adding model files

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "</headline>": 32008,
+  "</scratchpad>": 32006,
+  "<</SYS>>": 32004,
+  "<<SYS>>": 32003,
+  "<headline>": 32007,
+  "<pad>": 32000,
+  "<scratchpad>": 32005,
+  "[/INST]": 32002,
+  "[INST]": 32001
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "teknium/OpenHermes-13B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.2",
+  "use_cache": false
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0cae2a615dd910189ffed31c589276f2bbc7726b92d014ee1f27ab9e60d46b
+size 4881575536

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64ab9fbc554a39a6a05f30deff45f2ae8e1305100dd39b495b5303a7c362ff2
+size 4970418112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690b455aa833cf46ebf885598913d04f805c2c2646bd3fd698aeeb7e3f8c5aaa
+size 4970418120

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e35ab153b03753c08517fd067da9e473ca83b3b9e8fd2dce17c2b21555f4c62
+size 4970418144

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faecf7c66b9a030846f124213e1aeaf40dc8cdcff7dcd9b1c937db2f21680c50
+size 4970418144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea880fcb64291e3cb8e8f0939be5aa824b397ab96eff0e51ebd8cfe2b11cd9f5
+size 4792119040

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2727e95824d423695b3d8550c20d14be7b13dff66d1a463ab9aa32e98e0bbef5
+size 4792160232

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4aa3e9849dfaf2fc0e6bd6d5759a6d69dc5097033cf50c5135cfdd097eb6d8
+size 4792160224

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4e75e83462c2ba9cdf6b616ffc90b965cb68491be6eebe08e9d995a5c391fc
+size 4970418144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540731d34e4b647eed6a1aafbbe82de396296caaa7a5c26e091a8131d8f91c8e
+size 4970418144

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fe6fc84898eb31e848e7253b64e096ff48eebb8f43a566b4148aeeae61b08f
+size 2983630864

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 52064112640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,88 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,128 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32002": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32003": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32004": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32005": {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32006": {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32007": {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32008": {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[INST]",
+    "[/INST]",
+    "<<SYS>>",
+    "<</SYS>>",
+    "<scratchpad>",
+    "</scratchpad>",
+    "<headline>",
+    "</headline>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": 8,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,929 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 50,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0026666666666666666,
+      "eval_loss": 2.2441093921661377,
+      "eval_runtime": 2.1394,
+      "eval_samples_per_second": 72.919,
+      "eval_steps_per_second": 3.739,
+      "step": 2
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 13.812788009643555,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.4545,
+      "step": 50
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "eval_loss": 0.7968010902404785,
+      "eval_runtime": 1.9308,
+      "eval_samples_per_second": 80.794,
+      "eval_steps_per_second": 4.143,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 14.612204551696777,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.6877,
+      "step": 100
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 0.7099941968917847,
+      "eval_runtime": 1.9396,
+      "eval_samples_per_second": 80.427,
+      "eval_steps_per_second": 4.124,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.911639213562012,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6406,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.7064129710197449,
+      "eval_runtime": 1.9386,
+      "eval_samples_per_second": 80.47,
+      "eval_steps_per_second": 4.127,
+      "step": 150
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4.795286655426025,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.6159,
+      "step": 200
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.7062311172485352,
+      "eval_runtime": 1.937,
+      "eval_samples_per_second": 80.535,
+      "eval_steps_per_second": 4.13,
+      "step": 200
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.772829055786133,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.645,
+      "step": 250
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 0.7101395726203918,
+      "eval_runtime": 1.9368,
+      "eval_samples_per_second": 80.545,
+      "eval_steps_per_second": 4.131,
+      "step": 250
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.455453395843506,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6779,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.7204328179359436,
+      "eval_runtime": 1.9515,
+      "eval_samples_per_second": 79.937,
+      "eval_steps_per_second": 4.099,
+      "step": 300
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 3.8921704292297363,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.6739,
+      "step": 350
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "eval_loss": 0.7367281317710876,
+      "eval_runtime": 1.9424,
+      "eval_samples_per_second": 80.313,
+      "eval_steps_per_second": 4.119,
+      "step": 350
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.5156171321868896,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.6666,
+      "step": 400
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.7475255131721497,
+      "eval_runtime": 1.9493,
+      "eval_samples_per_second": 80.028,
+      "eval_steps_per_second": 4.104,
+      "step": 400
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.8510982990264893,
+      "learning_rate": 2e-05,
+      "loss": 0.678,
+      "step": 450
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.7600880861282349,
+      "eval_runtime": 1.9393,
+      "eval_samples_per_second": 80.442,
+      "eval_steps_per_second": 4.125,
+      "step": 450
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.131458282470703,
+      "learning_rate": 1.9992479525042305e-05,
+      "loss": 0.6761,
+      "step": 500
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.7700127363204956,
+      "eval_runtime": 1.9451,
+      "eval_samples_per_second": 80.203,
+      "eval_steps_per_second": 4.113,
+      "step": 500
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 2.8056657314300537,
+      "learning_rate": 1.996992941167792e-05,
+      "loss": 0.7065,
+      "step": 550
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "eval_loss": 0.7661844491958618,
+      "eval_runtime": 1.985,
+      "eval_samples_per_second": 78.589,
+      "eval_steps_per_second": 4.03,
+      "step": 550
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.530026912689209,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.7292,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.7726808190345764,
+      "eval_runtime": 1.9778,
+      "eval_samples_per_second": 78.876,
+      "eval_steps_per_second": 4.045,
+      "step": 600
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 3.747391700744629,
+      "learning_rate": 1.9879898494768093e-05,
+      "loss": 0.7048,
+      "step": 650
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "eval_loss": 0.77761310338974,
+      "eval_runtime": 1.9355,
+      "eval_samples_per_second": 80.6,
+      "eval_steps_per_second": 4.133,
+      "step": 650
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.626871347427368,
+      "learning_rate": 1.9812553106273848e-05,
+      "loss": 0.7399,
+      "step": 700
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 0.7751242518424988,
+      "eval_runtime": 1.9443,
+      "eval_samples_per_second": 80.235,
+      "eval_steps_per_second": 4.115,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.370767831802368,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.6998,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7795637249946594,
+      "eval_runtime": 1.964,
+      "eval_samples_per_second": 79.43,
+      "eval_steps_per_second": 4.073,
+      "step": 750
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 2.8861231803894043,
+      "learning_rate": 1.9633708786158803e-05,
+      "loss": 0.3823,
+      "step": 800
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 0.8237621784210205,
+      "eval_runtime": 1.9417,
+      "eval_samples_per_second": 80.343,
+      "eval_steps_per_second": 4.12,
+      "step": 800
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 2.800626754760742,
+      "learning_rate": 1.9522478853384154e-05,
+      "loss": 0.3672,
+      "step": 850
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "eval_loss": 0.8094993233680725,
+      "eval_runtime": 1.941,
+      "eval_samples_per_second": 80.371,
+      "eval_steps_per_second": 4.122,
+      "step": 850
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.921535611152649,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3982,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.8282511830329895,
+      "eval_runtime": 1.9446,
+      "eval_samples_per_second": 80.223,
+      "eval_steps_per_second": 4.114,
+      "step": 900
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 3.1929402351379395,
+      "learning_rate": 1.9257239692688907e-05,
+      "loss": 0.408,
+      "step": 950
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "eval_loss": 0.8225230574607849,
+      "eval_runtime": 1.9396,
+      "eval_samples_per_second": 80.428,
+      "eval_steps_per_second": 4.125,
+      "step": 950
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.0759708881378174,
+      "learning_rate": 1.9103629409661468e-05,
+      "loss": 0.3856,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.8219059705734253,
+      "eval_runtime": 1.9374,
+      "eval_samples_per_second": 80.521,
+      "eval_steps_per_second": 4.129,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.7090229988098145,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.3798,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.8336038589477539,
+      "eval_runtime": 1.9583,
+      "eval_samples_per_second": 79.66,
+      "eval_steps_per_second": 4.085,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 3.3651938438415527,
+      "learning_rate": 1.8755582313020912e-05,
+      "loss": 0.3906,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "eval_loss": 0.8176392912864685,
+      "eval_runtime": 1.947,
+      "eval_samples_per_second": 80.123,
+      "eval_steps_per_second": 4.109,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 2.7494823932647705,
+      "learning_rate": 1.8561668995302668e-05,
+      "loss": 0.4051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "eval_loss": 0.809560239315033,
+      "eval_runtime": 1.9379,
+      "eval_samples_per_second": 80.499,
+      "eval_steps_per_second": 4.128,
+      "step": 1150
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.4698486328125,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.3901,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.902604341506958,
+      "eval_runtime": 1.9678,
+      "eval_samples_per_second": 79.278,
+      "eval_steps_per_second": 4.066,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.4756592512130737,
+      "learning_rate": 1.8135520702629677e-05,
+      "loss": 0.3959,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.822571873664856,
+      "eval_runtime": 1.9359,
+      "eval_samples_per_second": 80.581,
+      "eval_steps_per_second": 4.132,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 3.273878812789917,
+      "learning_rate": 1.7903926695187595e-05,
+      "loss": 0.4275,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "eval_loss": 0.8240092396736145,
+      "eval_runtime": 1.9541,
+      "eval_samples_per_second": 79.831,
+      "eval_steps_per_second": 4.094,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.898964762687683,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.4102,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.8196238875389099,
+      "eval_runtime": 1.9631,
+      "eval_samples_per_second": 79.467,
+      "eval_steps_per_second": 4.075,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.8440319299697876,
+      "learning_rate": 1.740544013109005e-05,
+      "loss": 0.4063,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "eval_loss": 0.826339840888977,
+      "eval_runtime": 1.9444,
+      "eval_samples_per_second": 80.232,
+      "eval_steps_per_second": 4.114,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.9113894701004028,
+      "learning_rate": 1.7139297345578992e-05,
+      "loss": 0.4157,
+      "step": 1450
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "eval_loss": 0.809698760509491,
+      "eval_runtime": 1.9623,
+      "eval_samples_per_second": 79.5,
+      "eval_steps_per_second": 4.077,
+      "step": 1450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8541122674942017,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.4078,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8137311935424805,
+      "eval_runtime": 1.9502,
+      "eval_samples_per_second": 79.991,
+      "eval_steps_per_second": 4.102,
+      "step": 1500
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 2.6007161140441895,
+      "learning_rate": 1.657521368569064e-05,
+      "loss": 0.1949,
+      "step": 1550
+    },
+    {
+      "epoch": 2.066666666666667,
+      "eval_loss": 0.8720932006835938,
+      "eval_runtime": 1.9736,
+      "eval_samples_per_second": 79.045,
+      "eval_steps_per_second": 4.054,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.146995186805725,
+      "learning_rate": 1.627812124672099e-05,
+      "loss": 0.2022,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 0.8959416151046753,
+      "eval_runtime": 1.935,
+      "eval_samples_per_second": 80.621,
+      "eval_steps_per_second": 4.134,
+      "step": 1600
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.6238232851028442,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.2048,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 0.9047269821166992,
+      "eval_runtime": 1.9624,
+      "eval_samples_per_second": 79.494,
+      "eval_steps_per_second": 4.077,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.9952141046524048,
+      "learning_rate": 1.5656068754865388e-05,
+      "loss": 0.2025,
+      "step": 1700
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "eval_loss": 0.8975375294685364,
+      "eval_runtime": 1.9628,
+      "eval_samples_per_second": 79.479,
+      "eval_steps_per_second": 4.076,
+      "step": 1700
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 2.458026170730591,
+      "learning_rate": 1.5332044328016916e-05,
+      "loss": 0.203,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "eval_loss": 0.9088010787963867,
+      "eval_runtime": 1.9857,
+      "eval_samples_per_second": 78.561,
+      "eval_steps_per_second": 4.029,
+      "step": 1750
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8629381060600281,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2021,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9120263457298279,
+      "eval_runtime": 1.974,
+      "eval_samples_per_second": 79.027,
+      "eval_steps_per_second": 4.053,
+      "step": 1800
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 1.108939528465271,
+      "learning_rate": 1.4660435197025391e-05,
+      "loss": 0.2105,
+      "step": 1850
+    },
+    {
+      "epoch": 2.466666666666667,
+      "eval_loss": 0.8986693024635315,
+      "eval_runtime": 1.9334,
+      "eval_samples_per_second": 80.686,
+      "eval_steps_per_second": 4.138,
+      "step": 1850
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.5985965728759766,
+      "learning_rate": 1.4313860656812537e-05,
+      "loss": 0.198,
+      "step": 1900
+    },
+    {
+      "epoch": 2.533333333333333,
+      "eval_loss": 0.912500262260437,
+      "eval_runtime": 1.9589,
+      "eval_samples_per_second": 79.637,
+      "eval_steps_per_second": 4.084,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.7191044092178345,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.2036,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.9057779312133789,
+      "eval_runtime": 1.9653,
+      "eval_samples_per_second": 79.376,
+      "eval_steps_per_second": 4.071,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 3.347895860671997,
+      "learning_rate": 1.3601777248047105e-05,
+      "loss": 0.2095,
+      "step": 2000
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.9151327610015869,
+      "eval_runtime": 1.9423,
+      "eval_samples_per_second": 80.319,
+      "eval_steps_per_second": 4.119,
+      "step": 2000
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 2.2837843894958496,
+      "learning_rate": 1.3237339420583213e-05,
+      "loss": 0.2086,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "eval_loss": 0.8929597735404968,
+      "eval_runtime": 1.9354,
+      "eval_samples_per_second": 80.604,
+      "eval_steps_per_second": 4.134,
+      "step": 2050
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.551108717918396,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.2193,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.9003872871398926,
+      "eval_runtime": 1.9656,
+      "eval_samples_per_second": 79.364,
+      "eval_steps_per_second": 4.07,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 1.4159841537475586,
+      "learning_rate": 1.2494411440579814e-05,
+      "loss": 0.1949,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "eval_loss": 0.908513605594635,
+      "eval_runtime": 1.936,
+      "eval_samples_per_second": 80.577,
+      "eval_steps_per_second": 4.132,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.6562224626541138,
+      "learning_rate": 1.211703872229411e-05,
+      "loss": 0.2101,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "eval_loss": 0.9001446962356567,
+      "eval_runtime": 1.9653,
+      "eval_samples_per_second": 79.377,
+      "eval_steps_per_second": 4.071,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3242262601852417,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.2113,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8952978253364563,
+      "eval_runtime": 1.9621,
+      "eval_samples_per_second": 79.505,
+      "eval_steps_per_second": 4.077,
+      "step": 2250
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 1.1005603075027466,
+      "learning_rate": 1.1353312997501313e-05,
+      "loss": 0.1217,
+      "step": 2300
+    },
+    {
+      "epoch": 3.066666666666667,
+      "eval_loss": 0.9499949216842651,
+      "eval_runtime": 1.9416,
+      "eval_samples_per_second": 80.345,
+      "eval_steps_per_second": 4.12,
+      "step": 2300
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 1.5264954566955566,
+      "learning_rate": 1.0968108707031792e-05,
+      "loss": 0.1258,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "eval_loss": 0.9499000906944275,
+      "eval_runtime": 1.9473,
+      "eval_samples_per_second": 80.109,
+      "eval_steps_per_second": 4.108,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.8560168743133545,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.1266,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 0.9572532773017883,
+      "eval_runtime": 1.935,
+      "eval_samples_per_second": 80.618,
+      "eval_steps_per_second": 4.134,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.8490918278694153,
+      "learning_rate": 1.0193913317718245e-05,
+      "loss": 0.1317,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "eval_loss": 0.9423532485961914,
+      "eval_runtime": 1.9683,
+      "eval_samples_per_second": 79.257,
+      "eval_steps_per_second": 4.064,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.1821798086166382,
+      "learning_rate": 9.806086682281759e-06,
+      "loss": 0.1302,
+      "step": 2500
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 0.9516943097114563,
+      "eval_runtime": 1.9297,
+      "eval_samples_per_second": 80.841,
+      "eval_steps_per_second": 4.146,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.8500071167945862,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.131,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4,
+      "eval_loss": 0.9390648007392883,
+      "eval_runtime": 1.9424,
+      "eval_samples_per_second": 80.312,
+      "eval_steps_per_second": 4.119,
+      "step": 2550
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.5849168300628662,
+      "learning_rate": 9.03189129296821e-06,
+      "loss": 0.1275,
+      "step": 2600
+    },
+    {
+      "epoch": 3.466666666666667,
+      "eval_loss": 0.9507057070732117,
+      "eval_runtime": 1.9348,
+      "eval_samples_per_second": 80.627,
+      "eval_steps_per_second": 4.135,
+      "step": 2600
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 1.1941384077072144,
+      "learning_rate": 8.646687002498692e-06,
+      "loss": 0.1253,
+      "step": 2650
+    },
+    {
+      "epoch": 3.533333333333333,
+      "eval_loss": 0.9462794661521912,
+      "eval_runtime": 1.9308,
+      "eval_samples_per_second": 80.797,
+      "eval_steps_per_second": 4.143,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.1456445455551147,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.1253,
+      "step": 2700
+    },
+    {
+      "epoch": 3.6,
+      "eval_loss": 0.9547935724258423,
+      "eval_runtime": 1.9666,
+      "eval_samples_per_second": 79.326,
+      "eval_steps_per_second": 4.068,
+      "step": 2700
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 1.1091175079345703,
+      "learning_rate": 7.882961277705897e-06,
+      "loss": 0.1288,
+      "step": 2750
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "eval_loss": 0.9615420699119568,
+      "eval_runtime": 1.9482,
+      "eval_samples_per_second": 80.075,
+      "eval_steps_per_second": 4.106,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.9740545153617859,
+      "learning_rate": 7.505588559420188e-06,
+      "loss": 0.1264,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "eval_loss": 0.9537524580955505,
+      "eval_runtime": 1.9575,
+      "eval_samples_per_second": 79.692,
+      "eval_steps_per_second": 4.087,
+      "step": 2800
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.9862896800041199,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.1274,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 0.9457467198371887,
+      "eval_runtime": 1.9325,
+      "eval_samples_per_second": 80.723,
+      "eval_steps_per_second": 4.14,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 0.7105234265327454,
+      "learning_rate": 6.762660579416791e-06,
+      "loss": 0.1288,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "eval_loss": 0.940463125705719,
+      "eval_runtime": 1.9277,
+      "eval_samples_per_second": 80.924,
+      "eval_steps_per_second": 4.15,
+      "step": 2900
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 1.2161469459533691,
+      "learning_rate": 6.3982227519528986e-06,
+      "loss": 0.1243,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "eval_loss": 0.9474909901618958,
+      "eval_runtime": 1.961,
+      "eval_samples_per_second": 79.553,
+      "eval_steps_per_second": 4.08,
+      "step": 2950
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7539545297622681,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.1298,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.945076584815979,
+      "eval_runtime": 1.9371,
+      "eval_samples_per_second": 80.534,
+      "eval_steps_per_second": 4.13,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1.1736354739401523e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10577b3bb45f69080db4ca130182bcafdcdc26c5606678e405cef9f5b13d11fc
+size 5112