Training in progress, step 338, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-338/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-338/chat_template.jinja

@@ -0,0 +1,4 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
+' + message['content'] | trim + '<end_of_turn>
+' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
+'}}{% endif %}

checkpoint-338/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 2048,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 256000
+}

checkpoint-338/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.2"
+}

checkpoint-338/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ba566c65354efcf1eab09af59fbb80d4a05968117a9be332fcf407ca4da59e
+size 4945242264

checkpoint-338/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5b5aed24fc9109803d6c404bf83f0cdb9148412ad63d1a58dea473dce2c7c3
+size 67121608

checkpoint-338/model.safetensors.index.json

@@ -0,0 +1,172 @@
+{
+  "metadata": {
+    "total_parameters": 2506172416,
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-338/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625b89b528343136b1c7c9a27154b59e2e5da03f55aa4ce4551c6ed832a636bb
+size 8220638802

checkpoint-338/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e271db059ee705520b0102bdbb522c5c372acf668aa9b12f38477021ca2f6b79
+size 14180

checkpoint-338/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1645fc6c6769deebd7949e8908f6796c92fdfac4038f3346c9b63182736efd
+size 1064

checkpoint-338/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-338/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041

checkpoint-338/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-338/tokenizer_config.json

@@ -0,0 +1,1758 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-338/trainer_state.json

@@ -0,0 +1,2400 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 338,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002962962962962963,
+      "grad_norm": 82.5,
+      "learning_rate": 0.0,
+      "loss": 5.4851,
+      "step": 1
+    },
+    {
+      "epoch": 0.005925925925925926,
+      "grad_norm": 81.5,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 5.5219,
+      "step": 2
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 83.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 5.7155,
+      "step": 3
+    },
+    {
+      "epoch": 0.011851851851851851,
+      "grad_norm": 74.0,
+      "learning_rate": 3e-06,
+      "loss": 5.5065,
+      "step": 4
+    },
+    {
+      "epoch": 0.014814814814814815,
+      "grad_norm": 60.5,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 4.8696,
+      "step": 5
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 48.25,
+      "learning_rate": 5e-06,
+      "loss": 4.3835,
+      "step": 6
+    },
+    {
+      "epoch": 0.02074074074074074,
+      "grad_norm": 40.5,
+      "learning_rate": 6e-06,
+      "loss": 4.1231,
+      "step": 7
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 50.5,
+      "learning_rate": 7e-06,
+      "loss": 3.6886,
+      "step": 8
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 34.5,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.3401,
+      "step": 9
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 27.125,
+      "learning_rate": 9e-06,
+      "loss": 3.043,
+      "step": 10
+    },
+    {
+      "epoch": 0.03259259259259259,
+      "grad_norm": 21.5,
+      "learning_rate": 1e-05,
+      "loss": 2.7408,
+      "step": 11
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 19.875,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.5235,
+      "step": 12
+    },
+    {
+      "epoch": 0.03851851851851852,
+      "grad_norm": 19.0,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4532,
+      "step": 13
+    },
+    {
+      "epoch": 0.04148148148148148,
+      "grad_norm": 19.625,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.3238,
+      "step": 14
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 20.125,
+      "learning_rate": 1.4e-05,
+      "loss": 2.2851,
+      "step": 15
+    },
+    {
+      "epoch": 0.047407407407407405,
+      "grad_norm": 17.5,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.2676,
+      "step": 16
+    },
+    {
+      "epoch": 0.05037037037037037,
+      "grad_norm": 16.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.1502,
+      "step": 17
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 14.4375,
+      "learning_rate": 1.7e-05,
+      "loss": 2.1293,
+      "step": 18
+    },
+    {
+      "epoch": 0.056296296296296296,
+      "grad_norm": 15.5625,
+      "learning_rate": 1.8e-05,
+      "loss": 2.0649,
+      "step": 19
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 19.0,
+      "learning_rate": 1.9e-05,
+      "loss": 1.961,
+      "step": 20
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 14.375,
+      "learning_rate": 2e-05,
+      "loss": 1.9368,
+      "step": 21
+    },
+    {
+      "epoch": 0.06518518518518518,
+      "grad_norm": 15.75,
+      "learning_rate": 1.999951200881446e-05,
+      "loss": 1.9511,
+      "step": 22
+    },
+    {
+      "epoch": 0.06814814814814815,
+      "grad_norm": 13.5625,
+      "learning_rate": 1.999804808288491e-05,
+      "loss": 1.8874,
+      "step": 23
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 13.4375,
+      "learning_rate": 1.9995608365087945e-05,
+      "loss": 1.7678,
+      "step": 24
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 14.25,
+      "learning_rate": 1.999219309353572e-05,
+      "loss": 1.8061,
+      "step": 25
+    },
+    {
+      "epoch": 0.07703703703703704,
+      "grad_norm": 13.9375,
+      "learning_rate": 1.9987802601552717e-05,
+      "loss": 1.778,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 11.3125,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 1.5772,
+      "step": 27
+    },
+    {
+      "epoch": 0.08296296296296296,
+      "grad_norm": 13.3125,
+      "learning_rate": 1.9976097765449463e-05,
+      "loss": 1.7557,
+      "step": 28
+    },
+    {
+      "epoch": 0.08592592592592592,
+      "grad_norm": 12.9375,
+      "learning_rate": 1.9968784563700586e-05,
+      "loss": 1.6816,
+      "step": 29
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 12.8125,
+      "learning_rate": 1.996049842615217e-05,
+      "loss": 1.742,
+      "step": 30
+    },
+    {
+      "epoch": 0.09185185185185185,
+      "grad_norm": 12.125,
+      "learning_rate": 1.9951240161516643e-05,
+      "loss": 1.7055,
+      "step": 31
+    },
+    {
+      "epoch": 0.09481481481481481,
+      "grad_norm": 11.5625,
+      "learning_rate": 1.9941010673384307e-05,
+      "loss": 1.6907,
+      "step": 32
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 11.4375,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 1.7213,
+      "step": 33
+    },
+    {
+      "epoch": 0.10074074074074074,
+      "grad_norm": 12.125,
+      "learning_rate": 1.9917642114841505e-05,
+      "loss": 1.8787,
+      "step": 34
+    },
+    {
+      "epoch": 0.1037037037037037,
+      "grad_norm": 11.125,
+      "learning_rate": 1.990450532516116e-05,
+      "loss": 1.6781,
+      "step": 35
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 12.8125,
+      "learning_rate": 1.9890401873221642e-05,
+      "loss": 1.5917,
+      "step": 36
+    },
+    {
+      "epoch": 0.10962962962962963,
+      "grad_norm": 12.0625,
+      "learning_rate": 1.9875333135495e-05,
+      "loss": 1.7399,
+      "step": 37
+    },
+    {
+      "epoch": 0.11259259259259259,
+      "grad_norm": 11.6875,
+      "learning_rate": 1.985930058266348e-05,
+      "loss": 1.8376,
+      "step": 38
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 10.9375,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 1.7302,
+      "step": 39
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 10.125,
+      "learning_rate": 1.9824350384595295e-05,
+      "loss": 1.6194,
+      "step": 40
+    },
+    {
+      "epoch": 0.12148148148148148,
+      "grad_norm": 10.375,
+      "learning_rate": 1.9805436150436352e-05,
+      "loss": 1.6648,
+      "step": 41
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.9785564922995042e-05,
+      "loss": 1.7417,
+      "step": 42
+    },
+    {
+      "epoch": 0.1274074074074074,
+      "grad_norm": 11.625,
+      "learning_rate": 1.9764738641668137e-05,
+      "loss": 1.6403,
+      "step": 43
+    },
+    {
+      "epoch": 0.13037037037037036,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9742959339063977e-05,
+      "loss": 1.6204,
+      "step": 44
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 11.75,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 1.7575,
+      "step": 45
+    },
+    {
+      "epoch": 0.1362962962962963,
+      "grad_norm": 12.625,
+      "learning_rate": 1.9696550265315805e-05,
+      "loss": 1.594,
+      "step": 46
+    },
+    {
+      "epoch": 0.13925925925925925,
+      "grad_norm": 11.3125,
+      "learning_rate": 1.9671925023615572e-05,
+      "loss": 1.6259,
+      "step": 47
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 11.9375,
+      "learning_rate": 1.964635581908359e-05,
+      "loss": 1.7574,
+      "step": 48
+    },
+    {
+      "epoch": 0.1451851851851852,
+      "grad_norm": 10.75,
+      "learning_rate": 1.961984514722914e-05,
+      "loss": 1.7021,
+      "step": 49
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9592395595447064e-05,
+      "loss": 1.5892,
+      "step": 50
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 1.6846,
+      "step": 51
+    },
+    {
+      "epoch": 0.15407407407407409,
+      "grad_norm": 10.375,
+      "learning_rate": 1.9534690659583045e-05,
+      "loss": 1.6761,
+      "step": 52
+    },
+    {
+      "epoch": 0.15703703703703703,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9504440907401113e-05,
+      "loss": 1.4986,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.4375,
+      "learning_rate": 1.9473263538541916e-05,
+      "loss": 1.6183,
+      "step": 54
+    },
+    {
+      "epoch": 0.16296296296296298,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.944116159586169e-05,
+      "loss": 1.7405,
+      "step": 55
+    },
+    {
+      "epoch": 0.16592592592592592,
+      "grad_norm": 11.75,
+      "learning_rate": 1.9408138212453456e-05,
+      "loss": 1.608,
+      "step": 56
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 1.6267,
+      "step": 57
+    },
+    {
+      "epoch": 0.17185185185185184,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.933934010516539e-05,
+      "loss": 1.7335,
+      "step": 58
+    },
+    {
+      "epoch": 0.1748148148148148,
+      "grad_norm": 11.125,
+      "learning_rate": 1.9303572095859545e-05,
+      "loss": 1.7112,
+      "step": 59
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 11.75,
+      "learning_rate": 1.9266896074318335e-05,
+      "loss": 1.8106,
+      "step": 60
+    },
+    {
+      "epoch": 0.18074074074074073,
+      "grad_norm": 10.875,
+      "learning_rate": 1.9229315620056805e-05,
+      "loss": 1.5596,
+      "step": 61
+    },
+    {
+      "epoch": 0.1837037037037037,
+      "grad_norm": 14.0625,
+      "learning_rate": 1.9190834400861035e-05,
+      "loss": 1.5379,
+      "step": 62
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 10.875,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 1.5921,
+      "step": 63
+    },
+    {
+      "epoch": 0.18962962962962962,
+      "grad_norm": 10.75,
+      "learning_rate": 1.9111184778009934e-05,
+      "loss": 1.6252,
+      "step": 64
+    },
+    {
+      "epoch": 0.1925925925925926,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.9070024148017375e-05,
+      "loss": 1.7589,
+      "step": 65
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.9027978299657436e-05,
+      "loss": 1.4877,
+      "step": 66
+    },
+    {
+      "epoch": 0.1985185185185185,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.89850513365308e-05,
+      "loss": 1.6578,
+      "step": 67
+    },
+    {
+      "epoch": 0.20148148148148148,
+      "grad_norm": 11.5,
+      "learning_rate": 1.8941247448233386e-05,
+      "loss": 1.5563,
+      "step": 68
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 12.25,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 1.6964,
+      "step": 69
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 10.5625,
+      "learning_rate": 1.885102608202444e-05,
+      "loss": 1.5913,
+      "step": 70
+    },
+    {
+      "epoch": 0.21037037037037037,
+      "grad_norm": 10.625,
+      "learning_rate": 1.88046174095592e-05,
+      "loss": 1.5556,
+      "step": 71
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.875734942195637e-05,
+      "loss": 1.5116,
+      "step": 72
+    },
+    {
+      "epoch": 0.2162962962962963,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.8709226732488216e-05,
+      "loss": 1.5118,
+      "step": 73
+    },
+    {
+      "epoch": 0.21925925925925926,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.6544,
+      "step": 74
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 10.875,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 1.5481,
+      "step": 75
+    },
+    {
+      "epoch": 0.22518518518518518,
+      "grad_norm": 10.75,
+      "learning_rate": 1.8559777834116906e-05,
+      "loss": 1.5817,
+      "step": 76
+    },
+    {
+      "epoch": 0.22814814814814816,
+      "grad_norm": 10.5,
+      "learning_rate": 1.8508284131333604e-05,
+      "loss": 1.5016,
+      "step": 77
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 10.8125,
+      "learning_rate": 1.845596003501826e-05,
+      "loss": 1.5924,
+      "step": 78
+    },
+    {
+      "epoch": 0.23407407407407407,
+      "grad_norm": 10.25,
+      "learning_rate": 1.8402810651910444e-05,
+      "loss": 1.63,
+      "step": 79
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 10.5625,
+      "learning_rate": 1.8348841169296247e-05,
+      "loss": 1.5974,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.875,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 1.5722,
+      "step": 81
+    },
+    {
+      "epoch": 0.24296296296296296,
+      "grad_norm": 10.5,
+      "learning_rate": 1.823846305438032e-05,
+      "loss": 1.4561,
+      "step": 82
+    },
+    {
+      "epoch": 0.24592592592592594,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.8182065194788024e-05,
+      "loss": 1.4567,
+      "step": 83
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 9.875,
+      "learning_rate": 1.8124868780056814e-05,
+      "loss": 1.613,
+      "step": 84
+    },
+    {
+      "epoch": 0.2518518518518518,
+      "grad_norm": 9.75,
+      "learning_rate": 1.8066879392455932e-05,
+      "loss": 1.609,
+      "step": 85
+    },
+    {
+      "epoch": 0.2548148148148148,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.800810269164738e-05,
+      "loss": 1.6807,
+      "step": 86
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.7948544414133534e-05,
+      "loss": 1.6024,
+      "step": 87
+    },
+    {
+      "epoch": 0.2607407407407407,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.7888210372697292e-05,
+      "loss": 1.4733,
+      "step": 88
+    },
+    {
+      "epoch": 0.2637037037037037,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.782710645583473e-05,
+      "loss": 1.5994,
+      "step": 89
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 13.625,
+      "learning_rate": 1.7765238627180424e-05,
+      "loss": 1.3751,
+      "step": 90
+    },
+    {
+      "epoch": 0.2696296296296296,
+      "grad_norm": 10.875,
+      "learning_rate": 1.7702612924925377e-05,
+      "loss": 1.436,
+      "step": 91
+    },
+    {
+      "epoch": 0.2725925925925926,
+      "grad_norm": 9.625,
+      "learning_rate": 1.7639235461227727e-05,
+      "loss": 1.5887,
+      "step": 92
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.7575112421616203e-05,
+      "loss": 1.5977,
+      "step": 93
+    },
+    {
+      "epoch": 0.2785185185185185,
+      "grad_norm": 10.25,
+      "learning_rate": 1.751025006438643e-05,
+      "loss": 1.518,
+      "step": 94
+    },
+    {
+      "epoch": 0.2814814814814815,
+      "grad_norm": 10.8125,
+      "learning_rate": 1.7444654719990128e-05,
+      "loss": 1.6543,
+      "step": 95
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.7378332790417275e-05,
+      "loss": 1.5368,
+      "step": 96
+    },
+    {
+      "epoch": 0.2874074074074074,
+      "grad_norm": 10.0,
+      "learning_rate": 1.7311290748571273e-05,
+      "loss": 1.5349,
+      "step": 97
+    },
+    {
+      "epoch": 0.2903703703703704,
+      "grad_norm": 9.875,
+      "learning_rate": 1.7243535137637227e-05,
+      "loss": 1.6126,
+      "step": 98
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.717507257044331e-05,
+      "loss": 1.5037,
+      "step": 99
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.7105909728815398e-05,
+      "loss": 1.5038,
+      "step": 100
+    },
+    {
+      "epoch": 0.2992592592592593,
+      "grad_norm": 9.0,
+      "learning_rate": 1.7036053362924896e-05,
+      "loss": 1.3771,
+      "step": 101
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 9.375,
+      "learning_rate": 1.6965510290629973e-05,
+      "loss": 1.5432,
+      "step": 102
+    },
+    {
+      "epoch": 0.30518518518518517,
+      "grad_norm": 9.375,
+      "learning_rate": 1.689428739681012e-05,
+      "loss": 1.4479,
+      "step": 103
+    },
+    {
+      "epoch": 0.30814814814814817,
+      "grad_norm": 11.1875,
+      "learning_rate": 1.682239163269422e-05,
+      "loss": 1.5956,
+      "step": 104
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 10.5,
+      "learning_rate": 1.6749830015182106e-05,
+      "loss": 1.4063,
+      "step": 105
+    },
+    {
+      "epoch": 0.31407407407407406,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.667660962615973e-05,
+      "loss": 1.6329,
+      "step": 106
+    },
+    {
+      "epoch": 0.31703703703703706,
+      "grad_norm": 11.3125,
+      "learning_rate": 1.6602737611807975e-05,
+      "loss": 1.5915,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 9.375,
+      "learning_rate": 1.6528221181905217e-05,
+      "loss": 1.3679,
+      "step": 108
+    },
+    {
+      "epoch": 0.32296296296296295,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.6453067609123656e-05,
+      "loss": 1.4718,
+      "step": 109
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.6377284228319496e-05,
+      "loss": 1.4929,
+      "step": 110
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.6300878435817115e-05,
+      "loss": 1.4887,
+      "step": 111
+    },
+    {
+      "epoch": 0.33185185185185184,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.622385768868716e-05,
+      "loss": 1.5634,
+      "step": 112
+    },
+    {
+      "epoch": 0.3348148148148148,
+      "grad_norm": 9.75,
+      "learning_rate": 1.6146229504018777e-05,
+      "loss": 1.4839,
+      "step": 113
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 10.9375,
+      "learning_rate": 1.6068001458185934e-05,
+      "loss": 1.4955,
+      "step": 114
+    },
+    {
+      "epoch": 0.34074074074074073,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.5989181186108003e-05,
+      "loss": 1.4464,
+      "step": 115
+    },
+    {
+      "epoch": 0.3437037037037037,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.5909776380504583e-05,
+      "loss": 1.4568,
+      "step": 116
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.5829794791144723e-05,
+      "loss": 1.5491,
+      "step": 117
+    },
+    {
+      "epoch": 0.3496296296296296,
+      "grad_norm": 10.9375,
+      "learning_rate": 1.5749244224090537e-05,
+      "loss": 1.4774,
+      "step": 118
+    },
+    {
+      "epoch": 0.35259259259259257,
+      "grad_norm": 10.875,
+      "learning_rate": 1.566813254093538e-05,
+      "loss": 1.5642,
+      "step": 119
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.5586467658036526e-05,
+      "loss": 1.5229,
+      "step": 120
+    },
+    {
+      "epoch": 0.3585185185185185,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.5504257545742585e-05,
+      "loss": 1.5067,
+      "step": 121
+    },
+    {
+      "epoch": 0.36148148148148146,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.5421510227615587e-05,
+      "loss": 1.4074,
+      "step": 122
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 11.3125,
+      "learning_rate": 1.533823377964791e-05,
+      "loss": 1.4726,
+      "step": 123
+    },
+    {
+      "epoch": 0.3674074074074074,
+      "grad_norm": 12.75,
+      "learning_rate": 1.5254436329474062e-05,
+      "loss": 1.351,
+      "step": 124
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.517012605557746e-05,
+      "loss": 1.5042,
+      "step": 125
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.5085311186492206e-05,
+      "loss": 1.5669,
+      "step": 126
+    },
+    {
+      "epoch": 0.3762962962962963,
+      "grad_norm": 9.75,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.4575,
+      "step": 127
+    },
+    {
+      "epoch": 0.37925925925925924,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.4914200822322255e-05,
+      "loss": 1.5091,
+      "step": 128
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 12.5,
+      "learning_rate": 1.482792202730745e-05,
+      "loss": 1.6976,
+      "step": 129
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 11.625,
+      "learning_rate": 1.4741172035613884e-05,
+      "loss": 1.5555,
+      "step": 130
+    },
+    {
+      "epoch": 0.38814814814814813,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.4653959313887813e-05,
+      "loss": 1.7106,
+      "step": 131
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.4566292373937133e-05,
+      "loss": 1.4944,
+      "step": 132
+    },
+    {
+      "epoch": 0.3940740740740741,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.4478179771900634e-05,
+      "loss": 1.4851,
+      "step": 133
+    },
+    {
+      "epoch": 0.397037037037037,
+      "grad_norm": 9.0,
+      "learning_rate": 1.4389630107412942e-05,
+      "loss": 1.5191,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.625,
+      "learning_rate": 1.4300652022765207e-05,
+      "loss": 1.3619,
+      "step": 135
+    },
+    {
+      "epoch": 0.40296296296296297,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.4211254202061632e-05,
+      "loss": 1.457,
+      "step": 136
+    },
+    {
+      "epoch": 0.4059259259259259,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.4121445370371922e-05,
+      "loss": 1.4453,
+      "step": 137
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 9.375,
+      "learning_rate": 1.4031234292879726e-05,
+      "loss": 1.4961,
+      "step": 138
+    },
+    {
+      "epoch": 0.41185185185185186,
+      "grad_norm": 9.625,
+      "learning_rate": 1.394062977402717e-05,
+      "loss": 1.4724,
+      "step": 139
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.3849640656655572e-05,
+      "loss": 1.4337,
+      "step": 140
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 11.1875,
+      "learning_rate": 1.3758275821142382e-05,
+      "loss": 1.4608,
+      "step": 141
+    },
+    {
+      "epoch": 0.42074074074074075,
+      "grad_norm": 10.0,
+      "learning_rate": 1.3666544184534483e-05,
+      "loss": 1.4542,
+      "step": 142
+    },
+    {
+      "epoch": 0.4237037037037037,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.3574454699677893e-05,
+      "loss": 1.5512,
+      "step": 143
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.348201635434399e-05,
+      "loss": 1.56,
+      "step": 144
+    },
+    {
+      "epoch": 0.42962962962962964,
+      "grad_norm": 9.625,
+      "learning_rate": 1.3389238170352318e-05,
+      "loss": 1.3596,
+      "step": 145
+    },
+    {
+      "epoch": 0.4325925925925926,
+      "grad_norm": 9.5,
+      "learning_rate": 1.329612920269008e-05,
+      "loss": 1.4438,
+      "step": 146
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.3202698538628376e-05,
+      "loss": 1.4873,
+      "step": 147
+    },
+    {
+      "epoch": 0.43851851851851853,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.3108955296835313e-05,
+      "loss": 1.4859,
+      "step": 148
+    },
+    {
+      "epoch": 0.4414814814814815,
+      "grad_norm": 9.75,
+      "learning_rate": 1.3014908626486032e-05,
+      "loss": 1.4505,
+      "step": 149
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.292056770636976e-05,
+      "loss": 1.3619,
+      "step": 150
+    },
+    {
+      "epoch": 0.4474074074074074,
+      "grad_norm": 10.25,
+      "learning_rate": 1.282594174399399e-05,
+      "loss": 1.4956,
+      "step": 151
+    },
+    {
+      "epoch": 0.45037037037037037,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.2731039974685833e-05,
+      "loss": 1.4486,
+      "step": 152
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.2635871660690677e-05,
+      "loss": 1.377,
+      "step": 153
+    },
+    {
+      "epoch": 0.4562962962962963,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.2540446090268193e-05,
+      "loss": 1.4245,
+      "step": 154
+    },
+    {
+      "epoch": 0.45925925925925926,
+      "grad_norm": 9.375,
+      "learning_rate": 1.2444772576785828e-05,
+      "loss": 1.407,
+      "step": 155
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.234886045780984e-05,
+      "loss": 1.4341,
+      "step": 156
+    },
+    {
+      "epoch": 0.4651851851851852,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.225271909419395e-05,
+      "loss": 1.5296,
+      "step": 157
+    },
+    {
+      "epoch": 0.46814814814814815,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.2156357869165771e-05,
+      "loss": 1.4201,
+      "step": 158
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.2059786187410984e-05,
+      "loss": 1.458,
+      "step": 159
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.1963013474155487e-05,
+      "loss": 1.5306,
+      "step": 160
+    },
+    {
+      "epoch": 0.47703703703703704,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.186604917424549e-05,
+      "loss": 1.437,
+      "step": 161
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.5,
+      "learning_rate": 1.176890275122573e-05,
+      "loss": 1.4678,
+      "step": 162
+    },
+    {
+      "epoch": 0.482962962962963,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.1671583686415833e-05,
+      "loss": 1.2917,
+      "step": 163
+    },
+    {
+      "epoch": 0.48592592592592593,
+      "grad_norm": 9.25,
+      "learning_rate": 1.1574101477984966e-05,
+      "loss": 1.4942,
+      "step": 164
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.1476465640024814e-05,
+      "loss": 1.458,
+      "step": 165
+    },
+    {
+      "epoch": 0.4918518518518519,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.1378685701621047e-05,
+      "loss": 1.4213,
+      "step": 166
+    },
+    {
+      "epoch": 0.4948148148148148,
+      "grad_norm": 8.625,
+      "learning_rate": 1.1280771205923269e-05,
+      "loss": 1.2903,
+      "step": 167
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 9.125,
+      "learning_rate": 1.1182731709213658e-05,
+      "loss": 1.3953,
+      "step": 168
+    },
+    {
+      "epoch": 0.5007407407407407,
+      "grad_norm": 9.5,
+      "learning_rate": 1.1084576779974257e-05,
+      "loss": 1.4805,
+      "step": 169
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 9.75,
+      "learning_rate": 1.0986315997953118e-05,
+      "loss": 1.4822,
+      "step": 170
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 9.75,
+      "learning_rate": 1.0887958953229349e-05,
+      "loss": 1.4369,
+      "step": 171
+    },
+    {
+      "epoch": 0.5096296296296297,
+      "grad_norm": 9.375,
+      "learning_rate": 1.078951524527712e-05,
+      "loss": 1.3851,
+      "step": 172
+    },
+    {
+      "epoch": 0.5125925925925926,
+      "grad_norm": 10.375,
+      "learning_rate": 1.069099448202878e-05,
+      "loss": 1.6454,
+      "step": 173
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.0592406278937143e-05,
+      "loss": 1.4134,
+      "step": 174
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 9.625,
+      "learning_rate": 1.049376025803703e-05,
+      "loss": 1.3613,
+      "step": 175
+    },
+    {
+      "epoch": 0.5214814814814814,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.039506604700618e-05,
+      "loss": 1.3413,
+      "step": 176
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 8.875,
+      "learning_rate": 1.0296333278225599e-05,
+      "loss": 1.3768,
+      "step": 177
+    },
+    {
+      "epoch": 0.5274074074074074,
+      "grad_norm": 9.875,
+      "learning_rate": 1.0197571587839466e-05,
+      "loss": 1.4624,
+      "step": 178
+    },
+    {
+      "epoch": 0.5303703703703704,
+      "grad_norm": 9.5,
+      "learning_rate": 1.0098790614814658e-05,
+      "loss": 1.3982,
+      "step": 179
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 1.4345,
+      "step": 180
+    },
+    {
+      "epoch": 0.5362962962962963,
+      "grad_norm": 9.4375,
+      "learning_rate": 9.901209385185345e-06,
+      "loss": 1.4967,
+      "step": 181
+    },
+    {
+      "epoch": 0.5392592592592592,
+      "grad_norm": 10.0625,
+      "learning_rate": 9.802428412160538e-06,
+      "loss": 1.5533,
+      "step": 182
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 10.375,
+      "learning_rate": 9.703666721774403e-06,
+      "loss": 1.4622,
+      "step": 183
+    },
+    {
+      "epoch": 0.5451851851851852,
+      "grad_norm": 9.4375,
+      "learning_rate": 9.604933952993822e-06,
+      "loss": 1.4235,
+      "step": 184
+    },
+    {
+      "epoch": 0.5481481481481482,
+      "grad_norm": 9.5,
+      "learning_rate": 9.506239741962971e-06,
+      "loss": 1.4563,
+      "step": 185
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 9.6875,
+      "learning_rate": 9.407593721062858e-06,
+      "loss": 1.5149,
+      "step": 186
+    },
+    {
+      "epoch": 0.554074074074074,
+      "grad_norm": 9.25,
+      "learning_rate": 9.309005517971222e-06,
+      "loss": 1.4514,
+      "step": 187
+    },
+    {
+      "epoch": 0.557037037037037,
+      "grad_norm": 9.8125,
+      "learning_rate": 9.210484754722882e-06,
+      "loss": 1.4964,
+      "step": 188
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 9.375,
+      "learning_rate": 9.112041046770653e-06,
+      "loss": 1.3697,
+      "step": 189
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 10.25,
+      "learning_rate": 9.013684002046883e-06,
+      "loss": 1.2907,
+      "step": 190
+    },
+    {
+      "epoch": 0.5659259259259259,
+      "grad_norm": 9.625,
+      "learning_rate": 8.915423220025747e-06,
+      "loss": 1.3109,
+      "step": 191
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 9.25,
+      "learning_rate": 8.817268290786343e-06,
+      "loss": 1.4432,
+      "step": 192
+    },
+    {
+      "epoch": 0.5718518518518518,
+      "grad_norm": 9.6875,
+      "learning_rate": 8.719228794076733e-06,
+      "loss": 1.4068,
+      "step": 193
+    },
+    {
+      "epoch": 0.5748148148148148,
+      "grad_norm": 10.75,
+      "learning_rate": 8.621314298378958e-06,
+      "loss": 1.4999,
+      "step": 194
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 9.875,
+      "learning_rate": 8.52353435997519e-06,
+      "loss": 1.5483,
+      "step": 195
+    },
+    {
+      "epoch": 0.5807407407407408,
+      "grad_norm": 9.25,
+      "learning_rate": 8.425898522015038e-06,
+      "loss": 1.3818,
+      "step": 196
+    },
+    {
+      "epoch": 0.5837037037037037,
+      "grad_norm": 9.8125,
+      "learning_rate": 8.328416313584169e-06,
+      "loss": 1.4961,
+      "step": 197
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 9.8125,
+      "learning_rate": 8.231097248774273e-06,
+      "loss": 1.4898,
+      "step": 198
+    },
+    {
+      "epoch": 0.5896296296296296,
+      "grad_norm": 9.4375,
+      "learning_rate": 8.133950825754511e-06,
+      "loss": 1.3789,
+      "step": 199
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 9.5625,
+      "learning_rate": 8.036986525844516e-06,
+      "loss": 1.3425,
+      "step": 200
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 10.4375,
+      "learning_rate": 7.940213812589018e-06,
+      "loss": 1.6482,
+      "step": 201
+    },
+    {
+      "epoch": 0.5985185185185186,
+      "grad_norm": 9.875,
+      "learning_rate": 7.843642130834232e-06,
+      "loss": 1.4535,
+      "step": 202
+    },
+    {
+      "epoch": 0.6014814814814815,
+      "grad_norm": 9.5625,
+      "learning_rate": 7.747280905806051e-06,
+      "loss": 1.3676,
+      "step": 203
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 9.6875,
+      "learning_rate": 7.651139542190164e-06,
+      "loss": 1.498,
+      "step": 204
+    },
+    {
+      "epoch": 0.6074074074074074,
+      "grad_norm": 9.75,
+      "learning_rate": 7.555227423214174e-06,
+      "loss": 1.4675,
+      "step": 205
+    },
+    {
+      "epoch": 0.6103703703703703,
+      "grad_norm": 9.75,
+      "learning_rate": 7.45955390973181e-06,
+      "loss": 1.5049,
+      "step": 206
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 9.125,
+      "learning_rate": 7.364128339309326e-06,
+      "loss": 1.4279,
+      "step": 207
+    },
+    {
+      "epoch": 0.6162962962962963,
+      "grad_norm": 9.5625,
+      "learning_rate": 7.268960025314169e-06,
+      "loss": 1.504,
+      "step": 208
+    },
+    {
+      "epoch": 0.6192592592592593,
+      "grad_norm": 9.0625,
+      "learning_rate": 7.174058256006012e-06,
+      "loss": 1.4354,
+      "step": 209
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 9.1875,
+      "learning_rate": 7.079432293630244e-06,
+      "loss": 1.3362,
+      "step": 210
+    },
+    {
+      "epoch": 0.6251851851851852,
+      "grad_norm": 9.9375,
+      "learning_rate": 6.985091373513972e-06,
+      "loss": 1.3616,
+      "step": 211
+    },
+    {
+      "epoch": 0.6281481481481481,
+      "grad_norm": 9.4375,
+      "learning_rate": 6.8910447031646884e-06,
+      "loss": 1.4284,
+      "step": 212
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 9.0,
+      "learning_rate": 6.797301461371626e-06,
+      "loss": 1.2881,
+      "step": 213
+    },
+    {
+      "epoch": 0.6340740740740741,
+      "grad_norm": 10.0625,
+      "learning_rate": 6.703870797309922e-06,
+      "loss": 1.4838,
+      "step": 214
+    },
+    {
+      "epoch": 0.6370370370370371,
+      "grad_norm": 10.625,
+      "learning_rate": 6.610761829647685e-06,
+      "loss": 1.5364,
+      "step": 215
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 9.625,
+      "learning_rate": 6.517983645656014e-06,
+      "loss": 1.4076,
+      "step": 216
+    },
+    {
+      "epoch": 0.642962962962963,
+      "grad_norm": 9.8125,
+      "learning_rate": 6.4255453003221115e-06,
+      "loss": 1.3774,
+      "step": 217
+    },
+    {
+      "epoch": 0.6459259259259259,
+      "grad_norm": 9.4375,
+      "learning_rate": 6.33345581546552e-06,
+      "loss": 1.4266,
+      "step": 218
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 8.875,
+      "learning_rate": 6.241724178857621e-06,
+      "loss": 1.3279,
+      "step": 219
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 10.5625,
+      "learning_rate": 6.1503593433444316e-06,
+      "loss": 1.4278,
+      "step": 220
+    },
+    {
+      "epoch": 0.6548148148148148,
+      "grad_norm": 9.6875,
+      "learning_rate": 6.059370225972834e-06,
+      "loss": 1.454,
+      "step": 221
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 9.5,
+      "learning_rate": 5.96876570712028e-06,
+      "loss": 1.3883,
+      "step": 222
+    },
+    {
+      "epoch": 0.6607407407407407,
+      "grad_norm": 9.5,
+      "learning_rate": 5.878554629628081e-06,
+      "loss": 1.3739,
+      "step": 223
+    },
+    {
+      "epoch": 0.6637037037037037,
+      "grad_norm": 9.3125,
+      "learning_rate": 5.788745797938372e-06,
+      "loss": 1.381,
+      "step": 224
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 9.375,
+      "learning_rate": 5.699347977234799e-06,
+      "loss": 1.3763,
+      "step": 225
+    },
+    {
+      "epoch": 0.6696296296296296,
+      "grad_norm": 9.4375,
+      "learning_rate": 5.610369892587064e-06,
+      "loss": 1.2782,
+      "step": 226
+    },
+    {
+      "epoch": 0.6725925925925926,
+      "grad_norm": 9.1875,
+      "learning_rate": 5.5218202280993725e-06,
+      "loss": 1.428,
+      "step": 227
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 9.4375,
+      "learning_rate": 5.43370762606287e-06,
+      "loss": 1.4381,
+      "step": 228
+    },
+    {
+      "epoch": 0.6785185185185185,
+      "grad_norm": 9.875,
+      "learning_rate": 5.346040686112189e-06,
+      "loss": 1.3499,
+      "step": 229
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 9.6875,
+      "learning_rate": 5.25882796438612e-06,
+      "loss": 1.3794,
+      "step": 230
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 9.6875,
+      "learning_rate": 5.172077972692553e-06,
+      "loss": 1.3564,
+      "step": 231
+    },
+    {
+      "epoch": 0.6874074074074074,
+      "grad_norm": 10.0,
+      "learning_rate": 5.08579917767775e-06,
+      "loss": 1.4274,
+      "step": 232
+    },
+    {
+      "epoch": 0.6903703703703704,
+      "grad_norm": 8.9375,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.267,
+      "step": 233
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 9.375,
+      "learning_rate": 4.914688813507798e-06,
+      "loss": 1.3242,
+      "step": 234
+    },
+    {
+      "epoch": 0.6962962962962963,
+      "grad_norm": 9.25,
+      "learning_rate": 4.829873944422544e-06,
+      "loss": 1.3488,
+      "step": 235
+    },
+    {
+      "epoch": 0.6992592592592592,
+      "grad_norm": 9.125,
+      "learning_rate": 4.745563670525942e-06,
+      "loss": 1.3237,
+      "step": 236
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 9.5625,
+      "learning_rate": 4.661766220352098e-06,
+      "loss": 1.3183,
+      "step": 237
+    },
+    {
+      "epoch": 0.7051851851851851,
+      "grad_norm": 9.5625,
+      "learning_rate": 4.578489772384415e-06,
+      "loss": 1.4587,
+      "step": 238
+    },
+    {
+      "epoch": 0.7081481481481482,
+      "grad_norm": 9.5,
+      "learning_rate": 4.495742454257418e-06,
+      "loss": 1.2974,
+      "step": 239
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 9.5625,
+      "learning_rate": 4.413532341963477e-06,
+      "loss": 1.4561,
+      "step": 240
+    },
+    {
+      "epoch": 0.7140740740740741,
+      "grad_norm": 9.625,
+      "learning_rate": 4.331867459064623e-06,
+      "loss": 1.4047,
+      "step": 241
+    },
+    {
+      "epoch": 0.717037037037037,
+      "grad_norm": 9.3125,
+      "learning_rate": 4.250755775909465e-06,
+      "loss": 1.4223,
+      "step": 242
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 9.3125,
+      "learning_rate": 4.170205208855281e-06,
+      "loss": 1.4031,
+      "step": 243
+    },
+    {
+      "epoch": 0.7229629629629629,
+      "grad_norm": 9.125,
+      "learning_rate": 4.090223619495419e-06,
+      "loss": 1.3283,
+      "step": 244
+    },
+    {
+      "epoch": 0.725925925925926,
+      "grad_norm": 9.375,
+      "learning_rate": 4.010818813892e-06,
+      "loss": 1.419,
+      "step": 245
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 9.25,
+      "learning_rate": 3.931998541814069e-06,
+      "loss": 1.3429,
+      "step": 246
+    },
+    {
+      "epoch": 0.7318518518518519,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.85377049598123e-06,
+      "loss": 1.436,
+      "step": 247
+    },
+    {
+      "epoch": 0.7348148148148148,
+      "grad_norm": 9.375,
+      "learning_rate": 3.7761423113128427e-06,
+      "loss": 1.3918,
+      "step": 248
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 9.6875,
+      "learning_rate": 3.6991215641828903e-06,
+      "loss": 1.3523,
+      "step": 249
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.622715771680508e-06,
+      "loss": 1.3808,
+      "step": 250
+    },
+    {
+      "epoch": 0.7437037037037038,
+      "grad_norm": 9.375,
+      "learning_rate": 3.5469323908763507e-06,
+      "loss": 1.4308,
+      "step": 251
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.4717788180947855e-06,
+      "loss": 1.3985,
+      "step": 252
+    },
+    {
+      "epoch": 0.7496296296296296,
+      "grad_norm": 9.625,
+      "learning_rate": 3.3972623881920296e-06,
+      "loss": 1.3034,
+      "step": 253
+    },
+    {
+      "epoch": 0.7525925925925926,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.323390373840276e-06,
+      "loss": 1.3579,
+      "step": 254
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 9.25,
+      "learning_rate": 3.250169984817897e-06,
+      "loss": 1.3301,
+      "step": 255
+    },
+    {
+      "epoch": 0.7585185185185185,
+      "grad_norm": 9.125,
+      "learning_rate": 3.1776083673057834e-06,
+      "loss": 1.308,
+      "step": 256
+    },
+    {
+      "epoch": 0.7614814814814815,
+      "grad_norm": 9.1875,
+      "learning_rate": 3.1057126031898843e-06,
+      "loss": 1.3278,
+      "step": 257
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.0344897093700333e-06,
+      "loss": 1.3678,
+      "step": 258
+    },
+    {
+      "epoch": 0.7674074074074074,
+      "grad_norm": 9.25,
+      "learning_rate": 2.963946637075107e-06,
+      "loss": 1.2888,
+      "step": 259
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 9.1875,
+      "learning_rate": 2.8940902711846052e-06,
+      "loss": 1.2899,
+      "step": 260
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 8.625,
+      "learning_rate": 2.8249274295566863e-06,
+      "loss": 1.2525,
+      "step": 261
+    },
+    {
+      "epoch": 0.7762962962962963,
+      "grad_norm": 8.8125,
+      "learning_rate": 2.756464862362772e-06,
+      "loss": 1.2665,
+      "step": 262
+    },
+    {
+      "epoch": 0.7792592592592592,
+      "grad_norm": 9.4375,
+      "learning_rate": 2.688709251428725e-06,
+      "loss": 1.363,
+      "step": 263
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 9.0625,
+      "learning_rate": 2.6216672095827267e-06,
+      "loss": 1.3086,
+      "step": 264
+    },
+    {
+      "epoch": 0.7851851851851852,
+      "grad_norm": 9.3125,
+      "learning_rate": 2.555345280009872e-06,
+      "loss": 1.4259,
+      "step": 265
+    },
+    {
+      "epoch": 0.7881481481481482,
+      "grad_norm": 9.125,
+      "learning_rate": 2.4897499356135712e-06,
+      "loss": 1.2748,
+      "step": 266
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 9.25,
+      "learning_rate": 2.424887578383799e-06,
+      "loss": 1.329,
+      "step": 267
+    },
+    {
+      "epoch": 0.794074074074074,
+      "grad_norm": 9.5625,
+      "learning_rate": 2.3607645387722753e-06,
+      "loss": 1.4323,
+      "step": 268
+    },
+    {
+      "epoch": 0.797037037037037,
+      "grad_norm": 9.5625,
+      "learning_rate": 2.2973870750746253e-06,
+      "loss": 1.3081,
+      "step": 269
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.375,
+      "learning_rate": 2.234761372819577e-06,
+      "loss": 1.3967,
+      "step": 270
+    },
+    {
+      "epoch": 0.802962962962963,
+      "grad_norm": 9.3125,
+      "learning_rate": 2.1728935441652687e-06,
+      "loss": 1.345,
+      "step": 271
+    },
+    {
+      "epoch": 0.8059259259259259,
+      "grad_norm": 9.0,
+      "learning_rate": 2.111789627302707e-06,
+      "loss": 1.3009,
+      "step": 272
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 9.25,
+      "learning_rate": 2.0514555858664663e-06,
+      "loss": 1.3242,
+      "step": 273
+    },
+    {
+      "epoch": 0.8118518518518518,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.991897308352624e-06,
+      "loss": 1.3109,
+      "step": 274
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 8.9375,
+      "learning_rate": 1.93312060754407e-06,
+      "loss": 1.3353,
+      "step": 275
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 9.625,
+      "learning_rate": 1.875131219943187e-06,
+      "loss": 1.2318,
+      "step": 276
+    },
+    {
+      "epoch": 0.8207407407407408,
+      "grad_norm": 9.0,
+      "learning_rate": 1.817934805211976e-06,
+      "loss": 1.2841,
+      "step": 277
+    },
+    {
+      "epoch": 0.8237037037037037,
+      "grad_norm": 8.6875,
+      "learning_rate": 1.761536945619684e-06,
+      "loss": 1.2261,
+      "step": 278
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.7059431454979825e-06,
+      "loss": 1.364,
+      "step": 279
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 9.125,
+      "learning_rate": 1.6511588307037596e-06,
+      "loss": 1.426,
+      "step": 280
+    },
+    {
+      "epoch": 0.8325925925925926,
+      "grad_norm": 9.625,
+      "learning_rate": 1.5971893480895583e-06,
+      "loss": 1.458,
+      "step": 281
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 8.875,
+      "learning_rate": 1.5440399649817384e-06,
+      "loss": 1.4178,
+      "step": 282
+    },
+    {
+      "epoch": 0.8385185185185186,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.4917158686663992e-06,
+      "loss": 1.3404,
+      "step": 283
+    },
+    {
+      "epoch": 0.8414814814814815,
+      "grad_norm": 8.75,
+      "learning_rate": 1.4402221658830963e-06,
+      "loss": 1.3145,
+      "step": 284
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.3895638823264447e-06,
+      "loss": 1.2529,
+      "step": 285
+    },
+    {
+      "epoch": 0.8474074074074074,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.5298,
+      "step": 286
+    },
+    {
+      "epoch": 0.8503703703703703,
+      "grad_norm": 8.75,
+      "learning_rate": 1.2907732675117878e-06,
+      "loss": 1.2976,
+      "step": 287
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 9.875,
+      "learning_rate": 1.2426505780436326e-06,
+      "loss": 1.3695,
+      "step": 288
+    },
+    {
+      "epoch": 0.8562962962962963,
+      "grad_norm": 8.75,
+      "learning_rate": 1.1953825904408033e-06,
+      "loss": 1.2496,
+      "step": 289
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.1489739179755622e-06,
+      "loss": 1.4167,
+      "step": 290
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 9.5,
+      "learning_rate": 1.1034290900525279e-06,
+      "loss": 1.3485,
+      "step": 291
+    },
+    {
+      "epoch": 0.8651851851851852,
+      "grad_norm": 8.9375,
+      "learning_rate": 1.0587525517666142e-06,
+      "loss": 1.2987,
+      "step": 292
+    },
+    {
+      "epoch": 0.8681481481481481,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.0149486634692019e-06,
+      "loss": 1.2708,
+      "step": 293
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 9.0625,
+      "learning_rate": 9.720217003425648e-07,
+      "loss": 1.405,
+      "step": 294
+    },
+    {
+      "epoch": 0.8740740740740741,
+      "grad_norm": 9.125,
+      "learning_rate": 9.299758519826274e-07,
+      "loss": 1.3643,
+      "step": 295
+    },
+    {
+      "epoch": 0.8770370370370371,
+      "grad_norm": 9.125,
+      "learning_rate": 8.888152219900692e-07,
+      "loss": 1.33,
+      "step": 296
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 9.6875,
+      "learning_rate": 8.485438275698154e-07,
+      "loss": 1.4734,
+      "step": 297
+    },
+    {
+      "epoch": 0.882962962962963,
+      "grad_norm": 9.75,
+      "learning_rate": 8.091655991389668e-07,
+      "loss": 1.3231,
+      "step": 298
+    },
+    {
+      "epoch": 0.8859259259259259,
+      "grad_norm": 8.9375,
+      "learning_rate": 7.706843799431985e-07,
+      "loss": 1.2256,
+      "step": 299
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 9.6875,
+      "learning_rate": 7.331039256816664e-07,
+      "loss": 1.3831,
+      "step": 300
+    },
+    {
+      "epoch": 0.8918518518518519,
+      "grad_norm": 8.9375,
+      "learning_rate": 6.964279041404553e-07,
+      "loss": 1.2743,
+      "step": 301
+    },
+    {
+      "epoch": 0.8948148148148148,
+      "grad_norm": 9.1875,
+      "learning_rate": 6.606598948346132e-07,
+      "loss": 1.3141,
+      "step": 302
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 9.8125,
+      "learning_rate": 6.258033886587911e-07,
+      "loss": 1.4539,
+      "step": 303
+    },
+    {
+      "epoch": 0.9007407407407407,
+      "grad_norm": 10.3125,
+      "learning_rate": 5.918617875465449e-07,
+      "loss": 1.4409,
+      "step": 304
+    },
+    {
+      "epoch": 0.9037037037037037,
+      "grad_norm": 9.9375,
+      "learning_rate": 5.588384041383089e-07,
+      "loss": 1.3793,
+      "step": 305
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 9.8125,
+      "learning_rate": 5.267364614580861e-07,
+      "loss": 1.391,
+      "step": 306
+    },
+    {
+      "epoch": 0.9096296296296297,
+      "grad_norm": 8.9375,
+      "learning_rate": 4.955590925988896e-07,
+      "loss": 1.2844,
+      "step": 307
+    },
+    {
+      "epoch": 0.9125925925925926,
+      "grad_norm": 9.6875,
+      "learning_rate": 4.653093404169573e-07,
+      "loss": 1.3854,
+      "step": 308
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 9.9375,
+      "learning_rate": 4.359901572347758e-07,
+      "loss": 1.378,
+      "step": 309
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 10.0625,
+      "learning_rate": 4.0760440455293703e-07,
+      "loss": 1.4957,
+      "step": 310
+    },
+    {
+      "epoch": 0.9214814814814815,
+      "grad_norm": 10.0625,
+      "learning_rate": 3.801548527708621e-07,
+      "loss": 1.518,
+      "step": 311
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 9.1875,
+      "learning_rate": 3.5364418091641374e-07,
+      "loss": 1.2608,
+      "step": 312
+    },
+    {
+      "epoch": 0.9274074074074075,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.280749763844293e-07,
+      "loss": 1.3896,
+      "step": 313
+    },
+    {
+      "epoch": 0.9303703703703704,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.034497346841958e-07,
+      "loss": 1.4369,
+      "step": 314
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 9.0,
+      "learning_rate": 2.7977085919589253e-07,
+      "loss": 1.4707,
+      "step": 315
+    },
+    {
+      "epoch": 0.9362962962962963,
+      "grad_norm": 8.875,
+      "learning_rate": 2.570406609360221e-07,
+      "loss": 1.2772,
+      "step": 316
+    },
+    {
+      "epoch": 0.9392592592592592,
+      "grad_norm": 9.6875,
+      "learning_rate": 2.3526135833186527e-07,
+      "loss": 1.3784,
+      "step": 317
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 9.3125,
+      "learning_rate": 2.1443507700495968e-07,
+      "loss": 1.3823,
+      "step": 318
+    },
+    {
+      "epoch": 0.9451851851851852,
+      "grad_norm": 9.375,
+      "learning_rate": 1.9456384956365149e-07,
+      "loss": 1.3478,
+      "step": 319
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 9.875,
+      "learning_rate": 1.7564961540470492e-07,
+      "loss": 1.3708,
+      "step": 320
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 9.125,
+      "learning_rate": 1.5769422052403172e-07,
+      "loss": 1.2729,
+      "step": 321
+    },
+    {
+      "epoch": 0.9540740740740741,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.4069941733651948e-07,
+      "loss": 1.3488,
+      "step": 322
+    },
+    {
+      "epoch": 0.957037037037037,
+      "grad_norm": 9.0,
+      "learning_rate": 1.2466686450499866e-07,
+      "loss": 1.3308,
+      "step": 323
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.0959812677835968e-07,
+      "loss": 1.3702,
+      "step": 324
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 9.125,
+      "learning_rate": 9.549467483884412e-08,
+      "loss": 1.2894,
+      "step": 325
+    },
+    {
+      "epoch": 0.965925925925926,
+      "grad_norm": 9.6875,
+      "learning_rate": 8.235788515849607e-08,
+      "loss": 1.4597,
+      "step": 326
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 8.9375,
+      "learning_rate": 7.018903986483083e-08,
+      "loss": 1.3452,
+      "step": 327
+    },
+    {
+      "epoch": 0.9718518518518519,
+      "grad_norm": 9.1875,
+      "learning_rate": 5.89893266156949e-08,
+      "loss": 1.3317,
+      "step": 328
+    },
+    {
+      "epoch": 0.9748148148148148,
+      "grad_norm": 9.9375,
+      "learning_rate": 4.8759838483358745e-08,
+      "loss": 1.325,
+      "step": 329
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 9.125,
+      "learning_rate": 3.950157384783104e-08,
+      "loss": 1.3164,
+      "step": 330
+    },
+    {
+      "epoch": 0.9807407407407407,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.12154362994177e-08,
+      "loss": 1.4195,
+      "step": 331
+    },
+    {
+      "epoch": 0.9837037037037037,
+      "grad_norm": 9.375,
+      "learning_rate": 2.3902234550536862e-08,
+      "loss": 1.3961,
+      "step": 332
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.7562682356786488e-08,
+      "loss": 1.2901,
+      "step": 333
+    },
+    {
+      "epoch": 0.9896296296296296,
+      "grad_norm": 10.0,
+      "learning_rate": 1.2197398447283404e-08,
+      "loss": 1.5034,
+      "step": 334
+    },
+    {
+      "epoch": 0.9925925925925926,
+      "grad_norm": 10.0625,
+      "learning_rate": 7.806906464281617e-09,
+      "loss": 1.4242,
+      "step": 335
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 9.625,
+      "learning_rate": 4.39163491205652e-09,
+      "loss": 1.4248,
+      "step": 336
+    },
+    {
+      "epoch": 0.9985185185185185,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.951917115091684e-09,
+      "loss": 1.3997,
+      "step": 337
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 13.5625,
+      "learning_rate": 4.879911855426578e-10,
+      "loss": 1.3577,
+      "step": 338
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 338,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5614551709925376.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-338/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e208ca8d5ec9994728b931eda9cdb80dc0a6ebdb8d0187175a9d1fd08f1ba1
+size 5752