Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1000/added_tokens.json

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

checkpoint-1000/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-1000/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-1000/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-1000/model-00001-of-00005.safetensors

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

checkpoint-1000/model-00002-of-00005.safetensors

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

checkpoint-1000/model-00003-of-00005.safetensors

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

checkpoint-1000/model-00004-of-00005.safetensors

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

checkpoint-1000/model-00005-of-00005.safetensors

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

checkpoint-1000/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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91861e673783103b21a79d949ed9e8491382c01c03a0dfac6dac094ef797dcca
+size 18355

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bf96921d4da8b61663178a411f06e7fa998416e8e1f6df81ce9d5b5c397b95
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6078e52773a379f026b8fbbbc5546ab7ed9418d05b713f8aff2a4f3c7e12f108
+size 1465

checkpoint-1000/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-1000/tokenizer.json

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

checkpoint-1000/tokenizer.model

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

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7797930343829975,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.4441180236637594,
+      "epoch": 0.017803493935684877,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 1.8e-07,
+      "loss": 3.382,
+      "mean_token_accuracy": 0.4423037525266409,
+      "num_tokens": 257189.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.45082361549139,
+      "epoch": 0.035606987871369754,
+      "grad_norm": 0.0086669921875,
+      "learning_rate": 3.8e-07,
+      "loss": 3.375,
+      "mean_token_accuracy": 0.4396079422906041,
+      "num_tokens": 528285.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.461306857317686,
+      "epoch": 0.053410481807054634,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 3.3839,
+      "mean_token_accuracy": 0.43654753603041174,
+      "num_tokens": 801635.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.486989914625883,
+      "epoch": 0.07121397574273951,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 7.8e-07,
+      "loss": 3.4182,
+      "mean_token_accuracy": 0.435793649405241,
+      "num_tokens": 1060812.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.4777335457503797,
+      "epoch": 0.08901746967842439,
+      "grad_norm": 0.007049560546875,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 3.407,
+      "mean_token_accuracy": 0.4357369150966406,
+      "num_tokens": 1327380.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.478399809449911,
+      "epoch": 0.10682096361410927,
+      "grad_norm": 0.00726318359375,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 3.4405,
+      "mean_token_accuracy": 0.43458456825464964,
+      "num_tokens": 1597405.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.5134010180830955,
+      "epoch": 0.12462445754979415,
+      "grad_norm": 0.006683349609375,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 3.4613,
+      "mean_token_accuracy": 0.4291722310706973,
+      "num_tokens": 1859684.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.5495446130633352,
+      "epoch": 0.14242795148547902,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 3.5072,
+      "mean_token_accuracy": 0.42735045179724696,
+      "num_tokens": 2118068.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.4757557071745397,
+      "epoch": 0.1602314454211639,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 3.4228,
+      "mean_token_accuracy": 0.43469055872410534,
+      "num_tokens": 2388824.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.5207040145993234,
+      "epoch": 0.17803493935684878,
+      "grad_norm": 0.00994873046875,
+      "learning_rate": 1.98e-06,
+      "loss": 3.506,
+      "mean_token_accuracy": 0.4275117186829448,
+      "num_tokens": 2644330.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.17803493935684878,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 2644330.0,
+      "eval_chemistry_runtime": 42.5715,
+      "eval_chemistry_samples_per_second": 11.745,
+      "eval_chemistry_steps_per_second": 2.936,
+      "step": 100
+    },
+    {
+      "entropy": 2.460470324009657,
+      "epoch": 0.19583843329253367,
+      "grad_norm": 0.0084228515625,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 3.3945,
+      "mean_token_accuracy": 0.4391466261819005,
+      "num_tokens": 2913700.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.478592600673437,
+      "epoch": 0.21364192722821854,
+      "grad_norm": 0.006866455078125,
+      "learning_rate": 2.38e-06,
+      "loss": 3.3703,
+      "mean_token_accuracy": 0.4405368799343705,
+      "num_tokens": 3185255.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.4654680602252483,
+      "epoch": 0.2314454211639034,
+      "grad_norm": 0.00994873046875,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 3.3981,
+      "mean_token_accuracy": 0.43972534593194723,
+      "num_tokens": 3454750.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.5018775165081024,
+      "epoch": 0.2492489150995883,
+      "grad_norm": 0.0091552734375,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 3.4682,
+      "mean_token_accuracy": 0.4316142167896032,
+      "num_tokens": 3719113.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.568158584088087,
+      "epoch": 0.26705240903527316,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 3.5044,
+      "mean_token_accuracy": 0.4264186339452863,
+      "num_tokens": 3990505.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.420287236571312,
+      "epoch": 0.28485590297095803,
+      "grad_norm": 0.007415771484375,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 3.3513,
+      "mean_token_accuracy": 0.44414950646460055,
+      "num_tokens": 4267403.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.4532286070287226,
+      "epoch": 0.30265939690664295,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 3.3478,
+      "mean_token_accuracy": 0.4404185781255364,
+      "num_tokens": 4535458.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.4985749416053293,
+      "epoch": 0.3204628908423278,
+      "grad_norm": 0.007720947265625,
+      "learning_rate": 3.58e-06,
+      "loss": 3.4363,
+      "mean_token_accuracy": 0.4365795683115721,
+      "num_tokens": 4796815.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.4519996128976347,
+      "epoch": 0.3382663847780127,
+      "grad_norm": 0.00701904296875,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 3.3977,
+      "mean_token_accuracy": 0.440047624707222,
+      "num_tokens": 5066948.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.521295293420553,
+      "epoch": 0.35606987871369755,
+      "grad_norm": 0.010009765625,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 3.4496,
+      "mean_token_accuracy": 0.4322214875370264,
+      "num_tokens": 5324751.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.35606987871369755,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 5324751.0,
+      "eval_chemistry_runtime": 42.5086,
+      "eval_chemistry_samples_per_second": 11.762,
+      "eval_chemistry_steps_per_second": 2.941,
+      "step": 200
+    },
+    {
+      "entropy": 2.44460117071867,
+      "epoch": 0.3738733726493824,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 4.18e-06,
+      "loss": 3.3862,
+      "mean_token_accuracy": 0.4415476618334651,
+      "num_tokens": 5585508.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.480318387597799,
+      "epoch": 0.39167686658506734,
+      "grad_norm": 0.006591796875,
+      "learning_rate": 4.38e-06,
+      "loss": 3.4199,
+      "mean_token_accuracy": 0.43676935136318207,
+      "num_tokens": 5848889.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.4665837228298186,
+      "epoch": 0.4094803605207522,
+      "grad_norm": 0.007049560546875,
+      "learning_rate": 4.58e-06,
+      "loss": 3.399,
+      "mean_token_accuracy": 0.4371540261432528,
+      "num_tokens": 6114855.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.4934676766395567,
+      "epoch": 0.4272838544564371,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 4.78e-06,
+      "loss": 3.392,
+      "mean_token_accuracy": 0.4352115549147129,
+      "num_tokens": 6378152.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.510968402773142,
+      "epoch": 0.44508734839212194,
+      "grad_norm": 0.00811767578125,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 3.4512,
+      "mean_token_accuracy": 0.43123594429343937,
+      "num_tokens": 6637273.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.459284470230341,
+      "epoch": 0.4628908423278068,
+      "grad_norm": 0.0081787109375,
+      "learning_rate": 5.18e-06,
+      "loss": 3.4105,
+      "mean_token_accuracy": 0.43572237603366376,
+      "num_tokens": 6896684.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.4737772688269617,
+      "epoch": 0.48069433626349173,
+      "grad_norm": 0.01324462890625,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 3.4275,
+      "mean_token_accuracy": 0.4344434389844537,
+      "num_tokens": 7166608.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.393792650848627,
+      "epoch": 0.4984978301991766,
+      "grad_norm": 0.00714111328125,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 3.3174,
+      "mean_token_accuracy": 0.445861529558897,
+      "num_tokens": 7444923.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.4808071456849574,
+      "epoch": 0.5163013241348615,
+      "grad_norm": 0.0125732421875,
+      "learning_rate": 5.78e-06,
+      "loss": 3.4216,
+      "mean_token_accuracy": 0.4335135340690613,
+      "num_tokens": 7706502.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.4993100173771383,
+      "epoch": 0.5341048180705463,
+      "grad_norm": 0.01153564453125,
+      "learning_rate": 5.98e-06,
+      "loss": 3.4677,
+      "mean_token_accuracy": 0.43226035628467796,
+      "num_tokens": 7969704.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5341048180705463,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 7969704.0,
+      "eval_chemistry_runtime": 42.3808,
+      "eval_chemistry_samples_per_second": 11.798,
+      "eval_chemistry_steps_per_second": 2.949,
+      "step": 300
+    },
+    {
+      "entropy": 2.49663657695055,
+      "epoch": 0.5519083120062312,
+      "grad_norm": 0.0101318359375,
+      "learning_rate": 6.18e-06,
+      "loss": 3.452,
+      "mean_token_accuracy": 0.4326026676222682,
+      "num_tokens": 8242162.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.491827418655157,
+      "epoch": 0.5697118059419161,
+      "grad_norm": 0.007476806640625,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 3.4701,
+      "mean_token_accuracy": 0.4347437607124448,
+      "num_tokens": 8497852.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.526278664171696,
+      "epoch": 0.587515299877601,
+      "grad_norm": 0.00946044921875,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 3.504,
+      "mean_token_accuracy": 0.4276865454390645,
+      "num_tokens": 8757753.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.4302435807883738,
+      "epoch": 0.6053187938132859,
+      "grad_norm": 0.0189208984375,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 3.3655,
+      "mean_token_accuracy": 0.4372914243489504,
+      "num_tokens": 9024677.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.4870374642312525,
+      "epoch": 0.6231222877489707,
+      "grad_norm": 0.00750732421875,
+      "learning_rate": 6.98e-06,
+      "loss": 3.4166,
+      "mean_token_accuracy": 0.4357576759532094,
+      "num_tokens": 9291760.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.440358117222786,
+      "epoch": 0.6409257816846556,
+      "grad_norm": 0.007415771484375,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 3.3708,
+      "mean_token_accuracy": 0.43819774594157934,
+      "num_tokens": 9561091.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.4518581442534924,
+      "epoch": 0.6587292756203404,
+      "grad_norm": 0.01177978515625,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 3.39,
+      "mean_token_accuracy": 0.4373545182868838,
+      "num_tokens": 9827272.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.4458557978272437,
+      "epoch": 0.6765327695560254,
+      "grad_norm": 0.01019287109375,
+      "learning_rate": 7.58e-06,
+      "loss": 3.3803,
+      "mean_token_accuracy": 0.44243213571608064,
+      "num_tokens": 10096065.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.457463264465332,
+      "epoch": 0.6943362634917103,
+      "grad_norm": 0.00775146484375,
+      "learning_rate": 7.78e-06,
+      "loss": 3.3973,
+      "mean_token_accuracy": 0.43960350602865217,
+      "num_tokens": 10364601.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.4410374239087105,
+      "epoch": 0.7121397574273951,
+      "grad_norm": 0.00860595703125,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 3.3916,
+      "mean_token_accuracy": 0.4379643935710192,
+      "num_tokens": 10633325.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7121397574273951,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 10633325.0,
+      "eval_chemistry_runtime": 42.4526,
+      "eval_chemistry_samples_per_second": 11.778,
+      "eval_chemistry_steps_per_second": 2.944,
+      "step": 400
+    },
+    {
+      "entropy": 2.409457255154848,
+      "epoch": 0.72994325136308,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 8.18e-06,
+      "loss": 3.3536,
+      "mean_token_accuracy": 0.4413986885920167,
+      "num_tokens": 10897916.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.4690888836979865,
+      "epoch": 0.7477467452987648,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 3.4202,
+      "mean_token_accuracy": 0.43675678241997956,
+      "num_tokens": 11165356.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.456707588583231,
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.0074462890625,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.3849,
+      "mean_token_accuracy": 0.43797059506177904,
+      "num_tokens": 11436799.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.481979151070118,
+      "epoch": 0.7833537331701347,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 8.78e-06,
+      "loss": 3.3948,
+      "mean_token_accuracy": 0.4386452713981271,
+      "num_tokens": 11703496.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.511328932642937,
+      "epoch": 0.8011572271058195,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 8.98e-06,
+      "loss": 3.4704,
+      "mean_token_accuracy": 0.4308528220281005,
+      "num_tokens": 11965530.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.4488867104053496,
+      "epoch": 0.8189607210415044,
+      "grad_norm": 0.00897216796875,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 3.4121,
+      "mean_token_accuracy": 0.43401869516819713,
+      "num_tokens": 12224427.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.41854225769639,
+      "epoch": 0.8367642149771892,
+      "grad_norm": 0.01202392578125,
+      "learning_rate": 9.38e-06,
+      "loss": 3.312,
+      "mean_token_accuracy": 0.4470580581575632,
+      "num_tokens": 12509124.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.4362686768174173,
+      "epoch": 0.8545677089128741,
+      "grad_norm": 0.007232666015625,
+      "learning_rate": 9.58e-06,
+      "loss": 3.3794,
+      "mean_token_accuracy": 0.4400447830557823,
+      "num_tokens": 12778408.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.4321289747953414,
+      "epoch": 0.8723712028485591,
+      "grad_norm": 0.00811767578125,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 3.3687,
+      "mean_token_accuracy": 0.44097492955625056,
+      "num_tokens": 13046473.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.4888896882534026,
+      "epoch": 0.8901746967842439,
+      "grad_norm": 0.007720947265625,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 3.4261,
+      "mean_token_accuracy": 0.43556336853653194,
+      "num_tokens": 13301659.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.8901746967842439,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 13301659.0,
+      "eval_chemistry_runtime": 42.4183,
+      "eval_chemistry_samples_per_second": 11.787,
+      "eval_chemistry_steps_per_second": 2.947,
+      "step": 500
+    },
+    {
+      "entropy": 2.4065550975501537,
+      "epoch": 0.9079781907199288,
+      "grad_norm": 0.007110595703125,
+      "learning_rate": 1.018e-05,
+      "loss": 3.3268,
+      "mean_token_accuracy": 0.44642978757619856,
+      "num_tokens": 13570986.0,
+      "step": 510
+    },
+    {
+      "entropy": 2.4483018897473814,
+      "epoch": 0.9257816846556136,
+      "grad_norm": 0.0087890625,
+      "learning_rate": 1.038e-05,
+      "loss": 3.4018,
+      "mean_token_accuracy": 0.4386210318654776,
+      "num_tokens": 13833901.0,
+      "step": 520
+    },
+    {
+      "entropy": 2.454428631067276,
+      "epoch": 0.9435851785912985,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 1.0580000000000002e-05,
+      "loss": 3.4197,
+      "mean_token_accuracy": 0.43513929657638073,
+      "num_tokens": 14093888.0,
+      "step": 530
+    },
+    {
+      "entropy": 2.4978294670581818,
+      "epoch": 0.9613886725269835,
+      "grad_norm": 0.00750732421875,
+      "learning_rate": 1.0780000000000002e-05,
+      "loss": 3.43,
+      "mean_token_accuracy": 0.43464562948793173,
+      "num_tokens": 14354918.0,
+      "step": 540
+    },
+    {
+      "entropy": 2.46180320456624,
+      "epoch": 0.9791921664626683,
+      "grad_norm": 0.00811767578125,
+      "learning_rate": 1.0980000000000002e-05,
+      "loss": 3.4206,
+      "mean_token_accuracy": 0.43483266811817883,
+      "num_tokens": 14620244.0,
+      "step": 550
+    },
+    {
+      "entropy": 2.4592869602143765,
+      "epoch": 0.9969956603983532,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 1.1180000000000001e-05,
+      "loss": 3.4471,
+      "mean_token_accuracy": 0.43371057212352754,
+      "num_tokens": 14886593.0,
+      "step": 560
+    },
+    {
+      "entropy": 2.3787012269420007,
+      "epoch": 1.014242795148548,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 1.138e-05,
+      "loss": 3.2918,
+      "mean_token_accuracy": 0.44634086931905437,
+      "num_tokens": 15146469.0,
+      "step": 570
+    },
+    {
+      "entropy": 2.524292258173227,
+      "epoch": 1.0320462890842328,
+      "grad_norm": 0.0128173828125,
+      "learning_rate": 1.1580000000000001e-05,
+      "loss": 3.4816,
+      "mean_token_accuracy": 0.43193594105541705,
+      "num_tokens": 15404569.0,
+      "step": 580
+    },
+    {
+      "entropy": 2.4150695733726026,
+      "epoch": 1.0498497830199176,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 1.178e-05,
+      "loss": 3.3678,
+      "mean_token_accuracy": 0.4405944043770432,
+      "num_tokens": 15681709.0,
+      "step": 590
+    },
+    {
+      "entropy": 2.441706320643425,
+      "epoch": 1.0676532769556026,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 1.198e-05,
+      "loss": 3.3742,
+      "mean_token_accuracy": 0.4395477233454585,
+      "num_tokens": 15949421.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.0676532769556026,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 15949421.0,
+      "eval_chemistry_runtime": 42.5959,
+      "eval_chemistry_samples_per_second": 11.738,
+      "eval_chemistry_steps_per_second": 2.935,
+      "step": 600
+    },
+    {
+      "entropy": 2.4119591929018496,
+      "epoch": 1.0854567708912874,
+      "grad_norm": 0.0076904296875,
+      "learning_rate": 1.218e-05,
+      "loss": 3.367,
+      "mean_token_accuracy": 0.4415699910372496,
+      "num_tokens": 16221916.0,
+      "step": 610
+    },
+    {
+      "entropy": 2.51780494004488,
+      "epoch": 1.1032602648269723,
+      "grad_norm": 0.007537841796875,
+      "learning_rate": 1.2380000000000002e-05,
+      "loss": 3.4485,
+      "mean_token_accuracy": 0.4301307639107108,
+      "num_tokens": 16488154.0,
+      "step": 620
+    },
+    {
+      "entropy": 2.4647247321903705,
+      "epoch": 1.121063758762657,
+      "grad_norm": 0.007354736328125,
+      "learning_rate": 1.2580000000000002e-05,
+      "loss": 3.4027,
+      "mean_token_accuracy": 0.4368906727060676,
+      "num_tokens": 16756828.0,
+      "step": 630
+    },
+    {
+      "entropy": 2.4489255413413047,
+      "epoch": 1.138867252698342,
+      "grad_norm": 0.00799560546875,
+      "learning_rate": 1.2780000000000001e-05,
+      "loss": 3.3816,
+      "mean_token_accuracy": 0.43627936094999314,
+      "num_tokens": 17023681.0,
+      "step": 640
+    },
+    {
+      "entropy": 2.4757089667022227,
+      "epoch": 1.156670746634027,
+      "grad_norm": 0.01190185546875,
+      "learning_rate": 1.2980000000000001e-05,
+      "loss": 3.4233,
+      "mean_token_accuracy": 0.4360200822353363,
+      "num_tokens": 17286672.0,
+      "step": 650
+    },
+    {
+      "entropy": 2.542103400081396,
+      "epoch": 1.1744742405697117,
+      "grad_norm": 0.00726318359375,
+      "learning_rate": 1.3180000000000001e-05,
+      "loss": 3.4708,
+      "mean_token_accuracy": 0.42764721568673847,
+      "num_tokens": 17551581.0,
+      "step": 660
+    },
+    {
+      "entropy": 2.4632993809878827,
+      "epoch": 1.1922777345053968,
+      "grad_norm": 0.00946044921875,
+      "learning_rate": 1.3380000000000002e-05,
+      "loss": 3.3879,
+      "mean_token_accuracy": 0.43964554853737353,
+      "num_tokens": 17821205.0,
+      "step": 670
+    },
+    {
+      "entropy": 2.4974757246673107,
+      "epoch": 1.2100812284410816,
+      "grad_norm": 0.007415771484375,
+      "learning_rate": 1.3580000000000002e-05,
+      "loss": 3.4339,
+      "mean_token_accuracy": 0.4323098760098219,
+      "num_tokens": 18087759.0,
+      "step": 680
+    },
+    {
+      "entropy": 2.485871135443449,
+      "epoch": 1.2278847223767664,
+      "grad_norm": 0.0084228515625,
+      "learning_rate": 1.378e-05,
+      "loss": 3.4259,
+      "mean_token_accuracy": 0.4338374109938741,
+      "num_tokens": 18355732.0,
+      "step": 690
+    },
+    {
+      "entropy": 2.4948798827826977,
+      "epoch": 1.2456882163124514,
+      "grad_norm": 0.0069580078125,
+      "learning_rate": 1.398e-05,
+      "loss": 3.4297,
+      "mean_token_accuracy": 0.435987046174705,
+      "num_tokens": 18626245.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.2456882163124514,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 18626245.0,
+      "eval_chemistry_runtime": 42.5841,
+      "eval_chemistry_samples_per_second": 11.741,
+      "eval_chemistry_steps_per_second": 2.935,
+      "step": 700
+    },
+    {
+      "entropy": 2.408124291151762,
+      "epoch": 1.2634917102481362,
+      "grad_norm": 0.00927734375,
+      "learning_rate": 1.418e-05,
+      "loss": 3.3266,
+      "mean_token_accuracy": 0.4450059160590172,
+      "num_tokens": 18899632.0,
+      "step": 710
+    },
+    {
+      "entropy": 2.4984724432229997,
+      "epoch": 1.281295204183821,
+      "grad_norm": 0.01214599609375,
+      "learning_rate": 1.4380000000000001e-05,
+      "loss": 3.4488,
+      "mean_token_accuracy": 0.4306912997737527,
+      "num_tokens": 19173635.0,
+      "step": 720
+    },
+    {
+      "entropy": 2.407220109552145,
+      "epoch": 1.299098698119506,
+      "grad_norm": 0.01129150390625,
+      "learning_rate": 1.4580000000000001e-05,
+      "loss": 3.3575,
+      "mean_token_accuracy": 0.44124190472066405,
+      "num_tokens": 19453495.0,
+      "step": 730
+    },
+    {
+      "entropy": 2.426318255066872,
+      "epoch": 1.3169021920551909,
+      "grad_norm": 0.007049560546875,
+      "learning_rate": 1.478e-05,
+      "loss": 3.366,
+      "mean_token_accuracy": 0.43959415052086115,
+      "num_tokens": 19719086.0,
+      "step": 740
+    },
+    {
+      "entropy": 2.4674886889755725,
+      "epoch": 1.3347056859908757,
+      "grad_norm": 0.009033203125,
+      "learning_rate": 1.498e-05,
+      "loss": 3.4065,
+      "mean_token_accuracy": 0.4346128342673182,
+      "num_tokens": 19981272.0,
+      "step": 750
+    },
+    {
+      "entropy": 2.4601897999644278,
+      "epoch": 1.3525091799265607,
+      "grad_norm": 0.007354736328125,
+      "learning_rate": 1.5180000000000002e-05,
+      "loss": 3.4277,
+      "mean_token_accuracy": 0.43639134224504234,
+      "num_tokens": 20243034.0,
+      "step": 760
+    },
+    {
+      "entropy": 2.4810195587575437,
+      "epoch": 1.3703126738622455,
+      "grad_norm": 0.0084228515625,
+      "learning_rate": 1.5380000000000002e-05,
+      "loss": 3.4245,
+      "mean_token_accuracy": 0.43384860958904026,
+      "num_tokens": 20509028.0,
+      "step": 770
+    },
+    {
+      "entropy": 2.5357875250279904,
+      "epoch": 1.3881161677979303,
+      "grad_norm": 0.006988525390625,
+      "learning_rate": 1.5580000000000003e-05,
+      "loss": 3.5276,
+      "mean_token_accuracy": 0.42721649557352065,
+      "num_tokens": 20762668.0,
+      "step": 780
+    },
+    {
+      "entropy": 2.573459583520889,
+      "epoch": 1.4059196617336152,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 1.578e-05,
+      "loss": 3.5041,
+      "mean_token_accuracy": 0.42504764050245286,
+      "num_tokens": 21025277.0,
+      "step": 790
+    },
+    {
+      "entropy": 2.5099629506468775,
+      "epoch": 1.4237231556693,
+      "grad_norm": 0.0091552734375,
+      "learning_rate": 1.5980000000000003e-05,
+      "loss": 3.4735,
+      "mean_token_accuracy": 0.42990608550608156,
+      "num_tokens": 21292320.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.4237231556693,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 21292320.0,
+      "eval_chemistry_runtime": 42.58,
+      "eval_chemistry_samples_per_second": 11.743,
+      "eval_chemistry_steps_per_second": 2.936,
+      "step": 800
+    },
+    {
+      "entropy": 2.5165034629404546,
+      "epoch": 1.441526649604985,
+      "grad_norm": 0.00732421875,
+      "learning_rate": 1.618e-05,
+      "loss": 3.4497,
+      "mean_token_accuracy": 0.4366149786859751,
+      "num_tokens": 21563668.0,
+      "step": 810
+    },
+    {
+      "entropy": 2.4973253421485424,
+      "epoch": 1.4593301435406698,
+      "grad_norm": 0.007232666015625,
+      "learning_rate": 1.638e-05,
+      "loss": 3.4814,
+      "mean_token_accuracy": 0.4312220415100455,
+      "num_tokens": 21817298.0,
+      "step": 820
+    },
+    {
+      "entropy": 2.52367008626461,
+      "epoch": 1.4771336374763546,
+      "grad_norm": 0.007598876953125,
+      "learning_rate": 1.658e-05,
+      "loss": 3.468,
+      "mean_token_accuracy": 0.4320263473317027,
+      "num_tokens": 22083010.0,
+      "step": 830
+    },
+    {
+      "entropy": 2.50519383251667,
+      "epoch": 1.4949371314120397,
+      "grad_norm": 0.0074462890625,
+      "learning_rate": 1.6780000000000002e-05,
+      "loss": 3.4575,
+      "mean_token_accuracy": 0.4309014746919274,
+      "num_tokens": 22350046.0,
+      "step": 840
+    },
+    {
+      "entropy": 2.458015527576208,
+      "epoch": 1.5127406253477245,
+      "grad_norm": 0.0081787109375,
+      "learning_rate": 1.698e-05,
+      "loss": 3.4087,
+      "mean_token_accuracy": 0.4401903055608273,
+      "num_tokens": 22615933.0,
+      "step": 850
+    },
+    {
+      "entropy": 2.4192430078983307,
+      "epoch": 1.5305441192834093,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 1.718e-05,
+      "loss": 3.3493,
+      "mean_token_accuracy": 0.4408345725387335,
+      "num_tokens": 22886843.0,
+      "step": 860
+    },
+    {
+      "entropy": 2.4866544254124165,
+      "epoch": 1.5483476132190943,
+      "grad_norm": 0.006927490234375,
+      "learning_rate": 1.7380000000000003e-05,
+      "loss": 3.4323,
+      "mean_token_accuracy": 0.4359192430973053,
+      "num_tokens": 23140244.0,
+      "step": 870
+    },
+    {
+      "entropy": 2.472956708818674,
+      "epoch": 1.5661511071547791,
+      "grad_norm": 0.0076904296875,
+      "learning_rate": 1.758e-05,
+      "loss": 3.4127,
+      "mean_token_accuracy": 0.4368757115676999,
+      "num_tokens": 23405121.0,
+      "step": 880
+    },
+    {
+      "entropy": 2.4871600806713103,
+      "epoch": 1.583954601090464,
+      "grad_norm": 0.006378173828125,
+      "learning_rate": 1.7780000000000003e-05,
+      "loss": 3.425,
+      "mean_token_accuracy": 0.43275546226650474,
+      "num_tokens": 23671826.0,
+      "step": 890
+    },
+    {
+      "entropy": 2.5024729229509832,
+      "epoch": 1.601758095026149,
+      "grad_norm": 0.01068115234375,
+      "learning_rate": 1.798e-05,
+      "loss": 3.4415,
+      "mean_token_accuracy": 0.43367660194635393,
+      "num_tokens": 23933374.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.601758095026149,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 23933374.0,
+      "eval_chemistry_runtime": 42.5199,
+      "eval_chemistry_samples_per_second": 11.759,
+      "eval_chemistry_steps_per_second": 2.94,
+      "step": 900
+    },
+    {
+      "entropy": 2.4241936951875687,
+      "epoch": 1.6195615889618338,
+      "grad_norm": 0.00836181640625,
+      "learning_rate": 1.8180000000000002e-05,
+      "loss": 3.3926,
+      "mean_token_accuracy": 0.4393082341179252,
+      "num_tokens": 24210156.0,
+      "step": 910
+    },
+    {
+      "entropy": 2.501750738918781,
+      "epoch": 1.6373650828975186,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 1.8380000000000004e-05,
+      "loss": 3.428,
+      "mean_token_accuracy": 0.4345035368576646,
+      "num_tokens": 24462726.0,
+      "step": 920
+    },
+    {
+      "entropy": 2.4093470610678196,
+      "epoch": 1.6551685768332036,
+      "grad_norm": 0.0118408203125,
+      "learning_rate": 1.858e-05,
+      "loss": 3.3407,
+      "mean_token_accuracy": 0.44576158542186023,
+      "num_tokens": 24732815.0,
+      "step": 930
+    },
+    {
+      "entropy": 2.469248706102371,
+      "epoch": 1.6729720707688884,
+      "grad_norm": 0.0128173828125,
+      "learning_rate": 1.878e-05,
+      "loss": 3.3903,
+      "mean_token_accuracy": 0.4362227080389857,
+      "num_tokens": 25002091.0,
+      "step": 940
+    },
+    {
+      "entropy": 2.4393011182546616,
+      "epoch": 1.6907755647045732,
+      "grad_norm": 0.00982666015625,
+      "learning_rate": 1.898e-05,
+      "loss": 3.4097,
+      "mean_token_accuracy": 0.4377862988039851,
+      "num_tokens": 25267949.0,
+      "step": 950
+    },
+    {
+      "entropy": 2.499985621124506,
+      "epoch": 1.7085790586402583,
+      "grad_norm": 0.007110595703125,
+      "learning_rate": 1.918e-05,
+      "loss": 3.4206,
+      "mean_token_accuracy": 0.4386218637228012,
+      "num_tokens": 25525772.0,
+      "step": 960
+    },
+    {
+      "entropy": 2.518709710240364,
+      "epoch": 1.7263825525759429,
+      "grad_norm": 0.015625,
+      "learning_rate": 1.938e-05,
+      "loss": 3.4744,
+      "mean_token_accuracy": 0.4290819203481078,
+      "num_tokens": 25787727.0,
+      "step": 970
+    },
+    {
+      "entropy": 2.434730440378189,
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.007110595703125,
+      "learning_rate": 1.9580000000000002e-05,
+      "loss": 3.3452,
+      "mean_token_accuracy": 0.4429737152531743,
+      "num_tokens": 26058026.0,
+      "step": 980
+    },
+    {
+      "entropy": 2.405204129964113,
+      "epoch": 1.761989540447313,
+      "grad_norm": 0.007659912109375,
+      "learning_rate": 1.978e-05,
+      "loss": 3.3339,
+      "mean_token_accuracy": 0.44453586284071206,
+      "num_tokens": 26326631.0,
+      "step": 990
+    },
+    {
+      "entropy": 2.473785638809204,
+      "epoch": 1.7797930343829975,
+      "grad_norm": 0.008056640625,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 3.3982,
+      "mean_token_accuracy": 0.4379414787515998,
+      "num_tokens": 26591735.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7797930343829975,
+      "eval_chemistry_entropy": 2.4951189584732054,
+      "eval_chemistry_loss": 3.512981414794922,
+      "eval_chemistry_mean_token_accuracy": 0.4329572098255157,
+      "eval_chemistry_num_tokens": 26591735.0,
+      "eval_chemistry_runtime": 42.6898,
+      "eval_chemistry_samples_per_second": 11.712,
+      "eval_chemistry_steps_per_second": 2.928,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 18,
+  "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": 2.672881625860089e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c203431b23c0b2024be20ba2c3b8d6912d99b5a0839b2ccb6094a319dbeed0e
+size 6481