Upload Gemma 4 native SFT model

.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

chat_template.jinja

@@ -0,0 +1,354 @@
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
+                        {%- for tc in message['tool_calls'] -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not has_content) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+        {%- if not enable_thinking | default(false) -%}
+            {{- '<|channel>thought\n<channel|>' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,114 @@
+{
+  "architectures": [
+    "Gemma4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_k_eq_v": true,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "enable_moe_block": false,
+  "eos_token_id": 1,
+  "expert_intermediate_size": null,
+  "final_logit_softcapping": 30.0,
+  "global_head_dim": 512,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 5376,
+  "hidden_size_per_layer_input": 0,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "model_type": "gemma4_text",
+  "moe_intermediate_size": null,
+  "num_attention_heads": 32,
+  "num_experts": null,
+  "num_global_key_value_heads": 4,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 16,
+  "num_kv_shared_layers": 0,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 1000000.0,
+      "rope_type": "proportional"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 1024,
+  "tie_word_embeddings": true,
+  "top_k_experts": null,
+  "transformers_version": "5.5.0",
+  "use_bidirectional_attention": "vision",
+  "use_cache": false,
+  "use_double_wide_mlp": false,
+  "vocab_size": 262144,
+  "vocab_size_per_layer_input": 262144
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38dcec721677d382b8ac147be48ce7ea76b8b94d95858aa2a438a230a93e78d
+size 49899519758

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd270eb6078197e94be52e9b4178e68a2c4ad9c21fb22bc2a849ec697d16a9a
+size 49987959420

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0571f709c1bec1d235ff118cb051acc23c7bc8ce28d0f779bc5adba7b190ebc4
+size 28539143502

model.safetensors.index.json

@@ -0,0 +1,841 @@
+{
+  "metadata": {
+    "total_parameters": 4013328928,
+    "total_size": 128426525816
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.layer_scalar": "model-00002-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.layer_scalar": "model-00003-of-00003.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.layer_scalar": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,3604 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00196078431372549,
+      "grad_norm": 138868.515625,
+      "learning_rate": 0.0,
+      "loss": 17.658615112304688,
+      "step": 1
+    },
+    {
+      "epoch": 0.00392156862745098,
+      "grad_norm": 14902.44140625,
+      "learning_rate": 3.2258064516129035e-07,
+      "loss": 15.435331344604492,
+      "step": 2
+    },
+    {
+      "epoch": 0.0058823529411764705,
+      "grad_norm": 18682.611328125,
+      "learning_rate": 6.451612903225807e-07,
+      "loss": 17.053977966308594,
+      "step": 3
+    },
+    {
+      "epoch": 0.00784313725490196,
+      "grad_norm": 25779.986328125,
+      "learning_rate": 9.67741935483871e-07,
+      "loss": 17.117534637451172,
+      "step": 4
+    },
+    {
+      "epoch": 0.00980392156862745,
+      "grad_norm": 15318.7373046875,
+      "learning_rate": 1.2903225806451614e-06,
+      "loss": 17.542219161987305,
+      "step": 5
+    },
+    {
+      "epoch": 0.011764705882352941,
+      "grad_norm": 19811.609375,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 17.963178634643555,
+      "step": 6
+    },
+    {
+      "epoch": 0.013725490196078431,
+      "grad_norm": 9440.365234375,
+      "learning_rate": 1.935483870967742e-06,
+      "loss": 13.022825241088867,
+      "step": 7
+    },
+    {
+      "epoch": 0.01568627450980392,
+      "grad_norm": 88075.3046875,
+      "learning_rate": 2.2580645161290324e-06,
+      "loss": 16.652803421020508,
+      "step": 8
+    },
+    {
+      "epoch": 0.01764705882352941,
+      "grad_norm": 20173.8203125,
+      "learning_rate": 2.580645161290323e-06,
+      "loss": 16.681129455566406,
+      "step": 9
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 20974.09765625,
+      "learning_rate": 2.903225806451613e-06,
+      "loss": 14.24374771118164,
+      "step": 10
+    },
+    {
+      "epoch": 0.021568627450980392,
+      "grad_norm": 22168.7890625,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 13.430747985839844,
+      "step": 11
+    },
+    {
+      "epoch": 0.023529411764705882,
+      "grad_norm": 6798.2158203125,
+      "learning_rate": 3.548387096774194e-06,
+      "loss": 13.947168350219727,
+      "step": 12
+    },
+    {
+      "epoch": 0.025490196078431372,
+      "grad_norm": 11967.0244140625,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 15.127799034118652,
+      "step": 13
+    },
+    {
+      "epoch": 0.027450980392156862,
+      "grad_norm": 11873.794921875,
+      "learning_rate": 4.193548387096774e-06,
+      "loss": 13.805913925170898,
+      "step": 14
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 25335.591796875,
+      "learning_rate": 4.516129032258065e-06,
+      "loss": 13.47291374206543,
+      "step": 15
+    },
+    {
+      "epoch": 0.03137254901960784,
+      "grad_norm": 21837.5234375,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 14.185405731201172,
+      "step": 16
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 6198.25146484375,
+      "learning_rate": 5.161290322580646e-06,
+      "loss": 11.65322494506836,
+      "step": 17
+    },
+    {
+      "epoch": 0.03529411764705882,
+      "grad_norm": 5560.4794921875,
+      "learning_rate": 5.483870967741935e-06,
+      "loss": 11.970712661743164,
+      "step": 18
+    },
+    {
+      "epoch": 0.03725490196078431,
+      "grad_norm": 2361.835693359375,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 11.846226692199707,
+      "step": 19
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 3759.865478515625,
+      "learning_rate": 6.129032258064517e-06,
+      "loss": 10.710617065429688,
+      "step": 20
+    },
+    {
+      "epoch": 0.041176470588235294,
+      "grad_norm": 6874.8154296875,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 9.231167793273926,
+      "step": 21
+    },
+    {
+      "epoch": 0.043137254901960784,
+      "grad_norm": 19366.40625,
+      "learning_rate": 6.774193548387097e-06,
+      "loss": 11.892879486083984,
+      "step": 22
+    },
+    {
+      "epoch": 0.045098039215686274,
+      "grad_norm": 6423.419921875,
+      "learning_rate": 7.096774193548388e-06,
+      "loss": 9.792671203613281,
+      "step": 23
+    },
+    {
+      "epoch": 0.047058823529411764,
+      "grad_norm": 3562.012451171875,
+      "learning_rate": 7.4193548387096784e-06,
+      "loss": 9.525957107543945,
+      "step": 24
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 4905.87060546875,
+      "learning_rate": 7.741935483870968e-06,
+      "loss": 11.546586036682129,
+      "step": 25
+    },
+    {
+      "epoch": 0.050980392156862744,
+      "grad_norm": 162666.359375,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 9.598024368286133,
+      "step": 26
+    },
+    {
+      "epoch": 0.052941176470588235,
+      "grad_norm": 8230.1279296875,
+      "learning_rate": 8.387096774193549e-06,
+      "loss": 12.389551162719727,
+      "step": 27
+    },
+    {
+      "epoch": 0.054901960784313725,
+      "grad_norm": 14983.3798828125,
+      "learning_rate": 8.70967741935484e-06,
+      "loss": 14.294782638549805,
+      "step": 28
+    },
+    {
+      "epoch": 0.056862745098039215,
+      "grad_norm": 8721.31640625,
+      "learning_rate": 9.03225806451613e-06,
+      "loss": 10.350369453430176,
+      "step": 29
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 2975.934814453125,
+      "learning_rate": 9.35483870967742e-06,
+      "loss": 9.85280704498291,
+      "step": 30
+    },
+    {
+      "epoch": 0.060784313725490195,
+      "grad_norm": 4804.4228515625,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 8.866147994995117,
+      "step": 31
+    },
+    {
+      "epoch": 0.06274509803921569,
+      "grad_norm": 3305.45361328125,
+      "learning_rate": 1e-05,
+      "loss": 10.436628341674805,
+      "step": 32
+    },
+    {
+      "epoch": 0.06470588235294118,
+      "grad_norm": 11790.716796875,
+      "learning_rate": 9.999974774092107e-06,
+      "loss": 10.873075485229492,
+      "step": 33
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 4500.14111328125,
+      "learning_rate": 9.999899096622962e-06,
+      "loss": 10.806778907775879,
+      "step": 34
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 164.95433044433594,
+      "learning_rate": 9.999772968356182e-06,
+      "loss": 11.633756637573242,
+      "step": 35
+    },
+    {
+      "epoch": 0.07058823529411765,
+      "grad_norm": 43294.8359375,
+      "learning_rate": 9.999596390564446e-06,
+      "loss": 9.791693687438965,
+      "step": 36
+    },
+    {
+      "epoch": 0.07254901960784314,
+      "grad_norm": 39442.3984375,
+      "learning_rate": 9.999369365029487e-06,
+      "loss": 8.951934814453125,
+      "step": 37
+    },
+    {
+      "epoch": 0.07450980392156863,
+      "grad_norm": 588.51171875,
+      "learning_rate": 9.999091894042077e-06,
+      "loss": 8.9212646484375,
+      "step": 38
+    },
+    {
+      "epoch": 0.07647058823529412,
+      "grad_norm": 1923.2791748046875,
+      "learning_rate": 9.998763980401997e-06,
+      "loss": 7.225367546081543,
+      "step": 39
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 657.7442016601562,
+      "learning_rate": 9.998385627418015e-06,
+      "loss": 6.479832172393799,
+      "step": 40
+    },
+    {
+      "epoch": 0.0803921568627451,
+      "grad_norm": 136.12237548828125,
+      "learning_rate": 9.997956838907853e-06,
+      "loss": 6.8389177322387695,
+      "step": 41
+    },
+    {
+      "epoch": 0.08235294117647059,
+      "grad_norm": 251.0398712158203,
+      "learning_rate": 9.997477619198138e-06,
+      "loss": 6.4207072257995605,
+      "step": 42
+    },
+    {
+      "epoch": 0.08431372549019608,
+      "grad_norm": 577.7664794921875,
+      "learning_rate": 9.996947973124372e-06,
+      "loss": 7.31302547454834,
+      "step": 43
+    },
+    {
+      "epoch": 0.08627450980392157,
+      "grad_norm": 91.31795501708984,
+      "learning_rate": 9.996367906030879e-06,
+      "loss": 6.951511383056641,
+      "step": 44
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 6586.15673828125,
+      "learning_rate": 9.995737423770746e-06,
+      "loss": 6.607446670532227,
+      "step": 45
+    },
+    {
+      "epoch": 0.09019607843137255,
+      "grad_norm": 2296.7861328125,
+      "learning_rate": 9.995056532705766e-06,
+      "loss": 5.819401264190674,
+      "step": 46
+    },
+    {
+      "epoch": 0.09215686274509804,
+      "grad_norm": 61.191524505615234,
+      "learning_rate": 9.994325239706377e-06,
+      "loss": 5.54649019241333,
+      "step": 47
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 82.74103546142578,
+      "learning_rate": 9.993543552151594e-06,
+      "loss": 5.546056747436523,
+      "step": 48
+    },
+    {
+      "epoch": 0.09607843137254903,
+      "grad_norm": 2329.645263671875,
+      "learning_rate": 9.992711477928925e-06,
+      "loss": 6.310848712921143,
+      "step": 49
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 210.10841369628906,
+      "learning_rate": 9.991829025434305e-06,
+      "loss": 4.921277046203613,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 153.93605041503906,
+      "learning_rate": 9.990896203571994e-06,
+      "loss": 5.7787909507751465,
+      "step": 51
+    },
+    {
+      "epoch": 0.10196078431372549,
+      "grad_norm": 146.04843139648438,
+      "learning_rate": 9.98991302175451e-06,
+      "loss": 5.398743629455566,
+      "step": 52
+    },
+    {
+      "epoch": 0.10392156862745099,
+      "grad_norm": 84.42292022705078,
+      "learning_rate": 9.98887948990251e-06,
+      "loss": 5.348798751831055,
+      "step": 53
+    },
+    {
+      "epoch": 0.10588235294117647,
+      "grad_norm": 1806.098388671875,
+      "learning_rate": 9.987795618444707e-06,
+      "loss": 5.749485969543457,
+      "step": 54
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 19992.6953125,
+      "learning_rate": 9.986661418317759e-06,
+      "loss": 4.9936370849609375,
+      "step": 55
+    },
+    {
+      "epoch": 0.10980392156862745,
+      "grad_norm": 479.07501220703125,
+      "learning_rate": 9.985476900966156e-06,
+      "loss": 5.318588733673096,
+      "step": 56
+    },
+    {
+      "epoch": 0.11176470588235295,
+      "grad_norm": 161.11553955078125,
+      "learning_rate": 9.984242078342108e-06,
+      "loss": 5.936580181121826,
+      "step": 57
+    },
+    {
+      "epoch": 0.11372549019607843,
+      "grad_norm": 47.58917236328125,
+      "learning_rate": 9.982956962905423e-06,
+      "loss": 5.245980739593506,
+      "step": 58
+    },
+    {
+      "epoch": 0.11568627450980393,
+      "grad_norm": 64.91607666015625,
+      "learning_rate": 9.981621567623385e-06,
+      "loss": 5.656664848327637,
+      "step": 59
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 193.08592224121094,
+      "learning_rate": 9.980235905970615e-06,
+      "loss": 5.183746337890625,
+      "step": 60
+    },
+    {
+      "epoch": 0.11960784313725491,
+      "grad_norm": 197.5607452392578,
+      "learning_rate": 9.978799991928945e-06,
+      "loss": 4.836249351501465,
+      "step": 61
+    },
+    {
+      "epoch": 0.12156862745098039,
+      "grad_norm": 836.5057983398438,
+      "learning_rate": 9.977313839987265e-06,
+      "loss": 4.21888542175293,
+      "step": 62
+    },
+    {
+      "epoch": 0.12352941176470589,
+      "grad_norm": 4496.34228515625,
+      "learning_rate": 9.975777465141391e-06,
+      "loss": 4.858551979064941,
+      "step": 63
+    },
+    {
+      "epoch": 0.12549019607843137,
+      "grad_norm": 33.644187927246094,
+      "learning_rate": 9.974190882893901e-06,
+      "loss": 4.454083442687988,
+      "step": 64
+    },
+    {
+      "epoch": 0.12745098039215685,
+      "grad_norm": 389.5293273925781,
+      "learning_rate": 9.972554109253988e-06,
+      "loss": 4.7087812423706055,
+      "step": 65
+    },
+    {
+      "epoch": 0.12941176470588237,
+      "grad_norm": 234.9954833984375,
+      "learning_rate": 9.970867160737293e-06,
+      "loss": 4.443643569946289,
+      "step": 66
+    },
+    {
+      "epoch": 0.13137254901960785,
+      "grad_norm": 127.71284484863281,
+      "learning_rate": 9.969130054365737e-06,
+      "loss": 5.485596179962158,
+      "step": 67
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 73.74437713623047,
+      "learning_rate": 9.967342807667355e-06,
+      "loss": 5.120403289794922,
+      "step": 68
+    },
+    {
+      "epoch": 0.13529411764705881,
+      "grad_norm": 49.9027214050293,
+      "learning_rate": 9.965505438676115e-06,
+      "loss": 5.075076580047607,
+      "step": 69
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 138.47344970703125,
+      "learning_rate": 9.963617965931738e-06,
+      "loss": 5.561940670013428,
+      "step": 70
+    },
+    {
+      "epoch": 0.1392156862745098,
+      "grad_norm": 322.7532043457031,
+      "learning_rate": 9.961680408479508e-06,
+      "loss": 4.983658790588379,
+      "step": 71
+    },
+    {
+      "epoch": 0.1411764705882353,
+      "grad_norm": 41682.1875,
+      "learning_rate": 9.959692785870086e-06,
+      "loss": 4.346513748168945,
+      "step": 72
+    },
+    {
+      "epoch": 0.14313725490196078,
+      "grad_norm": 22.722593307495117,
+      "learning_rate": 9.957655118159304e-06,
+      "loss": 4.279910087585449,
+      "step": 73
+    },
+    {
+      "epoch": 0.1450980392156863,
+      "grad_norm": 1315.896240234375,
+      "learning_rate": 9.955567425907968e-06,
+      "loss": 5.980461597442627,
+      "step": 74
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 34.87533950805664,
+      "learning_rate": 9.953429730181653e-06,
+      "loss": 4.460562705993652,
+      "step": 75
+    },
+    {
+      "epoch": 0.14901960784313725,
+      "grad_norm": 34.65178680419922,
+      "learning_rate": 9.951242052550487e-06,
+      "loss": 4.673140525817871,
+      "step": 76
+    },
+    {
+      "epoch": 0.15098039215686274,
+      "grad_norm": 188.9655303955078,
+      "learning_rate": 9.949004415088928e-06,
+      "loss": 4.867604732513428,
+      "step": 77
+    },
+    {
+      "epoch": 0.15294117647058825,
+      "grad_norm": 267.5862121582031,
+      "learning_rate": 9.946716840375552e-06,
+      "loss": 4.577199935913086,
+      "step": 78
+    },
+    {
+      "epoch": 0.15490196078431373,
+      "grad_norm": 427.12872314453125,
+      "learning_rate": 9.944379351492818e-06,
+      "loss": 4.855893135070801,
+      "step": 79
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 119.81890869140625,
+      "learning_rate": 9.941991972026839e-06,
+      "loss": 4.051677703857422,
+      "step": 80
+    },
+    {
+      "epoch": 0.1588235294117647,
+      "grad_norm": 6054.2958984375,
+      "learning_rate": 9.939554726067142e-06,
+      "loss": 4.933249473571777,
+      "step": 81
+    },
+    {
+      "epoch": 0.1607843137254902,
+      "grad_norm": 62.10055923461914,
+      "learning_rate": 9.937067638206418e-06,
+      "loss": 4.819094657897949,
+      "step": 82
+    },
+    {
+      "epoch": 0.1627450980392157,
+      "grad_norm": 450.60992431640625,
+      "learning_rate": 9.934530733540293e-06,
+      "loss": 4.19674825668335,
+      "step": 83
+    },
+    {
+      "epoch": 0.16470588235294117,
+      "grad_norm": 350.167724609375,
+      "learning_rate": 9.931944037667056e-06,
+      "loss": 4.2217607498168945,
+      "step": 84
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1959.1741943359375,
+      "learning_rate": 9.929307576687404e-06,
+      "loss": 4.780778884887695,
+      "step": 85
+    },
+    {
+      "epoch": 0.16862745098039217,
+      "grad_norm": 178.00027465820312,
+      "learning_rate": 9.926621377204188e-06,
+      "loss": 4.609301567077637,
+      "step": 86
+    },
+    {
+      "epoch": 0.17058823529411765,
+      "grad_norm": 1623.9786376953125,
+      "learning_rate": 9.923885466322135e-06,
+      "loss": 5.524645805358887,
+      "step": 87
+    },
+    {
+      "epoch": 0.17254901960784313,
+      "grad_norm": 26.787124633789062,
+      "learning_rate": 9.921099871647582e-06,
+      "loss": 4.657105445861816,
+      "step": 88
+    },
+    {
+      "epoch": 0.17450980392156862,
+      "grad_norm": 438.51654052734375,
+      "learning_rate": 9.918264621288187e-06,
+      "loss": 5.135782241821289,
+      "step": 89
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 68.33883666992188,
+      "learning_rate": 9.91537974385266e-06,
+      "loss": 4.544101715087891,
+      "step": 90
+    },
+    {
+      "epoch": 0.1784313725490196,
+      "grad_norm": 184.18646240234375,
+      "learning_rate": 9.912445268450459e-06,
+      "loss": 5.053075790405273,
+      "step": 91
+    },
+    {
+      "epoch": 0.1803921568627451,
+      "grad_norm": 1090.8336181640625,
+      "learning_rate": 9.909461224691506e-06,
+      "loss": 4.8303327560424805,
+      "step": 92
+    },
+    {
+      "epoch": 0.18235294117647058,
+      "grad_norm": 61.77042007446289,
+      "learning_rate": 9.906427642685889e-06,
+      "loss": 4.788046360015869,
+      "step": 93
+    },
+    {
+      "epoch": 0.1843137254901961,
+      "grad_norm": 103.00730895996094,
+      "learning_rate": 9.90334455304355e-06,
+      "loss": 5.147237300872803,
+      "step": 94
+    },
+    {
+      "epoch": 0.18627450980392157,
+      "grad_norm": 46.233280181884766,
+      "learning_rate": 9.900211986873986e-06,
+      "loss": 4.351109981536865,
+      "step": 95
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 305.6100769042969,
+      "learning_rate": 9.897029975785924e-06,
+      "loss": 4.575442790985107,
+      "step": 96
+    },
+    {
+      "epoch": 0.19019607843137254,
+      "grad_norm": 109.36982727050781,
+      "learning_rate": 9.89379855188701e-06,
+      "loss": 4.224271774291992,
+      "step": 97
+    },
+    {
+      "epoch": 0.19215686274509805,
+      "grad_norm": 100.88874816894531,
+      "learning_rate": 9.89051774778349e-06,
+      "loss": 4.574636936187744,
+      "step": 98
+    },
+    {
+      "epoch": 0.19411764705882353,
+      "grad_norm": 285.57757568359375,
+      "learning_rate": 9.887187596579865e-06,
+      "loss": 5.0750861167907715,
+      "step": 99
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 87.83949279785156,
+      "learning_rate": 9.883808131878573e-06,
+      "loss": 4.645264148712158,
+      "step": 100
+    },
+    {
+      "epoch": 0.1980392156862745,
+      "grad_norm": 414.4931335449219,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 4.512279510498047,
+      "step": 101
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 607.8229370117188,
+      "learning_rate": 9.87690139888033e-06,
+      "loss": 4.384090423583984,
+      "step": 102
+    },
+    {
+      "epoch": 0.2019607843137255,
+      "grad_norm": 33.75107192993164,
+      "learning_rate": 9.873374200274826e-06,
+      "loss": 4.4997639656066895,
+      "step": 103
+    },
+    {
+      "epoch": 0.20392156862745098,
+      "grad_norm": 302.5324401855469,
+      "learning_rate": 9.869797827553837e-06,
+      "loss": 4.900559902191162,
+      "step": 104
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 59.07832717895508,
+      "learning_rate": 9.866172316804265e-06,
+      "loss": 4.729743957519531,
+      "step": 105
+    },
+    {
+      "epoch": 0.20784313725490197,
+      "grad_norm": 555.4403686523438,
+      "learning_rate": 9.862497704608829e-06,
+      "loss": 4.753190517425537,
+      "step": 106
+    },
+    {
+      "epoch": 0.20980392156862746,
+      "grad_norm": 649.705810546875,
+      "learning_rate": 9.8587740280457e-06,
+      "loss": 4.613556861877441,
+      "step": 107
+    },
+    {
+      "epoch": 0.21176470588235294,
+      "grad_norm": 414.4284973144531,
+      "learning_rate": 9.855001324688128e-06,
+      "loss": 4.940046310424805,
+      "step": 108
+    },
+    {
+      "epoch": 0.21372549019607842,
+      "grad_norm": 417.20989990234375,
+      "learning_rate": 9.851179632604057e-06,
+      "loss": 4.4412970542907715,
+      "step": 109
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 60.889366149902344,
+      "learning_rate": 9.847308990355752e-06,
+      "loss": 4.690826416015625,
+      "step": 110
+    },
+    {
+      "epoch": 0.21764705882352942,
+      "grad_norm": 83.28646087646484,
+      "learning_rate": 9.843389436999396e-06,
+      "loss": 4.576815605163574,
+      "step": 111
+    },
+    {
+      "epoch": 0.2196078431372549,
+      "grad_norm": 144.78509521484375,
+      "learning_rate": 9.839421012084709e-06,
+      "loss": 4.536053657531738,
+      "step": 112
+    },
+    {
+      "epoch": 0.22156862745098038,
+      "grad_norm": 87.0609359741211,
+      "learning_rate": 9.835403755654535e-06,
+      "loss": 4.452672004699707,
+      "step": 113
+    },
+    {
+      "epoch": 0.2235294117647059,
+      "grad_norm": 49.286476135253906,
+      "learning_rate": 9.831337708244454e-06,
+      "loss": 4.295703887939453,
+      "step": 114
+    },
+    {
+      "epoch": 0.22549019607843138,
+      "grad_norm": 225.94625854492188,
+      "learning_rate": 9.827222910882358e-06,
+      "loss": 5.346158504486084,
+      "step": 115
+    },
+    {
+      "epoch": 0.22745098039215686,
+      "grad_norm": 116.64401245117188,
+      "learning_rate": 9.82305940508805e-06,
+      "loss": 4.404465675354004,
+      "step": 116
+    },
+    {
+      "epoch": 0.22941176470588234,
+      "grad_norm": 71.7906265258789,
+      "learning_rate": 9.818847232872815e-06,
+      "loss": 4.849125862121582,
+      "step": 117
+    },
+    {
+      "epoch": 0.23137254901960785,
+      "grad_norm": 116.41288757324219,
+      "learning_rate": 9.814586436738998e-06,
+      "loss": 4.716423988342285,
+      "step": 118
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 107.20303344726562,
+      "learning_rate": 9.81027705967958e-06,
+      "loss": 4.078630447387695,
+      "step": 119
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 44.105812072753906,
+      "learning_rate": 9.805919145177741e-06,
+      "loss": 4.686631679534912,
+      "step": 120
+    },
+    {
+      "epoch": 0.2372549019607843,
+      "grad_norm": 793.5034790039062,
+      "learning_rate": 9.801512737206422e-06,
+      "loss": 5.099960803985596,
+      "step": 121
+    },
+    {
+      "epoch": 0.23921568627450981,
+      "grad_norm": 91.11273956298828,
+      "learning_rate": 9.797057880227878e-06,
+      "loss": 4.722168922424316,
+      "step": 122
+    },
+    {
+      "epoch": 0.2411764705882353,
+      "grad_norm": 25.48920440673828,
+      "learning_rate": 9.792554619193235e-06,
+      "loss": 4.521475791931152,
+      "step": 123
+    },
+    {
+      "epoch": 0.24313725490196078,
+      "grad_norm": 9693.837890625,
+      "learning_rate": 9.78800299954203e-06,
+      "loss": 4.789237976074219,
+      "step": 124
+    },
+    {
+      "epoch": 0.24509803921568626,
+      "grad_norm": 144.1415252685547,
+      "learning_rate": 9.783403067201763e-06,
+      "loss": 4.778863906860352,
+      "step": 125
+    },
+    {
+      "epoch": 0.24705882352941178,
+      "grad_norm": 11.692220687866211,
+      "learning_rate": 9.778754868587414e-06,
+      "loss": 5.121346473693848,
+      "step": 126
+    },
+    {
+      "epoch": 0.24901960784313726,
+      "grad_norm": 35.05064010620117,
+      "learning_rate": 9.774058450601003e-06,
+      "loss": 5.001660346984863,
+      "step": 127
+    },
+    {
+      "epoch": 0.25098039215686274,
+      "grad_norm": 137.78485107421875,
+      "learning_rate": 9.76931386063109e-06,
+      "loss": 4.57066535949707,
+      "step": 128
+    },
+    {
+      "epoch": 0.2529411764705882,
+      "grad_norm": 43.179466247558594,
+      "learning_rate": 9.76452114655231e-06,
+      "loss": 4.620499610900879,
+      "step": 129
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "grad_norm": 33.09333038330078,
+      "learning_rate": 9.759680356724888e-06,
+      "loss": 4.002799034118652,
+      "step": 130
+    },
+    {
+      "epoch": 0.2568627450980392,
+      "grad_norm": 61.24403762817383,
+      "learning_rate": 9.754791539994153e-06,
+      "loss": 5.060644149780273,
+      "step": 131
+    },
+    {
+      "epoch": 0.25882352941176473,
+      "grad_norm": 8565.3466796875,
+      "learning_rate": 9.749854745690041e-06,
+      "loss": 4.671350479125977,
+      "step": 132
+    },
+    {
+      "epoch": 0.2607843137254902,
+      "grad_norm": 59.654541015625,
+      "learning_rate": 9.744870023626598e-06,
+      "loss": 4.615689277648926,
+      "step": 133
+    },
+    {
+      "epoch": 0.2627450980392157,
+      "grad_norm": 58.113155364990234,
+      "learning_rate": 9.739837424101484e-06,
+      "loss": 4.944394588470459,
+      "step": 134
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 44.76533126831055,
+      "learning_rate": 9.73475699789545e-06,
+      "loss": 4.559343338012695,
+      "step": 135
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4049.171142578125,
+      "learning_rate": 9.729628796271844e-06,
+      "loss": 4.097330093383789,
+      "step": 136
+    },
+    {
+      "epoch": 0.26862745098039215,
+      "grad_norm": 91.75375366210938,
+      "learning_rate": 9.724452870976084e-06,
+      "loss": 4.160323143005371,
+      "step": 137
+    },
+    {
+      "epoch": 0.27058823529411763,
+      "grad_norm": 92.1652603149414,
+      "learning_rate": 9.719229274235134e-06,
+      "loss": 4.578685760498047,
+      "step": 138
+    },
+    {
+      "epoch": 0.2725490196078431,
+      "grad_norm": 21.699565887451172,
+      "learning_rate": 9.713958058756985e-06,
+      "loss": 4.3331217765808105,
+      "step": 139
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 2818.811279296875,
+      "learning_rate": 9.708639277730112e-06,
+      "loss": 4.388368606567383,
+      "step": 140
+    },
+    {
+      "epoch": 0.27647058823529413,
+      "grad_norm": 58.03261184692383,
+      "learning_rate": 9.703272984822947e-06,
+      "loss": 4.328610897064209,
+      "step": 141
+    },
+    {
+      "epoch": 0.2784313725490196,
+      "grad_norm": 85.0673599243164,
+      "learning_rate": 9.697859234183336e-06,
+      "loss": 4.389078617095947,
+      "step": 142
+    },
+    {
+      "epoch": 0.2803921568627451,
+      "grad_norm": 47.508522033691406,
+      "learning_rate": 9.692398080437991e-06,
+      "loss": 4.623535633087158,
+      "step": 143
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 26.19891357421875,
+      "learning_rate": 9.68688957869193e-06,
+      "loss": 4.690242767333984,
+      "step": 144
+    },
+    {
+      "epoch": 0.28431372549019607,
+      "grad_norm": 27.067237854003906,
+      "learning_rate": 9.681333784527945e-06,
+      "loss": 4.570530414581299,
+      "step": 145
+    },
+    {
+      "epoch": 0.28627450980392155,
+      "grad_norm": 241.20358276367188,
+      "learning_rate": 9.67573075400601e-06,
+      "loss": 4.467217922210693,
+      "step": 146
+    },
+    {
+      "epoch": 0.28823529411764703,
+      "grad_norm": 14.455266952514648,
+      "learning_rate": 9.670080543662742e-06,
+      "loss": 4.641494274139404,
+      "step": 147
+    },
+    {
+      "epoch": 0.2901960784313726,
+      "grad_norm": 31.17917251586914,
+      "learning_rate": 9.66438321051081e-06,
+      "loss": 4.5704450607299805,
+      "step": 148
+    },
+    {
+      "epoch": 0.29215686274509806,
+      "grad_norm": 31.33642578125,
+      "learning_rate": 9.658638812038379e-06,
+      "loss": 4.436771869659424,
+      "step": 149
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 44.800392150878906,
+      "learning_rate": 9.652847406208514e-06,
+      "loss": 4.712490558624268,
+      "step": 150
+    },
+    {
+      "epoch": 0.296078431372549,
+      "grad_norm": 25.672563552856445,
+      "learning_rate": 9.647009051458604e-06,
+      "loss": 5.042919158935547,
+      "step": 151
+    },
+    {
+      "epoch": 0.2980392156862745,
+      "grad_norm": 16.580514907836914,
+      "learning_rate": 9.641123806699769e-06,
+      "loss": 4.510254859924316,
+      "step": 152
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 15.236343383789062,
+      "learning_rate": 9.635191731316262e-06,
+      "loss": 4.711069583892822,
+      "step": 153
+    },
+    {
+      "epoch": 0.30196078431372547,
+      "grad_norm": 216.19012451171875,
+      "learning_rate": 9.629212885164882e-06,
+      "loss": 4.6602983474731445,
+      "step": 154
+    },
+    {
+      "epoch": 0.30392156862745096,
+      "grad_norm": 23.054521560668945,
+      "learning_rate": 9.623187328574357e-06,
+      "loss": 4.656505584716797,
+      "step": 155
+    },
+    {
+      "epoch": 0.3058823529411765,
+      "grad_norm": 75.67474365234375,
+      "learning_rate": 9.617115122344742e-06,
+      "loss": 4.795361042022705,
+      "step": 156
+    },
+    {
+      "epoch": 0.307843137254902,
+      "grad_norm": 10.801730155944824,
+      "learning_rate": 9.6109963277468e-06,
+      "loss": 4.377931118011475,
+      "step": 157
+    },
+    {
+      "epoch": 0.30980392156862746,
+      "grad_norm": 50.18651580810547,
+      "learning_rate": 9.604831006521393e-06,
+      "loss": 4.209827423095703,
+      "step": 158
+    },
+    {
+      "epoch": 0.31176470588235294,
+      "grad_norm": 65.79145812988281,
+      "learning_rate": 9.598619220878852e-06,
+      "loss": 4.403324127197266,
+      "step": 159
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 717.3584594726562,
+      "learning_rate": 9.592361033498349e-06,
+      "loss": 4.686285972595215,
+      "step": 160
+    },
+    {
+      "epoch": 0.3156862745098039,
+      "grad_norm": 6.576393127441406,
+      "learning_rate": 9.586056507527266e-06,
+      "loss": 4.493882179260254,
+      "step": 161
+    },
+    {
+      "epoch": 0.3176470588235294,
+      "grad_norm": 22.952342987060547,
+      "learning_rate": 9.57970570658056e-06,
+      "loss": 3.9739434719085693,
+      "step": 162
+    },
+    {
+      "epoch": 0.3196078431372549,
+      "grad_norm": 19.122220993041992,
+      "learning_rate": 9.57330869474012e-06,
+      "loss": 4.901614189147949,
+      "step": 163
+    },
+    {
+      "epoch": 0.3215686274509804,
+      "grad_norm": 13.962799072265625,
+      "learning_rate": 9.566865536554119e-06,
+      "loss": 4.684842109680176,
+      "step": 164
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 588.8753051757812,
+      "learning_rate": 9.560376297036362e-06,
+      "loss": 4.2213664054870605,
+      "step": 165
+    },
+    {
+      "epoch": 0.3254901960784314,
+      "grad_norm": 52.16958999633789,
+      "learning_rate": 9.553841041665632e-06,
+      "loss": 4.610918045043945,
+      "step": 166
+    },
+    {
+      "epoch": 0.32745098039215687,
+      "grad_norm": 10.890721321105957,
+      "learning_rate": 9.54725983638503e-06,
+      "loss": 4.533082485198975,
+      "step": 167
+    },
+    {
+      "epoch": 0.32941176470588235,
+      "grad_norm": 16.27850914001465,
+      "learning_rate": 9.540632747601309e-06,
+      "loss": 4.84617805480957,
+      "step": 168
+    },
+    {
+      "epoch": 0.33137254901960783,
+      "grad_norm": 23.593048095703125,
+      "learning_rate": 9.533959842184195e-06,
+      "loss": 4.829172611236572,
+      "step": 169
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 12.077108383178711,
+      "learning_rate": 9.527241187465735e-06,
+      "loss": 4.293300151824951,
+      "step": 170
+    },
+    {
+      "epoch": 0.3352941176470588,
+      "grad_norm": 21.818492889404297,
+      "learning_rate": 9.520476851239588e-06,
+      "loss": 4.222914695739746,
+      "step": 171
+    },
+    {
+      "epoch": 0.33725490196078434,
+      "grad_norm": 14.46260929107666,
+      "learning_rate": 9.513666901760368e-06,
+      "loss": 4.497089385986328,
+      "step": 172
+    },
+    {
+      "epoch": 0.3392156862745098,
+      "grad_norm": 15.194242477416992,
+      "learning_rate": 9.506811407742938e-06,
+      "loss": 4.559511661529541,
+      "step": 173
+    },
+    {
+      "epoch": 0.3411764705882353,
+      "grad_norm": 23.59486198425293,
+      "learning_rate": 9.49991043836172e-06,
+      "loss": 4.664986610412598,
+      "step": 174
+    },
+    {
+      "epoch": 0.3431372549019608,
+      "grad_norm": 12.736374855041504,
+      "learning_rate": 9.49296406325e-06,
+      "loss": 3.997081756591797,
+      "step": 175
+    },
+    {
+      "epoch": 0.34509803921568627,
+      "grad_norm": 32.026031494140625,
+      "learning_rate": 9.485972352499231e-06,
+      "loss": 3.9222970008850098,
+      "step": 176
+    },
+    {
+      "epoch": 0.34705882352941175,
+      "grad_norm": 74.40033721923828,
+      "learning_rate": 9.478935376658308e-06,
+      "loss": 4.217952728271484,
+      "step": 177
+    },
+    {
+      "epoch": 0.34901960784313724,
+      "grad_norm": 32.45917892456055,
+      "learning_rate": 9.471853206732875e-06,
+      "loss": 4.877760887145996,
+      "step": 178
+    },
+    {
+      "epoch": 0.3509803921568627,
+      "grad_norm": 133.5160675048828,
+      "learning_rate": 9.4647259141846e-06,
+      "loss": 4.599568843841553,
+      "step": 179
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 110.89315795898438,
+      "learning_rate": 9.457553570930451e-06,
+      "loss": 4.784282684326172,
+      "step": 180
+    },
+    {
+      "epoch": 0.35490196078431374,
+      "grad_norm": 7.933850288391113,
+      "learning_rate": 9.450336249341976e-06,
+      "loss": 4.384489059448242,
+      "step": 181
+    },
+    {
+      "epoch": 0.3568627450980392,
+      "grad_norm": 90.08252716064453,
+      "learning_rate": 9.443074022244573e-06,
+      "loss": 4.630293846130371,
+      "step": 182
+    },
+    {
+      "epoch": 0.3588235294117647,
+      "grad_norm": 203.20277404785156,
+      "learning_rate": 9.435766962916749e-06,
+      "loss": 4.612138748168945,
+      "step": 183
+    },
+    {
+      "epoch": 0.3607843137254902,
+      "grad_norm": 29.04180145263672,
+      "learning_rate": 9.428415145089385e-06,
+      "loss": 4.887096405029297,
+      "step": 184
+    },
+    {
+      "epoch": 0.3627450980392157,
+      "grad_norm": 21.732030868530273,
+      "learning_rate": 9.421018642944996e-06,
+      "loss": 4.200204372406006,
+      "step": 185
+    },
+    {
+      "epoch": 0.36470588235294116,
+      "grad_norm": 88.96598052978516,
+      "learning_rate": 9.413577531116973e-06,
+      "loss": 4.376042366027832,
+      "step": 186
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 97.27217102050781,
+      "learning_rate": 9.406091884688837e-06,
+      "loss": 4.695228099822998,
+      "step": 187
+    },
+    {
+      "epoch": 0.3686274509803922,
+      "grad_norm": 50.880985260009766,
+      "learning_rate": 9.398561779193477e-06,
+      "loss": 4.356112003326416,
+      "step": 188
+    },
+    {
+      "epoch": 0.37058823529411766,
+      "grad_norm": 12.541425704956055,
+      "learning_rate": 9.390987290612396e-06,
+      "loss": 4.752440452575684,
+      "step": 189
+    },
+    {
+      "epoch": 0.37254901960784315,
+      "grad_norm": 236.70387268066406,
+      "learning_rate": 9.38336849537493e-06,
+      "loss": 4.593203067779541,
+      "step": 190
+    },
+    {
+      "epoch": 0.37450980392156863,
+      "grad_norm": 2993.429931640625,
+      "learning_rate": 9.375705470357493e-06,
+      "loss": 4.44484806060791,
+      "step": 191
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 150.78634643554688,
+      "learning_rate": 9.367998292882789e-06,
+      "loss": 3.959789514541626,
+      "step": 192
+    },
+    {
+      "epoch": 0.3784313725490196,
+      "grad_norm": 39.33837127685547,
+      "learning_rate": 9.36024704071904e-06,
+      "loss": 4.030791759490967,
+      "step": 193
+    },
+    {
+      "epoch": 0.3803921568627451,
+      "grad_norm": 18.125226974487305,
+      "learning_rate": 9.35245179207919e-06,
+      "loss": 4.262718200683594,
+      "step": 194
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 70.55377960205078,
+      "learning_rate": 9.344612625620134e-06,
+      "loss": 4.606302261352539,
+      "step": 195
+    },
+    {
+      "epoch": 0.3843137254901961,
+      "grad_norm": 1980.358154296875,
+      "learning_rate": 9.336729620441906e-06,
+      "loss": 4.8002824783325195,
+      "step": 196
+    },
+    {
+      "epoch": 0.3862745098039216,
+      "grad_norm": 31.0122013092041,
+      "learning_rate": 9.328802856086891e-06,
+      "loss": 4.136668682098389,
+      "step": 197
+    },
+    {
+      "epoch": 0.38823529411764707,
+      "grad_norm": 13.777653694152832,
+      "learning_rate": 9.32083241253902e-06,
+      "loss": 4.453038692474365,
+      "step": 198
+    },
+    {
+      "epoch": 0.39019607843137255,
+      "grad_norm": 15.520337104797363,
+      "learning_rate": 9.312818370222962e-06,
+      "loss": 4.666173934936523,
+      "step": 199
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 25.686555862426758,
+      "learning_rate": 9.304760810003318e-06,
+      "loss": 4.567206859588623,
+      "step": 200
+    },
+    {
+      "epoch": 0.3941176470588235,
+      "grad_norm": 34.059505462646484,
+      "learning_rate": 9.296659813183794e-06,
+      "loss": 4.661189556121826,
+      "step": 201
+    },
+    {
+      "epoch": 0.396078431372549,
+      "grad_norm": 20.709781646728516,
+      "learning_rate": 9.28851546150639e-06,
+      "loss": 4.140271186828613,
+      "step": 202
+    },
+    {
+      "epoch": 0.3980392156862745,
+      "grad_norm": 52.71310043334961,
+      "learning_rate": 9.280327837150572e-06,
+      "loss": 4.564424514770508,
+      "step": 203
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.125553131103516,
+      "learning_rate": 9.272097022732444e-06,
+      "loss": 4.352408409118652,
+      "step": 204
+    },
+    {
+      "epoch": 0.4019607843137255,
+      "grad_norm": 10.148744583129883,
+      "learning_rate": 9.263823101303911e-06,
+      "loss": 3.883530616760254,
+      "step": 205
+    },
+    {
+      "epoch": 0.403921568627451,
+      "grad_norm": 22.48365020751953,
+      "learning_rate": 9.255506156351846e-06,
+      "loss": 4.559526443481445,
+      "step": 206
+    },
+    {
+      "epoch": 0.40588235294117647,
+      "grad_norm": 1699.036865234375,
+      "learning_rate": 9.247146271797244e-06,
+      "loss": 4.905045509338379,
+      "step": 207
+    },
+    {
+      "epoch": 0.40784313725490196,
+      "grad_norm": 7.313532829284668,
+      "learning_rate": 9.238743531994378e-06,
+      "loss": 3.642618417739868,
+      "step": 208
+    },
+    {
+      "epoch": 0.40980392156862744,
+      "grad_norm": 35.672157287597656,
+      "learning_rate": 9.23029802172994e-06,
+      "loss": 4.230594635009766,
+      "step": 209
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 202.3529815673828,
+      "learning_rate": 9.221809826222198e-06,
+      "loss": 4.2360124588012695,
+      "step": 210
+    },
+    {
+      "epoch": 0.4137254901960784,
+      "grad_norm": 117.8387222290039,
+      "learning_rate": 9.213279031120129e-06,
+      "loss": 4.491461277008057,
+      "step": 211
+    },
+    {
+      "epoch": 0.41568627450980394,
+      "grad_norm": 34.6633186340332,
+      "learning_rate": 9.20470572250255e-06,
+      "loss": 4.295816898345947,
+      "step": 212
+    },
+    {
+      "epoch": 0.4176470588235294,
+      "grad_norm": 8.826363563537598,
+      "learning_rate": 9.196089986877262e-06,
+      "loss": 4.463611602783203,
+      "step": 213
+    },
+    {
+      "epoch": 0.4196078431372549,
+      "grad_norm": 26.18223762512207,
+      "learning_rate": 9.18743191118016e-06,
+      "loss": 4.4809675216674805,
+      "step": 214
+    },
+    {
+      "epoch": 0.4215686274509804,
+      "grad_norm": 23.7016544342041,
+      "learning_rate": 9.17873158277438e-06,
+      "loss": 4.53269100189209,
+      "step": 215
+    },
+    {
+      "epoch": 0.4235294117647059,
+      "grad_norm": 147.547119140625,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 4.548085689544678,
+      "step": 216
+    },
+    {
+      "epoch": 0.42549019607843136,
+      "grad_norm": 33.69279098510742,
+      "learning_rate": 9.161204519420126e-06,
+      "loss": 4.510319709777832,
+      "step": 217
+    },
+    {
+      "epoch": 0.42745098039215684,
+      "grad_norm": 21.794368743896484,
+      "learning_rate": 9.152377961326085e-06,
+      "loss": 3.977487564086914,
+      "step": 218
+    },
+    {
+      "epoch": 0.4294117647058823,
+      "grad_norm": 17.71551513671875,
+      "learning_rate": 9.14350950423045e-06,
+      "loss": 4.281040191650391,
+      "step": 219
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 91.0526123046875,
+      "learning_rate": 9.134599237619167e-06,
+      "loss": 4.954435348510742,
+      "step": 220
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 39.16487121582031,
+      "learning_rate": 9.125647251400068e-06,
+      "loss": 4.5113935470581055,
+      "step": 221
+    },
+    {
+      "epoch": 0.43529411764705883,
+      "grad_norm": 304.0317687988281,
+      "learning_rate": 9.11665363590194e-06,
+      "loss": 4.286795139312744,
+      "step": 222
+    },
+    {
+      "epoch": 0.4372549019607843,
+      "grad_norm": 64.62968444824219,
+      "learning_rate": 9.107618481873632e-06,
+      "loss": 4.302193641662598,
+      "step": 223
+    },
+    {
+      "epoch": 0.4392156862745098,
+      "grad_norm": 9.797171592712402,
+      "learning_rate": 9.098541880483129e-06,
+      "loss": 4.519267559051514,
+      "step": 224
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 16.81446647644043,
+      "learning_rate": 9.089423923316636e-06,
+      "loss": 4.170806884765625,
+      "step": 225
+    },
+    {
+      "epoch": 0.44313725490196076,
+      "grad_norm": 97.48379516601562,
+      "learning_rate": 9.08026470237765e-06,
+      "loss": 4.171516418457031,
+      "step": 226
+    },
+    {
+      "epoch": 0.44509803921568625,
+      "grad_norm": 8.226983070373535,
+      "learning_rate": 9.07106431008604e-06,
+      "loss": 4.536833763122559,
+      "step": 227
+    },
+    {
+      "epoch": 0.4470588235294118,
+      "grad_norm": 17.50508689880371,
+      "learning_rate": 9.0618228392771e-06,
+      "loss": 4.602504730224609,
+      "step": 228
+    },
+    {
+      "epoch": 0.44901960784313727,
+      "grad_norm": 1409.4854736328125,
+      "learning_rate": 9.052540383200634e-06,
+      "loss": 4.213375091552734,
+      "step": 229
+    },
+    {
+      "epoch": 0.45098039215686275,
+      "grad_norm": 18.96872901916504,
+      "learning_rate": 9.043217035519986e-06,
+      "loss": 4.0827131271362305,
+      "step": 230
+    },
+    {
+      "epoch": 0.45294117647058824,
+      "grad_norm": 16.178728103637695,
+      "learning_rate": 9.033852890311127e-06,
+      "loss": 4.6328125,
+      "step": 231
+    },
+    {
+      "epoch": 0.4549019607843137,
+      "grad_norm": 10.366260528564453,
+      "learning_rate": 9.02444804206168e-06,
+      "loss": 4.5647430419921875,
+      "step": 232
+    },
+    {
+      "epoch": 0.4568627450980392,
+      "grad_norm": 17.84885597229004,
+      "learning_rate": 9.01500258566998e-06,
+      "loss": 4.389437198638916,
+      "step": 233
+    },
+    {
+      "epoch": 0.4588235294117647,
+      "grad_norm": 11.878860473632812,
+      "learning_rate": 9.005516616444112e-06,
+      "loss": 4.770614147186279,
+      "step": 234
+    },
+    {
+      "epoch": 0.46078431372549017,
+      "grad_norm": 85.99885559082031,
+      "learning_rate": 8.99599023010095e-06,
+      "loss": 4.427285194396973,
+      "step": 235
+    },
+    {
+      "epoch": 0.4627450980392157,
+      "grad_norm": 77.5919189453125,
+      "learning_rate": 8.986423522765191e-06,
+      "loss": 4.447712421417236,
+      "step": 236
+    },
+    {
+      "epoch": 0.4647058823529412,
+      "grad_norm": 19.800437927246094,
+      "learning_rate": 8.976816590968388e-06,
+      "loss": 4.388566017150879,
+      "step": 237
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 29.633106231689453,
+      "learning_rate": 8.967169531647971e-06,
+      "loss": 4.662332534790039,
+      "step": 238
+    },
+    {
+      "epoch": 0.46862745098039216,
+      "grad_norm": 11.136107444763184,
+      "learning_rate": 8.957482442146271e-06,
+      "loss": 4.721919059753418,
+      "step": 239
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 23.172388076782227,
+      "learning_rate": 8.947755420209541e-06,
+      "loss": 4.55937385559082,
+      "step": 240
+    },
+    {
+      "epoch": 0.4725490196078431,
+      "grad_norm": 22.51704216003418,
+      "learning_rate": 8.937988563986963e-06,
+      "loss": 4.346927642822266,
+      "step": 241
+    },
+    {
+      "epoch": 0.4745098039215686,
+      "grad_norm": 9.842615127563477,
+      "learning_rate": 8.928181972029664e-06,
+      "loss": 4.690535545349121,
+      "step": 242
+    },
+    {
+      "epoch": 0.4764705882352941,
+      "grad_norm": 158.396484375,
+      "learning_rate": 8.918335743289717e-06,
+      "loss": 4.770160675048828,
+      "step": 243
+    },
+    {
+      "epoch": 0.47843137254901963,
+      "grad_norm": 18.87772560119629,
+      "learning_rate": 8.90844997711915e-06,
+      "loss": 4.694735527038574,
+      "step": 244
+    },
+    {
+      "epoch": 0.4803921568627451,
+      "grad_norm": 10.401981353759766,
+      "learning_rate": 8.898524773268926e-06,
+      "loss": 4.433718681335449,
+      "step": 245
+    },
+    {
+      "epoch": 0.4823529411764706,
+      "grad_norm": 35.996971130371094,
+      "learning_rate": 8.888560231887963e-06,
+      "loss": 4.435983180999756,
+      "step": 246
+    },
+    {
+      "epoch": 0.4843137254901961,
+      "grad_norm": 144.66212463378906,
+      "learning_rate": 8.8785564535221e-06,
+      "loss": 4.828408241271973,
+      "step": 247
+    },
+    {
+      "epoch": 0.48627450980392156,
+      "grad_norm": 61.79336166381836,
+      "learning_rate": 8.868513539113093e-06,
+      "loss": 4.478762149810791,
+      "step": 248
+    },
+    {
+      "epoch": 0.48823529411764705,
+      "grad_norm": 111.1070556640625,
+      "learning_rate": 8.858431589997597e-06,
+      "loss": 4.791953086853027,
+      "step": 249
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 43.53703308105469,
+      "learning_rate": 8.848310707906138e-06,
+      "loss": 4.221644401550293,
+      "step": 250
+    },
+    {
+      "epoch": 0.492156862745098,
+      "grad_norm": 30.130136489868164,
+      "learning_rate": 8.838150994962094e-06,
+      "loss": 3.9666197299957275,
+      "step": 251
+    },
+    {
+      "epoch": 0.49411764705882355,
+      "grad_norm": 24.61577033996582,
+      "learning_rate": 8.827952553680656e-06,
+      "loss": 4.494099140167236,
+      "step": 252
+    },
+    {
+      "epoch": 0.49607843137254903,
+      "grad_norm": 95.78424835205078,
+      "learning_rate": 8.817715486967803e-06,
+      "loss": 4.37385368347168,
+      "step": 253
+    },
+    {
+      "epoch": 0.4980392156862745,
+      "grad_norm": 12.204360008239746,
+      "learning_rate": 8.807439898119252e-06,
+      "loss": 4.433926582336426,
+      "step": 254
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 14.268149375915527,
+      "learning_rate": 8.797125890819429e-06,
+      "loss": 4.530971527099609,
+      "step": 255
+    },
+    {
+      "epoch": 0.5019607843137255,
+      "grad_norm": 17.889156341552734,
+      "learning_rate": 8.786773569140414e-06,
+      "loss": 4.126347541809082,
+      "step": 256
+    },
+    {
+      "epoch": 0.503921568627451,
+      "grad_norm": 18.556318283081055,
+      "learning_rate": 8.776383037540888e-06,
+      "loss": 4.337622165679932,
+      "step": 257
+    },
+    {
+      "epoch": 0.5058823529411764,
+      "grad_norm": 679.375244140625,
+      "learning_rate": 8.765954400865093e-06,
+      "loss": 4.433990478515625,
+      "step": 258
+    },
+    {
+      "epoch": 0.5078431372549019,
+      "grad_norm": 42.50425338745117,
+      "learning_rate": 8.755487764341756e-06,
+      "loss": 4.115379810333252,
+      "step": 259
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 53.077613830566406,
+      "learning_rate": 8.744983233583044e-06,
+      "loss": 4.244760036468506,
+      "step": 260
+    },
+    {
+      "epoch": 0.5117647058823529,
+      "grad_norm": 17.79299545288086,
+      "learning_rate": 8.734440914583486e-06,
+      "loss": 4.051713943481445,
+      "step": 261
+    },
+    {
+      "epoch": 0.5137254901960784,
+      "grad_norm": 15.688224792480469,
+      "learning_rate": 8.72386091371891e-06,
+      "loss": 4.603087425231934,
+      "step": 262
+    },
+    {
+      "epoch": 0.515686274509804,
+      "grad_norm": 55.612709045410156,
+      "learning_rate": 8.713243337745366e-06,
+      "loss": 4.455329418182373,
+      "step": 263
+    },
+    {
+      "epoch": 0.5176470588235295,
+      "grad_norm": 18.093618392944336,
+      "learning_rate": 8.70258829379805e-06,
+      "loss": 4.481441497802734,
+      "step": 264
+    },
+    {
+      "epoch": 0.5196078431372549,
+      "grad_norm": 290.83355712890625,
+      "learning_rate": 8.691895889390228e-06,
+      "loss": 4.285877227783203,
+      "step": 265
+    },
+    {
+      "epoch": 0.5215686274509804,
+      "grad_norm": 17.16389274597168,
+      "learning_rate": 8.681166232412142e-06,
+      "loss": 4.445030212402344,
+      "step": 266
+    },
+    {
+      "epoch": 0.5235294117647059,
+      "grad_norm": 26.885225296020508,
+      "learning_rate": 8.670399431129926e-06,
+      "loss": 4.563932418823242,
+      "step": 267
+    },
+    {
+      "epoch": 0.5254901960784314,
+      "grad_norm": 42.71232604980469,
+      "learning_rate": 8.659595594184516e-06,
+      "loss": 3.8843421936035156,
+      "step": 268
+    },
+    {
+      "epoch": 0.5274509803921569,
+      "grad_norm": 28.694578170776367,
+      "learning_rate": 8.648754830590552e-06,
+      "loss": 3.6372265815734863,
+      "step": 269
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 43.32936477661133,
+      "learning_rate": 8.637877249735274e-06,
+      "loss": 4.222830295562744,
+      "step": 270
+    },
+    {
+      "epoch": 0.5313725490196078,
+      "grad_norm": 72.35948944091797,
+      "learning_rate": 8.626962961377423e-06,
+      "loss": 4.611291408538818,
+      "step": 271
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 15.251282691955566,
+      "learning_rate": 8.616012075646134e-06,
+      "loss": 4.276963233947754,
+      "step": 272
+    },
+    {
+      "epoch": 0.5352941176470588,
+      "grad_norm": 776.6341552734375,
+      "learning_rate": 8.605024703039817e-06,
+      "loss": 4.6572585105896,
+      "step": 273
+    },
+    {
+      "epoch": 0.5372549019607843,
+      "grad_norm": 22.79600715637207,
+      "learning_rate": 8.594000954425056e-06,
+      "loss": 4.917038917541504,
+      "step": 274
+    },
+    {
+      "epoch": 0.5392156862745098,
+      "grad_norm": 10.690701484680176,
+      "learning_rate": 8.582940941035476e-06,
+      "loss": 4.69964599609375,
+      "step": 275
+    },
+    {
+      "epoch": 0.5411764705882353,
+      "grad_norm": 86.31309509277344,
+      "learning_rate": 8.571844774470627e-06,
+      "loss": 4.586027145385742,
+      "step": 276
+    },
+    {
+      "epoch": 0.5431372549019607,
+      "grad_norm": 17.10081672668457,
+      "learning_rate": 8.560712566694863e-06,
+      "loss": 4.531658172607422,
+      "step": 277
+    },
+    {
+      "epoch": 0.5450980392156862,
+      "grad_norm": 15.138278007507324,
+      "learning_rate": 8.549544430036198e-06,
+      "loss": 4.515611171722412,
+      "step": 278
+    },
+    {
+      "epoch": 0.5470588235294118,
+      "grad_norm": 11.231842994689941,
+      "learning_rate": 8.538340477185191e-06,
+      "loss": 4.401930809020996,
+      "step": 279
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 9.649141311645508,
+      "learning_rate": 8.527100821193797e-06,
+      "loss": 4.2050909996032715,
+      "step": 280
+    },
+    {
+      "epoch": 0.5509803921568628,
+      "grad_norm": 44.636756896972656,
+      "learning_rate": 8.51582557547422e-06,
+      "loss": 4.522353649139404,
+      "step": 281
+    },
+    {
+      "epoch": 0.5529411764705883,
+      "grad_norm": 10.403969764709473,
+      "learning_rate": 8.504514853797789e-06,
+      "loss": 4.316591262817383,
+      "step": 282
+    },
+    {
+      "epoch": 0.5549019607843138,
+      "grad_norm": 45.07345199584961,
+      "learning_rate": 8.493168770293793e-06,
+      "loss": 4.220366477966309,
+      "step": 283
+    },
+    {
+      "epoch": 0.5568627450980392,
+      "grad_norm": 81.64495849609375,
+      "learning_rate": 8.481787439448332e-06,
+      "loss": 4.375057220458984,
+      "step": 284
+    },
+    {
+      "epoch": 0.5588235294117647,
+      "grad_norm": 22.120563507080078,
+      "learning_rate": 8.470370976103171e-06,
+      "loss": 4.166134834289551,
+      "step": 285
+    },
+    {
+      "epoch": 0.5607843137254902,
+      "grad_norm": 10.833823204040527,
+      "learning_rate": 8.458919495454567e-06,
+      "loss": 4.409770965576172,
+      "step": 286
+    },
+    {
+      "epoch": 0.5627450980392157,
+      "grad_norm": 81.50211334228516,
+      "learning_rate": 8.447433113052124e-06,
+      "loss": 4.4287190437316895,
+      "step": 287
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 16.984268188476562,
+      "learning_rate": 8.435911944797605e-06,
+      "loss": 4.146420955657959,
+      "step": 288
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 85.84491729736328,
+      "learning_rate": 8.42435610694379e-06,
+      "loss": 4.802792549133301,
+      "step": 289
+    },
+    {
+      "epoch": 0.5686274509803921,
+      "grad_norm": 1234.199951171875,
+      "learning_rate": 8.412765716093273e-06,
+      "loss": 4.3419270515441895,
+      "step": 290
+    },
+    {
+      "epoch": 0.5705882352941176,
+      "grad_norm": 12.962360382080078,
+      "learning_rate": 8.401140889197305e-06,
+      "loss": 4.3528547286987305,
+      "step": 291
+    },
+    {
+      "epoch": 0.5725490196078431,
+      "grad_norm": 26.18000030517578,
+      "learning_rate": 8.38948174355462e-06,
+      "loss": 4.065543174743652,
+      "step": 292
+    },
+    {
+      "epoch": 0.5745098039215686,
+      "grad_norm": 35.139549255371094,
+      "learning_rate": 8.377788396810223e-06,
+      "loss": 4.251129150390625,
+      "step": 293
+    },
+    {
+      "epoch": 0.5764705882352941,
+      "grad_norm": 37.94339370727539,
+      "learning_rate": 8.366060966954235e-06,
+      "loss": 4.624574661254883,
+      "step": 294
+    },
+    {
+      "epoch": 0.5784313725490197,
+      "grad_norm": 11.896288871765137,
+      "learning_rate": 8.354299572320679e-06,
+      "loss": 4.315122604370117,
+      "step": 295
+    },
+    {
+      "epoch": 0.5803921568627451,
+      "grad_norm": 41.16322708129883,
+      "learning_rate": 8.342504331586298e-06,
+      "loss": 4.489446640014648,
+      "step": 296
+    },
+    {
+      "epoch": 0.5823529411764706,
+      "grad_norm": 28.843425750732422,
+      "learning_rate": 8.330675363769356e-06,
+      "loss": 4.456976890563965,
+      "step": 297
+    },
+    {
+      "epoch": 0.5843137254901961,
+      "grad_norm": 14.19128704071045,
+      "learning_rate": 8.318812788228434e-06,
+      "loss": 4.4964447021484375,
+      "step": 298
+    },
+    {
+      "epoch": 0.5862745098039216,
+      "grad_norm": 41.6136474609375,
+      "learning_rate": 8.306916724661225e-06,
+      "loss": 4.119976043701172,
+      "step": 299
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 20.12372398376465,
+      "learning_rate": 8.294987293103334e-06,
+      "loss": 4.503427505493164,
+      "step": 300
+    },
+    {
+      "epoch": 0.5901960784313726,
+      "grad_norm": 96.8432846069336,
+      "learning_rate": 8.283024613927055e-06,
+      "loss": 4.409475326538086,
+      "step": 301
+    },
+    {
+      "epoch": 0.592156862745098,
+      "grad_norm": 24.83096694946289,
+      "learning_rate": 8.271028807840164e-06,
+      "loss": 4.263705730438232,
+      "step": 302
+    },
+    {
+      "epoch": 0.5941176470588235,
+      "grad_norm": 92.04113006591797,
+      "learning_rate": 8.258999995884706e-06,
+      "loss": 4.188453674316406,
+      "step": 303
+    },
+    {
+      "epoch": 0.596078431372549,
+      "grad_norm": 32.55808639526367,
+      "learning_rate": 8.246938299435759e-06,
+      "loss": 4.0705437660217285,
+      "step": 304
+    },
+    {
+      "epoch": 0.5980392156862745,
+      "grad_norm": 28.917774200439453,
+      "learning_rate": 8.234843840200218e-06,
+      "loss": 4.273771286010742,
+      "step": 305
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 14.942693710327148,
+      "learning_rate": 8.222716740215573e-06,
+      "loss": 4.468536376953125,
+      "step": 306
+    },
+    {
+      "epoch": 0.6019607843137255,
+      "grad_norm": 76.9916763305664,
+      "learning_rate": 8.210557121848664e-06,
+      "loss": 4.393499851226807,
+      "step": 307
+    },
+    {
+      "epoch": 0.6039215686274509,
+      "grad_norm": 87.08967590332031,
+      "learning_rate": 8.198365107794457e-06,
+      "loss": 4.2165422439575195,
+      "step": 308
+    },
+    {
+      "epoch": 0.6058823529411764,
+      "grad_norm": 76.53693389892578,
+      "learning_rate": 8.186140821074801e-06,
+      "loss": 4.373100757598877,
+      "step": 309
+    },
+    {
+      "epoch": 0.6078431372549019,
+      "grad_norm": 13.614083290100098,
+      "learning_rate": 8.173884385037193e-06,
+      "loss": 4.481573581695557,
+      "step": 310
+    },
+    {
+      "epoch": 0.6098039215686275,
+      "grad_norm": 39.6025505065918,
+      "learning_rate": 8.161595923353516e-06,
+      "loss": 4.316531181335449,
+      "step": 311
+    },
+    {
+      "epoch": 0.611764705882353,
+      "grad_norm": 41.38591003417969,
+      "learning_rate": 8.149275560018816e-06,
+      "loss": 4.617020130157471,
+      "step": 312
+    },
+    {
+      "epoch": 0.6137254901960785,
+      "grad_norm": 156.15367126464844,
+      "learning_rate": 8.136923419350032e-06,
+      "loss": 4.4222869873046875,
+      "step": 313
+    },
+    {
+      "epoch": 0.615686274509804,
+      "grad_norm": 32.320045471191406,
+      "learning_rate": 8.12453962598475e-06,
+      "loss": 4.656857967376709,
+      "step": 314
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "grad_norm": 17.588327407836914,
+      "learning_rate": 8.112124304879938e-06,
+      "loss": 4.441835403442383,
+      "step": 315
+    },
+    {
+      "epoch": 0.6196078431372549,
+      "grad_norm": 30.43013572692871,
+      "learning_rate": 8.0996775813107e-06,
+      "loss": 4.392027854919434,
+      "step": 316
+    },
+    {
+      "epoch": 0.6215686274509804,
+      "grad_norm": 21.386093139648438,
+      "learning_rate": 8.087199580868997e-06,
+      "loss": 4.848608016967773,
+      "step": 317
+    },
+    {
+      "epoch": 0.6235294117647059,
+      "grad_norm": 81.71918487548828,
+      "learning_rate": 8.07469042946238e-06,
+      "loss": 4.443190097808838,
+      "step": 318
+    },
+    {
+      "epoch": 0.6254901960784314,
+      "grad_norm": 20.856964111328125,
+      "learning_rate": 8.062150253312735e-06,
+      "loss": 4.9603166580200195,
+      "step": 319
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 145.81161499023438,
+      "learning_rate": 8.04957917895499e-06,
+      "loss": 4.618847846984863,
+      "step": 320
+    },
+    {
+      "epoch": 0.6294117647058823,
+      "grad_norm": 14.190864562988281,
+      "learning_rate": 8.03697733323585e-06,
+      "loss": 4.593096733093262,
+      "step": 321
+    },
+    {
+      "epoch": 0.6313725490196078,
+      "grad_norm": 23.47496795654297,
+      "learning_rate": 8.024344843312517e-06,
+      "loss": 4.16273307800293,
+      "step": 322
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 39.30678176879883,
+      "learning_rate": 8.011681836651401e-06,
+      "loss": 4.198973655700684,
+      "step": 323
+    },
+    {
+      "epoch": 0.6352941176470588,
+      "grad_norm": 55.29441452026367,
+      "learning_rate": 7.99898844102684e-06,
+      "loss": 4.373217582702637,
+      "step": 324
+    },
+    {
+      "epoch": 0.6372549019607843,
+      "grad_norm": 87.39408111572266,
+      "learning_rate": 7.986264784519801e-06,
+      "loss": 4.491955280303955,
+      "step": 325
+    },
+    {
+      "epoch": 0.6392156862745098,
+      "grad_norm": 71.22431182861328,
+      "learning_rate": 7.973510995516603e-06,
+      "loss": 4.367103576660156,
+      "step": 326
+    },
+    {
+      "epoch": 0.6411764705882353,
+      "grad_norm": 32.032073974609375,
+      "learning_rate": 7.960727202707605e-06,
+      "loss": 4.673696041107178,
+      "step": 327
+    },
+    {
+      "epoch": 0.6431372549019608,
+      "grad_norm": 14.861653327941895,
+      "learning_rate": 7.947913535085925e-06,
+      "loss": 4.37457275390625,
+      "step": 328
+    },
+    {
+      "epoch": 0.6450980392156863,
+      "grad_norm": 43.02954864501953,
+      "learning_rate": 7.935070121946116e-06,
+      "loss": 4.4756364822387695,
+      "step": 329
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 40.1738395690918,
+      "learning_rate": 7.922197092882882e-06,
+      "loss": 4.393209457397461,
+      "step": 330
+    },
+    {
+      "epoch": 0.6490196078431373,
+      "grad_norm": 58.01616668701172,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 4.345884323120117,
+      "step": 331
+    },
+    {
+      "epoch": 0.6509803921568628,
+      "grad_norm": 14.342921257019043,
+      "learning_rate": 7.896362706857825e-06,
+      "loss": 4.297840118408203,
+      "step": 332
+    },
+    {
+      "epoch": 0.6529411764705882,
+      "grad_norm": 8.965250015258789,
+      "learning_rate": 7.883401610574338e-06,
+      "loss": 4.571505546569824,
+      "step": 333
+    },
+    {
+      "epoch": 0.6549019607843137,
+      "grad_norm": 21.012739181518555,
+      "learning_rate": 7.870411419721468e-06,
+      "loss": 4.734814167022705,
+      "step": 334
+    },
+    {
+      "epoch": 0.6568627450980392,
+      "grad_norm": 30.89315414428711,
+      "learning_rate": 7.857392265374963e-06,
+      "loss": 4.410980701446533,
+      "step": 335
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 9.218079566955566,
+      "learning_rate": 7.844344278902815e-06,
+      "loss": 4.341933250427246,
+      "step": 336
+    },
+    {
+      "epoch": 0.6607843137254902,
+      "grad_norm": 17.145496368408203,
+      "learning_rate": 7.83126759196395e-06,
+      "loss": 4.177962779998779,
+      "step": 337
+    },
+    {
+      "epoch": 0.6627450980392157,
+      "grad_norm": 16.176719665527344,
+      "learning_rate": 7.818162336506885e-06,
+      "loss": 4.377812385559082,
+      "step": 338
+    },
+    {
+      "epoch": 0.6647058823529411,
+      "grad_norm": 23.922420501708984,
+      "learning_rate": 7.805028644768407e-06,
+      "loss": 3.9010050296783447,
+      "step": 339
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 467.1762390136719,
+      "learning_rate": 7.791866649272236e-06,
+      "loss": 4.715754508972168,
+      "step": 340
+    },
+    {
+      "epoch": 0.6686274509803921,
+      "grad_norm": 86.71304321289062,
+      "learning_rate": 7.778676482827686e-06,
+      "loss": 4.450630187988281,
+      "step": 341
+    },
+    {
+      "epoch": 0.6705882352941176,
+      "grad_norm": 208.03579711914062,
+      "learning_rate": 7.765458278528327e-06,
+      "loss": 4.261456489562988,
+      "step": 342
+    },
+    {
+      "epoch": 0.6725490196078432,
+      "grad_norm": 10.478469848632812,
+      "learning_rate": 7.752212169750642e-06,
+      "loss": 3.6522653102874756,
+      "step": 343
+    },
+    {
+      "epoch": 0.6745098039215687,
+      "grad_norm": 109.38081359863281,
+      "learning_rate": 7.738938290152675e-06,
+      "loss": 4.505516529083252,
+      "step": 344
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 114.52716827392578,
+      "learning_rate": 7.725636773672694e-06,
+      "loss": 4.370604038238525,
+      "step": 345
+    },
+    {
+      "epoch": 0.6784313725490196,
+      "grad_norm": 14.925344467163086,
+      "learning_rate": 7.712307754527832e-06,
+      "loss": 4.476314544677734,
+      "step": 346
+    },
+    {
+      "epoch": 0.6803921568627451,
+      "grad_norm": 53.75554275512695,
+      "learning_rate": 7.69895136721273e-06,
+      "loss": 4.616474151611328,
+      "step": 347
+    },
+    {
+      "epoch": 0.6823529411764706,
+      "grad_norm": 42.78981399536133,
+      "learning_rate": 7.685567746498191e-06,
+      "loss": 4.426451683044434,
+      "step": 348
+    },
+    {
+      "epoch": 0.6843137254901961,
+      "grad_norm": 80.6156234741211,
+      "learning_rate": 7.672157027429803e-06,
+      "loss": 4.43165397644043,
+      "step": 349
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 46.6151123046875,
+      "learning_rate": 7.658719345326595e-06,
+      "loss": 4.440042495727539,
+      "step": 350
+    },
+    {
+      "epoch": 0.6882352941176471,
+      "grad_norm": 104.17079162597656,
+      "learning_rate": 7.645254835779657e-06,
+      "loss": 4.430392265319824,
+      "step": 351
+    },
+    {
+      "epoch": 0.6901960784313725,
+      "grad_norm": 502.8309020996094,
+      "learning_rate": 7.631763634650783e-06,
+      "loss": 4.152275562286377,
+      "step": 352
+    },
+    {
+      "epoch": 0.692156862745098,
+      "grad_norm": 23.371397018432617,
+      "learning_rate": 7.618245878071091e-06,
+      "loss": 4.074784278869629,
+      "step": 353
+    },
+    {
+      "epoch": 0.6941176470588235,
+      "grad_norm": 93.83110809326172,
+      "learning_rate": 7.604701702439652e-06,
+      "loss": 4.7920379638671875,
+      "step": 354
+    },
+    {
+      "epoch": 0.696078431372549,
+      "grad_norm": 20.388896942138672,
+      "learning_rate": 7.591131244422118e-06,
+      "loss": 4.258466720581055,
+      "step": 355
+    },
+    {
+      "epoch": 0.6980392156862745,
+      "grad_norm": 25.022539138793945,
+      "learning_rate": 7.57753464094934e-06,
+      "loss": 4.348616600036621,
+      "step": 356
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 24.122034072875977,
+      "learning_rate": 7.563912029215983e-06,
+      "loss": 4.450387954711914,
+      "step": 357
+    },
+    {
+      "epoch": 0.7019607843137254,
+      "grad_norm": 47.63944625854492,
+      "learning_rate": 7.550263546679148e-06,
+      "loss": 4.950525760650635,
+      "step": 358
+    },
+    {
+      "epoch": 0.703921568627451,
+      "grad_norm": 18.94533348083496,
+      "learning_rate": 7.536589331056976e-06,
+      "loss": 5.012373924255371,
+      "step": 359
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 96.9211196899414,
+      "learning_rate": 7.522889520327275e-06,
+      "loss": 4.925107955932617,
+      "step": 360
+    },
+    {
+      "epoch": 0.707843137254902,
+      "grad_norm": 42.01844024658203,
+      "learning_rate": 7.509164252726107e-06,
+      "loss": 4.5356903076171875,
+      "step": 361
+    },
+    {
+      "epoch": 0.7098039215686275,
+      "grad_norm": 59.13837814331055,
+      "learning_rate": 7.495413666746406e-06,
+      "loss": 4.559690475463867,
+      "step": 362
+    },
+    {
+      "epoch": 0.711764705882353,
+      "grad_norm": 67.81266784667969,
+      "learning_rate": 7.481637901136578e-06,
+      "loss": 4.372148513793945,
+      "step": 363
+    },
+    {
+      "epoch": 0.7137254901960784,
+      "grad_norm": 35.04251480102539,
+      "learning_rate": 7.467837094899104e-06,
+      "loss": 4.26740837097168,
+      "step": 364
+    },
+    {
+      "epoch": 0.7156862745098039,
+      "grad_norm": 28.242380142211914,
+      "learning_rate": 7.454011387289127e-06,
+      "loss": 4.79606819152832,
+      "step": 365
+    },
+    {
+      "epoch": 0.7176470588235294,
+      "grad_norm": 33.4775505065918,
+      "learning_rate": 7.440160917813059e-06,
+      "loss": 4.412802696228027,
+      "step": 366
+    },
+    {
+      "epoch": 0.7196078431372549,
+      "grad_norm": 58.53046417236328,
+      "learning_rate": 7.426285826227171e-06,
+      "loss": 3.844216823577881,
+      "step": 367
+    },
+    {
+      "epoch": 0.7215686274509804,
+      "grad_norm": 67.4899673461914,
+      "learning_rate": 7.412386252536168e-06,
+      "loss": 4.131912708282471,
+      "step": 368
+    },
+    {
+      "epoch": 0.7235294117647059,
+      "grad_norm": 3803.90185546875,
+      "learning_rate": 7.398462336991802e-06,
+      "loss": 4.365766525268555,
+      "step": 369
+    },
+    {
+      "epoch": 0.7254901960784313,
+      "grad_norm": 76.64689636230469,
+      "learning_rate": 7.384514220091437e-06,
+      "loss": 4.796448707580566,
+      "step": 370
+    },
+    {
+      "epoch": 0.7274509803921568,
+      "grad_norm": 101.20423126220703,
+      "learning_rate": 7.370542042576635e-06,
+      "loss": 4.397182941436768,
+      "step": 371
+    },
+    {
+      "epoch": 0.7294117647058823,
+      "grad_norm": 73.64826965332031,
+      "learning_rate": 7.356545945431744e-06,
+      "loss": 4.440197944641113,
+      "step": 372
+    },
+    {
+      "epoch": 0.7313725490196078,
+      "grad_norm": 66.81968688964844,
+      "learning_rate": 7.342526069882465e-06,
+      "loss": 4.575042724609375,
+      "step": 373
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 40.752525329589844,
+      "learning_rate": 7.328482557394435e-06,
+      "loss": 4.159431457519531,
+      "step": 374
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 27.12578010559082,
+      "learning_rate": 7.314415549671795e-06,
+      "loss": 4.4377336502075195,
+      "step": 375
+    },
+    {
+      "epoch": 0.7372549019607844,
+      "grad_norm": 231.64231872558594,
+      "learning_rate": 7.300325188655762e-06,
+      "loss": 4.438188552856445,
+      "step": 376
+    },
+    {
+      "epoch": 0.7392156862745098,
+      "grad_norm": 23.71122932434082,
+      "learning_rate": 7.286211616523193e-06,
+      "loss": 4.190389633178711,
+      "step": 377
+    },
+    {
+      "epoch": 0.7411764705882353,
+      "grad_norm": 277.79718017578125,
+      "learning_rate": 7.27207497568516e-06,
+      "loss": 3.8417224884033203,
+      "step": 378
+    },
+    {
+      "epoch": 0.7431372549019608,
+      "grad_norm": 30.528398513793945,
+      "learning_rate": 7.257915408785499e-06,
+      "loss": 4.584486961364746,
+      "step": 379
+    },
+    {
+      "epoch": 0.7450980392156863,
+      "grad_norm": 618.6641845703125,
+      "learning_rate": 7.243733058699386e-06,
+      "loss": 4.159678936004639,
+      "step": 380
+    },
+    {
+      "epoch": 0.7470588235294118,
+      "grad_norm": 20.201461791992188,
+      "learning_rate": 7.229528068531881e-06,
+      "loss": 4.334630489349365,
+      "step": 381
+    },
+    {
+      "epoch": 0.7490196078431373,
+      "grad_norm": 69.16433715820312,
+      "learning_rate": 7.215300581616496e-06,
+      "loss": 4.4458160400390625,
+      "step": 382
+    },
+    {
+      "epoch": 0.7509803921568627,
+      "grad_norm": 50.7408332824707,
+      "learning_rate": 7.201050741513735e-06,
+      "loss": 4.584663391113281,
+      "step": 383
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 71.0459213256836,
+      "learning_rate": 7.186778692009669e-06,
+      "loss": 4.636325359344482,
+      "step": 384
+    },
+    {
+      "epoch": 0.7549019607843137,
+      "grad_norm": 38.0345344543457,
+      "learning_rate": 7.172484577114452e-06,
+      "loss": 4.060024261474609,
+      "step": 385
+    },
+    {
+      "epoch": 0.7568627450980392,
+      "grad_norm": 40.320499420166016,
+      "learning_rate": 7.1581685410609e-06,
+      "loss": 4.512998580932617,
+      "step": 386
+    },
+    {
+      "epoch": 0.7588235294117647,
+      "grad_norm": 33.043148040771484,
+      "learning_rate": 7.1438307283030106e-06,
+      "loss": 4.692201614379883,
+      "step": 387
+    },
+    {
+      "epoch": 0.7607843137254902,
+      "grad_norm": 137.872314453125,
+      "learning_rate": 7.129471283514525e-06,
+      "loss": 4.415122985839844,
+      "step": 388
+    },
+    {
+      "epoch": 0.7627450980392156,
+      "grad_norm": 76.47061157226562,
+      "learning_rate": 7.115090351587455e-06,
+      "loss": 4.573295593261719,
+      "step": 389
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 328.7730712890625,
+      "learning_rate": 7.100688077630628e-06,
+      "loss": 4.141142845153809,
+      "step": 390
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 43.609642028808594,
+      "learning_rate": 7.086264606968215e-06,
+      "loss": 4.211104393005371,
+      "step": 391
+    },
+    {
+      "epoch": 0.7686274509803922,
+      "grad_norm": 125.07260131835938,
+      "learning_rate": 7.071820085138275e-06,
+      "loss": 4.797672271728516,
+      "step": 392
+    },
+    {
+      "epoch": 0.7705882352941177,
+      "grad_norm": 61.34317398071289,
+      "learning_rate": 7.05735465789128e-06,
+      "loss": 4.348987579345703,
+      "step": 393
+    },
+    {
+      "epoch": 0.7725490196078432,
+      "grad_norm": 75.8901596069336,
+      "learning_rate": 7.042868471188642e-06,
+      "loss": 4.376434803009033,
+      "step": 394
+    },
+    {
+      "epoch": 0.7745098039215687,
+      "grad_norm": 172.4529571533203,
+      "learning_rate": 7.028361671201245e-06,
+      "loss": 4.280189514160156,
+      "step": 395
+    },
+    {
+      "epoch": 0.7764705882352941,
+      "grad_norm": 67.70394897460938,
+      "learning_rate": 7.013834404307972e-06,
+      "loss": 4.715417861938477,
+      "step": 396
+    },
+    {
+      "epoch": 0.7784313725490196,
+      "grad_norm": 17.541534423828125,
+      "learning_rate": 6.9992868170942205e-06,
+      "loss": 4.301790237426758,
+      "step": 397
+    },
+    {
+      "epoch": 0.7803921568627451,
+      "grad_norm": 17.7639217376709,
+      "learning_rate": 6.9847190563504284e-06,
+      "loss": 4.332895278930664,
+      "step": 398
+    },
+    {
+      "epoch": 0.7823529411764706,
+      "grad_norm": 77.33992767333984,
+      "learning_rate": 6.970131269070591e-06,
+      "loss": 4.072659492492676,
+      "step": 399
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 30.242053985595703,
+      "learning_rate": 6.95552360245078e-06,
+      "loss": 4.5907301902771,
+      "step": 400
+    },
+    {
+      "epoch": 0.7862745098039216,
+      "grad_norm": 157.5186767578125,
+      "learning_rate": 6.940896203887659e-06,
+      "loss": 4.161381721496582,
+      "step": 401
+    },
+    {
+      "epoch": 0.788235294117647,
+      "grad_norm": 48.990875244140625,
+      "learning_rate": 6.926249220976988e-06,
+      "loss": 4.169566631317139,
+      "step": 402
+    },
+    {
+      "epoch": 0.7901960784313725,
+      "grad_norm": 33.2501220703125,
+      "learning_rate": 6.911582801512146e-06,
+      "loss": 4.37021017074585,
+      "step": 403
+    },
+    {
+      "epoch": 0.792156862745098,
+      "grad_norm": 29.51424789428711,
+      "learning_rate": 6.8968970934826296e-06,
+      "loss": 3.938095808029175,
+      "step": 404
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": 86.2677001953125,
+      "learning_rate": 6.88219224507257e-06,
+      "loss": 4.483772277832031,
+      "step": 405
+    },
+    {
+      "epoch": 0.796078431372549,
+      "grad_norm": 25.195167541503906,
+      "learning_rate": 6.867468404659222e-06,
+      "loss": 4.458285331726074,
+      "step": 406
+    },
+    {
+      "epoch": 0.7980392156862746,
+      "grad_norm": 22.213388442993164,
+      "learning_rate": 6.852725720811487e-06,
+      "loss": 3.883963108062744,
+      "step": 407
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 60.982303619384766,
+      "learning_rate": 6.837964342288399e-06,
+      "loss": 4.16390323638916,
+      "step": 408
+    },
+    {
+      "epoch": 0.8019607843137255,
+      "grad_norm": 255.90065002441406,
+      "learning_rate": 6.823184418037625e-06,
+      "loss": 4.246565818786621,
+      "step": 409
+    },
+    {
+      "epoch": 0.803921568627451,
+      "grad_norm": 80.53013610839844,
+      "learning_rate": 6.808386097193969e-06,
+      "loss": 3.941505193710327,
+      "step": 410
+    },
+    {
+      "epoch": 0.8058823529411765,
+      "grad_norm": 70.98387145996094,
+      "learning_rate": 6.793569529077864e-06,
+      "loss": 4.301395416259766,
+      "step": 411
+    },
+    {
+      "epoch": 0.807843137254902,
+      "grad_norm": 117.46578979492188,
+      "learning_rate": 6.778734863193862e-06,
+      "loss": 4.3663835525512695,
+      "step": 412
+    },
+    {
+      "epoch": 0.8098039215686275,
+      "grad_norm": 32.978851318359375,
+      "learning_rate": 6.76388224922913e-06,
+      "loss": 4.204647064208984,
+      "step": 413
+    },
+    {
+      "epoch": 0.8117647058823529,
+      "grad_norm": 21.284744262695312,
+      "learning_rate": 6.7490118370519356e-06,
+      "loss": 4.878431797027588,
+      "step": 414
+    },
+    {
+      "epoch": 0.8137254901960784,
+      "grad_norm": 116.35888671875,
+      "learning_rate": 6.7341237767101375e-06,
+      "loss": 4.751389503479004,
+      "step": 415
+    },
+    {
+      "epoch": 0.8156862745098039,
+      "grad_norm": 58.715450286865234,
+      "learning_rate": 6.7192182184296725e-06,
+      "loss": 4.176122665405273,
+      "step": 416
+    },
+    {
+      "epoch": 0.8176470588235294,
+      "grad_norm": 266.84912109375,
+      "learning_rate": 6.704295312613037e-06,
+      "loss": 4.090945243835449,
+      "step": 417
+    },
+    {
+      "epoch": 0.8196078431372549,
+      "grad_norm": 282.4599609375,
+      "learning_rate": 6.689355209837769e-06,
+      "loss": 4.8022003173828125,
+      "step": 418
+    },
+    {
+      "epoch": 0.8215686274509804,
+      "grad_norm": 17.034099578857422,
+      "learning_rate": 6.674398060854931e-06,
+      "loss": 4.382605075836182,
+      "step": 419
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 45.16923904418945,
+      "learning_rate": 6.65942401658759e-06,
+      "loss": 4.5414934158325195,
+      "step": 420
+    },
+    {
+      "epoch": 0.8254901960784313,
+      "grad_norm": 68.16588592529297,
+      "learning_rate": 6.644433228129288e-06,
+      "loss": 4.519162654876709,
+      "step": 421
+    },
+    {
+      "epoch": 0.8274509803921568,
+      "grad_norm": 30.64187240600586,
+      "learning_rate": 6.6294258467425256e-06,
+      "loss": 4.278877258300781,
+      "step": 422
+    },
+    {
+      "epoch": 0.8294117647058824,
+      "grad_norm": 50.78958511352539,
+      "learning_rate": 6.614402023857231e-06,
+      "loss": 4.127124786376953,
+      "step": 423
+    },
+    {
+      "epoch": 0.8313725490196079,
+      "grad_norm": 16.406599044799805,
+      "learning_rate": 6.599361911069235e-06,
+      "loss": 4.240130424499512,
+      "step": 424
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 8.257003784179688,
+      "learning_rate": 6.584305660138734e-06,
+      "loss": 4.398717880249023,
+      "step": 425
+    },
+    {
+      "epoch": 0.8352941176470589,
+      "grad_norm": 53.47596740722656,
+      "learning_rate": 6.569233422988771e-06,
+      "loss": 4.362873554229736,
+      "step": 426
+    },
+    {
+      "epoch": 0.8372549019607843,
+      "grad_norm": 163.6345672607422,
+      "learning_rate": 6.554145351703689e-06,
+      "loss": 4.455537796020508,
+      "step": 427
+    },
+    {
+      "epoch": 0.8392156862745098,
+      "grad_norm": 222.5769805908203,
+      "learning_rate": 6.539041598527612e-06,
+      "loss": 4.446180820465088,
+      "step": 428
+    },
+    {
+      "epoch": 0.8411764705882353,
+      "grad_norm": 193.03797912597656,
+      "learning_rate": 6.523922315862887e-06,
+      "loss": 3.9635980129241943,
+      "step": 429
+    },
+    {
+      "epoch": 0.8431372549019608,
+      "grad_norm": 259.9488830566406,
+      "learning_rate": 6.508787656268573e-06,
+      "loss": 4.20033073425293,
+      "step": 430
+    },
+    {
+      "epoch": 0.8450980392156863,
+      "grad_norm": 79.64652252197266,
+      "learning_rate": 6.4936377724588794e-06,
+      "loss": 4.132991790771484,
+      "step": 431
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 89.49686431884766,
+      "learning_rate": 6.478472817301635e-06,
+      "loss": 4.8201904296875,
+      "step": 432
+    },
+    {
+      "epoch": 0.8490196078431372,
+      "grad_norm": 36.88655090332031,
+      "learning_rate": 6.463292943816747e-06,
+      "loss": 4.225468635559082,
+      "step": 433
+    },
+    {
+      "epoch": 0.8509803921568627,
+      "grad_norm": 167.7744140625,
+      "learning_rate": 6.448098305174648e-06,
+      "loss": 4.24064826965332,
+      "step": 434
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 320.5234069824219,
+      "learning_rate": 6.4328890546947645e-06,
+      "loss": 4.498333930969238,
+      "step": 435
+    },
+    {
+      "epoch": 0.8549019607843137,
+      "grad_norm": 108.37223815917969,
+      "learning_rate": 6.417665345843952e-06,
+      "loss": 3.9274849891662598,
+      "step": 436
+    },
+    {
+      "epoch": 0.8568627450980392,
+      "grad_norm": 53.389373779296875,
+      "learning_rate": 6.402427332234965e-06,
+      "loss": 4.50510835647583,
+      "step": 437
+    },
+    {
+      "epoch": 0.8588235294117647,
+      "grad_norm": 586.7931518554688,
+      "learning_rate": 6.387175167624894e-06,
+      "loss": 4.44918966293335,
+      "step": 438
+    },
+    {
+      "epoch": 0.8607843137254902,
+      "grad_norm": 64.9321517944336,
+      "learning_rate": 6.371909005913618e-06,
+      "loss": 4.453424453735352,
+      "step": 439
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 21.094820022583008,
+      "learning_rate": 6.3566290011422515e-06,
+      "loss": 4.252875328063965,
+      "step": 440
+    },
+    {
+      "epoch": 0.8647058823529412,
+      "grad_norm": 302.2917785644531,
+      "learning_rate": 6.341335307491596e-06,
+      "loss": 3.92726993560791,
+      "step": 441
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 44.52492141723633,
+      "learning_rate": 6.32602807928057e-06,
+      "loss": 4.290216445922852,
+      "step": 442
+    },
+    {
+      "epoch": 0.8686274509803922,
+      "grad_norm": 48.71710205078125,
+      "learning_rate": 6.310707470964668e-06,
+      "loss": 4.29799747467041,
+      "step": 443
+    },
+    {
+      "epoch": 0.8705882352941177,
+      "grad_norm": 224.1940460205078,
+      "learning_rate": 6.29537363713439e-06,
+      "loss": 4.234777450561523,
+      "step": 444
+    },
+    {
+      "epoch": 0.8725490196078431,
+      "grad_norm": 198.24740600585938,
+      "learning_rate": 6.280026732513689e-06,
+      "loss": 4.185808181762695,
+      "step": 445
+    },
+    {
+      "epoch": 0.8745098039215686,
+      "grad_norm": 35.172672271728516,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 4.557499885559082,
+      "step": 446
+    },
+    {
+      "epoch": 0.8764705882352941,
+      "grad_norm": 63.40365219116211,
+      "learning_rate": 6.249294330454705e-06,
+      "loss": 4.098924160003662,
+      "step": 447
+    },
+    {
+      "epoch": 0.8784313725490196,
+      "grad_norm": 145.4202117919922,
+      "learning_rate": 6.233909143117521e-06,
+      "loss": 4.268922805786133,
+      "step": 448
+    },
+    {
+      "epoch": 0.8803921568627451,
+      "grad_norm": 149.33828735351562,
+      "learning_rate": 6.21851150518898e-06,
+      "loss": 4.938076019287109,
+      "step": 449
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 42.62335205078125,
+      "learning_rate": 6.203101572036839e-06,
+      "loss": 4.535097599029541,
+      "step": 450
+    },
+    {
+      "epoch": 0.884313725490196,
+      "grad_norm": 29.659095764160156,
+      "learning_rate": 6.18767949915292e-06,
+      "loss": 4.5162248611450195,
+      "step": 451
+    },
+    {
+      "epoch": 0.8862745098039215,
+      "grad_norm": 385.17120361328125,
+      "learning_rate": 6.172245442151541e-06,
+      "loss": 4.205960273742676,
+      "step": 452
+    },
+    {
+      "epoch": 0.888235294117647,
+      "grad_norm": 41.33932113647461,
+      "learning_rate": 6.156799556767941e-06,
+      "loss": 4.351683139801025,
+      "step": 453
+    },
+    {
+      "epoch": 0.8901960784313725,
+      "grad_norm": 143.6595458984375,
+      "learning_rate": 6.141341998856711e-06,
+      "loss": 4.250962257385254,
+      "step": 454
+    },
+    {
+      "epoch": 0.8921568627450981,
+      "grad_norm": 37.78490447998047,
+      "learning_rate": 6.125872924390226e-06,
+      "loss": 4.384239196777344,
+      "step": 455
+    },
+    {
+      "epoch": 0.8941176470588236,
+      "grad_norm": 515.0045166015625,
+      "learning_rate": 6.110392489457067e-06,
+      "loss": 4.019399166107178,
+      "step": 456
+    },
+    {
+      "epoch": 0.8960784313725491,
+      "grad_norm": 55.70957946777344,
+      "learning_rate": 6.094900850260439e-06,
+      "loss": 4.14704704284668,
+      "step": 457
+    },
+    {
+      "epoch": 0.8980392156862745,
+      "grad_norm": 193.2394256591797,
+      "learning_rate": 6.079398163116611e-06,
+      "loss": 4.078997611999512,
+      "step": 458
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5256.82421875,
+      "learning_rate": 6.063884584453326e-06,
+      "loss": 4.191615104675293,
+      "step": 459
+    },
+    {
+      "epoch": 0.9019607843137255,
+      "grad_norm": 100.2900390625,
+      "learning_rate": 6.048360270808226e-06,
+      "loss": 4.465028762817383,
+      "step": 460
+    },
+    {
+      "epoch": 0.903921568627451,
+      "grad_norm": 1331.4735107421875,
+      "learning_rate": 6.032825378827273e-06,
+      "loss": 4.066887378692627,
+      "step": 461
+    },
+    {
+      "epoch": 0.9058823529411765,
+      "grad_norm": 452.3879699707031,
+      "learning_rate": 6.0172800652631706e-06,
+      "loss": 4.527779579162598,
+      "step": 462
+    },
+    {
+      "epoch": 0.907843137254902,
+      "grad_norm": 2017.1990966796875,
+      "learning_rate": 6.001724486973774e-06,
+      "loss": 4.606598854064941,
+      "step": 463
+    },
+    {
+      "epoch": 0.9098039215686274,
+      "grad_norm": 754.1237182617188,
+      "learning_rate": 5.986158800920523e-06,
+      "loss": 4.566285133361816,
+      "step": 464
+    },
+    {
+      "epoch": 0.9117647058823529,
+      "grad_norm": 384.491943359375,
+      "learning_rate": 5.970583164166838e-06,
+      "loss": 4.586278915405273,
+      "step": 465
+    },
+    {
+      "epoch": 0.9137254901960784,
+      "grad_norm": 33.79523468017578,
+      "learning_rate": 5.954997733876552e-06,
+      "loss": 3.9631872177124023,
+      "step": 466
+    },
+    {
+      "epoch": 0.9156862745098039,
+      "grad_norm": 66.47810363769531,
+      "learning_rate": 5.939402667312316e-06,
+      "loss": 4.857361793518066,
+      "step": 467
+    },
+    {
+      "epoch": 0.9176470588235294,
+      "grad_norm": 32.95048904418945,
+      "learning_rate": 5.923798121834016e-06,
+      "loss": 4.744093418121338,
+      "step": 468
+    },
+    {
+      "epoch": 0.9196078431372549,
+      "grad_norm": 66.45060729980469,
+      "learning_rate": 5.908184254897183e-06,
+      "loss": 4.424873352050781,
+      "step": 469
+    },
+    {
+      "epoch": 0.9215686274509803,
+      "grad_norm": 160.2024688720703,
+      "learning_rate": 5.892561224051403e-06,
+      "loss": 4.0311994552612305,
+      "step": 470
+    },
+    {
+      "epoch": 0.9235294117647059,
+      "grad_norm": 26.441673278808594,
+      "learning_rate": 5.876929186938734e-06,
+      "loss": 4.408843040466309,
+      "step": 471
+    },
+    {
+      "epoch": 0.9254901960784314,
+      "grad_norm": 95.61007690429688,
+      "learning_rate": 5.861288301292103e-06,
+      "loss": 4.58468770980835,
+      "step": 472
+    },
+    {
+      "epoch": 0.9274509803921569,
+      "grad_norm": 101.88788604736328,
+      "learning_rate": 5.845638724933729e-06,
+      "loss": 4.604763031005859,
+      "step": 473
+    },
+    {
+      "epoch": 0.9294117647058824,
+      "grad_norm": 196.6406707763672,
+      "learning_rate": 5.82998061577352e-06,
+      "loss": 3.798020839691162,
+      "step": 474
+    },
+    {
+      "epoch": 0.9313725490196079,
+      "grad_norm": 64.56034088134766,
+      "learning_rate": 5.814314131807486e-06,
+      "loss": 4.227663040161133,
+      "step": 475
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 43.46277618408203,
+      "learning_rate": 5.798639431116135e-06,
+      "loss": 4.6275858879089355,
+      "step": 476
+    },
+    {
+      "epoch": 0.9352941176470588,
+      "grad_norm": 624.3564453125,
+      "learning_rate": 5.782956671862895e-06,
+      "loss": 4.316646575927734,
+      "step": 477
+    },
+    {
+      "epoch": 0.9372549019607843,
+      "grad_norm": 105.81096649169922,
+      "learning_rate": 5.767266012292496e-06,
+      "loss": 4.3191094398498535,
+      "step": 478
+    },
+    {
+      "epoch": 0.9392156862745098,
+      "grad_norm": 11.598875045776367,
+      "learning_rate": 5.751567610729398e-06,
+      "loss": 4.125179767608643,
+      "step": 479
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 80.84516143798828,
+      "learning_rate": 5.735861625576167e-06,
+      "loss": 4.346436977386475,
+      "step": 480
+    },
+    {
+      "epoch": 0.9431372549019608,
+      "grad_norm": 74.3943862915039,
+      "learning_rate": 5.720148215311902e-06,
+      "loss": 4.7361907958984375,
+      "step": 481
+    },
+    {
+      "epoch": 0.9450980392156862,
+      "grad_norm": 28.853347778320312,
+      "learning_rate": 5.7044275384906164e-06,
+      "loss": 4.320212364196777,
+      "step": 482
+    },
+    {
+      "epoch": 0.9470588235294117,
+      "grad_norm": 12.190153121948242,
+      "learning_rate": 5.688699753739649e-06,
+      "loss": 4.433542251586914,
+      "step": 483
+    },
+    {
+      "epoch": 0.9490196078431372,
+      "grad_norm": 14.953727722167969,
+      "learning_rate": 5.672965019758061e-06,
+      "loss": 4.154573440551758,
+      "step": 484
+    },
+    {
+      "epoch": 0.9509803921568627,
+      "grad_norm": 45.093048095703125,
+      "learning_rate": 5.657223495315031e-06,
+      "loss": 4.646431922912598,
+      "step": 485
+    },
+    {
+      "epoch": 0.9529411764705882,
+      "grad_norm": 67.42533111572266,
+      "learning_rate": 5.641475339248257e-06,
+      "loss": 4.0797953605651855,
+      "step": 486
+    },
+    {
+      "epoch": 0.9549019607843138,
+      "grad_norm": 31.419174194335938,
+      "learning_rate": 5.625720710462352e-06,
+      "loss": 4.35106086730957,
+      "step": 487
+    },
+    {
+      "epoch": 0.9568627450980393,
+      "grad_norm": 72.13565063476562,
+      "learning_rate": 5.609959767927247e-06,
+      "loss": 4.7546563148498535,
+      "step": 488
+    },
+    {
+      "epoch": 0.9588235294117647,
+      "grad_norm": 1067.875,
+      "learning_rate": 5.594192670676568e-06,
+      "loss": 4.418883323669434,
+      "step": 489
+    },
+    {
+      "epoch": 0.9607843137254902,
+      "grad_norm": 183.54017639160156,
+      "learning_rate": 5.578419577806058e-06,
+      "loss": 4.376974105834961,
+      "step": 490
+    },
+    {
+      "epoch": 0.9627450980392157,
+      "grad_norm": 95.38218688964844,
+      "learning_rate": 5.562640648471951e-06,
+      "loss": 4.362179756164551,
+      "step": 491
+    },
+    {
+      "epoch": 0.9647058823529412,
+      "grad_norm": 71.57412719726562,
+      "learning_rate": 5.546856041889374e-06,
+      "loss": 4.819134712219238,
+      "step": 492
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 16.976749420166016,
+      "learning_rate": 5.531065917330737e-06,
+      "loss": 4.120271682739258,
+      "step": 493
+    },
+    {
+      "epoch": 0.9686274509803922,
+      "grad_norm": 71.98576354980469,
+      "learning_rate": 5.515270434124136e-06,
+      "loss": 4.1797919273376465,
+      "step": 494
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 4.768789768218994,
+      "learning_rate": 5.499469751651728e-06,
+      "loss": 4.024587631225586,
+      "step": 495
+    },
+    {
+      "epoch": 0.9725490196078431,
+      "grad_norm": 408.6588134765625,
+      "learning_rate": 5.483664029348141e-06,
+      "loss": 4.756344795227051,
+      "step": 496
+    },
+    {
+      "epoch": 0.9745098039215686,
+      "grad_norm": 10.495368957519531,
+      "learning_rate": 5.467853426698852e-06,
+      "loss": 4.134525299072266,
+      "step": 497
+    },
+    {
+      "epoch": 0.9764705882352941,
+      "grad_norm": 183.8063201904297,
+      "learning_rate": 5.452038103238582e-06,
+      "loss": 4.6963725090026855,
+      "step": 498
+    },
+    {
+      "epoch": 0.9784313725490196,
+      "grad_norm": 83.09385681152344,
+      "learning_rate": 5.43621821854969e-06,
+      "loss": 4.915416717529297,
+      "step": 499
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 33.74040985107422,
+      "learning_rate": 5.420393932260557e-06,
+      "loss": 4.430484294891357,
+      "step": 500
+    },
+    {
+      "epoch": 0.9823529411764705,
+      "grad_norm": 41.18917465209961,
+      "learning_rate": 5.404565404043977e-06,
+      "loss": 4.3449602127075195,
+      "step": 501
+    },
+    {
+      "epoch": 0.984313725490196,
+      "grad_norm": 243.4974822998047,
+      "learning_rate": 5.388732793615551e-06,
+      "loss": 4.609969139099121,
+      "step": 502
+    },
+    {
+      "epoch": 0.9862745098039216,
+      "grad_norm": 24.437667846679688,
+      "learning_rate": 5.372896260732065e-06,
+      "loss": 4.368291854858398,
+      "step": 503
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "grad_norm": 36.5069694519043,
+      "learning_rate": 5.357055965189888e-06,
+      "loss": 4.355335712432861,
+      "step": 504
+    },
+    {
+      "epoch": 0.9901960784313726,
+      "grad_norm": 156.41387939453125,
+      "learning_rate": 5.341212066823356e-06,
+      "loss": 4.198671340942383,
+      "step": 505
+    },
+    {
+      "epoch": 0.9921568627450981,
+      "grad_norm": 32.02665710449219,
+      "learning_rate": 5.325364725503155e-06,
+      "loss": 5.039112567901611,
+      "step": 506
+    },
+    {
+      "epoch": 0.9941176470588236,
+      "grad_norm": 28.728458404541016,
+      "learning_rate": 5.3095141011347155e-06,
+      "loss": 4.022368907928467,
+      "step": 507
+    },
+    {
+      "epoch": 0.996078431372549,
+      "grad_norm": 82.8222427368164,
+      "learning_rate": 5.2936603536565915e-06,
+      "loss": 4.288028717041016,
+      "step": 508
+    },
+    {
+      "epoch": 0.9980392156862745,
+      "grad_norm": 46.44649124145508,
+      "learning_rate": 5.277803643038855e-06,
+      "loss": 4.239832401275635,
+      "step": 509
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 85.16124725341797,
+      "learning_rate": 5.261944129281474e-06,
+      "loss": 4.053654193878174,
+      "step": 510
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1020,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.411555016453128e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b008530e22acccf367c57c94461395f10e23b15baa643afb0d25dfaf97317e
+size 5905