Upload folder using huggingface_hub

checkpoint-1628/config.json

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

checkpoint-1628/generation_config.json

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

checkpoint-1628/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034c747954dfc5929edfeb1bf860f8798f063adc1dc0ef549ca6126107079e7e
+size 4950070472

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2a54dccfae7d16cab544c00d4a49ba6760c28e81adad87271da71096a67e12
+size 4614509080

checkpoint-1628/model.safetensors.index.json

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

checkpoint-1628/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f24fa3aaaccd25174788d5d49e813bdac5afba67139f7428afcaa145bad015
+size 13055369358

checkpoint-1628/rng_state.pth

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

checkpoint-1628/scheduler.pt

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

checkpoint-1628/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d82c066c91a79366b3e96e9c460da879e9a732d59289e5adf55018f93502588
+size 5432

checkpoint-814/config.json

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

checkpoint-814/generation_config.json

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

checkpoint-814/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d786c78b55ee8f24010e1d0f8a6fab0ff95485f7f4c91d1d03b8f4fad2ca2b
+size 4950070472

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb56d7502c0eb78c7004de3c67533cb2a8e88cb0d8ca0fe8304dfb0c473aba32
+size 4614509080

checkpoint-814/model.safetensors.index.json

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

checkpoint-814/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39d11a44c91ef5e252481016a22a9096a534d6d96acdcf1a986adbbebb9ded4
+size 13055369358

checkpoint-814/rng_state.pth

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

checkpoint-814/scheduler.pt

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

checkpoint-814/trainer_state.json

@@ -0,0 +1,2882 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002457002457002457,
+      "grad_norm": 4.019700050354004,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 6.2086,
+      "step": 2
+    },
+    {
+      "epoch": 0.004914004914004914,
+      "grad_norm": 4.2945332527160645,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 6.1853,
+      "step": 4
+    },
+    {
+      "epoch": 0.007371007371007371,
+      "grad_norm": 3.930802583694458,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 6.38,
+      "step": 6
+    },
+    {
+      "epoch": 0.009828009828009828,
+      "grad_norm": 3.6977317333221436,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 6.1601,
+      "step": 8
+    },
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 25.07744789123535,
+      "learning_rate": 1.2195121951219513e-05,
+      "loss": 6.5514,
+      "step": 10
+    },
+    {
+      "epoch": 0.014742014742014743,
+      "grad_norm": 3.566401720046997,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 5.6854,
+      "step": 12
+    },
+    {
+      "epoch": 0.0171990171990172,
+      "grad_norm": 24.404541015625,
+      "learning_rate": 1.707317073170732e-05,
+      "loss": 5.8838,
+      "step": 14
+    },
+    {
+      "epoch": 0.019656019656019656,
+      "grad_norm": 3.1777548789978027,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 5.3108,
+      "step": 16
+    },
+    {
+      "epoch": 0.022113022113022112,
+      "grad_norm": 2.769148349761963,
+      "learning_rate": 2.1951219512195124e-05,
+      "loss": 4.8014,
+      "step": 18
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 3.1796083450317383,
+      "learning_rate": 2.4390243902439026e-05,
+      "loss": 5.3203,
+      "step": 20
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 3.617638349533081,
+      "learning_rate": 2.682926829268293e-05,
+      "loss": 5.5772,
+      "step": 22
+    },
+    {
+      "epoch": 0.029484029484029485,
+      "grad_norm": 7.00071382522583,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 5.0532,
+      "step": 24
+    },
+    {
+      "epoch": 0.03194103194103194,
+      "grad_norm": 3.52091908454895,
+      "learning_rate": 3.170731707317073e-05,
+      "loss": 5.1329,
+      "step": 26
+    },
+    {
+      "epoch": 0.0343980343980344,
+      "grad_norm": 3.3309226036071777,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 4.6793,
+      "step": 28
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 2.865582227706909,
+      "learning_rate": 3.6585365853658535e-05,
+      "loss": 4.5865,
+      "step": 30
+    },
+    {
+      "epoch": 0.03931203931203931,
+      "grad_norm": 3.092682123184204,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 4.4673,
+      "step": 32
+    },
+    {
+      "epoch": 0.04176904176904177,
+      "grad_norm": 2.843824863433838,
+      "learning_rate": 4.146341463414634e-05,
+      "loss": 4.4617,
+      "step": 34
+    },
+    {
+      "epoch": 0.044226044226044224,
+      "grad_norm": 3.029207229614258,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 4.394,
+      "step": 36
+    },
+    {
+      "epoch": 0.04668304668304668,
+      "grad_norm": 2.6937527656555176,
+      "learning_rate": 4.634146341463415e-05,
+      "loss": 4.1312,
+      "step": 38
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 205.6438751220703,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 4.1717,
+      "step": 40
+    },
+    {
+      "epoch": 0.051597051597051594,
+      "grad_norm": 2.583071708679199,
+      "learning_rate": 5.121951219512195e-05,
+      "loss": 4.2337,
+      "step": 42
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 2.7350614070892334,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 4.2223,
+      "step": 44
+    },
+    {
+      "epoch": 0.056511056511056514,
+      "grad_norm": 2.6410160064697266,
+      "learning_rate": 5.6097560975609764e-05,
+      "loss": 4.0693,
+      "step": 46
+    },
+    {
+      "epoch": 0.05896805896805897,
+      "grad_norm": 2.716932535171509,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 4.0604,
+      "step": 48
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 2.662912368774414,
+      "learning_rate": 6.097560975609756e-05,
+      "loss": 4.106,
+      "step": 50
+    },
+    {
+      "epoch": 0.06388206388206388,
+      "grad_norm": 2.6940219402313232,
+      "learning_rate": 6.341463414634146e-05,
+      "loss": 3.9797,
+      "step": 52
+    },
+    {
+      "epoch": 0.06633906633906633,
+      "grad_norm": 2.474919319152832,
+      "learning_rate": 6.585365853658538e-05,
+      "loss": 3.9617,
+      "step": 54
+    },
+    {
+      "epoch": 0.0687960687960688,
+      "grad_norm": 3.2239887714385986,
+      "learning_rate": 6.829268292682928e-05,
+      "loss": 3.8198,
+      "step": 56
+    },
+    {
+      "epoch": 0.07125307125307126,
+      "grad_norm": 2.245703935623169,
+      "learning_rate": 7.073170731707317e-05,
+      "loss": 3.7654,
+      "step": 58
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 2.289674758911133,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 3.9226,
+      "step": 60
+    },
+    {
+      "epoch": 0.07616707616707617,
+      "grad_norm": 2.497066020965576,
+      "learning_rate": 7.560975609756099e-05,
+      "loss": 3.8096,
+      "step": 62
+    },
+    {
+      "epoch": 0.07862407862407862,
+      "grad_norm": 2.301783800125122,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 3.7816,
+      "step": 64
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 2.323812484741211,
+      "learning_rate": 8.048780487804879e-05,
+      "loss": 3.852,
+      "step": 66
+    },
+    {
+      "epoch": 0.08353808353808354,
+      "grad_norm": 2.500802755355835,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 3.6985,
+      "step": 68
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 2.634605646133423,
+      "learning_rate": 8.53658536585366e-05,
+      "loss": 3.6143,
+      "step": 70
+    },
+    {
+      "epoch": 0.08845208845208845,
+      "grad_norm": 2.6327457427978516,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 3.6925,
+      "step": 72
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 2.969693899154663,
+      "learning_rate": 9.02439024390244e-05,
+      "loss": 3.7667,
+      "step": 74
+    },
+    {
+      "epoch": 0.09336609336609336,
+      "grad_norm": 2.198855400085449,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 3.4533,
+      "step": 76
+    },
+    {
+      "epoch": 0.09582309582309582,
+      "grad_norm": 2.361680030822754,
+      "learning_rate": 9.51219512195122e-05,
+      "loss": 3.592,
+      "step": 78
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 2.2100822925567627,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 3.6584,
+      "step": 80
+    },
+    {
+      "epoch": 0.10073710073710074,
+      "grad_norm": 2.6485509872436523,
+      "learning_rate": 0.0001,
+      "loss": 3.7041,
+      "step": 82
+    },
+    {
+      "epoch": 0.10319410319410319,
+      "grad_norm": 2.305530548095703,
+      "learning_rate": 9.999958706645134e-05,
+      "loss": 3.4613,
+      "step": 84
+    },
+    {
+      "epoch": 0.10565110565110565,
+      "grad_norm": 2.2900867462158203,
+      "learning_rate": 9.999834827262588e-05,
+      "loss": 3.5832,
+      "step": 86
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 2.804309368133545,
+      "learning_rate": 9.999628363898526e-05,
+      "loss": 3.6276,
+      "step": 88
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 2.169964075088501,
+      "learning_rate": 9.999339319963168e-05,
+      "loss": 3.6038,
+      "step": 90
+    },
+    {
+      "epoch": 0.11302211302211303,
+      "grad_norm": 1.9803478717803955,
+      "learning_rate": 9.998967700230757e-05,
+      "loss": 3.6076,
+      "step": 92
+    },
+    {
+      "epoch": 0.11547911547911548,
+      "grad_norm": 2.2166459560394287,
+      "learning_rate": 9.998513510839458e-05,
+      "loss": 3.5336,
+      "step": 94
+    },
+    {
+      "epoch": 0.11793611793611794,
+      "grad_norm": 2.4060072898864746,
+      "learning_rate": 9.997976759291276e-05,
+      "loss": 3.4553,
+      "step": 96
+    },
+    {
+      "epoch": 0.12039312039312039,
+      "grad_norm": 2.0433080196380615,
+      "learning_rate": 9.997357454451919e-05,
+      "loss": 3.5237,
+      "step": 98
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 14.874445915222168,
+      "learning_rate": 9.996655606550656e-05,
+      "loss": 3.5126,
+      "step": 100
+    },
+    {
+      "epoch": 0.12530712530712532,
+      "grad_norm": 2.1172244548797607,
+      "learning_rate": 9.99587122718015e-05,
+      "loss": 3.6411,
+      "step": 102
+    },
+    {
+      "epoch": 0.12776412776412777,
+      "grad_norm": 2.2137668132781982,
+      "learning_rate": 9.995004329296263e-05,
+      "loss": 3.7789,
+      "step": 104
+    },
+    {
+      "epoch": 0.13022113022113022,
+      "grad_norm": 2.1240861415863037,
+      "learning_rate": 9.994054927217842e-05,
+      "loss": 3.5804,
+      "step": 106
+    },
+    {
+      "epoch": 0.13267813267813267,
+      "grad_norm": 2.106127977371216,
+      "learning_rate": 9.993023036626488e-05,
+      "loss": 3.5019,
+      "step": 108
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 2.0348684787750244,
+      "learning_rate": 9.99190867456629e-05,
+      "loss": 3.5321,
+      "step": 110
+    },
+    {
+      "epoch": 0.1375921375921376,
+      "grad_norm": 2.0568437576293945,
+      "learning_rate": 9.990711859443546e-05,
+      "loss": 3.3903,
+      "step": 112
+    },
+    {
+      "epoch": 0.14004914004914004,
+      "grad_norm": 2.1058425903320312,
+      "learning_rate": 9.989432611026464e-05,
+      "loss": 3.2349,
+      "step": 114
+    },
+    {
+      "epoch": 0.14250614250614252,
+      "grad_norm": 2.5870158672332764,
+      "learning_rate": 9.988070950444823e-05,
+      "loss": 3.3838,
+      "step": 116
+    },
+    {
+      "epoch": 0.14496314496314497,
+      "grad_norm": 1.9624409675598145,
+      "learning_rate": 9.986626900189641e-05,
+      "loss": 3.4498,
+      "step": 118
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 2.063462972640991,
+      "learning_rate": 9.985100484112785e-05,
+      "loss": 3.3871,
+      "step": 120
+    },
+    {
+      "epoch": 0.14987714987714987,
+      "grad_norm": 2.190028667449951,
+      "learning_rate": 9.983491727426598e-05,
+      "loss": 3.3708,
+      "step": 122
+    },
+    {
+      "epoch": 0.15233415233415235,
+      "grad_norm": 1.8697468042373657,
+      "learning_rate": 9.981800656703457e-05,
+      "loss": 3.5375,
+      "step": 124
+    },
+    {
+      "epoch": 0.1547911547911548,
+      "grad_norm": 2.1959290504455566,
+      "learning_rate": 9.980027299875358e-05,
+      "loss": 3.4274,
+      "step": 126
+    },
+    {
+      "epoch": 0.15724815724815724,
+      "grad_norm": 1.9716213941574097,
+      "learning_rate": 9.978171686233445e-05,
+      "loss": 3.2983,
+      "step": 128
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 2.224968910217285,
+      "learning_rate": 9.97623384642752e-05,
+      "loss": 3.3369,
+      "step": 130
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 1.896340012550354,
+      "learning_rate": 9.974213812465547e-05,
+      "loss": 3.4335,
+      "step": 132
+    },
+    {
+      "epoch": 0.16461916461916462,
+      "grad_norm": 2.3304531574249268,
+      "learning_rate": 9.972111617713116e-05,
+      "loss": 3.2502,
+      "step": 134
+    },
+    {
+      "epoch": 0.16707616707616707,
+      "grad_norm": 2.0420844554901123,
+      "learning_rate": 9.969927296892898e-05,
+      "loss": 3.4312,
+      "step": 136
+    },
+    {
+      "epoch": 0.16953316953316952,
+      "grad_norm": 2.021531105041504,
+      "learning_rate": 9.967660886084066e-05,
+      "loss": 3.2728,
+      "step": 138
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 2.0841152667999268,
+      "learning_rate": 9.965312422721704e-05,
+      "loss": 3.1727,
+      "step": 140
+    },
+    {
+      "epoch": 0.17444717444717445,
+      "grad_norm": 2.6040847301483154,
+      "learning_rate": 9.962881945596184e-05,
+      "loss": 3.3739,
+      "step": 142
+    },
+    {
+      "epoch": 0.1769041769041769,
+      "grad_norm": 15.763100624084473,
+      "learning_rate": 9.960369494852525e-05,
+      "loss": 3.1624,
+      "step": 144
+    },
+    {
+      "epoch": 0.17936117936117937,
+      "grad_norm": 2.2386856079101562,
+      "learning_rate": 9.95777511198974e-05,
+      "loss": 3.2584,
+      "step": 146
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.857926607131958,
+      "learning_rate": 9.955098839860133e-05,
+      "loss": 3.4066,
+      "step": 148
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 2.4381282329559326,
+      "learning_rate": 9.952340722668609e-05,
+      "loss": 3.2631,
+      "step": 150
+    },
+    {
+      "epoch": 0.18673218673218672,
+      "grad_norm": 2.13820481300354,
+      "learning_rate": 9.949500805971932e-05,
+      "loss": 3.3381,
+      "step": 152
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 2.0036275386810303,
+      "learning_rate": 9.946579136677978e-05,
+      "loss": 3.3253,
+      "step": 154
+    },
+    {
+      "epoch": 0.19164619164619165,
+      "grad_norm": 2.3847107887268066,
+      "learning_rate": 9.943575763044955e-05,
+      "loss": 3.1658,
+      "step": 156
+    },
+    {
+      "epoch": 0.1941031941031941,
+      "grad_norm": 1.883772373199463,
+      "learning_rate": 9.940490734680614e-05,
+      "loss": 3.1963,
+      "step": 158
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.8654661178588867,
+      "learning_rate": 9.937324102541423e-05,
+      "loss": 3.2319,
+      "step": 160
+    },
+    {
+      "epoch": 0.19901719901719903,
+      "grad_norm": 1.8905117511749268,
+      "learning_rate": 9.93407591893173e-05,
+      "loss": 3.3699,
+      "step": 162
+    },
+    {
+      "epoch": 0.20147420147420148,
+      "grad_norm": 1.8974312543869019,
+      "learning_rate": 9.930746237502892e-05,
+      "loss": 3.2576,
+      "step": 164
+    },
+    {
+      "epoch": 0.20393120393120392,
+      "grad_norm": 1.9088815450668335,
+      "learning_rate": 9.927335113252396e-05,
+      "loss": 3.3929,
+      "step": 166
+    },
+    {
+      "epoch": 0.20638820638820637,
+      "grad_norm": 1.8603475093841553,
+      "learning_rate": 9.923842602522949e-05,
+      "loss": 3.2274,
+      "step": 168
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.8516125679016113,
+      "learning_rate": 9.920268763001542e-05,
+      "loss": 3.1596,
+      "step": 170
+    },
+    {
+      "epoch": 0.2113022113022113,
+      "grad_norm": 1.9465285539627075,
+      "learning_rate": 9.916613653718509e-05,
+      "loss": 3.2853,
+      "step": 172
+    },
+    {
+      "epoch": 0.21375921375921375,
+      "grad_norm": 1.9433836936950684,
+      "learning_rate": 9.912877335046535e-05,
+      "loss": 3.1986,
+      "step": 174
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 1.9821792840957642,
+      "learning_rate": 9.909059868699678e-05,
+      "loss": 3.1233,
+      "step": 176
+    },
+    {
+      "epoch": 0.21867321867321868,
+      "grad_norm": 1.904826283454895,
+      "learning_rate": 9.905161317732331e-05,
+      "loss": 3.221,
+      "step": 178
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.9415316581726074,
+      "learning_rate": 9.901181746538196e-05,
+      "loss": 3.1107,
+      "step": 180
+    },
+    {
+      "epoch": 0.22358722358722358,
+      "grad_norm": 1.8300875425338745,
+      "learning_rate": 9.897121220849208e-05,
+      "loss": 3.1114,
+      "step": 182
+    },
+    {
+      "epoch": 0.22604422604422605,
+      "grad_norm": 1.972747802734375,
+      "learning_rate": 9.892979807734462e-05,
+      "loss": 3.1652,
+      "step": 184
+    },
+    {
+      "epoch": 0.2285012285012285,
+      "grad_norm": 1.9549387693405151,
+      "learning_rate": 9.888757575599093e-05,
+      "loss": 3.2123,
+      "step": 186
+    },
+    {
+      "epoch": 0.23095823095823095,
+      "grad_norm": 1.856306552886963,
+      "learning_rate": 9.884454594183154e-05,
+      "loss": 3.235,
+      "step": 188
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 1.743513584136963,
+      "learning_rate": 9.880070934560458e-05,
+      "loss": 3.1647,
+      "step": 190
+    },
+    {
+      "epoch": 0.23587223587223588,
+      "grad_norm": 1.884634256362915,
+      "learning_rate": 9.875606669137412e-05,
+      "loss": 3.1963,
+      "step": 192
+    },
+    {
+      "epoch": 0.23832923832923833,
+      "grad_norm": 1.966579556465149,
+      "learning_rate": 9.871061871651815e-05,
+      "loss": 2.9626,
+      "step": 194
+    },
+    {
+      "epoch": 0.24078624078624078,
+      "grad_norm": 1.7920762300491333,
+      "learning_rate": 9.866436617171638e-05,
+      "loss": 3.3341,
+      "step": 196
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 1.9862432479858398,
+      "learning_rate": 9.861730982093793e-05,
+      "loss": 3.2039,
+      "step": 198
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 1.7585490942001343,
+      "learning_rate": 9.856945044142865e-05,
+      "loss": 3.1915,
+      "step": 200
+    },
+    {
+      "epoch": 0.24815724815724816,
+      "grad_norm": 1.7467507123947144,
+      "learning_rate": 9.852078882369827e-05,
+      "loss": 3.1105,
+      "step": 202
+    },
+    {
+      "epoch": 0.25061425061425063,
+      "grad_norm": 1.9189780950546265,
+      "learning_rate": 9.847132577150733e-05,
+      "loss": 3.1065,
+      "step": 204
+    },
+    {
+      "epoch": 0.25307125307125306,
+      "grad_norm": 1.8920857906341553,
+      "learning_rate": 9.842106210185403e-05,
+      "loss": 3.1573,
+      "step": 206
+    },
+    {
+      "epoch": 0.25552825552825553,
+      "grad_norm": 1.7997002601623535,
+      "learning_rate": 9.836999864496057e-05,
+      "loss": 3.0638,
+      "step": 208
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 1.8181427717208862,
+      "learning_rate": 9.831813624425952e-05,
+      "loss": 3.166,
+      "step": 210
+    },
+    {
+      "epoch": 0.26044226044226043,
+      "grad_norm": 1.7454043626785278,
+      "learning_rate": 9.82654757563799e-05,
+      "loss": 2.9648,
+      "step": 212
+    },
+    {
+      "epoch": 0.2628992628992629,
+      "grad_norm": 1.9787805080413818,
+      "learning_rate": 9.821201805113298e-05,
+      "loss": 3.0446,
+      "step": 214
+    },
+    {
+      "epoch": 0.26535626535626533,
+      "grad_norm": 1.8889926671981812,
+      "learning_rate": 9.815776401149796e-05,
+      "loss": 3.1998,
+      "step": 216
+    },
+    {
+      "epoch": 0.2678132678132678,
+      "grad_norm": 1.9100897312164307,
+      "learning_rate": 9.810271453360738e-05,
+      "loss": 3.0167,
+      "step": 218
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.72272527217865,
+      "learning_rate": 9.804687052673229e-05,
+      "loss": 3.0516,
+      "step": 220
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 1.7406550645828247,
+      "learning_rate": 9.799023291326722e-05,
+      "loss": 3.1492,
+      "step": 222
+    },
+    {
+      "epoch": 0.2751842751842752,
+      "grad_norm": 1.7723503112792969,
+      "learning_rate": 9.793280262871502e-05,
+      "loss": 3.1282,
+      "step": 224
+    },
+    {
+      "epoch": 0.27764127764127766,
+      "grad_norm": 1.7942124605178833,
+      "learning_rate": 9.787458062167134e-05,
+      "loss": 3.0463,
+      "step": 226
+    },
+    {
+      "epoch": 0.2800982800982801,
+      "grad_norm": 1.8124969005584717,
+      "learning_rate": 9.781556785380899e-05,
+      "loss": 3.295,
+      "step": 228
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 1.7787127494812012,
+      "learning_rate": 9.775576529986199e-05,
+      "loss": 3.3415,
+      "step": 230
+    },
+    {
+      "epoch": 0.28501228501228504,
+      "grad_norm": 1.967888355255127,
+      "learning_rate": 9.769517394760962e-05,
+      "loss": 2.9891,
+      "step": 232
+    },
+    {
+      "epoch": 0.28746928746928746,
+      "grad_norm": 1.9067909717559814,
+      "learning_rate": 9.763379479785995e-05,
+      "loss": 3.1963,
+      "step": 234
+    },
+    {
+      "epoch": 0.28992628992628994,
+      "grad_norm": 1.8959527015686035,
+      "learning_rate": 9.757162886443336e-05,
+      "loss": 3.0906,
+      "step": 236
+    },
+    {
+      "epoch": 0.29238329238329236,
+      "grad_norm": 1.756986141204834,
+      "learning_rate": 9.750867717414586e-05,
+      "loss": 3.1538,
+      "step": 238
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 1.7642282247543335,
+      "learning_rate": 9.744494076679205e-05,
+      "loss": 3.0886,
+      "step": 240
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 1.8129557371139526,
+      "learning_rate": 9.738042069512795e-05,
+      "loss": 3.2687,
+      "step": 242
+    },
+    {
+      "epoch": 0.29975429975429974,
+      "grad_norm": 1.6599668264389038,
+      "learning_rate": 9.731511802485364e-05,
+      "loss": 3.0165,
+      "step": 244
+    },
+    {
+      "epoch": 0.3022113022113022,
+      "grad_norm": 1.7890832424163818,
+      "learning_rate": 9.724903383459566e-05,
+      "loss": 3.1224,
+      "step": 246
+    },
+    {
+      "epoch": 0.3046683046683047,
+      "grad_norm": 1.901267170906067,
+      "learning_rate": 9.718216921588919e-05,
+      "loss": 2.9377,
+      "step": 248
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 1.8047585487365723,
+      "learning_rate": 9.711452527315998e-05,
+      "loss": 3.2727,
+      "step": 250
+    },
+    {
+      "epoch": 0.3095823095823096,
+      "grad_norm": 1.9266289472579956,
+      "learning_rate": 9.704610312370617e-05,
+      "loss": 3.0795,
+      "step": 252
+    },
+    {
+      "epoch": 0.31203931203931207,
+      "grad_norm": 1.8360109329223633,
+      "learning_rate": 9.697690389767981e-05,
+      "loss": 3.1791,
+      "step": 254
+    },
+    {
+      "epoch": 0.3144963144963145,
+      "grad_norm": 1.7929311990737915,
+      "learning_rate": 9.690692873806816e-05,
+      "loss": 3.1926,
+      "step": 256
+    },
+    {
+      "epoch": 0.31695331695331697,
+      "grad_norm": 1.7981804609298706,
+      "learning_rate": 9.683617880067489e-05,
+      "loss": 3.2032,
+      "step": 258
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.8404676914215088,
+      "learning_rate": 9.676465525410088e-05,
+      "loss": 3.1692,
+      "step": 260
+    },
+    {
+      "epoch": 0.32186732186732187,
+      "grad_norm": 1.7135553359985352,
+      "learning_rate": 9.669235927972502e-05,
+      "loss": 3.2311,
+      "step": 262
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 1.8173389434814453,
+      "learning_rate": 9.661929207168463e-05,
+      "loss": 2.938,
+      "step": 264
+    },
+    {
+      "epoch": 0.32678132678132676,
+      "grad_norm": 1.8518667221069336,
+      "learning_rate": 9.654545483685578e-05,
+      "loss": 2.9593,
+      "step": 266
+    },
+    {
+      "epoch": 0.32923832923832924,
+      "grad_norm": 1.7250562906265259,
+      "learning_rate": 9.647084879483332e-05,
+      "loss": 3.2025,
+      "step": 268
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 1.7107222080230713,
+      "learning_rate": 9.639547517791076e-05,
+      "loss": 3.0682,
+      "step": 270
+    },
+    {
+      "epoch": 0.33415233415233414,
+      "grad_norm": 1.6773762702941895,
+      "learning_rate": 9.631933523105991e-05,
+      "loss": 2.99,
+      "step": 272
+    },
+    {
+      "epoch": 0.3366093366093366,
+      "grad_norm": 1.758596420288086,
+      "learning_rate": 9.624243021191029e-05,
+      "loss": 2.9892,
+      "step": 274
+    },
+    {
+      "epoch": 0.33906633906633904,
+      "grad_norm": 1.8285568952560425,
+      "learning_rate": 9.61647613907284e-05,
+      "loss": 3.0917,
+      "step": 276
+    },
+    {
+      "epoch": 0.3415233415233415,
+      "grad_norm": 1.8026080131530762,
+      "learning_rate": 9.608633005039675e-05,
+      "loss": 3.0702,
+      "step": 278
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 11.102814674377441,
+      "learning_rate": 9.600713748639258e-05,
+      "loss": 3.1327,
+      "step": 280
+    },
+    {
+      "epoch": 0.3464373464373464,
+      "grad_norm": 1.9404098987579346,
+      "learning_rate": 9.592718500676656e-05,
+      "loss": 3.0348,
+      "step": 282
+    },
+    {
+      "epoch": 0.3488943488943489,
+      "grad_norm": 1.7170964479446411,
+      "learning_rate": 9.584647393212113e-05,
+      "loss": 3.0137,
+      "step": 284
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 2.194800615310669,
+      "learning_rate": 9.576500559558869e-05,
+      "loss": 3.0657,
+      "step": 286
+    },
+    {
+      "epoch": 0.3538083538083538,
+      "grad_norm": 2.2819526195526123,
+      "learning_rate": 9.568278134280966e-05,
+      "loss": 2.9922,
+      "step": 288
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 1.764850378036499,
+      "learning_rate": 9.55998025319101e-05,
+      "loss": 3.0742,
+      "step": 290
+    },
+    {
+      "epoch": 0.35872235872235875,
+      "grad_norm": 1.675075650215149,
+      "learning_rate": 9.551607053347942e-05,
+      "loss": 3.14,
+      "step": 292
+    },
+    {
+      "epoch": 0.36117936117936117,
+      "grad_norm": 1.730245590209961,
+      "learning_rate": 9.543158673054767e-05,
+      "loss": 2.9738,
+      "step": 294
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.6660993099212646,
+      "learning_rate": 9.534635251856267e-05,
+      "loss": 2.7211,
+      "step": 296
+    },
+    {
+      "epoch": 0.36609336609336607,
+      "grad_norm": 1.6620466709136963,
+      "learning_rate": 9.526036930536712e-05,
+      "loss": 2.9747,
+      "step": 298
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 1.6838281154632568,
+      "learning_rate": 9.517363851117512e-05,
+      "loss": 3.0342,
+      "step": 300
+    },
+    {
+      "epoch": 0.371007371007371,
+      "grad_norm": 3.0981221199035645,
+      "learning_rate": 9.508616156854883e-05,
+      "loss": 3.1151,
+      "step": 302
+    },
+    {
+      "epoch": 0.37346437346437344,
+      "grad_norm": 1.954408049583435,
+      "learning_rate": 9.499793992237485e-05,
+      "loss": 2.7723,
+      "step": 304
+    },
+    {
+      "epoch": 0.3759213759213759,
+      "grad_norm": 1.7550610303878784,
+      "learning_rate": 9.490897502984028e-05,
+      "loss": 2.9576,
+      "step": 306
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 1.854491114616394,
+      "learning_rate": 9.481926836040866e-05,
+      "loss": 2.9745,
+      "step": 308
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 1.6988489627838135,
+      "learning_rate": 9.472882139579572e-05,
+      "loss": 3.1205,
+      "step": 310
+    },
+    {
+      "epoch": 0.3832923832923833,
+      "grad_norm": 1.682507038116455,
+      "learning_rate": 9.463763562994491e-05,
+      "loss": 3.0174,
+      "step": 312
+    },
+    {
+      "epoch": 0.3857493857493858,
+      "grad_norm": 1.7135891914367676,
+      "learning_rate": 9.454571256900272e-05,
+      "loss": 2.8791,
+      "step": 314
+    },
+    {
+      "epoch": 0.3882063882063882,
+      "grad_norm": 1.6604820489883423,
+      "learning_rate": 9.445305373129375e-05,
+      "loss": 2.9726,
+      "step": 316
+    },
+    {
+      "epoch": 0.3906633906633907,
+      "grad_norm": 1.8734002113342285,
+      "learning_rate": 9.435966064729574e-05,
+      "loss": 3.2479,
+      "step": 318
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 2.204241991043091,
+      "learning_rate": 9.426553485961415e-05,
+      "loss": 3.092,
+      "step": 320
+    },
+    {
+      "epoch": 0.3955773955773956,
+      "grad_norm": 1.7275304794311523,
+      "learning_rate": 9.417067792295684e-05,
+      "loss": 2.9288,
+      "step": 322
+    },
+    {
+      "epoch": 0.39803439803439805,
+      "grad_norm": 1.720664381980896,
+      "learning_rate": 9.407509140410826e-05,
+      "loss": 2.9628,
+      "step": 324
+    },
+    {
+      "epoch": 0.4004914004914005,
+      "grad_norm": 1.6769790649414062,
+      "learning_rate": 9.397877688190362e-05,
+      "loss": 2.8215,
+      "step": 326
+    },
+    {
+      "epoch": 0.40294840294840295,
+      "grad_norm": 2.712700843811035,
+      "learning_rate": 9.388173594720281e-05,
+      "loss": 2.9122,
+      "step": 328
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 1.8222036361694336,
+      "learning_rate": 9.378397020286417e-05,
+      "loss": 3.0608,
+      "step": 330
+    },
+    {
+      "epoch": 0.40786240786240785,
+      "grad_norm": 1.794284462928772,
+      "learning_rate": 9.368548126371788e-05,
+      "loss": 2.994,
+      "step": 332
+    },
+    {
+      "epoch": 0.4103194103194103,
+      "grad_norm": 1.6459068059921265,
+      "learning_rate": 9.358627075653946e-05,
+      "loss": 2.9682,
+      "step": 334
+    },
+    {
+      "epoch": 0.41277641277641275,
+      "grad_norm": 1.6979544162750244,
+      "learning_rate": 9.348634032002277e-05,
+      "loss": 3.0303,
+      "step": 336
+    },
+    {
+      "epoch": 0.4152334152334152,
+      "grad_norm": 1.724778175354004,
+      "learning_rate": 9.338569160475299e-05,
+      "loss": 2.7861,
+      "step": 338
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 1.737809658050537,
+      "learning_rate": 9.328432627317938e-05,
+      "loss": 2.9365,
+      "step": 340
+    },
+    {
+      "epoch": 0.4201474201474201,
+      "grad_norm": 1.6635717153549194,
+      "learning_rate": 9.318224599958778e-05,
+      "loss": 2.9818,
+      "step": 342
+    },
+    {
+      "epoch": 0.4226044226044226,
+      "grad_norm": 1.696031093597412,
+      "learning_rate": 9.307945247007299e-05,
+      "loss": 3.0177,
+      "step": 344
+    },
+    {
+      "epoch": 0.4250614250614251,
+      "grad_norm": 1.7607593536376953,
+      "learning_rate": 9.297594738251086e-05,
+      "loss": 3.0018,
+      "step": 346
+    },
+    {
+      "epoch": 0.4275184275184275,
+      "grad_norm": 1.6658580303192139,
+      "learning_rate": 9.287173244653032e-05,
+      "loss": 2.9692,
+      "step": 348
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 1.7650336027145386,
+      "learning_rate": 9.276680938348512e-05,
+      "loss": 2.9828,
+      "step": 350
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 1.6512577533721924,
+      "learning_rate": 9.266117992642536e-05,
+      "loss": 2.9751,
+      "step": 352
+    },
+    {
+      "epoch": 0.4348894348894349,
+      "grad_norm": 1.7206581830978394,
+      "learning_rate": 9.25548458200689e-05,
+      "loss": 2.948,
+      "step": 354
+    },
+    {
+      "epoch": 0.43734643734643736,
+      "grad_norm": 1.7989583015441895,
+      "learning_rate": 9.244780882077254e-05,
+      "loss": 2.6979,
+      "step": 356
+    },
+    {
+      "epoch": 0.4398034398034398,
+      "grad_norm": 1.7424843311309814,
+      "learning_rate": 9.2340070696503e-05,
+      "loss": 3.0316,
+      "step": 358
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 1.726643443107605,
+      "learning_rate": 9.223163322680772e-05,
+      "loss": 2.9751,
+      "step": 360
+    },
+    {
+      "epoch": 0.44471744471744473,
+      "grad_norm": 1.670101523399353,
+      "learning_rate": 9.212249820278545e-05,
+      "loss": 2.8993,
+      "step": 362
+    },
+    {
+      "epoch": 0.44717444717444715,
+      "grad_norm": 1.6568448543548584,
+      "learning_rate": 9.201266742705672e-05,
+      "loss": 3.1154,
+      "step": 364
+    },
+    {
+      "epoch": 0.44963144963144963,
+      "grad_norm": 1.776298999786377,
+      "learning_rate": 9.190214271373398e-05,
+      "loss": 2.8871,
+      "step": 366
+    },
+    {
+      "epoch": 0.4520884520884521,
+      "grad_norm": 1.67928147315979,
+      "learning_rate": 9.179092588839178e-05,
+      "loss": 2.7472,
+      "step": 368
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.657324194908142,
+      "learning_rate": 9.167901878803638e-05,
+      "loss": 2.8401,
+      "step": 370
+    },
+    {
+      "epoch": 0.457002457002457,
+      "grad_norm": 1.7573364973068237,
+      "learning_rate": 9.156642326107565e-05,
+      "loss": 2.91,
+      "step": 372
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 1.6229298114776611,
+      "learning_rate": 9.145314116728841e-05,
+      "loss": 3.0171,
+      "step": 374
+    },
+    {
+      "epoch": 0.4619164619164619,
+      "grad_norm": 1.7045820951461792,
+      "learning_rate": 9.133917437779375e-05,
+      "loss": 2.9076,
+      "step": 376
+    },
+    {
+      "epoch": 0.4643734643734644,
+      "grad_norm": 1.5423696041107178,
+      "learning_rate": 9.12245247750201e-05,
+      "loss": 2.9438,
+      "step": 378
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 1.6251273155212402,
+      "learning_rate": 9.110919425267415e-05,
+      "loss": 2.998,
+      "step": 380
+    },
+    {
+      "epoch": 0.4692874692874693,
+      "grad_norm": 1.7428491115570068,
+      "learning_rate": 9.099318471570957e-05,
+      "loss": 2.9253,
+      "step": 382
+    },
+    {
+      "epoch": 0.47174447174447176,
+      "grad_norm": 1.7721710205078125,
+      "learning_rate": 9.087649808029554e-05,
+      "loss": 2.8592,
+      "step": 384
+    },
+    {
+      "epoch": 0.4742014742014742,
+      "grad_norm": 1.8491050004959106,
+      "learning_rate": 9.075913627378513e-05,
+      "loss": 2.994,
+      "step": 386
+    },
+    {
+      "epoch": 0.47665847665847666,
+      "grad_norm": 1.6777352094650269,
+      "learning_rate": 9.064110123468345e-05,
+      "loss": 2.9855,
+      "step": 388
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 1.717166781425476,
+      "learning_rate": 9.052239491261559e-05,
+      "loss": 3.0357,
+      "step": 390
+    },
+    {
+      "epoch": 0.48157248157248156,
+      "grad_norm": 1.6935992240905762,
+      "learning_rate": 9.040301926829445e-05,
+      "loss": 3.0939,
+      "step": 392
+    },
+    {
+      "epoch": 0.48402948402948404,
+      "grad_norm": 1.7372186183929443,
+      "learning_rate": 9.028297627348835e-05,
+      "loss": 2.7582,
+      "step": 394
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 1.6863627433776855,
+      "learning_rate": 9.016226791098851e-05,
+      "loss": 3.0831,
+      "step": 396
+    },
+    {
+      "epoch": 0.48894348894348894,
+      "grad_norm": 1.5812780857086182,
+      "learning_rate": 9.004089617457625e-05,
+      "loss": 2.8814,
+      "step": 398
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 1.6280958652496338,
+      "learning_rate": 8.991886306899002e-05,
+      "loss": 3.0318,
+      "step": 400
+    },
+    {
+      "epoch": 0.49385749385749383,
+      "grad_norm": 1.703506588935852,
+      "learning_rate": 8.979617060989234e-05,
+      "loss": 3.1265,
+      "step": 402
+    },
+    {
+      "epoch": 0.4963144963144963,
+      "grad_norm": 1.596043348312378,
+      "learning_rate": 8.967282082383652e-05,
+      "loss": 3.0872,
+      "step": 404
+    },
+    {
+      "epoch": 0.4987714987714988,
+      "grad_norm": 1.8576503992080688,
+      "learning_rate": 8.954881574823317e-05,
+      "loss": 2.9286,
+      "step": 406
+    },
+    {
+      "epoch": 0.5012285012285013,
+      "grad_norm": 1.8761273622512817,
+      "learning_rate": 8.942415743131651e-05,
+      "loss": 2.8426,
+      "step": 408
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 1.6055220365524292,
+      "learning_rate": 8.92988479321106e-05,
+      "loss": 2.7407,
+      "step": 410
+    },
+    {
+      "epoch": 0.5061425061425061,
+      "grad_norm": 1.5771170854568481,
+      "learning_rate": 8.917288932039529e-05,
+      "loss": 3.0324,
+      "step": 412
+    },
+    {
+      "epoch": 0.5085995085995086,
+      "grad_norm": 1.5361248254776,
+      "learning_rate": 8.904628367667202e-05,
+      "loss": 2.901,
+      "step": 414
+    },
+    {
+      "epoch": 0.5110565110565111,
+      "grad_norm": 1.662143588066101,
+      "learning_rate": 8.891903309212952e-05,
+      "loss": 2.8503,
+      "step": 416
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 1.6230075359344482,
+      "learning_rate": 8.87911396686092e-05,
+      "loss": 2.7839,
+      "step": 418
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 1.7319310903549194,
+      "learning_rate": 8.866260551857045e-05,
+      "loss": 2.9908,
+      "step": 420
+    },
+    {
+      "epoch": 0.5184275184275184,
+      "grad_norm": 1.6889699697494507,
+      "learning_rate": 8.853343276505581e-05,
+      "loss": 2.7828,
+      "step": 422
+    },
+    {
+      "epoch": 0.5208845208845209,
+      "grad_norm": 11.279559135437012,
+      "learning_rate": 8.840362354165581e-05,
+      "loss": 2.8784,
+      "step": 424
+    },
+    {
+      "epoch": 0.5233415233415234,
+      "grad_norm": 1.7862719297409058,
+      "learning_rate": 8.827317999247378e-05,
+      "loss": 2.9174,
+      "step": 426
+    },
+    {
+      "epoch": 0.5257985257985258,
+      "grad_norm": 1.6923807859420776,
+      "learning_rate": 8.81421042720904e-05,
+      "loss": 3.0122,
+      "step": 428
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 29.5804386138916,
+      "learning_rate": 8.801039854552821e-05,
+      "loss": 2.9432,
+      "step": 430
+    },
+    {
+      "epoch": 0.5307125307125307,
+      "grad_norm": 1.7361953258514404,
+      "learning_rate": 8.787806498821571e-05,
+      "loss": 2.881,
+      "step": 432
+    },
+    {
+      "epoch": 0.5331695331695332,
+      "grad_norm": 1.7489663362503052,
+      "learning_rate": 8.774510578595153e-05,
+      "loss": 2.9763,
+      "step": 434
+    },
+    {
+      "epoch": 0.5356265356265356,
+      "grad_norm": 1.5390799045562744,
+      "learning_rate": 8.761152313486824e-05,
+      "loss": 2.9691,
+      "step": 436
+    },
+    {
+      "epoch": 0.538083538083538,
+      "grad_norm": 1.8254520893096924,
+      "learning_rate": 8.747731924139622e-05,
+      "loss": 2.7518,
+      "step": 438
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 1.6369190216064453,
+      "learning_rate": 8.734249632222702e-05,
+      "loss": 2.9397,
+      "step": 440
+    },
+    {
+      "epoch": 0.542997542997543,
+      "grad_norm": 1.5464283227920532,
+      "learning_rate": 8.720705660427692e-05,
+      "loss": 2.85,
+      "step": 442
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.9427014589309692,
+      "learning_rate": 8.707100232465007e-05,
+      "loss": 2.8669,
+      "step": 444
+    },
+    {
+      "epoch": 0.547911547911548,
+      "grad_norm": 1.6004284620285034,
+      "learning_rate": 8.69343357306015e-05,
+      "loss": 2.8216,
+      "step": 446
+    },
+    {
+      "epoch": 0.5503685503685504,
+      "grad_norm": 1.615379810333252,
+      "learning_rate": 8.67970590795001e-05,
+      "loss": 2.6078,
+      "step": 448
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 1.7116811275482178,
+      "learning_rate": 8.665917463879125e-05,
+      "loss": 3.1718,
+      "step": 450
+    },
+    {
+      "epoch": 0.5552825552825553,
+      "grad_norm": 1.7578415870666504,
+      "learning_rate": 8.65206846859594e-05,
+      "loss": 2.9675,
+      "step": 452
+    },
+    {
+      "epoch": 0.5577395577395577,
+      "grad_norm": 1.6257036924362183,
+      "learning_rate": 8.638159150849046e-05,
+      "loss": 3.0276,
+      "step": 454
+    },
+    {
+      "epoch": 0.5601965601965602,
+      "grad_norm": 1.6307907104492188,
+      "learning_rate": 8.6241897403834e-05,
+      "loss": 2.984,
+      "step": 456
+    },
+    {
+      "epoch": 0.5626535626535627,
+      "grad_norm": 1.628524661064148,
+      "learning_rate": 8.610160467936533e-05,
+      "loss": 2.9575,
+      "step": 458
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.656004786491394,
+      "learning_rate": 8.596071565234733e-05,
+      "loss": 3.0361,
+      "step": 460
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 1.5190882682800293,
+      "learning_rate": 8.581923264989228e-05,
+      "loss": 2.8684,
+      "step": 462
+    },
+    {
+      "epoch": 0.5700245700245701,
+      "grad_norm": 1.6448097229003906,
+      "learning_rate": 8.567715800892326e-05,
+      "loss": 3.0113,
+      "step": 464
+    },
+    {
+      "epoch": 0.5724815724815725,
+      "grad_norm": 1.7265264987945557,
+      "learning_rate": 8.553449407613572e-05,
+      "loss": 2.9945,
+      "step": 466
+    },
+    {
+      "epoch": 0.5749385749385749,
+      "grad_norm": 7.519404411315918,
+      "learning_rate": 8.539124320795862e-05,
+      "loss": 3.0108,
+      "step": 468
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 1.586311936378479,
+      "learning_rate": 8.524740777051555e-05,
+      "loss": 2.7747,
+      "step": 470
+    },
+    {
+      "epoch": 0.5798525798525799,
+      "grad_norm": 1.7437552213668823,
+      "learning_rate": 8.510299013958558e-05,
+      "loss": 3.0769,
+      "step": 472
+    },
+    {
+      "epoch": 0.5823095823095823,
+      "grad_norm": 1.757537603378296,
+      "learning_rate": 8.495799270056412e-05,
+      "loss": 2.9696,
+      "step": 474
+    },
+    {
+      "epoch": 0.5847665847665847,
+      "grad_norm": 1.5627938508987427,
+      "learning_rate": 8.481241784842344e-05,
+      "loss": 2.7725,
+      "step": 476
+    },
+    {
+      "epoch": 0.5872235872235873,
+      "grad_norm": 1.6397974491119385,
+      "learning_rate": 8.466626798767318e-05,
+      "loss": 3.0094,
+      "step": 478
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 1.6290757656097412,
+      "learning_rate": 8.451954553232055e-05,
+      "loss": 3.0959,
+      "step": 480
+    },
+    {
+      "epoch": 0.5921375921375921,
+      "grad_norm": 1.628265619277954,
+      "learning_rate": 8.437225290583051e-05,
+      "loss": 2.7791,
+      "step": 482
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 1.6443836688995361,
+      "learning_rate": 8.422439254108576e-05,
+      "loss": 2.9753,
+      "step": 484
+    },
+    {
+      "epoch": 0.597051597051597,
+      "grad_norm": 1.617613673210144,
+      "learning_rate": 8.407596688034648e-05,
+      "loss": 3.0032,
+      "step": 486
+    },
+    {
+      "epoch": 0.5995085995085995,
+      "grad_norm": 1.6962013244628906,
+      "learning_rate": 8.392697837521007e-05,
+      "loss": 2.845,
+      "step": 488
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 1.5888972282409668,
+      "learning_rate": 8.37774294865706e-05,
+      "loss": 2.7606,
+      "step": 490
+    },
+    {
+      "epoch": 0.6044226044226044,
+      "grad_norm": 1.5973700284957886,
+      "learning_rate": 8.362732268457824e-05,
+      "loss": 3.1137,
+      "step": 492
+    },
+    {
+      "epoch": 0.6068796068796068,
+      "grad_norm": 27.63825035095215,
+      "learning_rate": 8.347666044859833e-05,
+      "loss": 2.8452,
+      "step": 494
+    },
+    {
+      "epoch": 0.6093366093366094,
+      "grad_norm": 1.592497706413269,
+      "learning_rate": 8.332544526717057e-05,
+      "loss": 2.8386,
+      "step": 496
+    },
+    {
+      "epoch": 0.6117936117936118,
+      "grad_norm": 1.5605237483978271,
+      "learning_rate": 8.317367963796778e-05,
+      "loss": 2.9155,
+      "step": 498
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 1.5933369398117065,
+      "learning_rate": 8.30213660677548e-05,
+      "loss": 2.8719,
+      "step": 500
+    },
+    {
+      "epoch": 0.6167076167076168,
+      "grad_norm": 1.649196743965149,
+      "learning_rate": 8.286850707234691e-05,
+      "loss": 2.8277,
+      "step": 502
+    },
+    {
+      "epoch": 0.6191646191646192,
+      "grad_norm": 1.671309232711792,
+      "learning_rate": 8.271510517656845e-05,
+      "loss": 2.8637,
+      "step": 504
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 1.6627384424209595,
+      "learning_rate": 8.256116291421094e-05,
+      "loss": 3.0589,
+      "step": 506
+    },
+    {
+      "epoch": 0.6240786240786241,
+      "grad_norm": 1.6332685947418213,
+      "learning_rate": 8.24066828279914e-05,
+      "loss": 2.8909,
+      "step": 508
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 1.5245287418365479,
+      "learning_rate": 8.225166746951023e-05,
+      "loss": 3.0116,
+      "step": 510
+    },
+    {
+      "epoch": 0.628992628992629,
+      "grad_norm": 1.6836432218551636,
+      "learning_rate": 8.209611939920912e-05,
+      "loss": 2.6435,
+      "step": 512
+    },
+    {
+      "epoch": 0.6314496314496314,
+      "grad_norm": 1.5706799030303955,
+      "learning_rate": 8.194004118632873e-05,
+      "loss": 2.8328,
+      "step": 514
+    },
+    {
+      "epoch": 0.6339066339066339,
+      "grad_norm": 1.6746190786361694,
+      "learning_rate": 8.178343540886626e-05,
+      "loss": 2.8675,
+      "step": 516
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.629543662071228,
+      "learning_rate": 8.162630465353292e-05,
+      "loss": 2.7241,
+      "step": 518
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 1.6499792337417603,
+      "learning_rate": 8.146865151571108e-05,
+      "loss": 2.8229,
+      "step": 520
+    },
+    {
+      "epoch": 0.6412776412776413,
+      "grad_norm": 1.7184644937515259,
+      "learning_rate": 8.131047859941156e-05,
+      "loss": 2.77,
+      "step": 522
+    },
+    {
+      "epoch": 0.6437346437346437,
+      "grad_norm": 4.247711181640625,
+      "learning_rate": 8.11517885172305e-05,
+      "loss": 2.9487,
+      "step": 524
+    },
+    {
+      "epoch": 0.6461916461916462,
+      "grad_norm": 1.6026562452316284,
+      "learning_rate": 8.099258389030624e-05,
+      "loss": 2.6282,
+      "step": 526
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 1.6910419464111328,
+      "learning_rate": 8.083286734827605e-05,
+      "loss": 2.8437,
+      "step": 528
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 2.3516945838928223,
+      "learning_rate": 8.067264152923268e-05,
+      "loss": 2.8406,
+      "step": 530
+    },
+    {
+      "epoch": 0.6535626535626535,
+      "grad_norm": 1.7951064109802246,
+      "learning_rate": 8.051190907968076e-05,
+      "loss": 2.7437,
+      "step": 532
+    },
+    {
+      "epoch": 0.6560196560196561,
+      "grad_norm": 1.6154842376708984,
+      "learning_rate": 8.035067265449312e-05,
+      "loss": 2.7701,
+      "step": 534
+    },
+    {
+      "epoch": 0.6584766584766585,
+      "grad_norm": 1.5919100046157837,
+      "learning_rate": 8.018893491686692e-05,
+      "loss": 2.8796,
+      "step": 536
+    },
+    {
+      "epoch": 0.6609336609336609,
+      "grad_norm": 1.6625549793243408,
+      "learning_rate": 8.00266985382797e-05,
+      "loss": 2.8874,
+      "step": 538
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 1.5272475481033325,
+      "learning_rate": 7.986396619844519e-05,
+      "loss": 2.8395,
+      "step": 540
+    },
+    {
+      "epoch": 0.6658476658476659,
+      "grad_norm": 1.6629564762115479,
+      "learning_rate": 7.970074058526908e-05,
+      "loss": 2.8472,
+      "step": 542
+    },
+    {
+      "epoch": 0.6683046683046683,
+      "grad_norm": 1.5899837017059326,
+      "learning_rate": 7.953702439480468e-05,
+      "loss": 2.5589,
+      "step": 544
+    },
+    {
+      "epoch": 0.6707616707616708,
+      "grad_norm": 1.6535660028457642,
+      "learning_rate": 7.937282033120825e-05,
+      "loss": 3.002,
+      "step": 546
+    },
+    {
+      "epoch": 0.6732186732186732,
+      "grad_norm": 1.7113556861877441,
+      "learning_rate": 7.920813110669445e-05,
+      "loss": 2.921,
+      "step": 548
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.6539169549942017,
+      "learning_rate": 7.904295944149157e-05,
+      "loss": 2.7657,
+      "step": 550
+    },
+    {
+      "epoch": 0.6781326781326781,
+      "grad_norm": 1.499321699142456,
+      "learning_rate": 7.887730806379641e-05,
+      "loss": 2.5954,
+      "step": 552
+    },
+    {
+      "epoch": 0.6805896805896806,
+      "grad_norm": 1.5506938695907593,
+      "learning_rate": 7.871117970972948e-05,
+      "loss": 2.9977,
+      "step": 554
+    },
+    {
+      "epoch": 0.683046683046683,
+      "grad_norm": 1.60562264919281,
+      "learning_rate": 7.854457712328957e-05,
+      "loss": 2.8725,
+      "step": 556
+    },
+    {
+      "epoch": 0.6855036855036855,
+      "grad_norm": 1.5586713552474976,
+      "learning_rate": 7.837750305630862e-05,
+      "loss": 2.7757,
+      "step": 558
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 1.4952479600906372,
+      "learning_rate": 7.820996026840607e-05,
+      "loss": 2.8109,
+      "step": 560
+    },
+    {
+      "epoch": 0.6904176904176904,
+      "grad_norm": 1.5375022888183594,
+      "learning_rate": 7.804195152694347e-05,
+      "loss": 2.8958,
+      "step": 562
+    },
+    {
+      "epoch": 0.6928746928746928,
+      "grad_norm": 1.5429644584655762,
+      "learning_rate": 7.787347960697863e-05,
+      "loss": 2.848,
+      "step": 564
+    },
+    {
+      "epoch": 0.6953316953316954,
+      "grad_norm": 1.5820600986480713,
+      "learning_rate": 7.77045472912199e-05,
+      "loss": 2.7349,
+      "step": 566
+    },
+    {
+      "epoch": 0.6977886977886978,
+      "grad_norm": 1.6391702890396118,
+      "learning_rate": 7.753515736998007e-05,
+      "loss": 2.7536,
+      "step": 568
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 1.8837157487869263,
+      "learning_rate": 7.736531264113041e-05,
+      "loss": 2.5788,
+      "step": 570
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 1.6547040939331055,
+      "learning_rate": 7.719501591005436e-05,
+      "loss": 2.9089,
+      "step": 572
+    },
+    {
+      "epoch": 0.7051597051597052,
+      "grad_norm": 1.6191688776016235,
+      "learning_rate": 7.702426998960129e-05,
+      "loss": 2.7423,
+      "step": 574
+    },
+    {
+      "epoch": 0.7076167076167076,
+      "grad_norm": 1.63784658908844,
+      "learning_rate": 7.685307770003993e-05,
+      "loss": 2.9405,
+      "step": 576
+    },
+    {
+      "epoch": 0.7100737100737101,
+      "grad_norm": 1.7041395902633667,
+      "learning_rate": 7.668144186901189e-05,
+      "loss": 2.7419,
+      "step": 578
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 1.626767635345459,
+      "learning_rate": 7.650936533148485e-05,
+      "loss": 2.917,
+      "step": 580
+    },
+    {
+      "epoch": 0.714987714987715,
+      "grad_norm": 1.5805187225341797,
+      "learning_rate": 7.633685092970584e-05,
+      "loss": 2.9039,
+      "step": 582
+    },
+    {
+      "epoch": 0.7174447174447175,
+      "grad_norm": 1.5578582286834717,
+      "learning_rate": 7.616390151315422e-05,
+      "loss": 2.7313,
+      "step": 584
+    },
+    {
+      "epoch": 0.7199017199017199,
+      "grad_norm": 1.5582646131515503,
+      "learning_rate": 7.599051993849467e-05,
+      "loss": 2.4935,
+      "step": 586
+    },
+    {
+      "epoch": 0.7223587223587223,
+      "grad_norm": 1.6257047653198242,
+      "learning_rate": 7.58167090695299e-05,
+      "loss": 2.9326,
+      "step": 588
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 1.534566879272461,
+      "learning_rate": 7.56424717771535e-05,
+      "loss": 2.7481,
+      "step": 590
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 4.033563137054443,
+      "learning_rate": 7.546781093930238e-05,
+      "loss": 2.6916,
+      "step": 592
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 1.7314389944076538,
+      "learning_rate": 7.529272944090935e-05,
+      "loss": 2.8562,
+      "step": 594
+    },
+    {
+      "epoch": 0.7321867321867321,
+      "grad_norm": 1.5590124130249023,
+      "learning_rate": 7.511723017385538e-05,
+      "loss": 2.6231,
+      "step": 596
+    },
+    {
+      "epoch": 0.7346437346437347,
+      "grad_norm": 1.5711228847503662,
+      "learning_rate": 7.494131603692187e-05,
+      "loss": 2.7342,
+      "step": 598
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 1.6933467388153076,
+      "learning_rate": 7.476498993574277e-05,
+      "loss": 2.8793,
+      "step": 600
+    },
+    {
+      "epoch": 0.7395577395577395,
+      "grad_norm": 1.652563214302063,
+      "learning_rate": 7.45882547827566e-05,
+      "loss": 2.8555,
+      "step": 602
+    },
+    {
+      "epoch": 0.742014742014742,
+      "grad_norm": 1.5554332733154297,
+      "learning_rate": 7.441111349715832e-05,
+      "loss": 2.7455,
+      "step": 604
+    },
+    {
+      "epoch": 0.7444717444717445,
+      "grad_norm": 1.5497958660125732,
+      "learning_rate": 7.423356900485108e-05,
+      "loss": 2.7962,
+      "step": 606
+    },
+    {
+      "epoch": 0.7469287469287469,
+      "grad_norm": 2.072221040725708,
+      "learning_rate": 7.405562423839801e-05,
+      "loss": 2.7827,
+      "step": 608
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 1.6481581926345825,
+      "learning_rate": 7.387728213697365e-05,
+      "loss": 2.7402,
+      "step": 610
+    },
+    {
+      "epoch": 0.7518427518427518,
+      "grad_norm": 1.605137825012207,
+      "learning_rate": 7.369854564631548e-05,
+      "loss": 2.9223,
+      "step": 612
+    },
+    {
+      "epoch": 0.7542997542997543,
+      "grad_norm": 1.502097725868225,
+      "learning_rate": 7.351941771867523e-05,
+      "loss": 2.811,
+      "step": 614
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 1.4896032810211182,
+      "learning_rate": 7.333990131277013e-05,
+      "loss": 2.7072,
+      "step": 616
+    },
+    {
+      "epoch": 0.7592137592137592,
+      "grad_norm": 1.5070993900299072,
+      "learning_rate": 7.315999939373404e-05,
+      "loss": 2.6862,
+      "step": 618
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 1.5684906244277954,
+      "learning_rate": 7.297971493306848e-05,
+      "loss": 2.9692,
+      "step": 620
+    },
+    {
+      "epoch": 0.7641277641277642,
+      "grad_norm": 1.6148993968963623,
+      "learning_rate": 7.279905090859352e-05,
+      "loss": 2.6739,
+      "step": 622
+    },
+    {
+      "epoch": 0.7665847665847666,
+      "grad_norm": 1.8809860944747925,
+      "learning_rate": 7.261801030439864e-05,
+      "loss": 2.6416,
+      "step": 624
+    },
+    {
+      "epoch": 0.769041769041769,
+      "grad_norm": 1.9866212606430054,
+      "learning_rate": 7.243659611079343e-05,
+      "loss": 2.6516,
+      "step": 626
+    },
+    {
+      "epoch": 0.7714987714987716,
+      "grad_norm": 1.5821627378463745,
+      "learning_rate": 7.225481132425812e-05,
+      "loss": 2.5458,
+      "step": 628
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 2.8795077800750732,
+      "learning_rate": 7.20726589473942e-05,
+      "loss": 2.7961,
+      "step": 630
+    },
+    {
+      "epoch": 0.7764127764127764,
+      "grad_norm": 1.6154601573944092,
+      "learning_rate": 7.189014198887478e-05,
+      "loss": 2.9093,
+      "step": 632
+    },
+    {
+      "epoch": 0.7788697788697788,
+      "grad_norm": 1.677990436553955,
+      "learning_rate": 7.170726346339488e-05,
+      "loss": 2.888,
+      "step": 634
+    },
+    {
+      "epoch": 0.7813267813267813,
+      "grad_norm": 2.146972417831421,
+      "learning_rate": 7.15240263916216e-05,
+      "loss": 2.7926,
+      "step": 636
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 1.5269049406051636,
+      "learning_rate": 7.134043380014436e-05,
+      "loss": 2.6542,
+      "step": 638
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 1.5493632555007935,
+      "learning_rate": 7.115648872142475e-05,
+      "loss": 2.5847,
+      "step": 640
+    },
+    {
+      "epoch": 0.7886977886977887,
+      "grad_norm": 1.7266803979873657,
+      "learning_rate": 7.097219419374652e-05,
+      "loss": 2.8569,
+      "step": 642
+    },
+    {
+      "epoch": 0.7911547911547911,
+      "grad_norm": 1.5810487270355225,
+      "learning_rate": 7.078755326116542e-05,
+      "loss": 2.5271,
+      "step": 644
+    },
+    {
+      "epoch": 0.7936117936117936,
+      "grad_norm": 1.8903851509094238,
+      "learning_rate": 7.060256897345888e-05,
+      "loss": 2.8828,
+      "step": 646
+    },
+    {
+      "epoch": 0.7960687960687961,
+      "grad_norm": 1.6093307733535767,
+      "learning_rate": 7.041724438607563e-05,
+      "loss": 2.9436,
+      "step": 648
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 1.629585862159729,
+      "learning_rate": 7.023158256008521e-05,
+      "loss": 2.9666,
+      "step": 650
+    },
+    {
+      "epoch": 0.800982800982801,
+      "grad_norm": 1.62311851978302,
+      "learning_rate": 7.004558656212753e-05,
+      "loss": 2.8761,
+      "step": 652
+    },
+    {
+      "epoch": 0.8034398034398035,
+      "grad_norm": 1.5945847034454346,
+      "learning_rate": 6.985925946436213e-05,
+      "loss": 2.8419,
+      "step": 654
+    },
+    {
+      "epoch": 0.8058968058968059,
+      "grad_norm": 1.5463379621505737,
+      "learning_rate": 6.967260434441729e-05,
+      "loss": 2.7639,
+      "step": 656
+    },
+    {
+      "epoch": 0.8083538083538083,
+      "grad_norm": 3.601102590560913,
+      "learning_rate": 6.948562428533955e-05,
+      "loss": 2.8573,
+      "step": 658
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.59696364402771,
+      "learning_rate": 6.929832237554241e-05,
+      "loss": 2.8708,
+      "step": 660
+    },
+    {
+      "epoch": 0.8132678132678133,
+      "grad_norm": 1.577546238899231,
+      "learning_rate": 6.911070170875562e-05,
+      "loss": 2.8815,
+      "step": 662
+    },
+    {
+      "epoch": 0.8157248157248157,
+      "grad_norm": 1.4518203735351562,
+      "learning_rate": 6.892276538397384e-05,
+      "loss": 2.7745,
+      "step": 664
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 1.5612823963165283,
+      "learning_rate": 6.873451650540566e-05,
+      "loss": 2.6452,
+      "step": 666
+    },
+    {
+      "epoch": 0.8206388206388207,
+      "grad_norm": 1.5459407567977905,
+      "learning_rate": 6.854595818242213e-05,
+      "loss": 2.8471,
+      "step": 668
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 1.6408060789108276,
+      "learning_rate": 6.835709352950557e-05,
+      "loss": 2.8203,
+      "step": 670
+    },
+    {
+      "epoch": 0.8255528255528255,
+      "grad_norm": 1.6304421424865723,
+      "learning_rate": 6.816792566619806e-05,
+      "loss": 2.6816,
+      "step": 672
+    },
+    {
+      "epoch": 0.828009828009828,
+      "grad_norm": 1.6135345697402954,
+      "learning_rate": 6.797845771704983e-05,
+      "loss": 2.7026,
+      "step": 674
+    },
+    {
+      "epoch": 0.8304668304668305,
+      "grad_norm": 1.6707392930984497,
+      "learning_rate": 6.778869281156784e-05,
+      "loss": 2.8929,
+      "step": 676
+    },
+    {
+      "epoch": 0.8329238329238329,
+      "grad_norm": 1.621004581451416,
+      "learning_rate": 6.759863408416386e-05,
+      "loss": 2.7963,
+      "step": 678
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 1.5636838674545288,
+      "learning_rate": 6.740828467410294e-05,
+      "loss": 2.9369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 1.6135865449905396,
+      "learning_rate": 6.721764772545135e-05,
+      "loss": 2.5881,
+      "step": 682
+    },
+    {
+      "epoch": 0.8402948402948403,
+      "grad_norm": 1.6814947128295898,
+      "learning_rate": 6.702672638702475e-05,
+      "loss": 2.8039,
+      "step": 684
+    },
+    {
+      "epoch": 0.8427518427518428,
+      "grad_norm": 1.5667632818222046,
+      "learning_rate": 6.68355238123362e-05,
+      "loss": 2.8448,
+      "step": 686
+    },
+    {
+      "epoch": 0.8452088452088452,
+      "grad_norm": 1.6321567296981812,
+      "learning_rate": 6.664404315954397e-05,
+      "loss": 2.7062,
+      "step": 688
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 1.4741226434707642,
+      "learning_rate": 6.64522875913995e-05,
+      "loss": 2.8175,
+      "step": 690
+    },
+    {
+      "epoch": 0.8501228501228502,
+      "grad_norm": 1.583012580871582,
+      "learning_rate": 6.626026027519509e-05,
+      "loss": 2.7698,
+      "step": 692
+    },
+    {
+      "epoch": 0.8525798525798526,
+      "grad_norm": 1.650833010673523,
+      "learning_rate": 6.606796438271156e-05,
+      "loss": 2.7542,
+      "step": 694
+    },
+    {
+      "epoch": 0.855036855036855,
+      "grad_norm": 1.736618161201477,
+      "learning_rate": 6.587540309016592e-05,
+      "loss": 2.5914,
+      "step": 696
+    },
+    {
+      "epoch": 0.8574938574938575,
+      "grad_norm": 1.5331878662109375,
+      "learning_rate": 6.568257957815893e-05,
+      "loss": 2.7587,
+      "step": 698
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 2.8066611289978027,
+      "learning_rate": 6.54894970316224e-05,
+      "loss": 2.5376,
+      "step": 700
+    },
+    {
+      "epoch": 0.8624078624078624,
+      "grad_norm": 1.8552104234695435,
+      "learning_rate": 6.529615863976684e-05,
+      "loss": 2.8213,
+      "step": 702
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 7.016737937927246,
+      "learning_rate": 6.510256759602857e-05,
+      "loss": 2.763,
+      "step": 704
+    },
+    {
+      "epoch": 0.8673218673218673,
+      "grad_norm": 8.383584022521973,
+      "learning_rate": 6.4908727098017e-05,
+      "loss": 2.8134,
+      "step": 706
+    },
+    {
+      "epoch": 0.8697788697788698,
+      "grad_norm": 2.5546131134033203,
+      "learning_rate": 6.4714640347462e-05,
+      "loss": 2.5981,
+      "step": 708
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 1.4681930541992188,
+      "learning_rate": 6.452031055016073e-05,
+      "loss": 2.6272,
+      "step": 710
+    },
+    {
+      "epoch": 0.8746928746928747,
+      "grad_norm": 1.540204405784607,
+      "learning_rate": 6.432574091592494e-05,
+      "loss": 2.6063,
+      "step": 712
+    },
+    {
+      "epoch": 0.8771498771498771,
+      "grad_norm": 2.637376308441162,
+      "learning_rate": 6.41309346585278e-05,
+      "loss": 2.931,
+      "step": 714
+    },
+    {
+      "epoch": 0.8796068796068796,
+      "grad_norm": 1.6025326251983643,
+      "learning_rate": 6.393589499565088e-05,
+      "loss": 2.6114,
+      "step": 716
+    },
+    {
+      "epoch": 0.8820638820638821,
+      "grad_norm": 1.6360759735107422,
+      "learning_rate": 6.374062514883099e-05,
+      "loss": 2.8207,
+      "step": 718
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 1.5794533491134644,
+      "learning_rate": 6.354512834340695e-05,
+      "loss": 2.6199,
+      "step": 720
+    },
+    {
+      "epoch": 0.8869778869778869,
+      "grad_norm": 1.4947880506515503,
+      "learning_rate": 6.334940780846634e-05,
+      "loss": 2.6621,
+      "step": 722
+    },
+    {
+      "epoch": 0.8894348894348895,
+      "grad_norm": 1.632408618927002,
+      "learning_rate": 6.315346677679218e-05,
+      "loss": 2.8979,
+      "step": 724
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 1.636464238166809,
+      "learning_rate": 6.295730848480947e-05,
+      "loss": 2.714,
+      "step": 726
+    },
+    {
+      "epoch": 0.8943488943488943,
+      "grad_norm": 1.55814790725708,
+      "learning_rate": 6.276093617253182e-05,
+      "loss": 2.7157,
+      "step": 728
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 1.559779405593872,
+      "learning_rate": 6.256435308350786e-05,
+      "loss": 2.6694,
+      "step": 730
+    },
+    {
+      "epoch": 0.8992628992628993,
+      "grad_norm": 1.5911952257156372,
+      "learning_rate": 6.236756246476765e-05,
+      "loss": 2.8256,
+      "step": 732
+    },
+    {
+      "epoch": 0.9017199017199017,
+      "grad_norm": 1.542946457862854,
+      "learning_rate": 6.217056756676917e-05,
+      "loss": 2.5519,
+      "step": 734
+    },
+    {
+      "epoch": 0.9041769041769042,
+      "grad_norm": 1.6930584907531738,
+      "learning_rate": 6.197337164334453e-05,
+      "loss": 2.8785,
+      "step": 736
+    },
+    {
+      "epoch": 0.9066339066339066,
+      "grad_norm": 1.5558332204818726,
+      "learning_rate": 6.177597795164616e-05,
+      "loss": 2.6596,
+      "step": 738
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.4722115993499756,
+      "learning_rate": 6.157838975209323e-05,
+      "loss": 2.5197,
+      "step": 740
+    },
+    {
+      "epoch": 0.9115479115479116,
+      "grad_norm": 1.4730453491210938,
+      "learning_rate": 6.138061030831755e-05,
+      "loss": 2.8153,
+      "step": 742
+    },
+    {
+      "epoch": 0.914004914004914,
+      "grad_norm": 1.6478359699249268,
+      "learning_rate": 6.118264288710988e-05,
+      "loss": 2.7405,
+      "step": 744
+    },
+    {
+      "epoch": 0.9164619164619164,
+      "grad_norm": 1.4796196222305298,
+      "learning_rate": 6.098449075836575e-05,
+      "loss": 2.753,
+      "step": 746
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 1.9191288948059082,
+      "learning_rate": 6.0786157195031653e-05,
+      "loss": 2.6252,
+      "step": 748
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 1.553387999534607,
+      "learning_rate": 6.058764547305088e-05,
+      "loss": 2.8045,
+      "step": 750
+    },
+    {
+      "epoch": 0.9238329238329238,
+      "grad_norm": 1.4824281930923462,
+      "learning_rate": 6.038895887130942e-05,
+      "loss": 2.7996,
+      "step": 752
+    },
+    {
+      "epoch": 0.9262899262899262,
+      "grad_norm": 1.5677618980407715,
+      "learning_rate": 6.019010067158181e-05,
+      "loss": 2.891,
+      "step": 754
+    },
+    {
+      "epoch": 0.9287469287469288,
+      "grad_norm": 1.6281031370162964,
+      "learning_rate": 5.9991074158476935e-05,
+      "loss": 2.7762,
+      "step": 756
+    },
+    {
+      "epoch": 0.9312039312039312,
+      "grad_norm": 1.5614237785339355,
+      "learning_rate": 5.9791882619383766e-05,
+      "loss": 2.726,
+      "step": 758
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 1.446755290031433,
+      "learning_rate": 5.959252934441707e-05,
+      "loss": 2.5548,
+      "step": 760
+    },
+    {
+      "epoch": 0.9361179361179361,
+      "grad_norm": 1.5004243850708008,
+      "learning_rate": 5.939301762636307e-05,
+      "loss": 2.8673,
+      "step": 762
+    },
+    {
+      "epoch": 0.9385749385749386,
+      "grad_norm": 8.901308059692383,
+      "learning_rate": 5.9193350760625014e-05,
+      "loss": 2.6982,
+      "step": 764
+    },
+    {
+      "epoch": 0.941031941031941,
+      "grad_norm": 1.6001726388931274,
+      "learning_rate": 5.8993532045168795e-05,
+      "loss": 2.6233,
+      "step": 766
+    },
+    {
+      "epoch": 0.9434889434889435,
+      "grad_norm": 1.5054491758346558,
+      "learning_rate": 5.879356478046849e-05,
+      "loss": 2.7115,
+      "step": 768
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 1.4467328786849976,
+      "learning_rate": 5.8593452269451775e-05,
+      "loss": 2.6884,
+      "step": 770
+    },
+    {
+      "epoch": 0.9484029484029484,
+      "grad_norm": 1.4677785634994507,
+      "learning_rate": 5.839319781744542e-05,
+      "loss": 2.845,
+      "step": 772
+    },
+    {
+      "epoch": 0.9508599508599509,
+      "grad_norm": 1.5005624294281006,
+      "learning_rate": 5.81928047321207e-05,
+      "loss": 2.6341,
+      "step": 774
+    },
+    {
+      "epoch": 0.9533169533169533,
+      "grad_norm": 1.468900442123413,
+      "learning_rate": 5.79922763234387e-05,
+      "loss": 2.6078,
+      "step": 776
+    },
+    {
+      "epoch": 0.9557739557739557,
+      "grad_norm": 1.5839577913284302,
+      "learning_rate": 5.779161590359573e-05,
+      "loss": 2.6946,
+      "step": 778
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 1.5110023021697998,
+      "learning_rate": 5.7590826786968576e-05,
+      "loss": 2.6369,
+      "step": 780
+    },
+    {
+      "epoch": 0.9606879606879607,
+      "grad_norm": 1.4900883436203003,
+      "learning_rate": 5.738991229005972e-05,
+      "loss": 2.5128,
+      "step": 782
+    },
+    {
+      "epoch": 0.9631449631449631,
+      "grad_norm": 1.5296499729156494,
+      "learning_rate": 5.7188875731442605e-05,
+      "loss": 2.5457,
+      "step": 784
+    },
+    {
+      "epoch": 0.9656019656019657,
+      "grad_norm": 1.5462408065795898,
+      "learning_rate": 5.6987720431706826e-05,
+      "loss": 2.5989,
+      "step": 786
+    },
+    {
+      "epoch": 0.9680589680589681,
+      "grad_norm": 1.476729154586792,
+      "learning_rate": 5.678644971340326e-05,
+      "loss": 2.9144,
+      "step": 788
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 1.6275049448013306,
+      "learning_rate": 5.658506690098916e-05,
+      "loss": 2.7696,
+      "step": 790
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 1.4835902452468872,
+      "learning_rate": 5.638357532077331e-05,
+      "loss": 2.5136,
+      "step": 792
+    },
+    {
+      "epoch": 0.9754299754299754,
+      "grad_norm": 1.526121973991394,
+      "learning_rate": 5.6181978300861046e-05,
+      "loss": 2.4791,
+      "step": 794
+    },
+    {
+      "epoch": 0.9778869778869779,
+      "grad_norm": 1.4545388221740723,
+      "learning_rate": 5.598027917109929e-05,
+      "loss": 2.5994,
+      "step": 796
+    },
+    {
+      "epoch": 0.9803439803439803,
+      "grad_norm": 2.1908226013183594,
+      "learning_rate": 5.577848126302152e-05,
+      "loss": 2.8895,
+      "step": 798
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 1.504654049873352,
+      "learning_rate": 5.55765879097928e-05,
+      "loss": 2.7705,
+      "step": 800
+    },
+    {
+      "epoch": 0.9852579852579852,
+      "grad_norm": 1.6015645265579224,
+      "learning_rate": 5.5374602446154665e-05,
+      "loss": 2.845,
+      "step": 802
+    },
+    {
+      "epoch": 0.9877149877149877,
+      "grad_norm": 1.4529505968093872,
+      "learning_rate": 5.517252820837011e-05,
+      "loss": 2.5013,
+      "step": 804
+    },
+    {
+      "epoch": 0.9901719901719902,
+      "grad_norm": 1.4882707595825195,
+      "learning_rate": 5.49703685341684e-05,
+      "loss": 2.7789,
+      "step": 806
+    },
+    {
+      "epoch": 0.9926289926289926,
+      "grad_norm": 1.589077353477478,
+      "learning_rate": 5.4768126762690034e-05,
+      "loss": 2.6236,
+      "step": 808
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 1.4018021821975708,
+      "learning_rate": 5.456580623443145e-05,
+      "loss": 2.6779,
+      "step": 810
+    },
+    {
+      "epoch": 0.9975429975429976,
+      "grad_norm": 1.4764320850372314,
+      "learning_rate": 5.436341029119004e-05,
+      "loss": 2.7036,
+      "step": 812
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.599942684173584,
+      "learning_rate": 5.416094227600881e-05,
+      "loss": 3.0131,
+      "step": 814
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1628,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 814,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3763952104177664e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-814/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d82c066c91a79366b3e96e9c460da879e9a732d59289e5adf55018f93502588
+size 5432

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/OLMo-2-1124-7B-ban_Latn-coli-rand/",
+  "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 sha256:034c747954dfc5929edfeb1bf860f8798f063adc1dc0ef549ca6126107079e7e
+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 sha256:6a2a54dccfae7d16cab544c00d4a49ba6760c28e81adad87271da71096a67e12
+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 sha256:5d82c066c91a79366b3e96e9c460da879e9a732d59289e5adf55018f93502588
+size 5432