Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee4e9b1b78262c5ea3b460b7ed6231ab00a0b13a149fac3077af78160742a26
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59620eabaf438533c845d54d79160abeff7b8dd05bc41d8f751964dd14d6c003
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-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_norm.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.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.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_norm.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_norm.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.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-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_norm.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_norm.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.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d7643b30a00af1add3757b968e9ae598f906e0fadf68a354cd3629fbcd9660
+size 14534279706

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd50dcddd76a88c1d10f985b5a08df6e34744c003b6feff687f4774bf36a1513
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096e351ace65ff91008be171a45173ed6369cc639fce73a288f671041e24b0ec
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21c61b1a7e793bbdec183de3b52da90042305234bc7e5887986655cd3fc2192
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348742498d81780506d9760c655a7a7555185b5fbd70a7ae296d88fd9aeecd84
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399c4700dab9ae7b754110ce307fb7e26e22cb49b5bb233c435f0f12b77c202f
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864ea2379cc907eb4189c52706cb978150d9c26e18abf74679590729a8f0c8e8
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25755ba07299ee6ff45936dd04df329596319c9f8095af71e6f3a219e7543e26
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908f018cd701ed629c41299726da4a25f202f20a1d4bc2075a2266ed4013db3a
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9149eb1a87bd99c883a7b9adf5ffab0fe75c86a60665dba5feb76d7679e2eab1
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3dfe474a8bbe89b0e83627fd9ff784ad71027f12fd8c618708c818e808789d
+size 11422648

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2433 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 2000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001,
+      "grad_norm": 4736.0,
+      "learning_rate": 1.9e-05,
+      "loss": 132.1055,
+      "loss/crossentropy": 12.246079635620116,
+      "loss/hidden": 18.7125,
+      "loss/jsd": 0.0,
+      "loss/logits": 10.372939014434815,
+      "step": 10
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 330.0,
+      "grad_norm_var": 91640269.18333334,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 95.9731,
+      "loss/crossentropy": 8.862393474578857,
+      "loss/hidden": 18.675,
+      "loss/jsd": 0.0,
+      "loss/logits": 6.677179157733917,
+      "step": 20
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 394.0,
+      "grad_norm_var": 237715.45,
+      "learning_rate": 3.7e-05,
+      "loss": 86.3778,
+      "loss/crossentropy": 8.083840227127075,
+      "loss/hidden": 18.259375,
+      "loss/jsd": 0.0,
+      "loss/logits": 6.130921971797943,
+      "step": 30
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 924.0,
+      "grad_norm_var": 2.6757682503402172e+16,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 82.5914,
+      "loss/crossentropy": 7.802511918544769,
+      "loss/hidden": 17.440625,
+      "loss/jsd": 0.0,
+      "loss/logits": 5.772503018379211,
+      "step": 40
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 516.0,
+      "grad_norm_var": 38597.583333333336,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 75.3397,
+      "loss/crossentropy": 7.156700026988983,
+      "loss/hidden": 17.253125,
+      "loss/jsd": 0.0,
+      "loss/logits": 5.156575608253479,
+      "step": 50
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 1232.0,
+      "grad_norm_var": 68241.45,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 61.2745,
+      "loss/crossentropy": 6.0138510942459105,
+      "loss/hidden": 15.80625,
+      "loss/jsd": 0.0,
+      "loss/logits": 3.8037488579750063,
+      "step": 60
+    },
+    {
+      "epoch": 0.007,
+      "grad_norm": 376.0,
+      "grad_norm_var": 626103.4,
+      "learning_rate": 7.3e-05,
+      "loss": 41.3695,
+      "loss/crossentropy": 4.422797441482544,
+      "loss/hidden": 13.1125,
+      "loss/jsd": 0.0,
+      "loss/logits": 2.4006322652101515,
+      "step": 70
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 272.0,
+      "grad_norm_var": 674923.45,
+      "learning_rate": 8.200000000000001e-05,
+      "loss": 27.4755,
+      "loss/crossentropy": 3.3576226443052293,
+      "loss/hidden": 10.7359375,
+      "loss/jsd": 0.0,
+      "loss/logits": 1.3968962401151657,
+      "step": 80
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 296.0,
+      "grad_norm_var": 15426.383333333333,
+      "learning_rate": 9.1e-05,
+      "loss": 22.6607,
+      "loss/crossentropy": 3.217679074406624,
+      "loss/hidden": 9.2140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 1.055714099109173,
+      "step": 90
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 328.0,
+      "grad_norm_var": 9349.666666666666,
+      "learning_rate": 0.0001,
+      "loss": 20.3108,
+      "loss/crossentropy": 2.934060016274452,
+      "loss/hidden": 8.40703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.8702833190560341,
+      "step": 100
+    },
+    {
+      "epoch": 0.011,
+      "grad_norm": 194.0,
+      "grad_norm_var": 5992.866666666667,
+      "learning_rate": 0.0001,
+      "loss": 18.8852,
+      "loss/crossentropy": 2.8450062334537507,
+      "loss/hidden": 8.221875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.8380498677492142,
+      "step": 110
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 244.0,
+      "grad_norm_var": 1176.5333333333333,
+      "learning_rate": 0.0001,
+      "loss": 17.97,
+      "loss/crossentropy": 2.612249107658863,
+      "loss/hidden": 7.578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.686215291172266,
+      "step": 120
+    },
+    {
+      "epoch": 0.013,
+      "grad_norm": 242.0,
+      "grad_norm_var": 1168.8958333333333,
+      "learning_rate": 0.0001,
+      "loss": 17.2904,
+      "loss/crossentropy": 2.8242316216230394,
+      "loss/hidden": 7.7390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.7805894792079926,
+      "step": 130
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 179.0,
+      "grad_norm_var": 1465.1333333333334,
+      "learning_rate": 0.0001,
+      "loss": 16.5581,
+      "loss/crossentropy": 2.737143725156784,
+      "loss/hidden": 7.3421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.6888546235859394,
+      "step": 140
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 175.0,
+      "grad_norm_var": 1119.8625,
+      "learning_rate": 0.0001,
+      "loss": 16.0501,
+      "loss/crossentropy": 2.7599751561880113,
+      "loss/hidden": 7.05703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.6640767879784107,
+      "step": 150
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 186.0,
+      "grad_norm_var": 1044.5166666666667,
+      "learning_rate": 0.0001,
+      "loss": 15.4631,
+      "loss/crossentropy": 2.6100075274705885,
+      "loss/hidden": 6.8203125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5824844464659691,
+      "step": 160
+    },
+    {
+      "epoch": 0.017,
+      "grad_norm": 179.0,
+      "grad_norm_var": 1082.8,
+      "learning_rate": 0.0001,
+      "loss": 15.2201,
+      "loss/crossentropy": 2.4276285111904143,
+      "loss/hidden": 6.8203125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5915141828358174,
+      "step": 170
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 153.0,
+      "grad_norm_var": 622.6625,
+      "learning_rate": 0.0001,
+      "loss": 14.9606,
+      "loss/crossentropy": 2.630460512638092,
+      "loss/hidden": 6.52578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5396774187684059,
+      "step": 180
+    },
+    {
+      "epoch": 0.019,
+      "grad_norm": 176.0,
+      "grad_norm_var": 1093.2,
+      "learning_rate": 0.0001,
+      "loss": 14.6255,
+      "loss/crossentropy": 2.3158223152160646,
+      "loss/hidden": 6.50390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4905257746577263,
+      "step": 190
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 112.0,
+      "grad_norm_var": 695.7291666666666,
+      "learning_rate": 0.0001,
+      "loss": 14.3647,
+      "loss/crossentropy": 2.586851382255554,
+      "loss/hidden": 6.42265625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5586091712117195,
+      "step": 200
+    },
+    {
+      "epoch": 0.021,
+      "grad_norm": 118.5,
+      "grad_norm_var": 574.3072916666666,
+      "learning_rate": 0.0001,
+      "loss": 14.0867,
+      "loss/crossentropy": 2.5010055124759676,
+      "loss/hidden": 6.34453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4965482771396637,
+      "step": 210
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 88.5,
+      "grad_norm_var": 662.65,
+      "learning_rate": 0.0001,
+      "loss": 13.6551,
+      "loss/crossentropy": 2.573444625735283,
+      "loss/hidden": 6.33125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5534068010747433,
+      "step": 220
+    },
+    {
+      "epoch": 0.023,
+      "grad_norm": 118.0,
+      "grad_norm_var": 412.1958333333333,
+      "learning_rate": 0.0001,
+      "loss": 13.4715,
+      "loss/crossentropy": 2.4142292886972427,
+      "loss/hidden": 5.96640625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.44360905699431896,
+      "step": 230
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 134.0,
+      "grad_norm_var": 242.9,
+      "learning_rate": 0.0001,
+      "loss": 13.3289,
+      "loss/crossentropy": 2.4670142769813537,
+      "loss/hidden": 5.98671875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.47392544001340864,
+      "step": 240
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 137.0,
+      "grad_norm_var": 158.4625,
+      "learning_rate": 0.0001,
+      "loss": 13.0031,
+      "loss/crossentropy": 2.416000656783581,
+      "loss/hidden": 5.7859375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.44607544504106045,
+      "step": 250
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 109.0,
+      "grad_norm_var": 279.990625,
+      "learning_rate": 0.0001,
+      "loss": 13.0076,
+      "loss/crossentropy": 2.370332670211792,
+      "loss/hidden": 5.9984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.5006627842783928,
+      "step": 260
+    },
+    {
+      "epoch": 0.027,
+      "grad_norm": 129.0,
+      "grad_norm_var": 427.37395833333335,
+      "learning_rate": 0.0001,
+      "loss": 12.8809,
+      "loss/crossentropy": 2.281908763945103,
+      "loss/hidden": 5.98671875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.45061586182564495,
+      "step": 270
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 98.0,
+      "grad_norm_var": 278.1489583333333,
+      "learning_rate": 0.0001,
+      "loss": 12.8942,
+      "loss/crossentropy": 2.3922384053468706,
+      "loss/hidden": 5.6984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.44376694336533545,
+      "step": 280
+    },
+    {
+      "epoch": 0.029,
+      "grad_norm": 99.5,
+      "grad_norm_var": 303.55,
+      "learning_rate": 0.0001,
+      "loss": 12.7122,
+      "loss/crossentropy": 2.730095013976097,
+      "loss/hidden": 5.49140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4411045670509338,
+      "step": 290
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 112.5,
+      "grad_norm_var": 359.56666666666666,
+      "learning_rate": 0.0001,
+      "loss": 12.5618,
+      "loss/crossentropy": 2.3741705983877184,
+      "loss/hidden": 5.43203125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.40091707594692705,
+      "step": 300
+    },
+    {
+      "epoch": 0.031,
+      "grad_norm": 84.5,
+      "grad_norm_var": 245.25729166666667,
+      "learning_rate": 0.0001,
+      "loss": 12.2525,
+      "loss/crossentropy": 2.2781229317188263,
+      "loss/hidden": 5.53515625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4274128321558237,
+      "step": 310
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 108.5,
+      "grad_norm_var": 140.59583333333333,
+      "learning_rate": 0.0001,
+      "loss": 12.2935,
+      "loss/crossentropy": 2.5757294684648513,
+      "loss/hidden": 5.4609375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.42916890494525434,
+      "step": 320
+    },
+    {
+      "epoch": 0.033,
+      "grad_norm": 108.0,
+      "grad_norm_var": 70.89895833333334,
+      "learning_rate": 0.0001,
+      "loss": 12.1545,
+      "loss/crossentropy": 2.527638339996338,
+      "loss/hidden": 5.378125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4032053742557764,
+      "step": 330
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 210.0,
+      "grad_norm_var": 1272.465625,
+      "learning_rate": 0.0001,
+      "loss": 12.2482,
+      "loss/crossentropy": 2.5401821002364158,
+      "loss/hidden": 5.390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4444709587842226,
+      "step": 340
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 79.5,
+      "grad_norm_var": 1376.5958333333333,
+      "learning_rate": 0.0001,
+      "loss": 12.08,
+      "loss/crossentropy": 2.514840933680534,
+      "loss/hidden": 5.2640625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4077944982796907,
+      "step": 350
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 87.0,
+      "grad_norm_var": 418.83229166666666,
+      "learning_rate": 0.0001,
+      "loss": 12.0245,
+      "loss/crossentropy": 2.420889538526535,
+      "loss/hidden": 5.34921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.44222328886389733,
+      "step": 360
+    },
+    {
+      "epoch": 0.037,
+      "grad_norm": 76.5,
+      "grad_norm_var": 138.5625,
+      "learning_rate": 0.0001,
+      "loss": 11.7097,
+      "loss/crossentropy": 2.2826619133353234,
+      "loss/hidden": 5.3296875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3849468305706978,
+      "step": 370
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 96.5,
+      "grad_norm_var": 184.93229166666666,
+      "learning_rate": 0.0001,
+      "loss": 11.465,
+      "loss/crossentropy": 2.4052042722702027,
+      "loss/hidden": 5.16796875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.40173302926123144,
+      "step": 380
+    },
+    {
+      "epoch": 0.039,
+      "grad_norm": 125.5,
+      "grad_norm_var": 183.09583333333333,
+      "learning_rate": 0.0001,
+      "loss": 11.6273,
+      "loss/crossentropy": 2.540145033597946,
+      "loss/hidden": 5.215625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.41224894523620603,
+      "step": 390
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 83.5,
+      "grad_norm_var": 258.315625,
+      "learning_rate": 0.0001,
+      "loss": 11.397,
+      "loss/crossentropy": 2.207468980550766,
+      "loss/hidden": 5.09296875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3590874429792166,
+      "step": 400
+    },
+    {
+      "epoch": 0.041,
+      "grad_norm": 94.5,
+      "grad_norm_var": 184.5625,
+      "learning_rate": 0.0001,
+      "loss": 11.443,
+      "loss/crossentropy": 2.4378984421491623,
+      "loss/hidden": 5.21171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.40493359677493573,
+      "step": 410
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 106.5,
+      "grad_norm_var": 125.590625,
+      "learning_rate": 0.0001,
+      "loss": 11.5678,
+      "loss/crossentropy": 2.518555220961571,
+      "loss/hidden": 5.07265625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.4297170080244541,
+      "step": 420
+    },
+    {
+      "epoch": 0.043,
+      "grad_norm": 87.5,
+      "grad_norm_var": 115.765625,
+      "learning_rate": 0.0001,
+      "loss": 11.3132,
+      "loss/crossentropy": 2.490597203373909,
+      "loss/hidden": 5.11171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.403754598274827,
+      "step": 430
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 92.5,
+      "grad_norm_var": 156.35729166666667,
+      "learning_rate": 0.0001,
+      "loss": 11.1476,
+      "loss/crossentropy": 2.037529316544533,
+      "loss/hidden": 5.07421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.35246654506772757,
+      "step": 440
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 80.5,
+      "grad_norm_var": 210.66666666666666,
+      "learning_rate": 0.0001,
+      "loss": 11.3038,
+      "loss/crossentropy": 2.3201738983392715,
+      "loss/hidden": 5.0828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.38196625709533694,
+      "step": 450
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 107.5,
+      "grad_norm_var": 284.1666666666667,
+      "learning_rate": 0.0001,
+      "loss": 11.3625,
+      "loss/crossentropy": 2.4791718110442162,
+      "loss/hidden": 4.95546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.36495909169316293,
+      "step": 460
+    },
+    {
+      "epoch": 0.047,
+      "grad_norm": 91.5,
+      "grad_norm_var": 247.39895833333333,
+      "learning_rate": 0.0001,
+      "loss": 11.0542,
+      "loss/crossentropy": 2.3155667960643767,
+      "loss/hidden": 4.93828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.362844867631793,
+      "step": 470
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 95.0,
+      "grad_norm_var": 194.79895833333333,
+      "learning_rate": 0.0001,
+      "loss": 11.2413,
+      "loss/crossentropy": 2.496318203210831,
+      "loss/hidden": 4.840625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3887303464114666,
+      "step": 480
+    },
+    {
+      "epoch": 0.049,
+      "grad_norm": 74.5,
+      "grad_norm_var": 243.840625,
+      "learning_rate": 0.0001,
+      "loss": 10.9416,
+      "loss/crossentropy": 2.385223904252052,
+      "loss/hidden": 4.85234375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3598880790174007,
+      "step": 490
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 79.0,
+      "grad_norm_var": 105.990625,
+      "learning_rate": 0.0001,
+      "loss": 10.9114,
+      "loss/crossentropy": 2.2462552055716514,
+      "loss/hidden": 4.80859375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3265662036836147,
+      "step": 500
+    },
+    {
+      "epoch": 0.051,
+      "grad_norm": 96.5,
+      "grad_norm_var": 138.43229166666666,
+      "learning_rate": 0.0001,
+      "loss": 10.8821,
+      "loss/crossentropy": 2.297148121893406,
+      "loss/hidden": 4.8609375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3467547960579395,
+      "step": 510
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 97.5,
+      "grad_norm_var": 129.365625,
+      "learning_rate": 0.0001,
+      "loss": 10.9299,
+      "loss/crossentropy": 2.4197026968002318,
+      "loss/hidden": 4.7921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3632193084806204,
+      "step": 520
+    },
+    {
+      "epoch": 0.053,
+      "grad_norm": 81.5,
+      "grad_norm_var": 99.47395833333333,
+      "learning_rate": 0.0001,
+      "loss": 10.787,
+      "loss/crossentropy": 2.36982424557209,
+      "loss/hidden": 4.825,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3405680742114782,
+      "step": 530
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 85.5,
+      "grad_norm_var": 48.340625,
+      "learning_rate": 0.0001,
+      "loss": 10.8675,
+      "loss/crossentropy": 2.4611779801547526,
+      "loss/hidden": 4.8625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.36872007288038733,
+      "step": 540
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 93.5,
+      "grad_norm_var": 84.24895833333333,
+      "learning_rate": 0.0001,
+      "loss": 10.64,
+      "loss/crossentropy": 2.1758567959070207,
+      "loss/hidden": 4.7484375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3336840860545635,
+      "step": 550
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 114.0,
+      "grad_norm_var": 129.53098958333334,
+      "learning_rate": 0.0001,
+      "loss": 10.5615,
+      "loss/crossentropy": 2.3970536097884176,
+      "loss/hidden": 4.7625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.34276723079383375,
+      "step": 560
+    },
+    {
+      "epoch": 0.057,
+      "grad_norm": 80.0,
+      "grad_norm_var": 579.57890625,
+      "learning_rate": 0.0001,
+      "loss": 10.8999,
+      "loss/crossentropy": 2.4695185527205465,
+      "loss/hidden": 4.9453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.42829814068973066,
+      "step": 570
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 85.0,
+      "grad_norm_var": 596.9572916666667,
+      "learning_rate": 0.0001,
+      "loss": 10.8802,
+      "loss/crossentropy": 2.3520184576511385,
+      "loss/hidden": 4.790625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3662864986807108,
+      "step": 580
+    },
+    {
+      "epoch": 0.059,
+      "grad_norm": 73.0,
+      "grad_norm_var": 181.69583333333333,
+      "learning_rate": 0.0001,
+      "loss": 10.6744,
+      "loss/crossentropy": 2.2842736929655074,
+      "loss/hidden": 4.71484375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3500846643000841,
+      "step": 590
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 97.0,
+      "grad_norm_var": 160.58307291666668,
+      "learning_rate": 0.0001,
+      "loss": 10.6987,
+      "loss/crossentropy": 2.29906165599823,
+      "loss/hidden": 4.602734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.334361494705081,
+      "step": 600
+    },
+    {
+      "epoch": 0.061,
+      "grad_norm": 89.0,
+      "grad_norm_var": 162.67682291666668,
+      "learning_rate": 0.0001,
+      "loss": 10.6143,
+      "loss/crossentropy": 2.3032930195331573,
+      "loss/hidden": 4.6703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3258141163736582,
+      "step": 610
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 77.5,
+      "grad_norm_var": 97.12916666666666,
+      "learning_rate": 0.0001,
+      "loss": 10.5946,
+      "loss/crossentropy": 2.452244046330452,
+      "loss/hidden": 4.7109375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3432691916823387,
+      "step": 620
+    },
+    {
+      "epoch": 0.063,
+      "grad_norm": 75.5,
+      "grad_norm_var": 227.69973958333333,
+      "learning_rate": 0.0001,
+      "loss": 10.6287,
+      "loss/crossentropy": 2.2894835874438284,
+      "loss/hidden": 4.74609375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.35672005768865345,
+      "step": 630
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 70.0,
+      "grad_norm_var": 541.2322916666667,
+      "learning_rate": 0.0001,
+      "loss": 10.6195,
+      "loss/crossentropy": 2.4114772886037827,
+      "loss/hidden": 4.70546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.35591375902295114,
+      "step": 640
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 77.0,
+      "grad_norm_var": 435.15390625,
+      "learning_rate": 0.0001,
+      "loss": 10.4142,
+      "loss/crossentropy": 2.332440134882927,
+      "loss/hidden": 4.634375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.339809150993824,
+      "step": 650
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 71.5,
+      "grad_norm_var": 118.03307291666667,
+      "learning_rate": 0.0001,
+      "loss": 10.4602,
+      "loss/crossentropy": 2.154422373324633,
+      "loss/hidden": 4.54140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3334257358685136,
+      "step": 660
+    },
+    {
+      "epoch": 0.067,
+      "grad_norm": 73.5,
+      "grad_norm_var": 144.94166666666666,
+      "learning_rate": 0.0001,
+      "loss": 10.5185,
+      "loss/crossentropy": 2.3223402693867685,
+      "loss/hidden": 4.795703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.37188967503607273,
+      "step": 670
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 61.5,
+      "grad_norm_var": 169.65598958333334,
+      "learning_rate": 0.0001,
+      "loss": 10.5323,
+      "loss/crossentropy": 2.332353001832962,
+      "loss/hidden": 4.50625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31948004066944125,
+      "step": 680
+    },
+    {
+      "epoch": 0.069,
+      "grad_norm": 74.0,
+      "grad_norm_var": 155.94140625,
+      "learning_rate": 0.0001,
+      "loss": 10.4359,
+      "loss/crossentropy": 2.4077556908130644,
+      "loss/hidden": 4.623828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.339173823595047,
+      "step": 690
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 82.5,
+      "grad_norm_var": 125.55416666666666,
+      "learning_rate": 0.0001,
+      "loss": 10.4493,
+      "loss/crossentropy": 2.292634981870651,
+      "loss/hidden": 4.571875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3477486100047827,
+      "step": 700
+    },
+    {
+      "epoch": 0.071,
+      "grad_norm": 88.0,
+      "grad_norm_var": 155.84166666666667,
+      "learning_rate": 0.0001,
+      "loss": 10.2041,
+      "loss/crossentropy": 2.4034020826220512,
+      "loss/hidden": 4.53046875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3406600248068571,
+      "step": 710
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 124.0,
+      "grad_norm_var": 230.83307291666668,
+      "learning_rate": 0.0001,
+      "loss": 10.3489,
+      "loss/crossentropy": 2.333241228759289,
+      "loss/hidden": 4.6015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3285223826766014,
+      "step": 720
+    },
+    {
+      "epoch": 0.073,
+      "grad_norm": 71.0,
+      "grad_norm_var": 278.95390625,
+      "learning_rate": 0.0001,
+      "loss": 10.1548,
+      "loss/crossentropy": 2.4066421508789064,
+      "loss/hidden": 4.682421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.338771004602313,
+      "step": 730
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 84.5,
+      "grad_norm_var": 166.85729166666667,
+      "learning_rate": 0.0001,
+      "loss": 10.2647,
+      "loss/crossentropy": 2.2724754482507707,
+      "loss/hidden": 4.567578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3267147310078144,
+      "step": 740
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 67.5,
+      "grad_norm_var": 343.5247395833333,
+      "learning_rate": 0.0001,
+      "loss": 10.2815,
+      "loss/crossentropy": 2.3046080738306047,
+      "loss/hidden": 4.473828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.33236319161951544,
+      "step": 750
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 68.5,
+      "grad_norm_var": 306.540625,
+      "learning_rate": 0.0001,
+      "loss": 10.2479,
+      "loss/crossentropy": 2.2831736013293265,
+      "loss/hidden": 4.62734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3329113606363535,
+      "step": 760
+    },
+    {
+      "epoch": 0.077,
+      "grad_norm": 88.5,
+      "grad_norm_var": 111.57473958333334,
+      "learning_rate": 0.0001,
+      "loss": 10.2161,
+      "loss/crossentropy": 2.3853780582547186,
+      "loss/hidden": 4.541015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31959532871842383,
+      "step": 770
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 80.5,
+      "grad_norm_var": 110.65729166666667,
+      "learning_rate": 0.0001,
+      "loss": 10.2076,
+      "loss/crossentropy": 2.3982744574546815,
+      "loss/hidden": 4.55859375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3542841043323278,
+      "step": 780
+    },
+    {
+      "epoch": 0.079,
+      "grad_norm": 66.0,
+      "grad_norm_var": 275.6322916666667,
+      "learning_rate": 0.0001,
+      "loss": 10.1697,
+      "loss/crossentropy": 2.4292824655771255,
+      "loss/hidden": 4.632421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.36711033545434474,
+      "step": 790
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 57.25,
+      "grad_norm_var": 290.9291666666667,
+      "learning_rate": 0.0001,
+      "loss": 10.2176,
+      "loss/crossentropy": 2.380542576313019,
+      "loss/hidden": 4.509375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3368827097117901,
+      "step": 800
+    },
+    {
+      "epoch": 0.081,
+      "grad_norm": 60.75,
+      "grad_norm_var": 52.67916666666667,
+      "learning_rate": 0.0001,
+      "loss": 10.2311,
+      "loss/crossentropy": 2.4212940514087675,
+      "loss/hidden": 4.55546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.355662290379405,
+      "step": 810
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 60.75,
+      "grad_norm_var": 65.81666666666666,
+      "learning_rate": 0.0001,
+      "loss": 10.1866,
+      "loss/crossentropy": 2.4809795886278154,
+      "loss/hidden": 4.49140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3553234666585922,
+      "step": 820
+    },
+    {
+      "epoch": 0.083,
+      "grad_norm": 56.5,
+      "grad_norm_var": 98.2875,
+      "learning_rate": 0.0001,
+      "loss": 9.9805,
+      "loss/crossentropy": 2.306653854250908,
+      "loss/hidden": 4.40078125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3146494958549738,
+      "step": 830
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 68.0,
+      "grad_norm_var": 38.51015625,
+      "learning_rate": 0.0001,
+      "loss": 10.1087,
+      "loss/crossentropy": 2.250006601214409,
+      "loss/hidden": 4.422265625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30200174674391744,
+      "step": 840
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 70.5,
+      "grad_norm_var": 43.483072916666664,
+      "learning_rate": 0.0001,
+      "loss": 10.0526,
+      "loss/crossentropy": 2.211633677780628,
+      "loss/hidden": 4.47421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31178686060011385,
+      "step": 850
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 61.0,
+      "grad_norm_var": 41.545572916666664,
+      "learning_rate": 0.0001,
+      "loss": 10.1915,
+      "loss/crossentropy": 2.5281356513500213,
+      "loss/hidden": 4.389453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.34625968635082244,
+      "step": 860
+    },
+    {
+      "epoch": 0.087,
+      "grad_norm": 72.5,
+      "grad_norm_var": 54.475,
+      "learning_rate": 0.0001,
+      "loss": 10.0007,
+      "loss/crossentropy": 2.4020907685160635,
+      "loss/hidden": 4.326171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.32252500094473363,
+      "step": 870
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 142.0,
+      "grad_norm_var": 499.1375,
+      "learning_rate": 0.0001,
+      "loss": 9.99,
+      "loss/crossentropy": 2.384984764456749,
+      "loss/hidden": 4.38515625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3189360786229372,
+      "step": 880
+    },
+    {
+      "epoch": 0.089,
+      "grad_norm": 57.75,
+      "grad_norm_var": 527.23515625,
+      "learning_rate": 0.0001,
+      "loss": 9.9879,
+      "loss/crossentropy": 2.3401281625032424,
+      "loss/hidden": 4.46328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3382201848551631,
+      "step": 890
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 71.5,
+      "grad_norm_var": 95.97265625,
+      "learning_rate": 0.0001,
+      "loss": 9.9352,
+      "loss/crossentropy": 2.3969784706830977,
+      "loss/hidden": 4.384375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.336395762488246,
+      "step": 900
+    },
+    {
+      "epoch": 0.091,
+      "grad_norm": 79.0,
+      "grad_norm_var": 144.96666666666667,
+      "learning_rate": 0.0001,
+      "loss": 10.149,
+      "loss/crossentropy": 2.4599110893905163,
+      "loss/hidden": 4.30703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3240171395242214,
+      "step": 910
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 65.5,
+      "grad_norm_var": 119.2375,
+      "learning_rate": 0.0001,
+      "loss": 9.9634,
+      "loss/crossentropy": 2.4210876494646074,
+      "loss/hidden": 4.30390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.32166178375482557,
+      "step": 920
+    },
+    {
+      "epoch": 0.093,
+      "grad_norm": 63.0,
+      "grad_norm_var": 41.47083333333333,
+      "learning_rate": 0.0001,
+      "loss": 9.744,
+      "loss/crossentropy": 2.2256636448204516,
+      "loss/hidden": 4.284765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29795306362211704,
+      "step": 930
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 53.5,
+      "grad_norm_var": 192.55807291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.8636,
+      "loss/crossentropy": 2.297808923572302,
+      "loss/hidden": 4.31640625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30742434673011304,
+      "step": 940
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 61.0,
+      "grad_norm_var": 81.95729166666666,
+      "learning_rate": 0.0001,
+      "loss": 9.798,
+      "loss/crossentropy": 2.3219059616327287,
+      "loss/hidden": 4.211328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30037002861499784,
+      "step": 950
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 56.75,
+      "grad_norm_var": 61.55807291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.7449,
+      "loss/crossentropy": 2.3104363679885864,
+      "loss/hidden": 4.388671875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.327311984449625,
+      "step": 960
+    },
+    {
+      "epoch": 0.097,
+      "grad_norm": 60.0,
+      "grad_norm_var": 56.18932291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.9668,
+      "loss/crossentropy": 2.308886554837227,
+      "loss/hidden": 4.407421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3183224782347679,
+      "step": 970
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 66.5,
+      "grad_norm_var": 42.05416666666667,
+      "learning_rate": 0.0001,
+      "loss": 9.7807,
+      "loss/crossentropy": 2.3363482102751734,
+      "loss/hidden": 4.2921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3384779039770365,
+      "step": 980
+    },
+    {
+      "epoch": 0.099,
+      "grad_norm": 57.25,
+      "grad_norm_var": 56.891666666666666,
+      "learning_rate": 0.0001,
+      "loss": 9.7501,
+      "loss/crossentropy": 2.1767295479774473,
+      "loss/hidden": 4.466015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31410733237862587,
+      "step": 990
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 50.25,
+      "grad_norm_var": 75.85598958333334,
+      "learning_rate": 0.0001,
+      "loss": 9.9273,
+      "loss/crossentropy": 2.505411845445633,
+      "loss/hidden": 4.36015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.33212706074118614,
+      "step": 1000
+    },
+    {
+      "epoch": 0.101,
+      "grad_norm": 77.5,
+      "grad_norm_var": 196.21848958333334,
+      "learning_rate": 0.0001,
+      "loss": 9.9237,
+      "loss/crossentropy": 2.3281257838010787,
+      "loss/hidden": 4.35546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.32293859515339135,
+      "step": 1010
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 63.25,
+      "grad_norm_var": 167.42395833333333,
+      "learning_rate": 0.0001,
+      "loss": 9.7592,
+      "loss/crossentropy": 2.3165650010108947,
+      "loss/hidden": 4.32890625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31759811006486416,
+      "step": 1020
+    },
+    {
+      "epoch": 0.103,
+      "grad_norm": 60.0,
+      "grad_norm_var": 153.80833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.7366,
+      "loss/crossentropy": 2.3203016728162766,
+      "loss/hidden": 4.28515625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31944827549159527,
+      "step": 1030
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 66.5,
+      "grad_norm_var": 3319.3958333333335,
+      "learning_rate": 0.0001,
+      "loss": 10.0035,
+      "loss/crossentropy": 2.4188640087842943,
+      "loss/hidden": 4.38828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3581279247999191,
+      "step": 1040
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 60.25,
+      "grad_norm_var": 3338.31640625,
+      "learning_rate": 0.0001,
+      "loss": 9.6837,
+      "loss/crossentropy": 2.2860016629099844,
+      "loss/hidden": 4.325390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.318701284006238,
+      "step": 1050
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 74.0,
+      "grad_norm_var": 112.4,
+      "learning_rate": 0.0001,
+      "loss": 9.517,
+      "loss/crossentropy": 2.4143033266067504,
+      "loss/hidden": 4.319140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3072842717170715,
+      "step": 1060
+    },
+    {
+      "epoch": 0.107,
+      "grad_norm": 71.5,
+      "grad_norm_var": 68.60598958333334,
+      "learning_rate": 0.0001,
+      "loss": 9.8549,
+      "loss/crossentropy": 2.351083371043205,
+      "loss/hidden": 4.398046875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.33429058492183683,
+      "step": 1070
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 53.25,
+      "grad_norm_var": 43.83229166666667,
+      "learning_rate": 0.0001,
+      "loss": 9.7738,
+      "loss/crossentropy": 2.4011227190494537,
+      "loss/hidden": 4.29453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3128178097307682,
+      "step": 1080
+    },
+    {
+      "epoch": 0.109,
+      "grad_norm": 72.0,
+      "grad_norm_var": 34.82890625,
+      "learning_rate": 0.0001,
+      "loss": 9.7432,
+      "loss/crossentropy": 2.310031126439571,
+      "loss/hidden": 4.38984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3273486144840717,
+      "step": 1090
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 66.5,
+      "grad_norm_var": 111.64895833333334,
+      "learning_rate": 0.0001,
+      "loss": 9.6743,
+      "loss/crossentropy": 2.3055127263069153,
+      "loss/hidden": 4.21796875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.32233874313533306,
+      "step": 1100
+    },
+    {
+      "epoch": 0.111,
+      "grad_norm": 51.5,
+      "grad_norm_var": 46.70729166666667,
+      "learning_rate": 0.0001,
+      "loss": 9.8026,
+      "loss/crossentropy": 2.314373381435871,
+      "loss/hidden": 4.256640625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3083756107836962,
+      "step": 1110
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 57.75,
+      "grad_norm_var": 7292.4375,
+      "learning_rate": 0.0001,
+      "loss": 9.7291,
+      "loss/crossentropy": 2.5138203650712967,
+      "loss/hidden": 4.19921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30809955932199956,
+      "step": 1120
+    },
+    {
+      "epoch": 0.113,
+      "grad_norm": 56.5,
+      "grad_norm_var": 29.190625,
+      "learning_rate": 0.0001,
+      "loss": 9.6823,
+      "loss/crossentropy": 2.2719234466552733,
+      "loss/hidden": 4.294140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3143883816897869,
+      "step": 1130
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 60.5,
+      "grad_norm_var": 45.925,
+      "learning_rate": 0.0001,
+      "loss": 9.7564,
+      "loss/crossentropy": 2.4254489660263063,
+      "loss/hidden": 4.261328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3154076419770718,
+      "step": 1140
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 56.0,
+      "grad_norm_var": 71.74583333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.7001,
+      "loss/crossentropy": 2.28252642005682,
+      "loss/hidden": 4.323046875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3203336976468563,
+      "step": 1150
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 67.0,
+      "grad_norm_var": 46.040625,
+      "learning_rate": 0.0001,
+      "loss": 9.7436,
+      "loss/crossentropy": 2.391976150870323,
+      "loss/hidden": 4.225390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31455044373869895,
+      "step": 1160
+    },
+    {
+      "epoch": 0.117,
+      "grad_norm": 46.0,
+      "grad_norm_var": 47.06640625,
+      "learning_rate": 0.0001,
+      "loss": 9.5622,
+      "loss/crossentropy": 2.3361207604408265,
+      "loss/hidden": 4.19296875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30060703232884406,
+      "step": 1170
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 56.25,
+      "grad_norm_var": 49.264322916666664,
+      "learning_rate": 0.0001,
+      "loss": 9.6834,
+      "loss/crossentropy": 2.297483670711517,
+      "loss/hidden": 4.2890625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2907493541017175,
+      "step": 1180
+    },
+    {
+      "epoch": 0.119,
+      "grad_norm": 52.5,
+      "grad_norm_var": 12.27890625,
+      "learning_rate": 0.0001,
+      "loss": 9.6207,
+      "loss/crossentropy": 2.2364058643579483,
+      "loss/hidden": 4.277734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3097097765654325,
+      "step": 1190
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 68.5,
+      "grad_norm_var": 35.055989583333336,
+      "learning_rate": 0.0001,
+      "loss": 9.6018,
+      "loss/crossentropy": 2.2412969201803206,
+      "loss/hidden": 4.287109375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31851550191640854,
+      "step": 1200
+    },
+    {
+      "epoch": 0.121,
+      "grad_norm": 60.5,
+      "grad_norm_var": 25.774739583333332,
+      "learning_rate": 0.0001,
+      "loss": 9.6979,
+      "loss/crossentropy": 2.3062032952904703,
+      "loss/hidden": 4.258984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3124631106853485,
+      "step": 1210
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 59.25,
+      "grad_norm_var": 20.026822916666667,
+      "learning_rate": 0.0001,
+      "loss": 9.7129,
+      "loss/crossentropy": 2.4036868065595627,
+      "loss/hidden": 4.20234375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31101155243813994,
+      "step": 1220
+    },
+    {
+      "epoch": 0.123,
+      "grad_norm": 53.25,
+      "grad_norm_var": 75.30833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.7047,
+      "loss/crossentropy": 2.3730016142129897,
+      "loss/hidden": 4.193359375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3105484452098608,
+      "step": 1230
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 62.25,
+      "grad_norm_var": 33.27682291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.6313,
+      "loss/crossentropy": 2.2872567594051363,
+      "loss/hidden": 4.319140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3244694545865059,
+      "step": 1240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 61.25,
+      "grad_norm_var": 25.673958333333335,
+      "learning_rate": 0.0001,
+      "loss": 9.6217,
+      "loss/crossentropy": 2.3013710603117943,
+      "loss/hidden": 4.29140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.32178852558135984,
+      "step": 1250
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 49.5,
+      "grad_norm_var": 46.97265625,
+      "learning_rate": 0.0001,
+      "loss": 9.6151,
+      "loss/crossentropy": 2.2743802405893803,
+      "loss/hidden": 4.19921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3104738780297339,
+      "step": 1260
+    },
+    {
+      "epoch": 0.127,
+      "grad_norm": 52.25,
+      "grad_norm_var": 318.94557291666666,
+      "learning_rate": 0.0001,
+      "loss": 9.635,
+      "loss/crossentropy": 2.2751111879944803,
+      "loss/hidden": 4.17578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2947248375043273,
+      "step": 1270
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 59.5,
+      "grad_norm_var": 201.26848958333332,
+      "learning_rate": 0.0001,
+      "loss": 9.605,
+      "loss/crossentropy": 2.3590754181146623,
+      "loss/hidden": 4.116015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29773430675268175,
+      "step": 1280
+    },
+    {
+      "epoch": 0.129,
+      "grad_norm": 50.0,
+      "grad_norm_var": 25.795833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.4314,
+      "loss/crossentropy": 2.165515697002411,
+      "loss/hidden": 4.148046875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2729496695101261,
+      "step": 1290
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 51.5,
+      "grad_norm_var": 65.69557291666666,
+      "learning_rate": 0.0001,
+      "loss": 9.4579,
+      "loss/crossentropy": 2.425456903874874,
+      "loss/hidden": 4.1140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3002984166145325,
+      "step": 1300
+    },
+    {
+      "epoch": 0.131,
+      "grad_norm": 55.75,
+      "grad_norm_var": 74.63515625,
+      "learning_rate": 0.0001,
+      "loss": 9.562,
+      "loss/crossentropy": 2.3212677478790282,
+      "loss/hidden": 4.209765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28645528480410576,
+      "step": 1310
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 44.75,
+      "grad_norm_var": 39.139322916666664,
+      "learning_rate": 0.0001,
+      "loss": 9.305,
+      "loss/crossentropy": 2.2911602184176445,
+      "loss/hidden": 4.133984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28404638059437276,
+      "step": 1320
+    },
+    {
+      "epoch": 0.133,
+      "grad_norm": 52.25,
+      "grad_norm_var": 76.19583333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.3122,
+      "loss/crossentropy": 2.3109163105487824,
+      "loss/hidden": 4.137109375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2864396806806326,
+      "step": 1330
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 47.0,
+      "grad_norm_var": 41.66015625,
+      "learning_rate": 0.0001,
+      "loss": 9.4629,
+      "loss/crossentropy": 2.353537403047085,
+      "loss/hidden": 4.08203125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2971150416880846,
+      "step": 1340
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 46.25,
+      "grad_norm_var": 45.31848958333333,
+      "learning_rate": 0.0001,
+      "loss": 9.365,
+      "loss/crossentropy": 2.3774181246757506,
+      "loss/hidden": 4.09296875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2799839396029711,
+      "step": 1350
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 51.0,
+      "grad_norm_var": 17.93515625,
+      "learning_rate": 0.0001,
+      "loss": 9.3498,
+      "loss/crossentropy": 2.246833881735802,
+      "loss/hidden": 4.18828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2903384942561388,
+      "step": 1360
+    },
+    {
+      "epoch": 0.137,
+      "grad_norm": 51.25,
+      "grad_norm_var": 12.420833333333333,
+      "learning_rate": 0.0001,
+      "loss": 9.4976,
+      "loss/crossentropy": 2.453240838646889,
+      "loss/hidden": 4.173828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3144164770841599,
+      "step": 1370
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 70.0,
+      "grad_norm_var": 2011.0322916666667,
+      "learning_rate": 0.0001,
+      "loss": 9.5884,
+      "loss/crossentropy": 2.174116183817387,
+      "loss/hidden": 4.24921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2923248626291752,
+      "step": 1380
+    },
+    {
+      "epoch": 0.139,
+      "grad_norm": 53.75,
+      "grad_norm_var": 1988.8833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.5249,
+      "loss/crossentropy": 2.3638354018330574,
+      "loss/hidden": 4.184765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3066251628100872,
+      "step": 1390
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 55.5,
+      "grad_norm_var": 22.779166666666665,
+      "learning_rate": 0.0001,
+      "loss": 9.3528,
+      "loss/crossentropy": 2.4166768550872804,
+      "loss/hidden": 4.123828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29636494982987643,
+      "step": 1400
+    },
+    {
+      "epoch": 0.141,
+      "grad_norm": 60.5,
+      "grad_norm_var": 66.59348958333334,
+      "learning_rate": 0.0001,
+      "loss": 9.5339,
+      "loss/crossentropy": 2.3475931867957116,
+      "loss/hidden": 4.1953125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30608872696757317,
+      "step": 1410
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 51.25,
+      "grad_norm_var": 62.49140625,
+      "learning_rate": 0.0001,
+      "loss": 9.3342,
+      "loss/crossentropy": 2.1785849004983904,
+      "loss/hidden": 4.161328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27641028352081776,
+      "step": 1420
+    },
+    {
+      "epoch": 0.143,
+      "grad_norm": 54.25,
+      "grad_norm_var": 30.154166666666665,
+      "learning_rate": 0.0001,
+      "loss": 9.3898,
+      "loss/crossentropy": 2.3990818440914152,
+      "loss/hidden": 4.18359375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2944341886788607,
+      "step": 1430
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 51.75,
+      "grad_norm_var": 38.93932291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.4628,
+      "loss/crossentropy": 2.4946817860007284,
+      "loss/hidden": 4.198828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31867978498339655,
+      "step": 1440
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 53.75,
+      "grad_norm_var": 33.9,
+      "learning_rate": 0.0001,
+      "loss": 9.3416,
+      "loss/crossentropy": 2.2067521095275877,
+      "loss/hidden": 4.235546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2976540043950081,
+      "step": 1450
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 60.75,
+      "grad_norm_var": 142.08229166666666,
+      "learning_rate": 0.0001,
+      "loss": 9.4716,
+      "loss/crossentropy": 2.4361192852258684,
+      "loss/hidden": 4.1140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2877715673297644,
+      "step": 1460
+    },
+    {
+      "epoch": 0.147,
+      "grad_norm": 58.75,
+      "grad_norm_var": 44.35,
+      "learning_rate": 0.0001,
+      "loss": 9.4006,
+      "loss/crossentropy": 2.239429622516036,
+      "loss/hidden": 4.026171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27844256814569235,
+      "step": 1470
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 45.0,
+      "grad_norm_var": 33.95390625,
+      "learning_rate": 0.0001,
+      "loss": 9.3993,
+      "loss/crossentropy": 2.0759536787867545,
+      "loss/hidden": 4.068359375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2688772227615118,
+      "step": 1480
+    },
+    {
+      "epoch": 0.149,
+      "grad_norm": 51.75,
+      "grad_norm_var": 25.795833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.3786,
+      "loss/crossentropy": 2.286362998187542,
+      "loss/hidden": 4.15078125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2942257083952427,
+      "step": 1490
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 46.75,
+      "grad_norm_var": 20.520833333333332,
+      "learning_rate": 0.0001,
+      "loss": 9.2903,
+      "loss/crossentropy": 2.312733788788319,
+      "loss/hidden": 3.971484375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2691910218447447,
+      "step": 1500
+    },
+    {
+      "epoch": 0.151,
+      "grad_norm": 50.25,
+      "grad_norm_var": 28.290625,
+      "learning_rate": 0.0001,
+      "loss": 9.3076,
+      "loss/crossentropy": 2.2467628076672552,
+      "loss/hidden": 4.105078125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2887777745723724,
+      "step": 1510
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 63.5,
+      "grad_norm_var": 33.73098958333333,
+      "learning_rate": 0.0001,
+      "loss": 9.4203,
+      "loss/crossentropy": 2.372379180788994,
+      "loss/hidden": 4.07578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3087839350104332,
+      "step": 1520
+    },
+    {
+      "epoch": 0.153,
+      "grad_norm": 45.5,
+      "grad_norm_var": 40.108333333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.3215,
+      "loss/crossentropy": 2.3452367037534714,
+      "loss/hidden": 4.210546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3159611392766237,
+      "step": 1530
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 58.25,
+      "grad_norm_var": 27.539322916666666,
+      "learning_rate": 0.0001,
+      "loss": 9.3755,
+      "loss/crossentropy": 2.3029753446578978,
+      "loss/hidden": 3.999609375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2623455457389355,
+      "step": 1540
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 51.75,
+      "grad_norm_var": 26.9,
+      "learning_rate": 0.0001,
+      "loss": 9.3578,
+      "loss/crossentropy": 2.3988554388284684,
+      "loss/hidden": 4.08828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2846154376864433,
+      "step": 1550
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 91.0,
+      "grad_norm_var": 1307.8372395833333,
+      "learning_rate": 0.0001,
+      "loss": 9.432,
+      "loss/crossentropy": 2.343544365465641,
+      "loss/hidden": 4.021875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2907770898193121,
+      "step": 1560
+    },
+    {
+      "epoch": 0.157,
+      "grad_norm": 52.0,
+      "grad_norm_var": 170.62890625,
+      "learning_rate": 0.0001,
+      "loss": 9.3432,
+      "loss/crossentropy": 2.173108433187008,
+      "loss/hidden": 4.10859375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28518917988985776,
+      "step": 1570
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 42.0,
+      "grad_norm_var": 47.56015625,
+      "learning_rate": 0.0001,
+      "loss": 9.367,
+      "loss/crossentropy": 2.2230691239237785,
+      "loss/hidden": 4.23515625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30039387457072736,
+      "step": 1580
+    },
+    {
+      "epoch": 0.159,
+      "grad_norm": 72.0,
+      "grad_norm_var": 1.226104970407838e+18,
+      "learning_rate": 0.0001,
+      "loss": 9.3564,
+      "loss/crossentropy": 2.263391149044037,
+      "loss/hidden": 4.10625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2923804897814989,
+      "step": 1590
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 52.5,
+      "grad_norm_var": 1.2261049681378806e+18,
+      "learning_rate": 0.0001,
+      "loss": 9.4959,
+      "loss/crossentropy": 2.113241518288851,
+      "loss/hidden": 4.087109375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2759646028280258,
+      "step": 1600
+    },
+    {
+      "epoch": 0.161,
+      "grad_norm": 66.0,
+      "grad_norm_var": 734.1489583333333,
+      "learning_rate": 0.0001,
+      "loss": 9.4743,
+      "loss/crossentropy": 2.3895165085792542,
+      "loss/hidden": 4.059765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2987998936325312,
+      "step": 1610
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 44.75,
+      "grad_norm_var": 50.00182291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.1919,
+      "loss/crossentropy": 2.251766300201416,
+      "loss/hidden": 4.04375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2781111396849155,
+      "step": 1620
+    },
+    {
+      "epoch": 0.163,
+      "grad_norm": 52.75,
+      "grad_norm_var": 437.49583333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.4572,
+      "loss/crossentropy": 2.382322034239769,
+      "loss/hidden": 4.07734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31318275928497313,
+      "step": 1630
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 61.0,
+      "grad_norm_var": 40.301822916666666,
+      "learning_rate": 0.0001,
+      "loss": 9.2668,
+      "loss/crossentropy": 2.1683703124523164,
+      "loss/hidden": 4.07578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.283413190767169,
+      "step": 1640
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 42.75,
+      "grad_norm_var": 57.307291666666664,
+      "learning_rate": 0.0001,
+      "loss": 9.339,
+      "loss/crossentropy": 2.3430400043725967,
+      "loss/hidden": 4.036328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.287694800645113,
+      "step": 1650
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 46.75,
+      "grad_norm_var": 65.52395833333334,
+      "learning_rate": 0.0001,
+      "loss": 9.3768,
+      "loss/crossentropy": 2.2867416352033616,
+      "loss/hidden": 4.017578125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29683431759476664,
+      "step": 1660
+    },
+    {
+      "epoch": 0.167,
+      "grad_norm": 52.5,
+      "grad_norm_var": 61.18932291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.2451,
+      "loss/crossentropy": 2.3707614041864873,
+      "loss/hidden": 4.06015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29184688804671166,
+      "step": 1670
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 51.75,
+      "grad_norm_var": 20.895572916666666,
+      "learning_rate": 0.0001,
+      "loss": 9.3601,
+      "loss/crossentropy": 2.3268392831087112,
+      "loss/hidden": 4.12734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29570323824882505,
+      "step": 1680
+    },
+    {
+      "epoch": 0.169,
+      "grad_norm": 44.0,
+      "grad_norm_var": 10.290625,
+      "learning_rate": 0.0001,
+      "loss": 9.4214,
+      "loss/crossentropy": 2.324131193757057,
+      "loss/hidden": 4.1984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3133995305746794,
+      "step": 1690
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 58.25,
+      "grad_norm_var": 19.124739583333334,
+      "learning_rate": 0.0001,
+      "loss": 9.2465,
+      "loss/crossentropy": 2.35849623978138,
+      "loss/hidden": 4.00703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2762619823217392,
+      "step": 1700
+    },
+    {
+      "epoch": 0.171,
+      "grad_norm": 45.75,
+      "grad_norm_var": 53.89895833333333,
+      "learning_rate": 0.0001,
+      "loss": 9.1951,
+      "loss/crossentropy": 2.3914038598537446,
+      "loss/hidden": 3.9984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2871177852153778,
+      "step": 1710
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 43.25,
+      "grad_norm_var": 16.479166666666668,
+      "learning_rate": 0.0001,
+      "loss": 9.1669,
+      "loss/crossentropy": 2.152750685811043,
+      "loss/hidden": 4.100390625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28708020225167274,
+      "step": 1720
+    },
+    {
+      "epoch": 0.173,
+      "grad_norm": 49.25,
+      "grad_norm_var": 13.45390625,
+      "learning_rate": 0.0001,
+      "loss": 9.1015,
+      "loss/crossentropy": 2.2946193665266037,
+      "loss/hidden": 4.085546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3062314610928297,
+      "step": 1730
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 46.5,
+      "grad_norm_var": 22.473958333333332,
+      "learning_rate": 0.0001,
+      "loss": 9.1287,
+      "loss/crossentropy": 2.1538643553853034,
+      "loss/hidden": 3.9421875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2666194221004844,
+      "step": 1740
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 47.0,
+      "grad_norm_var": 32.62057291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.411,
+      "loss/crossentropy": 2.387891933321953,
+      "loss/hidden": 4.14921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29542505368590355,
+      "step": 1750
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 45.25,
+      "grad_norm_var": 26.92265625,
+      "learning_rate": 0.0001,
+      "loss": 9.2833,
+      "loss/crossentropy": 2.3024097591638566,
+      "loss/hidden": 4.03984375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29066667445003985,
+      "step": 1760
+    },
+    {
+      "epoch": 0.177,
+      "grad_norm": 53.5,
+      "grad_norm_var": 17.832291666666666,
+      "learning_rate": 0.0001,
+      "loss": 9.2665,
+      "loss/crossentropy": 2.4454205125570296,
+      "loss/hidden": 3.955859375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2910691563040018,
+      "step": 1770
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 42.25,
+      "grad_norm_var": 29.865625,
+      "learning_rate": 0.0001,
+      "loss": 9.1701,
+      "loss/crossentropy": 2.2966391056776048,
+      "loss/hidden": 4.027734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2789210833609104,
+      "step": 1780
+    },
+    {
+      "epoch": 0.179,
+      "grad_norm": 48.25,
+      "grad_norm_var": 17.548958333333335,
+      "learning_rate": 0.0001,
+      "loss": 9.1992,
+      "loss/crossentropy": 2.395502945780754,
+      "loss/hidden": 3.934765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2776679117232561,
+      "step": 1790
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 40.75,
+      "grad_norm_var": 13.282291666666667,
+      "learning_rate": 0.0001,
+      "loss": 9.1046,
+      "loss/crossentropy": 2.22285817861557,
+      "loss/hidden": 3.9046875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.26667180880904195,
+      "step": 1800
+    },
+    {
+      "epoch": 0.181,
+      "grad_norm": 36.25,
+      "grad_norm_var": 34.90807291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.3204,
+      "loss/crossentropy": 2.3842350512743,
+      "loss/hidden": 4.009375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.300260554254055,
+      "step": 1810
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 46.75,
+      "grad_norm_var": 27.77890625,
+      "learning_rate": 0.0001,
+      "loss": 9.0943,
+      "loss/crossentropy": 2.274762773513794,
+      "loss/hidden": 4.01328125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28360783979296683,
+      "step": 1820
+    },
+    {
+      "epoch": 0.183,
+      "grad_norm": 55.5,
+      "grad_norm_var": 27.298958333333335,
+      "learning_rate": 0.0001,
+      "loss": 9.1699,
+      "loss/crossentropy": 2.1643219627439976,
+      "loss/hidden": 3.9921875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.267458438500762,
+      "step": 1830
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 49.75,
+      "grad_norm_var": 43.94583333333333,
+      "learning_rate": 0.0001,
+      "loss": 9.3022,
+      "loss/crossentropy": 2.464679929614067,
+      "loss/hidden": 3.9546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.29758369028568266,
+      "step": 1840
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 51.0,
+      "grad_norm_var": 37.90807291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.1863,
+      "loss/crossentropy": 2.3199010998010636,
+      "loss/hidden": 3.99453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27702242247760295,
+      "step": 1850
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 46.5,
+      "grad_norm_var": 40.920833333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.2872,
+      "loss/crossentropy": 2.4041683062911035,
+      "loss/hidden": 4.09140625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.30005627647042277,
+      "step": 1860
+    },
+    {
+      "epoch": 0.187,
+      "grad_norm": 39.75,
+      "grad_norm_var": 40.723958333333336,
+      "learning_rate": 0.0001,
+      "loss": 9.1081,
+      "loss/crossentropy": 2.273802790045738,
+      "loss/hidden": 4.175,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.3045934235677123,
+      "step": 1870
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 43.25,
+      "grad_norm_var": 33.35729166666667,
+      "learning_rate": 0.0001,
+      "loss": 9.106,
+      "loss/crossentropy": 2.3607766672968866,
+      "loss/hidden": 3.9765625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28193066976964476,
+      "step": 1880
+    },
+    {
+      "epoch": 0.189,
+      "grad_norm": 48.25,
+      "grad_norm_var": 14.915625,
+      "learning_rate": 0.0001,
+      "loss": 9.1437,
+      "loss/crossentropy": 2.2798361241817475,
+      "loss/hidden": 3.9890625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2721746701747179,
+      "step": 1890
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 44.0,
+      "grad_norm_var": 21.223958333333332,
+      "learning_rate": 0.0001,
+      "loss": 9.0972,
+      "loss/crossentropy": 2.21695294380188,
+      "loss/hidden": 4.0015625,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2832322970032692,
+      "step": 1900
+    },
+    {
+      "epoch": 0.191,
+      "grad_norm": 39.5,
+      "grad_norm_var": 27.808333333333334,
+      "learning_rate": 0.0001,
+      "loss": 9.1587,
+      "loss/crossentropy": 2.1728454776108266,
+      "loss/hidden": 3.98828125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27170457877218723,
+      "step": 1910
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 41.75,
+      "grad_norm_var": 13.315625,
+      "learning_rate": 0.0001,
+      "loss": 9.1326,
+      "loss/crossentropy": 2.154237084835768,
+      "loss/hidden": 4.063671875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27950075305998323,
+      "step": 1920
+    },
+    {
+      "epoch": 0.193,
+      "grad_norm": 43.0,
+      "grad_norm_var": 25.240625,
+      "learning_rate": 0.0001,
+      "loss": 9.1013,
+      "loss/crossentropy": 2.2507698431611063,
+      "loss/hidden": 4.01171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2808088269084692,
+      "step": 1930
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 49.25,
+      "grad_norm_var": 22.832291666666666,
+      "learning_rate": 0.0001,
+      "loss": 9.2429,
+      "loss/crossentropy": 2.288056728243828,
+      "loss/hidden": 4.1546875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.31668607220053674,
+      "step": 1940
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 48.5,
+      "grad_norm_var": 58.09557291666667,
+      "learning_rate": 0.0001,
+      "loss": 9.1742,
+      "loss/crossentropy": 2.2107961744070055,
+      "loss/hidden": 4.05078125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2858551822602749,
+      "step": 1950
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 39.25,
+      "grad_norm_var": 49.50390625,
+      "learning_rate": 0.0001,
+      "loss": 9.1293,
+      "loss/crossentropy": 2.224529256671667,
+      "loss/hidden": 3.9703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.27973891496658326,
+      "step": 1960
+    },
+    {
+      "epoch": 0.197,
+      "grad_norm": 39.25,
+      "grad_norm_var": 13.890625,
+      "learning_rate": 0.0001,
+      "loss": 9.0689,
+      "loss/crossentropy": 2.363737019896507,
+      "loss/hidden": 4.027734375,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2919711694121361,
+      "step": 1970
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 55.75,
+      "grad_norm_var": 26.655989583333334,
+      "learning_rate": 0.0001,
+      "loss": 9.2228,
+      "loss/crossentropy": 2.3380469545722007,
+      "loss/hidden": 4.0171875,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28581551983952524,
+      "step": 1980
+    },
+    {
+      "epoch": 0.199,
+      "grad_norm": 45.0,
+      "grad_norm_var": 27.357291666666665,
+      "learning_rate": 0.0001,
+      "loss": 9.173,
+      "loss/crossentropy": 2.43135461807251,
+      "loss/hidden": 3.970703125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.28222124874591825,
+      "step": 1990
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 44.5,
+      "grad_norm_var": 16.04140625,
+      "learning_rate": 0.0001,
+      "loss": 9.1554,
+      "loss/crossentropy": 2.4415812104940415,
+      "loss/hidden": 4.064453125,
+      "loss/jsd": 0.0,
+      "loss/logits": 0.2984179027378559,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.715020064017613e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a25da17eff495e1e71f9cb40dc8e2af9b7ac9d1878cc59e1f0d23bc294798cd
+size 5496