890535917903e-06,
+      "loss": 2.8363,
+      "step": 1325
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.1866757571697235,
+      "learning_rate": 8.962371721778792e-06,
+      "loss": 2.8213,
+      "step": 1330
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 0.18803808093070984,
+      "learning_rate": 8.876852907639681e-06,
+      "loss": 2.8232,
+      "step": 1335
+    },
+    {
+      "epoch": 4.33,
+      "grad_norm": 0.2101515531539917,
+      "learning_rate": 8.79133409350057e-06,
+      "loss": 2.8275,
+      "step": 1340
+    },
+    {
+      "epoch": 4.35,
+      "grad_norm": 0.2047651708126068,
+      "learning_rate": 8.705815279361461e-06,
+      "loss": 2.8112,
+      "step": 1345
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 0.1994614452123642,
+      "learning_rate": 8.62029646522235e-06,
+      "loss": 2.8344,
+      "step": 1350
+    },
+    {
+      "epoch": 4.38,
+      "grad_norm": 0.21065644919872284,
+      "learning_rate": 8.534777651083239e-06,
+      "loss": 2.811,
+      "step": 1355
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.21383103728294373,
+      "learning_rate": 8.449258836944128e-06,
+      "loss": 2.8073,
+      "step": 1360
+    },
+    {
+      "epoch": 4.41,
+      "grad_norm": 0.20263946056365967,
+      "learning_rate": 8.363740022805016e-06,
+      "loss": 2.8115,
+      "step": 1365
+    },
+    {
+      "epoch": 4.43,
+      "grad_norm": 0.19944559037685394,
+      "learning_rate": 8.278221208665906e-06,
+      "loss": 2.8155,
+      "step": 1370
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 0.18889665603637695,
+      "learning_rate": 8.192702394526796e-06,
+      "loss": 2.8307,
+      "step": 1375
+    },
+    {
+      "epoch": 4.46,
+      "grad_norm": 0.20692084729671478,
+      "learning_rate": 8.107183580387685e-06,
+      "loss": 2.8126,
+      "step": 1380
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.21253955364227295,
+      "learning_rate": 8.021664766248574e-06,
+      "loss": 2.8035,
+      "step": 1385
+    },
+    {
+      "epoch": 4.49,
+      "grad_norm": 0.20105835795402527,
+      "learning_rate": 7.936145952109463e-06,
+      "loss": 2.8426,
+      "step": 1390
+    },
+    {
+      "epoch": 4.51,
+      "grad_norm": 0.21002836525440216,
+      "learning_rate": 7.850627137970354e-06,
+      "loss": 2.8018,
+      "step": 1395
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 0.22299815714359283,
+      "learning_rate": 7.765108323831243e-06,
+      "loss": 2.8413,
+      "step": 1400
+    },
+    {
+      "epoch": 4.54,
+      "grad_norm": 0.20295199751853943,
+      "learning_rate": 7.679589509692132e-06,
+      "loss": 2.8411,
+      "step": 1405
+    },
+    {
+      "epoch": 4.56,
+      "grad_norm": 0.20713861286640167,
+      "learning_rate": 7.594070695553022e-06,
+      "loss": 2.8258,
+      "step": 1410
+    },
+    {
+      "epoch": 4.57,
+      "grad_norm": 0.21353642642498016,
+      "learning_rate": 7.508551881413911e-06,
+      "loss": 2.8142,
+      "step": 1415
+    },
+    {
+      "epoch": 4.59,
+      "grad_norm": 0.2093668282032013,
+      "learning_rate": 7.4230330672748e-06,
+      "loss": 2.8135,
+      "step": 1420
+    },
+    {
+      "epoch": 4.61,
+      "grad_norm": 0.2017381191253662,
+      "learning_rate": 7.33751425313569e-06,
+      "loss": 2.8181,
+      "step": 1425
+    },
+    {
+      "epoch": 4.62,
+      "grad_norm": 0.2110336720943451,
+      "learning_rate": 7.251995438996579e-06,
+      "loss": 2.8025,
+      "step": 1430
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.20439700782299042,
+      "learning_rate": 7.166476624857469e-06,
+      "loss": 2.8214,
+      "step": 1435
+    },
+    {
+      "epoch": 4.65,
+      "grad_norm": 0.22022387385368347,
+      "learning_rate": 7.080957810718358e-06,
+      "loss": 2.8007,
+      "step": 1440
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 0.19444230198860168,
+      "learning_rate": 6.995438996579247e-06,
+      "loss": 2.8183,
+      "step": 1445
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.20547039806842804,
+      "learning_rate": 6.909920182440137e-06,
+      "loss": 2.8066,
+      "step": 1450
+    },
+    {
+      "epoch": 4.7,
+      "grad_norm": 0.20443764328956604,
+      "learning_rate": 6.824401368301026e-06,
+      "loss": 2.8312,
+      "step": 1455
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.20165589451789856,
+      "learning_rate": 6.738882554161916e-06,
+      "loss": 2.8389,
+      "step": 1460
+    },
+    {
+      "epoch": 4.73,
+      "grad_norm": 0.222417414188385,
+      "learning_rate": 6.653363740022805e-06,
+      "loss": 2.8186,
+      "step": 1465
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.21495650708675385,
+      "learning_rate": 6.5678449258836945e-06,
+      "loss": 2.8433,
+      "step": 1470
+    },
+    {
+      "epoch": 4.77,
+      "grad_norm": 0.2121262550354004,
+      "learning_rate": 6.4823261117445844e-06,
+      "loss": 2.8128,
+      "step": 1475
+    },
+    {
+      "epoch": 4.78,
+      "grad_norm": 0.2040678709745407,
+      "learning_rate": 6.3968072976054735e-06,
+      "loss": 2.8367,
+      "step": 1480
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.19694024324417114,
+      "learning_rate": 6.3112884834663635e-06,
+      "loss": 2.782,
+      "step": 1485
+    },
+    {
+      "epoch": 4.82,
+      "grad_norm": 0.20558282732963562,
+      "learning_rate": 6.225769669327253e-06,
+      "loss": 2.805,
+      "step": 1490
+    },
+    {
+      "epoch": 4.83,
+      "grad_norm": 0.2115090787410736,
+      "learning_rate": 6.140250855188141e-06,
+      "loss": 2.8085,
+      "step": 1495
+    },
+    {
+      "epoch": 4.85,
+      "grad_norm": 0.2121584117412567,
+      "learning_rate": 6.054732041049031e-06,
+      "loss": 2.7917,
+      "step": 1500
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 0.200391486287117,
+      "learning_rate": 5.96921322690992e-06,
+      "loss": 2.7941,
+      "step": 1505
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.21317771077156067,
+      "learning_rate": 5.88369441277081e-06,
+      "loss": 2.7956,
+      "step": 1510
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.21627019345760345,
+      "learning_rate": 5.798175598631699e-06,
+      "loss": 2.8107,
+      "step": 1515
+    },
+    {
+      "epoch": 4.91,
+      "grad_norm": 0.2093602418899536,
+      "learning_rate": 5.712656784492588e-06,
+      "loss": 2.8022,
+      "step": 1520
+    },
+    {
+      "epoch": 4.93,
+      "grad_norm": 0.1991538405418396,
+      "learning_rate": 5.627137970353478e-06,
+      "loss": 2.8011,
+      "step": 1525
+    },
+    {
+      "epoch": 4.94,
+      "grad_norm": 0.20621471107006073,
+      "learning_rate": 5.541619156214367e-06,
+      "loss": 2.7987,
+      "step": 1530
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.21053887903690338,
+      "learning_rate": 5.456100342075257e-06,
+      "loss": 2.8148,
+      "step": 1535
+    },
+    {
+      "epoch": 4.98,
+      "grad_norm": 0.19427061080932617,
+      "learning_rate": 5.370581527936146e-06,
+      "loss": 2.8302,
+      "step": 1540
+    },
+    {
+      "epoch": 4.99,
+      "grad_norm": 0.20684009790420532,
+      "learning_rate": 5.285062713797035e-06,
+      "loss": 2.8071,
+      "step": 1545
+    },
+    {
+      "epoch": 5.01,
+      "grad_norm": 0.2079547643661499,
+      "learning_rate": 5.199543899657925e-06,
+      "loss": 2.7831,
+      "step": 1550
+    },
+    {
+      "epoch": 5.03,
+      "grad_norm": 0.2271408885717392,
+      "learning_rate": 5.114025085518814e-06,
+      "loss": 2.7772,
+      "step": 1555
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 0.21122708916664124,
+      "learning_rate": 5.028506271379704e-06,
+      "loss": 2.7941,
+      "step": 1560
+    },
+    {
+      "epoch": 5.06,
+      "grad_norm": 0.20626038312911987,
+      "learning_rate": 4.9429874572405934e-06,
+      "loss": 2.7601,
+      "step": 1565
+    },
+    {
+      "epoch": 5.07,
+      "grad_norm": 0.21984724700450897,
+      "learning_rate": 4.8574686431014825e-06,
+      "loss": 2.7797,
+      "step": 1570
+    },
+    {
+      "epoch": 5.09,
+      "grad_norm": 0.24193266034126282,
+      "learning_rate": 4.7719498289623725e-06,
+      "loss": 2.7841,
+      "step": 1575
+    },
+    {
+      "epoch": 5.11,
+      "grad_norm": 0.2213587611913681,
+      "learning_rate": 4.686431014823261e-06,
+      "loss": 2.7867,
+      "step": 1580
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.20624710619449615,
+      "learning_rate": 4.600912200684151e-06,
+      "loss": 2.7814,
+      "step": 1585
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 0.21868358552455902,
+      "learning_rate": 4.51539338654504e-06,
+      "loss": 2.8011,
+      "step": 1590
+    },
+    {
+      "epoch": 5.15,
+      "grad_norm": 0.22464773058891296,
+      "learning_rate": 4.429874572405929e-06,
+      "loss": 2.7808,
+      "step": 1595
+    },
+    {
+      "epoch": 5.17,
+      "grad_norm": 0.21239249408245087,
+      "learning_rate": 4.344355758266819e-06,
+      "loss": 2.7682,
+      "step": 1600
+    },
+    {
+      "epoch": 5.19,
+      "grad_norm": 0.2032070755958557,
+      "learning_rate": 3e-05,
+      "loss": 2.7738,
+      "step": 1605
+    },
+    {
+      "epoch": 5.21,
+      "grad_norm": 0.24147231876850128,
+      "learning_rate": 3e-05,
+      "loss": 2.8026,
+      "step": 1610
+    },
+    {
+      "epoch": 5.23,
+      "grad_norm": 0.21959525346755981,
+      "learning_rate": 3e-05,
+      "loss": 2.7317,
+      "step": 1615
+    },
+    {
+      "epoch": 5.24,
+      "grad_norm": 0.22994889318943024,
+      "learning_rate": 3e-05,
+      "loss": 2.7574,
+      "step": 1620
+    },
+    {
+      "epoch": 5.26,
+      "grad_norm": 0.22466912865638733,
+      "learning_rate": 3e-05,
+      "loss": 2.7974,
+      "step": 1625
+    },
+    {
+      "epoch": 5.27,
+      "grad_norm": 0.23403416574001312,
+      "learning_rate": 3e-05,
+      "loss": 2.771,
+      "step": 1630
+    },
+    {
+      "epoch": 5.29,
+      "grad_norm": 0.22054152190685272,
+      "learning_rate": 3e-05,
+      "loss": 2.792,
+      "step": 1635
+    },
+    {
+      "epoch": 5.31,
+      "grad_norm": 0.2172236293554306,
+      "learning_rate": 3e-05,
+      "loss": 2.7555,
+      "step": 1640
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 0.21500498056411743,
+      "learning_rate": 3e-05,
+      "loss": 2.8126,
+      "step": 1645
+    },
+    {
+      "epoch": 5.34,
+      "grad_norm": 0.2480950951576233,
+      "learning_rate": 3e-05,
+      "loss": 2.7834,
+      "step": 1650
+    },
+    {
+      "epoch": 5.36,
+      "grad_norm": 0.22709690034389496,
+      "learning_rate": 3e-05,
+      "loss": 2.7954,
+      "step": 1655
+    },
+    {
+      "epoch": 5.37,
+      "grad_norm": 0.22354279458522797,
+      "learning_rate": 3e-05,
+      "loss": 2.7705,
+      "step": 1660
+    },
+    {
+      "epoch": 5.39,
+      "grad_norm": 0.26233839988708496,
+      "learning_rate": 3e-05,
+      "loss": 2.7603,
+      "step": 1665
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.23743155598640442,
+      "learning_rate": 3e-05,
+      "loss": 2.7997,
+      "step": 1670
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.23243878781795502,
+      "learning_rate": 3e-05,
+      "loss": 2.7624,
+      "step": 1675
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.2384800910949707,
+      "learning_rate": 3e-05,
+      "loss": 2.7781,
+      "step": 1680
+    },
+    {
+      "epoch": 5.45,
+      "grad_norm": 0.2814362347126007,
+      "learning_rate": 3e-05,
+      "loss": 2.7528,
+      "step": 1685
+    },
+    {
+      "epoch": 5.47,
+      "grad_norm": 0.2459874302148819,
+      "learning_rate": 3e-05,
+      "loss": 2.8155,
+      "step": 1690
+    },
+    {
+      "epoch": 5.48,
+      "grad_norm": 0.25781503319740295,
+      "learning_rate": 3e-05,
+      "loss": 2.7466,
+      "step": 1695
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.24334032833576202,
+      "learning_rate": 3e-05,
+      "loss": 2.8122,
+      "step": 1700
+    },
+    {
+      "epoch": 5.52,
+      "grad_norm": 0.24697226285934448,
+      "learning_rate": 3e-05,
+      "loss": 2.7956,
+      "step": 1705
+    },
+    {
+      "epoch": 5.53,
+      "grad_norm": 0.24803857505321503,
+      "learning_rate": 3e-05,
+      "loss": 2.7465,
+      "step": 1710
+    },
+    {
+      "epoch": 5.55,
+      "grad_norm": 0.24284283816814423,
+      "learning_rate": 3e-05,
+      "loss": 2.7559,
+      "step": 1715
+    },
+    {
+      "epoch": 5.57,
+      "grad_norm": 0.23661333322525024,
+      "learning_rate": 3e-05,
+      "loss": 2.7692,
+      "step": 1720
+    },
+    {
+      "epoch": 5.58,
+      "grad_norm": 0.2449016571044922,
+      "learning_rate": 3e-05,
+      "loss": 2.7318,
+      "step": 1725
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.2179490625858307,
+      "learning_rate": 3e-05,
+      "loss": 2.7636,
+      "step": 1730
+    },
+    {
+      "epoch": 5.61,
+      "grad_norm": 0.22239655256271362,
+      "learning_rate": 3e-05,
+      "loss": 2.7878,
+      "step": 1735
+    },
+    {
+      "epoch": 5.63,
+      "grad_norm": 0.23438027501106262,
+      "learning_rate": 3e-05,
+      "loss": 2.7741,
+      "step": 1740
+    },
+    {
+      "epoch": 5.65,
+      "grad_norm": 0.24237991869449615,
+      "learning_rate": 3e-05,
+      "loss": 2.7865,
+      "step": 1745
+    },
+    {
+      "epoch": 5.66,
+      "grad_norm": 0.2225206047296524,
+      "learning_rate": 3e-05,
+      "loss": 2.7905,
+      "step": 1750
+    },
+    {
+      "epoch": 5.68,
+      "grad_norm": 0.2413685917854309,
+      "learning_rate": 3e-05,
+      "loss": 2.745,
+      "step": 1755
+    },
+    {
+      "epoch": 5.69,
+      "grad_norm": 0.23114730417728424,
+      "learning_rate": 3e-05,
+      "loss": 2.7465,
+      "step": 1760
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": 0.2584913969039917,
+      "learning_rate": 3e-05,
+      "loss": 2.7599,
+      "step": 1765
+    },
+    {
+      "epoch": 5.73,
+      "grad_norm": 0.2540834844112396,
+      "learning_rate": 3e-05,
+      "loss": 2.7412,
+      "step": 1770
+    },
+    {
+      "epoch": 5.74,
+      "grad_norm": 0.28105732798576355,
+      "learning_rate": 3e-05,
+      "loss": 2.7226,
+      "step": 1775
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.24792756140232086,
+      "learning_rate": 3e-05,
+      "loss": 2.7304,
+      "step": 1780
+    },
+    {
+      "epoch": 5.78,
+      "grad_norm": 0.2415696680545807,
+      "learning_rate": 3e-05,
+      "loss": 2.7635,
+      "step": 1785
+    },
+    {
+      "epoch": 5.79,
+      "grad_norm": 0.264769971370697,
+      "learning_rate": 3e-05,
+      "loss": 2.7464,
+      "step": 1790
+    },
+    {
+      "epoch": 5.81,
+      "grad_norm": 0.23595955967903137,
+      "learning_rate": 5e-05,
+      "loss": 2.745,
+      "step": 1795
+    },
+    {
+      "epoch": 5.82,
+      "grad_norm": 0.24608966708183289,
+      "learning_rate": 5e-05,
+      "loss": 2.7633,
+      "step": 1800
+    },
+    {
+      "epoch": 5.84,
+      "grad_norm": 0.2487153708934784,
+      "learning_rate": 3e-05,
+      "loss": 2.7586,
+      "step": 1805
+    },
+    {
+      "epoch": 5.86,
+      "grad_norm": 0.24857081472873688,
+      "learning_rate": 3e-05,
+      "loss": 2.7464,
+      "step": 1810
+    },
+    {
+      "epoch": 5.87,
+      "grad_norm": 0.2426629513502121,
+      "learning_rate": 3e-05,
+      "loss": 2.7385,
+      "step": 1815
+    },
+    {
+      "epoch": 5.89,
+      "grad_norm": 0.23641450703144073,
+      "learning_rate": 3e-05,
+      "loss": 2.7677,
+      "step": 1820
+    },
+    {
+      "epoch": 5.9,
+      "grad_norm": 0.23726724088191986,
+      "learning_rate": 3e-05,
+      "loss": 2.7348,
+      "step": 1825
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.26856401562690735,
+      "learning_rate": 3e-05,
+      "loss": 2.7428,
+      "step": 1830
+    },
+    {
+      "epoch": 5.93,
+      "step": 1832,
+      "total_flos": 2.9122521101461094e+19,
+      "train_loss": 0.048051854148181763,
+      "train_runtime": 5063.5443,
+      "train_samples_per_second": 54.75,
+      "train_steps_per_second": 0.427
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2163,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 200,
+  "total_flos": 2.9122521101461094e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74447e73949de815ee16e8b0446c4452b54de282d9d694bf33539c2386a0bda
+size 5112