Upload folder using huggingface_hub

checkpoint-1250/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-bjn_Latn-coli-cw2v/",
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100384
+}

checkpoint-1250/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.48.0.dev0"
+}

checkpoint-1250/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcab17684cfa23bd2206a1d95cf55871fabb85b5affecebb57d26fc3dbe4e171
+size 4950070472

checkpoint-1250/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0b6a357d03676c4986588aaf4dc96afc3f44a0498514961d2b2cfa1940655e
+size 4991622816

checkpoint-1250/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1038a7d346a681a8fb6949e054c2246f3f3c80e826855c1cec6af1155cc607d
+size 4924546896

checkpoint-1250/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c0a21146ace02d36928787ae7f34be868f7c81b894dea98ec7b0e5a3ea01b2
+size 4857404928

checkpoint-1250/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f82a3014ccfc0f67208f63785ae4bc71f09aba86db48bf6139d18178abbfed
+size 4857404928

checkpoint-1250/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6e00741b4ee61aa3308ec367b988e85cdea5d870c66fb4a866e27613e90079
+size 4614509080

checkpoint-1250/model.safetensors.index.json

@@ -0,0 +1,362 @@
+{
+  "metadata": {
+    "total_size": 29195517952
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfa119298ec0611eb8b8fa67e924314a00a32a3126ed8733ce15450ee944606
+size 13055369358

checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f24bdfc61fb1561d8dfbb28db229e64f52f3ccb0400c6d2034437ea3f88522
+size 1064

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897bf89d23736d5420c5afd648a553e7134f06192c6a200daea71920837be1e4
+size 5432

checkpoint-625/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-bjn_Latn-coli-cw2v/",
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100384
+}

checkpoint-625/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.48.0.dev0"
+}

checkpoint-625/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea583755956775bd3340b805e18e40dddbbe40b5ad868382d1d2bc720412a468
+size 4950070472

checkpoint-625/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0b6a357d03676c4986588aaf4dc96afc3f44a0498514961d2b2cfa1940655e
+size 4991622816

checkpoint-625/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1038a7d346a681a8fb6949e054c2246f3f3c80e826855c1cec6af1155cc607d
+size 4924546896

checkpoint-625/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c0a21146ace02d36928787ae7f34be868f7c81b894dea98ec7b0e5a3ea01b2
+size 4857404928

checkpoint-625/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f82a3014ccfc0f67208f63785ae4bc71f09aba86db48bf6139d18178abbfed
+size 4857404928

checkpoint-625/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4adb395614291f235845d88209f5ad969b3fc1cdc3efd4b834235441c76c84
+size 4614509080

checkpoint-625/model.safetensors.index.json

@@ -0,0 +1,362 @@
+{
+  "metadata": {
+    "total_size": 29195517952
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-625/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576d910e338bac10e9b95c1d91ffcaccbce4779460f8c6ab208422b983ccbef6
+size 13055369358

checkpoint-625/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-625/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1701cf55b4ad1045d3f9ea702d2328d058fe9477bd471b3c941161ddc0988d
+size 1064

checkpoint-625/trainer_state.json

@@ -0,0 +1,2217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032,
+      "grad_norm": 5.2346367835998535,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 5.8721,
+      "step": 2
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 6.022397994995117,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 5.775,
+      "step": 4
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 4.282025337219238,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 5.6253,
+      "step": 6
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 3.7371106147766113,
+      "learning_rate": 1.2698412698412699e-05,
+      "loss": 5.1153,
+      "step": 8
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 8.722667694091797,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 5.3364,
+      "step": 10
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 4.185220718383789,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 5.3102,
+      "step": 12
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 3.5511889457702637,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 4.9739,
+      "step": 14
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 3.152355194091797,
+      "learning_rate": 2.5396825396825397e-05,
+      "loss": 4.5878,
+      "step": 16
+    },
+    {
+      "epoch": 0.0288,
+      "grad_norm": 2.925100326538086,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.7562,
+      "step": 18
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 3.192331552505493,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 4.6627,
+      "step": 20
+    },
+    {
+      "epoch": 0.0352,
+      "grad_norm": 2.958089590072632,
+      "learning_rate": 3.492063492063492e-05,
+      "loss": 4.6227,
+      "step": 22
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 4.2280592918396,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 4.4283,
+      "step": 24
+    },
+    {
+      "epoch": 0.0416,
+      "grad_norm": 2.748825788497925,
+      "learning_rate": 4.126984126984127e-05,
+      "loss": 4.2503,
+      "step": 26
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 2.705292224884033,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 4.4007,
+      "step": 28
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.5890371799468994,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 4.3219,
+      "step": 30
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 2.485609769821167,
+      "learning_rate": 5.0793650793650794e-05,
+      "loss": 4.2298,
+      "step": 32
+    },
+    {
+      "epoch": 0.0544,
+      "grad_norm": 2.5438082218170166,
+      "learning_rate": 5.396825396825397e-05,
+      "loss": 4.2862,
+      "step": 34
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 2.5402183532714844,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 4.0492,
+      "step": 36
+    },
+    {
+      "epoch": 0.0608,
+      "grad_norm": 2.5497469902038574,
+      "learning_rate": 6.0317460317460316e-05,
+      "loss": 4.0702,
+      "step": 38
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.3628146648406982,
+      "learning_rate": 6.349206349206349e-05,
+      "loss": 3.9895,
+      "step": 40
+    },
+    {
+      "epoch": 0.0672,
+      "grad_norm": 2.201223611831665,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 3.9743,
+      "step": 42
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 2.448514938354492,
+      "learning_rate": 6.984126984126984e-05,
+      "loss": 4.076,
+      "step": 44
+    },
+    {
+      "epoch": 0.0736,
+      "grad_norm": 2.386176824569702,
+      "learning_rate": 7.301587301587302e-05,
+      "loss": 3.912,
+      "step": 46
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 2.2783148288726807,
+      "learning_rate": 7.619047619047618e-05,
+      "loss": 3.8678,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.472463369369507,
+      "learning_rate": 7.936507936507937e-05,
+      "loss": 3.9058,
+      "step": 50
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 2.548892021179199,
+      "learning_rate": 8.253968253968255e-05,
+      "loss": 3.7761,
+      "step": 52
+    },
+    {
+      "epoch": 0.0864,
+      "grad_norm": 2.4397833347320557,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 3.9437,
+      "step": 54
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 2.532597303390503,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 3.8437,
+      "step": 56
+    },
+    {
+      "epoch": 0.0928,
+      "grad_norm": 2.45221209526062,
+      "learning_rate": 9.206349206349206e-05,
+      "loss": 3.8429,
+      "step": 58
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.645132064819336,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 3.7965,
+      "step": 60
+    },
+    {
+      "epoch": 0.0992,
+      "grad_norm": 2.385370969772339,
+      "learning_rate": 9.841269841269841e-05,
+      "loss": 3.7968,
+      "step": 62
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 2.2052712440490723,
+      "learning_rate": 9.99998248790669e-05,
+      "loss": 3.7794,
+      "step": 64
+    },
+    {
+      "epoch": 0.1056,
+      "grad_norm": 2.3219361305236816,
+      "learning_rate": 9.999842391896222e-05,
+      "loss": 3.6841,
+      "step": 66
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 2.5465614795684814,
+      "learning_rate": 9.999562203800676e-05,
+      "loss": 3.5312,
+      "step": 68
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.497755527496338,
+      "learning_rate": 9.999141931470729e-05,
+      "loss": 3.6803,
+      "step": 70
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 2.157752752304077,
+      "learning_rate": 9.998581586682116e-05,
+      "loss": 3.5856,
+      "step": 72
+    },
+    {
+      "epoch": 0.1184,
+      "grad_norm": 2.1215410232543945,
+      "learning_rate": 9.997881185135307e-05,
+      "loss": 3.5429,
+      "step": 74
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 3.784062385559082,
+      "learning_rate": 9.997040746455062e-05,
+      "loss": 3.6365,
+      "step": 76
+    },
+    {
+      "epoch": 0.1248,
+      "grad_norm": 2.2366509437561035,
+      "learning_rate": 9.996060294189887e-05,
+      "loss": 3.5129,
+      "step": 78
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 2.240877628326416,
+      "learning_rate": 9.994939855811362e-05,
+      "loss": 3.6185,
+      "step": 80
+    },
+    {
+      "epoch": 0.1312,
+      "grad_norm": 2.176579475402832,
+      "learning_rate": 9.993679462713395e-05,
+      "loss": 3.4999,
+      "step": 82
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 2.3514060974121094,
+      "learning_rate": 9.992279150211314e-05,
+      "loss": 3.466,
+      "step": 84
+    },
+    {
+      "epoch": 0.1376,
+      "grad_norm": 2.2598917484283447,
+      "learning_rate": 9.990738957540896e-05,
+      "loss": 3.6413,
+      "step": 86
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 2.0476276874542236,
+      "learning_rate": 9.989058927857263e-05,
+      "loss": 3.5978,
+      "step": 88
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 2.1762521266937256,
+      "learning_rate": 9.987239108233668e-05,
+      "loss": 3.6667,
+      "step": 90
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": 2.274958848953247,
+      "learning_rate": 9.985279549660185e-05,
+      "loss": 3.6054,
+      "step": 92
+    },
+    {
+      "epoch": 0.1504,
+      "grad_norm": 2.249992847442627,
+      "learning_rate": 9.983180307042274e-05,
+      "loss": 3.6287,
+      "step": 94
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 2.23592209815979,
+      "learning_rate": 9.980941439199246e-05,
+      "loss": 3.5967,
+      "step": 96
+    },
+    {
+      "epoch": 0.1568,
+      "grad_norm": 2.1270549297332764,
+      "learning_rate": 9.97856300886261e-05,
+      "loss": 3.4583,
+      "step": 98
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.140577554702759,
+      "learning_rate": 9.976045082674319e-05,
+      "loss": 3.4091,
+      "step": 100
+    },
+    {
+      "epoch": 0.1632,
+      "grad_norm": 2.1698827743530273,
+      "learning_rate": 9.973387731184902e-05,
+      "loss": 3.5535,
+      "step": 102
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 2.188966751098633,
+      "learning_rate": 9.97059102885149e-05,
+      "loss": 3.4673,
+      "step": 104
+    },
+    {
+      "epoch": 0.1696,
+      "grad_norm": 2.015054702758789,
+      "learning_rate": 9.967655054035727e-05,
+      "loss": 3.5025,
+      "step": 106
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 2.42785906791687,
+      "learning_rate": 9.964579889001569e-05,
+      "loss": 3.3789,
+      "step": 108
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 3.828245162963867,
+      "learning_rate": 9.961365619912989e-05,
+      "loss": 3.3673,
+      "step": 110
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 2.0954813957214355,
+      "learning_rate": 9.95801233683156e-05,
+      "loss": 3.501,
+      "step": 112
+    },
+    {
+      "epoch": 0.1824,
+      "grad_norm": 2.17081618309021,
+      "learning_rate": 9.954520133713924e-05,
+      "loss": 3.3926,
+      "step": 114
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 2.04852557182312,
+      "learning_rate": 9.950889108409172e-05,
+      "loss": 3.391,
+      "step": 116
+    },
+    {
+      "epoch": 0.1888,
+      "grad_norm": 2.426689386367798,
+      "learning_rate": 9.947119362656092e-05,
+      "loss": 3.4257,
+      "step": 118
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 3.680421829223633,
+      "learning_rate": 9.94321100208032e-05,
+      "loss": 3.2982,
+      "step": 120
+    },
+    {
+      "epoch": 0.1952,
+      "grad_norm": 2.1409482955932617,
+      "learning_rate": 9.939164136191384e-05,
+      "loss": 3.4619,
+      "step": 122
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 1.9399126768112183,
+      "learning_rate": 9.934978878379636e-05,
+      "loss": 3.3362,
+      "step": 124
+    },
+    {
+      "epoch": 0.2016,
+      "grad_norm": 1.954500675201416,
+      "learning_rate": 9.930655345913071e-05,
+      "loss": 3.1957,
+      "step": 126
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 2.1550300121307373,
+      "learning_rate": 9.926193659934043e-05,
+      "loss": 3.4578,
+      "step": 128
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 2.44838547706604,
+      "learning_rate": 9.921593945455869e-05,
+      "loss": 3.3975,
+      "step": 130
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 2.087881565093994,
+      "learning_rate": 9.916856331359335e-05,
+      "loss": 3.3682,
+      "step": 132
+    },
+    {
+      "epoch": 0.2144,
+      "grad_norm": 2.253127336502075,
+      "learning_rate": 9.911980950389067e-05,
+      "loss": 3.2451,
+      "step": 134
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 2.3103411197662354,
+      "learning_rate": 9.906967939149831e-05,
+      "loss": 3.3999,
+      "step": 136
+    },
+    {
+      "epoch": 0.2208,
+      "grad_norm": 2.2471373081207275,
+      "learning_rate": 9.901817438102695e-05,
+      "loss": 3.2925,
+      "step": 138
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 2.1333861351013184,
+      "learning_rate": 9.896529591561093e-05,
+      "loss": 3.3604,
+      "step": 140
+    },
+    {
+      "epoch": 0.2272,
+      "grad_norm": 1.914016842842102,
+      "learning_rate": 9.891104547686782e-05,
+      "loss": 3.1728,
+      "step": 142
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 2.061126232147217,
+      "learning_rate": 9.8855424584857e-05,
+      "loss": 3.2384,
+      "step": 144
+    },
+    {
+      "epoch": 0.2336,
+      "grad_norm": 2.153684139251709,
+      "learning_rate": 9.879843479803691e-05,
+      "loss": 3.2965,
+      "step": 146
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 2.109224557876587,
+      "learning_rate": 9.874007771322151e-05,
+      "loss": 3.2568,
+      "step": 148
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.588501214981079,
+      "learning_rate": 9.868035496553546e-05,
+      "loss": 3.223,
+      "step": 150
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 2.2085981369018555,
+      "learning_rate": 9.86192682283684e-05,
+      "loss": 3.3506,
+      "step": 152
+    },
+    {
+      "epoch": 0.2464,
+      "grad_norm": 1.9722400903701782,
+      "learning_rate": 9.855681921332793e-05,
+      "loss": 3.2184,
+      "step": 154
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 2.0837275981903076,
+      "learning_rate": 9.849300967019175e-05,
+      "loss": 3.2083,
+      "step": 156
+    },
+    {
+      "epoch": 0.2528,
+      "grad_norm": 1.799812912940979,
+      "learning_rate": 9.84278413868586e-05,
+      "loss": 3.2038,
+      "step": 158
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.0242528915405273,
+      "learning_rate": 9.836131618929819e-05,
+      "loss": 3.3193,
+      "step": 160
+    },
+    {
+      "epoch": 0.2592,
+      "grad_norm": 1.948160171508789,
+      "learning_rate": 9.82934359415e-05,
+      "loss": 3.2132,
+      "step": 162
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 2.1192405223846436,
+      "learning_rate": 9.822420254542108e-05,
+      "loss": 3.2444,
+      "step": 164
+    },
+    {
+      "epoch": 0.2656,
+      "grad_norm": 1.9564788341522217,
+      "learning_rate": 9.815361794093272e-05,
+      "loss": 3.105,
+      "step": 166
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 2.1899731159210205,
+      "learning_rate": 9.808168410576617e-05,
+      "loss": 3.1558,
+      "step": 168
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 2.0988922119140625,
+      "learning_rate": 9.800840305545715e-05,
+      "loss": 3.2485,
+      "step": 170
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 2.2193591594696045,
+      "learning_rate": 9.793377684328939e-05,
+      "loss": 3.296,
+      "step": 172
+    },
+    {
+      "epoch": 0.2784,
+      "grad_norm": 2.007413864135742,
+      "learning_rate": 9.785780756023714e-05,
+      "loss": 3.1287,
+      "step": 174
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 1.9749376773834229,
+      "learning_rate": 9.778049733490655e-05,
+      "loss": 3.0076,
+      "step": 176
+    },
+    {
+      "epoch": 0.2848,
+      "grad_norm": 2.059288263320923,
+      "learning_rate": 9.770184833347606e-05,
+      "loss": 3.1663,
+      "step": 178
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 1.96829354763031,
+      "learning_rate": 9.762186275963563e-05,
+      "loss": 3.2163,
+      "step": 180
+    },
+    {
+      "epoch": 0.2912,
+      "grad_norm": 2.0208017826080322,
+      "learning_rate": 9.754054285452506e-05,
+      "loss": 3.2242,
+      "step": 182
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 1.88913094997406,
+      "learning_rate": 9.745789089667121e-05,
+      "loss": 3.0072,
+      "step": 184
+    },
+    {
+      "epoch": 0.2976,
+      "grad_norm": 1.996383547782898,
+      "learning_rate": 9.737390920192408e-05,
+      "loss": 3.2108,
+      "step": 186
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 2.0667550563812256,
+      "learning_rate": 9.7288600123392e-05,
+      "loss": 3.108,
+      "step": 188
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 1.9526984691619873,
+      "learning_rate": 9.720196605137565e-05,
+      "loss": 3.067,
+      "step": 190
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 2.0643012523651123,
+      "learning_rate": 9.71140094133011e-05,
+      "loss": 3.2143,
+      "step": 192
+    },
+    {
+      "epoch": 0.3104,
+      "grad_norm": 2.187326431274414,
+      "learning_rate": 9.702473267365182e-05,
+      "loss": 3.1007,
+      "step": 194
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 2.1299145221710205,
+      "learning_rate": 9.693413833389956e-05,
+      "loss": 3.1868,
+      "step": 196
+    },
+    {
+      "epoch": 0.3168,
+      "grad_norm": 1.7644037008285522,
+      "learning_rate": 9.684222893243431e-05,
+      "loss": 2.9406,
+      "step": 198
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.112617015838623,
+      "learning_rate": 9.674900704449324e-05,
+      "loss": 3.1198,
+      "step": 200
+    },
+    {
+      "epoch": 0.3232,
+      "grad_norm": 1.8327059745788574,
+      "learning_rate": 9.665447528208836e-05,
+      "loss": 3.1278,
+      "step": 202
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 1.8569375276565552,
+      "learning_rate": 9.655863629393351e-05,
+      "loss": 3.2069,
+      "step": 204
+    },
+    {
+      "epoch": 0.3296,
+      "grad_norm": 1.7960104942321777,
+      "learning_rate": 9.64614927653701e-05,
+      "loss": 3.0708,
+      "step": 206
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 1.888593316078186,
+      "learning_rate": 9.636304741829181e-05,
+      "loss": 3.1365,
+      "step": 208
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 1.8564034700393677,
+      "learning_rate": 9.626330301106837e-05,
+      "loss": 3.0059,
+      "step": 210
+    },
+    {
+      "epoch": 0.3392,
+      "grad_norm": 1.9591517448425293,
+      "learning_rate": 9.616226233846828e-05,
+      "loss": 2.9778,
+      "step": 212
+    },
+    {
+      "epoch": 0.3424,
+      "grad_norm": 2.025777816772461,
+      "learning_rate": 9.605992823158046e-05,
+      "loss": 3.0969,
+      "step": 214
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 1.8839352130889893,
+      "learning_rate": 9.595630355773501e-05,
+      "loss": 3.1342,
+      "step": 216
+    },
+    {
+      "epoch": 0.3488,
+      "grad_norm": 5.388115882873535,
+      "learning_rate": 9.585139122042274e-05,
+      "loss": 3.1961,
+      "step": 218
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 2.056678533554077,
+      "learning_rate": 9.574519415921396e-05,
+      "loss": 3.1183,
+      "step": 220
+    },
+    {
+      "epoch": 0.3552,
+      "grad_norm": 3.0575530529022217,
+      "learning_rate": 9.5637715349676e-05,
+      "loss": 3.1446,
+      "step": 222
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 1.8165247440338135,
+      "learning_rate": 9.552895780328987e-05,
+      "loss": 3.0338,
+      "step": 224
+    },
+    {
+      "epoch": 0.3616,
+      "grad_norm": 1.845023512840271,
+      "learning_rate": 9.541892456736595e-05,
+      "loss": 3.194,
+      "step": 226
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 1.9389755725860596,
+      "learning_rate": 9.530761872495849e-05,
+      "loss": 3.0054,
+      "step": 228
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 1.9471769332885742,
+      "learning_rate": 9.519504339477932e-05,
+      "loss": 3.1499,
+      "step": 230
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 1.9367070198059082,
+      "learning_rate": 9.508120173111039e-05,
+      "loss": 3.0068,
+      "step": 232
+    },
+    {
+      "epoch": 0.3744,
+      "grad_norm": 2.018630027770996,
+      "learning_rate": 9.496609692371548e-05,
+      "loss": 3.1722,
+      "step": 234
+    },
+    {
+      "epoch": 0.3776,
+      "grad_norm": 2.0086734294891357,
+      "learning_rate": 9.484973219775074e-05,
+      "loss": 3.2773,
+      "step": 236
+    },
+    {
+      "epoch": 0.3808,
+      "grad_norm": 1.9771322011947632,
+      "learning_rate": 9.473211081367436e-05,
+      "loss": 3.0502,
+      "step": 238
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 1.9231762886047363,
+      "learning_rate": 9.46132360671552e-05,
+      "loss": 3.0415,
+      "step": 240
+    },
+    {
+      "epoch": 0.3872,
+      "grad_norm": 1.924302101135254,
+      "learning_rate": 9.449311128898049e-05,
+      "loss": 3.0794,
+      "step": 242
+    },
+    {
+      "epoch": 0.3904,
+      "grad_norm": 1.967323899269104,
+      "learning_rate": 9.437173984496246e-05,
+      "loss": 3.1527,
+      "step": 244
+    },
+    {
+      "epoch": 0.3936,
+      "grad_norm": 1.9681285619735718,
+      "learning_rate": 9.424912513584401e-05,
+      "loss": 3.1767,
+      "step": 246
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 1.908687710762024,
+      "learning_rate": 9.412527059720352e-05,
+      "loss": 2.9755,
+      "step": 248
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.9891773462295532,
+      "learning_rate": 9.400017969935848e-05,
+      "loss": 2.9644,
+      "step": 250
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 1.8200337886810303,
+      "learning_rate": 9.387385594726829e-05,
+      "loss": 3.0334,
+      "step": 252
+    },
+    {
+      "epoch": 0.4064,
+      "grad_norm": 1.9553104639053345,
+      "learning_rate": 9.374630288043614e-05,
+      "loss": 3.1011,
+      "step": 254
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 3.5282905101776123,
+      "learning_rate": 9.361752407280965e-05,
+      "loss": 2.9859,
+      "step": 256
+    },
+    {
+      "epoch": 0.4128,
+      "grad_norm": 1.9712797403335571,
+      "learning_rate": 9.348752313268093e-05,
+      "loss": 2.9472,
+      "step": 258
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 1.927635908126831,
+      "learning_rate": 9.335630370258533e-05,
+      "loss": 3.1396,
+      "step": 260
+    },
+    {
+      "epoch": 0.4192,
+      "grad_norm": 1.9233123064041138,
+      "learning_rate": 9.322386945919946e-05,
+      "loss": 3.1889,
+      "step": 262
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 1.870160460472107,
+      "learning_rate": 9.309022411323816e-05,
+      "loss": 3.0916,
+      "step": 264
+    },
+    {
+      "epoch": 0.4256,
+      "grad_norm": 1.7860538959503174,
+      "learning_rate": 9.295537140935049e-05,
+      "loss": 3.1584,
+      "step": 266
+    },
+    {
+      "epoch": 0.4288,
+      "grad_norm": 1.723097801208496,
+      "learning_rate": 9.281931512601485e-05,
+      "loss": 2.8587,
+      "step": 268
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 1.976706862449646,
+      "learning_rate": 9.26820590754331e-05,
+      "loss": 2.9942,
+      "step": 270
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 1.8147152662277222,
+      "learning_rate": 9.254360710342371e-05,
+      "loss": 3.087,
+      "step": 272
+    },
+    {
+      "epoch": 0.4384,
+      "grad_norm": 1.8946576118469238,
+      "learning_rate": 9.240396308931407e-05,
+      "loss": 3.0101,
+      "step": 274
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 1.8432953357696533,
+      "learning_rate": 9.226313094583173e-05,
+      "loss": 3.0351,
+      "step": 276
+    },
+    {
+      "epoch": 0.4448,
+      "grad_norm": 1.8600575923919678,
+      "learning_rate": 9.212111461899479e-05,
+      "loss": 3.0027,
+      "step": 278
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 1.7912688255310059,
+      "learning_rate": 9.197791808800135e-05,
+      "loss": 3.0568,
+      "step": 280
+    },
+    {
+      "epoch": 0.4512,
+      "grad_norm": 2.005932569503784,
+      "learning_rate": 9.183354536511803e-05,
+      "loss": 2.9778,
+      "step": 282
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 1.8989531993865967,
+      "learning_rate": 9.168800049556747e-05,
+      "loss": 2.9711,
+      "step": 284
+    },
+    {
+      "epoch": 0.4576,
+      "grad_norm": 1.7888331413269043,
+      "learning_rate": 9.154128755741509e-05,
+      "loss": 2.9901,
+      "step": 286
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 1.9094816446304321,
+      "learning_rate": 9.139341066145472e-05,
+      "loss": 3.0248,
+      "step": 288
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 1.7940737009048462,
+      "learning_rate": 9.124437395109353e-05,
+      "loss": 3.0141,
+      "step": 290
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 1.7626845836639404,
+      "learning_rate": 9.109418160223585e-05,
+      "loss": 2.9531,
+      "step": 292
+    },
+    {
+      "epoch": 0.4704,
+      "grad_norm": 1.9440515041351318,
+      "learning_rate": 9.094283782316619e-05,
+      "loss": 2.9732,
+      "step": 294
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 1.7515082359313965,
+      "learning_rate": 9.079034685443133e-05,
+      "loss": 2.8,
+      "step": 296
+    },
+    {
+      "epoch": 0.4768,
+      "grad_norm": 1.8595532178878784,
+      "learning_rate": 9.063671296872149e-05,
+      "loss": 2.9873,
+      "step": 298
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.9954842329025269,
+      "learning_rate": 9.048194047075069e-05,
+      "loss": 2.9793,
+      "step": 300
+    },
+    {
+      "epoch": 0.4832,
+      "grad_norm": 1.8819364309310913,
+      "learning_rate": 9.032603369713596e-05,
+      "loss": 2.8904,
+      "step": 302
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 1.75027596950531,
+      "learning_rate": 9.016899701627604e-05,
+      "loss": 2.9811,
+      "step": 304
+    },
+    {
+      "epoch": 0.4896,
+      "grad_norm": 1.9617975950241089,
+      "learning_rate": 9.00108348282288e-05,
+      "loss": 3.0418,
+      "step": 306
+    },
+    {
+      "epoch": 0.4928,
+      "grad_norm": 1.8097938299179077,
+      "learning_rate": 8.985155156458811e-05,
+      "loss": 3.0068,
+      "step": 308
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 2.008989095687866,
+      "learning_rate": 8.969115168835954e-05,
+      "loss": 2.8913,
+      "step": 310
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 1.8119149208068848,
+      "learning_rate": 8.952963969383538e-05,
+      "loss": 3.004,
+      "step": 312
+    },
+    {
+      "epoch": 0.5024,
+      "grad_norm": 1.9150359630584717,
+      "learning_rate": 8.93670201064687e-05,
+      "loss": 2.9404,
+      "step": 314
+    },
+    {
+      "epoch": 0.5056,
+      "grad_norm": 1.8803378343582153,
+      "learning_rate": 8.920329748274649e-05,
+      "loss": 2.9279,
+      "step": 316
+    },
+    {
+      "epoch": 0.5088,
+      "grad_norm": 1.7308014631271362,
+      "learning_rate": 8.903847641006218e-05,
+      "loss": 2.9482,
+      "step": 318
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2.0764575004577637,
+      "learning_rate": 8.887256150658684e-05,
+      "loss": 2.9425,
+      "step": 320
+    },
+    {
+      "epoch": 0.5152,
+      "grad_norm": 1.8219692707061768,
+      "learning_rate": 8.870555742113998e-05,
+      "loss": 3.0176,
+      "step": 322
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 1.8642444610595703,
+      "learning_rate": 8.85374688330592e-05,
+      "loss": 3.0474,
+      "step": 324
+    },
+    {
+      "epoch": 0.5216,
+      "grad_norm": 1.9277112483978271,
+      "learning_rate": 8.836830045206911e-05,
+      "loss": 2.9487,
+      "step": 326
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 1.793232798576355,
+      "learning_rate": 8.81980570181494e-05,
+      "loss": 2.8907,
+      "step": 328
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 1.8513329029083252,
+      "learning_rate": 8.802674330140192e-05,
+      "loss": 2.9645,
+      "step": 330
+    },
+    {
+      "epoch": 0.5312,
+      "grad_norm": 1.7978984117507935,
+      "learning_rate": 8.785436410191714e-05,
+      "loss": 2.9939,
+      "step": 332
+    },
+    {
+      "epoch": 0.5344,
+      "grad_norm": 1.7157683372497559,
+      "learning_rate": 8.76809242496396e-05,
+      "loss": 2.8079,
+      "step": 334
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 1.7450584173202515,
+      "learning_rate": 8.750642860423262e-05,
+      "loss": 2.9477,
+      "step": 336
+    },
+    {
+      "epoch": 0.5408,
+      "grad_norm": 1.812904715538025,
+      "learning_rate": 8.733088205494205e-05,
+      "loss": 2.9842,
+      "step": 338
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 1.878509759902954,
+      "learning_rate": 8.715428952045936e-05,
+      "loss": 2.8992,
+      "step": 340
+    },
+    {
+      "epoch": 0.5472,
+      "grad_norm": 1.8090356588363647,
+      "learning_rate": 8.697665594878382e-05,
+      "loss": 2.9507,
+      "step": 342
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 1.8601405620574951,
+      "learning_rate": 8.679798631708375e-05,
+      "loss": 2.8263,
+      "step": 344
+    },
+    {
+      "epoch": 0.5536,
+      "grad_norm": 1.8406038284301758,
+      "learning_rate": 8.661828563155727e-05,
+      "loss": 2.8991,
+      "step": 346
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 1.7687346935272217,
+      "learning_rate": 8.643755892729179e-05,
+      "loss": 2.8437,
+      "step": 348
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9318656921386719,
+      "learning_rate": 8.625581126812312e-05,
+      "loss": 3.0261,
+      "step": 350
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 1.8095970153808594,
+      "learning_rate": 8.607304774649349e-05,
+      "loss": 2.9269,
+      "step": 352
+    },
+    {
+      "epoch": 0.5664,
+      "grad_norm": 1.8424136638641357,
+      "learning_rate": 8.588927348330887e-05,
+      "loss": 2.7917,
+      "step": 354
+    },
+    {
+      "epoch": 0.5696,
+      "grad_norm": 1.9472522735595703,
+      "learning_rate": 8.57044936277955e-05,
+      "loss": 2.7557,
+      "step": 356
+    },
+    {
+      "epoch": 0.5728,
+      "grad_norm": 1.8774663209915161,
+      "learning_rate": 8.551871335735565e-05,
+      "loss": 2.8426,
+      "step": 358
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.0363616943359375,
+      "learning_rate": 8.533193787742251e-05,
+      "loss": 2.8605,
+      "step": 360
+    },
+    {
+      "epoch": 0.5792,
+      "grad_norm": 1.802148699760437,
+      "learning_rate": 8.51441724213143e-05,
+      "loss": 2.8999,
+      "step": 362
+    },
+    {
+      "epoch": 0.5824,
+      "grad_norm": 1.9002522230148315,
+      "learning_rate": 8.495542225008771e-05,
+      "loss": 2.854,
+      "step": 364
+    },
+    {
+      "epoch": 0.5856,
+      "grad_norm": 1.715409755706787,
+      "learning_rate": 8.476569265239046e-05,
+      "loss": 2.8574,
+      "step": 366
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 1.9336328506469727,
+      "learning_rate": 8.457498894431311e-05,
+      "loss": 2.7513,
+      "step": 368
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 1.8150614500045776,
+      "learning_rate": 8.438331646924013e-05,
+      "loss": 2.8648,
+      "step": 370
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 1.745450735092163,
+      "learning_rate": 8.419068059770011e-05,
+      "loss": 2.8102,
+      "step": 372
+    },
+    {
+      "epoch": 0.5984,
+      "grad_norm": 1.7649202346801758,
+      "learning_rate": 8.399708672721539e-05,
+      "loss": 2.943,
+      "step": 374
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 1.9029461145401,
+      "learning_rate": 8.380254028215076e-05,
+      "loss": 2.9549,
+      "step": 376
+    },
+    {
+      "epoch": 0.6048,
+      "grad_norm": 1.6569948196411133,
+      "learning_rate": 8.360704671356145e-05,
+      "loss": 2.762,
+      "step": 378
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 1.8082654476165771,
+      "learning_rate": 8.341061149904045e-05,
+      "loss": 2.8673,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112,
+      "grad_norm": 2.0130746364593506,
+      "learning_rate": 8.321324014256504e-05,
+      "loss": 2.8208,
+      "step": 382
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 1.9243208169937134,
+      "learning_rate": 8.30149381743425e-05,
+      "loss": 2.8175,
+      "step": 384
+    },
+    {
+      "epoch": 0.6176,
+      "grad_norm": 1.7602218389511108,
+      "learning_rate": 8.28157111506552e-05,
+      "loss": 2.8133,
+      "step": 386
+    },
+    {
+      "epoch": 0.6208,
+      "grad_norm": 1.9011287689208984,
+      "learning_rate": 8.261556465370493e-05,
+      "loss": 2.915,
+      "step": 388
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 1.8260935544967651,
+      "learning_rate": 8.24145042914565e-05,
+      "loss": 2.7879,
+      "step": 390
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 2.0104498863220215,
+      "learning_rate": 8.221253569748055e-05,
+      "loss": 2.9628,
+      "step": 392
+    },
+    {
+      "epoch": 0.6304,
+      "grad_norm": 1.821583867073059,
+      "learning_rate": 8.200966453079575e-05,
+      "loss": 2.8391,
+      "step": 394
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 1.8291980028152466,
+      "learning_rate": 8.180589647571023e-05,
+      "loss": 2.8921,
+      "step": 396
+    },
+    {
+      "epoch": 0.6368,
+      "grad_norm": 1.8733659982681274,
+      "learning_rate": 8.16012372416623e-05,
+      "loss": 2.8988,
+      "step": 398
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.9064126014709473,
+      "learning_rate": 8.13956925630605e-05,
+      "loss": 2.8047,
+      "step": 400
+    },
+    {
+      "epoch": 0.6432,
+      "grad_norm": 1.7694967985153198,
+      "learning_rate": 8.118926819912287e-05,
+      "loss": 2.8175,
+      "step": 402
+    },
+    {
+      "epoch": 0.6464,
+      "grad_norm": 1.9278019666671753,
+      "learning_rate": 8.098196993371565e-05,
+      "loss": 2.7233,
+      "step": 404
+    },
+    {
+      "epoch": 0.6496,
+      "grad_norm": 1.7496165037155151,
+      "learning_rate": 8.077380357519115e-05,
+      "loss": 2.8196,
+      "step": 406
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 1.8212895393371582,
+      "learning_rate": 8.056477495622511e-05,
+      "loss": 2.8749,
+      "step": 408
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 1.8443467617034912,
+      "learning_rate": 8.035488993365312e-05,
+      "loss": 2.8373,
+      "step": 410
+    },
+    {
+      "epoch": 0.6592,
+      "grad_norm": 1.804992437362671,
+      "learning_rate": 8.014415438830667e-05,
+      "loss": 2.8248,
+      "step": 412
+    },
+    {
+      "epoch": 0.6624,
+      "grad_norm": 1.7744520902633667,
+      "learning_rate": 7.993257422484826e-05,
+      "loss": 2.8403,
+      "step": 414
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 1.9854934215545654,
+      "learning_rate": 7.972015537160602e-05,
+      "loss": 2.9588,
+      "step": 416
+    },
+    {
+      "epoch": 0.6688,
+      "grad_norm": 1.7830610275268555,
+      "learning_rate": 7.950690378040758e-05,
+      "loss": 2.7737,
+      "step": 418
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 1.8114231824874878,
+      "learning_rate": 7.929282542641325e-05,
+      "loss": 2.7003,
+      "step": 420
+    },
+    {
+      "epoch": 0.6752,
+      "grad_norm": 1.931700348854065,
+      "learning_rate": 7.907792630794876e-05,
+      "loss": 2.8088,
+      "step": 422
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 1.8684518337249756,
+      "learning_rate": 7.886221244633703e-05,
+      "loss": 2.878,
+      "step": 424
+    },
+    {
+      "epoch": 0.6816,
+      "grad_norm": 1.8997987508773804,
+      "learning_rate": 7.864568988572947e-05,
+      "loss": 2.9374,
+      "step": 426
+    },
+    {
+      "epoch": 0.6848,
+      "grad_norm": 1.7682809829711914,
+      "learning_rate": 7.842836469293673e-05,
+      "loss": 2.7694,
+      "step": 428
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 1.8019146919250488,
+      "learning_rate": 7.821024295725865e-05,
+      "loss": 2.8153,
+      "step": 430
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 1.8119292259216309,
+      "learning_rate": 7.79913307903136e-05,
+      "loss": 2.8072,
+      "step": 432
+    },
+    {
+      "epoch": 0.6944,
+      "grad_norm": 1.8016608953475952,
+      "learning_rate": 7.777163432586734e-05,
+      "loss": 2.7276,
+      "step": 434
+    },
+    {
+      "epoch": 0.6976,
+      "grad_norm": 1.8160144090652466,
+      "learning_rate": 7.755115971966104e-05,
+      "loss": 2.8539,
+      "step": 436
+    },
+    {
+      "epoch": 0.7008,
+      "grad_norm": 1.825020670890808,
+      "learning_rate": 7.732991314923891e-05,
+      "loss": 2.7796,
+      "step": 438
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 1.7632222175598145,
+      "learning_rate": 7.710790081377502e-05,
+      "loss": 2.7914,
+      "step": 440
+    },
+    {
+      "epoch": 0.7072,
+      "grad_norm": 1.8498951196670532,
+      "learning_rate": 7.688512893389964e-05,
+      "loss": 2.6861,
+      "step": 442
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 2.0129451751708984,
+      "learning_rate": 7.666160375152496e-05,
+      "loss": 2.8217,
+      "step": 444
+    },
+    {
+      "epoch": 0.7136,
+      "grad_norm": 1.780062198638916,
+      "learning_rate": 7.643733152967019e-05,
+      "loss": 2.8554,
+      "step": 446
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 1.726577877998352,
+      "learning_rate": 7.621231855228604e-05,
+      "loss": 2.831,
+      "step": 448
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7651227712631226,
+      "learning_rate": 7.598657112407865e-05,
+      "loss": 2.8193,
+      "step": 450
+    },
+    {
+      "epoch": 0.7232,
+      "grad_norm": 1.7961740493774414,
+      "learning_rate": 7.576009557033304e-05,
+      "loss": 2.8149,
+      "step": 452
+    },
+    {
+      "epoch": 0.7264,
+      "grad_norm": 1.813366174697876,
+      "learning_rate": 7.553289823673568e-05,
+      "loss": 2.855,
+      "step": 454
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 1.8143000602722168,
+      "learning_rate": 7.530498548919693e-05,
+      "loss": 2.8651,
+      "step": 456
+    },
+    {
+      "epoch": 0.7328,
+      "grad_norm": 1.7585805654525757,
+      "learning_rate": 7.507636371367246e-05,
+      "loss": 3.0031,
+      "step": 458
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 2.2777135372161865,
+      "learning_rate": 7.484703931598445e-05,
+      "loss": 2.8548,
+      "step": 460
+    },
+    {
+      "epoch": 0.7392,
+      "grad_norm": 1.8288154602050781,
+      "learning_rate": 7.461701872164204e-05,
+      "loss": 2.7425,
+      "step": 462
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 1.8734841346740723,
+      "learning_rate": 7.438630837566133e-05,
+      "loss": 2.8703,
+      "step": 464
+    },
+    {
+      "epoch": 0.7456,
+      "grad_norm": 1.742242455482483,
+      "learning_rate": 7.415491474238475e-05,
+      "loss": 2.772,
+      "step": 466
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 1.7874287366867065,
+      "learning_rate": 7.39228443053e-05,
+      "loss": 2.7379,
+      "step": 468
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 1.8021794557571411,
+      "learning_rate": 7.369010356685833e-05,
+      "loss": 2.9262,
+      "step": 470
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 1.7524378299713135,
+      "learning_rate": 7.345669904829237e-05,
+      "loss": 2.6676,
+      "step": 472
+    },
+    {
+      "epoch": 0.7584,
+      "grad_norm": 1.8277724981307983,
+      "learning_rate": 7.32226372894334e-05,
+      "loss": 2.771,
+      "step": 474
+    },
+    {
+      "epoch": 0.7616,
+      "grad_norm": 1.7385722398757935,
+      "learning_rate": 7.298792484852808e-05,
+      "loss": 2.7508,
+      "step": 476
+    },
+    {
+      "epoch": 0.7648,
+      "grad_norm": 1.927331805229187,
+      "learning_rate": 7.27525683020548e-05,
+      "loss": 2.8279,
+      "step": 478
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.7165371179580688,
+      "learning_rate": 7.251657424453928e-05,
+      "loss": 2.6799,
+      "step": 480
+    },
+    {
+      "epoch": 0.7712,
+      "grad_norm": 1.6585590839385986,
+      "learning_rate": 7.227994928836988e-05,
+      "loss": 2.6849,
+      "step": 482
+    },
+    {
+      "epoch": 0.7744,
+      "grad_norm": 1.7066259384155273,
+      "learning_rate": 7.204270006361228e-05,
+      "loss": 2.7189,
+      "step": 484
+    },
+    {
+      "epoch": 0.7776,
+      "grad_norm": 1.8811277151107788,
+      "learning_rate": 7.180483321782374e-05,
+      "loss": 2.7771,
+      "step": 486
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 1.790667176246643,
+      "learning_rate": 7.156635541586682e-05,
+      "loss": 2.6777,
+      "step": 488
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 1.7074140310287476,
+      "learning_rate": 7.132727333972265e-05,
+      "loss": 2.7974,
+      "step": 490
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 1.6692975759506226,
+      "learning_rate": 7.108759368830371e-05,
+      "loss": 2.7194,
+      "step": 492
+    },
+    {
+      "epoch": 0.7904,
+      "grad_norm": 1.759386420249939,
+      "learning_rate": 7.084732317726611e-05,
+      "loss": 2.7475,
+      "step": 494
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 1.7140787839889526,
+      "learning_rate": 7.060646853882145e-05,
+      "loss": 2.7576,
+      "step": 496
+    },
+    {
+      "epoch": 0.7968,
+      "grad_norm": 1.6590884923934937,
+      "learning_rate": 7.036503652154812e-05,
+      "loss": 2.8157,
+      "step": 498
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.7052589654922485,
+      "learning_rate": 7.012303389020234e-05,
+      "loss": 2.7951,
+      "step": 500
+    },
+    {
+      "epoch": 0.8032,
+      "grad_norm": 1.730635166168213,
+      "learning_rate": 6.988046742552845e-05,
+      "loss": 2.8279,
+      "step": 502
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 1.7786180973052979,
+      "learning_rate": 6.963734392406907e-05,
+      "loss": 2.6559,
+      "step": 504
+    },
+    {
+      "epoch": 0.8096,
+      "grad_norm": 1.901053547859192,
+      "learning_rate": 6.93936701979746e-05,
+      "loss": 2.8896,
+      "step": 506
+    },
+    {
+      "epoch": 0.8128,
+      "grad_norm": 1.7321664094924927,
+      "learning_rate": 6.914945307481228e-05,
+      "loss": 2.795,
+      "step": 508
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 1.7901755571365356,
+      "learning_rate": 6.890469939737506e-05,
+      "loss": 2.7142,
+      "step": 510
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 1.7946327924728394,
+      "learning_rate": 6.865941602348966e-05,
+      "loss": 2.781,
+      "step": 512
+    },
+    {
+      "epoch": 0.8224,
+      "grad_norm": 1.8260494470596313,
+      "learning_rate": 6.841360982582463e-05,
+      "loss": 2.6868,
+      "step": 514
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 1.8089832067489624,
+      "learning_rate": 6.816728769169757e-05,
+      "loss": 2.7845,
+      "step": 516
+    },
+    {
+      "epoch": 0.8288,
+      "grad_norm": 1.711962342262268,
+      "learning_rate": 6.792045652288234e-05,
+      "loss": 2.7037,
+      "step": 518
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 1.7422336339950562,
+      "learning_rate": 6.767312323541555e-05,
+      "loss": 2.7938,
+      "step": 520
+    },
+    {
+      "epoch": 0.8352,
+      "grad_norm": 1.7964292764663696,
+      "learning_rate": 6.742529475940284e-05,
+      "loss": 2.6584,
+      "step": 522
+    },
+    {
+      "epoch": 0.8384,
+      "grad_norm": 1.7422146797180176,
+      "learning_rate": 6.717697803882467e-05,
+      "loss": 2.735,
+      "step": 524
+    },
+    {
+      "epoch": 0.8416,
+      "grad_norm": 1.7856199741363525,
+      "learning_rate": 6.692818003134184e-05,
+      "loss": 2.7753,
+      "step": 526
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 1.7519943714141846,
+      "learning_rate": 6.667890770810035e-05,
+      "loss": 2.7173,
+      "step": 528
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 1.705423355102539,
+      "learning_rate": 6.64291680535363e-05,
+      "loss": 2.7212,
+      "step": 530
+    },
+    {
+      "epoch": 0.8512,
+      "grad_norm": 1.787747859954834,
+      "learning_rate": 6.617896806518005e-05,
+      "loss": 2.7499,
+      "step": 532
+    },
+    {
+      "epoch": 0.8544,
+      "grad_norm": 1.652585744857788,
+      "learning_rate": 6.592831475346018e-05,
+      "loss": 2.5542,
+      "step": 534
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 1.8116321563720703,
+      "learning_rate": 6.56772151415071e-05,
+      "loss": 2.8155,
+      "step": 536
+    },
+    {
+      "epoch": 0.8608,
+      "grad_norm": 1.7901153564453125,
+      "learning_rate": 6.542567626495619e-05,
+      "loss": 2.7472,
+      "step": 538
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 1.7034342288970947,
+      "learning_rate": 6.517370517175081e-05,
+      "loss": 2.7116,
+      "step": 540
+    },
+    {
+      "epoch": 0.8672,
+      "grad_norm": 1.832322597503662,
+      "learning_rate": 6.492130892194461e-05,
+      "loss": 2.7618,
+      "step": 542
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 1.7125661373138428,
+      "learning_rate": 6.466849458750394e-05,
+      "loss": 2.6383,
+      "step": 544
+    },
+    {
+      "epoch": 0.8736,
+      "grad_norm": 1.801355004310608,
+      "learning_rate": 6.441526925210949e-05,
+      "loss": 2.5274,
+      "step": 546
+    },
+    {
+      "epoch": 0.8768,
+      "grad_norm": 1.7398046255111694,
+      "learning_rate": 6.416164001095799e-05,
+      "loss": 2.7207,
+      "step": 548
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.6901566982269287,
+      "learning_rate": 6.390761397056328e-05,
+      "loss": 2.7043,
+      "step": 550
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 1.6404509544372559,
+      "learning_rate": 6.365319824855727e-05,
+      "loss": 2.6003,
+      "step": 552
+    },
+    {
+      "epoch": 0.8864,
+      "grad_norm": 1.6571403741836548,
+      "learning_rate": 6.339839997349045e-05,
+      "loss": 2.7515,
+      "step": 554
+    },
+    {
+      "epoch": 0.8896,
+      "grad_norm": 1.64620041847229,
+      "learning_rate": 6.314322628463219e-05,
+      "loss": 2.619,
+      "step": 556
+    },
+    {
+      "epoch": 0.8928,
+      "grad_norm": 1.7471263408660889,
+      "learning_rate": 6.288768433177068e-05,
+      "loss": 2.6689,
+      "step": 558
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 1.7717193365097046,
+      "learning_rate": 6.26317812750126e-05,
+      "loss": 2.7607,
+      "step": 560
+    },
+    {
+      "epoch": 0.8992,
+      "grad_norm": 1.6764250993728638,
+      "learning_rate": 6.237552428458256e-05,
+      "loss": 2.6201,
+      "step": 562
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 1.6406267881393433,
+      "learning_rate": 6.21189205406221e-05,
+      "loss": 2.7044,
+      "step": 564
+    },
+    {
+      "epoch": 0.9056,
+      "grad_norm": 1.7228118181228638,
+      "learning_rate": 6.186197723298855e-05,
+      "loss": 2.8106,
+      "step": 566
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 1.6297177076339722,
+      "learning_rate": 6.160470156105362e-05,
+      "loss": 2.7442,
+      "step": 568
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 1.691156268119812,
+      "learning_rate": 6.134710073350156e-05,
+      "loss": 2.6915,
+      "step": 570
+    },
+    {
+      "epoch": 0.9152,
+      "grad_norm": 1.7338085174560547,
+      "learning_rate": 6.108918196812734e-05,
+      "loss": 2.6418,
+      "step": 572
+    },
+    {
+      "epoch": 0.9184,
+      "grad_norm": 1.7589360475540161,
+      "learning_rate": 6.083095249163424e-05,
+      "loss": 2.7577,
+      "step": 574
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 1.6277837753295898,
+      "learning_rate": 6.057241953943154e-05,
+      "loss": 2.6624,
+      "step": 576
+    },
+    {
+      "epoch": 0.9248,
+      "grad_norm": 1.7026268243789673,
+      "learning_rate": 6.031359035543158e-05,
+      "loss": 2.6401,
+      "step": 578
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 1.781171202659607,
+      "learning_rate": 6.005447219184702e-05,
+      "loss": 2.7218,
+      "step": 580
+    },
+    {
+      "epoch": 0.9312,
+      "grad_norm": 1.7018693685531616,
+      "learning_rate": 5.9795072308987485e-05,
+      "loss": 2.5756,
+      "step": 582
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 1.710750699043274,
+      "learning_rate": 5.9535397975056154e-05,
+      "loss": 2.738,
+      "step": 584
+    },
+    {
+      "epoch": 0.9376,
+      "grad_norm": 1.7480794191360474,
+      "learning_rate": 5.927545646594617e-05,
+      "loss": 2.5714,
+      "step": 586
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 1.7700692415237427,
+      "learning_rate": 5.901525506503668e-05,
+      "loss": 2.8079,
+      "step": 588
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 1.7823493480682373,
+      "learning_rate": 5.87548010629889e-05,
+      "loss": 2.6776,
+      "step": 590
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 1.6947530508041382,
+      "learning_rate": 5.8494101757541676e-05,
+      "loss": 2.6956,
+      "step": 592
+    },
+    {
+      "epoch": 0.9504,
+      "grad_norm": 3.6984357833862305,
+      "learning_rate": 5.8233164453307156e-05,
+      "loss": 2.7138,
+      "step": 594
+    },
+    {
+      "epoch": 0.9536,
+      "grad_norm": 1.7368056774139404,
+      "learning_rate": 5.797199646156596e-05,
+      "loss": 2.6646,
+      "step": 596
+    },
+    {
+      "epoch": 0.9568,
+      "grad_norm": 1.7944828271865845,
+      "learning_rate": 5.7710605100062485e-05,
+      "loss": 2.7675,
+      "step": 598
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6918281316757202,
+      "learning_rate": 5.7448997692799764e-05,
+      "loss": 2.5737,
+      "step": 600
+    },
+    {
+      "epoch": 0.9632,
+      "grad_norm": 1.6261357069015503,
+      "learning_rate": 5.718718156983428e-05,
+      "loss": 2.6307,
+      "step": 602
+    },
+    {
+      "epoch": 0.9664,
+      "grad_norm": 1.7582976818084717,
+      "learning_rate": 5.69251640670706e-05,
+      "loss": 2.6687,
+      "step": 604
+    },
+    {
+      "epoch": 0.9696,
+      "grad_norm": 1.6695537567138672,
+      "learning_rate": 5.6662952526055793e-05,
+      "loss": 2.5779,
+      "step": 606
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 1.7661280632019043,
+      "learning_rate": 5.6400554293773744e-05,
+      "loss": 2.7142,
+      "step": 608
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 1.8265255689620972,
+      "learning_rate": 5.61379767224393e-05,
+      "loss": 2.749,
+      "step": 610
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 1.6744146347045898,
+      "learning_rate": 5.587522716929228e-05,
+      "loss": 2.5499,
+      "step": 612
+    },
+    {
+      "epoch": 0.9824,
+      "grad_norm": 1.6788204908370972,
+      "learning_rate": 5.561231299639127e-05,
+      "loss": 2.7511,
+      "step": 614
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 1.8337587118148804,
+      "learning_rate": 5.534924157040745e-05,
+      "loss": 2.7018,
+      "step": 616
+    },
+    {
+      "epoch": 0.9888,
+      "grad_norm": 1.706388235092163,
+      "learning_rate": 5.508602026241807e-05,
+      "loss": 2.6037,
+      "step": 618
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 1.699271559715271,
+      "learning_rate": 5.482265644769998e-05,
+      "loss": 2.7222,
+      "step": 620
+    },
+    {
+      "epoch": 0.9952,
+      "grad_norm": 1.67972993850708,
+      "learning_rate": 5.4559157505522985e-05,
+      "loss": 2.4653,
+      "step": 622
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 1.6633968353271484,
+      "learning_rate": 5.429553081894304e-05,
+      "loss": 2.6239,
+      "step": 624
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 625,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0577401470989107e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-625/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897bf89d23736d5420c5afd648a553e7134f06192c6a200daea71920837be1e4
+size 5432

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-bjn_Latn-coli-cw2v/",
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100384
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.48.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcab17684cfa23bd2206a1d95cf55871fabb85b5affecebb57d26fc3dbe4e171
+size 4950070472

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0b6a357d03676c4986588aaf4dc96afc3f44a0498514961d2b2cfa1940655e
+size 4991622816

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1038a7d346a681a8fb6949e054c2246f3f3c80e826855c1cec6af1155cc607d
+size 4924546896

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c0a21146ace02d36928787ae7f34be868f7c81b894dea98ec7b0e5a3ea01b2
+size 4857404928

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f82a3014ccfc0f67208f63785ae4bc71f09aba86db48bf6139d18178abbfed
+size 4857404928

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6e00741b4ee61aa3308ec367b988e85cdea5d870c66fb4a866e27613e90079
+size 4614509080

model.safetensors.index.json

@@ -0,0 +1,362 @@
+{
+  "metadata": {
+    "total_size": 29195517952
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897bf89d23736d5420c5afd648a553e7134f06192c6a200daea71920837be1e4
+size 5432