Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151329,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a07beb7eb82efedb7366e9ed40de91efea0213ab4c351d166a40504f1fdb2e
+size 4964110224

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4141652e42adf345eee1599470db7f3578b3fac865f3e1c6f42403b60f73933
+size 4951627112

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377e781dc38dc345f1cd829a76a830d420b33dffe3ace2709fb79d007dd9203c
+size 4750251160

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff21a96e9921a3ba870e26be6c88ffd5d332b63e128b0a8116f05ae18516b2e2
+size 4467185280

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c645281d42e76335143bce1b045e42df6efa2a6ae5e0f08d574f32e6e399475
+size 4957918856

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edd1bdef651a86b9ac49936c0ad3301998dc473fe8b8274ddcce8c262bb4f9f
+size 4951627160

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9aab402d4af0fb0ab29f02905ce238af6816cf42039763da83bcf909ed788a
+size 4750251184

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741003d1a6b40e297f976a39157aeaee037544b5d51c4ba063943674e7c01575
+size 4467185280

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5fae354dc96af9ad1decddc846312e64ff7b893ccd09dd329ae2176ebe3324
+size 4957918856

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4026ec5ff03fc3fa24f1720342688a18b69321ec51208f01aa8d867d7f81e91
+size 4951627160

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2524d7cc36367c2d2c620ab34e9a9a9c9481ef5d33d0dce9a831795176d789
+size 4750251184

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2909bc23f7dc5032e58c29c67bd92d643b226a0810b67aa88240968a98f064fb
+size 4467185280

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fdc19d1292fea0bd492816e38410682a2575f18b238bd7cb6770117d8e5a9a
+size 4957918856

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69de5e70d460df619ff34734b0daa8c7bbe7185dc83586214817c367d7e0e0ef
+size 2787177488

model.safetensors.index.json

@@ -0,0 +1,621 @@
+{
+  "metadata": {
+    "total_parameters": 1505280,
+    "total_size": 65132163072
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,404 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004,
+      "grad_norm": 20.83503743012713,
+      "learning_rate": 0.0,
+      "loss": 1.9929,
+      "step": 1
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 43.45925720487911,
+      "learning_rate": 4.999999999999999e-07,
+      "loss": 2.0965,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 34.18390588136545,
+      "learning_rate": 6.505149978319905e-07,
+      "loss": 2.0602,
+      "step": 20
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 27.864272589144427,
+      "learning_rate": 7.38560627359831e-07,
+      "loss": 2.0778,
+      "step": 30
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 35.609909029437205,
+      "learning_rate": 8.01029995663981e-07,
+      "loss": 2.0888,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 23.33297023251517,
+      "learning_rate": 8.494850021680092e-07,
+      "loss": 2.064,
+      "step": 50
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 35.83386869510132,
+      "learning_rate": 8.890756251918216e-07,
+      "loss": 2.0856,
+      "step": 60
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 22.54353083862507,
+      "learning_rate": 9.225490200071283e-07,
+      "loss": 2.0496,
+      "step": 70
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 30.136085615180335,
+      "learning_rate": 9.515449934959715e-07,
+      "loss": 2.0554,
+      "step": 80
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 68.44218543524343,
+      "learning_rate": 9.771212547196622e-07,
+      "loss": 2.0578,
+      "step": 90,
+      "train/grad_norm": 0.0
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 25.623069449188854,
+      "learning_rate": 9.999999999999997e-07,
+      "loss": 2.0441,
+      "step": 100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 37.14087912962716,
+      "learning_rate": 9.99695443968197e-07,
+      "loss": 2.0572,
+      "step": 110
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 34.46641304389256,
+      "learning_rate": 9.987821469273991e-07,
+      "loss": 2.0485,
+      "step": 120
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 212.8287452523741,
+      "learning_rate": 9.972612215893683e-07,
+      "loss": 2.0647,
+      "step": 130
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 55.367715246454054,
+      "learning_rate": 9.951345209673481e-07,
+      "loss": 2.0478,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 31.03945521265294,
+      "learning_rate": 9.924046361184534e-07,
+      "loss": 2.059,
+      "step": 150
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 38.876781827855474,
+      "learning_rate": 9.890748929868662e-07,
+      "loss": 2.0556,
+      "step": 160
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 54.1903104922321,
+      "learning_rate": 9.851493483516842e-07,
+      "loss": 2.0415,
+      "step": 170
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 55.11628816930071,
+      "learning_rate": 9.806327848843624e-07,
+      "loss": 2.0655,
+      "step": 180
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 26.97245146968765,
+      "learning_rate": 9.75530705321762e-07,
+      "loss": 2.0754,
+      "step": 190,
+      "train/grad_norm": 0.0
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 22.263511489429174,
+      "learning_rate": 9.69849325761915e-07,
+      "loss": 2.0291,
+      "step": 200
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 40.77859688901546,
+      "learning_rate": 9.635955680906653e-07,
+      "loss": 2.0633,
+      "step": 210
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 22.619267431397528,
+      "learning_rate": 9.567770515484182e-07,
+      "loss": 2.0601,
+      "step": 220
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 41.43388162557619,
+      "learning_rate": 9.494020834472684e-07,
+      "loss": 2.0203,
+      "step": 230
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 20.201018907973786,
+      "learning_rate": 9.414796490498204e-07,
+      "loss": 2.0645,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 30.050916470650286,
+      "learning_rate": 9.330194006220302e-07,
+      "loss": 2.0813,
+      "step": 250
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 30.049843490600335,
+      "learning_rate": 9.24031645673405e-07,
+      "loss": 2.0678,
+      "step": 260
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 30.560708322783146,
+      "learning_rate": 9.145273343988931e-07,
+      "loss": 2.0737,
+      "step": 270
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 22.123281382761533,
+      "learning_rate": 9.045180463377549e-07,
+      "loss": 2.0392,
+      "step": 280
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 30.838671792268336,
+      "learning_rate": 8.940159762656805e-07,
+      "loss": 2.0591,
+      "step": 290,
+      "train/grad_norm": 0.0
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 41.098014895676286,
+      "learning_rate": 8.83033919337333e-07,
+      "loss": 2.053,
+      "step": 300
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 20.75530739464329,
+      "learning_rate": 8.715852554974232e-07,
+      "loss": 2.0513,
+      "step": 310
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 35.30518129856715,
+      "learning_rate": 8.596839331793086e-07,
+      "loss": 2.0203,
+      "step": 320
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 29.126621734644562,
+      "learning_rate": 8.473444523109757e-07,
+      "loss": 2.0516,
+      "step": 330
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 60.0509536695053,
+      "learning_rate": 8.345818466491111e-07,
+      "loss": 2.0346,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 34.04867198356122,
+      "learning_rate": 8.214116654627854e-07,
+      "loss": 2.0181,
+      "step": 350
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 21.00356347932767,
+      "learning_rate": 8.078499545890628e-07,
+      "loss": 2.0484,
+      "step": 360
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 26.575443230668622,
+      "learning_rate": 7.939132368836219e-07,
+      "loss": 2.04,
+      "step": 370
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 21.408930933647035,
+      "learning_rate": 7.796184920901999e-07,
+      "loss": 2.0392,
+      "step": 380
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 22.306054471587874,
+      "learning_rate": 7.649831361533908e-07,
+      "loss": 2.0567,
+      "step": 390,
+      "train/grad_norm": 0.0
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 36.12831562007634,
+      "learning_rate": 7.500249999999999e-07,
+      "loss": 2.0179,
+      "step": 400
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 23.842294906470897,
+      "learning_rate": 7.347623078148061e-07,
+      "loss": 1.9866,
+      "step": 410
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 21.883189031795506,
+      "learning_rate": 7.192136548371992e-07,
+      "loss": 2.0327,
+      "step": 420
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 27.455775863241843,
+      "learning_rate": 7.033979847057464e-07,
+      "loss": 2.04,
+      "step": 430
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 30.460092590260228,
+      "learning_rate": 6.873345663782851e-07,
+      "loss": 2.008,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 34.075344014202166,
+      "learning_rate": 6.710429706556681e-07,
+      "loss": 2.0087,
+      "step": 450
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 32.56016725035176,
+      "learning_rate": 6.545430463377549e-07,
+      "loss": 2.0134,
+      "step": 460
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 62.53402964557859,
+      "learning_rate": 6.378548960407088e-07,
+      "loss": 2.0397,
+      "step": 470
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 71.66034942508398,
+      "learning_rate": 6.209988517050537e-07,
+      "loss": 2.035,
+      "step": 480
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 39.3336859845859,
+      "learning_rate": 6.039954498243388e-07,
+      "loss": 2.0052,
+      "step": 490,
+      "train/grad_norm": 0.0
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 30.745716101151523,
+      "learning_rate": 5.86865406424582e-07,
+      "loss": 2.0438,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 2.082026958465576,
+      "eval_runtime": 33.6778,
+      "eval_samples_per_second": 3.237,
+      "eval_steps_per_second": 0.831,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.836546672033792e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf531d08434a04184e9650887d0f86576f78d1b55009273eab7dd44db3afc30
+size 7953