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 sha256:0b93567178616e69ce827728bd810b66284b6ad281065967b54c574752de9a56
+size 4881575536

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67bd8be694aa853bbd431c9d26cbaeed99c133eb1e9c4d0741b0e91c21dac290
+size 4970418112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312b6e7342b07558c437ca9df1eaec63cc5c1e2739372f4924f31d36966d829a
+size 4970418120

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fe4ea46dab7f023f4cb0c7a49a024174c9bf57c5db7ae49b56cac4db2905f0
+size 4970418144

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72d39ef879da042c9e8dce46137120c91a5263a044e25ab0762aa6cb00a8594
+size 4970418144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c728a511cc5b37f0ec960314df663960c23f32298c6b90c5fa85ae7fc1ec89f
+size 4792119040

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4fba5cfeec93fe3bccaba998c1221cea9e1e5bdc0d39a287528e7dad6ea22e
+size 4792160232

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0e57129e156b63f1f8d67ea7d4bcbf7931d4c4f75fd3657f7f8b882e5dcf87
+size 4792160224

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ba032cf1dd76663d80e91e759012cac04cbe033930c97876dc0b4b03e977d7
+size 4970418144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e10982c4e81a2d9a9146ff41fd0ab593ad6c1ac9ab0052d8cd2b8470ac0bcfd
+size 4970418144

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8809b05147da41091a09c81b8c7704f3821ce7cdfb58d1323505beebe4b3a8
+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"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c557dfe33955be7f2112326073a378fdc39b85a11eba8148f601ffbc5af9cc08
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435c3b862c0ec12c43dc83874d4ae3938cdaeee7d9b3604046f9e3ebb47d1666
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:613a3670568470dda326f582acf7ad00a2d2eb6d063b173b117d0c9c50d64c31
+size 1064

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 +1,1041 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.230769230769231,
+  "eval_steps": 50,
+  "global_step": 3400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 6.20859956741333,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.2312,
+      "step": 50
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "eval_loss": 0.7887434959411621,
+      "eval_runtime": 2.062,
+      "eval_samples_per_second": 55.287,
+      "eval_steps_per_second": 2.91,
+      "step": 50
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 13.618162155151367,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.7309,
+      "step": 100
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "eval_loss": 0.7180795669555664,
+      "eval_runtime": 2.061,
+      "eval_samples_per_second": 55.312,
+      "eval_steps_per_second": 2.911,
+      "step": 100
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 14.984538078308105,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.6,
+      "step": 150
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "eval_loss": 0.6879476308822632,
+      "eval_runtime": 2.0438,
+      "eval_samples_per_second": 55.779,
+      "eval_steps_per_second": 2.936,
+      "step": 150
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 5.807656764984131,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.6093,
+      "step": 200
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "eval_loss": 0.6873595714569092,
+      "eval_runtime": 2.0664,
+      "eval_samples_per_second": 55.168,
+      "eval_steps_per_second": 2.904,
+      "step": 200
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 5.073987007141113,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.6292,
+      "step": 250
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "eval_loss": 0.6914292573928833,
+      "eval_runtime": 2.0537,
+      "eval_samples_per_second": 55.51,
+      "eval_steps_per_second": 2.922,
+      "step": 250
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 4.3011474609375,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.634,
+      "step": 300
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "eval_loss": 0.6931818127632141,
+      "eval_runtime": 2.0591,
+      "eval_samples_per_second": 55.363,
+      "eval_steps_per_second": 2.914,
+      "step": 300
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 3.1700639724731445,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.6556,
+      "step": 350
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "eval_loss": 0.6960527300834656,
+      "eval_runtime": 2.0563,
+      "eval_samples_per_second": 55.441,
+      "eval_steps_per_second": 2.918,
+      "step": 350
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 3.3075673580169678,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.6446,
+      "step": 400
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "eval_loss": 0.7140386700630188,
+      "eval_runtime": 2.0545,
+      "eval_samples_per_second": 55.487,
+      "eval_steps_per_second": 2.92,
+      "step": 400
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 3.119046211242676,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.5876,
+      "step": 450
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "eval_loss": 0.7231343984603882,
+      "eval_runtime": 2.0524,
+      "eval_samples_per_second": 55.544,
+      "eval_steps_per_second": 2.923,
+      "step": 450
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.419959545135498,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.6659,
+      "step": 500
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 0.7319712042808533,
+      "eval_runtime": 2.056,
+      "eval_samples_per_second": 55.447,
+      "eval_steps_per_second": 2.918,
+      "step": 500
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 5.57989501953125,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 0.7143,
+      "step": 550
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "eval_loss": 0.7315487861633301,
+      "eval_runtime": 2.0861,
+      "eval_samples_per_second": 54.647,
+      "eval_steps_per_second": 2.876,
+      "step": 550
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 3.6438112258911133,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.7114,
+      "step": 600
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": 0.7460434436798096,
+      "eval_runtime": 2.1,
+      "eval_samples_per_second": 54.287,
+      "eval_steps_per_second": 2.857,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.682473659515381,
+      "learning_rate": 2e-05,
+      "loss": 0.684,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7617189884185791,
+      "eval_runtime": 2.072,
+      "eval_samples_per_second": 55.019,
+      "eval_steps_per_second": 2.896,
+      "step": 650
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 1.6887282133102417,
+      "learning_rate": 1.9996395276708856e-05,
+      "loss": 0.3876,
+      "step": 700
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "eval_loss": 0.7934516668319702,
+      "eval_runtime": 2.0787,
+      "eval_samples_per_second": 54.841,
+      "eval_steps_per_second": 2.886,
+      "step": 700
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 4.347091197967529,
+      "learning_rate": 1.9985583705641418e-05,
+      "loss": 0.4194,
+      "step": 750
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "eval_loss": 0.8033629059791565,
+      "eval_runtime": 2.0558,
+      "eval_samples_per_second": 55.452,
+      "eval_steps_per_second": 2.919,
+      "step": 750
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 3.296565055847168,
+      "learning_rate": 1.9967573081342103e-05,
+      "loss": 0.3787,
+      "step": 800
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "eval_loss": 0.7959336638450623,
+      "eval_runtime": 2.0595,
+      "eval_samples_per_second": 55.353,
+      "eval_steps_per_second": 2.913,
+      "step": 800
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.9989190101623535,
+      "learning_rate": 1.9942376388474282e-05,
+      "loss": 0.4152,
+      "step": 850
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "eval_loss": 0.8067893385887146,
+      "eval_runtime": 2.0487,
+      "eval_samples_per_second": 55.644,
+      "eval_steps_per_second": 2.929,
+      "step": 850
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.2108572721481323,
+      "learning_rate": 1.9910011792459086e-05,
+      "loss": 0.4138,
+      "step": 900
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "eval_loss": 0.8018213510513306,
+      "eval_runtime": 2.0607,
+      "eval_samples_per_second": 55.322,
+      "eval_steps_per_second": 2.912,
+      "step": 900
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 2.7825069427490234,
+      "learning_rate": 1.9870502626379127e-05,
+      "loss": 0.4182,
+      "step": 950
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "eval_loss": 0.8101919293403625,
+      "eval_runtime": 2.0423,
+      "eval_samples_per_second": 55.818,
+      "eval_steps_per_second": 2.938,
+      "step": 950
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 2.586528778076172,
+      "learning_rate": 1.9823877374156647e-05,
+      "loss": 0.399,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 0.8011198043823242,
+      "eval_runtime": 2.0578,
+      "eval_samples_per_second": 55.399,
+      "eval_steps_per_second": 2.916,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 2.5284111499786377,
+      "learning_rate": 1.977016965001817e-05,
+      "loss": 0.4307,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "eval_loss": 0.8032751083374023,
+      "eval_runtime": 2.0607,
+      "eval_samples_per_second": 55.32,
+      "eval_steps_per_second": 2.912,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 2.9282965660095215,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.4321,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "eval_loss": 0.8253058195114136,
+      "eval_runtime": 2.0634,
+      "eval_samples_per_second": 55.25,
+      "eval_steps_per_second": 2.908,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 3.837848663330078,
+      "learning_rate": 1.9641666745335626e-05,
+      "loss": 0.4333,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "eval_loss": 0.8016666769981384,
+      "eval_runtime": 2.0452,
+      "eval_samples_per_second": 55.741,
+      "eval_steps_per_second": 2.934,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 3.095435619354248,
+      "learning_rate": 1.9566964208274254e-05,
+      "loss": 0.4001,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "eval_loss": 0.8035697340965271,
+      "eval_runtime": 2.0435,
+      "eval_samples_per_second": 55.787,
+      "eval_steps_per_second": 2.936,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 2.91595196723938,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 0.417,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "eval_loss": 0.7995880246162415,
+      "eval_runtime": 2.061,
+      "eval_samples_per_second": 55.312,
+      "eval_steps_per_second": 2.911,
+      "step": 1250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.497450113296509,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.4115,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8174861669540405,
+      "eval_runtime": 2.0588,
+      "eval_samples_per_second": 55.371,
+      "eval_steps_per_second": 2.914,
+      "step": 1300
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 2.0989558696746826,
+      "learning_rate": 1.9301713332493386e-05,
+      "loss": 0.2315,
+      "step": 1350
+    },
+    {
+      "epoch": 2.076923076923077,
+      "eval_loss": 0.8770357370376587,
+      "eval_runtime": 2.0393,
+      "eval_samples_per_second": 55.901,
+      "eval_steps_per_second": 2.942,
+      "step": 1350
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.8478964567184448,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 0.2078,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "eval_loss": 0.9085343480110168,
+      "eval_runtime": 2.0622,
+      "eval_samples_per_second": 55.282,
+      "eval_steps_per_second": 2.91,
+      "step": 1400
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 2.153414726257324,
+      "learning_rate": 1.909124299802724e-05,
+      "loss": 0.221,
+      "step": 1450
+    },
+    {
+      "epoch": 2.230769230769231,
+      "eval_loss": 0.9092664122581482,
+      "eval_runtime": 2.0445,
+      "eval_samples_per_second": 55.76,
+      "eval_steps_per_second": 2.935,
+      "step": 1450
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.1897672414779663,
+      "learning_rate": 1.8976137276390145e-05,
+      "loss": 0.2226,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 0.9329500794410706,
+      "eval_runtime": 2.0535,
+      "eval_samples_per_second": 55.514,
+      "eval_steps_per_second": 2.922,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 1.8265583515167236,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.2089,
+      "step": 1550
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "eval_loss": 0.9150766730308533,
+      "eval_runtime": 2.0377,
+      "eval_samples_per_second": 55.946,
+      "eval_steps_per_second": 2.945,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 2.9092257022857666,
+      "learning_rate": 1.8726599588756144e-05,
+      "loss": 0.2063,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "eval_loss": 0.9301209449768066,
+      "eval_runtime": 2.0587,
+      "eval_samples_per_second": 55.375,
+      "eval_steps_per_second": 2.914,
+      "step": 1600
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 2.421351432800293,
+      "learning_rate": 1.859234752562217e-05,
+      "loss": 0.2204,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "eval_loss": 0.903638482093811,
+      "eval_runtime": 2.0675,
+      "eval_samples_per_second": 55.14,
+      "eval_steps_per_second": 2.902,
+      "step": 1650
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 2.4857378005981445,
+      "learning_rate": 1.845190085543795e-05,
+      "loss": 0.2307,
+      "step": 1700
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "eval_loss": 0.9092226624488831,
+      "eval_runtime": 2.0741,
+      "eval_samples_per_second": 54.964,
+      "eval_steps_per_second": 2.893,
+      "step": 1700
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 1.8273831605911255,
+      "learning_rate": 1.8305360832480118e-05,
+      "loss": 0.2237,
+      "step": 1750
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "eval_loss": 0.8973789811134338,
+      "eval_runtime": 2.0928,
+      "eval_samples_per_second": 54.472,
+      "eval_steps_per_second": 2.867,
+      "step": 1750
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 2.9124813079833984,
+      "learning_rate": 1.8152833103995443e-05,
+      "loss": 0.2168,
+      "step": 1800
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": 0.9017825126647949,
+      "eval_runtime": 2.0552,
+      "eval_samples_per_second": 55.468,
+      "eval_steps_per_second": 2.919,
+      "step": 1800
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 3.047213554382324,
+      "learning_rate": 1.7994427634035016e-05,
+      "loss": 0.2222,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "eval_loss": 0.8894063234329224,
+      "eval_runtime": 2.1976,
+      "eval_samples_per_second": 51.874,
+      "eval_steps_per_second": 2.73,
+      "step": 1850
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 2.380671501159668,
+      "learning_rate": 1.7830258624176224e-05,
+      "loss": 0.2476,
+      "step": 1900
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_loss": 0.9025631546974182,
+      "eval_runtime": 2.0638,
+      "eval_samples_per_second": 55.237,
+      "eval_steps_per_second": 2.907,
+      "step": 1900
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.0212879180908203,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.2238,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9079655408859253,
+      "eval_runtime": 2.0553,
+      "eval_samples_per_second": 55.465,
+      "eval_steps_per_second": 2.919,
+      "step": 1950
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 1.594594120979309,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.1259,
+      "step": 2000
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 0.9700338840484619,
+      "eval_runtime": 2.0452,
+      "eval_samples_per_second": 55.739,
+      "eval_steps_per_second": 2.934,
+      "step": 2000
+    },
+    {
+      "epoch": 3.1538461538461537,
+      "grad_norm": 1.646579623222351,
+      "learning_rate": 1.7304374183977032e-05,
+      "loss": 0.1391,
+      "step": 2050
+    },
+    {
+      "epoch": 3.1538461538461537,
+      "eval_loss": 0.9763591885566711,
+      "eval_runtime": 2.063,
+      "eval_samples_per_second": 55.258,
+      "eval_steps_per_second": 2.908,
+      "step": 2050
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 1.3508063554763794,
+      "learning_rate": 1.7118374836693407e-05,
+      "loss": 0.1312,
+      "step": 2100
+    },
+    {
+      "epoch": 3.230769230769231,
+      "eval_loss": 0.980839729309082,
+      "eval_runtime": 2.0521,
+      "eval_samples_per_second": 55.552,
+      "eval_steps_per_second": 2.924,
+      "step": 2100
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 1.7058746814727783,
+      "learning_rate": 1.6927243535095995e-05,
+      "loss": 0.1403,
+      "step": 2150
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "eval_loss": 0.9776920676231384,
+      "eval_runtime": 2.0686,
+      "eval_samples_per_second": 55.109,
+      "eval_steps_per_second": 2.9,
+      "step": 2150
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 1.7895987033843994,
+      "learning_rate": 1.67311180742757e-05,
+      "loss": 0.1331,
+      "step": 2200
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "eval_loss": 0.9762499332427979,
+      "eval_runtime": 2.0534,
+      "eval_samples_per_second": 55.517,
+      "eval_steps_per_second": 2.922,
+      "step": 2200
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "grad_norm": 2.487821340560913,
+      "learning_rate": 1.653013984983585e-05,
+      "loss": 0.1473,
+      "step": 2250
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "eval_loss": 0.977838933467865,
+      "eval_runtime": 2.0467,
+      "eval_samples_per_second": 55.699,
+      "eval_steps_per_second": 2.932,
+      "step": 2250
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 1.2084770202636719,
+      "learning_rate": 1.6324453755953772e-05,
+      "loss": 0.1325,
+      "step": 2300
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "eval_loss": 0.9857913851737976,
+      "eval_runtime": 2.0583,
+      "eval_samples_per_second": 55.386,
+      "eval_steps_per_second": 2.915,
+      "step": 2300
+    },
+    {
+      "epoch": 3.6153846153846154,
+      "grad_norm": 1.8410896062850952,
+      "learning_rate": 1.6114208080920125e-05,
+      "loss": 0.1312,
+      "step": 2350
+    },
+    {
+      "epoch": 3.6153846153846154,
+      "eval_loss": 0.9874659180641174,
+      "eval_runtime": 2.0587,
+      "eval_samples_per_second": 55.376,
+      "eval_steps_per_second": 2.915,
+      "step": 2350
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 1.4452548027038574,
+      "learning_rate": 1.5899554400231233e-05,
+      "loss": 0.1417,
+      "step": 2400
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "eval_loss": 0.9763025045394897,
+      "eval_runtime": 2.0495,
+      "eval_samples_per_second": 55.624,
+      "eval_steps_per_second": 2.928,
+      "step": 2400
+    },
+    {
+      "epoch": 3.769230769230769,
+      "grad_norm": 1.0431134700775146,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.1236,
+      "step": 2450
+    },
+    {
+      "epoch": 3.769230769230769,
+      "eval_loss": 0.9919494986534119,
+      "eval_runtime": 2.0616,
+      "eval_samples_per_second": 55.296,
+      "eval_steps_per_second": 2.91,
+      "step": 2450
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 1.0208054780960083,
+      "learning_rate": 1.5457645101945046e-05,
+      "loss": 0.1416,
+      "step": 2500
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "eval_loss": 0.9878425002098083,
+      "eval_runtime": 2.0627,
+      "eval_samples_per_second": 55.268,
+      "eval_steps_per_second": 2.909,
+      "step": 2500
+    },
+    {
+      "epoch": 3.9230769230769234,
+      "grad_norm": 1.5294251441955566,
+      "learning_rate": 1.5230708076495777e-05,
+      "loss": 0.1312,
+      "step": 2550
+    },
+    {
+      "epoch": 3.9230769230769234,
+      "eval_loss": 0.9936930537223816,
+      "eval_runtime": 2.0508,
+      "eval_samples_per_second": 55.587,
+      "eval_steps_per_second": 2.926,
+      "step": 2550
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.475224018096924,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1376,
+      "step": 2600
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9945727586746216,
+      "eval_runtime": 2.0897,
+      "eval_samples_per_second": 54.553,
+      "eval_steps_per_second": 2.871,
+      "step": 2600
+    },
+    {
+      "epoch": 4.076923076923077,
+      "grad_norm": 0.8589996695518494,
+      "learning_rate": 1.4765687200213079e-05,
+      "loss": 0.1013,
+      "step": 2650
+    },
+    {
+      "epoch": 4.076923076923077,
+      "eval_loss": 1.0391929149627686,
+      "eval_runtime": 2.0679,
+      "eval_samples_per_second": 55.129,
+      "eval_steps_per_second": 2.902,
+      "step": 2650
+    },
+    {
+      "epoch": 4.153846153846154,
+      "grad_norm": 0.7440477013587952,
+      "learning_rate": 1.4527938603696376e-05,
+      "loss": 0.1065,
+      "step": 2700
+    },
+    {
+      "epoch": 4.153846153846154,
+      "eval_loss": 1.0234330892562866,
+      "eval_runtime": 2.0764,
+      "eval_samples_per_second": 54.903,
+      "eval_steps_per_second": 2.89,
+      "step": 2700
+    },
+    {
+      "epoch": 4.230769230769231,
+      "grad_norm": 0.8905901908874512,
+      "learning_rate": 1.4286925614030542e-05,
+      "loss": 0.088,
+      "step": 2750
+    },
+    {
+      "epoch": 4.230769230769231,
+      "eval_loss": 1.0325380563735962,
+      "eval_runtime": 2.0861,
+      "eval_samples_per_second": 54.647,
+      "eval_steps_per_second": 2.876,
+      "step": 2750
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 0.4518909752368927,
+      "learning_rate": 1.404282198824305e-05,
+      "loss": 0.1027,
+      "step": 2800
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "eval_loss": 1.024627923965454,
+      "eval_runtime": 2.1968,
+      "eval_samples_per_second": 51.895,
+      "eval_steps_per_second": 2.731,
+      "step": 2800
+    },
+    {
+      "epoch": 4.384615384615385,
+      "grad_norm": 1.2069981098175049,
+      "learning_rate": 1.3795803711538966e-05,
+      "loss": 0.1004,
+      "step": 2850
+    },
+    {
+      "epoch": 4.384615384615385,
+      "eval_loss": 1.0142472982406616,
+      "eval_runtime": 2.1058,
+      "eval_samples_per_second": 54.137,
+      "eval_steps_per_second": 2.849,
+      "step": 2850
+    },
+    {
+      "epoch": 4.461538461538462,
+      "grad_norm": 0.8361554741859436,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.0959,
+      "step": 2900
+    },
+    {
+      "epoch": 4.461538461538462,
+      "eval_loss": 1.0328094959259033,
+      "eval_runtime": 2.0484,
+      "eval_samples_per_second": 55.654,
+      "eval_steps_per_second": 2.929,
+      "step": 2900
+    },
+    {
+      "epoch": 4.538461538461538,
+      "grad_norm": 1.5358504056930542,
+      "learning_rate": 1.3293737524320798e-05,
+      "loss": 0.0883,
+      "step": 2950
+    },
+    {
+      "epoch": 4.538461538461538,
+      "eval_loss": 1.0490965843200684,
+      "eval_runtime": 2.042,
+      "eval_samples_per_second": 55.828,
+      "eval_steps_per_second": 2.938,
+      "step": 2950
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 1.1605786085128784,
+      "learning_rate": 1.303905157574247e-05,
+      "loss": 0.0994,
+      "step": 3000
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_loss": 1.026671051979065,
+      "eval_runtime": 2.0528,
+      "eval_samples_per_second": 55.535,
+      "eval_steps_per_second": 2.923,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6923076923076925,
+      "grad_norm": 0.734259307384491,
+      "learning_rate": 1.2782174639164528e-05,
+      "loss": 0.1001,
+      "step": 3050
+    },
+    {
+      "epoch": 4.6923076923076925,
+      "eval_loss": 1.0184227228164673,
+      "eval_runtime": 2.0577,
+      "eval_samples_per_second": 55.4,
+      "eval_steps_per_second": 2.916,
+      "step": 3050
+    },
+    {
+      "epoch": 4.769230769230769,
+      "grad_norm": 1.0172340869903564,
+      "learning_rate": 1.2523291908642219e-05,
+      "loss": 0.1026,
+      "step": 3100
+    },
+    {
+      "epoch": 4.769230769230769,
+      "eval_loss": 1.02394437789917,
+      "eval_runtime": 2.0572,
+      "eval_samples_per_second": 55.415,
+      "eval_steps_per_second": 2.917,
+      "step": 3100
+    },
+    {
+      "epoch": 4.846153846153846,
+      "grad_norm": 1.0702561140060425,
+      "learning_rate": 1.2262590024297226e-05,
+      "loss": 0.0947,
+      "step": 3150
+    },
+    {
+      "epoch": 4.846153846153846,
+      "eval_loss": 1.0371849536895752,
+      "eval_runtime": 2.0649,
+      "eval_samples_per_second": 55.208,
+      "eval_steps_per_second": 2.906,
+      "step": 3150
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 0.9528751373291016,
+      "learning_rate": 1.2000256937760446e-05,
+      "loss": 0.0953,
+      "step": 3200
+    },
+    {
+      "epoch": 4.923076923076923,
+      "eval_loss": 1.012660264968872,
+      "eval_runtime": 2.2321,
+      "eval_samples_per_second": 51.074,
+      "eval_steps_per_second": 2.688,
+      "step": 3200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5601332783699036,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0943,
+      "step": 3250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0416377782821655,
+      "eval_runtime": 2.0812,
+      "eval_samples_per_second": 54.777,
+      "eval_steps_per_second": 2.883,
+      "step": 3250
+    },
+    {
+      "epoch": 5.076923076923077,
+      "grad_norm": 0.8849101662635803,
+      "learning_rate": 1.1471454708317163e-05,
+      "loss": 0.0724,
+      "step": 3300
+    },
+    {
+      "epoch": 5.076923076923077,
+      "eval_loss": 1.082357406616211,
+      "eval_runtime": 2.0473,
+      "eval_samples_per_second": 55.682,
+      "eval_steps_per_second": 2.931,
+      "step": 3300
+    },
+    {
+      "epoch": 5.153846153846154,
+      "grad_norm": 2.244279384613037,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.0698,
+      "step": 3350
+    },
+    {
+      "epoch": 5.153846153846154,
+      "eval_loss": 1.0606184005737305,
+      "eval_runtime": 2.0544,
+      "eval_samples_per_second": 55.49,
+      "eval_steps_per_second": 2.921,
+      "step": 3350
+    },
+    {
+      "epoch": 5.230769230769231,
+      "grad_norm": 1.1950870752334595,
+      "learning_rate": 1.0938409894031793e-05,
+      "loss": 0.0768,
+      "step": 3400
+    },
+    {
+      "epoch": 5.230769230769231,
+      "eval_loss": 1.096448302268982,
+      "eval_runtime": 2.0548,
+      "eval_samples_per_second": 55.479,
+      "eval_steps_per_second": 2.92,
+      "step": 3400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1700,
+  "total_flos": 1.6533587657700147e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}