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:d1a1e3c7e7747c09f73e9990ec092b1e76c8b76e14fb0e5172ccf47c7c793575
+size 4881575536

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152585eedd0688bdbdf708b59cee778dbf2ff946f7046dd9b5eb64fd8b9e378b
+size 4970418112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4155fadcc36263a1a0a30ead70725839800b608b63d3c3d4c0c64ec67e6f8884
+size 4970418120

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfbbd72b1fd7b0b88c5c14ddf198b465e9f7be6cbf0e4d61adf5e84bc6b533c
+size 4970418144

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b34db8365078fdec80e0e59e8c0b5f270e965258eb65fa95b7bbeb3bc9ab28
+size 4970418144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ef2040c0c227d9e04a5877f065a0465b0e782ad7ec883341a315943eb8cdc1
+size 4792119040

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e132f278e22b923d17cbdb08171dac88e38cd123756e14ac7bf5277ce8da42
+size 4792160232

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ad02b786c233dcdafcb9a07b9fbb98f6393c1edeab75ac5178e1813ef8c133
+size 4792160224

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31661eb0c830f430ee9e493371624428873363285dd1f6faa3c01de3673562b6
+size 4970418144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af771c027a94d3f81b2b14372dffad52af9a3f7a29759a47fef1499818671b0
+size 4970418144

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35501a67a4c9a1dac82fef670fc130983cfe0e4b7bce3553adcea2407053b379
+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 +1,1581 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.619987269255251,
+  "eval_steps": 50,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06365372374283895,
+      "grad_norm": 8.618297576904297,
+      "learning_rate": 1.2738853503184715e-06,
+      "loss": 1.5929,
+      "step": 50
+    },
+    {
+      "epoch": 0.06365372374283895,
+      "eval_loss": 0.8718269467353821,
+      "eval_runtime": 1.9665,
+      "eval_samples_per_second": 79.328,
+      "eval_steps_per_second": 4.068,
+      "step": 50
+    },
+    {
+      "epoch": 0.1273074474856779,
+      "grad_norm": 13.18759822845459,
+      "learning_rate": 2.547770700636943e-06,
+      "loss": 0.7086,
+      "step": 100
+    },
+    {
+      "epoch": 0.1273074474856779,
+      "eval_loss": 0.7185815572738647,
+      "eval_runtime": 1.9537,
+      "eval_samples_per_second": 79.847,
+      "eval_steps_per_second": 4.095,
+      "step": 100
+    },
+    {
+      "epoch": 0.19096117122851686,
+      "grad_norm": 7.225034236907959,
+      "learning_rate": 3.821656050955415e-06,
+      "loss": 0.6164,
+      "step": 150
+    },
+    {
+      "epoch": 0.19096117122851686,
+      "eval_loss": 0.7371894717216492,
+      "eval_runtime": 1.9509,
+      "eval_samples_per_second": 79.963,
+      "eval_steps_per_second": 4.101,
+      "step": 150
+    },
+    {
+      "epoch": 0.2546148949713558,
+      "grad_norm": 3.914799213409424,
+      "learning_rate": 5.095541401273886e-06,
+      "loss": 0.6015,
+      "step": 200
+    },
+    {
+      "epoch": 0.2546148949713558,
+      "eval_loss": 0.6896682381629944,
+      "eval_runtime": 1.9812,
+      "eval_samples_per_second": 78.74,
+      "eval_steps_per_second": 4.038,
+      "step": 200
+    },
+    {
+      "epoch": 0.31826861871419476,
+      "grad_norm": 4.877476215362549,
+      "learning_rate": 6.369426751592357e-06,
+      "loss": 0.6245,
+      "step": 250
+    },
+    {
+      "epoch": 0.31826861871419476,
+      "eval_loss": 0.6881433725357056,
+      "eval_runtime": 1.9896,
+      "eval_samples_per_second": 78.407,
+      "eval_steps_per_second": 4.021,
+      "step": 250
+    },
+    {
+      "epoch": 0.3819223424570337,
+      "grad_norm": 4.47362756729126,
+      "learning_rate": 7.64331210191083e-06,
+      "loss": 0.5852,
+      "step": 300
+    },
+    {
+      "epoch": 0.3819223424570337,
+      "eval_loss": 0.6920483708381653,
+      "eval_runtime": 1.9486,
+      "eval_samples_per_second": 80.059,
+      "eval_steps_per_second": 4.106,
+      "step": 300
+    },
+    {
+      "epoch": 0.44557606619987267,
+      "grad_norm": 3.484682559967041,
+      "learning_rate": 8.9171974522293e-06,
+      "loss": 0.6307,
+      "step": 350
+    },
+    {
+      "epoch": 0.44557606619987267,
+      "eval_loss": 0.6990864276885986,
+      "eval_runtime": 1.9831,
+      "eval_samples_per_second": 78.663,
+      "eval_steps_per_second": 4.034,
+      "step": 350
+    },
+    {
+      "epoch": 0.5092297899427116,
+      "grad_norm": 3.779184103012085,
+      "learning_rate": 1.0191082802547772e-05,
+      "loss": 0.6639,
+      "step": 400
+    },
+    {
+      "epoch": 0.5092297899427116,
+      "eval_loss": 0.7543805241584778,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 79.916,
+      "eval_steps_per_second": 4.098,
+      "step": 400
+    },
+    {
+      "epoch": 0.5728835136855506,
+      "grad_norm": 2.8436331748962402,
+      "learning_rate": 1.1464968152866242e-05,
+      "loss": 0.6431,
+      "step": 450
+    },
+    {
+      "epoch": 0.5728835136855506,
+      "eval_loss": 0.7171684503555298,
+      "eval_runtime": 1.993,
+      "eval_samples_per_second": 78.274,
+      "eval_steps_per_second": 4.014,
+      "step": 450
+    },
+    {
+      "epoch": 0.6365372374283895,
+      "grad_norm": 3.409532070159912,
+      "learning_rate": 1.2738853503184714e-05,
+      "loss": 0.6183,
+      "step": 500
+    },
+    {
+      "epoch": 0.6365372374283895,
+      "eval_loss": 0.7295389175415039,
+      "eval_runtime": 1.9547,
+      "eval_samples_per_second": 79.809,
+      "eval_steps_per_second": 4.093,
+      "step": 500
+    },
+    {
+      "epoch": 0.7001909611712285,
+      "grad_norm": 2.2884674072265625,
+      "learning_rate": 1.4012738853503186e-05,
+      "loss": 0.6344,
+      "step": 550
+    },
+    {
+      "epoch": 0.7001909611712285,
+      "eval_loss": 0.7278215885162354,
+      "eval_runtime": 1.9597,
+      "eval_samples_per_second": 79.605,
+      "eval_steps_per_second": 4.082,
+      "step": 550
+    },
+    {
+      "epoch": 0.7638446849140674,
+      "grad_norm": 2.662555694580078,
+      "learning_rate": 1.528662420382166e-05,
+      "loss": 0.6635,
+      "step": 600
+    },
+    {
+      "epoch": 0.7638446849140674,
+      "eval_loss": 0.7314972281455994,
+      "eval_runtime": 1.9527,
+      "eval_samples_per_second": 79.889,
+      "eval_steps_per_second": 4.097,
+      "step": 600
+    },
+    {
+      "epoch": 0.8274984086569064,
+      "grad_norm": 2.6137986183166504,
+      "learning_rate": 1.6560509554140128e-05,
+      "loss": 0.7083,
+      "step": 650
+    },
+    {
+      "epoch": 0.8274984086569064,
+      "eval_loss": 0.7786588668823242,
+      "eval_runtime": 1.9552,
+      "eval_samples_per_second": 79.787,
+      "eval_steps_per_second": 4.092,
+      "step": 650
+    },
+    {
+      "epoch": 0.8911521323997453,
+      "grad_norm": 3.339657783508301,
+      "learning_rate": 1.78343949044586e-05,
+      "loss": 0.6841,
+      "step": 700
+    },
+    {
+      "epoch": 0.8911521323997453,
+      "eval_loss": 0.752537727355957,
+      "eval_runtime": 1.9503,
+      "eval_samples_per_second": 79.986,
+      "eval_steps_per_second": 4.102,
+      "step": 700
+    },
+    {
+      "epoch": 0.9548058561425843,
+      "grad_norm": 2.102302312850952,
+      "learning_rate": 1.910828025477707e-05,
+      "loss": 0.6622,
+      "step": 750
+    },
+    {
+      "epoch": 0.9548058561425843,
+      "eval_loss": 0.7738191485404968,
+      "eval_runtime": 1.9545,
+      "eval_samples_per_second": 79.818,
+      "eval_steps_per_second": 4.093,
+      "step": 750
+    },
+    {
+      "epoch": 1.0184595798854232,
+      "grad_norm": 4.052014350891113,
+      "learning_rate": 1.999977755311665e-05,
+      "loss": 0.6277,
+      "step": 800
+    },
+    {
+      "epoch": 1.0184595798854232,
+      "eval_loss": 0.7977485656738281,
+      "eval_runtime": 1.9587,
+      "eval_samples_per_second": 79.643,
+      "eval_steps_per_second": 4.084,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821133036282622,
+      "grad_norm": 2.9770467281341553,
+      "learning_rate": 1.99958232171617e-05,
+      "loss": 0.4164,
+      "step": 850
+    },
+    {
+      "epoch": 1.0821133036282622,
+      "eval_loss": 0.8168254494667053,
+      "eval_runtime": 1.9783,
+      "eval_samples_per_second": 78.855,
+      "eval_steps_per_second": 4.044,
+      "step": 850
+    },
+    {
+      "epoch": 1.1457670273711011,
+      "grad_norm": 2.4140615463256836,
+      "learning_rate": 1.9986927867052226e-05,
+      "loss": 0.3963,
+      "step": 900
+    },
+    {
+      "epoch": 1.1457670273711011,
+      "eval_loss": 0.8188236355781555,
+      "eval_runtime": 1.9525,
+      "eval_samples_per_second": 79.898,
+      "eval_steps_per_second": 4.097,
+      "step": 900
+    },
+    {
+      "epoch": 1.20942075111394,
+      "grad_norm": 2.735466718673706,
+      "learning_rate": 1.997309589982985e-05,
+      "loss": 0.4199,
+      "step": 950
+    },
+    {
+      "epoch": 1.20942075111394,
+      "eval_loss": 0.812458336353302,
+      "eval_runtime": 1.9598,
+      "eval_samples_per_second": 79.601,
+      "eval_steps_per_second": 4.082,
+      "step": 950
+    },
+    {
+      "epoch": 1.273074474856779,
+      "grad_norm": 2.7539219856262207,
+      "learning_rate": 1.995433415274493e-05,
+      "loss": 0.4159,
+      "step": 1000
+    },
+    {
+      "epoch": 1.273074474856779,
+      "eval_loss": 0.80951327085495,
+      "eval_runtime": 1.9753,
+      "eval_samples_per_second": 78.975,
+      "eval_steps_per_second": 4.05,
+      "step": 1000
+    },
+    {
+      "epoch": 1.336728198599618,
+      "grad_norm": 2.275360584259033,
+      "learning_rate": 1.993065189987684e-05,
+      "loss": 0.4107,
+      "step": 1050
+    },
+    {
+      "epoch": 1.336728198599618,
+      "eval_loss": 0.8287139534950256,
+      "eval_runtime": 1.9574,
+      "eval_samples_per_second": 79.696,
+      "eval_steps_per_second": 4.087,
+      "step": 1050
+    },
+    {
+      "epoch": 1.400381922342457,
+      "grad_norm": 2.8758232593536377,
+      "learning_rate": 1.9902060847549716e-05,
+      "loss": 0.434,
+      "step": 1100
+    },
+    {
+      "epoch": 1.400381922342457,
+      "eval_loss": 0.8138644695281982,
+      "eval_runtime": 1.9536,
+      "eval_samples_per_second": 79.852,
+      "eval_steps_per_second": 4.095,
+      "step": 1100
+    },
+    {
+      "epoch": 1.464035646085296,
+      "grad_norm": 2.412508964538574,
+      "learning_rate": 1.986857512854594e-05,
+      "loss": 0.4443,
+      "step": 1150
+    },
+    {
+      "epoch": 1.464035646085296,
+      "eval_loss": 0.8119045495986938,
+      "eval_runtime": 1.9894,
+      "eval_samples_per_second": 78.417,
+      "eval_steps_per_second": 4.021,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5276893698281349,
+      "grad_norm": 1.9511016607284546,
+      "learning_rate": 1.983021129512019e-05,
+      "loss": 0.4203,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5276893698281349,
+      "eval_loss": 0.8141614198684692,
+      "eval_runtime": 1.9602,
+      "eval_samples_per_second": 79.584,
+      "eval_steps_per_second": 4.081,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5913430935709738,
+      "grad_norm": 2.6505215167999268,
+      "learning_rate": 1.9786988310817523e-05,
+      "loss": 0.4385,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5913430935709738,
+      "eval_loss": 0.8097578883171082,
+      "eval_runtime": 1.9831,
+      "eval_samples_per_second": 78.665,
+      "eval_steps_per_second": 4.034,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6549968173138128,
+      "grad_norm": 2.4782555103302,
+      "learning_rate": 1.973892754109955e-05,
+      "loss": 0.4625,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6549968173138128,
+      "eval_loss": 0.8060766458511353,
+      "eval_runtime": 1.953,
+      "eval_samples_per_second": 79.877,
+      "eval_steps_per_second": 4.096,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7186505410566517,
+      "grad_norm": 2.4227771759033203,
+      "learning_rate": 1.9686052742783324e-05,
+      "loss": 0.4417,
+      "step": 1350
+    },
+    {
+      "epoch": 1.7186505410566517,
+      "eval_loss": 0.8126944303512573,
+      "eval_runtime": 2.1634,
+      "eval_samples_per_second": 72.108,
+      "eval_steps_per_second": 3.698,
+      "step": 1350
+    },
+    {
+      "epoch": 1.7823042647994907,
+      "grad_norm": 2.3015785217285156,
+      "learning_rate": 1.9628390052298155e-05,
+      "loss": 0.4483,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7823042647994907,
+      "eval_loss": 0.8172005414962769,
+      "eval_runtime": 1.9944,
+      "eval_samples_per_second": 78.219,
+      "eval_steps_per_second": 4.011,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8459579885423296,
+      "grad_norm": 2.7847931385040283,
+      "learning_rate": 1.9565967972766164e-05,
+      "loss": 0.4551,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8459579885423296,
+      "eval_loss": 0.8149409890174866,
+      "eval_runtime": 1.9515,
+      "eval_samples_per_second": 79.937,
+      "eval_steps_per_second": 4.099,
+      "step": 1450
+    },
+    {
+      "epoch": 1.9096117122851686,
+      "grad_norm": 2.573996067047119,
+      "learning_rate": 1.9498817359912973e-05,
+      "loss": 0.4526,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9096117122851686,
+      "eval_loss": 0.8210792541503906,
+      "eval_runtime": 1.957,
+      "eval_samples_per_second": 79.715,
+      "eval_steps_per_second": 4.088,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9732654360280075,
+      "grad_norm": 2.4847145080566406,
+      "learning_rate": 1.9426971406815464e-05,
+      "loss": 0.436,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9732654360280075,
+      "eval_loss": 0.8161709904670715,
+      "eval_runtime": 1.9565,
+      "eval_samples_per_second": 79.732,
+      "eval_steps_per_second": 4.089,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0369191597708465,
+      "grad_norm": 2.272801637649536,
+      "learning_rate": 1.9350465627494196e-05,
+      "loss": 0.3299,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0369191597708465,
+      "eval_loss": 0.8792819380760193,
+      "eval_runtime": 1.9865,
+      "eval_samples_per_second": 78.531,
+      "eval_steps_per_second": 4.027,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1005728835136854,
+      "grad_norm": 2.545703172683716,
+      "learning_rate": 1.926933783935853e-05,
+      "loss": 0.2247,
+      "step": 1650
+    },
+    {
+      "epoch": 2.1005728835136854,
+      "eval_loss": 0.89618319272995,
+      "eval_runtime": 1.9719,
+      "eval_samples_per_second": 79.113,
+      "eval_steps_per_second": 4.057,
+      "step": 1650
+    },
+    {
+      "epoch": 2.1642266072565244,
+      "grad_norm": 1.6922868490219116,
+      "learning_rate": 1.9183628144513196e-05,
+      "loss": 0.2404,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1642266072565244,
+      "eval_loss": 0.8865496516227722,
+      "eval_runtime": 1.9548,
+      "eval_samples_per_second": 79.805,
+      "eval_steps_per_second": 4.093,
+      "step": 1700
+    },
+    {
+      "epoch": 2.2278803309993633,
+      "grad_norm": 1.7290230989456177,
+      "learning_rate": 1.9093378909935503e-05,
+      "loss": 0.226,
+      "step": 1750
+    },
+    {
+      "epoch": 2.2278803309993633,
+      "eval_loss": 0.9072224497795105,
+      "eval_runtime": 1.979,
+      "eval_samples_per_second": 78.828,
+      "eval_steps_per_second": 4.042,
+      "step": 1750
+    },
+    {
+      "epoch": 2.2915340547422023,
+      "grad_norm": 1.6177765130996704,
+      "learning_rate": 1.8998634746533004e-05,
+      "loss": 0.2395,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2915340547422023,
+      "eval_loss": 0.9168246388435364,
+      "eval_runtime": 1.956,
+      "eval_samples_per_second": 79.753,
+      "eval_steps_per_second": 4.09,
+      "step": 1800
+    },
+    {
+      "epoch": 2.3551877784850412,
+      "grad_norm": 2.4058384895324707,
+      "learning_rate": 1.889944248709198e-05,
+      "loss": 0.2425,
+      "step": 1850
+    },
+    {
+      "epoch": 2.3551877784850412,
+      "eval_loss": 0.9104910492897034,
+      "eval_runtime": 1.9546,
+      "eval_samples_per_second": 79.811,
+      "eval_steps_per_second": 4.093,
+      "step": 1850
+    },
+    {
+      "epoch": 2.41884150222788,
+      "grad_norm": 1.7686213254928589,
+      "learning_rate": 1.8795851163127626e-05,
+      "loss": 0.2456,
+      "step": 1900
+    },
+    {
+      "epoch": 2.41884150222788,
+      "eval_loss": 0.9102558493614197,
+      "eval_runtime": 2.0139,
+      "eval_samples_per_second": 77.463,
+      "eval_steps_per_second": 3.972,
+      "step": 1900
+    },
+    {
+      "epoch": 2.482495225970719,
+      "grad_norm": 2.483212947845459,
+      "learning_rate": 1.8687911980647375e-05,
+      "loss": 0.241,
+      "step": 1950
+    },
+    {
+      "epoch": 2.482495225970719,
+      "eval_loss": 0.930452287197113,
+      "eval_runtime": 1.964,
+      "eval_samples_per_second": 79.428,
+      "eval_steps_per_second": 4.073,
+      "step": 1950
+    },
+    {
+      "epoch": 2.546148949713558,
+      "grad_norm": 2.0306715965270996,
+      "learning_rate": 1.857567829483937e-05,
+      "loss": 0.2529,
+      "step": 2000
+    },
+    {
+      "epoch": 2.546148949713558,
+      "eval_loss": 0.9052493572235107,
+      "eval_runtime": 1.9617,
+      "eval_samples_per_second": 79.522,
+      "eval_steps_per_second": 4.078,
+      "step": 2000
+    },
+    {
+      "epoch": 2.609802673456397,
+      "grad_norm": 2.4319934844970703,
+      "learning_rate": 1.8459205583698598e-05,
+      "loss": 0.2479,
+      "step": 2050
+    },
+    {
+      "epoch": 2.609802673456397,
+      "eval_loss": 0.909498929977417,
+      "eval_runtime": 1.9526,
+      "eval_samples_per_second": 79.894,
+      "eval_steps_per_second": 4.097,
+      "step": 2050
+    },
+    {
+      "epoch": 2.673456397199236,
+      "grad_norm": 1.3272260427474976,
+      "learning_rate": 1.833855142060364e-05,
+      "loss": 0.2411,
+      "step": 2100
+    },
+    {
+      "epoch": 2.673456397199236,
+      "eval_loss": 0.9212460517883301,
+      "eval_runtime": 1.9521,
+      "eval_samples_per_second": 79.913,
+      "eval_steps_per_second": 4.098,
+      "step": 2100
+    },
+    {
+      "epoch": 2.737110120942075,
+      "grad_norm": 1.639654278755188,
+      "learning_rate": 1.8213775445857716e-05,
+      "loss": 0.2392,
+      "step": 2150
+    },
+    {
+      "epoch": 2.737110120942075,
+      "eval_loss": 0.911665678024292,
+      "eval_runtime": 1.9821,
+      "eval_samples_per_second": 78.704,
+      "eval_steps_per_second": 4.036,
+      "step": 2150
+    },
+    {
+      "epoch": 2.800763844684914,
+      "grad_norm": 1.5815492868423462,
+      "learning_rate": 1.808493933720802e-05,
+      "loss": 0.2568,
+      "step": 2200
+    },
+    {
+      "epoch": 2.800763844684914,
+      "eval_loss": 0.910538375377655,
+      "eval_runtime": 1.9947,
+      "eval_samples_per_second": 78.207,
+      "eval_steps_per_second": 4.011,
+      "step": 2200
+    },
+    {
+      "epoch": 2.864417568427753,
+      "grad_norm": 1.519374132156372,
+      "learning_rate": 1.7952106779357922e-05,
+      "loss": 0.2459,
+      "step": 2250
+    },
+    {
+      "epoch": 2.864417568427753,
+      "eval_loss": 0.9174743890762329,
+      "eval_runtime": 1.9547,
+      "eval_samples_per_second": 79.81,
+      "eval_steps_per_second": 4.093,
+      "step": 2250
+    },
+    {
+      "epoch": 2.928071292170592,
+      "grad_norm": 2.186408042907715,
+      "learning_rate": 1.7815343432487094e-05,
+      "loss": 0.2521,
+      "step": 2300
+    },
+    {
+      "epoch": 2.928071292170592,
+      "eval_loss": 0.9191064238548279,
+      "eval_runtime": 1.972,
+      "eval_samples_per_second": 79.107,
+      "eval_steps_per_second": 4.057,
+      "step": 2300
+    },
+    {
+      "epoch": 2.991725015913431,
+      "grad_norm": 1.9706707000732422,
+      "learning_rate": 1.7674716899795205e-05,
+      "loss": 0.2462,
+      "step": 2350
+    },
+    {
+      "epoch": 2.991725015913431,
+      "eval_loss": 0.9158605933189392,
+      "eval_runtime": 1.9566,
+      "eval_samples_per_second": 79.73,
+      "eval_steps_per_second": 4.089,
+      "step": 2350
+    },
+    {
+      "epoch": 3.0553787396562697,
+      "grad_norm": 2.1943814754486084,
+      "learning_rate": 1.753029669408509e-05,
+      "loss": 0.1712,
+      "step": 2400
+    },
+    {
+      "epoch": 3.0553787396562697,
+      "eval_loss": 0.9773328900337219,
+      "eval_runtime": 1.9608,
+      "eval_samples_per_second": 79.559,
+      "eval_steps_per_second": 4.08,
+      "step": 2400
+    },
+    {
+      "epoch": 3.1190324633991087,
+      "grad_norm": 1.6751331090927124,
+      "learning_rate": 1.738215420340205e-05,
+      "loss": 0.1609,
+      "step": 2450
+    },
+    {
+      "epoch": 3.1190324633991087,
+      "eval_loss": 0.9757582545280457,
+      "eval_runtime": 1.9922,
+      "eval_samples_per_second": 78.306,
+      "eval_steps_per_second": 4.016,
+      "step": 2450
+    },
+    {
+      "epoch": 3.1826861871419476,
+      "grad_norm": 1.4819265604019165,
+      "learning_rate": 1.723036265574616e-05,
+      "loss": 0.1684,
+      "step": 2500
+    },
+    {
+      "epoch": 3.1826861871419476,
+      "eval_loss": 0.9819521903991699,
+      "eval_runtime": 1.9611,
+      "eval_samples_per_second": 79.546,
+      "eval_steps_per_second": 4.079,
+      "step": 2500
+    },
+    {
+      "epoch": 3.2463399108847866,
+      "grad_norm": 1.6287983655929565,
+      "learning_rate": 1.7074997082875113e-05,
+      "loss": 0.1677,
+      "step": 2550
+    },
+    {
+      "epoch": 3.2463399108847866,
+      "eval_loss": 0.9783702492713928,
+      "eval_runtime": 1.9577,
+      "eval_samples_per_second": 79.684,
+      "eval_steps_per_second": 4.086,
+      "step": 2550
+    },
+    {
+      "epoch": 3.3099936346276255,
+      "grad_norm": 0.7324376106262207,
+      "learning_rate": 1.6916134283215412e-05,
+      "loss": 0.1705,
+      "step": 2600
+    },
+    {
+      "epoch": 3.3099936346276255,
+      "eval_loss": 0.9991599917411804,
+      "eval_runtime": 1.9593,
+      "eval_samples_per_second": 79.622,
+      "eval_steps_per_second": 4.083,
+      "step": 2600
+    },
+    {
+      "epoch": 3.373647358370465,
+      "grad_norm": 2.1236824989318848,
+      "learning_rate": 1.6753852783900306e-05,
+      "loss": 0.1679,
+      "step": 2650
+    },
+    {
+      "epoch": 3.373647358370465,
+      "eval_loss": 0.9751440286636353,
+      "eval_runtime": 1.9544,
+      "eval_samples_per_second": 79.821,
+      "eval_steps_per_second": 4.093,
+      "step": 2650
+    },
+    {
+      "epoch": 3.4373010821133034,
+      "grad_norm": 1.1708719730377197,
+      "learning_rate": 1.6588232801953223e-05,
+      "loss": 0.1668,
+      "step": 2700
+    },
+    {
+      "epoch": 3.4373010821133034,
+      "eval_loss": 0.9651870727539062,
+      "eval_runtime": 1.9795,
+      "eval_samples_per_second": 78.809,
+      "eval_steps_per_second": 4.041,
+      "step": 2700
+    },
+    {
+      "epoch": 3.500954805856143,
+      "grad_norm": 1.5355838537216187,
+      "learning_rate": 1.641935620463584e-05,
+      "loss": 0.1673,
+      "step": 2750
+    },
+    {
+      "epoch": 3.500954805856143,
+      "eval_loss": 0.9585145115852356,
+      "eval_runtime": 1.9555,
+      "eval_samples_per_second": 79.775,
+      "eval_steps_per_second": 4.091,
+      "step": 2750
+    },
+    {
+      "epoch": 3.5646085295989813,
+      "grad_norm": 1.21344792842865,
+      "learning_rate": 1.6247306468980475e-05,
+      "loss": 0.1691,
+      "step": 2800
+    },
+    {
+      "epoch": 3.5646085295989813,
+      "eval_loss": 0.9902192950248718,
+      "eval_runtime": 1.9655,
+      "eval_samples_per_second": 79.368,
+      "eval_steps_per_second": 4.07,
+      "step": 2800
+    },
+    {
+      "epoch": 3.6282622533418207,
+      "grad_norm": 1.3404573202133179,
+      "learning_rate": 1.607216864052672e-05,
+      "loss": 0.1707,
+      "step": 2850
+    },
+    {
+      "epoch": 3.6282622533418207,
+      "eval_loss": 0.9820557832717896,
+      "eval_runtime": 1.957,
+      "eval_samples_per_second": 79.716,
+      "eval_steps_per_second": 4.088,
+      "step": 2850
+    },
+    {
+      "epoch": 3.6919159770846592,
+      "grad_norm": 1.7005574703216553,
+      "learning_rate": 1.589402929128276e-05,
+      "loss": 0.1694,
+      "step": 2900
+    },
+    {
+      "epoch": 3.6919159770846592,
+      "eval_loss": 0.9860473871231079,
+      "eval_runtime": 1.9577,
+      "eval_samples_per_second": 79.685,
+      "eval_steps_per_second": 4.086,
+      "step": 2900
+    },
+    {
+      "epoch": 3.7555697008274986,
+      "grad_norm": 3.1085927486419678,
+      "learning_rate": 1.571297647693215e-05,
+      "loss": 0.1693,
+      "step": 2950
+    },
+    {
+      "epoch": 3.7555697008274986,
+      "eval_loss": 0.9597901701927185,
+      "eval_runtime": 1.9583,
+      "eval_samples_per_second": 79.66,
+      "eval_steps_per_second": 4.085,
+      "step": 2950
+    },
+    {
+      "epoch": 3.819223424570337,
+      "grad_norm": 1.1406304836273193,
+      "learning_rate": 1.5529099693307205e-05,
+      "loss": 0.1708,
+      "step": 3000
+    },
+    {
+      "epoch": 3.819223424570337,
+      "eval_loss": 0.9565241932868958,
+      "eval_runtime": 1.9592,
+      "eval_samples_per_second": 79.623,
+      "eval_steps_per_second": 4.083,
+      "step": 3000
+    },
+    {
+      "epoch": 3.8828771483131765,
+      "grad_norm": 1.1178061962127686,
+      "learning_rate": 1.534248983215048e-05,
+      "loss": 0.1671,
+      "step": 3050
+    },
+    {
+      "epoch": 3.8828771483131765,
+      "eval_loss": 0.9801331758499146,
+      "eval_runtime": 1.9614,
+      "eval_samples_per_second": 79.536,
+      "eval_steps_per_second": 4.079,
+      "step": 3050
+    },
+    {
+      "epoch": 3.946530872056015,
+      "grad_norm": 1.7261744737625122,
+      "learning_rate": 1.5153239136186297e-05,
+      "loss": 0.1603,
+      "step": 3100
+    },
+    {
+      "epoch": 3.946530872056015,
+      "eval_loss": 0.9833694100379944,
+      "eval_runtime": 1.9582,
+      "eval_samples_per_second": 79.664,
+      "eval_steps_per_second": 4.085,
+      "step": 3100
+    },
+    {
+      "epoch": 4.0101845957988544,
+      "grad_norm": 1.4014726877212524,
+      "learning_rate": 1.4961441153524421e-05,
+      "loss": 0.1604,
+      "step": 3150
+    },
+    {
+      "epoch": 4.0101845957988544,
+      "eval_loss": 1.0256284475326538,
+      "eval_runtime": 1.9881,
+      "eval_samples_per_second": 78.467,
+      "eval_steps_per_second": 4.024,
+      "step": 3150
+    },
+    {
+      "epoch": 4.073838319541693,
+      "grad_norm": 0.9033142924308777,
+      "learning_rate": 1.47671906914185e-05,
+      "loss": 0.1046,
+      "step": 3200
+    },
+    {
+      "epoch": 4.073838319541693,
+      "eval_loss": 1.0567926168441772,
+      "eval_runtime": 1.9551,
+      "eval_samples_per_second": 79.79,
+      "eval_steps_per_second": 4.092,
+      "step": 3200
+    },
+    {
+      "epoch": 4.137492043284532,
+      "grad_norm": 0.9893561005592346,
+      "learning_rate": 1.4570583769402085e-05,
+      "loss": 0.1069,
+      "step": 3250
+    },
+    {
+      "epoch": 4.137492043284532,
+      "eval_loss": 1.0297176837921143,
+      "eval_runtime": 1.9549,
+      "eval_samples_per_second": 79.801,
+      "eval_steps_per_second": 4.092,
+      "step": 3250
+    },
+    {
+      "epoch": 4.201145767027371,
+      "grad_norm": 1.3346303701400757,
+      "learning_rate": 1.437171757182542e-05,
+      "loss": 0.1032,
+      "step": 3300
+    },
+    {
+      "epoch": 4.201145767027371,
+      "eval_loss": 1.0205018520355225,
+      "eval_runtime": 1.9586,
+      "eval_samples_per_second": 79.648,
+      "eval_steps_per_second": 4.084,
+      "step": 3300
+    },
+    {
+      "epoch": 4.26479949077021,
+      "grad_norm": 0.8845686316490173,
+      "learning_rate": 1.4170690399816469e-05,
+      "loss": 0.1038,
+      "step": 3350
+    },
+    {
+      "epoch": 4.26479949077021,
+      "eval_loss": 1.027697205543518,
+      "eval_runtime": 1.9567,
+      "eval_samples_per_second": 79.727,
+      "eval_steps_per_second": 4.089,
+      "step": 3350
+    },
+    {
+      "epoch": 4.328453214513049,
+      "grad_norm": 0.8891485333442688,
+      "learning_rate": 1.3967601622689864e-05,
+      "loss": 0.1122,
+      "step": 3400
+    },
+    {
+      "epoch": 4.328453214513049,
+      "eval_loss": 1.0382416248321533,
+      "eval_runtime": 1.9585,
+      "eval_samples_per_second": 79.654,
+      "eval_steps_per_second": 4.085,
+      "step": 3400
+    },
+    {
+      "epoch": 4.392106938255888,
+      "grad_norm": 1.3972492218017578,
+      "learning_rate": 1.3762551628827892e-05,
+      "loss": 0.1086,
+      "step": 3450
+    },
+    {
+      "epoch": 4.392106938255888,
+      "eval_loss": 1.0479986667633057,
+      "eval_runtime": 1.9854,
+      "eval_samples_per_second": 78.575,
+      "eval_steps_per_second": 4.03,
+      "step": 3450
+    },
+    {
+      "epoch": 4.455760661998727,
+      "grad_norm": 0.9529390335083008,
+      "learning_rate": 1.3555641776057729e-05,
+      "loss": 0.1086,
+      "step": 3500
+    },
+    {
+      "epoch": 4.455760661998727,
+      "eval_loss": 1.026903748512268,
+      "eval_runtime": 1.9801,
+      "eval_samples_per_second": 78.783,
+      "eval_steps_per_second": 4.04,
+      "step": 3500
+    },
+    {
+      "epoch": 4.519414385741566,
+      "grad_norm": 0.9916590452194214,
+      "learning_rate": 1.3346974341549448e-05,
+      "loss": 0.1082,
+      "step": 3550
+    },
+    {
+      "epoch": 4.519414385741566,
+      "eval_loss": 1.0392361879348755,
+      "eval_runtime": 1.9611,
+      "eval_samples_per_second": 79.546,
+      "eval_steps_per_second": 4.079,
+      "step": 3550
+    },
+    {
+      "epoch": 4.583068109484405,
+      "grad_norm": 1.4986087083816528,
+      "learning_rate": 1.3136652471259624e-05,
+      "loss": 0.1067,
+      "step": 3600
+    },
+    {
+      "epoch": 4.583068109484405,
+      "eval_loss": 1.014196753501892,
+      "eval_runtime": 1.9787,
+      "eval_samples_per_second": 78.839,
+      "eval_steps_per_second": 4.043,
+      "step": 3600
+    },
+    {
+      "epoch": 4.646721833227244,
+      "grad_norm": 1.2164666652679443,
+      "learning_rate": 1.2924780128945473e-05,
+      "loss": 0.1124,
+      "step": 3650
+    },
+    {
+      "epoch": 4.646721833227244,
+      "eval_loss": 1.0109295845031738,
+      "eval_runtime": 1.9575,
+      "eval_samples_per_second": 79.695,
+      "eval_steps_per_second": 4.087,
+      "step": 3650
+    },
+    {
+      "epoch": 4.7103755569700825,
+      "grad_norm": 0.980490505695343,
+      "learning_rate": 1.2711462044774747e-05,
+      "loss": 0.1079,
+      "step": 3700
+    },
+    {
+      "epoch": 4.7103755569700825,
+      "eval_loss": 1.025646686553955,
+      "eval_runtime": 1.9514,
+      "eval_samples_per_second": 79.941,
+      "eval_steps_per_second": 4.1,
+      "step": 3700
+    },
+    {
+      "epoch": 4.774029280712922,
+      "grad_norm": 1.684493064880371,
+      "learning_rate": 1.249680366355678e-05,
+      "loss": 0.1106,
+      "step": 3750
+    },
+    {
+      "epoch": 4.774029280712922,
+      "eval_loss": 1.0292022228240967,
+      "eval_runtime": 1.9487,
+      "eval_samples_per_second": 80.051,
+      "eval_steps_per_second": 4.105,
+      "step": 3750
+    },
+    {
+      "epoch": 4.83768300445576,
+      "grad_norm": 0.6794301867485046,
+      "learning_rate": 1.2280911092620298e-05,
+      "loss": 0.108,
+      "step": 3800
+    },
+    {
+      "epoch": 4.83768300445576,
+      "eval_loss": 1.012285828590393,
+      "eval_runtime": 1.9548,
+      "eval_samples_per_second": 79.806,
+      "eval_steps_per_second": 4.093,
+      "step": 3800
+    },
+    {
+      "epoch": 4.9013367281986,
+      "grad_norm": 1.613420009613037,
+      "learning_rate": 1.2063891049363725e-05,
+      "loss": 0.1078,
+      "step": 3850
+    },
+    {
+      "epoch": 4.9013367281986,
+      "eval_loss": 1.029428482055664,
+      "eval_runtime": 1.9459,
+      "eval_samples_per_second": 80.167,
+      "eval_steps_per_second": 4.111,
+      "step": 3850
+    },
+    {
+      "epoch": 4.964990451941438,
+      "grad_norm": 0.8637195825576782,
+      "learning_rate": 1.1845850808503939e-05,
+      "loss": 0.1012,
+      "step": 3900
+    },
+    {
+      "epoch": 4.964990451941438,
+      "eval_loss": 1.0551037788391113,
+      "eval_runtime": 1.9584,
+      "eval_samples_per_second": 79.656,
+      "eval_steps_per_second": 4.085,
+      "step": 3900
+    },
+    {
+      "epoch": 5.028644175684278,
+      "grad_norm": 1.0889546871185303,
+      "learning_rate": 1.1626898149049523e-05,
+      "loss": 0.0913,
+      "step": 3950
+    },
+    {
+      "epoch": 5.028644175684278,
+      "eval_loss": 1.0936988592147827,
+      "eval_runtime": 1.9524,
+      "eval_samples_per_second": 79.901,
+      "eval_steps_per_second": 4.097,
+      "step": 3950
+    },
+    {
+      "epoch": 5.092297899427116,
+      "grad_norm": 1.0244091749191284,
+      "learning_rate": 1.1407141301024762e-05,
+      "loss": 0.0699,
+      "step": 4000
+    },
+    {
+      "epoch": 5.092297899427116,
+      "eval_loss": 1.0808786153793335,
+      "eval_runtime": 1.9799,
+      "eval_samples_per_second": 78.793,
+      "eval_steps_per_second": 4.041,
+      "step": 4000
+    },
+    {
+      "epoch": 5.155951623169956,
+      "grad_norm": 0.9700921773910522,
+      "learning_rate": 1.1186688891970686e-05,
+      "loss": 0.0685,
+      "step": 4050
+    },
+    {
+      "epoch": 5.155951623169956,
+      "eval_loss": 1.0664215087890625,
+      "eval_runtime": 1.9478,
+      "eval_samples_per_second": 80.091,
+      "eval_steps_per_second": 4.107,
+      "step": 4050
+    },
+    {
+      "epoch": 5.219605346912794,
+      "grad_norm": 0.8142929077148438,
+      "learning_rate": 1.0965649893249619e-05,
+      "loss": 0.0667,
+      "step": 4100
+    },
+    {
+      "epoch": 5.219605346912794,
+      "eval_loss": 1.0777896642684937,
+      "eval_runtime": 1.9828,
+      "eval_samples_per_second": 78.676,
+      "eval_steps_per_second": 4.035,
+      "step": 4100
+    },
+    {
+      "epoch": 5.2832590706556335,
+      "grad_norm": 0.47455140948295593,
+      "learning_rate": 1.074413356617978e-05,
+      "loss": 0.0689,
+      "step": 4150
+    },
+    {
+      "epoch": 5.2832590706556335,
+      "eval_loss": 1.0918174982070923,
+      "eval_runtime": 1.9937,
+      "eval_samples_per_second": 78.247,
+      "eval_steps_per_second": 4.013,
+      "step": 4150
+    },
+    {
+      "epoch": 5.346912794398472,
+      "grad_norm": 0.5227736234664917,
+      "learning_rate": 1.0522249408026553e-05,
+      "loss": 0.0662,
+      "step": 4200
+    },
+    {
+      "epoch": 5.346912794398472,
+      "eval_loss": 1.0910652875900269,
+      "eval_runtime": 1.9443,
+      "eval_samples_per_second": 80.236,
+      "eval_steps_per_second": 4.115,
+      "step": 4200
+    },
+    {
+      "epoch": 5.410566518141311,
+      "grad_norm": 0.9572489261627197,
+      "learning_rate": 1.0300107097877114e-05,
+      "loss": 0.066,
+      "step": 4250
+    },
+    {
+      "epoch": 5.410566518141311,
+      "eval_loss": 1.0842642784118652,
+      "eval_runtime": 1.9976,
+      "eval_samples_per_second": 78.093,
+      "eval_steps_per_second": 4.005,
+      "step": 4250
+    },
+    {
+      "epoch": 5.47422024188415,
+      "grad_norm": 1.3733848333358765,
+      "learning_rate": 1.0077816442425216e-05,
+      "loss": 0.0717,
+      "step": 4300
+    },
+    {
+      "epoch": 5.47422024188415,
+      "eval_loss": 1.0852998495101929,
+      "eval_runtime": 1.9568,
+      "eval_samples_per_second": 79.722,
+      "eval_steps_per_second": 4.088,
+      "step": 4300
+    },
+    {
+      "epoch": 5.537873965626989,
+      "grad_norm": 0.3845078945159912,
+      "learning_rate": 9.85548732169286e-06,
+      "loss": 0.0668,
+      "step": 4350
+    },
+    {
+      "epoch": 5.537873965626989,
+      "eval_loss": 1.0928053855895996,
+      "eval_runtime": 1.9824,
+      "eval_samples_per_second": 78.692,
+      "eval_steps_per_second": 4.036,
+      "step": 4350
+    },
+    {
+      "epoch": 5.601527689369828,
+      "grad_norm": 0.6611254215240479,
+      "learning_rate": 9.633229634715734e-06,
+      "loss": 0.0683,
+      "step": 4400
+    },
+    {
+      "epoch": 5.601527689369828,
+      "eval_loss": 1.08696448802948,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 80.082,
+      "eval_steps_per_second": 4.107,
+      "step": 4400
+    },
+    {
+      "epoch": 5.665181413112667,
+      "grad_norm": 0.2818908095359802,
+      "learning_rate": 9.411153245219262e-06,
+      "loss": 0.0672,
+      "step": 4450
+    },
+    {
+      "epoch": 5.665181413112667,
+      "eval_loss": 1.0971331596374512,
+      "eval_runtime": 1.9492,
+      "eval_samples_per_second": 80.034,
+      "eval_steps_per_second": 4.104,
+      "step": 4450
+    },
+    {
+      "epoch": 5.728835136855506,
+      "grad_norm": 0.5571719408035278,
+      "learning_rate": 9.18936792731209e-06,
+      "loss": 0.0716,
+      "step": 4500
+    },
+    {
+      "epoch": 5.728835136855506,
+      "eval_loss": 1.084871530532837,
+      "eval_runtime": 1.9919,
+      "eval_samples_per_second": 78.318,
+      "eval_steps_per_second": 4.016,
+      "step": 4500
+    },
+    {
+      "epoch": 5.792488860598345,
+      "grad_norm": 0.5682917237281799,
+      "learning_rate": 8.967983311223898e-06,
+      "loss": 0.0699,
+      "step": 4550
+    },
+    {
+      "epoch": 5.792488860598345,
+      "eval_loss": 1.092268943786621,
+      "eval_runtime": 2.0128,
+      "eval_samples_per_second": 77.502,
+      "eval_steps_per_second": 3.974,
+      "step": 4550
+    },
+    {
+      "epoch": 5.856142584341184,
+      "grad_norm": 0.7702981233596802,
+      "learning_rate": 8.747108829114284e-06,
+      "loss": 0.0731,
+      "step": 4600
+    },
+    {
+      "epoch": 5.856142584341184,
+      "eval_loss": 1.0890579223632812,
+      "eval_runtime": 1.9571,
+      "eval_samples_per_second": 79.711,
+      "eval_steps_per_second": 4.088,
+      "step": 4600
+    },
+    {
+      "epoch": 5.919796308084023,
+      "grad_norm": 0.8630861043930054,
+      "learning_rate": 8.526853660979609e-06,
+      "loss": 0.0664,
+      "step": 4650
+    },
+    {
+      "epoch": 5.919796308084023,
+      "eval_loss": 1.0908620357513428,
+      "eval_runtime": 1.962,
+      "eval_samples_per_second": 79.511,
+      "eval_steps_per_second": 4.077,
+      "step": 4650
+    },
+    {
+      "epoch": 5.9834500318268615,
+      "grad_norm": 1.2592061758041382,
+      "learning_rate": 8.30732668068446e-06,
+      "loss": 0.0723,
+      "step": 4700
+    },
+    {
+      "epoch": 5.9834500318268615,
+      "eval_loss": 1.0808950662612915,
+      "eval_runtime": 1.9536,
+      "eval_samples_per_second": 79.853,
+      "eval_steps_per_second": 4.095,
+      "step": 4700
+    },
+    {
+      "epoch": 6.047103755569701,
+      "grad_norm": 0.3191361725330353,
+      "learning_rate": 8.088636402144442e-06,
+      "loss": 0.0584,
+      "step": 4750
+    },
+    {
+      "epoch": 6.047103755569701,
+      "eval_loss": 1.1153998374938965,
+      "eval_runtime": 1.9605,
+      "eval_samples_per_second": 79.571,
+      "eval_steps_per_second": 4.081,
+      "step": 4750
+    },
+    {
+      "epoch": 6.110757479312539,
+      "grad_norm": 0.5758917927742004,
+      "learning_rate": 7.870890925686875e-06,
+      "loss": 0.0528,
+      "step": 4800
+    },
+    {
+      "epoch": 6.110757479312539,
+      "eval_loss": 1.1246304512023926,
+      "eval_runtime": 1.9862,
+      "eval_samples_per_second": 78.541,
+      "eval_steps_per_second": 4.028,
+      "step": 4800
+    },
+    {
+      "epoch": 6.174411203055379,
+      "grad_norm": 0.8011472821235657,
+      "learning_rate": 7.654197884615991e-06,
+      "loss": 0.0549,
+      "step": 4850
+    },
+    {
+      "epoch": 6.174411203055379,
+      "eval_loss": 1.1302942037582397,
+      "eval_runtime": 1.9621,
+      "eval_samples_per_second": 79.507,
+      "eval_steps_per_second": 4.077,
+      "step": 4850
+    },
+    {
+      "epoch": 6.238064926798217,
+      "grad_norm": 0.45742979645729065,
+      "learning_rate": 7.438664392008903e-06,
+      "loss": 0.0548,
+      "step": 4900
+    },
+    {
+      "epoch": 6.238064926798217,
+      "eval_loss": 1.1371703147888184,
+      "eval_runtime": 1.9865,
+      "eval_samples_per_second": 78.531,
+      "eval_steps_per_second": 4.027,
+      "step": 4900
+    },
+    {
+      "epoch": 6.301718650541057,
+      "grad_norm": 1.6437746286392212,
+      "learning_rate": 7.224396987768785e-06,
+      "loss": 0.0552,
+      "step": 4950
+    },
+    {
+      "epoch": 6.301718650541057,
+      "eval_loss": 1.1244136095046997,
+      "eval_runtime": 1.9966,
+      "eval_samples_per_second": 78.133,
+      "eval_steps_per_second": 4.007,
+      "step": 4950
+    },
+    {
+      "epoch": 6.365372374283895,
+      "grad_norm": 0.2734375298023224,
+      "learning_rate": 7.011501585961369e-06,
+      "loss": 0.053,
+      "step": 5000
+    },
+    {
+      "epoch": 6.365372374283895,
+      "eval_loss": 1.1277772188186646,
+      "eval_runtime": 1.9932,
+      "eval_samples_per_second": 78.265,
+      "eval_steps_per_second": 4.014,
+      "step": 5000
+    },
+    {
+      "epoch": 6.429026098026735,
+      "grad_norm": 0.3379392623901367,
+      "learning_rate": 6.800083422460766e-06,
+      "loss": 0.0556,
+      "step": 5050
+    },
+    {
+      "epoch": 6.429026098026735,
+      "eval_loss": 1.1319537162780762,
+      "eval_runtime": 1.9815,
+      "eval_samples_per_second": 78.728,
+      "eval_steps_per_second": 4.037,
+      "step": 5050
+    },
+    {
+      "epoch": 6.492679821769573,
+      "grad_norm": 0.34678924083709717,
+      "learning_rate": 6.590247002930567e-06,
+      "loss": 0.0574,
+      "step": 5100
+    },
+    {
+      "epoch": 6.492679821769573,
+      "eval_loss": 1.112044334411621,
+      "eval_runtime": 1.9568,
+      "eval_samples_per_second": 79.721,
+      "eval_steps_per_second": 4.088,
+      "step": 5100
+    },
+    {
+      "epoch": 6.5563335455124125,
+      "grad_norm": 0.6663870811462402,
+      "learning_rate": 6.382096051165847e-06,
+      "loss": 0.0536,
+      "step": 5150
+    },
+    {
+      "epoch": 6.5563335455124125,
+      "eval_loss": 1.135048747062683,
+      "eval_runtime": 1.955,
+      "eval_samples_per_second": 79.795,
+      "eval_steps_per_second": 4.092,
+      "step": 5150
+    },
+    {
+      "epoch": 6.619987269255251,
+      "grad_norm": 0.5493341088294983,
+      "learning_rate": 6.175733457821691e-06,
+      "loss": 0.0548,
+      "step": 5200
+    },
+    {
+      "epoch": 6.619987269255251,
+      "eval_loss": 1.1426846981048584,
+      "eval_runtime": 1.9543,
+      "eval_samples_per_second": 79.823,
+      "eval_steps_per_second": 4.094,
+      "step": 5200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 7850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 400,
+  "total_flos": 2.0478057288984166e+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 sha256:215e07827f5404d05da05d13437fbf3bf18248131047f1c67a0e2855b7cda048
+size 5112