Upload folder using huggingface_hub

checkpoint-1628/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-ban_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-1628/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-1628/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a4272ec4e7529ec7b13562a278f19fb9e358893f48f491738f36005fbbf5ac
+size 4950070472

checkpoint-1628/model-00002-of-00006.safetensors

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

checkpoint-1628/model-00003-of-00006.safetensors

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

checkpoint-1628/model-00004-of-00006.safetensors

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

checkpoint-1628/model-00005-of-00006.safetensors

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

checkpoint-1628/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c6952ea39686798f9d62bed9ff2d1d117c15ee79c0a1d99365be1d63f4cb3b
+size 4614509080

checkpoint-1628/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-1628/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689539b26bc0a0bfd83f0d427ad2060b440df56053c100fe2edf5a7e433ff131
+size 13055369358

checkpoint-1628/rng_state.pth

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

checkpoint-1628/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f21457119cda62dc413199c73f6ec25fe0b6ac52b8b47f01cad76f341ecf780
+size 1064

checkpoint-1628/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6928cbd68be40f1db7704fe9adf1988b07c0adf326e5ecd940c3f031a819851
+size 5432

checkpoint-814/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-ban_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-814/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-814/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944b42d8de984adeded3d22a584a1a6181c55984fc799b36131347ccbd56c89b
+size 4950070472

checkpoint-814/model-00002-of-00006.safetensors

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

checkpoint-814/model-00003-of-00006.safetensors

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

checkpoint-814/model-00004-of-00006.safetensors

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

checkpoint-814/model-00005-of-00006.safetensors

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

checkpoint-814/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e47d1f7647567282d6f5e44fe1711ff5c64059fe5cf2c66e0959fca056312
+size 4614509080

checkpoint-814/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-814/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd98daf1233103602795760af74874a9f0a03328064efe0a596e461ae595ba1d
+size 13055369358

checkpoint-814/rng_state.pth

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

checkpoint-814/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e00b16497a748b1876120c4263bf1a4eb69cba3ea237d87805fb3a6055ccf3
+size 1064

checkpoint-814/trainer_state.json

@@ -0,0 +1,2882 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002457002457002457,
+      "grad_norm": 4.916572570800781,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 5.9819,
+      "step": 2
+    },
+    {
+      "epoch": 0.004914004914004914,
+      "grad_norm": 4.77026891708374,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 5.953,
+      "step": 4
+    },
+    {
+      "epoch": 0.007371007371007371,
+      "grad_norm": 5.246749401092529,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 5.9223,
+      "step": 6
+    },
+    {
+      "epoch": 0.009828009828009828,
+      "grad_norm": 5.039796829223633,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 5.5883,
+      "step": 8
+    },
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 6.014425277709961,
+      "learning_rate": 1.2195121951219513e-05,
+      "loss": 5.539,
+      "step": 10
+    },
+    {
+      "epoch": 0.014742014742014743,
+      "grad_norm": 10.090555191040039,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 5.2428,
+      "step": 12
+    },
+    {
+      "epoch": 0.0171990171990172,
+      "grad_norm": 6.888723850250244,
+      "learning_rate": 1.707317073170732e-05,
+      "loss": 5.239,
+      "step": 14
+    },
+    {
+      "epoch": 0.019656019656019656,
+      "grad_norm": 4.933538436889648,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 4.8712,
+      "step": 16
+    },
+    {
+      "epoch": 0.022113022113022112,
+      "grad_norm": 2.7991392612457275,
+      "learning_rate": 2.1951219512195124e-05,
+      "loss": 4.4757,
+      "step": 18
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 4.74180793762207,
+      "learning_rate": 2.4390243902439026e-05,
+      "loss": 4.8469,
+      "step": 20
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 4.044187068939209,
+      "learning_rate": 2.682926829268293e-05,
+      "loss": 5.049,
+      "step": 22
+    },
+    {
+      "epoch": 0.029484029484029485,
+      "grad_norm": 2.664706230163574,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 4.6624,
+      "step": 24
+    },
+    {
+      "epoch": 0.03194103194103194,
+      "grad_norm": 3.159350633621216,
+      "learning_rate": 3.170731707317073e-05,
+      "loss": 4.7993,
+      "step": 26
+    },
+    {
+      "epoch": 0.0343980343980344,
+      "grad_norm": 2.5463948249816895,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 4.4235,
+      "step": 28
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 4.2436113357543945,
+      "learning_rate": 3.6585365853658535e-05,
+      "loss": 4.4116,
+      "step": 30
+    },
+    {
+      "epoch": 0.03931203931203931,
+      "grad_norm": 2.924164295196533,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 4.2755,
+      "step": 32
+    },
+    {
+      "epoch": 0.04176904176904177,
+      "grad_norm": 2.3113248348236084,
+      "learning_rate": 4.146341463414634e-05,
+      "loss": 4.3122,
+      "step": 34
+    },
+    {
+      "epoch": 0.044226044226044224,
+      "grad_norm": 2.386974573135376,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 4.3088,
+      "step": 36
+    },
+    {
+      "epoch": 0.04668304668304668,
+      "grad_norm": 2.69736385345459,
+      "learning_rate": 4.634146341463415e-05,
+      "loss": 4.0982,
+      "step": 38
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 3.7191948890686035,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 4.1512,
+      "step": 40
+    },
+    {
+      "epoch": 0.051597051597051594,
+      "grad_norm": 2.4278435707092285,
+      "learning_rate": 5.121951219512195e-05,
+      "loss": 4.2134,
+      "step": 42
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 3.0863969326019287,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 4.2307,
+      "step": 44
+    },
+    {
+      "epoch": 0.056511056511056514,
+      "grad_norm": 3.4245433807373047,
+      "learning_rate": 5.6097560975609764e-05,
+      "loss": 4.0733,
+      "step": 46
+    },
+    {
+      "epoch": 0.05896805896805897,
+      "grad_norm": 3.0049750804901123,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 4.0946,
+      "step": 48
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 3.220999240875244,
+      "learning_rate": 6.097560975609756e-05,
+      "loss": 4.1286,
+      "step": 50
+    },
+    {
+      "epoch": 0.06388206388206388,
+      "grad_norm": 2.5109856128692627,
+      "learning_rate": 6.341463414634146e-05,
+      "loss": 3.997,
+      "step": 52
+    },
+    {
+      "epoch": 0.06633906633906633,
+      "grad_norm": 2.430593252182007,
+      "learning_rate": 6.585365853658538e-05,
+      "loss": 4.0292,
+      "step": 54
+    },
+    {
+      "epoch": 0.0687960687960688,
+      "grad_norm": 2.1860780715942383,
+      "learning_rate": 6.829268292682928e-05,
+      "loss": 3.8444,
+      "step": 56
+    },
+    {
+      "epoch": 0.07125307125307126,
+      "grad_norm": 2.2836203575134277,
+      "learning_rate": 7.073170731707317e-05,
+      "loss": 3.7986,
+      "step": 58
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 2.4450736045837402,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 3.9541,
+      "step": 60
+    },
+    {
+      "epoch": 0.07616707616707617,
+      "grad_norm": 2.628493309020996,
+      "learning_rate": 7.560975609756099e-05,
+      "loss": 3.8559,
+      "step": 62
+    },
+    {
+      "epoch": 0.07862407862407862,
+      "grad_norm": 2.1850173473358154,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 3.8247,
+      "step": 64
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 2.2945919036865234,
+      "learning_rate": 8.048780487804879e-05,
+      "loss": 3.915,
+      "step": 66
+    },
+    {
+      "epoch": 0.08353808353808354,
+      "grad_norm": 2.381680727005005,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 3.7283,
+      "step": 68
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 2.36006498336792,
+      "learning_rate": 8.53658536585366e-05,
+      "loss": 3.6579,
+      "step": 70
+    },
+    {
+      "epoch": 0.08845208845208845,
+      "grad_norm": 3.086056709289551,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 3.7464,
+      "step": 72
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 3.201338529586792,
+      "learning_rate": 9.02439024390244e-05,
+      "loss": 3.8884,
+      "step": 74
+    },
+    {
+      "epoch": 0.09336609336609336,
+      "grad_norm": 2.7978038787841797,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 3.5131,
+      "step": 76
+    },
+    {
+      "epoch": 0.09582309582309582,
+      "grad_norm": 3.1305155754089355,
+      "learning_rate": 9.51219512195122e-05,
+      "loss": 3.6623,
+      "step": 78
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 2.570423126220703,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 3.7053,
+      "step": 80
+    },
+    {
+      "epoch": 0.10073710073710074,
+      "grad_norm": 2.9331843852996826,
+      "learning_rate": 0.0001,
+      "loss": 3.7604,
+      "step": 82
+    },
+    {
+      "epoch": 0.10319410319410319,
+      "grad_norm": 2.7446630001068115,
+      "learning_rate": 9.999958706645134e-05,
+      "loss": 3.5296,
+      "step": 84
+    },
+    {
+      "epoch": 0.10565110565110565,
+      "grad_norm": 3.145533323287964,
+      "learning_rate": 9.999834827262588e-05,
+      "loss": 3.6484,
+      "step": 86
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 2.7964529991149902,
+      "learning_rate": 9.999628363898526e-05,
+      "loss": 3.6839,
+      "step": 88
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 2.17167067527771,
+      "learning_rate": 9.999339319963168e-05,
+      "loss": 3.6529,
+      "step": 90
+    },
+    {
+      "epoch": 0.11302211302211303,
+      "grad_norm": 2.126905679702759,
+      "learning_rate": 9.998967700230757e-05,
+      "loss": 3.7187,
+      "step": 92
+    },
+    {
+      "epoch": 0.11547911547911548,
+      "grad_norm": 2.5139994621276855,
+      "learning_rate": 9.998513510839458e-05,
+      "loss": 3.6367,
+      "step": 94
+    },
+    {
+      "epoch": 0.11793611793611794,
+      "grad_norm": 2.635418653488159,
+      "learning_rate": 9.997976759291276e-05,
+      "loss": 3.5057,
+      "step": 96
+    },
+    {
+      "epoch": 0.12039312039312039,
+      "grad_norm": 2.3161840438842773,
+      "learning_rate": 9.997357454451919e-05,
+      "loss": 3.5836,
+      "step": 98
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 2.4925875663757324,
+      "learning_rate": 9.996655606550656e-05,
+      "loss": 3.559,
+      "step": 100
+    },
+    {
+      "epoch": 0.12530712530712532,
+      "grad_norm": 2.4260857105255127,
+      "learning_rate": 9.99587122718015e-05,
+      "loss": 3.6824,
+      "step": 102
+    },
+    {
+      "epoch": 0.12776412776412777,
+      "grad_norm": 4.071969509124756,
+      "learning_rate": 9.995004329296263e-05,
+      "loss": 3.8088,
+      "step": 104
+    },
+    {
+      "epoch": 0.13022113022113022,
+      "grad_norm": 2.3777356147766113,
+      "learning_rate": 9.994054927217842e-05,
+      "loss": 3.6324,
+      "step": 106
+    },
+    {
+      "epoch": 0.13267813267813267,
+      "grad_norm": 2.1969950199127197,
+      "learning_rate": 9.993023036626488e-05,
+      "loss": 3.5438,
+      "step": 108
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 2.2005531787872314,
+      "learning_rate": 9.99190867456629e-05,
+      "loss": 3.5784,
+      "step": 110
+    },
+    {
+      "epoch": 0.1375921375921376,
+      "grad_norm": 2.205366611480713,
+      "learning_rate": 9.990711859443546e-05,
+      "loss": 3.4397,
+      "step": 112
+    },
+    {
+      "epoch": 0.14004914004914004,
+      "grad_norm": 2.119697332382202,
+      "learning_rate": 9.989432611026464e-05,
+      "loss": 3.2832,
+      "step": 114
+    },
+    {
+      "epoch": 0.14250614250614252,
+      "grad_norm": 2.2541282176971436,
+      "learning_rate": 9.988070950444823e-05,
+      "loss": 3.4448,
+      "step": 116
+    },
+    {
+      "epoch": 0.14496314496314497,
+      "grad_norm": 2.172215461730957,
+      "learning_rate": 9.986626900189641e-05,
+      "loss": 3.4868,
+      "step": 118
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 2.158733606338501,
+      "learning_rate": 9.985100484112785e-05,
+      "loss": 3.4516,
+      "step": 120
+    },
+    {
+      "epoch": 0.14987714987714987,
+      "grad_norm": 2.2100753784179688,
+      "learning_rate": 9.983491727426598e-05,
+      "loss": 3.4269,
+      "step": 122
+    },
+    {
+      "epoch": 0.15233415233415235,
+      "grad_norm": 2.00675106048584,
+      "learning_rate": 9.981800656703457e-05,
+      "loss": 3.5985,
+      "step": 124
+    },
+    {
+      "epoch": 0.1547911547911548,
+      "grad_norm": 2.1808011531829834,
+      "learning_rate": 9.980027299875358e-05,
+      "loss": 3.4741,
+      "step": 126
+    },
+    {
+      "epoch": 0.15724815724815724,
+      "grad_norm": 2.197129011154175,
+      "learning_rate": 9.978171686233445e-05,
+      "loss": 3.3629,
+      "step": 128
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 2.001347780227661,
+      "learning_rate": 9.97623384642752e-05,
+      "loss": 3.4066,
+      "step": 130
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 2.0654983520507812,
+      "learning_rate": 9.974213812465547e-05,
+      "loss": 3.473,
+      "step": 132
+    },
+    {
+      "epoch": 0.16461916461916462,
+      "grad_norm": 2.565753698348999,
+      "learning_rate": 9.972111617713116e-05,
+      "loss": 3.3103,
+      "step": 134
+    },
+    {
+      "epoch": 0.16707616707616707,
+      "grad_norm": 2.33060884475708,
+      "learning_rate": 9.969927296892898e-05,
+      "loss": 3.4601,
+      "step": 136
+    },
+    {
+      "epoch": 0.16953316953316952,
+      "grad_norm": 2.2303621768951416,
+      "learning_rate": 9.967660886084066e-05,
+      "loss": 3.3306,
+      "step": 138
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 2.0361993312835693,
+      "learning_rate": 9.965312422721704e-05,
+      "loss": 3.2357,
+      "step": 140
+    },
+    {
+      "epoch": 0.17444717444717445,
+      "grad_norm": 2.2737162113189697,
+      "learning_rate": 9.962881945596184e-05,
+      "loss": 3.3979,
+      "step": 142
+    },
+    {
+      "epoch": 0.1769041769041769,
+      "grad_norm": 1.971992015838623,
+      "learning_rate": 9.960369494852525e-05,
+      "loss": 3.1709,
+      "step": 144
+    },
+    {
+      "epoch": 0.17936117936117937,
+      "grad_norm": 2.1188580989837646,
+      "learning_rate": 9.95777511198974e-05,
+      "loss": 3.2497,
+      "step": 146
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.1659576892852783,
+      "learning_rate": 9.955098839860133e-05,
+      "loss": 3.4369,
+      "step": 148
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 2.2103657722473145,
+      "learning_rate": 9.952340722668609e-05,
+      "loss": 3.2721,
+      "step": 150
+    },
+    {
+      "epoch": 0.18673218673218672,
+      "grad_norm": 2.0780789852142334,
+      "learning_rate": 9.949500805971932e-05,
+      "loss": 3.3651,
+      "step": 152
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 2.086878538131714,
+      "learning_rate": 9.946579136677978e-05,
+      "loss": 3.3741,
+      "step": 154
+    },
+    {
+      "epoch": 0.19164619164619165,
+      "grad_norm": 2.0054385662078857,
+      "learning_rate": 9.943575763044955e-05,
+      "loss": 3.1859,
+      "step": 156
+    },
+    {
+      "epoch": 0.1941031941031941,
+      "grad_norm": 2.0755085945129395,
+      "learning_rate": 9.940490734680614e-05,
+      "loss": 3.2251,
+      "step": 158
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 3.059140920639038,
+      "learning_rate": 9.937324102541423e-05,
+      "loss": 3.2752,
+      "step": 160
+    },
+    {
+      "epoch": 0.19901719901719903,
+      "grad_norm": 2.0540404319763184,
+      "learning_rate": 9.93407591893173e-05,
+      "loss": 3.3965,
+      "step": 162
+    },
+    {
+      "epoch": 0.20147420147420148,
+      "grad_norm": 2.07104754447937,
+      "learning_rate": 9.930746237502892e-05,
+      "loss": 3.2951,
+      "step": 164
+    },
+    {
+      "epoch": 0.20393120393120392,
+      "grad_norm": 2.12972354888916,
+      "learning_rate": 9.927335113252396e-05,
+      "loss": 3.4232,
+      "step": 166
+    },
+    {
+      "epoch": 0.20638820638820637,
+      "grad_norm": 2.369746685028076,
+      "learning_rate": 9.923842602522949e-05,
+      "loss": 3.2721,
+      "step": 168
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 2.08709454536438,
+      "learning_rate": 9.920268763001542e-05,
+      "loss": 3.2015,
+      "step": 170
+    },
+    {
+      "epoch": 0.2113022113022113,
+      "grad_norm": 2.0221400260925293,
+      "learning_rate": 9.916613653718509e-05,
+      "loss": 3.3356,
+      "step": 172
+    },
+    {
+      "epoch": 0.21375921375921375,
+      "grad_norm": 2.353618860244751,
+      "learning_rate": 9.912877335046535e-05,
+      "loss": 3.2471,
+      "step": 174
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 3.3538386821746826,
+      "learning_rate": 9.909059868699678e-05,
+      "loss": 3.1677,
+      "step": 176
+    },
+    {
+      "epoch": 0.21867321867321868,
+      "grad_norm": 2.3216552734375,
+      "learning_rate": 9.905161317732331e-05,
+      "loss": 3.2548,
+      "step": 178
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 2.058231830596924,
+      "learning_rate": 9.901181746538196e-05,
+      "loss": 3.1647,
+      "step": 180
+    },
+    {
+      "epoch": 0.22358722358722358,
+      "grad_norm": 2.3197808265686035,
+      "learning_rate": 9.897121220849208e-05,
+      "loss": 3.1369,
+      "step": 182
+    },
+    {
+      "epoch": 0.22604422604422605,
+      "grad_norm": 2.5758109092712402,
+      "learning_rate": 9.892979807734462e-05,
+      "loss": 3.206,
+      "step": 184
+    },
+    {
+      "epoch": 0.2285012285012285,
+      "grad_norm": 2.34597110748291,
+      "learning_rate": 9.888757575599093e-05,
+      "loss": 3.2325,
+      "step": 186
+    },
+    {
+      "epoch": 0.23095823095823095,
+      "grad_norm": 2.0011579990386963,
+      "learning_rate": 9.884454594183154e-05,
+      "loss": 3.2801,
+      "step": 188
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 2.094426155090332,
+      "learning_rate": 9.880070934560458e-05,
+      "loss": 3.207,
+      "step": 190
+    },
+    {
+      "epoch": 0.23587223587223588,
+      "grad_norm": 2.8441734313964844,
+      "learning_rate": 9.875606669137412e-05,
+      "loss": 3.2559,
+      "step": 192
+    },
+    {
+      "epoch": 0.23832923832923833,
+      "grad_norm": 2.490898370742798,
+      "learning_rate": 9.871061871651815e-05,
+      "loss": 2.9974,
+      "step": 194
+    },
+    {
+      "epoch": 0.24078624078624078,
+      "grad_norm": 2.0442817211151123,
+      "learning_rate": 9.866436617171638e-05,
+      "loss": 3.357,
+      "step": 196
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 2.0015676021575928,
+      "learning_rate": 9.861730982093793e-05,
+      "loss": 3.2276,
+      "step": 198
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 2.024724245071411,
+      "learning_rate": 9.856945044142865e-05,
+      "loss": 3.2181,
+      "step": 200
+    },
+    {
+      "epoch": 0.24815724815724816,
+      "grad_norm": 2.0588181018829346,
+      "learning_rate": 9.852078882369827e-05,
+      "loss": 3.1506,
+      "step": 202
+    },
+    {
+      "epoch": 0.25061425061425063,
+      "grad_norm": 2.1806745529174805,
+      "learning_rate": 9.847132577150733e-05,
+      "loss": 3.1492,
+      "step": 204
+    },
+    {
+      "epoch": 0.25307125307125306,
+      "grad_norm": 2.226822853088379,
+      "learning_rate": 9.842106210185403e-05,
+      "loss": 3.1743,
+      "step": 206
+    },
+    {
+      "epoch": 0.25552825552825553,
+      "grad_norm": 2.317154884338379,
+      "learning_rate": 9.836999864496057e-05,
+      "loss": 3.0891,
+      "step": 208
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 2.1667487621307373,
+      "learning_rate": 9.831813624425952e-05,
+      "loss": 3.1981,
+      "step": 210
+    },
+    {
+      "epoch": 0.26044226044226043,
+      "grad_norm": 1.8015401363372803,
+      "learning_rate": 9.82654757563799e-05,
+      "loss": 2.9991,
+      "step": 212
+    },
+    {
+      "epoch": 0.2628992628992629,
+      "grad_norm": 2.3263139724731445,
+      "learning_rate": 9.821201805113298e-05,
+      "loss": 3.0811,
+      "step": 214
+    },
+    {
+      "epoch": 0.26535626535626533,
+      "grad_norm": 2.251429796218872,
+      "learning_rate": 9.815776401149796e-05,
+      "loss": 3.222,
+      "step": 216
+    },
+    {
+      "epoch": 0.2678132678132678,
+      "grad_norm": 2.134190320968628,
+      "learning_rate": 9.810271453360738e-05,
+      "loss": 3.0341,
+      "step": 218
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.9004825353622437,
+      "learning_rate": 9.804687052673229e-05,
+      "loss": 3.0711,
+      "step": 220
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 2.2338693141937256,
+      "learning_rate": 9.799023291326722e-05,
+      "loss": 3.1774,
+      "step": 222
+    },
+    {
+      "epoch": 0.2751842751842752,
+      "grad_norm": 2.2935733795166016,
+      "learning_rate": 9.793280262871502e-05,
+      "loss": 3.1498,
+      "step": 224
+    },
+    {
+      "epoch": 0.27764127764127766,
+      "grad_norm": 2.144819736480713,
+      "learning_rate": 9.787458062167134e-05,
+      "loss": 3.0688,
+      "step": 226
+    },
+    {
+      "epoch": 0.2800982800982801,
+      "grad_norm": 1.9869056940078735,
+      "learning_rate": 9.781556785380899e-05,
+      "loss": 3.3,
+      "step": 228
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 1.8830708265304565,
+      "learning_rate": 9.775576529986199e-05,
+      "loss": 3.3633,
+      "step": 230
+    },
+    {
+      "epoch": 0.28501228501228504,
+      "grad_norm": 2.0476791858673096,
+      "learning_rate": 9.769517394760962e-05,
+      "loss": 3.0215,
+      "step": 232
+    },
+    {
+      "epoch": 0.28746928746928746,
+      "grad_norm": 2.008009433746338,
+      "learning_rate": 9.763379479785995e-05,
+      "loss": 3.1849,
+      "step": 234
+    },
+    {
+      "epoch": 0.28992628992628994,
+      "grad_norm": 2.0959136486053467,
+      "learning_rate": 9.757162886443336e-05,
+      "loss": 3.1097,
+      "step": 236
+    },
+    {
+      "epoch": 0.29238329238329236,
+      "grad_norm": 1.8712128400802612,
+      "learning_rate": 9.750867717414586e-05,
+      "loss": 3.1607,
+      "step": 238
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 1.8421741724014282,
+      "learning_rate": 9.744494076679205e-05,
+      "loss": 3.1217,
+      "step": 240
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 1.9873462915420532,
+      "learning_rate": 9.738042069512795e-05,
+      "loss": 3.2857,
+      "step": 242
+    },
+    {
+      "epoch": 0.29975429975429974,
+      "grad_norm": 1.790082573890686,
+      "learning_rate": 9.731511802485364e-05,
+      "loss": 3.0234,
+      "step": 244
+    },
+    {
+      "epoch": 0.3022113022113022,
+      "grad_norm": 1.915837049484253,
+      "learning_rate": 9.724903383459566e-05,
+      "loss": 3.1364,
+      "step": 246
+    },
+    {
+      "epoch": 0.3046683046683047,
+      "grad_norm": 2.401880979537964,
+      "learning_rate": 9.718216921588919e-05,
+      "loss": 2.975,
+      "step": 248
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 2.079129695892334,
+      "learning_rate": 9.711452527315998e-05,
+      "loss": 3.2686,
+      "step": 250
+    },
+    {
+      "epoch": 0.3095823095823096,
+      "grad_norm": 1.9599655866622925,
+      "learning_rate": 9.704610312370617e-05,
+      "loss": 3.0804,
+      "step": 252
+    },
+    {
+      "epoch": 0.31203931203931207,
+      "grad_norm": 2.091503858566284,
+      "learning_rate": 9.697690389767981e-05,
+      "loss": 3.1895,
+      "step": 254
+    },
+    {
+      "epoch": 0.3144963144963145,
+      "grad_norm": 2.054234743118286,
+      "learning_rate": 9.690692873806816e-05,
+      "loss": 3.2141,
+      "step": 256
+    },
+    {
+      "epoch": 0.31695331695331697,
+      "grad_norm": 2.081094264984131,
+      "learning_rate": 9.683617880067489e-05,
+      "loss": 3.2369,
+      "step": 258
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 2.1534552574157715,
+      "learning_rate": 9.676465525410088e-05,
+      "loss": 3.1827,
+      "step": 260
+    },
+    {
+      "epoch": 0.32186732186732187,
+      "grad_norm": 1.9752203226089478,
+      "learning_rate": 9.669235927972502e-05,
+      "loss": 3.2592,
+      "step": 262
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 1.8343819379806519,
+      "learning_rate": 9.661929207168463e-05,
+      "loss": 2.9579,
+      "step": 264
+    },
+    {
+      "epoch": 0.32678132678132676,
+      "grad_norm": 2.117063283920288,
+      "learning_rate": 9.654545483685578e-05,
+      "loss": 2.9743,
+      "step": 266
+    },
+    {
+      "epoch": 0.32923832923832924,
+      "grad_norm": 1.9216965436935425,
+      "learning_rate": 9.647084879483332e-05,
+      "loss": 3.1944,
+      "step": 268
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 2.0310311317443848,
+      "learning_rate": 9.639547517791076e-05,
+      "loss": 3.088,
+      "step": 270
+    },
+    {
+      "epoch": 0.33415233415233414,
+      "grad_norm": 2.0127720832824707,
+      "learning_rate": 9.631933523105991e-05,
+      "loss": 3.0136,
+      "step": 272
+    },
+    {
+      "epoch": 0.3366093366093366,
+      "grad_norm": 1.8773679733276367,
+      "learning_rate": 9.624243021191029e-05,
+      "loss": 3.0069,
+      "step": 274
+    },
+    {
+      "epoch": 0.33906633906633904,
+      "grad_norm": 2.039201259613037,
+      "learning_rate": 9.61647613907284e-05,
+      "loss": 3.107,
+      "step": 276
+    },
+    {
+      "epoch": 0.3415233415233415,
+      "grad_norm": 2.52468204498291,
+      "learning_rate": 9.608633005039675e-05,
+      "loss": 3.1008,
+      "step": 278
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 1.853696346282959,
+      "learning_rate": 9.600713748639258e-05,
+      "loss": 3.1372,
+      "step": 280
+    },
+    {
+      "epoch": 0.3464373464373464,
+      "grad_norm": 2.019024133682251,
+      "learning_rate": 9.592718500676656e-05,
+      "loss": 3.0446,
+      "step": 282
+    },
+    {
+      "epoch": 0.3488943488943489,
+      "grad_norm": 2.2153067588806152,
+      "learning_rate": 9.584647393212113e-05,
+      "loss": 3.0135,
+      "step": 284
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 1.997916579246521,
+      "learning_rate": 9.576500559558869e-05,
+      "loss": 3.0678,
+      "step": 286
+    },
+    {
+      "epoch": 0.3538083538083538,
+      "grad_norm": 1.8070591688156128,
+      "learning_rate": 9.568278134280966e-05,
+      "loss": 2.9913,
+      "step": 288
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 1.8850058317184448,
+      "learning_rate": 9.55998025319101e-05,
+      "loss": 3.0786,
+      "step": 290
+    },
+    {
+      "epoch": 0.35872235872235875,
+      "grad_norm": 1.8264799118041992,
+      "learning_rate": 9.551607053347942e-05,
+      "loss": 3.1469,
+      "step": 292
+    },
+    {
+      "epoch": 0.36117936117936117,
+      "grad_norm": 1.955801010131836,
+      "learning_rate": 9.543158673054767e-05,
+      "loss": 2.9848,
+      "step": 294
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.8326199054718018,
+      "learning_rate": 9.534635251856267e-05,
+      "loss": 2.7434,
+      "step": 296
+    },
+    {
+      "epoch": 0.36609336609336607,
+      "grad_norm": 1.8823051452636719,
+      "learning_rate": 9.526036930536712e-05,
+      "loss": 2.9899,
+      "step": 298
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 1.818613886833191,
+      "learning_rate": 9.517363851117512e-05,
+      "loss": 3.0477,
+      "step": 300
+    },
+    {
+      "epoch": 0.371007371007371,
+      "grad_norm": 1.9045586585998535,
+      "learning_rate": 9.508616156854883e-05,
+      "loss": 3.1337,
+      "step": 302
+    },
+    {
+      "epoch": 0.37346437346437344,
+      "grad_norm": 2.1247949600219727,
+      "learning_rate": 9.499793992237485e-05,
+      "loss": 2.8107,
+      "step": 304
+    },
+    {
+      "epoch": 0.3759213759213759,
+      "grad_norm": 1.9648290872573853,
+      "learning_rate": 9.490897502984028e-05,
+      "loss": 2.9724,
+      "step": 306
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 2.0654420852661133,
+      "learning_rate": 9.481926836040866e-05,
+      "loss": 2.9909,
+      "step": 308
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 1.8634198904037476,
+      "learning_rate": 9.472882139579572e-05,
+      "loss": 3.1364,
+      "step": 310
+    },
+    {
+      "epoch": 0.3832923832923833,
+      "grad_norm": 1.93793785572052,
+      "learning_rate": 9.463763562994491e-05,
+      "loss": 3.0364,
+      "step": 312
+    },
+    {
+      "epoch": 0.3857493857493858,
+      "grad_norm": 2.107790231704712,
+      "learning_rate": 9.454571256900272e-05,
+      "loss": 2.904,
+      "step": 314
+    },
+    {
+      "epoch": 0.3882063882063882,
+      "grad_norm": 1.9009639024734497,
+      "learning_rate": 9.445305373129375e-05,
+      "loss": 2.975,
+      "step": 316
+    },
+    {
+      "epoch": 0.3906633906633907,
+      "grad_norm": 2.067288875579834,
+      "learning_rate": 9.435966064729574e-05,
+      "loss": 3.2711,
+      "step": 318
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 2.018033981323242,
+      "learning_rate": 9.426553485961415e-05,
+      "loss": 3.1024,
+      "step": 320
+    },
+    {
+      "epoch": 0.3955773955773956,
+      "grad_norm": 1.9113644361495972,
+      "learning_rate": 9.417067792295684e-05,
+      "loss": 2.9457,
+      "step": 322
+    },
+    {
+      "epoch": 0.39803439803439805,
+      "grad_norm": 1.9023360013961792,
+      "learning_rate": 9.407509140410826e-05,
+      "loss": 2.9794,
+      "step": 324
+    },
+    {
+      "epoch": 0.4004914004914005,
+      "grad_norm": 1.987796425819397,
+      "learning_rate": 9.397877688190362e-05,
+      "loss": 2.8287,
+      "step": 326
+    },
+    {
+      "epoch": 0.40294840294840295,
+      "grad_norm": 1.9867451190948486,
+      "learning_rate": 9.388173594720281e-05,
+      "loss": 2.9206,
+      "step": 328
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 2.01375150680542,
+      "learning_rate": 9.378397020286417e-05,
+      "loss": 3.0713,
+      "step": 330
+    },
+    {
+      "epoch": 0.40786240786240785,
+      "grad_norm": 1.8884034156799316,
+      "learning_rate": 9.368548126371788e-05,
+      "loss": 3.0123,
+      "step": 332
+    },
+    {
+      "epoch": 0.4103194103194103,
+      "grad_norm": 1.8966444730758667,
+      "learning_rate": 9.358627075653946e-05,
+      "loss": 2.9806,
+      "step": 334
+    },
+    {
+      "epoch": 0.41277641277641275,
+      "grad_norm": 2.0271332263946533,
+      "learning_rate": 9.348634032002277e-05,
+      "loss": 3.0556,
+      "step": 336
+    },
+    {
+      "epoch": 0.4152334152334152,
+      "grad_norm": 2.061434507369995,
+      "learning_rate": 9.338569160475299e-05,
+      "loss": 2.8075,
+      "step": 338
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 1.9971458911895752,
+      "learning_rate": 9.328432627317938e-05,
+      "loss": 2.9535,
+      "step": 340
+    },
+    {
+      "epoch": 0.4201474201474201,
+      "grad_norm": 1.8785593509674072,
+      "learning_rate": 9.318224599958778e-05,
+      "loss": 2.9911,
+      "step": 342
+    },
+    {
+      "epoch": 0.4226044226044226,
+      "grad_norm": 1.8607487678527832,
+      "learning_rate": 9.307945247007299e-05,
+      "loss": 3.0419,
+      "step": 344
+    },
+    {
+      "epoch": 0.4250614250614251,
+      "grad_norm": 1.9788838624954224,
+      "learning_rate": 9.297594738251086e-05,
+      "loss": 3.0239,
+      "step": 346
+    },
+    {
+      "epoch": 0.4275184275184275,
+      "grad_norm": 1.7801693677902222,
+      "learning_rate": 9.287173244653032e-05,
+      "loss": 2.9975,
+      "step": 348
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 2.19821834564209,
+      "learning_rate": 9.276680938348512e-05,
+      "loss": 2.9937,
+      "step": 350
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.122514247894287,
+      "learning_rate": 9.266117992642536e-05,
+      "loss": 3.0017,
+      "step": 352
+    },
+    {
+      "epoch": 0.4348894348894349,
+      "grad_norm": 1.9420276880264282,
+      "learning_rate": 9.25548458200689e-05,
+      "loss": 2.9522,
+      "step": 354
+    },
+    {
+      "epoch": 0.43734643734643736,
+      "grad_norm": 2.0469229221343994,
+      "learning_rate": 9.244780882077254e-05,
+      "loss": 2.7391,
+      "step": 356
+    },
+    {
+      "epoch": 0.4398034398034398,
+      "grad_norm": 2.0379199981689453,
+      "learning_rate": 9.2340070696503e-05,
+      "loss": 3.0342,
+      "step": 358
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 1.8155155181884766,
+      "learning_rate": 9.223163322680772e-05,
+      "loss": 2.9597,
+      "step": 360
+    },
+    {
+      "epoch": 0.44471744471744473,
+      "grad_norm": 1.802756905555725,
+      "learning_rate": 9.212249820278545e-05,
+      "loss": 2.905,
+      "step": 362
+    },
+    {
+      "epoch": 0.44717444717444715,
+      "grad_norm": 1.8715476989746094,
+      "learning_rate": 9.201266742705672e-05,
+      "loss": 3.1148,
+      "step": 364
+    },
+    {
+      "epoch": 0.44963144963144963,
+      "grad_norm": 1.8322906494140625,
+      "learning_rate": 9.190214271373398e-05,
+      "loss": 2.8966,
+      "step": 366
+    },
+    {
+      "epoch": 0.4520884520884521,
+      "grad_norm": 1.8648380041122437,
+      "learning_rate": 9.179092588839178e-05,
+      "loss": 2.7409,
+      "step": 368
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.8744274377822876,
+      "learning_rate": 9.167901878803638e-05,
+      "loss": 2.8532,
+      "step": 370
+    },
+    {
+      "epoch": 0.457002457002457,
+      "grad_norm": 1.9579302072525024,
+      "learning_rate": 9.156642326107565e-05,
+      "loss": 2.9217,
+      "step": 372
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 1.7740904092788696,
+      "learning_rate": 9.145314116728841e-05,
+      "loss": 3.0257,
+      "step": 374
+    },
+    {
+      "epoch": 0.4619164619164619,
+      "grad_norm": 1.762803316116333,
+      "learning_rate": 9.133917437779375e-05,
+      "loss": 2.9256,
+      "step": 376
+    },
+    {
+      "epoch": 0.4643734643734644,
+      "grad_norm": 1.6586060523986816,
+      "learning_rate": 9.12245247750201e-05,
+      "loss": 2.9535,
+      "step": 378
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 1.8642548322677612,
+      "learning_rate": 9.110919425267415e-05,
+      "loss": 3.0129,
+      "step": 380
+    },
+    {
+      "epoch": 0.4692874692874693,
+      "grad_norm": 1.9764457941055298,
+      "learning_rate": 9.099318471570957e-05,
+      "loss": 2.9355,
+      "step": 382
+    },
+    {
+      "epoch": 0.47174447174447176,
+      "grad_norm": 1.7947139739990234,
+      "learning_rate": 9.087649808029554e-05,
+      "loss": 2.8716,
+      "step": 384
+    },
+    {
+      "epoch": 0.4742014742014742,
+      "grad_norm": 2.3146283626556396,
+      "learning_rate": 9.075913627378513e-05,
+      "loss": 2.9939,
+      "step": 386
+    },
+    {
+      "epoch": 0.47665847665847666,
+      "grad_norm": 1.7969456911087036,
+      "learning_rate": 9.064110123468345e-05,
+      "loss": 2.997,
+      "step": 388
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 1.8634977340698242,
+      "learning_rate": 9.052239491261559e-05,
+      "loss": 3.0475,
+      "step": 390
+    },
+    {
+      "epoch": 0.48157248157248156,
+      "grad_norm": 1.8688544034957886,
+      "learning_rate": 9.040301926829445e-05,
+      "loss": 3.0927,
+      "step": 392
+    },
+    {
+      "epoch": 0.48402948402948404,
+      "grad_norm": 1.8441022634506226,
+      "learning_rate": 9.028297627348835e-05,
+      "loss": 2.7731,
+      "step": 394
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 1.8934268951416016,
+      "learning_rate": 9.016226791098851e-05,
+      "loss": 3.0989,
+      "step": 396
+    },
+    {
+      "epoch": 0.48894348894348894,
+      "grad_norm": 1.7705714702606201,
+      "learning_rate": 9.004089617457625e-05,
+      "loss": 2.8965,
+      "step": 398
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 1.8468502759933472,
+      "learning_rate": 8.991886306899002e-05,
+      "loss": 3.0472,
+      "step": 400
+    },
+    {
+      "epoch": 0.49385749385749383,
+      "grad_norm": 1.8708940744400024,
+      "learning_rate": 8.979617060989234e-05,
+      "loss": 3.1242,
+      "step": 402
+    },
+    {
+      "epoch": 0.4963144963144963,
+      "grad_norm": 1.8563363552093506,
+      "learning_rate": 8.967282082383652e-05,
+      "loss": 3.0993,
+      "step": 404
+    },
+    {
+      "epoch": 0.4987714987714988,
+      "grad_norm": 1.8156354427337646,
+      "learning_rate": 8.954881574823317e-05,
+      "loss": 2.9281,
+      "step": 406
+    },
+    {
+      "epoch": 0.5012285012285013,
+      "grad_norm": 1.8335216045379639,
+      "learning_rate": 8.942415743131651e-05,
+      "loss": 2.8471,
+      "step": 408
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 1.8024260997772217,
+      "learning_rate": 8.92988479321106e-05,
+      "loss": 2.7557,
+      "step": 410
+    },
+    {
+      "epoch": 0.5061425061425061,
+      "grad_norm": 1.8545125722885132,
+      "learning_rate": 8.917288932039529e-05,
+      "loss": 3.0465,
+      "step": 412
+    },
+    {
+      "epoch": 0.5085995085995086,
+      "grad_norm": 1.9025720357894897,
+      "learning_rate": 8.904628367667202e-05,
+      "loss": 2.9257,
+      "step": 414
+    },
+    {
+      "epoch": 0.5110565110565111,
+      "grad_norm": 1.7344011068344116,
+      "learning_rate": 8.891903309212952e-05,
+      "loss": 2.8647,
+      "step": 416
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 2.9021973609924316,
+      "learning_rate": 8.87911396686092e-05,
+      "loss": 2.8066,
+      "step": 418
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 2.0105724334716797,
+      "learning_rate": 8.866260551857045e-05,
+      "loss": 3.0139,
+      "step": 420
+    },
+    {
+      "epoch": 0.5184275184275184,
+      "grad_norm": 1.9714957475662231,
+      "learning_rate": 8.853343276505581e-05,
+      "loss": 2.8111,
+      "step": 422
+    },
+    {
+      "epoch": 0.5208845208845209,
+      "grad_norm": 1.8330267667770386,
+      "learning_rate": 8.840362354165581e-05,
+      "loss": 2.8983,
+      "step": 424
+    },
+    {
+      "epoch": 0.5233415233415234,
+      "grad_norm": 2.052891969680786,
+      "learning_rate": 8.827317999247378e-05,
+      "loss": 2.9208,
+      "step": 426
+    },
+    {
+      "epoch": 0.5257985257985258,
+      "grad_norm": 1.8395956754684448,
+      "learning_rate": 8.81421042720904e-05,
+      "loss": 3.0045,
+      "step": 428
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 2.1694936752319336,
+      "learning_rate": 8.801039854552821e-05,
+      "loss": 2.9298,
+      "step": 430
+    },
+    {
+      "epoch": 0.5307125307125307,
+      "grad_norm": 1.9098365306854248,
+      "learning_rate": 8.787806498821571e-05,
+      "loss": 2.8694,
+      "step": 432
+    },
+    {
+      "epoch": 0.5331695331695332,
+      "grad_norm": 1.8973677158355713,
+      "learning_rate": 8.774510578595153e-05,
+      "loss": 3.0031,
+      "step": 434
+    },
+    {
+      "epoch": 0.5356265356265356,
+      "grad_norm": 1.8934143781661987,
+      "learning_rate": 8.761152313486824e-05,
+      "loss": 2.9812,
+      "step": 436
+    },
+    {
+      "epoch": 0.538083538083538,
+      "grad_norm": 1.8013354539871216,
+      "learning_rate": 8.747731924139622e-05,
+      "loss": 2.7604,
+      "step": 438
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 1.733801245689392,
+      "learning_rate": 8.734249632222702e-05,
+      "loss": 2.9479,
+      "step": 440
+    },
+    {
+      "epoch": 0.542997542997543,
+      "grad_norm": 1.780144214630127,
+      "learning_rate": 8.720705660427692e-05,
+      "loss": 2.8673,
+      "step": 442
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.930598258972168,
+      "learning_rate": 8.707100232465007e-05,
+      "loss": 2.85,
+      "step": 444
+    },
+    {
+      "epoch": 0.547911547911548,
+      "grad_norm": 1.886904239654541,
+      "learning_rate": 8.69343357306015e-05,
+      "loss": 2.8363,
+      "step": 446
+    },
+    {
+      "epoch": 0.5503685503685504,
+      "grad_norm": 2.0362017154693604,
+      "learning_rate": 8.67970590795001e-05,
+      "loss": 2.6025,
+      "step": 448
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 1.8580693006515503,
+      "learning_rate": 8.665917463879125e-05,
+      "loss": 3.1713,
+      "step": 450
+    },
+    {
+      "epoch": 0.5552825552825553,
+      "grad_norm": 1.9810400009155273,
+      "learning_rate": 8.65206846859594e-05,
+      "loss": 2.9814,
+      "step": 452
+    },
+    {
+      "epoch": 0.5577395577395577,
+      "grad_norm": 1.824465274810791,
+      "learning_rate": 8.638159150849046e-05,
+      "loss": 3.0354,
+      "step": 454
+    },
+    {
+      "epoch": 0.5601965601965602,
+      "grad_norm": 1.7572405338287354,
+      "learning_rate": 8.6241897403834e-05,
+      "loss": 2.9922,
+      "step": 456
+    },
+    {
+      "epoch": 0.5626535626535627,
+      "grad_norm": 1.7362189292907715,
+      "learning_rate": 8.610160467936533e-05,
+      "loss": 2.9658,
+      "step": 458
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.782990574836731,
+      "learning_rate": 8.596071565234733e-05,
+      "loss": 3.0351,
+      "step": 460
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 1.6694259643554688,
+      "learning_rate": 8.581923264989228e-05,
+      "loss": 2.8801,
+      "step": 462
+    },
+    {
+      "epoch": 0.5700245700245701,
+      "grad_norm": 1.7287397384643555,
+      "learning_rate": 8.567715800892326e-05,
+      "loss": 3.0199,
+      "step": 464
+    },
+    {
+      "epoch": 0.5724815724815725,
+      "grad_norm": 1.8691298961639404,
+      "learning_rate": 8.553449407613572e-05,
+      "loss": 2.9934,
+      "step": 466
+    },
+    {
+      "epoch": 0.5749385749385749,
+      "grad_norm": 1.8286222219467163,
+      "learning_rate": 8.539124320795862e-05,
+      "loss": 2.9836,
+      "step": 468
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 1.658504843711853,
+      "learning_rate": 8.524740777051555e-05,
+      "loss": 2.7834,
+      "step": 470
+    },
+    {
+      "epoch": 0.5798525798525799,
+      "grad_norm": 2.0098395347595215,
+      "learning_rate": 8.510299013958558e-05,
+      "loss": 3.0716,
+      "step": 472
+    },
+    {
+      "epoch": 0.5823095823095823,
+      "grad_norm": 1.998702883720398,
+      "learning_rate": 8.495799270056412e-05,
+      "loss": 2.9943,
+      "step": 474
+    },
+    {
+      "epoch": 0.5847665847665847,
+      "grad_norm": 1.7779194116592407,
+      "learning_rate": 8.481241784842344e-05,
+      "loss": 2.7784,
+      "step": 476
+    },
+    {
+      "epoch": 0.5872235872235873,
+      "grad_norm": 1.8476285934448242,
+      "learning_rate": 8.466626798767318e-05,
+      "loss": 3.0224,
+      "step": 478
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 1.759994626045227,
+      "learning_rate": 8.451954553232055e-05,
+      "loss": 3.1009,
+      "step": 480
+    },
+    {
+      "epoch": 0.5921375921375921,
+      "grad_norm": 1.7729698419570923,
+      "learning_rate": 8.437225290583051e-05,
+      "loss": 2.7858,
+      "step": 482
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 1.8636449575424194,
+      "learning_rate": 8.422439254108576e-05,
+      "loss": 2.974,
+      "step": 484
+    },
+    {
+      "epoch": 0.597051597051597,
+      "grad_norm": 1.938599944114685,
+      "learning_rate": 8.407596688034648e-05,
+      "loss": 3.0187,
+      "step": 486
+    },
+    {
+      "epoch": 0.5995085995085995,
+      "grad_norm": 1.7237671613693237,
+      "learning_rate": 8.392697837521007e-05,
+      "loss": 2.8565,
+      "step": 488
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 2.4623801708221436,
+      "learning_rate": 8.37774294865706e-05,
+      "loss": 2.7818,
+      "step": 490
+    },
+    {
+      "epoch": 0.6044226044226044,
+      "grad_norm": 1.7916040420532227,
+      "learning_rate": 8.362732268457824e-05,
+      "loss": 3.1151,
+      "step": 492
+    },
+    {
+      "epoch": 0.6068796068796068,
+      "grad_norm": 1.8052140474319458,
+      "learning_rate": 8.347666044859833e-05,
+      "loss": 2.8566,
+      "step": 494
+    },
+    {
+      "epoch": 0.6093366093366094,
+      "grad_norm": 1.9497567415237427,
+      "learning_rate": 8.332544526717057e-05,
+      "loss": 2.8451,
+      "step": 496
+    },
+    {
+      "epoch": 0.6117936117936118,
+      "grad_norm": 1.9246710538864136,
+      "learning_rate": 8.317367963796778e-05,
+      "loss": 2.9308,
+      "step": 498
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 1.8030129671096802,
+      "learning_rate": 8.30213660677548e-05,
+      "loss": 2.8824,
+      "step": 500
+    },
+    {
+      "epoch": 0.6167076167076168,
+      "grad_norm": 1.8339178562164307,
+      "learning_rate": 8.286850707234691e-05,
+      "loss": 2.8304,
+      "step": 502
+    },
+    {
+      "epoch": 0.6191646191646192,
+      "grad_norm": 2.070434808731079,
+      "learning_rate": 8.271510517656845e-05,
+      "loss": 2.8802,
+      "step": 504
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 2.7643368244171143,
+      "learning_rate": 8.256116291421094e-05,
+      "loss": 3.0449,
+      "step": 506
+    },
+    {
+      "epoch": 0.6240786240786241,
+      "grad_norm": 2.0422732830047607,
+      "learning_rate": 8.24066828279914e-05,
+      "loss": 2.9059,
+      "step": 508
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 2.012234687805176,
+      "learning_rate": 8.225166746951023e-05,
+      "loss": 3.0151,
+      "step": 510
+    },
+    {
+      "epoch": 0.628992628992629,
+      "grad_norm": 1.7563395500183105,
+      "learning_rate": 8.209611939920912e-05,
+      "loss": 2.6551,
+      "step": 512
+    },
+    {
+      "epoch": 0.6314496314496314,
+      "grad_norm": 1.9222311973571777,
+      "learning_rate": 8.194004118632873e-05,
+      "loss": 2.8514,
+      "step": 514
+    },
+    {
+      "epoch": 0.6339066339066339,
+      "grad_norm": 1.8835155963897705,
+      "learning_rate": 8.178343540886626e-05,
+      "loss": 2.883,
+      "step": 516
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.8356646299362183,
+      "learning_rate": 8.162630465353292e-05,
+      "loss": 2.7415,
+      "step": 518
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 1.890042781829834,
+      "learning_rate": 8.146865151571108e-05,
+      "loss": 2.82,
+      "step": 520
+    },
+    {
+      "epoch": 0.6412776412776413,
+      "grad_norm": 1.9901831150054932,
+      "learning_rate": 8.131047859941156e-05,
+      "loss": 2.7657,
+      "step": 522
+    },
+    {
+      "epoch": 0.6437346437346437,
+      "grad_norm": 1.8286992311477661,
+      "learning_rate": 8.11517885172305e-05,
+      "loss": 2.9325,
+      "step": 524
+    },
+    {
+      "epoch": 0.6461916461916462,
+      "grad_norm": 1.817006230354309,
+      "learning_rate": 8.099258389030624e-05,
+      "loss": 2.6395,
+      "step": 526
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 1.7543143033981323,
+      "learning_rate": 8.083286734827605e-05,
+      "loss": 2.847,
+      "step": 528
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 1.8252453804016113,
+      "learning_rate": 8.067264152923268e-05,
+      "loss": 2.8588,
+      "step": 530
+    },
+    {
+      "epoch": 0.6535626535626535,
+      "grad_norm": 1.9331204891204834,
+      "learning_rate": 8.051190907968076e-05,
+      "loss": 2.7571,
+      "step": 532
+    },
+    {
+      "epoch": 0.6560196560196561,
+      "grad_norm": 1.7939069271087646,
+      "learning_rate": 8.035067265449312e-05,
+      "loss": 2.7728,
+      "step": 534
+    },
+    {
+      "epoch": 0.6584766584766585,
+      "grad_norm": 4.82619571685791,
+      "learning_rate": 8.018893491686692e-05,
+      "loss": 2.891,
+      "step": 536
+    },
+    {
+      "epoch": 0.6609336609336609,
+      "grad_norm": 1.9427580833435059,
+      "learning_rate": 8.00266985382797e-05,
+      "loss": 2.9047,
+      "step": 538
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 1.8458834886550903,
+      "learning_rate": 7.986396619844519e-05,
+      "loss": 2.8492,
+      "step": 540
+    },
+    {
+      "epoch": 0.6658476658476659,
+      "grad_norm": 1.9331218004226685,
+      "learning_rate": 7.970074058526908e-05,
+      "loss": 2.8547,
+      "step": 542
+    },
+    {
+      "epoch": 0.6683046683046683,
+      "grad_norm": 1.8768330812454224,
+      "learning_rate": 7.953702439480468e-05,
+      "loss": 2.575,
+      "step": 544
+    },
+    {
+      "epoch": 0.6707616707616708,
+      "grad_norm": 1.9068561792373657,
+      "learning_rate": 7.937282033120825e-05,
+      "loss": 3.0085,
+      "step": 546
+    },
+    {
+      "epoch": 0.6732186732186732,
+      "grad_norm": 1.890088438987732,
+      "learning_rate": 7.920813110669445e-05,
+      "loss": 2.9341,
+      "step": 548
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.8849834203720093,
+      "learning_rate": 7.904295944149157e-05,
+      "loss": 2.7635,
+      "step": 550
+    },
+    {
+      "epoch": 0.6781326781326781,
+      "grad_norm": 1.7430170774459839,
+      "learning_rate": 7.887730806379641e-05,
+      "loss": 2.608,
+      "step": 552
+    },
+    {
+      "epoch": 0.6805896805896806,
+      "grad_norm": 1.7541913986206055,
+      "learning_rate": 7.871117970972948e-05,
+      "loss": 3.0008,
+      "step": 554
+    },
+    {
+      "epoch": 0.683046683046683,
+      "grad_norm": 1.8100526332855225,
+      "learning_rate": 7.854457712328957e-05,
+      "loss": 2.8934,
+      "step": 556
+    },
+    {
+      "epoch": 0.6855036855036855,
+      "grad_norm": 1.8675240278244019,
+      "learning_rate": 7.837750305630862e-05,
+      "loss": 2.7809,
+      "step": 558
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 2.3414931297302246,
+      "learning_rate": 7.820996026840607e-05,
+      "loss": 2.8065,
+      "step": 560
+    },
+    {
+      "epoch": 0.6904176904176904,
+      "grad_norm": 1.6343646049499512,
+      "learning_rate": 7.804195152694347e-05,
+      "loss": 2.9003,
+      "step": 562
+    },
+    {
+      "epoch": 0.6928746928746928,
+      "grad_norm": 1.7469531297683716,
+      "learning_rate": 7.787347960697863e-05,
+      "loss": 2.8534,
+      "step": 564
+    },
+    {
+      "epoch": 0.6953316953316954,
+      "grad_norm": 1.7567309141159058,
+      "learning_rate": 7.77045472912199e-05,
+      "loss": 2.7476,
+      "step": 566
+    },
+    {
+      "epoch": 0.6977886977886978,
+      "grad_norm": 1.7307237386703491,
+      "learning_rate": 7.753515736998007e-05,
+      "loss": 2.7558,
+      "step": 568
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 1.689818263053894,
+      "learning_rate": 7.736531264113041e-05,
+      "loss": 2.5798,
+      "step": 570
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 1.806868553161621,
+      "learning_rate": 7.719501591005436e-05,
+      "loss": 2.9242,
+      "step": 572
+    },
+    {
+      "epoch": 0.7051597051597052,
+      "grad_norm": 1.8649382591247559,
+      "learning_rate": 7.702426998960129e-05,
+      "loss": 2.7499,
+      "step": 574
+    },
+    {
+      "epoch": 0.7076167076167076,
+      "grad_norm": 1.8912419080734253,
+      "learning_rate": 7.685307770003993e-05,
+      "loss": 2.9558,
+      "step": 576
+    },
+    {
+      "epoch": 0.7100737100737101,
+      "grad_norm": 1.8979637622833252,
+      "learning_rate": 7.668144186901189e-05,
+      "loss": 2.7551,
+      "step": 578
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 1.737945556640625,
+      "learning_rate": 7.650936533148485e-05,
+      "loss": 2.9113,
+      "step": 580
+    },
+    {
+      "epoch": 0.714987714987715,
+      "grad_norm": 1.8241580724716187,
+      "learning_rate": 7.633685092970584e-05,
+      "loss": 2.9001,
+      "step": 582
+    },
+    {
+      "epoch": 0.7174447174447175,
+      "grad_norm": 1.7341822385787964,
+      "learning_rate": 7.616390151315422e-05,
+      "loss": 2.7347,
+      "step": 584
+    },
+    {
+      "epoch": 0.7199017199017199,
+      "grad_norm": 1.8221603631973267,
+      "learning_rate": 7.599051993849467e-05,
+      "loss": 2.501,
+      "step": 586
+    },
+    {
+      "epoch": 0.7223587223587223,
+      "grad_norm": 1.9198024272918701,
+      "learning_rate": 7.58167090695299e-05,
+      "loss": 2.9385,
+      "step": 588
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 1.725482702255249,
+      "learning_rate": 7.56424717771535e-05,
+      "loss": 2.7557,
+      "step": 590
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 2.0752015113830566,
+      "learning_rate": 7.546781093930238e-05,
+      "loss": 2.6973,
+      "step": 592
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 1.84364914894104,
+      "learning_rate": 7.529272944090935e-05,
+      "loss": 2.8651,
+      "step": 594
+    },
+    {
+      "epoch": 0.7321867321867321,
+      "grad_norm": 2.004852771759033,
+      "learning_rate": 7.511723017385538e-05,
+      "loss": 2.6205,
+      "step": 596
+    },
+    {
+      "epoch": 0.7346437346437347,
+      "grad_norm": 1.847954273223877,
+      "learning_rate": 7.494131603692187e-05,
+      "loss": 2.745,
+      "step": 598
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 1.865380048751831,
+      "learning_rate": 7.476498993574277e-05,
+      "loss": 2.8809,
+      "step": 600
+    },
+    {
+      "epoch": 0.7395577395577395,
+      "grad_norm": 1.8404914140701294,
+      "learning_rate": 7.45882547827566e-05,
+      "loss": 2.8683,
+      "step": 602
+    },
+    {
+      "epoch": 0.742014742014742,
+      "grad_norm": 1.783154010772705,
+      "learning_rate": 7.441111349715832e-05,
+      "loss": 2.7588,
+      "step": 604
+    },
+    {
+      "epoch": 0.7444717444717445,
+      "grad_norm": 1.7274466753005981,
+      "learning_rate": 7.423356900485108e-05,
+      "loss": 2.8013,
+      "step": 606
+    },
+    {
+      "epoch": 0.7469287469287469,
+      "grad_norm": 1.9206289052963257,
+      "learning_rate": 7.405562423839801e-05,
+      "loss": 2.7951,
+      "step": 608
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 1.9059563875198364,
+      "learning_rate": 7.387728213697365e-05,
+      "loss": 2.756,
+      "step": 610
+    },
+    {
+      "epoch": 0.7518427518427518,
+      "grad_norm": 3.3889310359954834,
+      "learning_rate": 7.369854564631548e-05,
+      "loss": 2.9342,
+      "step": 612
+    },
+    {
+      "epoch": 0.7542997542997543,
+      "grad_norm": 1.733508825302124,
+      "learning_rate": 7.351941771867523e-05,
+      "loss": 2.823,
+      "step": 614
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 1.679160475730896,
+      "learning_rate": 7.333990131277013e-05,
+      "loss": 2.7185,
+      "step": 616
+    },
+    {
+      "epoch": 0.7592137592137592,
+      "grad_norm": 3.083275318145752,
+      "learning_rate": 7.315999939373404e-05,
+      "loss": 2.6941,
+      "step": 618
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 1.7113125324249268,
+      "learning_rate": 7.297971493306848e-05,
+      "loss": 2.9749,
+      "step": 620
+    },
+    {
+      "epoch": 0.7641277641277642,
+      "grad_norm": 1.654995083808899,
+      "learning_rate": 7.279905090859352e-05,
+      "loss": 2.6857,
+      "step": 622
+    },
+    {
+      "epoch": 0.7665847665847666,
+      "grad_norm": 2.0876009464263916,
+      "learning_rate": 7.261801030439864e-05,
+      "loss": 2.6532,
+      "step": 624
+    },
+    {
+      "epoch": 0.769041769041769,
+      "grad_norm": 1.7576290369033813,
+      "learning_rate": 7.243659611079343e-05,
+      "loss": 2.6503,
+      "step": 626
+    },
+    {
+      "epoch": 0.7714987714987716,
+      "grad_norm": 1.8806345462799072,
+      "learning_rate": 7.225481132425812e-05,
+      "loss": 2.5581,
+      "step": 628
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 1.7295315265655518,
+      "learning_rate": 7.20726589473942e-05,
+      "loss": 2.7995,
+      "step": 630
+    },
+    {
+      "epoch": 0.7764127764127764,
+      "grad_norm": 1.7444125413894653,
+      "learning_rate": 7.189014198887478e-05,
+      "loss": 2.9175,
+      "step": 632
+    },
+    {
+      "epoch": 0.7788697788697788,
+      "grad_norm": 1.9849998950958252,
+      "learning_rate": 7.170726346339488e-05,
+      "loss": 2.9118,
+      "step": 634
+    },
+    {
+      "epoch": 0.7813267813267813,
+      "grad_norm": 1.7984490394592285,
+      "learning_rate": 7.15240263916216e-05,
+      "loss": 2.7955,
+      "step": 636
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 1.6878135204315186,
+      "learning_rate": 7.134043380014436e-05,
+      "loss": 2.6611,
+      "step": 638
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 1.6732217073440552,
+      "learning_rate": 7.115648872142475e-05,
+      "loss": 2.5905,
+      "step": 640
+    },
+    {
+      "epoch": 0.7886977886977887,
+      "grad_norm": 1.8399916887283325,
+      "learning_rate": 7.097219419374652e-05,
+      "loss": 2.8581,
+      "step": 642
+    },
+    {
+      "epoch": 0.7911547911547911,
+      "grad_norm": 1.6764298677444458,
+      "learning_rate": 7.078755326116542e-05,
+      "loss": 2.5396,
+      "step": 644
+    },
+    {
+      "epoch": 0.7936117936117936,
+      "grad_norm": 1.882920742034912,
+      "learning_rate": 7.060256897345888e-05,
+      "loss": 2.9048,
+      "step": 646
+    },
+    {
+      "epoch": 0.7960687960687961,
+      "grad_norm": 1.9298219680786133,
+      "learning_rate": 7.041724438607563e-05,
+      "loss": 2.954,
+      "step": 648
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 1.710889458656311,
+      "learning_rate": 7.023158256008521e-05,
+      "loss": 2.9693,
+      "step": 650
+    },
+    {
+      "epoch": 0.800982800982801,
+      "grad_norm": 1.7387322187423706,
+      "learning_rate": 7.004558656212753e-05,
+      "loss": 2.8788,
+      "step": 652
+    },
+    {
+      "epoch": 0.8034398034398035,
+      "grad_norm": 1.8131159543991089,
+      "learning_rate": 6.985925946436213e-05,
+      "loss": 2.8383,
+      "step": 654
+    },
+    {
+      "epoch": 0.8058968058968059,
+      "grad_norm": 1.7700482606887817,
+      "learning_rate": 6.967260434441729e-05,
+      "loss": 2.7677,
+      "step": 656
+    },
+    {
+      "epoch": 0.8083538083538083,
+      "grad_norm": 1.7338896989822388,
+      "learning_rate": 6.948562428533955e-05,
+      "loss": 2.8565,
+      "step": 658
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.7637079954147339,
+      "learning_rate": 6.929832237554241e-05,
+      "loss": 2.8684,
+      "step": 660
+    },
+    {
+      "epoch": 0.8132678132678133,
+      "grad_norm": 1.7479512691497803,
+      "learning_rate": 6.911070170875562e-05,
+      "loss": 2.8784,
+      "step": 662
+    },
+    {
+      "epoch": 0.8157248157248157,
+      "grad_norm": 2.2720673084259033,
+      "learning_rate": 6.892276538397384e-05,
+      "loss": 2.7932,
+      "step": 664
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 1.7335164546966553,
+      "learning_rate": 6.873451650540566e-05,
+      "loss": 2.6538,
+      "step": 666
+    },
+    {
+      "epoch": 0.8206388206388207,
+      "grad_norm": 1.8123350143432617,
+      "learning_rate": 6.854595818242213e-05,
+      "loss": 2.8612,
+      "step": 668
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 1.6376591920852661,
+      "learning_rate": 6.835709352950557e-05,
+      "loss": 2.8271,
+      "step": 670
+    },
+    {
+      "epoch": 0.8255528255528255,
+      "grad_norm": 1.863923192024231,
+      "learning_rate": 6.816792566619806e-05,
+      "loss": 2.6843,
+      "step": 672
+    },
+    {
+      "epoch": 0.828009828009828,
+      "grad_norm": 1.637650728225708,
+      "learning_rate": 6.797845771704983e-05,
+      "loss": 2.7099,
+      "step": 674
+    },
+    {
+      "epoch": 0.8304668304668305,
+      "grad_norm": 1.7621389627456665,
+      "learning_rate": 6.778869281156784e-05,
+      "loss": 2.8904,
+      "step": 676
+    },
+    {
+      "epoch": 0.8329238329238329,
+      "grad_norm": 1.6948051452636719,
+      "learning_rate": 6.759863408416386e-05,
+      "loss": 2.7876,
+      "step": 678
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 1.742684006690979,
+      "learning_rate": 6.740828467410294e-05,
+      "loss": 2.9384,
+      "step": 680
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 1.7781345844268799,
+      "learning_rate": 6.721764772545135e-05,
+      "loss": 2.5972,
+      "step": 682
+    },
+    {
+      "epoch": 0.8402948402948403,
+      "grad_norm": 1.7659155130386353,
+      "learning_rate": 6.702672638702475e-05,
+      "loss": 2.8173,
+      "step": 684
+    },
+    {
+      "epoch": 0.8427518427518428,
+      "grad_norm": 1.7547752857208252,
+      "learning_rate": 6.68355238123362e-05,
+      "loss": 2.8518,
+      "step": 686
+    },
+    {
+      "epoch": 0.8452088452088452,
+      "grad_norm": 1.634647250175476,
+      "learning_rate": 6.664404315954397e-05,
+      "loss": 2.7208,
+      "step": 688
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 1.6761173009872437,
+      "learning_rate": 6.64522875913995e-05,
+      "loss": 2.812,
+      "step": 690
+    },
+    {
+      "epoch": 0.8501228501228502,
+      "grad_norm": 1.7231212854385376,
+      "learning_rate": 6.626026027519509e-05,
+      "loss": 2.7787,
+      "step": 692
+    },
+    {
+      "epoch": 0.8525798525798526,
+      "grad_norm": 1.8298566341400146,
+      "learning_rate": 6.606796438271156e-05,
+      "loss": 2.755,
+      "step": 694
+    },
+    {
+      "epoch": 0.855036855036855,
+      "grad_norm": 1.7021121978759766,
+      "learning_rate": 6.587540309016592e-05,
+      "loss": 2.5943,
+      "step": 696
+    },
+    {
+      "epoch": 0.8574938574938575,
+      "grad_norm": 1.7043418884277344,
+      "learning_rate": 6.568257957815893e-05,
+      "loss": 2.7609,
+      "step": 698
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 1.7982568740844727,
+      "learning_rate": 6.54894970316224e-05,
+      "loss": 2.5406,
+      "step": 700
+    },
+    {
+      "epoch": 0.8624078624078624,
+      "grad_norm": 1.8539308309555054,
+      "learning_rate": 6.529615863976684e-05,
+      "loss": 2.8071,
+      "step": 702
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 1.7513319253921509,
+      "learning_rate": 6.510256759602857e-05,
+      "loss": 2.7662,
+      "step": 704
+    },
+    {
+      "epoch": 0.8673218673218673,
+      "grad_norm": 1.7730543613433838,
+      "learning_rate": 6.4908727098017e-05,
+      "loss": 2.8082,
+      "step": 706
+    },
+    {
+      "epoch": 0.8697788697788698,
+      "grad_norm": 1.6426489353179932,
+      "learning_rate": 6.4714640347462e-05,
+      "loss": 2.5879,
+      "step": 708
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 1.6702338457107544,
+      "learning_rate": 6.452031055016073e-05,
+      "loss": 2.6247,
+      "step": 710
+    },
+    {
+      "epoch": 0.8746928746928747,
+      "grad_norm": 1.6281359195709229,
+      "learning_rate": 6.432574091592494e-05,
+      "loss": 2.6192,
+      "step": 712
+    },
+    {
+      "epoch": 0.8771498771498771,
+      "grad_norm": 1.7311663627624512,
+      "learning_rate": 6.41309346585278e-05,
+      "loss": 2.916,
+      "step": 714
+    },
+    {
+      "epoch": 0.8796068796068796,
+      "grad_norm": 1.781010627746582,
+      "learning_rate": 6.393589499565088e-05,
+      "loss": 2.6185,
+      "step": 716
+    },
+    {
+      "epoch": 0.8820638820638821,
+      "grad_norm": 1.6897130012512207,
+      "learning_rate": 6.374062514883099e-05,
+      "loss": 2.8202,
+      "step": 718
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 1.6871286630630493,
+      "learning_rate": 6.354512834340695e-05,
+      "loss": 2.6197,
+      "step": 720
+    },
+    {
+      "epoch": 0.8869778869778869,
+      "grad_norm": 1.7017685174942017,
+      "learning_rate": 6.334940780846634e-05,
+      "loss": 2.6785,
+      "step": 722
+    },
+    {
+      "epoch": 0.8894348894348895,
+      "grad_norm": 1.6969901323318481,
+      "learning_rate": 6.315346677679218e-05,
+      "loss": 2.8976,
+      "step": 724
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 1.8819012641906738,
+      "learning_rate": 6.295730848480947e-05,
+      "loss": 2.7231,
+      "step": 726
+    },
+    {
+      "epoch": 0.8943488943488943,
+      "grad_norm": 1.8459581136703491,
+      "learning_rate": 6.276093617253182e-05,
+      "loss": 2.7186,
+      "step": 728
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 1.7170779705047607,
+      "learning_rate": 6.256435308350786e-05,
+      "loss": 2.6779,
+      "step": 730
+    },
+    {
+      "epoch": 0.8992628992628993,
+      "grad_norm": 1.7795841693878174,
+      "learning_rate": 6.236756246476765e-05,
+      "loss": 2.8444,
+      "step": 732
+    },
+    {
+      "epoch": 0.9017199017199017,
+      "grad_norm": 1.7305338382720947,
+      "learning_rate": 6.217056756676917e-05,
+      "loss": 2.5758,
+      "step": 734
+    },
+    {
+      "epoch": 0.9041769041769042,
+      "grad_norm": 1.757850170135498,
+      "learning_rate": 6.197337164334453e-05,
+      "loss": 2.8906,
+      "step": 736
+    },
+    {
+      "epoch": 0.9066339066339066,
+      "grad_norm": 1.7602792978286743,
+      "learning_rate": 6.177597795164616e-05,
+      "loss": 2.6525,
+      "step": 738
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.6600172519683838,
+      "learning_rate": 6.157838975209323e-05,
+      "loss": 2.5314,
+      "step": 740
+    },
+    {
+      "epoch": 0.9115479115479116,
+      "grad_norm": 1.699733018875122,
+      "learning_rate": 6.138061030831755e-05,
+      "loss": 2.8172,
+      "step": 742
+    },
+    {
+      "epoch": 0.914004914004914,
+      "grad_norm": 1.6197196245193481,
+      "learning_rate": 6.118264288710988e-05,
+      "loss": 2.7426,
+      "step": 744
+    },
+    {
+      "epoch": 0.9164619164619164,
+      "grad_norm": 1.6376876831054688,
+      "learning_rate": 6.098449075836575e-05,
+      "loss": 2.7575,
+      "step": 746
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 1.6010876893997192,
+      "learning_rate": 6.0786157195031653e-05,
+      "loss": 2.6253,
+      "step": 748
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 1.6927965879440308,
+      "learning_rate": 6.058764547305088e-05,
+      "loss": 2.8049,
+      "step": 750
+    },
+    {
+      "epoch": 0.9238329238329238,
+      "grad_norm": 1.682666540145874,
+      "learning_rate": 6.038895887130942e-05,
+      "loss": 2.8196,
+      "step": 752
+    },
+    {
+      "epoch": 0.9262899262899262,
+      "grad_norm": 1.8771963119506836,
+      "learning_rate": 6.019010067158181e-05,
+      "loss": 2.8902,
+      "step": 754
+    },
+    {
+      "epoch": 0.9287469287469288,
+      "grad_norm": 1.6778903007507324,
+      "learning_rate": 5.9991074158476935e-05,
+      "loss": 2.7642,
+      "step": 756
+    },
+    {
+      "epoch": 0.9312039312039312,
+      "grad_norm": 2.0854263305664062,
+      "learning_rate": 5.9791882619383766e-05,
+      "loss": 2.727,
+      "step": 758
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 1.6467037200927734,
+      "learning_rate": 5.959252934441707e-05,
+      "loss": 2.5711,
+      "step": 760
+    },
+    {
+      "epoch": 0.9361179361179361,
+      "grad_norm": 1.6560814380645752,
+      "learning_rate": 5.939301762636307e-05,
+      "loss": 2.8803,
+      "step": 762
+    },
+    {
+      "epoch": 0.9385749385749386,
+      "grad_norm": 1.6084171533584595,
+      "learning_rate": 5.9193350760625014e-05,
+      "loss": 2.6728,
+      "step": 764
+    },
+    {
+      "epoch": 0.941031941031941,
+      "grad_norm": 1.7624053955078125,
+      "learning_rate": 5.8993532045168795e-05,
+      "loss": 2.621,
+      "step": 766
+    },
+    {
+      "epoch": 0.9434889434889435,
+      "grad_norm": 1.6158403158187866,
+      "learning_rate": 5.879356478046849e-05,
+      "loss": 2.7241,
+      "step": 768
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 1.5942398309707642,
+      "learning_rate": 5.8593452269451775e-05,
+      "loss": 2.6864,
+      "step": 770
+    },
+    {
+      "epoch": 0.9484029484029484,
+      "grad_norm": 1.6023515462875366,
+      "learning_rate": 5.839319781744542e-05,
+      "loss": 2.8454,
+      "step": 772
+    },
+    {
+      "epoch": 0.9508599508599509,
+      "grad_norm": 1.6624382734298706,
+      "learning_rate": 5.81928047321207e-05,
+      "loss": 2.6242,
+      "step": 774
+    },
+    {
+      "epoch": 0.9533169533169533,
+      "grad_norm": 1.638469934463501,
+      "learning_rate": 5.79922763234387e-05,
+      "loss": 2.599,
+      "step": 776
+    },
+    {
+      "epoch": 0.9557739557739557,
+      "grad_norm": 1.7188334465026855,
+      "learning_rate": 5.779161590359573e-05,
+      "loss": 2.7079,
+      "step": 778
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 1.6725521087646484,
+      "learning_rate": 5.7590826786968576e-05,
+      "loss": 2.6391,
+      "step": 780
+    },
+    {
+      "epoch": 0.9606879606879607,
+      "grad_norm": 1.6070250272750854,
+      "learning_rate": 5.738991229005972e-05,
+      "loss": 2.5252,
+      "step": 782
+    },
+    {
+      "epoch": 0.9631449631449631,
+      "grad_norm": 1.8139675855636597,
+      "learning_rate": 5.7188875731442605e-05,
+      "loss": 2.545,
+      "step": 784
+    },
+    {
+      "epoch": 0.9656019656019657,
+      "grad_norm": 1.6884874105453491,
+      "learning_rate": 5.6987720431706826e-05,
+      "loss": 2.5958,
+      "step": 786
+    },
+    {
+      "epoch": 0.9680589680589681,
+      "grad_norm": 1.735592246055603,
+      "learning_rate": 5.678644971340326e-05,
+      "loss": 2.9243,
+      "step": 788
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 1.7505390644073486,
+      "learning_rate": 5.658506690098916e-05,
+      "loss": 2.782,
+      "step": 790
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 1.6411902904510498,
+      "learning_rate": 5.638357532077331e-05,
+      "loss": 2.5277,
+      "step": 792
+    },
+    {
+      "epoch": 0.9754299754299754,
+      "grad_norm": 1.745453119277954,
+      "learning_rate": 5.6181978300861046e-05,
+      "loss": 2.4979,
+      "step": 794
+    },
+    {
+      "epoch": 0.9778869778869779,
+      "grad_norm": 1.6847970485687256,
+      "learning_rate": 5.598027917109929e-05,
+      "loss": 2.6112,
+      "step": 796
+    },
+    {
+      "epoch": 0.9803439803439803,
+      "grad_norm": 1.7334604263305664,
+      "learning_rate": 5.577848126302152e-05,
+      "loss": 2.8999,
+      "step": 798
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 1.6627264022827148,
+      "learning_rate": 5.55765879097928e-05,
+      "loss": 2.7808,
+      "step": 800
+    },
+    {
+      "epoch": 0.9852579852579852,
+      "grad_norm": 1.8199021816253662,
+      "learning_rate": 5.5374602446154665e-05,
+      "loss": 2.846,
+      "step": 802
+    },
+    {
+      "epoch": 0.9877149877149877,
+      "grad_norm": 1.6511715650558472,
+      "learning_rate": 5.517252820837011e-05,
+      "loss": 2.518,
+      "step": 804
+    },
+    {
+      "epoch": 0.9901719901719902,
+      "grad_norm": 1.7161328792572021,
+      "learning_rate": 5.49703685341684e-05,
+      "loss": 2.7736,
+      "step": 806
+    },
+    {
+      "epoch": 0.9926289926289926,
+      "grad_norm": 1.740677833557129,
+      "learning_rate": 5.4768126762690034e-05,
+      "loss": 2.6334,
+      "step": 808
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 1.5712820291519165,
+      "learning_rate": 5.456580623443145e-05,
+      "loss": 2.6854,
+      "step": 810
+    },
+    {
+      "epoch": 0.9975429975429976,
+      "grad_norm": 1.6212587356567383,
+      "learning_rate": 5.436341029119004e-05,
+      "loss": 2.7081,
+      "step": 812
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.0476884841918945,
+      "learning_rate": 5.416094227600881e-05,
+      "loss": 3.0235,
+      "step": 814
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1628,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 814,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3763952104177664e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-814/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6928cbd68be40f1db7704fe9adf1988b07c0adf326e5ecd940c3f031a819851
+size 5432

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-ban_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:b1a4272ec4e7529ec7b13562a278f19fb9e358893f48f491738f36005fbbf5ac
+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:e1c6952ea39686798f9d62bed9ff2d1d117c15ee79c0a1d99365be1d63f4cb3b
+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:e6928cbd68be40f1db7704fe9adf1988b07c0adf326e5ecd940c3f031a819851
+size 5432