Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-500/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-500/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-500/config.json

@@ -0,0 +1,86 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3840,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "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"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 1024,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 262208
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.56.1"
+}

checkpoint-500/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4c14f38ffc9e23d873fa999eea1fc965dcedcec267e7a99f07c6fdbe8760d8
+size 4915892992

checkpoint-500/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0335ce336b31e38c581326acb77ff28330c2073764b1924ad7108d788b56ba68
+size 4931294472

checkpoint-500/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d6a60cf6a1708be0613ab7c4d10457ad99b98c02e40ebd5f320fe02aa0d50c
+size 4931294528

checkpoint-500/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd9340bc368427bcc805e329f32ec7f6a73ab12274d00a8b9c03d49fe0853d0
+size 4931294528

checkpoint-500/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80ec30fa09df9cb78149b3af4da5e7f22bbe89087198871d4f36c70903e30a6
+size 3822364808

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,634 @@
+{
+  "metadata": {
+    "total_parameters": 11766034176,
+    "total_size": 23532068352
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779a932e1b89a14f7e02977a3910a0c61fbd5749797168bfcc9989c9625e1413
+size 18355

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b6509f8bbdd943c9f8984cdc19d5d17ca63b6e47cd6e28080ebf502da06ddc
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63481e620bd287eefb582d20daf306c54c7268088fea6f19af8100945c7e3e7e
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-500/trainer_state.json

@@ -0,0 +1,644 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.085290367901325,
+      "epoch": 0.008,
+      "grad_norm": 0.0146484375,
+      "learning_rate": 1.8e-07,
+      "loss": 2.8737,
+      "mean_token_accuracy": 0.48555898685008286,
+      "num_tokens": 173886.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.082674165070057,
+      "epoch": 0.016,
+      "grad_norm": 0.00750732421875,
+      "learning_rate": 3.8e-07,
+      "loss": 2.8766,
+      "mean_token_accuracy": 0.48314503096044065,
+      "num_tokens": 338352.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.083346585184336,
+      "epoch": 0.024,
+      "grad_norm": 0.01116943359375,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 2.8206,
+      "mean_token_accuracy": 0.4898203007876873,
+      "num_tokens": 505613.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.084573998302221,
+      "epoch": 0.032,
+      "grad_norm": 0.01361083984375,
+      "learning_rate": 7.8e-07,
+      "loss": 2.846,
+      "mean_token_accuracy": 0.4879810094833374,
+      "num_tokens": 671193.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.112175610661507,
+      "epoch": 0.04,
+      "grad_norm": 0.0184326171875,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 2.8945,
+      "mean_token_accuracy": 0.48235367350280284,
+      "num_tokens": 835868.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.004745631664991,
+      "epoch": 0.048,
+      "grad_norm": 0.01055908203125,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 2.7943,
+      "mean_token_accuracy": 0.4953182445839047,
+      "num_tokens": 1001008.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.0760968685150147,
+      "epoch": 0.056,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 2.8689,
+      "mean_token_accuracy": 0.48274643896147607,
+      "num_tokens": 1166615.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.1421599693596365,
+      "epoch": 0.064,
+      "grad_norm": 0.01226806640625,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 2.927,
+      "mean_token_accuracy": 0.47564963400363924,
+      "num_tokens": 1331208.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.0629068821668626,
+      "epoch": 0.072,
+      "grad_norm": 0.00994873046875,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 2.8669,
+      "mean_token_accuracy": 0.48655857108533385,
+      "num_tokens": 1499449.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.1223726868629456,
+      "epoch": 0.08,
+      "grad_norm": 0.0184326171875,
+      "learning_rate": 1.98e-06,
+      "loss": 2.8834,
+      "mean_token_accuracy": 0.48028963077813386,
+      "num_tokens": 1667532.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 1667532.0,
+      "eval_coding_runtime": 96.0471,
+      "eval_coding_samples_per_second": 5.206,
+      "eval_coding_steps_per_second": 2.603,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 1667532.0,
+      "eval_physics_runtime": 63.6847,
+      "eval_physics_samples_per_second": 7.851,
+      "eval_physics_steps_per_second": 3.926,
+      "step": 100
+    },
+    {
+      "entropy": 2.028460328280926,
+      "epoch": 0.088,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 2.7998,
+      "mean_token_accuracy": 0.4919602179899812,
+      "num_tokens": 1835489.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.0500536493957044,
+      "epoch": 0.096,
+      "grad_norm": 0.0166015625,
+      "learning_rate": 2.38e-06,
+      "loss": 2.843,
+      "mean_token_accuracy": 0.486666096188128,
+      "num_tokens": 2007176.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.133950074762106,
+      "epoch": 0.104,
+      "grad_norm": 0.00897216796875,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 2.908,
+      "mean_token_accuracy": 0.47787463404238223,
+      "num_tokens": 2171335.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.0415130145847797,
+      "epoch": 0.112,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 2.8213,
+      "mean_token_accuracy": 0.48844432439655067,
+      "num_tokens": 2342259.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.19760585129261,
+      "epoch": 0.12,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 2.9587,
+      "mean_token_accuracy": 0.4719714432954788,
+      "num_tokens": 2504279.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.133862767368555,
+      "epoch": 0.128,
+      "grad_norm": 0.0101318359375,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 2.895,
+      "mean_token_accuracy": 0.48206167966127395,
+      "num_tokens": 2663987.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.1023842833936213,
+      "epoch": 0.136,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 2.8679,
+      "mean_token_accuracy": 0.48314376436173917,
+      "num_tokens": 2829720.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.096611645817757,
+      "epoch": 0.144,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 3.58e-06,
+      "loss": 2.882,
+      "mean_token_accuracy": 0.4854999572038651,
+      "num_tokens": 2997824.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.104377479106188,
+      "epoch": 0.152,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 2.8908,
+      "mean_token_accuracy": 0.48179021421819923,
+      "num_tokens": 3159946.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.091322401165962,
+      "epoch": 0.16,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 2.8428,
+      "mean_token_accuracy": 0.4882024429738522,
+      "num_tokens": 3330597.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 3330597.0,
+      "eval_coding_runtime": 95.6196,
+      "eval_coding_samples_per_second": 5.229,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 3330597.0,
+      "eval_physics_runtime": 63.6492,
+      "eval_physics_samples_per_second": 7.856,
+      "eval_physics_steps_per_second": 3.928,
+      "step": 200
+    },
+    {
+      "entropy": 2.142216607928276,
+      "epoch": 0.168,
+      "grad_norm": 0.00701904296875,
+      "learning_rate": 4.18e-06,
+      "loss": 2.9186,
+      "mean_token_accuracy": 0.4779110599309206,
+      "num_tokens": 3496104.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.1577497258782388,
+      "epoch": 0.176,
+      "grad_norm": 0.010498046875,
+      "learning_rate": 4.38e-06,
+      "loss": 2.9356,
+      "mean_token_accuracy": 0.4760912239551544,
+      "num_tokens": 3658264.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.1311790965497495,
+      "epoch": 0.184,
+      "grad_norm": 0.006317138671875,
+      "learning_rate": 4.58e-06,
+      "loss": 2.8804,
+      "mean_token_accuracy": 0.48113634046167136,
+      "num_tokens": 3821352.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.110344947129488,
+      "epoch": 0.192,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 4.78e-06,
+      "loss": 2.8458,
+      "mean_token_accuracy": 0.4866057766601443,
+      "num_tokens": 3995568.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.1274008348584177,
+      "epoch": 0.2,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 2.9325,
+      "mean_token_accuracy": 0.47856651023030283,
+      "num_tokens": 4160918.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.0445496000349523,
+      "epoch": 0.208,
+      "grad_norm": 0.0072021484375,
+      "learning_rate": 5.18e-06,
+      "loss": 2.7895,
+      "mean_token_accuracy": 0.49246302992105484,
+      "num_tokens": 4321436.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.118650445342064,
+      "epoch": 0.216,
+      "grad_norm": 0.0118408203125,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 2.831,
+      "mean_token_accuracy": 0.48565028738230465,
+      "num_tokens": 4482225.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.0710766136646273,
+      "epoch": 0.224,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 2.8524,
+      "mean_token_accuracy": 0.4889204766601324,
+      "num_tokens": 4648491.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.0747790560126305,
+      "epoch": 0.232,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 5.78e-06,
+      "loss": 2.8736,
+      "mean_token_accuracy": 0.4836031161248684,
+      "num_tokens": 4813449.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.1116694904863835,
+      "epoch": 0.24,
+      "grad_norm": 0.01141357421875,
+      "learning_rate": 5.98e-06,
+      "loss": 2.8974,
+      "mean_token_accuracy": 0.47815693244338037,
+      "num_tokens": 4986175.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 4986175.0,
+      "eval_coding_runtime": 95.7299,
+      "eval_coding_samples_per_second": 5.223,
+      "eval_coding_steps_per_second": 2.612,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 4986175.0,
+      "eval_physics_runtime": 63.6784,
+      "eval_physics_samples_per_second": 7.852,
+      "eval_physics_steps_per_second": 3.926,
+      "step": 300
+    },
+    {
+      "entropy": 2.085676248371601,
+      "epoch": 0.248,
+      "grad_norm": 0.01513671875,
+      "learning_rate": 6.18e-06,
+      "loss": 2.8547,
+      "mean_token_accuracy": 0.4871716873720288,
+      "num_tokens": 5164741.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.111249604821205,
+      "epoch": 0.256,
+      "grad_norm": 0.01324462890625,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 2.869,
+      "mean_token_accuracy": 0.482149850204587,
+      "num_tokens": 5329320.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.0735500395298003,
+      "epoch": 0.264,
+      "grad_norm": 0.01300048828125,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 2.815,
+      "mean_token_accuracy": 0.4895795300602913,
+      "num_tokens": 5497259.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.1957527093589304,
+      "epoch": 0.272,
+      "grad_norm": 0.0155029296875,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 2.9296,
+      "mean_token_accuracy": 0.4737250735983253,
+      "num_tokens": 5658796.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.0978702254593373,
+      "epoch": 0.28,
+      "grad_norm": 0.012939453125,
+      "learning_rate": 6.98e-06,
+      "loss": 2.9223,
+      "mean_token_accuracy": 0.47742239478975534,
+      "num_tokens": 5819027.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.126638425886631,
+      "epoch": 0.288,
+      "grad_norm": 0.01104736328125,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 2.8822,
+      "mean_token_accuracy": 0.48392471522092817,
+      "num_tokens": 5980201.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.1021372735500337,
+      "epoch": 0.296,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 2.8638,
+      "mean_token_accuracy": 0.4845348121598363,
+      "num_tokens": 6139830.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.1106897443532944,
+      "epoch": 0.304,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 7.58e-06,
+      "loss": 2.8357,
+      "mean_token_accuracy": 0.4834788400679827,
+      "num_tokens": 6298858.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.143523923307657,
+      "epoch": 0.312,
+      "grad_norm": 0.00958251953125,
+      "learning_rate": 7.78e-06,
+      "loss": 2.9236,
+      "mean_token_accuracy": 0.47671638112515213,
+      "num_tokens": 6456502.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.1132052429020405,
+      "epoch": 0.32,
+      "grad_norm": 0.01336669921875,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 2.8795,
+      "mean_token_accuracy": 0.48184755612164737,
+      "num_tokens": 6622798.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 6622798.0,
+      "eval_coding_runtime": 95.588,
+      "eval_coding_samples_per_second": 5.231,
+      "eval_coding_steps_per_second": 2.615,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 6622798.0,
+      "eval_physics_runtime": 63.5621,
+      "eval_physics_samples_per_second": 7.866,
+      "eval_physics_steps_per_second": 3.933,
+      "step": 400
+    },
+    {
+      "entropy": 2.1359100699424745,
+      "epoch": 0.328,
+      "grad_norm": 0.01220703125,
+      "learning_rate": 8.18e-06,
+      "loss": 2.892,
+      "mean_token_accuracy": 0.4762568075209856,
+      "num_tokens": 6782985.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.080799935385585,
+      "epoch": 0.336,
+      "grad_norm": 0.021484375,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 2.8705,
+      "mean_token_accuracy": 0.4826640056446195,
+      "num_tokens": 6953611.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.0621030911803246,
+      "epoch": 0.344,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 2.777,
+      "mean_token_accuracy": 0.48948597013950346,
+      "num_tokens": 7121949.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.0954283088445664,
+      "epoch": 0.352,
+      "grad_norm": 0.01080322265625,
+      "learning_rate": 8.78e-06,
+      "loss": 2.8529,
+      "mean_token_accuracy": 0.48598715253174307,
+      "num_tokens": 7290378.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.1145325861871243,
+      "epoch": 0.36,
+      "grad_norm": 0.01611328125,
+      "learning_rate": 8.98e-06,
+      "loss": 2.864,
+      "mean_token_accuracy": 0.48475142791867254,
+      "num_tokens": 7452920.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.0749227844178675,
+      "epoch": 0.368,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 2.842,
+      "mean_token_accuracy": 0.4888931142166257,
+      "num_tokens": 7621082.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.158674482256174,
+      "epoch": 0.376,
+      "grad_norm": 0.0189208984375,
+      "learning_rate": 9.38e-06,
+      "loss": 2.8965,
+      "mean_token_accuracy": 0.47893171701580284,
+      "num_tokens": 7787036.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.172913119196892,
+      "epoch": 0.384,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 9.58e-06,
+      "loss": 2.9484,
+      "mean_token_accuracy": 0.47502864580601456,
+      "num_tokens": 7955570.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.133708968013525,
+      "epoch": 0.392,
+      "grad_norm": 0.0089111328125,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 2.9115,
+      "mean_token_accuracy": 0.481097811833024,
+      "num_tokens": 8123527.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.075808613747358,
+      "epoch": 0.4,
+      "grad_norm": 0.01458740234375,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 2.8509,
+      "mean_token_accuracy": 0.4880217058584094,
+      "num_tokens": 8291049.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 8291049.0,
+      "eval_coding_runtime": 95.8745,
+      "eval_coding_samples_per_second": 5.215,
+      "eval_coding_steps_per_second": 2.608,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_physics_entropy": 2.116599133968353,
+      "eval_physics_loss": 2.9798319339752197,
+      "eval_physics_mean_token_accuracy": 0.4795549786090851,
+      "eval_physics_num_tokens": 8291049.0,
+      "eval_physics_runtime": 63.2475,
+      "eval_physics_samples_per_second": 7.905,
+      "eval_physics_steps_per_second": 3.953,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.705049732570829e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594a67699005466f1daf68590dd4f89845497a197a7fed03f0c80b5f94e6119e
+size 6417