Upload folder using huggingface_hub

checkpoint-1250/config.json

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

checkpoint-1250/generation_config.json

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1331a6f57197de8ca593bf68012c6e1e84c05cb32456a5be00fdf5298929fcc
+size 4950070472

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0028b6bd4c1142e0db2ef947bc0b3995e992cd9ef7d53c27fe63ee4fce5c6038
+size 4614509080

checkpoint-1250/model.safetensors.index.json

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

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a717264c3313ce0c00affca65c20689382a355dde66c64f71de678a84f37295
+size 13055369358

checkpoint-1250/rng_state.pth

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

checkpoint-1250/scheduler.pt

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

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a14ce667645cb7eeac31bbc81a8901ccab3bd9ee5946b30f64493f6131819cf
+size 5432

checkpoint-625/config.json

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

checkpoint-625/generation_config.json

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ad5447d1dbf429cecec53424a25caa5c493aebf9bbdddfb5961c862f8d90ee
+size 4950070472

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1ca37d58ed44bd3e236fd884d751702976ef2679db22a97a21d3d0dadbcb69
+size 4614509080

checkpoint-625/model.safetensors.index.json

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

checkpoint-625/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fa919e4642326903ca69c676d5e5ad185fd25a8ae86c59535b6dd1ebf9d193
+size 13055369358

checkpoint-625/rng_state.pth

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

checkpoint-625/scheduler.pt

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

checkpoint-625/trainer_state.json

@@ -0,0 +1,2217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032,
+      "grad_norm": 9.582864761352539,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 4.5696,
+      "step": 2
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 8.04224967956543,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 4.6008,
+      "step": 4
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 5.386164665222168,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 4.4741,
+      "step": 6
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 6.327683925628662,
+      "learning_rate": 1.2698412698412699e-05,
+      "loss": 4.3362,
+      "step": 8
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 4.981070518493652,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 4.3088,
+      "step": 10
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 5.140510559082031,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 4.1842,
+      "step": 12
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 4.240128993988037,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 4.0743,
+      "step": 14
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 4.0903096199035645,
+      "learning_rate": 2.5396825396825397e-05,
+      "loss": 4.0638,
+      "step": 16
+    },
+    {
+      "epoch": 0.0288,
+      "grad_norm": 3.6583104133605957,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 3.8422,
+      "step": 18
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 4.4048027992248535,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 3.8378,
+      "step": 20
+    },
+    {
+      "epoch": 0.0352,
+      "grad_norm": 2.8964569568634033,
+      "learning_rate": 3.492063492063492e-05,
+      "loss": 3.8245,
+      "step": 22
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 4.253384113311768,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 3.7656,
+      "step": 24
+    },
+    {
+      "epoch": 0.0416,
+      "grad_norm": 2.827834367752075,
+      "learning_rate": 4.126984126984127e-05,
+      "loss": 3.4934,
+      "step": 26
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 3.3544514179229736,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 3.5784,
+      "step": 28
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 3.2228829860687256,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 3.5281,
+      "step": 30
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 2.926682472229004,
+      "learning_rate": 5.0793650793650794e-05,
+      "loss": 3.3777,
+      "step": 32
+    },
+    {
+      "epoch": 0.0544,
+      "grad_norm": 3.137467861175537,
+      "learning_rate": 5.396825396825397e-05,
+      "loss": 3.333,
+      "step": 34
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 3.6552820205688477,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 3.3148,
+      "step": 36
+    },
+    {
+      "epoch": 0.0608,
+      "grad_norm": 2.9889962673187256,
+      "learning_rate": 6.0317460317460316e-05,
+      "loss": 3.2377,
+      "step": 38
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.781177520751953,
+      "learning_rate": 6.349206349206349e-05,
+      "loss": 3.2271,
+      "step": 40
+    },
+    {
+      "epoch": 0.0672,
+      "grad_norm": 3.2072460651397705,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 3.1445,
+      "step": 42
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 2.859445333480835,
+      "learning_rate": 6.984126984126984e-05,
+      "loss": 3.0457,
+      "step": 44
+    },
+    {
+      "epoch": 0.0736,
+      "grad_norm": 4.333473205566406,
+      "learning_rate": 7.301587301587302e-05,
+      "loss": 3.1162,
+      "step": 46
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 3.8664698600769043,
+      "learning_rate": 7.619047619047618e-05,
+      "loss": 2.9101,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.0567679405212402,
+      "learning_rate": 7.936507936507937e-05,
+      "loss": 2.9774,
+      "step": 50
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 2.5626678466796875,
+      "learning_rate": 8.253968253968255e-05,
+      "loss": 3.0596,
+      "step": 52
+    },
+    {
+      "epoch": 0.0864,
+      "grad_norm": 3.4151525497436523,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 2.9537,
+      "step": 54
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 3.9550039768218994,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 2.8869,
+      "step": 56
+    },
+    {
+      "epoch": 0.0928,
+      "grad_norm": 3.560119867324829,
+      "learning_rate": 9.206349206349206e-05,
+      "loss": 2.8154,
+      "step": 58
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.9746081829071045,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 2.841,
+      "step": 60
+    },
+    {
+      "epoch": 0.0992,
+      "grad_norm": 2.8667147159576416,
+      "learning_rate": 9.841269841269841e-05,
+      "loss": 2.777,
+      "step": 62
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 2.7489001750946045,
+      "learning_rate": 9.99998248790669e-05,
+      "loss": 2.7027,
+      "step": 64
+    },
+    {
+      "epoch": 0.1056,
+      "grad_norm": 2.734243392944336,
+      "learning_rate": 9.999842391896222e-05,
+      "loss": 2.7284,
+      "step": 66
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 2.6667640209198,
+      "learning_rate": 9.999562203800676e-05,
+      "loss": 2.6692,
+      "step": 68
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 3.080273389816284,
+      "learning_rate": 9.999141931470729e-05,
+      "loss": 2.6861,
+      "step": 70
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 3.324246406555176,
+      "learning_rate": 9.998581586682116e-05,
+      "loss": 2.7227,
+      "step": 72
+    },
+    {
+      "epoch": 0.1184,
+      "grad_norm": 2.7069027423858643,
+      "learning_rate": 9.997881185135307e-05,
+      "loss": 2.5695,
+      "step": 74
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 2.781511068344116,
+      "learning_rate": 9.997040746455062e-05,
+      "loss": 2.5662,
+      "step": 76
+    },
+    {
+      "epoch": 0.1248,
+      "grad_norm": 2.453489303588867,
+      "learning_rate": 9.996060294189887e-05,
+      "loss": 2.7143,
+      "step": 78
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 2.8613131046295166,
+      "learning_rate": 9.994939855811362e-05,
+      "loss": 2.6042,
+      "step": 80
+    },
+    {
+      "epoch": 0.1312,
+      "grad_norm": 2.4560399055480957,
+      "learning_rate": 9.993679462713395e-05,
+      "loss": 2.6329,
+      "step": 82
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 3.461649179458618,
+      "learning_rate": 9.992279150211314e-05,
+      "loss": 2.5056,
+      "step": 84
+    },
+    {
+      "epoch": 0.1376,
+      "grad_norm": 2.901437997817993,
+      "learning_rate": 9.990738957540896e-05,
+      "loss": 2.5626,
+      "step": 86
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 2.5126583576202393,
+      "learning_rate": 9.989058927857263e-05,
+      "loss": 2.4684,
+      "step": 88
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.184246778488159,
+      "learning_rate": 9.987239108233668e-05,
+      "loss": 2.4756,
+      "step": 90
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": 3.1928048133850098,
+      "learning_rate": 9.985279549660185e-05,
+      "loss": 2.4961,
+      "step": 92
+    },
+    {
+      "epoch": 0.1504,
+      "grad_norm": 2.3420567512512207,
+      "learning_rate": 9.983180307042274e-05,
+      "loss": 2.3984,
+      "step": 94
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 3.066572427749634,
+      "learning_rate": 9.980941439199246e-05,
+      "loss": 2.5094,
+      "step": 96
+    },
+    {
+      "epoch": 0.1568,
+      "grad_norm": 2.7460713386535645,
+      "learning_rate": 9.97856300886261e-05,
+      "loss": 2.4763,
+      "step": 98
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.51401424407959,
+      "learning_rate": 9.976045082674319e-05,
+      "loss": 2.3846,
+      "step": 100
+    },
+    {
+      "epoch": 0.1632,
+      "grad_norm": 2.2191078662872314,
+      "learning_rate": 9.973387731184902e-05,
+      "loss": 2.36,
+      "step": 102
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 2.5087525844573975,
+      "learning_rate": 9.97059102885149e-05,
+      "loss": 2.4398,
+      "step": 104
+    },
+    {
+      "epoch": 0.1696,
+      "grad_norm": 2.396519184112549,
+      "learning_rate": 9.967655054035727e-05,
+      "loss": 2.459,
+      "step": 106
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 2.6870367527008057,
+      "learning_rate": 9.964579889001569e-05,
+      "loss": 2.3118,
+      "step": 108
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.317108392715454,
+      "learning_rate": 9.961365619912989e-05,
+      "loss": 2.3219,
+      "step": 110
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 2.2667131423950195,
+      "learning_rate": 9.95801233683156e-05,
+      "loss": 2.4226,
+      "step": 112
+    },
+    {
+      "epoch": 0.1824,
+      "grad_norm": 1.9936238527297974,
+      "learning_rate": 9.954520133713924e-05,
+      "loss": 2.4241,
+      "step": 114
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 2.6429572105407715,
+      "learning_rate": 9.950889108409172e-05,
+      "loss": 2.3513,
+      "step": 116
+    },
+    {
+      "epoch": 0.1888,
+      "grad_norm": 2.2465708255767822,
+      "learning_rate": 9.947119362656092e-05,
+      "loss": 2.2819,
+      "step": 118
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 3.0118119716644287,
+      "learning_rate": 9.94321100208032e-05,
+      "loss": 2.4245,
+      "step": 120
+    },
+    {
+      "epoch": 0.1952,
+      "grad_norm": 2.177351236343384,
+      "learning_rate": 9.939164136191384e-05,
+      "loss": 2.5335,
+      "step": 122
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 2.1183319091796875,
+      "learning_rate": 9.934978878379636e-05,
+      "loss": 2.3807,
+      "step": 124
+    },
+    {
+      "epoch": 0.2016,
+      "grad_norm": 2.0215203762054443,
+      "learning_rate": 9.930655345913071e-05,
+      "loss": 2.228,
+      "step": 126
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 2.589059591293335,
+      "learning_rate": 9.926193659934043e-05,
+      "loss": 2.3367,
+      "step": 128
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 2.5615551471710205,
+      "learning_rate": 9.921593945455869e-05,
+      "loss": 2.2462,
+      "step": 130
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 2.5255088806152344,
+      "learning_rate": 9.916856331359335e-05,
+      "loss": 2.2562,
+      "step": 132
+    },
+    {
+      "epoch": 0.2144,
+      "grad_norm": 2.201739549636841,
+      "learning_rate": 9.911980950389067e-05,
+      "loss": 2.3823,
+      "step": 134
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 2.3065388202667236,
+      "learning_rate": 9.906967939149831e-05,
+      "loss": 2.2231,
+      "step": 136
+    },
+    {
+      "epoch": 0.2208,
+      "grad_norm": 2.7823500633239746,
+      "learning_rate": 9.901817438102695e-05,
+      "loss": 2.2203,
+      "step": 138
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 2.521483898162842,
+      "learning_rate": 9.896529591561093e-05,
+      "loss": 2.4067,
+      "step": 140
+    },
+    {
+      "epoch": 0.2272,
+      "grad_norm": 2.114596128463745,
+      "learning_rate": 9.891104547686782e-05,
+      "loss": 2.2335,
+      "step": 142
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 2.151817560195923,
+      "learning_rate": 9.8855424584857e-05,
+      "loss": 2.2483,
+      "step": 144
+    },
+    {
+      "epoch": 0.2336,
+      "grad_norm": 2.050886392593384,
+      "learning_rate": 9.879843479803691e-05,
+      "loss": 2.2825,
+      "step": 146
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 2.388864278793335,
+      "learning_rate": 9.874007771322151e-05,
+      "loss": 2.3412,
+      "step": 148
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.22013258934021,
+      "learning_rate": 9.868035496553546e-05,
+      "loss": 2.1599,
+      "step": 150
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 2.0260703563690186,
+      "learning_rate": 9.86192682283684e-05,
+      "loss": 2.1551,
+      "step": 152
+    },
+    {
+      "epoch": 0.2464,
+      "grad_norm": 2.3314321041107178,
+      "learning_rate": 9.855681921332793e-05,
+      "loss": 2.2231,
+      "step": 154
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 2.6237032413482666,
+      "learning_rate": 9.849300967019175e-05,
+      "loss": 2.2275,
+      "step": 156
+    },
+    {
+      "epoch": 0.2528,
+      "grad_norm": 2.053867816925049,
+      "learning_rate": 9.84278413868586e-05,
+      "loss": 2.2417,
+      "step": 158
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.3856852054595947,
+      "learning_rate": 9.836131618929819e-05,
+      "loss": 2.2179,
+      "step": 160
+    },
+    {
+      "epoch": 0.2592,
+      "grad_norm": 1.919459342956543,
+      "learning_rate": 9.82934359415e-05,
+      "loss": 2.2195,
+      "step": 162
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 2.281283378601074,
+      "learning_rate": 9.822420254542108e-05,
+      "loss": 2.211,
+      "step": 164
+    },
+    {
+      "epoch": 0.2656,
+      "grad_norm": 1.97679603099823,
+      "learning_rate": 9.815361794093272e-05,
+      "loss": 2.1523,
+      "step": 166
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 2.190410852432251,
+      "learning_rate": 9.808168410576617e-05,
+      "loss": 2.179,
+      "step": 168
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 2.4369115829467773,
+      "learning_rate": 9.800840305545715e-05,
+      "loss": 2.2628,
+      "step": 170
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 1.9605038166046143,
+      "learning_rate": 9.793377684328939e-05,
+      "loss": 2.3508,
+      "step": 172
+    },
+    {
+      "epoch": 0.2784,
+      "grad_norm": 2.3224270343780518,
+      "learning_rate": 9.785780756023714e-05,
+      "loss": 2.1655,
+      "step": 174
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 2.045945167541504,
+      "learning_rate": 9.778049733490655e-05,
+      "loss": 2.2663,
+      "step": 176
+    },
+    {
+      "epoch": 0.2848,
+      "grad_norm": 2.2260525226593018,
+      "learning_rate": 9.770184833347606e-05,
+      "loss": 2.1685,
+      "step": 178
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.0497450828552246,
+      "learning_rate": 9.762186275963563e-05,
+      "loss": 2.1108,
+      "step": 180
+    },
+    {
+      "epoch": 0.2912,
+      "grad_norm": 2.2114014625549316,
+      "learning_rate": 9.754054285452506e-05,
+      "loss": 2.1031,
+      "step": 182
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 2.2554216384887695,
+      "learning_rate": 9.745789089667121e-05,
+      "loss": 2.2677,
+      "step": 184
+    },
+    {
+      "epoch": 0.2976,
+      "grad_norm": 1.8373414278030396,
+      "learning_rate": 9.737390920192408e-05,
+      "loss": 2.2118,
+      "step": 186
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 2.319699764251709,
+      "learning_rate": 9.7288600123392e-05,
+      "loss": 2.1008,
+      "step": 188
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 2.0968804359436035,
+      "learning_rate": 9.720196605137565e-05,
+      "loss": 2.1803,
+      "step": 190
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 2.0866589546203613,
+      "learning_rate": 9.71140094133011e-05,
+      "loss": 2.2203,
+      "step": 192
+    },
+    {
+      "epoch": 0.3104,
+      "grad_norm": 2.236036777496338,
+      "learning_rate": 9.702473267365182e-05,
+      "loss": 2.2041,
+      "step": 194
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 1.8478028774261475,
+      "learning_rate": 9.693413833389956e-05,
+      "loss": 2.0953,
+      "step": 196
+    },
+    {
+      "epoch": 0.3168,
+      "grad_norm": 2.449432849884033,
+      "learning_rate": 9.684222893243431e-05,
+      "loss": 2.2525,
+      "step": 198
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.9800256490707397,
+      "learning_rate": 9.674900704449324e-05,
+      "loss": 2.0962,
+      "step": 200
+    },
+    {
+      "epoch": 0.3232,
+      "grad_norm": 1.9219201803207397,
+      "learning_rate": 9.665447528208836e-05,
+      "loss": 2.0759,
+      "step": 202
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 2.214970350265503,
+      "learning_rate": 9.655863629393351e-05,
+      "loss": 2.0526,
+      "step": 204
+    },
+    {
+      "epoch": 0.3296,
+      "grad_norm": 2.141845226287842,
+      "learning_rate": 9.64614927653701e-05,
+      "loss": 2.0032,
+      "step": 206
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 2.117124319076538,
+      "learning_rate": 9.636304741829181e-05,
+      "loss": 2.1147,
+      "step": 208
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 2.2099063396453857,
+      "learning_rate": 9.626330301106837e-05,
+      "loss": 2.0526,
+      "step": 210
+    },
+    {
+      "epoch": 0.3392,
+      "grad_norm": 2.162337064743042,
+      "learning_rate": 9.616226233846828e-05,
+      "loss": 2.0378,
+      "step": 212
+    },
+    {
+      "epoch": 0.3424,
+      "grad_norm": 1.9509609937667847,
+      "learning_rate": 9.605992823158046e-05,
+      "loss": 2.2311,
+      "step": 214
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 2.105393171310425,
+      "learning_rate": 9.595630355773501e-05,
+      "loss": 2.0036,
+      "step": 216
+    },
+    {
+      "epoch": 0.3488,
+      "grad_norm": 2.210383176803589,
+      "learning_rate": 9.585139122042274e-05,
+      "loss": 2.1254,
+      "step": 218
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 2.3816072940826416,
+      "learning_rate": 9.574519415921396e-05,
+      "loss": 2.078,
+      "step": 220
+    },
+    {
+      "epoch": 0.3552,
+      "grad_norm": 2.019214153289795,
+      "learning_rate": 9.5637715349676e-05,
+      "loss": 2.1598,
+      "step": 222
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 2.09932804107666,
+      "learning_rate": 9.552895780328987e-05,
+      "loss": 2.0171,
+      "step": 224
+    },
+    {
+      "epoch": 0.3616,
+      "grad_norm": 1.85040283203125,
+      "learning_rate": 9.541892456736595e-05,
+      "loss": 2.2289,
+      "step": 226
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 2.067749261856079,
+      "learning_rate": 9.530761872495849e-05,
+      "loss": 2.064,
+      "step": 228
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.581606388092041,
+      "learning_rate": 9.519504339477932e-05,
+      "loss": 2.1191,
+      "step": 230
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 2.451923131942749,
+      "learning_rate": 9.508120173111039e-05,
+      "loss": 1.9523,
+      "step": 232
+    },
+    {
+      "epoch": 0.3744,
+      "grad_norm": 1.9244287014007568,
+      "learning_rate": 9.496609692371548e-05,
+      "loss": 2.0501,
+      "step": 234
+    },
+    {
+      "epoch": 0.3776,
+      "grad_norm": 2.272866725921631,
+      "learning_rate": 9.484973219775074e-05,
+      "loss": 1.9952,
+      "step": 236
+    },
+    {
+      "epoch": 0.3808,
+      "grad_norm": 2.396249294281006,
+      "learning_rate": 9.473211081367436e-05,
+      "loss": 2.0369,
+      "step": 238
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 1.967800259590149,
+      "learning_rate": 9.46132360671552e-05,
+      "loss": 2.0272,
+      "step": 240
+    },
+    {
+      "epoch": 0.3872,
+      "grad_norm": 2.252021312713623,
+      "learning_rate": 9.449311128898049e-05,
+      "loss": 1.9491,
+      "step": 242
+    },
+    {
+      "epoch": 0.3904,
+      "grad_norm": 2.425724506378174,
+      "learning_rate": 9.437173984496246e-05,
+      "loss": 2.076,
+      "step": 244
+    },
+    {
+      "epoch": 0.3936,
+      "grad_norm": 2.0590147972106934,
+      "learning_rate": 9.424912513584401e-05,
+      "loss": 2.1357,
+      "step": 246
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 2.0368545055389404,
+      "learning_rate": 9.412527059720352e-05,
+      "loss": 2.0673,
+      "step": 248
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.0116140842437744,
+      "learning_rate": 9.400017969935848e-05,
+      "loss": 1.9939,
+      "step": 250
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 1.872152328491211,
+      "learning_rate": 9.387385594726829e-05,
+      "loss": 1.9777,
+      "step": 252
+    },
+    {
+      "epoch": 0.4064,
+      "grad_norm": 2.1459996700286865,
+      "learning_rate": 9.374630288043614e-05,
+      "loss": 2.1791,
+      "step": 254
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 2.0004026889801025,
+      "learning_rate": 9.361752407280965e-05,
+      "loss": 2.069,
+      "step": 256
+    },
+    {
+      "epoch": 0.4128,
+      "grad_norm": 1.9468940496444702,
+      "learning_rate": 9.348752313268093e-05,
+      "loss": 1.9954,
+      "step": 258
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 1.9674925804138184,
+      "learning_rate": 9.335630370258533e-05,
+      "loss": 2.0868,
+      "step": 260
+    },
+    {
+      "epoch": 0.4192,
+      "grad_norm": 1.8100794553756714,
+      "learning_rate": 9.322386945919946e-05,
+      "loss": 1.8544,
+      "step": 262
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 1.7924424409866333,
+      "learning_rate": 9.309022411323816e-05,
+      "loss": 2.1337,
+      "step": 264
+    },
+    {
+      "epoch": 0.4256,
+      "grad_norm": 2.407942771911621,
+      "learning_rate": 9.295537140935049e-05,
+      "loss": 2.0707,
+      "step": 266
+    },
+    {
+      "epoch": 0.4288,
+      "grad_norm": 3.1549575328826904,
+      "learning_rate": 9.281931512601485e-05,
+      "loss": 2.0362,
+      "step": 268
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 2.299870491027832,
+      "learning_rate": 9.26820590754331e-05,
+      "loss": 1.9683,
+      "step": 270
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 2.0636281967163086,
+      "learning_rate": 9.254360710342371e-05,
+      "loss": 1.9565,
+      "step": 272
+    },
+    {
+      "epoch": 0.4384,
+      "grad_norm": 2.0548760890960693,
+      "learning_rate": 9.240396308931407e-05,
+      "loss": 1.9686,
+      "step": 274
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 2.189924955368042,
+      "learning_rate": 9.226313094583173e-05,
+      "loss": 2.0544,
+      "step": 276
+    },
+    {
+      "epoch": 0.4448,
+      "grad_norm": 1.7277733087539673,
+      "learning_rate": 9.212111461899479e-05,
+      "loss": 2.1443,
+      "step": 278
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 2.1883883476257324,
+      "learning_rate": 9.197791808800135e-05,
+      "loss": 1.9916,
+      "step": 280
+    },
+    {
+      "epoch": 0.4512,
+      "grad_norm": 2.1574831008911133,
+      "learning_rate": 9.183354536511803e-05,
+      "loss": 2.0649,
+      "step": 282
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 1.9589487314224243,
+      "learning_rate": 9.168800049556747e-05,
+      "loss": 1.9466,
+      "step": 284
+    },
+    {
+      "epoch": 0.4576,
+      "grad_norm": 2.365525007247925,
+      "learning_rate": 9.154128755741509e-05,
+      "loss": 1.9666,
+      "step": 286
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 1.946046233177185,
+      "learning_rate": 9.139341066145472e-05,
+      "loss": 1.9854,
+      "step": 288
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 2.5430924892425537,
+      "learning_rate": 9.124437395109353e-05,
+      "loss": 1.9625,
+      "step": 290
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 2.154215097427368,
+      "learning_rate": 9.109418160223585e-05,
+      "loss": 1.9279,
+      "step": 292
+    },
+    {
+      "epoch": 0.4704,
+      "grad_norm": 2.0101840496063232,
+      "learning_rate": 9.094283782316619e-05,
+      "loss": 1.8481,
+      "step": 294
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 2.403233051300049,
+      "learning_rate": 9.079034685443133e-05,
+      "loss": 1.9778,
+      "step": 296
+    },
+    {
+      "epoch": 0.4768,
+      "grad_norm": 1.8693294525146484,
+      "learning_rate": 9.063671296872149e-05,
+      "loss": 1.8872,
+      "step": 298
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8005255460739136,
+      "learning_rate": 9.048194047075069e-05,
+      "loss": 1.9892,
+      "step": 300
+    },
+    {
+      "epoch": 0.4832,
+      "grad_norm": 1.8485512733459473,
+      "learning_rate": 9.032603369713596e-05,
+      "loss": 1.7879,
+      "step": 302
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 2.034468650817871,
+      "learning_rate": 9.016899701627604e-05,
+      "loss": 1.9269,
+      "step": 304
+    },
+    {
+      "epoch": 0.4896,
+      "grad_norm": 1.8233674764633179,
+      "learning_rate": 9.00108348282288e-05,
+      "loss": 2.0422,
+      "step": 306
+    },
+    {
+      "epoch": 0.4928,
+      "grad_norm": 2.109724998474121,
+      "learning_rate": 8.985155156458811e-05,
+      "loss": 1.8479,
+      "step": 308
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 2.107543468475342,
+      "learning_rate": 8.969115168835954e-05,
+      "loss": 1.9216,
+      "step": 310
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 1.83890700340271,
+      "learning_rate": 8.952963969383538e-05,
+      "loss": 1.8112,
+      "step": 312
+    },
+    {
+      "epoch": 0.5024,
+      "grad_norm": 1.8299955129623413,
+      "learning_rate": 8.93670201064687e-05,
+      "loss": 2.0874,
+      "step": 314
+    },
+    {
+      "epoch": 0.5056,
+      "grad_norm": 1.7529444694519043,
+      "learning_rate": 8.920329748274649e-05,
+      "loss": 1.9491,
+      "step": 316
+    },
+    {
+      "epoch": 0.5088,
+      "grad_norm": 2.1236982345581055,
+      "learning_rate": 8.903847641006218e-05,
+      "loss": 1.9849,
+      "step": 318
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.9501066207885742,
+      "learning_rate": 8.887256150658684e-05,
+      "loss": 1.8132,
+      "step": 320
+    },
+    {
+      "epoch": 0.5152,
+      "grad_norm": 2.057251214981079,
+      "learning_rate": 8.870555742113998e-05,
+      "loss": 1.8913,
+      "step": 322
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 1.5886375904083252,
+      "learning_rate": 8.85374688330592e-05,
+      "loss": 1.9817,
+      "step": 324
+    },
+    {
+      "epoch": 0.5216,
+      "grad_norm": 2.109905242919922,
+      "learning_rate": 8.836830045206911e-05,
+      "loss": 1.908,
+      "step": 326
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 1.9238070249557495,
+      "learning_rate": 8.81980570181494e-05,
+      "loss": 2.1003,
+      "step": 328
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 1.7516288757324219,
+      "learning_rate": 8.802674330140192e-05,
+      "loss": 1.8825,
+      "step": 330
+    },
+    {
+      "epoch": 0.5312,
+      "grad_norm": 1.7113988399505615,
+      "learning_rate": 8.785436410191714e-05,
+      "loss": 1.8977,
+      "step": 332
+    },
+    {
+      "epoch": 0.5344,
+      "grad_norm": 1.919970154762268,
+      "learning_rate": 8.76809242496396e-05,
+      "loss": 2.0056,
+      "step": 334
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 1.8441989421844482,
+      "learning_rate": 8.750642860423262e-05,
+      "loss": 1.9522,
+      "step": 336
+    },
+    {
+      "epoch": 0.5408,
+      "grad_norm": 2.240172863006592,
+      "learning_rate": 8.733088205494205e-05,
+      "loss": 2.0764,
+      "step": 338
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 1.7431479692459106,
+      "learning_rate": 8.715428952045936e-05,
+      "loss": 2.0673,
+      "step": 340
+    },
+    {
+      "epoch": 0.5472,
+      "grad_norm": 1.7653355598449707,
+      "learning_rate": 8.697665594878382e-05,
+      "loss": 1.8442,
+      "step": 342
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 2.4551286697387695,
+      "learning_rate": 8.679798631708375e-05,
+      "loss": 2.0315,
+      "step": 344
+    },
+    {
+      "epoch": 0.5536,
+      "grad_norm": 1.743158221244812,
+      "learning_rate": 8.661828563155727e-05,
+      "loss": 2.0135,
+      "step": 346
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 1.7268255949020386,
+      "learning_rate": 8.643755892729179e-05,
+      "loss": 2.0524,
+      "step": 348
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.032898426055908,
+      "learning_rate": 8.625581126812312e-05,
+      "loss": 1.9173,
+      "step": 350
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 2.1082491874694824,
+      "learning_rate": 8.607304774649349e-05,
+      "loss": 2.0753,
+      "step": 352
+    },
+    {
+      "epoch": 0.5664,
+      "grad_norm": 1.8048080205917358,
+      "learning_rate": 8.588927348330887e-05,
+      "loss": 1.8533,
+      "step": 354
+    },
+    {
+      "epoch": 0.5696,
+      "grad_norm": 1.8337701559066772,
+      "learning_rate": 8.57044936277955e-05,
+      "loss": 1.9847,
+      "step": 356
+    },
+    {
+      "epoch": 0.5728,
+      "grad_norm": 1.898160457611084,
+      "learning_rate": 8.551871335735565e-05,
+      "loss": 1.8207,
+      "step": 358
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 1.672937273979187,
+      "learning_rate": 8.533193787742251e-05,
+      "loss": 1.8368,
+      "step": 360
+    },
+    {
+      "epoch": 0.5792,
+      "grad_norm": 1.9867445230484009,
+      "learning_rate": 8.51441724213143e-05,
+      "loss": 1.9168,
+      "step": 362
+    },
+    {
+      "epoch": 0.5824,
+      "grad_norm": 1.8571895360946655,
+      "learning_rate": 8.495542225008771e-05,
+      "loss": 1.8886,
+      "step": 364
+    },
+    {
+      "epoch": 0.5856,
+      "grad_norm": 1.8292155265808105,
+      "learning_rate": 8.476569265239046e-05,
+      "loss": 1.8527,
+      "step": 366
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 1.817756175994873,
+      "learning_rate": 8.457498894431311e-05,
+      "loss": 1.843,
+      "step": 368
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 1.9946959018707275,
+      "learning_rate": 8.438331646924013e-05,
+      "loss": 1.8689,
+      "step": 370
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 1.6774402856826782,
+      "learning_rate": 8.419068059770011e-05,
+      "loss": 1.9314,
+      "step": 372
+    },
+    {
+      "epoch": 0.5984,
+      "grad_norm": 1.7767459154129028,
+      "learning_rate": 8.399708672721539e-05,
+      "loss": 1.8765,
+      "step": 374
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 2.1188535690307617,
+      "learning_rate": 8.380254028215076e-05,
+      "loss": 1.9367,
+      "step": 376
+    },
+    {
+      "epoch": 0.6048,
+      "grad_norm": 1.9462740421295166,
+      "learning_rate": 8.360704671356145e-05,
+      "loss": 1.8991,
+      "step": 378
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 1.850533127784729,
+      "learning_rate": 8.341061149904045e-05,
+      "loss": 2.0175,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112,
+      "grad_norm": 1.957470178604126,
+      "learning_rate": 8.321324014256504e-05,
+      "loss": 1.9628,
+      "step": 382
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 1.9237133264541626,
+      "learning_rate": 8.30149381743425e-05,
+      "loss": 1.9568,
+      "step": 384
+    },
+    {
+      "epoch": 0.6176,
+      "grad_norm": 2.103835105895996,
+      "learning_rate": 8.28157111506552e-05,
+      "loss": 1.932,
+      "step": 386
+    },
+    {
+      "epoch": 0.6208,
+      "grad_norm": 1.685325264930725,
+      "learning_rate": 8.261556465370493e-05,
+      "loss": 2.0071,
+      "step": 388
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 1.9392411708831787,
+      "learning_rate": 8.24145042914565e-05,
+      "loss": 1.8254,
+      "step": 390
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 1.759429931640625,
+      "learning_rate": 8.221253569748055e-05,
+      "loss": 1.7943,
+      "step": 392
+    },
+    {
+      "epoch": 0.6304,
+      "grad_norm": 1.9010182619094849,
+      "learning_rate": 8.200966453079575e-05,
+      "loss": 1.9736,
+      "step": 394
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 1.859298586845398,
+      "learning_rate": 8.180589647571023e-05,
+      "loss": 2.0887,
+      "step": 396
+    },
+    {
+      "epoch": 0.6368,
+      "grad_norm": 1.9668726921081543,
+      "learning_rate": 8.16012372416623e-05,
+      "loss": 1.8353,
+      "step": 398
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.8924115896224976,
+      "learning_rate": 8.13956925630605e-05,
+      "loss": 1.8227,
+      "step": 400
+    },
+    {
+      "epoch": 0.6432,
+      "grad_norm": 2.260485887527466,
+      "learning_rate": 8.118926819912287e-05,
+      "loss": 1.9317,
+      "step": 402
+    },
+    {
+      "epoch": 0.6464,
+      "grad_norm": 1.7944382429122925,
+      "learning_rate": 8.098196993371565e-05,
+      "loss": 1.92,
+      "step": 404
+    },
+    {
+      "epoch": 0.6496,
+      "grad_norm": 1.6864358186721802,
+      "learning_rate": 8.077380357519115e-05,
+      "loss": 1.8648,
+      "step": 406
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 1.7029087543487549,
+      "learning_rate": 8.056477495622511e-05,
+      "loss": 2.1089,
+      "step": 408
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 2.3869247436523438,
+      "learning_rate": 8.035488993365312e-05,
+      "loss": 1.8285,
+      "step": 410
+    },
+    {
+      "epoch": 0.6592,
+      "grad_norm": 1.8005602359771729,
+      "learning_rate": 8.014415438830667e-05,
+      "loss": 1.9826,
+      "step": 412
+    },
+    {
+      "epoch": 0.6624,
+      "grad_norm": 2.076176881790161,
+      "learning_rate": 7.993257422484826e-05,
+      "loss": 1.8091,
+      "step": 414
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 1.6236470937728882,
+      "learning_rate": 7.972015537160602e-05,
+      "loss": 1.9846,
+      "step": 416
+    },
+    {
+      "epoch": 0.6688,
+      "grad_norm": 1.7574564218521118,
+      "learning_rate": 7.950690378040758e-05,
+      "loss": 2.0633,
+      "step": 418
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 1.8413279056549072,
+      "learning_rate": 7.929282542641325e-05,
+      "loss": 1.7691,
+      "step": 420
+    },
+    {
+      "epoch": 0.6752,
+      "grad_norm": 1.750153660774231,
+      "learning_rate": 7.907792630794876e-05,
+      "loss": 1.724,
+      "step": 422
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 1.9424185752868652,
+      "learning_rate": 7.886221244633703e-05,
+      "loss": 1.8961,
+      "step": 424
+    },
+    {
+      "epoch": 0.6816,
+      "grad_norm": 1.8231415748596191,
+      "learning_rate": 7.864568988572947e-05,
+      "loss": 1.9455,
+      "step": 426
+    },
+    {
+      "epoch": 0.6848,
+      "grad_norm": 1.9073402881622314,
+      "learning_rate": 7.842836469293673e-05,
+      "loss": 1.7979,
+      "step": 428
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 1.8199973106384277,
+      "learning_rate": 7.821024295725865e-05,
+      "loss": 1.8819,
+      "step": 430
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 2.1633074283599854,
+      "learning_rate": 7.79913307903136e-05,
+      "loss": 1.8375,
+      "step": 432
+    },
+    {
+      "epoch": 0.6944,
+      "grad_norm": 2.62290620803833,
+      "learning_rate": 7.777163432586734e-05,
+      "loss": 1.8191,
+      "step": 434
+    },
+    {
+      "epoch": 0.6976,
+      "grad_norm": 1.9004080295562744,
+      "learning_rate": 7.755115971966104e-05,
+      "loss": 1.8747,
+      "step": 436
+    },
+    {
+      "epoch": 0.7008,
+      "grad_norm": 2.1421079635620117,
+      "learning_rate": 7.732991314923891e-05,
+      "loss": 1.804,
+      "step": 438
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 1.7792892456054688,
+      "learning_rate": 7.710790081377502e-05,
+      "loss": 1.8574,
+      "step": 440
+    },
+    {
+      "epoch": 0.7072,
+      "grad_norm": 1.7586500644683838,
+      "learning_rate": 7.688512893389964e-05,
+      "loss": 1.7981,
+      "step": 442
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 1.8390204906463623,
+      "learning_rate": 7.666160375152496e-05,
+      "loss": 1.9504,
+      "step": 444
+    },
+    {
+      "epoch": 0.7136,
+      "grad_norm": 1.8994488716125488,
+      "learning_rate": 7.643733152967019e-05,
+      "loss": 1.8502,
+      "step": 446
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 1.869563102722168,
+      "learning_rate": 7.621231855228604e-05,
+      "loss": 2.0965,
+      "step": 448
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.0518429279327393,
+      "learning_rate": 7.598657112407865e-05,
+      "loss": 1.821,
+      "step": 450
+    },
+    {
+      "epoch": 0.7232,
+      "grad_norm": 1.7781238555908203,
+      "learning_rate": 7.576009557033304e-05,
+      "loss": 2.1547,
+      "step": 452
+    },
+    {
+      "epoch": 0.7264,
+      "grad_norm": 1.897527813911438,
+      "learning_rate": 7.553289823673568e-05,
+      "loss": 1.905,
+      "step": 454
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 1.7613269090652466,
+      "learning_rate": 7.530498548919693e-05,
+      "loss": 1.7703,
+      "step": 456
+    },
+    {
+      "epoch": 0.7328,
+      "grad_norm": 2.0733559131622314,
+      "learning_rate": 7.507636371367246e-05,
+      "loss": 1.7406,
+      "step": 458
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 1.6685259342193604,
+      "learning_rate": 7.484703931598445e-05,
+      "loss": 2.008,
+      "step": 460
+    },
+    {
+      "epoch": 0.7392,
+      "grad_norm": 1.7001707553863525,
+      "learning_rate": 7.461701872164204e-05,
+      "loss": 1.8958,
+      "step": 462
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 1.6040148735046387,
+      "learning_rate": 7.438630837566133e-05,
+      "loss": 1.8792,
+      "step": 464
+    },
+    {
+      "epoch": 0.7456,
+      "grad_norm": 1.8001751899719238,
+      "learning_rate": 7.415491474238475e-05,
+      "loss": 1.9369,
+      "step": 466
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 1.7213135957717896,
+      "learning_rate": 7.39228443053e-05,
+      "loss": 1.9091,
+      "step": 468
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 1.8896820545196533,
+      "learning_rate": 7.369010356685833e-05,
+      "loss": 1.7765,
+      "step": 470
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 1.9900362491607666,
+      "learning_rate": 7.345669904829237e-05,
+      "loss": 1.8875,
+      "step": 472
+    },
+    {
+      "epoch": 0.7584,
+      "grad_norm": 1.7322590351104736,
+      "learning_rate": 7.32226372894334e-05,
+      "loss": 1.9698,
+      "step": 474
+    },
+    {
+      "epoch": 0.7616,
+      "grad_norm": 1.7330385446548462,
+      "learning_rate": 7.298792484852808e-05,
+      "loss": 1.8868,
+      "step": 476
+    },
+    {
+      "epoch": 0.7648,
+      "grad_norm": 1.7039341926574707,
+      "learning_rate": 7.27525683020548e-05,
+      "loss": 1.7435,
+      "step": 478
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.421879529953003,
+      "learning_rate": 7.251657424453928e-05,
+      "loss": 2.065,
+      "step": 480
+    },
+    {
+      "epoch": 0.7712,
+      "grad_norm": 1.754511833190918,
+      "learning_rate": 7.227994928836988e-05,
+      "loss": 1.8281,
+      "step": 482
+    },
+    {
+      "epoch": 0.7744,
+      "grad_norm": 1.6815738677978516,
+      "learning_rate": 7.204270006361228e-05,
+      "loss": 1.9892,
+      "step": 484
+    },
+    {
+      "epoch": 0.7776,
+      "grad_norm": 1.944504976272583,
+      "learning_rate": 7.180483321782374e-05,
+      "loss": 1.936,
+      "step": 486
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 1.8897745609283447,
+      "learning_rate": 7.156635541586682e-05,
+      "loss": 1.8541,
+      "step": 488
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 1.7814854383468628,
+      "learning_rate": 7.132727333972265e-05,
+      "loss": 1.7648,
+      "step": 490
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 2.232374906539917,
+      "learning_rate": 7.108759368830371e-05,
+      "loss": 1.7671,
+      "step": 492
+    },
+    {
+      "epoch": 0.7904,
+      "grad_norm": 1.7056297063827515,
+      "learning_rate": 7.084732317726611e-05,
+      "loss": 1.837,
+      "step": 494
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 1.651081919670105,
+      "learning_rate": 7.060646853882145e-05,
+      "loss": 1.9683,
+      "step": 496
+    },
+    {
+      "epoch": 0.7968,
+      "grad_norm": 1.8357526063919067,
+      "learning_rate": 7.036503652154812e-05,
+      "loss": 1.8938,
+      "step": 498
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5519391298294067,
+      "learning_rate": 7.012303389020234e-05,
+      "loss": 1.8466,
+      "step": 500
+    },
+    {
+      "epoch": 0.8032,
+      "grad_norm": 1.894633412361145,
+      "learning_rate": 6.988046742552845e-05,
+      "loss": 1.8514,
+      "step": 502
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 1.754236102104187,
+      "learning_rate": 6.963734392406907e-05,
+      "loss": 1.935,
+      "step": 504
+    },
+    {
+      "epoch": 0.8096,
+      "grad_norm": 1.702377438545227,
+      "learning_rate": 6.93936701979746e-05,
+      "loss": 1.8913,
+      "step": 506
+    },
+    {
+      "epoch": 0.8128,
+      "grad_norm": 2.0201923847198486,
+      "learning_rate": 6.914945307481228e-05,
+      "loss": 1.893,
+      "step": 508
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 1.64589524269104,
+      "learning_rate": 6.890469939737506e-05,
+      "loss": 1.8145,
+      "step": 510
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 1.6376056671142578,
+      "learning_rate": 6.865941602348966e-05,
+      "loss": 1.7757,
+      "step": 512
+    },
+    {
+      "epoch": 0.8224,
+      "grad_norm": 1.746893286705017,
+      "learning_rate": 6.841360982582463e-05,
+      "loss": 2.0359,
+      "step": 514
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 1.8241147994995117,
+      "learning_rate": 6.816728769169757e-05,
+      "loss": 1.8158,
+      "step": 516
+    },
+    {
+      "epoch": 0.8288,
+      "grad_norm": 1.8170113563537598,
+      "learning_rate": 6.792045652288234e-05,
+      "loss": 1.9136,
+      "step": 518
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 1.9374558925628662,
+      "learning_rate": 6.767312323541555e-05,
+      "loss": 1.8295,
+      "step": 520
+    },
+    {
+      "epoch": 0.8352,
+      "grad_norm": 1.7372517585754395,
+      "learning_rate": 6.742529475940284e-05,
+      "loss": 1.7011,
+      "step": 522
+    },
+    {
+      "epoch": 0.8384,
+      "grad_norm": 1.785727858543396,
+      "learning_rate": 6.717697803882467e-05,
+      "loss": 1.9221,
+      "step": 524
+    },
+    {
+      "epoch": 0.8416,
+      "grad_norm": 1.8377923965454102,
+      "learning_rate": 6.692818003134184e-05,
+      "loss": 1.9293,
+      "step": 526
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 1.8372453451156616,
+      "learning_rate": 6.667890770810035e-05,
+      "loss": 1.7977,
+      "step": 528
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 1.6308479309082031,
+      "learning_rate": 6.64291680535363e-05,
+      "loss": 1.8136,
+      "step": 530
+    },
+    {
+      "epoch": 0.8512,
+      "grad_norm": 1.6363590955734253,
+      "learning_rate": 6.617896806518005e-05,
+      "loss": 1.766,
+      "step": 532
+    },
+    {
+      "epoch": 0.8544,
+      "grad_norm": 1.8008592128753662,
+      "learning_rate": 6.592831475346018e-05,
+      "loss": 1.8626,
+      "step": 534
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 1.5823259353637695,
+      "learning_rate": 6.56772151415071e-05,
+      "loss": 1.6812,
+      "step": 536
+    },
+    {
+      "epoch": 0.8608,
+      "grad_norm": 1.6105380058288574,
+      "learning_rate": 6.542567626495619e-05,
+      "loss": 1.8237,
+      "step": 538
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 1.5150834321975708,
+      "learning_rate": 6.517370517175081e-05,
+      "loss": 1.8367,
+      "step": 540
+    },
+    {
+      "epoch": 0.8672,
+      "grad_norm": 1.796002984046936,
+      "learning_rate": 6.492130892194461e-05,
+      "loss": 2.0477,
+      "step": 542
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 1.647668480873108,
+      "learning_rate": 6.466849458750394e-05,
+      "loss": 2.0732,
+      "step": 544
+    },
+    {
+      "epoch": 0.8736,
+      "grad_norm": 1.5862977504730225,
+      "learning_rate": 6.441526925210949e-05,
+      "loss": 1.9539,
+      "step": 546
+    },
+    {
+      "epoch": 0.8768,
+      "grad_norm": 2.1107430458068848,
+      "learning_rate": 6.416164001095799e-05,
+      "loss": 1.8033,
+      "step": 548
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.886512041091919,
+      "learning_rate": 6.390761397056328e-05,
+      "loss": 1.7506,
+      "step": 550
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 1.6387286186218262,
+      "learning_rate": 6.365319824855727e-05,
+      "loss": 1.7166,
+      "step": 552
+    },
+    {
+      "epoch": 0.8864,
+      "grad_norm": 1.720944881439209,
+      "learning_rate": 6.339839997349045e-05,
+      "loss": 1.955,
+      "step": 554
+    },
+    {
+      "epoch": 0.8896,
+      "grad_norm": 1.8100652694702148,
+      "learning_rate": 6.314322628463219e-05,
+      "loss": 1.7356,
+      "step": 556
+    },
+    {
+      "epoch": 0.8928,
+      "grad_norm": 1.7271335124969482,
+      "learning_rate": 6.288768433177068e-05,
+      "loss": 1.8124,
+      "step": 558
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 1.8463622331619263,
+      "learning_rate": 6.26317812750126e-05,
+      "loss": 1.8924,
+      "step": 560
+    },
+    {
+      "epoch": 0.8992,
+      "grad_norm": 1.612862467765808,
+      "learning_rate": 6.237552428458256e-05,
+      "loss": 1.8984,
+      "step": 562
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 1.618046760559082,
+      "learning_rate": 6.21189205406221e-05,
+      "loss": 1.8639,
+      "step": 564
+    },
+    {
+      "epoch": 0.9056,
+      "grad_norm": 1.8677492141723633,
+      "learning_rate": 6.186197723298855e-05,
+      "loss": 1.9007,
+      "step": 566
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 1.5078552961349487,
+      "learning_rate": 6.160470156105362e-05,
+      "loss": 1.7474,
+      "step": 568
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 1.8413493633270264,
+      "learning_rate": 6.134710073350156e-05,
+      "loss": 1.7687,
+      "step": 570
+    },
+    {
+      "epoch": 0.9152,
+      "grad_norm": 1.6803293228149414,
+      "learning_rate": 6.108918196812734e-05,
+      "loss": 1.8477,
+      "step": 572
+    },
+    {
+      "epoch": 0.9184,
+      "grad_norm": 1.6897441148757935,
+      "learning_rate": 6.083095249163424e-05,
+      "loss": 1.7068,
+      "step": 574
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 1.6542898416519165,
+      "learning_rate": 6.057241953943154e-05,
+      "loss": 1.8733,
+      "step": 576
+    },
+    {
+      "epoch": 0.9248,
+      "grad_norm": 1.6907879114151,
+      "learning_rate": 6.031359035543158e-05,
+      "loss": 2.1063,
+      "step": 578
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 1.8007756471633911,
+      "learning_rate": 6.005447219184702e-05,
+      "loss": 1.8521,
+      "step": 580
+    },
+    {
+      "epoch": 0.9312,
+      "grad_norm": 1.7871769666671753,
+      "learning_rate": 5.9795072308987485e-05,
+      "loss": 1.7819,
+      "step": 582
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 1.678968071937561,
+      "learning_rate": 5.9535397975056154e-05,
+      "loss": 1.9387,
+      "step": 584
+    },
+    {
+      "epoch": 0.9376,
+      "grad_norm": 1.6597601175308228,
+      "learning_rate": 5.927545646594617e-05,
+      "loss": 1.825,
+      "step": 586
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 1.8375909328460693,
+      "learning_rate": 5.901525506503668e-05,
+      "loss": 1.8603,
+      "step": 588
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 1.7722874879837036,
+      "learning_rate": 5.87548010629889e-05,
+      "loss": 1.88,
+      "step": 590
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 1.6075280904769897,
+      "learning_rate": 5.8494101757541676e-05,
+      "loss": 1.7607,
+      "step": 592
+    },
+    {
+      "epoch": 0.9504,
+      "grad_norm": 1.7452820539474487,
+      "learning_rate": 5.8233164453307156e-05,
+      "loss": 1.8466,
+      "step": 594
+    },
+    {
+      "epoch": 0.9536,
+      "grad_norm": 1.6466399431228638,
+      "learning_rate": 5.797199646156596e-05,
+      "loss": 1.8487,
+      "step": 596
+    },
+    {
+      "epoch": 0.9568,
+      "grad_norm": 1.5579028129577637,
+      "learning_rate": 5.7710605100062485e-05,
+      "loss": 1.6981,
+      "step": 598
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6615177392959595,
+      "learning_rate": 5.7448997692799764e-05,
+      "loss": 1.9517,
+      "step": 600
+    },
+    {
+      "epoch": 0.9632,
+      "grad_norm": 1.6678462028503418,
+      "learning_rate": 5.718718156983428e-05,
+      "loss": 1.7882,
+      "step": 602
+    },
+    {
+      "epoch": 0.9664,
+      "grad_norm": 1.4700486660003662,
+      "learning_rate": 5.69251640670706e-05,
+      "loss": 1.7402,
+      "step": 604
+    },
+    {
+      "epoch": 0.9696,
+      "grad_norm": 1.5739563703536987,
+      "learning_rate": 5.6662952526055793e-05,
+      "loss": 1.843,
+      "step": 606
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 1.6076737642288208,
+      "learning_rate": 5.6400554293773744e-05,
+      "loss": 1.8319,
+      "step": 608
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 1.5903165340423584,
+      "learning_rate": 5.61379767224393e-05,
+      "loss": 1.7108,
+      "step": 610
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 1.6222702264785767,
+      "learning_rate": 5.587522716929228e-05,
+      "loss": 1.7096,
+      "step": 612
+    },
+    {
+      "epoch": 0.9824,
+      "grad_norm": 1.4682416915893555,
+      "learning_rate": 5.561231299639127e-05,
+      "loss": 1.7172,
+      "step": 614
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 1.542601466178894,
+      "learning_rate": 5.534924157040745e-05,
+      "loss": 1.9472,
+      "step": 616
+    },
+    {
+      "epoch": 0.9888,
+      "grad_norm": 1.862457513809204,
+      "learning_rate": 5.508602026241807e-05,
+      "loss": 1.7044,
+      "step": 618
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 1.7092889547348022,
+      "learning_rate": 5.482265644769998e-05,
+      "loss": 1.8067,
+      "step": 620
+    },
+    {
+      "epoch": 0.9952,
+      "grad_norm": 1.7380741834640503,
+      "learning_rate": 5.4559157505522985e-05,
+      "loss": 1.7857,
+      "step": 622
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 2.111462116241455,
+      "learning_rate": 5.429553081894304e-05,
+      "loss": 1.7447,
+      "step": 624
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 625,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0566821953614643e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-625/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a14ce667645cb7eeac31bbc81a8901ccab3bd9ee5946b30f64493f6131819cf
+size 5432

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-mag_Deva-coli-focus/",
+  "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:d1331a6f57197de8ca593bf68012c6e1e84c05cb32456a5be00fdf5298929fcc
+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 sha256:0028b6bd4c1142e0db2ef947bc0b3995e992cd9ef7d53c27fe63ee4fce5c6038
+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 sha256:4a14ce667645cb7eeac31bbc81a8901ccab3bd9ee5946b30f64493f6131819cf
+size 5432