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 sha256:5c069b8c199241e3bda2d2c126288dea0f3867cf1d0ce8e9ee29b8a8a9d13a7c
+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": 0.4451121126133645,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.4347459591925142,
+      "epoch": 0.00890224225226729,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 1.8e-07,
+      "loss": 3.3392,
+      "mean_token_accuracy": 0.4414398778229952,
+      "num_tokens": 128968.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.5189025782048704,
+      "epoch": 0.01780448450453458,
+      "grad_norm": 0.0098876953125,
+      "learning_rate": 3.8e-07,
+      "loss": 3.4461,
+      "mean_token_accuracy": 0.42950069066137075,
+      "num_tokens": 257189.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.4521907046437263,
+      "epoch": 0.026706726756801868,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 3.3929,
+      "mean_token_accuracy": 0.43435896690934894,
+      "num_tokens": 394654.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.4908889502286913,
+      "epoch": 0.03560896900906916,
+      "grad_norm": 0.00909423828125,
+      "learning_rate": 7.8e-07,
+      "loss": 3.3731,
+      "mean_token_accuracy": 0.4337937039323151,
+      "num_tokens": 528285.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.4656582184135916,
+      "epoch": 0.04451121126133645,
+      "grad_norm": 0.0078125,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 3.3705,
+      "mean_token_accuracy": 0.4305401614867151,
+      "num_tokens": 663126.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.5354390598833563,
+      "epoch": 0.053413453513603736,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 3.4166,
+      "mean_token_accuracy": 0.42836275026202203,
+      "num_tokens": 801635.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.496990965306759,
+      "epoch": 0.06231569576587103,
+      "grad_norm": 0.00885009765625,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 3.4009,
+      "mean_token_accuracy": 0.43142524575814606,
+      "num_tokens": 931344.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.5406345002353192,
+      "epoch": 0.07121793801813832,
+      "grad_norm": 0.007171630859375,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 3.4506,
+      "mean_token_accuracy": 0.42618109108880164,
+      "num_tokens": 1060812.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.4690978921949864,
+      "epoch": 0.08012018027040561,
+      "grad_norm": 0.0111083984375,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 3.375,
+      "mean_token_accuracy": 0.4317979410290718,
+      "num_tokens": 1200650.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.537689981609583,
+      "epoch": 0.0890224225226729,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 1.98e-06,
+      "loss": 3.4588,
+      "mean_token_accuracy": 0.4282337296754122,
+      "num_tokens": 1327380.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 1327380.0,
+      "eval_coding_runtime": 96.2988,
+      "eval_coding_samples_per_second": 5.192,
+      "eval_coding_steps_per_second": 2.596,
+      "step": 100
+    },
+    {
+      "epoch": 0.0890224225226729,
+      "eval_chemistry_entropy": 2.520227357387543,
+      "eval_chemistry_loss": 3.5777227878570557,
+      "eval_chemistry_mean_token_accuracy": 0.4262875291109085,
+      "eval_chemistry_num_tokens": 1327380.0,
+      "eval_chemistry_runtime": 53.689,
+      "eval_chemistry_samples_per_second": 9.313,
+      "eval_chemistry_steps_per_second": 4.656,
+      "step": 100
+    },
+    {
+      "entropy": 2.541736252605915,
+      "epoch": 0.09792466477494019,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 3.4778,
+      "mean_token_accuracy": 0.42182709854096173,
+      "num_tokens": 1460130.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.4891932401806116,
+      "epoch": 0.10682690702720747,
+      "grad_norm": 0.0091552734375,
+      "learning_rate": 2.38e-06,
+      "loss": 3.4123,
+      "mean_token_accuracy": 0.4318336697295308,
+      "num_tokens": 1597405.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.549714620411396,
+      "epoch": 0.11572914927947477,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 3.5233,
+      "mean_token_accuracy": 0.4176134932786226,
+      "num_tokens": 1728207.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.5017867423594,
+      "epoch": 0.12463139153174206,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 3.4252,
+      "mean_token_accuracy": 0.4325200604274869,
+      "num_tokens": 1859684.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.607860314100981,
+      "epoch": 0.13353363378400934,
+      "grad_norm": 0.0086669921875,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 3.5854,
+      "mean_token_accuracy": 0.41672497261315583,
+      "num_tokens": 1985766.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.546873392164707,
+      "epoch": 0.14243587603627664,
+      "grad_norm": 0.0096435546875,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 3.4451,
+      "mean_token_accuracy": 0.42558788452297447,
+      "num_tokens": 2118068.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.5062545992434027,
+      "epoch": 0.15133811828854393,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 3.4525,
+      "mean_token_accuracy": 0.42451597433537247,
+      "num_tokens": 2252650.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.490347370505333,
+      "epoch": 0.16024036054081123,
+      "grad_norm": 0.0106201171875,
+      "learning_rate": 3.58e-06,
+      "loss": 3.398,
+      "mean_token_accuracy": 0.4340389359742403,
+      "num_tokens": 2388824.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.5069186124950646,
+      "epoch": 0.1691426027930785,
+      "grad_norm": 0.01055908203125,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 3.4995,
+      "mean_token_accuracy": 0.42545853555202484,
+      "num_tokens": 2515325.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.569493807852268,
+      "epoch": 0.1780448450453458,
+      "grad_norm": 0.0174560546875,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 3.5293,
+      "mean_token_accuracy": 0.4203047439455986,
+      "num_tokens": 2644330.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 2644330.0,
+      "eval_coding_runtime": 95.9249,
+      "eval_coding_samples_per_second": 5.212,
+      "eval_coding_steps_per_second": 2.606,
+      "step": 200
+    },
+    {
+      "epoch": 0.1780448450453458,
+      "eval_chemistry_entropy": 2.520227357387543,
+      "eval_chemistry_loss": 3.5777227878570557,
+      "eval_chemistry_mean_token_accuracy": 0.4262875291109085,
+      "eval_chemistry_num_tokens": 2644330.0,
+      "eval_chemistry_runtime": 53.6456,
+      "eval_chemistry_samples_per_second": 9.32,
+      "eval_chemistry_steps_per_second": 4.66,
+      "step": 200
+    },
+    {
+      "entropy": 2.463035849481821,
+      "epoch": 0.18694708729761308,
+      "grad_norm": 0.01226806640625,
+      "learning_rate": 4.18e-06,
+      "loss": 3.3809,
+      "mean_token_accuracy": 0.43558520982041954,
+      "num_tokens": 2783261.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.5025305368006228,
+      "epoch": 0.19584932954988038,
+      "grad_norm": 0.007476806640625,
+      "learning_rate": 4.38e-06,
+      "loss": 3.4253,
+      "mean_token_accuracy": 0.4310411293059587,
+      "num_tokens": 2913700.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.455498095601797,
+      "epoch": 0.20475157180214767,
+      "grad_norm": 0.0068359375,
+      "learning_rate": 4.58e-06,
+      "loss": 3.3586,
+      "mean_token_accuracy": 0.43719491101801394,
+      "num_tokens": 3048973.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.5426308810710907,
+      "epoch": 0.21365381405441494,
+      "grad_norm": 0.007598876953125,
+      "learning_rate": 4.78e-06,
+      "loss": 3.406,
+      "mean_token_accuracy": 0.43309843018651006,
+      "num_tokens": 3185255.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.444308698922396,
+      "epoch": 0.22255605630668224,
+      "grad_norm": 0.01324462890625,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 3.337,
+      "mean_token_accuracy": 0.44262526389211415,
+      "num_tokens": 3322823.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.526992666721344,
+      "epoch": 0.23145829855894953,
+      "grad_norm": 0.0103759765625,
+      "learning_rate": 5.18e-06,
+      "loss": 3.478,
+      "mean_token_accuracy": 0.42772163953632114,
+      "num_tokens": 3454750.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.468804422393441,
+      "epoch": 0.24036054081121683,
+      "grad_norm": 0.0084228515625,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 3.3899,
+      "mean_token_accuracy": 0.4310757084749639,
+      "num_tokens": 3589449.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.5963171511888503,
+      "epoch": 0.24926278306348412,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 3.5597,
+      "mean_token_accuracy": 0.4164831433445215,
+      "num_tokens": 3719113.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.6820507936179636,
+      "epoch": 0.2581650253157514,
+      "grad_norm": 0.008056640625,
+      "learning_rate": 5.78e-06,
+      "loss": 3.6014,
+      "mean_token_accuracy": 0.4143718365579844,
+      "num_tokens": 3852276.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.5068675063550474,
+      "epoch": 0.2670672675680187,
+      "grad_norm": 0.01226806640625,
+      "learning_rate": 5.98e-06,
+      "loss": 3.4183,
+      "mean_token_accuracy": 0.4291886316612363,
+      "num_tokens": 3990505.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 3990505.0,
+      "eval_coding_runtime": 95.8518,
+      "eval_coding_samples_per_second": 5.216,
+      "eval_coding_steps_per_second": 2.608,
+      "step": 300
+    },
+    {
+      "epoch": 0.2670672675680187,
+      "eval_chemistry_entropy": 2.520227357387543,
+      "eval_chemistry_loss": 3.5777227878570557,
+      "eval_chemistry_mean_token_accuracy": 0.4262875291109085,
+      "eval_chemistry_num_tokens": 3990505.0,
+      "eval_chemistry_runtime": 53.7283,
+      "eval_chemistry_samples_per_second": 9.306,
+      "eval_chemistry_steps_per_second": 4.653,
+      "step": 300
+    },
+    {
+      "entropy": 2.4614722445607184,
+      "epoch": 0.275969509820286,
+      "grad_norm": 0.0091552734375,
+      "learning_rate": 6.18e-06,
+      "loss": 3.3329,
+      "mean_token_accuracy": 0.4380343802273273,
+      "num_tokens": 4133119.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.4565507762134073,
+      "epoch": 0.2848717520725533,
+      "grad_norm": 0.0074462890625,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 3.376,
+      "mean_token_accuracy": 0.4339581592008471,
+      "num_tokens": 4267403.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.4726619601249693,
+      "epoch": 0.29377399432482054,
+      "grad_norm": 0.007781982421875,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 3.3584,
+      "mean_token_accuracy": 0.43662677630782126,
+      "num_tokens": 4400242.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.4780636690557003,
+      "epoch": 0.30267623657708786,
+      "grad_norm": 0.009765625,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 3.3561,
+      "mean_token_accuracy": 0.4329976743087173,
+      "num_tokens": 4535458.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.4669046089053155,
+      "epoch": 0.31157847882935513,
+      "grad_norm": 0.01031494140625,
+      "learning_rate": 6.98e-06,
+      "loss": 3.4031,
+      "mean_token_accuracy": 0.43433742690831423,
+      "num_tokens": 4662903.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.5689725764095783,
+      "epoch": 0.32048072108162245,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 3.4889,
+      "mean_token_accuracy": 0.4287034338340163,
+      "num_tokens": 4796815.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.4410855643451215,
+      "epoch": 0.3293829633338897,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 3.3643,
+      "mean_token_accuracy": 0.43710872549563645,
+      "num_tokens": 4932671.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.5445352010428905,
+      "epoch": 0.338285205586157,
+      "grad_norm": 0.01129150390625,
+      "learning_rate": 7.58e-06,
+      "loss": 3.4525,
+      "mean_token_accuracy": 0.42816965784877536,
+      "num_tokens": 5066948.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.565714708715677,
+      "epoch": 0.3471874478384243,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 7.78e-06,
+      "loss": 3.4661,
+      "mean_token_accuracy": 0.4264904214069247,
+      "num_tokens": 5193519.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.516895131766796,
+      "epoch": 0.3560896900906916,
+      "grad_norm": 0.01031494140625,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 3.4401,
+      "mean_token_accuracy": 0.4265883769840002,
+      "num_tokens": 5324751.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 5324751.0,
+      "eval_coding_runtime": 95.8822,
+      "eval_coding_samples_per_second": 5.215,
+      "eval_coding_steps_per_second": 2.607,
+      "step": 400
+    },
+    {
+      "epoch": 0.3560896900906916,
+      "eval_chemistry_entropy": 2.520227357387543,
+      "eval_chemistry_loss": 3.5777227878570557,
+      "eval_chemistry_mean_token_accuracy": 0.4262875291109085,
+      "eval_chemistry_num_tokens": 5324751.0,
+      "eval_chemistry_runtime": 53.6645,
+      "eval_chemistry_samples_per_second": 9.317,
+      "eval_chemistry_steps_per_second": 4.659,
+      "step": 400
+    },
+    {
+      "entropy": 2.4508687026798723,
+      "epoch": 0.3649919323429589,
+      "grad_norm": 0.010986328125,
+      "learning_rate": 8.18e-06,
+      "loss": 3.3874,
+      "mean_token_accuracy": 0.4385754197835922,
+      "num_tokens": 5458519.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.4801586009562016,
+      "epoch": 0.37389417459522617,
+      "grad_norm": 0.00714111328125,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 3.4012,
+      "mean_token_accuracy": 0.43559422083199023,
+      "num_tokens": 5585508.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.4704861216247083,
+      "epoch": 0.38279641684749344,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.4353,
+      "mean_token_accuracy": 0.43275914546102284,
+      "num_tokens": 5716321.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.537934695184231,
+      "epoch": 0.39169865909976076,
+      "grad_norm": 0.0081787109375,
+      "learning_rate": 8.78e-06,
+      "loss": 3.4176,
+      "mean_token_accuracy": 0.4291856364347041,
+      "num_tokens": 5848889.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.513765400648117,
+      "epoch": 0.400600901352028,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 8.98e-06,
+      "loss": 3.4106,
+      "mean_token_accuracy": 0.42827712278813124,
+      "num_tokens": 5980229.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.4634178556501864,
+      "epoch": 0.40950314360429535,
+      "grad_norm": 0.01068115234375,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 3.4007,
+      "mean_token_accuracy": 0.4337839787825942,
+      "num_tokens": 6114855.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.5320842534303667,
+      "epoch": 0.4184053858565626,
+      "grad_norm": 0.007049560546875,
+      "learning_rate": 9.38e-06,
+      "loss": 3.4216,
+      "mean_token_accuracy": 0.4268041457980871,
+      "num_tokens": 6244987.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.4959075897932053,
+      "epoch": 0.4273076281088299,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 9.58e-06,
+      "loss": 3.3715,
+      "mean_token_accuracy": 0.432720182929188,
+      "num_tokens": 6378152.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.503755620121956,
+      "epoch": 0.4362098703610972,
+      "grad_norm": 0.01708984375,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 3.4343,
+      "mean_token_accuracy": 0.43189559010788797,
+      "num_tokens": 6510231.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.539106211811304,
+      "epoch": 0.4451121126133645,
+      "grad_norm": 0.0115966796875,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 3.4747,
+      "mean_token_accuracy": 0.42332094311714175,
+      "num_tokens": 6637273.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_coding_entropy": 1.266241003036499,
+      "eval_coding_loss": 1.2625732421875,
+      "eval_coding_mean_token_accuracy": 0.6838934738636017,
+      "eval_coding_num_tokens": 6637273.0,
+      "eval_coding_runtime": 95.8134,
+      "eval_coding_samples_per_second": 5.218,
+      "eval_coding_steps_per_second": 2.609,
+      "step": 500
+    },
+    {
+      "epoch": 0.4451121126133645,
+      "eval_chemistry_entropy": 2.520227357387543,
+      "eval_chemistry_loss": 3.5777227878570557,
+      "eval_chemistry_mean_token_accuracy": 0.4262875291109085,
+      "eval_chemistry_num_tokens": 6637273.0,
+      "eval_chemistry_runtime": 53.3031,
+      "eval_chemistry_samples_per_second": 9.38,
+      "eval_chemistry_steps_per_second": 4.69,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 5.5213033487934874e+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 sha256:98f6a4eed050ba43d4f1f37cb84e4a0e4c7e84f48c9b66045451e2ca37bc478d
+size 6417