Upload continuous evaluation checkpoints, batch 47

continuous/smollm2/webssl_mae3b_full2b_224/finetune/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ce200e9adbe69d32694a93777a13a62012d6e79c16aa55c562ee4648981b83
+size 4938476216

continuous/smollm2/webssl_mae3b_full2b_224/finetune/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85751722a16315e6367b3efac07456012d1146aa5ff0ccc92a1d26a63a038a78
+size 4642627952

continuous/smollm2/webssl_mae3b_full2b_224/finetune/model.safetensors.index.json

@@ -0,0 +1,655 @@
+{
+  "metadata": {
+    "total_parameters": 4679354368,
+    "total_size": 9581015040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.embeddings.cls_token": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.embeddings.position_embeddings": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.12.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.13.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.14.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.15.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.16.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.17.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.18.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.19.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.20.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.21.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.22.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.23.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.24.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.25.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.pooler.dense.weight": "model-00002-of-00002.safetensors"
+  }
+}

continuous/smollm2/webssl_mae3b_full2b_224/finetune/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

continuous/smollm2/webssl_mae3b_full2b_224/finetune/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

continuous/smollm2/webssl_mae3b_full2b_224/finetune/trainer_state.json

@@ -0,0 +1,1856 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850596842510589,
+      "grad_norm": 3.239999532699585,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 1.2805,
+      "step": 10
+    },
+    {
+      "epoch": 0.007701193685021178,
+      "grad_norm": 2.18229603767395,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.1467,
+      "step": 20
+    },
+    {
+      "epoch": 0.011551790527531768,
+      "grad_norm": 2.2215564250946045,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.0432,
+      "step": 30
+    },
+    {
+      "epoch": 0.015402387370042356,
+      "grad_norm": 1.430437445640564,
+      "learning_rate": 5e-06,
+      "loss": 1.0014,
+      "step": 40
+    },
+    {
+      "epoch": 0.019252984212552945,
+      "grad_norm": 1.2978633642196655,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 0.981,
+      "step": 50
+    },
+    {
+      "epoch": 0.023103581055063535,
+      "grad_norm": 0.2902723252773285,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9074,
+      "step": 60
+    },
+    {
+      "epoch": 0.026954177897574125,
+      "grad_norm": 0.23477667570114136,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.8602,
+      "step": 70
+    },
+    {
+      "epoch": 0.030804774740084712,
+      "grad_norm": 0.24033962190151215,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.8724,
+      "step": 80
+    },
+    {
+      "epoch": 0.0346553715825953,
+      "grad_norm": 0.2208697497844696,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8569,
+      "step": 90
+    },
+    {
+      "epoch": 0.03850596842510589,
+      "grad_norm": 0.21867066621780396,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8248,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235656526761648,
+      "grad_norm": 0.20699529349803925,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8142,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620716211012707,
+      "grad_norm": 0.21251344680786133,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8335,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005775895263766,
+      "grad_norm": 0.21196602284908295,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8114,
+      "step": 130
+    },
+    {
+      "epoch": 0.05390835579514825,
+      "grad_norm": 0.21868737041950226,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8235,
+      "step": 140
+    },
+    {
+      "epoch": 0.05775895263765884,
+      "grad_norm": 0.22111396491527557,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8023,
+      "step": 150
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "grad_norm": 0.1958588808774948,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8074,
+      "step": 160
+    },
+    {
+      "epoch": 0.06546014632268002,
+      "grad_norm": 0.17118585109710693,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.8079,
+      "step": 170
+    },
+    {
+      "epoch": 0.0693107431651906,
+      "grad_norm": 0.20156517624855042,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8412,
+      "step": 180
+    },
+    {
+      "epoch": 0.07316134000770119,
+      "grad_norm": 0.2060399353504181,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8279,
+      "step": 190
+    },
+    {
+      "epoch": 0.07701193685021178,
+      "grad_norm": 0.2029673457145691,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8262,
+      "step": 200
+    },
+    {
+      "epoch": 0.08086253369272237,
+      "grad_norm": 0.1980639100074768,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8118,
+      "step": 210
+    },
+    {
+      "epoch": 0.08471313053523297,
+      "grad_norm": 0.20143777132034302,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8041,
+      "step": 220
+    },
+    {
+      "epoch": 0.08856372737774355,
+      "grad_norm": 0.20460709929466248,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.7991,
+      "step": 230
+    },
+    {
+      "epoch": 0.09241432422025414,
+      "grad_norm": 0.20109869539737701,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.7933,
+      "step": 240
+    },
+    {
+      "epoch": 0.09626492106276473,
+      "grad_norm": 0.19099734723567963,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.811,
+      "step": 250
+    },
+    {
+      "epoch": 0.10011551790527531,
+      "grad_norm": 0.17824473977088928,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8088,
+      "step": 260
+    },
+    {
+      "epoch": 0.1039661147477859,
+      "grad_norm": 0.1974714696407318,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.791,
+      "step": 270
+    },
+    {
+      "epoch": 0.1078167115902965,
+      "grad_norm": 0.1763271540403366,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.7901,
+      "step": 280
+    },
+    {
+      "epoch": 0.11166730843280709,
+      "grad_norm": 0.19284720718860626,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8207,
+      "step": 290
+    },
+    {
+      "epoch": 0.11551790527531768,
+      "grad_norm": 0.18424829840660095,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.7785,
+      "step": 300
+    },
+    {
+      "epoch": 0.11936850211782826,
+      "grad_norm": 0.1897069215774536,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.7849,
+      "step": 310
+    },
+    {
+      "epoch": 0.12321909896033885,
+      "grad_norm": 0.18983194231987,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.7928,
+      "step": 320
+    },
+    {
+      "epoch": 0.12706969580284944,
+      "grad_norm": 0.1971319019794464,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.795,
+      "step": 330
+    },
+    {
+      "epoch": 0.13092029264536004,
+      "grad_norm": 0.20915600657463074,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.7982,
+      "step": 340
+    },
+    {
+      "epoch": 0.1347708894878706,
+      "grad_norm": 0.22058261930942535,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8047,
+      "step": 350
+    },
+    {
+      "epoch": 0.1386214863303812,
+      "grad_norm": 0.18222053349018097,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.784,
+      "step": 360
+    },
+    {
+      "epoch": 0.1424720831728918,
+      "grad_norm": 0.19447489082813263,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8124,
+      "step": 370
+    },
+    {
+      "epoch": 0.14632268001540238,
+      "grad_norm": 0.1800348162651062,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.778,
+      "step": 380
+    },
+    {
+      "epoch": 0.15017327685791299,
+      "grad_norm": 0.19001047313213348,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.781,
+      "step": 390
+    },
+    {
+      "epoch": 0.15402387370042356,
+      "grad_norm": 0.16910940408706665,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.7899,
+      "step": 400
+    },
+    {
+      "epoch": 0.15787447054293416,
+      "grad_norm": 0.20713822543621063,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.7864,
+      "step": 410
+    },
+    {
+      "epoch": 0.16172506738544473,
+      "grad_norm": 0.20902737975120544,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.801,
+      "step": 420
+    },
+    {
+      "epoch": 0.16557566422795533,
+      "grad_norm": 0.19298513233661652,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.7799,
+      "step": 430
+    },
+    {
+      "epoch": 0.16942626107046593,
+      "grad_norm": 0.18674832582473755,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.7889,
+      "step": 440
+    },
+    {
+      "epoch": 0.1732768579129765,
+      "grad_norm": 0.18115893006324768,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.7731,
+      "step": 450
+    },
+    {
+      "epoch": 0.1771274547554871,
+      "grad_norm": 0.2237580269575119,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.7814,
+      "step": 460
+    },
+    {
+      "epoch": 0.18097805159799768,
+      "grad_norm": 0.17887471616268158,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.7856,
+      "step": 470
+    },
+    {
+      "epoch": 0.18482864844050828,
+      "grad_norm": 0.1986105740070343,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.7853,
+      "step": 480
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 0.1785493791103363,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.7775,
+      "step": 490
+    },
+    {
+      "epoch": 0.19252984212552945,
+      "grad_norm": 0.1797049194574356,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.7801,
+      "step": 500
+    },
+    {
+      "epoch": 0.19638043896804006,
+      "grad_norm": 0.1900743544101715,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.7703,
+      "step": 510
+    },
+    {
+      "epoch": 0.20023103581055063,
+      "grad_norm": 0.18379895389080048,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.7954,
+      "step": 520
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.18928162753582,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.7786,
+      "step": 530
+    },
+    {
+      "epoch": 0.2079322294955718,
+      "grad_norm": 0.1871851235628128,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.7882,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117828263380824,
+      "grad_norm": 0.17527592182159424,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.7917,
+      "step": 550
+    },
+    {
+      "epoch": 0.215633423180593,
+      "grad_norm": 0.18673308193683624,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.7966,
+      "step": 560
+    },
+    {
+      "epoch": 0.21948402002310358,
+      "grad_norm": 0.21826854348182678,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.814,
+      "step": 570
+    },
+    {
+      "epoch": 0.22333461686561418,
+      "grad_norm": 0.19538535177707672,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.7775,
+      "step": 580
+    },
+    {
+      "epoch": 0.22718521370812475,
+      "grad_norm": 0.18353183567523956,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.7948,
+      "step": 590
+    },
+    {
+      "epoch": 0.23103581055063535,
+      "grad_norm": 0.17784273624420166,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.7923,
+      "step": 600
+    },
+    {
+      "epoch": 0.23488640739314592,
+      "grad_norm": 0.2006170004606247,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8096,
+      "step": 610
+    },
+    {
+      "epoch": 0.23873700423565652,
+      "grad_norm": 0.17390386760234833,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.788,
+      "step": 620
+    },
+    {
+      "epoch": 0.24258760107816713,
+      "grad_norm": 0.18933330476284027,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.7999,
+      "step": 630
+    },
+    {
+      "epoch": 0.2464381979206777,
+      "grad_norm": 0.1890488862991333,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.7955,
+      "step": 640
+    },
+    {
+      "epoch": 0.25028879476318827,
+      "grad_norm": 0.18799929320812225,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7572,
+      "step": 650
+    },
+    {
+      "epoch": 0.25413939160569887,
+      "grad_norm": 0.1874053180217743,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.7853,
+      "step": 660
+    },
+    {
+      "epoch": 0.2579899884482095,
+      "grad_norm": 0.18183879554271698,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.7916,
+      "step": 670
+    },
+    {
+      "epoch": 0.2618405852907201,
+      "grad_norm": 0.17335759103298187,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7752,
+      "step": 680
+    },
+    {
+      "epoch": 0.2656911821332307,
+      "grad_norm": 0.1821741908788681,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.7862,
+      "step": 690
+    },
+    {
+      "epoch": 0.2695417789757412,
+      "grad_norm": 0.18870986998081207,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.7968,
+      "step": 700
+    },
+    {
+      "epoch": 0.2733923758182518,
+      "grad_norm": 0.16938215494155884,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.7773,
+      "step": 710
+    },
+    {
+      "epoch": 0.2772429726607624,
+      "grad_norm": 0.17932264506816864,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.7778,
+      "step": 720
+    },
+    {
+      "epoch": 0.281093569503273,
+      "grad_norm": 0.18697483837604523,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.7894,
+      "step": 730
+    },
+    {
+      "epoch": 0.2849441663457836,
+      "grad_norm": 0.2007097601890564,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.7746,
+      "step": 740
+    },
+    {
+      "epoch": 0.28879476318829417,
+      "grad_norm": 0.1683148741722107,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.7712,
+      "step": 750
+    },
+    {
+      "epoch": 0.29264536003080477,
+      "grad_norm": 0.17736418545246124,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7684,
+      "step": 760
+    },
+    {
+      "epoch": 0.29649595687331537,
+      "grad_norm": 0.1755400151014328,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.7877,
+      "step": 770
+    },
+    {
+      "epoch": 0.30034655371582597,
+      "grad_norm": 0.1915617138147354,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.7812,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041971505583365,
+      "grad_norm": 0.18405422568321228,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.767,
+      "step": 790
+    },
+    {
+      "epoch": 0.3080477474008471,
+      "grad_norm": 0.1862984597682953,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.7886,
+      "step": 800
+    },
+    {
+      "epoch": 0.3118983442433577,
+      "grad_norm": 0.17636996507644653,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.7869,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157489410858683,
+      "grad_norm": 0.17654062807559967,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.7845,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195995379283789,
+      "grad_norm": 0.17636214196681976,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.77,
+      "step": 830
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 0.17627345025539398,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.769,
+      "step": 840
+    },
+    {
+      "epoch": 0.32730073161340006,
+      "grad_norm": 0.16671109199523926,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.7777,
+      "step": 850
+    },
+    {
+      "epoch": 0.33115132845591067,
+      "grad_norm": 0.18450124561786652,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.772,
+      "step": 860
+    },
+    {
+      "epoch": 0.33500192529842127,
+      "grad_norm": 0.18116196990013123,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.7743,
+      "step": 870
+    },
+    {
+      "epoch": 0.33885252214093187,
+      "grad_norm": 0.1737600862979889,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.778,
+      "step": 880
+    },
+    {
+      "epoch": 0.3427031189834424,
+      "grad_norm": 0.17943920195102692,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7704,
+      "step": 890
+    },
+    {
+      "epoch": 0.346553715825953,
+      "grad_norm": 0.16902227699756622,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.775,
+      "step": 900
+    },
+    {
+      "epoch": 0.3504043126684636,
+      "grad_norm": 0.20363783836364746,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.765,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542549095109742,
+      "grad_norm": 0.16659632325172424,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7694,
+      "step": 920
+    },
+    {
+      "epoch": 0.3581055063534848,
+      "grad_norm": 0.2024243175983429,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7519,
+      "step": 930
+    },
+    {
+      "epoch": 0.36195610319599536,
+      "grad_norm": 0.19041098654270172,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.7824,
+      "step": 940
+    },
+    {
+      "epoch": 0.36580670003850596,
+      "grad_norm": 0.190519317984581,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.7989,
+      "step": 950
+    },
+    {
+      "epoch": 0.36965729688101656,
+      "grad_norm": 0.18579207360744476,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.7944,
+      "step": 960
+    },
+    {
+      "epoch": 0.37350789372352716,
+      "grad_norm": 0.17519797384738922,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7653,
+      "step": 970
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.17635957896709442,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7721,
+      "step": 980
+    },
+    {
+      "epoch": 0.3812090874085483,
+      "grad_norm": 0.18370145559310913,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7623,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850596842510589,
+      "grad_norm": 0.18217962980270386,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.7706,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3889102810935695,
+      "grad_norm": 0.16850058734416962,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.7901,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3927608779360801,
+      "grad_norm": 0.209172785282135,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.7903,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39661147477859066,
+      "grad_norm": 0.16027028858661652,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.7873,
+      "step": 1030
+    },
+    {
+      "epoch": 0.40046207162110126,
+      "grad_norm": 0.18578214943408966,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.7749,
+      "step": 1040
+    },
+    {
+      "epoch": 0.40431266846361186,
+      "grad_norm": 0.16587679088115692,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7712,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.1668376922607422,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.777,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41201386214863306,
+      "grad_norm": 0.18517771363258362,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7688,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4158644589911436,
+      "grad_norm": 0.16672442853450775,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.7937,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4197150558336542,
+      "grad_norm": 0.1794673204421997,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7752,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235656526761648,
+      "grad_norm": 0.17443421483039856,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.7881,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4274162495186754,
+      "grad_norm": 0.18866755068302155,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.7812,
+      "step": 1110
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 0.19678707420825958,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.7792,
+      "step": 1120
+    },
+    {
+      "epoch": 0.43511744320369655,
+      "grad_norm": 0.19384296238422394,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7593,
+      "step": 1130
+    },
+    {
+      "epoch": 0.43896804004620715,
+      "grad_norm": 0.18984901905059814,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.7835,
+      "step": 1140
+    },
+    {
+      "epoch": 0.44281863688871775,
+      "grad_norm": 0.18158769607543945,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7679,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44666923373122835,
+      "grad_norm": 0.22304730117321014,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.7971,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45051983057373896,
+      "grad_norm": 0.18337224423885345,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.8051,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4543704274162495,
+      "grad_norm": 0.17632916569709778,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.7838,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4582210242587601,
+      "grad_norm": 0.1685275137424469,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7623,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4620716211012707,
+      "grad_norm": 0.17764639854431152,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7682,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4659222179437813,
+      "grad_norm": 0.172389417886734,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.7661,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46977281478629185,
+      "grad_norm": 0.19095014035701752,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.7931,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47362341162880245,
+      "grad_norm": 0.17224900424480438,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.7872,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47747400847131305,
+      "grad_norm": 0.1736161857843399,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7658,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48132460531382365,
+      "grad_norm": 0.17754483222961426,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7603,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48517520215633425,
+      "grad_norm": 0.1945013403892517,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7717,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4890257989988448,
+      "grad_norm": 0.19029873609542847,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7519,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928763958413554,
+      "grad_norm": 0.18371720612049103,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.766,
+      "step": 1280
+    },
+    {
+      "epoch": 0.496726992683866,
+      "grad_norm": 0.17304302752017975,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.7787,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005775895263765,
+      "grad_norm": 0.17651024460792542,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7692,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5044281863688872,
+      "grad_norm": 0.17889133095741272,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.7858,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082787832113977,
+      "grad_norm": 0.18478144705295563,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7588,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5121293800539084,
+      "grad_norm": 0.18864259123802185,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7687,
+      "step": 1330
+    },
+    {
+      "epoch": 0.515979976896419,
+      "grad_norm": 0.1801624298095703,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7726,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5198305737389295,
+      "grad_norm": 0.1764153242111206,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7684,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236811705814401,
+      "grad_norm": 0.19259284436702728,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.7863,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5275317674239507,
+      "grad_norm": 0.18833261728286743,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.78,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313823642664613,
+      "grad_norm": 0.17055898904800415,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.7918,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5352329611089719,
+      "grad_norm": 0.17754703760147095,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7683,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.1777285933494568,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.7682,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5429341547939931,
+      "grad_norm": 0.1875803917646408,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.7853,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467847516365036,
+      "grad_norm": 0.1960589438676834,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7713,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5506353484790143,
+      "grad_norm": 0.19577986001968384,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.7837,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544859453215248,
+      "grad_norm": 0.19485662877559662,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.7827,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5583365421640354,
+      "grad_norm": 0.19196665287017822,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.562187139006546,
+      "grad_norm": 0.18304066359996796,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.772,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 0.17350322008132935,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7696,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698883326915672,
+      "grad_norm": 0.186803936958313,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7621,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5737389295340778,
+      "grad_norm": 0.17886526882648468,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7721,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775895263765883,
+      "grad_norm": 0.17307007312774658,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.7816,
+      "step": 1500
+    },
+    {
+      "epoch": 0.581440123219099,
+      "grad_norm": 0.1760355681180954,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7759,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852907200616095,
+      "grad_norm": 0.18364371359348297,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.7844,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5891413169041202,
+      "grad_norm": 0.1713097244501114,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.7847,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929919137466307,
+      "grad_norm": 0.1740773618221283,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.784,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5968425105891413,
+      "grad_norm": 0.16994503140449524,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.7727,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006931074316519,
+      "grad_norm": 0.16983233392238617,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.7877,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6045437042741625,
+      "grad_norm": 0.18381839990615845,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.7895,
+      "step": 1570
+    },
+    {
+      "epoch": 0.608394301116673,
+      "grad_norm": 0.18878887593746185,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.7826,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.16132965683937073,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.7774,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160954948016942,
+      "grad_norm": 0.1764029562473297,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6199460916442049,
+      "grad_norm": 0.16569490730762482,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7515,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6237966884867154,
+      "grad_norm": 0.18546047806739807,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7524,
+      "step": 1620
+    },
+    {
+      "epoch": 0.627647285329226,
+      "grad_norm": 0.17470358312129974,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.7786,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314978821717366,
+      "grad_norm": 0.1643151044845581,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7696,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6353484790142472,
+      "grad_norm": 0.18254266679286957,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7833,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391990758567578,
+      "grad_norm": 0.17984023690223694,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7589,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6430496726992684,
+      "grad_norm": 0.18744513392448425,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.7765,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6469002695417789,
+      "grad_norm": 0.17499731481075287,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7724,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6507508663842896,
+      "grad_norm": 0.18107521533966064,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7663,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6546014632268001,
+      "grad_norm": 0.1736936718225479,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7702,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6584520600693108,
+      "grad_norm": 0.18224574625492096,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7727,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6623026569118213,
+      "grad_norm": 0.19080348312854767,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7658,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6661532537543319,
+      "grad_norm": 0.1896192729473114,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7749,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6700038505968425,
+      "grad_norm": 0.18156443536281586,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7825,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6738544474393531,
+      "grad_norm": 0.16959848999977112,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7737,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6777050442818637,
+      "grad_norm": 0.17227202653884888,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7682,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6815556411243743,
+      "grad_norm": 0.18346090614795685,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.802,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6854062379668848,
+      "grad_norm": 0.17094223201274872,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.7806,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6892568348093955,
+      "grad_norm": 0.17995920777320862,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.796,
+      "step": 1790
+    },
+    {
+      "epoch": 0.693107431651906,
+      "grad_norm": 0.17120049893856049,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7632,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6969580284944167,
+      "grad_norm": 0.1839759200811386,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7571,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7008086253369272,
+      "grad_norm": 0.1752973347902298,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.781,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7046592221794378,
+      "grad_norm": 0.17422926425933838,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7634,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7085098190219484,
+      "grad_norm": 0.179404154419899,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.768,
+      "step": 1840
+    },
+    {
+      "epoch": 0.712360415864459,
+      "grad_norm": 0.18556958436965942,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.7826,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7162110127069696,
+      "grad_norm": 0.17521986365318298,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7805,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7200616095494802,
+      "grad_norm": 0.17676812410354614,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7716,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7239122063919907,
+      "grad_norm": 0.17478066682815552,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7827,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7277628032345014,
+      "grad_norm": 0.17855648696422577,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7684,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7316134000770119,
+      "grad_norm": 0.19242259860038757,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.779,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7354639969195226,
+      "grad_norm": 0.17057369649410248,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7783,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7393145937620331,
+      "grad_norm": 0.1721663624048233,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7643,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7431651906045437,
+      "grad_norm": 0.18541523814201355,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.7865,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7470157874470543,
+      "grad_norm": 0.17186468839645386,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.7825,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7508663842895649,
+      "grad_norm": 0.17627353966236115,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7632,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.1883707046508789,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.7917,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7585675779745861,
+      "grad_norm": 0.1942831128835678,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.7796,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7624181748170966,
+      "grad_norm": 0.19011417031288147,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.78,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7662687716596073,
+      "grad_norm": 0.1932048350572586,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.766,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7701193685021178,
+      "grad_norm": 0.1758764237165451,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7694,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7739699653446284,
+      "grad_norm": 0.1693655103445053,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7746,
+      "step": 2010
+    },
+    {
+      "epoch": 0.777820562187139,
+      "grad_norm": 0.1742713898420334,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7577,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7816711590296496,
+      "grad_norm": 0.17463107407093048,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7533,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7855217558721602,
+      "grad_norm": 0.17823243141174316,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7688,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7893723527146708,
+      "grad_norm": 0.17314574122428894,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7708,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7932229495571813,
+      "grad_norm": 0.16192854940891266,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7579,
+      "step": 2060
+    },
+    {
+      "epoch": 0.797073546399692,
+      "grad_norm": 0.1823882907629013,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7746,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8009241432422025,
+      "grad_norm": 0.1653694361448288,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7493,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8047747400847132,
+      "grad_norm": 0.17266665399074554,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7757,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8086253369272237,
+      "grad_norm": 0.17636536061763763,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.77,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8124759337697343,
+      "grad_norm": 0.17032667994499207,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7696,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.18471738696098328,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7848,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8201771274547555,
+      "grad_norm": 0.18311548233032227,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7663,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8240277242972661,
+      "grad_norm": 0.17615772783756256,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7687,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8278783211397767,
+      "grad_norm": 0.1740947663784027,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7595,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8317289179822872,
+      "grad_norm": 0.17215745151042938,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.7796,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8355795148247979,
+      "grad_norm": 0.17850103974342346,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.7738,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8394301116673084,
+      "grad_norm": 0.1673368215560913,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7677,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8432807085098191,
+      "grad_norm": 0.18084464967250824,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.7706,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8471313053523296,
+      "grad_norm": 0.182454913854599,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7713,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8509819021948402,
+      "grad_norm": 0.17099542915821075,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7425,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8548324990373508,
+      "grad_norm": 0.1629817932844162,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7765,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586830958798614,
+      "grad_norm": 0.1888730674982071,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7693,
+      "step": 2230
+    },
+    {
+      "epoch": 0.862533692722372,
+      "grad_norm": 0.169301837682724,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.7794,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663842895648826,
+      "grad_norm": 0.17615675926208496,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7688,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8702348864073931,
+      "grad_norm": 0.20490558445453644,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7507,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740854832499038,
+      "grad_norm": 0.17429932951927185,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7699,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8779360800924143,
+      "grad_norm": 0.1715354472398758,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7726,
+      "step": 2280
+    },
+    {
+      "epoch": 0.881786676934925,
+      "grad_norm": 0.17635679244995117,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7801,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8856372737774355,
+      "grad_norm": 0.16879959404468536,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.76,
+      "step": 2300
+    },
+    {
+      "epoch": 0.889487870619946,
+      "grad_norm": 0.16405585408210754,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7708,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8933384674624567,
+      "grad_norm": 0.16609185934066772,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7745,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971890643049673,
+      "grad_norm": 0.1806134432554245,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.7835,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9010396611474779,
+      "grad_norm": 0.17159497737884521,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7767,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048902579899885,
+      "grad_norm": 0.17958620190620422,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.754,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908740854832499,
+      "grad_norm": 0.1731281578540802,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7698,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125914516750097,
+      "grad_norm": 0.19341103732585907,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7633,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9164420485175202,
+      "grad_norm": 0.1695488840341568,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7726,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202926453600309,
+      "grad_norm": 0.17018316686153412,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7838,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9241432422025414,
+      "grad_norm": 0.1882760375738144,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7784,
+      "step": 2400
+    },
+    {
+      "epoch": 0.927993839045052,
+      "grad_norm": 0.1671808362007141,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7567,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9318444358875626,
+      "grad_norm": 0.17302225530147552,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.7879,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9356950327300732,
+      "grad_norm": 0.17313244938850403,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.7799,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9395456295725837,
+      "grad_norm": 0.18129077553749084,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7718,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.19332674145698547,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7602,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9472468232576049,
+      "grad_norm": 0.184487983584404,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.7856,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510974201001156,
+      "grad_norm": 0.18049661815166473,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7822,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9549480169426261,
+      "grad_norm": 0.17971529066562653,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7677,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587986137851366,
+      "grad_norm": 0.16799326241016388,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7692,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9626492106276473,
+      "grad_norm": 0.16880232095718384,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7698,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664998074701578,
+      "grad_norm": 0.1710309088230133,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7684,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9703504043126685,
+      "grad_norm": 0.17211191356182098,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7825,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974201001155179,
+      "grad_norm": 0.18142619729042053,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7644,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9780515979976896,
+      "grad_norm": 0.1643381118774414,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7635,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9819021948402002,
+      "grad_norm": 0.16540053486824036,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7801,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9857527916827108,
+      "grad_norm": 0.16797679662704468,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.766,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9896033885252215,
+      "grad_norm": 0.17360465228557587,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7608,
+      "step": 2570
+    },
+    {
+      "epoch": 0.993453985367732,
+      "grad_norm": 0.16853104531764984,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7523,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9973045822102425,
+      "grad_norm": 0.18216222524642944,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7827,
+      "step": 2590
+    },
+    {
+      "epoch": 1.0,
+      "step": 2597,
+      "total_flos": 1.6052445933861863e+19,
+      "train_loss": 0.7865946378256203,
+      "train_runtime": 15415.2285,
+      "train_samples_per_second": 43.133,
+      "train_steps_per_second": 0.168
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 584317136,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6052445933861863e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/smollm2/webssl_mae3b_full2b_224/finetune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a35280562ca92fc0b1e041c3cd99dd0508f104d8432cfc8d1cb39c9594f2441
+size 6264

continuous/smollm2/webssl_mae3b_full2b_224/pretrain/config.json

@@ -0,0 +1,70 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_hidden_size": 3072,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "hf:/cache/ckpt/download/tokenizer/continuous/webssl/webssl-mae3b-full2b-224",
+  "mm_vision_tower_lr": null,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 49152
+}

continuous/smollm2/webssl_mae3b_full2b_224/pretrain/mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd461d7605eeff4625b5051d89390256f7dcbc04d9ed2fbf2db8f4ce18047d40
+size 41961528

continuous/smollm2/webssl_mae3b_full2b_224/pretrain/trainer_state.json

@@ -0,0 +1,421 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 15.429805755615234,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 4.8873,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.277868390083313,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 3.099,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.08794980496168137,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 2.8165,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.11398614197969437,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 2.7481,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.09792532026767731,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 2.731,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.14330044388771057,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 2.7087,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.13595284521579742,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 2.6911,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.17034049332141876,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 2.6718,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.15782517194747925,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 2.6539,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.18196243047714233,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 2.643,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.23070120811462402,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 2.6238,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.2893446385860443,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 2.6165,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.24239318072795868,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 2.5974,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.24815329909324646,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 2.5874,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.20086264610290527,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 2.5886,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.2944795787334442,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 2.5734,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.21838296949863434,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 2.571,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.3010435104370117,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 2.5577,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.33978304266929626,
+      "learning_rate": 0.000779204504653894,
+      "loss": 2.5553,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.3650014102458954,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 2.5329,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.21939657628536224,
+      "learning_rate": 0.00072685988254984,
+      "loss": 2.534,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.2599424719810486,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 2.5373,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.297713965177536,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 2.5354,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.32421648502349854,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 2.5272,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.19341343641281128,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 2.5178,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.19291949272155762,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 2.5243,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.26082533597946167,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 2.5042,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.3660660982131958,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 2.5097,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.331939697265625,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 2.4933,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.2336948961019516,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 2.4944,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.32608482241630554,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 2.5006,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.2551572024822235,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 2.4999,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.24266883730888367,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 2.4835,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.25914663076400757,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 2.4871,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.21899905800819397,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 2.4899,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.21978126466274261,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 2.4905,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.23956800997257233,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 2.4798,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.22943761944770813,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 2.4907,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.2295512706041336,
+      "learning_rate": 0.000208323983828828,
+      "loss": 2.4763,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.21079839766025543,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 2.4771,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.2530940771102905,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 2.4748,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.15145297348499298,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 2.4665,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.1946546733379364,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 2.4715,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.20023037493228912,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 2.4768,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.17691192030906677,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 2.4755,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.1780954748392105,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 2.4648,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.18580275774002075,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 2.4566,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.15745432674884796,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 2.4613,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.15123248100280762,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 2.4678,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.1699099987745285,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 2.471,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.15120835602283478,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 2.4618,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.14108987152576447,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 2.4557,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.12982480227947235,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 2.4609,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.16400261223316193,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 2.4632,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 9.521344904219853e+17,
+      "train_loss": 2.592465479439552,
+      "train_runtime": 2009.8269,
+      "train_samples_per_second": 277.7,
+      "train_steps_per_second": 0.271
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 34658176,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.521344904219853e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}