adding model checkpoints

checkpoint-100/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
+}

checkpoint-100/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": true,
+  "vocab_size": 32016
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

checkpoint-100/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf6caed8c97f44bbe37c808c8a62b9416485abda7013d5f9b392e72b09b5d21
+size 4840658560

checkpoint-100/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e2949393a3a2da8827f9b9afcc8efc533c9bb7870e57aa27901e8f9cc0f07f
+size 4857206856

checkpoint-100/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41444971f5252ace59fa664fbb0b832ccc0b9929bc17f07e16edf66e2b447c9
+size 4857206904

checkpoint-100/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5617442f4800ac0b5edf35327e81a7e095d279b27f32f65718d0f6810039d615
+size 4857206904

checkpoint-100/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5d26527e1940266b46172f944d603e9019fc396478ba61e878e50afbe66b16
+size 4857206904

checkpoint-100/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2ca27a259313f73c19818cd44230d75233087d6880623548eb882572c13b11
+size 2684734256

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26954186752
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,82 @@
+{
+  "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": "<pad>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3076923076923077,
+  "eval_steps": 10,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153846153846154,
+      "eval_loss": 1.845949411392212,
+      "eval_runtime": 1.9761,
+      "eval_samples_per_second": 57.69,
+      "eval_steps_per_second": 3.036,
+      "step": 2
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 29.46457290649414,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.944,
+      "step": 10
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "eval_loss": 1.7965577840805054,
+      "eval_runtime": 1.9506,
+      "eval_samples_per_second": 58.444,
+      "eval_steps_per_second": 3.076,
+      "step": 10
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 14.49207878112793,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.6999,
+      "step": 20
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "eval_loss": 1.5032916069030762,
+      "eval_runtime": 1.9599,
+      "eval_samples_per_second": 58.168,
+      "eval_steps_per_second": 3.061,
+      "step": 20
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 11.355466842651367,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.1499,
+      "step": 30
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "eval_loss": 0.8391174674034119,
+      "eval_runtime": 1.9437,
+      "eval_samples_per_second": 58.65,
+      "eval_steps_per_second": 3.087,
+      "step": 30
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 5.648468017578125,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.7194,
+      "step": 40
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "eval_loss": 0.6716201305389404,
+      "eval_runtime": 1.9517,
+      "eval_samples_per_second": 58.411,
+      "eval_steps_per_second": 3.074,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 5.752841949462891,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.6811,
+      "step": 50
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "eval_loss": 0.6289324164390564,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 58.401,
+      "eval_steps_per_second": 3.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 3.414722204208374,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.5924,
+      "step": 60
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "eval_loss": 0.6140013337135315,
+      "eval_runtime": 1.94,
+      "eval_samples_per_second": 58.762,
+      "eval_steps_per_second": 3.093,
+      "step": 60
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 5.556036949157715,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.6135,
+      "step": 70
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "eval_loss": 0.6054026484489441,
+      "eval_runtime": 1.9659,
+      "eval_samples_per_second": 57.988,
+      "eval_steps_per_second": 3.052,
+      "step": 70
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 4.436710834503174,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.5952,
+      "step": 80
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "eval_loss": 0.5986860990524292,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 58.677,
+      "eval_steps_per_second": 3.088,
+      "step": 80
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 3.496018409729004,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.5887,
+      "step": 90
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "eval_loss": 0.594973623752594,
+      "eval_runtime": 1.9468,
+      "eval_samples_per_second": 58.558,
+      "eval_steps_per_second": 3.082,
+      "step": 90
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.3540539741516113,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.5634,
+      "step": 100
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "eval_loss": 0.5954164266586304,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 58.521,
+      "eval_steps_per_second": 3.08,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 50,
+  "total_flos": 8660177976819712.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a275a1f941882da99f851a4d3084b949cf3401949c2995ebc356025dd22836
+size 5112

checkpoint-1000/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
+}

checkpoint-1000/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": true,
+  "vocab_size": 32016
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

checkpoint-1000/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2193c77d48cf1f9e545e0ee362d03edea1d033ec834ad6b2c54464b594ba9d0
+size 4840658560

checkpoint-1000/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a71c6a2864033940e34c086901765d593f907154be26b7197676af847550bd8
+size 4857206856

checkpoint-1000/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc005b5373d9088fb65610876527166c0d234b8d366ea7f12258ddde285aefc
+size 4857206904

checkpoint-1000/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9496bb0cb2f9861b8e74e2fc53a451f7c9152be8bb2c8f9a6053974592d3d9
+size 4857206904

checkpoint-1000/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8152d583ea7056435b233e05c9e86e5c4a300cebf21cd5a4f3a6dec150cf129
+size 4857206904

checkpoint-1000/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833450c1cfd9113ee1526b74e24b3ccb0fb15a10aac676a852a81c03ec4a5139
+size 2684734256

checkpoint-1000/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26954186752
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,82 @@
+{
+  "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": "<pad>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

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

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1529 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.076923076923077,
+  "eval_steps": 10,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153846153846154,
+      "eval_loss": 1.845949411392212,
+      "eval_runtime": 1.9761,
+      "eval_samples_per_second": 57.69,
+      "eval_steps_per_second": 3.036,
+      "step": 2
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 29.46457290649414,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.944,
+      "step": 10
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "eval_loss": 1.7965577840805054,
+      "eval_runtime": 1.9506,
+      "eval_samples_per_second": 58.444,
+      "eval_steps_per_second": 3.076,
+      "step": 10
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 14.49207878112793,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.6999,
+      "step": 20
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "eval_loss": 1.5032916069030762,
+      "eval_runtime": 1.9599,
+      "eval_samples_per_second": 58.168,
+      "eval_steps_per_second": 3.061,
+      "step": 20
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 11.355466842651367,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.1499,
+      "step": 30
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "eval_loss": 0.8391174674034119,
+      "eval_runtime": 1.9437,
+      "eval_samples_per_second": 58.65,
+      "eval_steps_per_second": 3.087,
+      "step": 30
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 5.648468017578125,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.7194,
+      "step": 40
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "eval_loss": 0.6716201305389404,
+      "eval_runtime": 1.9517,
+      "eval_samples_per_second": 58.411,
+      "eval_steps_per_second": 3.074,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 5.752841949462891,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.6811,
+      "step": 50
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "eval_loss": 0.6289324164390564,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 58.401,
+      "eval_steps_per_second": 3.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 3.414722204208374,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.5924,
+      "step": 60
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "eval_loss": 0.6140013337135315,
+      "eval_runtime": 1.94,
+      "eval_samples_per_second": 58.762,
+      "eval_steps_per_second": 3.093,
+      "step": 60
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 5.556036949157715,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.6135,
+      "step": 70
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "eval_loss": 0.6054026484489441,
+      "eval_runtime": 1.9659,
+      "eval_samples_per_second": 57.988,
+      "eval_steps_per_second": 3.052,
+      "step": 70
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 4.436710834503174,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.5952,
+      "step": 80
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "eval_loss": 0.5986860990524292,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 58.677,
+      "eval_steps_per_second": 3.088,
+      "step": 80
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 3.496018409729004,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.5887,
+      "step": 90
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "eval_loss": 0.594973623752594,
+      "eval_runtime": 1.9468,
+      "eval_samples_per_second": 58.558,
+      "eval_steps_per_second": 3.082,
+      "step": 90
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.3540539741516113,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.5634,
+      "step": 100
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "eval_loss": 0.5954164266586304,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 58.521,
+      "eval_steps_per_second": 3.08,
+      "step": 100
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "grad_norm": 2.9880635738372803,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.5827,
+      "step": 110
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "eval_loss": 0.5955133438110352,
+      "eval_runtime": 1.9432,
+      "eval_samples_per_second": 58.667,
+      "eval_steps_per_second": 3.088,
+      "step": 110
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 1.9405996799468994,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.5726,
+      "step": 120
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "eval_loss": 0.5951128602027893,
+      "eval_runtime": 1.9715,
+      "eval_samples_per_second": 57.824,
+      "eval_steps_per_second": 3.043,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.9948021173477173,
+      "learning_rate": 1e-05,
+      "loss": 0.6488,
+      "step": 130
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.5964463949203491,
+      "eval_runtime": 2.1032,
+      "eval_samples_per_second": 54.203,
+      "eval_steps_per_second": 2.853,
+      "step": 130
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 1.95350980758667,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.6218,
+      "step": 140
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "eval_loss": 0.5996471047401428,
+      "eval_runtime": 1.9539,
+      "eval_samples_per_second": 58.345,
+      "eval_steps_per_second": 3.071,
+      "step": 140
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 3.840015411376953,
+      "learning_rate": 1.1538461538461538e-05,
+      "loss": 0.5585,
+      "step": 150
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "eval_loss": 0.6000372767448425,
+      "eval_runtime": 1.9457,
+      "eval_samples_per_second": 58.592,
+      "eval_steps_per_second": 3.084,
+      "step": 150
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 2.345364809036255,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.5314,
+      "step": 160
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "eval_loss": 0.6025042533874512,
+      "eval_runtime": 1.9398,
+      "eval_samples_per_second": 58.768,
+      "eval_steps_per_second": 3.093,
+      "step": 160
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "grad_norm": 3.162071704864502,
+      "learning_rate": 1.3076923076923078e-05,
+      "loss": 0.6901,
+      "step": 170
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "eval_loss": 0.598171055316925,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.705,
+      "eval_steps_per_second": 3.09,
+      "step": 170
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 3.9432108402252197,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.6604,
+      "step": 180
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "eval_loss": 0.5974885821342468,
+      "eval_runtime": 1.9664,
+      "eval_samples_per_second": 57.975,
+      "eval_steps_per_second": 3.051,
+      "step": 180
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "grad_norm": 1.904718279838562,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 0.5806,
+      "step": 190
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "eval_loss": 0.6012160778045654,
+      "eval_runtime": 2.082,
+      "eval_samples_per_second": 54.755,
+      "eval_steps_per_second": 2.882,
+      "step": 190
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 2.2823173999786377,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.588,
+      "step": 200
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "eval_loss": 0.6052933931350708,
+      "eval_runtime": 1.9613,
+      "eval_samples_per_second": 58.124,
+      "eval_steps_per_second": 3.059,
+      "step": 200
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 1.8020161390304565,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.5826,
+      "step": 210
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "eval_loss": 0.6047356724739075,
+      "eval_runtime": 1.9487,
+      "eval_samples_per_second": 58.5,
+      "eval_steps_per_second": 3.079,
+      "step": 210
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 1.8297995328903198,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 0.5442,
+      "step": 220
+    },
+    {
+      "epoch": 0.676923076923077,
+      "eval_loss": 0.6105689406394958,
+      "eval_runtime": 2.0567,
+      "eval_samples_per_second": 55.429,
+      "eval_steps_per_second": 2.917,
+      "step": 220
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "grad_norm": 1.8141131401062012,
+      "learning_rate": 1.7692307692307694e-05,
+      "loss": 0.602,
+      "step": 230
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "eval_loss": 0.6149886250495911,
+      "eval_runtime": 2.1951,
+      "eval_samples_per_second": 51.933,
+      "eval_steps_per_second": 2.733,
+      "step": 230
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 2.093683958053589,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.6103,
+      "step": 240
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "eval_loss": 0.621900200843811,
+      "eval_runtime": 1.9465,
+      "eval_samples_per_second": 58.567,
+      "eval_steps_per_second": 3.082,
+      "step": 240
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.840038776397705,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 0.5775,
+      "step": 250
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 0.6232128739356995,
+      "eval_runtime": 1.9883,
+      "eval_samples_per_second": 57.334,
+      "eval_steps_per_second": 3.018,
+      "step": 250
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.7329185009002686,
+      "learning_rate": 2e-05,
+      "loss": 0.6808,
+      "step": 260
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.6226441264152527,
+      "eval_runtime": 1.9469,
+      "eval_samples_per_second": 58.553,
+      "eval_steps_per_second": 3.082,
+      "step": 260
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 2.738678455352783,
+      "learning_rate": 1.999909877856721e-05,
+      "loss": 0.5833,
+      "step": 270
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "eval_loss": 0.6240194439888,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.706,
+      "eval_steps_per_second": 3.09,
+      "step": 270
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 2.0359909534454346,
+      "learning_rate": 1.9996395276708856e-05,
+      "loss": 0.691,
+      "step": 280
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "eval_loss": 0.6267117857933044,
+      "eval_runtime": 1.939,
+      "eval_samples_per_second": 58.794,
+      "eval_steps_per_second": 3.094,
+      "step": 280
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "grad_norm": 1.7706685066223145,
+      "learning_rate": 1.9991889981715696e-05,
+      "loss": 0.6404,
+      "step": 290
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "eval_loss": 0.6222097873687744,
+      "eval_runtime": 1.9533,
+      "eval_samples_per_second": 58.363,
+      "eval_steps_per_second": 3.072,
+      "step": 290
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 2.129652976989746,
+      "learning_rate": 1.9985583705641418e-05,
+      "loss": 0.7109,
+      "step": 300
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": 0.6229674816131592,
+      "eval_runtime": 1.9467,
+      "eval_samples_per_second": 58.561,
+      "eval_steps_per_second": 3.082,
+      "step": 300
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "grad_norm": 1.8439427614212036,
+      "learning_rate": 1.9977477585156252e-05,
+      "loss": 0.6623,
+      "step": 310
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "eval_loss": 0.6273208856582642,
+      "eval_runtime": 2.0985,
+      "eval_samples_per_second": 54.324,
+      "eval_steps_per_second": 2.859,
+      "step": 310
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 2.1446306705474854,
+      "learning_rate": 1.9967573081342103e-05,
+      "loss": 0.5583,
+      "step": 320
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "eval_loss": 0.6260280013084412,
+      "eval_runtime": 1.9521,
+      "eval_samples_per_second": 58.398,
+      "eval_steps_per_second": 3.074,
+      "step": 320
+    },
+    {
+      "epoch": 1.0153846153846153,
+      "grad_norm": 1.9259562492370605,
+      "learning_rate": 1.9955871979429188e-05,
+      "loss": 0.4857,
+      "step": 330
+    },
+    {
+      "epoch": 1.0153846153846153,
+      "eval_loss": 0.6497873067855835,
+      "eval_runtime": 1.9489,
+      "eval_samples_per_second": 58.496,
+      "eval_steps_per_second": 3.079,
+      "step": 330
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 1.8625404834747314,
+      "learning_rate": 1.9942376388474282e-05,
+      "loss": 0.4152,
+      "step": 340
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "eval_loss": 0.6430822014808655,
+      "eval_runtime": 1.9534,
+      "eval_samples_per_second": 58.358,
+      "eval_steps_per_second": 3.071,
+      "step": 340
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 1.1712415218353271,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 0.3459,
+      "step": 350
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "eval_loss": 0.671064019203186,
+      "eval_runtime": 1.9772,
+      "eval_samples_per_second": 57.658,
+      "eval_steps_per_second": 3.035,
+      "step": 350
+    },
+    {
+      "epoch": 1.1076923076923078,
+      "grad_norm": 1.0710129737854004,
+      "learning_rate": 1.9910011792459086e-05,
+      "loss": 0.4307,
+      "step": 360
+    },
+    {
+      "epoch": 1.1076923076923078,
+      "eval_loss": 0.6545295119285583,
+      "eval_runtime": 2.0822,
+      "eval_samples_per_second": 54.749,
+      "eval_steps_per_second": 2.882,
+      "step": 360
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 1.839811086654663,
+      "learning_rate": 1.989114862093232e-05,
+      "loss": 0.4084,
+      "step": 370
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "eval_loss": 0.6743721961975098,
+      "eval_runtime": 1.962,
+      "eval_samples_per_second": 58.105,
+      "eval_steps_per_second": 3.058,
+      "step": 370
+    },
+    {
+      "epoch": 1.1692307692307693,
+      "grad_norm": 2.2416107654571533,
+      "learning_rate": 1.9870502626379127e-05,
+      "loss": 0.4203,
+      "step": 380
+    },
+    {
+      "epoch": 1.1692307692307693,
+      "eval_loss": 0.6703702211380005,
+      "eval_runtime": 2.0871,
+      "eval_samples_per_second": 54.621,
+      "eval_steps_per_second": 2.875,
+      "step": 380
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8775320053100586,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.3056,
+      "step": 390
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.680027425289154,
+      "eval_runtime": 2.0739,
+      "eval_samples_per_second": 54.97,
+      "eval_steps_per_second": 2.893,
+      "step": 390
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 2.1544764041900635,
+      "learning_rate": 1.9823877374156647e-05,
+      "loss": 0.4332,
+      "step": 400
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "eval_loss": 0.6662920117378235,
+      "eval_runtime": 1.9498,
+      "eval_samples_per_second": 58.466,
+      "eval_steps_per_second": 3.077,
+      "step": 400
+    },
+    {
+      "epoch": 1.2615384615384615,
+      "grad_norm": 1.740652084350586,
+      "learning_rate": 1.979790652042268e-05,
+      "loss": 0.3707,
+      "step": 410
+    },
+    {
+      "epoch": 1.2615384615384615,
+      "eval_loss": 0.6721649765968323,
+      "eval_runtime": 1.9421,
+      "eval_samples_per_second": 58.699,
+      "eval_steps_per_second": 3.089,
+      "step": 410
+    },
+    {
+      "epoch": 1.2923076923076924,
+      "grad_norm": 1.8645464181900024,
+      "learning_rate": 1.977016965001817e-05,
+      "loss": 0.412,
+      "step": 420
+    },
+    {
+      "epoch": 1.2923076923076924,
+      "eval_loss": 0.6605477333068848,
+      "eval_runtime": 1.9455,
+      "eval_samples_per_second": 58.597,
+      "eval_steps_per_second": 3.084,
+      "step": 420
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 1.3930943012237549,
+      "learning_rate": 1.9740671762355548e-05,
+      "loss": 0.388,
+      "step": 430
+    },
+    {
+      "epoch": 1.323076923076923,
+      "eval_loss": 0.6649342775344849,
+      "eval_runtime": 1.9497,
+      "eval_samples_per_second": 58.471,
+      "eval_steps_per_second": 3.077,
+      "step": 430
+    },
+    {
+      "epoch": 1.353846153846154,
+      "grad_norm": 1.8291655778884888,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.4118,
+      "step": 440
+    },
+    {
+      "epoch": 1.353846153846154,
+      "eval_loss": 0.6680696606636047,
+      "eval_runtime": 2.0262,
+      "eval_samples_per_second": 56.262,
+      "eval_steps_per_second": 2.961,
+      "step": 440
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.1135263442993164,
+      "learning_rate": 1.9676414519013782e-05,
+      "loss": 0.3205,
+      "step": 450
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "eval_loss": 0.6739374995231628,
+      "eval_runtime": 1.9443,
+      "eval_samples_per_second": 58.633,
+      "eval_steps_per_second": 3.086,
+      "step": 450
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 2.233457326889038,
+      "learning_rate": 1.9641666745335626e-05,
+      "loss": 0.3591,
+      "step": 460
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "eval_loss": 0.6751876473426819,
+      "eval_runtime": 1.9447,
+      "eval_samples_per_second": 58.622,
+      "eval_steps_per_second": 3.085,
+      "step": 460
+    },
+    {
+      "epoch": 1.4461538461538461,
+      "grad_norm": 1.815677523612976,
+      "learning_rate": 1.9605181116313725e-05,
+      "loss": 0.4107,
+      "step": 470
+    },
+    {
+      "epoch": 1.4461538461538461,
+      "eval_loss": 0.6670271158218384,
+      "eval_runtime": 1.9448,
+      "eval_samples_per_second": 58.618,
+      "eval_steps_per_second": 3.085,
+      "step": 470
+    },
+    {
+      "epoch": 1.476923076923077,
+      "grad_norm": 2.0177175998687744,
+      "learning_rate": 1.9566964208274254e-05,
+      "loss": 0.3954,
+      "step": 480
+    },
+    {
+      "epoch": 1.476923076923077,
+      "eval_loss": 0.6706439256668091,
+      "eval_runtime": 2.1454,
+      "eval_samples_per_second": 53.137,
+      "eval_steps_per_second": 2.797,
+      "step": 480
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 2.2797820568084717,
+      "learning_rate": 1.9527022909596537e-05,
+      "loss": 0.349,
+      "step": 490
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "eval_loss": 0.6916453242301941,
+      "eval_runtime": 1.9454,
+      "eval_samples_per_second": 58.599,
+      "eval_steps_per_second": 3.084,
+      "step": 490
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.6123872995376587,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 0.3796,
+      "step": 500
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 0.6646614670753479,
+      "eval_runtime": 1.9525,
+      "eval_samples_per_second": 58.386,
+      "eval_steps_per_second": 3.073,
+      "step": 500
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "grad_norm": 2.039036989212036,
+      "learning_rate": 1.9441996246603848e-05,
+      "loss": 0.4163,
+      "step": 510
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "eval_loss": 0.6671331524848938,
+      "eval_runtime": 1.9375,
+      "eval_samples_per_second": 58.84,
+      "eval_steps_per_second": 3.097,
+      "step": 510
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.8493613004684448,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3768,
+      "step": 520
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.6984831094741821,
+      "eval_runtime": 1.9384,
+      "eval_samples_per_second": 58.812,
+      "eval_steps_per_second": 3.095,
+      "step": 520
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "grad_norm": 1.1424219608306885,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.3985,
+      "step": 530
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "eval_loss": 0.6629871726036072,
+      "eval_runtime": 1.9471,
+      "eval_samples_per_second": 58.549,
+      "eval_steps_per_second": 3.082,
+      "step": 530
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "grad_norm": 1.8115930557250977,
+      "learning_rate": 1.9301713332493386e-05,
+      "loss": 0.397,
+      "step": 540
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "eval_loss": 0.6737513542175293,
+      "eval_runtime": 1.9496,
+      "eval_samples_per_second": 58.473,
+      "eval_steps_per_second": 3.078,
+      "step": 540
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.7575629949569702,
+      "learning_rate": 1.925158765744924e-05,
+      "loss": 0.4624,
+      "step": 550
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "eval_loss": 0.660962700843811,
+      "eval_runtime": 1.953,
+      "eval_samples_per_second": 58.372,
+      "eval_steps_per_second": 3.072,
+      "step": 550
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "grad_norm": 1.7702680826187134,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 0.3705,
+      "step": 560
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "eval_loss": 0.663165807723999,
+      "eval_runtime": 1.9548,
+      "eval_samples_per_second": 58.319,
+      "eval_steps_per_second": 3.069,
+      "step": 560
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "grad_norm": 1.4927833080291748,
+      "learning_rate": 1.9146343005342546e-05,
+      "loss": 0.3708,
+      "step": 570
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "eval_loss": 0.673720121383667,
+      "eval_runtime": 1.9582,
+      "eval_samples_per_second": 58.216,
+      "eval_steps_per_second": 3.064,
+      "step": 570
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 1.6623133420944214,
+      "learning_rate": 1.909124299802724e-05,
+      "loss": 0.399,
+      "step": 580
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "eval_loss": 0.6685453653335571,
+      "eval_runtime": 1.9645,
+      "eval_samples_per_second": 58.029,
+      "eval_steps_per_second": 3.054,
+      "step": 580
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "grad_norm": 2.253755807876587,
+      "learning_rate": 1.9034504346103825e-05,
+      "loss": 0.3642,
+      "step": 590
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "eval_loss": 0.6629040241241455,
+      "eval_runtime": 1.9527,
+      "eval_samples_per_second": 58.382,
+      "eval_steps_per_second": 3.073,
+      "step": 590
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 1.8123295307159424,
+      "learning_rate": 1.8976137276390145e-05,
+      "loss": 0.4213,
+      "step": 600
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "eval_loss": 0.6636160016059875,
+      "eval_runtime": 2.1305,
+      "eval_samples_per_second": 53.508,
+      "eval_steps_per_second": 2.816,
+      "step": 600
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 1.6377712488174438,
+      "learning_rate": 1.891615230921703e-05,
+      "loss": 0.3154,
+      "step": 610
+    },
+    {
+      "epoch": 1.876923076923077,
+      "eval_loss": 0.6621889472007751,
+      "eval_runtime": 1.9727,
+      "eval_samples_per_second": 57.789,
+      "eval_steps_per_second": 3.042,
+      "step": 610
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "grad_norm": 2.1680402755737305,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.421,
+      "step": 620
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "eval_loss": 0.6584432721138,
+      "eval_runtime": 1.9532,
+      "eval_samples_per_second": 58.367,
+      "eval_steps_per_second": 3.072,
+      "step": 620
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "grad_norm": 1.771596074104309,
+      "learning_rate": 1.879137221995095e-05,
+      "loss": 0.3625,
+      "step": 630
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "eval_loss": 0.6574673652648926,
+      "eval_runtime": 1.9593,
+      "eval_samples_per_second": 58.185,
+      "eval_steps_per_second": 3.062,
+      "step": 630
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 1.6291016340255737,
+      "learning_rate": 1.8726599588756144e-05,
+      "loss": 0.3787,
+      "step": 640
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "eval_loss": 0.6593620181083679,
+      "eval_runtime": 2.1362,
+      "eval_samples_per_second": 53.367,
+      "eval_steps_per_second": 2.809,
+      "step": 640
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.721921682357788,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.3923,
+      "step": 650
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6485319137573242,
+      "eval_runtime": 1.967,
+      "eval_samples_per_second": 57.957,
+      "eval_steps_per_second": 3.05,
+      "step": 650
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "grad_norm": 1.6391288042068481,
+      "learning_rate": 1.859234752562217e-05,
+      "loss": 0.2137,
+      "step": 660
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "eval_loss": 0.7283760905265808,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 58.678,
+      "eval_steps_per_second": 3.088,
+      "step": 660
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "grad_norm": 1.9791120290756226,
+      "learning_rate": 1.8522892291850335e-05,
+      "loss": 0.2221,
+      "step": 670
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "eval_loss": 0.7443767189979553,
+      "eval_runtime": 1.9429,
+      "eval_samples_per_second": 58.676,
+      "eval_steps_per_second": 3.088,
+      "step": 670
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 2.0093741416931152,
+      "learning_rate": 1.845190085543795e-05,
+      "loss": 0.1777,
+      "step": 680
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "eval_loss": 0.7445951700210571,
+      "eval_runtime": 1.9592,
+      "eval_samples_per_second": 58.186,
+      "eval_steps_per_second": 3.062,
+      "step": 680
+    },
+    {
+      "epoch": 2.123076923076923,
+      "grad_norm": 1.8424338102340698,
+      "learning_rate": 1.8379386012185813e-05,
+      "loss": 0.1755,
+      "step": 690
+    },
+    {
+      "epoch": 2.123076923076923,
+      "eval_loss": 0.7517443299293518,
+      "eval_runtime": 2.0747,
+      "eval_samples_per_second": 54.947,
+      "eval_steps_per_second": 2.892,
+      "step": 690
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.4635226726531982,
+      "learning_rate": 1.8305360832480118e-05,
+      "loss": 0.1742,
+      "step": 700
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "eval_loss": 0.7649147510528564,
+      "eval_runtime": 1.9437,
+      "eval_samples_per_second": 58.65,
+      "eval_steps_per_second": 3.087,
+      "step": 700
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 1.9029723405838013,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.2037,
+      "step": 710
+    },
+    {
+      "epoch": 2.184615384615385,
+      "eval_loss": 0.7539044618606567,
+      "eval_runtime": 2.1243,
+      "eval_samples_per_second": 53.664,
+      "eval_steps_per_second": 2.824,
+      "step": 710
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "grad_norm": 1.3570928573608398,
+      "learning_rate": 1.8152833103995443e-05,
+      "loss": 0.1954,
+      "step": 720
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "eval_loss": 0.7460123300552368,
+      "eval_runtime": 2.1466,
+      "eval_samples_per_second": 53.108,
+      "eval_steps_per_second": 2.795,
+      "step": 720
+    },
+    {
+      "epoch": 2.246153846153846,
+      "grad_norm": 1.5055183172225952,
+      "learning_rate": 1.807435804746807e-05,
+      "loss": 0.2027,
+      "step": 730
+    },
+    {
+      "epoch": 2.246153846153846,
+      "eval_loss": 0.7585832476615906,
+      "eval_runtime": 2.1298,
+      "eval_samples_per_second": 53.525,
+      "eval_steps_per_second": 2.817,
+      "step": 730
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 1.0890541076660156,
+      "learning_rate": 1.7994427634035016e-05,
+      "loss": 0.1867,
+      "step": 740
+    },
+    {
+      "epoch": 2.276923076923077,
+      "eval_loss": 0.7535340785980225,
+      "eval_runtime": 1.9471,
+      "eval_samples_per_second": 58.549,
+      "eval_steps_per_second": 3.082,
+      "step": 740
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.11017644405365,
+      "learning_rate": 1.791305627069662e-05,
+      "loss": 0.1875,
+      "step": 750
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 0.7587242126464844,
+      "eval_runtime": 1.9462,
+      "eval_samples_per_second": 58.575,
+      "eval_steps_per_second": 3.083,
+      "step": 750
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": 1.7792816162109375,
+      "learning_rate": 1.7830258624176224e-05,
+      "loss": 0.1841,
+      "step": 760
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "eval_loss": 0.7774962782859802,
+      "eval_runtime": 1.942,
+      "eval_samples_per_second": 58.703,
+      "eval_steps_per_second": 3.09,
+      "step": 760
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 1.384929895401001,
+      "learning_rate": 1.7746049618276545e-05,
+      "loss": 0.1724,
+      "step": 770
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "eval_loss": 0.7517464756965637,
+      "eval_runtime": 2.0655,
+      "eval_samples_per_second": 55.191,
+      "eval_steps_per_second": 2.905,
+      "step": 770
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.3608155250549316,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.1831,
+      "step": 780
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.7726874351501465,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 58.4,
+      "eval_steps_per_second": 3.074,
+      "step": 780
+    },
+    {
+      "epoch": 2.430769230769231,
+      "grad_norm": 0.9307472109794617,
+      "learning_rate": 1.7573458492761802e-05,
+      "loss": 0.1897,
+      "step": 790
+    },
+    {
+      "epoch": 2.430769230769231,
+      "eval_loss": 0.7573862075805664,
+      "eval_runtime": 1.9435,
+      "eval_samples_per_second": 58.658,
+      "eval_steps_per_second": 3.087,
+      "step": 790
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.0741816759109497,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.1936,
+      "step": 800
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "eval_loss": 0.7550384402275085,
+      "eval_runtime": 1.9506,
+      "eval_samples_per_second": 58.443,
+      "eval_steps_per_second": 3.076,
+      "step": 800
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 1.3956509828567505,
+      "learning_rate": 1.7395407322802374e-05,
+      "loss": 0.1969,
+      "step": 810
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "eval_loss": 0.7733697295188904,
+      "eval_runtime": 1.9492,
+      "eval_samples_per_second": 58.484,
+      "eval_steps_per_second": 3.078,
+      "step": 810
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": 1.529106855392456,
+      "learning_rate": 1.7304374183977032e-05,
+      "loss": 0.2222,
+      "step": 820
+    },
+    {
+      "epoch": 2.523076923076923,
+      "eval_loss": 0.753304660320282,
+      "eval_runtime": 1.9648,
+      "eval_samples_per_second": 58.022,
+      "eval_steps_per_second": 3.054,
+      "step": 820
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 1.6149755716323853,
+      "learning_rate": 1.7212024473438145e-05,
+      "loss": 0.1956,
+      "step": 830
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "eval_loss": 0.7569817900657654,
+      "eval_runtime": 1.9386,
+      "eval_samples_per_second": 58.804,
+      "eval_steps_per_second": 3.095,
+      "step": 830
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": 0.9965218901634216,
+      "learning_rate": 1.7118374836693407e-05,
+      "loss": 0.1945,
+      "step": 840
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "eval_loss": 0.7557573914527893,
+      "eval_runtime": 1.9446,
+      "eval_samples_per_second": 58.623,
+      "eval_steps_per_second": 3.085,
+      "step": 840
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 1.1858470439910889,
+      "learning_rate": 1.7023442153554776e-05,
+      "loss": 0.1964,
+      "step": 850
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "eval_loss": 0.7555262446403503,
+      "eval_runtime": 1.9665,
+      "eval_samples_per_second": 57.971,
+      "eval_steps_per_second": 3.051,
+      "step": 850
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 1.079675316810608,
+      "learning_rate": 1.6927243535095995e-05,
+      "loss": 0.2012,
+      "step": 860
+    },
+    {
+      "epoch": 2.646153846153846,
+      "eval_loss": 0.7503151893615723,
+      "eval_runtime": 1.9514,
+      "eval_samples_per_second": 58.421,
+      "eval_steps_per_second": 3.075,
+      "step": 860
+    },
+    {
+      "epoch": 2.676923076923077,
+      "grad_norm": 1.3259488344192505,
+      "learning_rate": 1.6829796320568416e-05,
+      "loss": 0.2022,
+      "step": 870
+    },
+    {
+      "epoch": 2.676923076923077,
+      "eval_loss": 0.7605793476104736,
+      "eval_runtime": 2.0581,
+      "eval_samples_per_second": 55.39,
+      "eval_steps_per_second": 2.915,
+      "step": 870
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": 1.1906328201293945,
+      "learning_rate": 1.67311180742757e-05,
+      "loss": 0.1874,
+      "step": 880
+    },
+    {
+      "epoch": 2.707692307692308,
+      "eval_loss": 0.767244815826416,
+      "eval_runtime": 1.9453,
+      "eval_samples_per_second": 58.602,
+      "eval_steps_per_second": 3.084,
+      "step": 880
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 1.5168702602386475,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.1939,
+      "step": 890
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "eval_loss": 0.7721065282821655,
+      "eval_runtime": 1.9592,
+      "eval_samples_per_second": 58.186,
+      "eval_steps_per_second": 3.062,
+      "step": 890
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 1.5762079954147339,
+      "learning_rate": 1.653013984983585e-05,
+      "loss": 0.1887,
+      "step": 900
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": 0.7561252117156982,
+      "eval_runtime": 1.9488,
+      "eval_samples_per_second": 58.496,
+      "eval_steps_per_second": 3.079,
+      "step": 900
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.2828755378723145,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.2039,
+      "step": 910
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.7597094178199768,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.706,
+      "eval_steps_per_second": 3.09,
+      "step": 910
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 1.1010947227478027,
+      "learning_rate": 1.6324453755953772e-05,
+      "loss": 0.1845,
+      "step": 920
+    },
+    {
+      "epoch": 2.830769230769231,
+      "eval_loss": 0.7654496431350708,
+      "eval_runtime": 1.9494,
+      "eval_samples_per_second": 58.478,
+      "eval_steps_per_second": 3.078,
+      "step": 920
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "grad_norm": 1.676522970199585,
+      "learning_rate": 1.621989146838704e-05,
+      "loss": 0.2192,
+      "step": 930
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "eval_loss": 0.756608247756958,
+      "eval_runtime": 1.9502,
+      "eval_samples_per_second": 58.457,
+      "eval_steps_per_second": 3.077,
+      "step": 930
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": 1.453100562095642,
+      "learning_rate": 1.6114208080920125e-05,
+      "loss": 0.2055,
+      "step": 940
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "eval_loss": 0.7652134895324707,
+      "eval_runtime": 1.976,
+      "eval_samples_per_second": 57.692,
+      "eval_steps_per_second": 3.036,
+      "step": 940
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.3680988550186157,
+      "learning_rate": 1.600742264237979e-05,
+      "loss": 0.2038,
+      "step": 950
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_loss": 0.7622235417366028,
+      "eval_runtime": 1.9779,
+      "eval_samples_per_second": 57.638,
+      "eval_steps_per_second": 3.034,
+      "step": 950
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 1.6015321016311646,
+      "learning_rate": 1.5899554400231233e-05,
+      "loss": 0.2149,
+      "step": 960
+    },
+    {
+      "epoch": 2.953846153846154,
+      "eval_loss": 0.7541946172714233,
+      "eval_runtime": 1.9407,
+      "eval_samples_per_second": 58.74,
+      "eval_steps_per_second": 3.092,
+      "step": 960
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "grad_norm": 1.2561781406402588,
+      "learning_rate": 1.579062279710879e-05,
+      "loss": 0.1844,
+      "step": 970
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "eval_loss": 0.7695141434669495,
+      "eval_runtime": 1.9507,
+      "eval_samples_per_second": 58.442,
+      "eval_steps_per_second": 3.076,
+      "step": 970
+    },
+    {
+      "epoch": 3.0153846153846153,
+      "grad_norm": 0.7629246711730957,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.1376,
+      "step": 980
+    },
+    {
+      "epoch": 3.0153846153846153,
+      "eval_loss": 0.7860725522041321,
+      "eval_runtime": 1.9563,
+      "eval_samples_per_second": 58.273,
+      "eval_steps_per_second": 3.067,
+      "step": 980
+    },
+    {
+      "epoch": 3.046153846153846,
+      "grad_norm": 0.9552655816078186,
+      "learning_rate": 1.5569648233264395e-05,
+      "loss": 0.1065,
+      "step": 990
+    },
+    {
+      "epoch": 3.046153846153846,
+      "eval_loss": 0.8531390428543091,
+      "eval_runtime": 1.9499,
+      "eval_samples_per_second": 58.465,
+      "eval_steps_per_second": 3.077,
+      "step": 990
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 1.4238945245742798,
+      "learning_rate": 1.5457645101945046e-05,
+      "loss": 0.1083,
+      "step": 1000
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 0.8417089581489563,
+      "eval_runtime": 2.0647,
+      "eval_samples_per_second": 55.214,
+      "eval_steps_per_second": 2.906,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 50,
+  "total_flos": 8.729990710637363e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a275a1f941882da99f851a4d3084b949cf3401949c2995ebc356025dd22836
+size 5112

checkpoint-1050/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
+}

checkpoint-1050/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": true,
+  "vocab_size": 32016
+}

checkpoint-1050/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

checkpoint-1050/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab0b04a0acb933e53c55229b6ea95ac86142e188ff1331b6e8e1bd1f7f60a7a
+size 4840658560

checkpoint-1050/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf365ccb88bd87f17f24ecd81951c5887c357127ed0ff53cf1839e58165b1525
+size 4857206856

checkpoint-1050/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76624d727db07c8009aede54901ea43aed542cc797414d567a0f4e052c807c59
+size 4857206904

checkpoint-1050/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4463b53c40a0f02db2b80450d0bd19afe12228168681cf3ffac1fba847615b1
+size 4857206904

checkpoint-1050/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893c3f65ec386a9c0b09a0dcbec7dc85392068d4fcc877976e1e9bd999480647
+size 4857206904

checkpoint-1050/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995a11dac64a232de76b62105a91f500570c03469355ddc43025b1c31b791975
+size 2684734256

checkpoint-1050/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26954186752
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-1050/special_tokens_map.json

@@ -0,0 +1,82 @@
+{
+  "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": "<pad>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1050/tokenizer.model

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

checkpoint-1050/tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1050/trainer_state.json

@@ -0,0 +1,1604 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.230769230769231,
+  "eval_steps": 10,
+  "global_step": 1050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153846153846154,
+      "eval_loss": 1.845949411392212,
+      "eval_runtime": 1.9761,
+      "eval_samples_per_second": 57.69,
+      "eval_steps_per_second": 3.036,
+      "step": 2
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 29.46457290649414,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.944,
+      "step": 10
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "eval_loss": 1.7965577840805054,
+      "eval_runtime": 1.9506,
+      "eval_samples_per_second": 58.444,
+      "eval_steps_per_second": 3.076,
+      "step": 10
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 14.49207878112793,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.6999,
+      "step": 20
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "eval_loss": 1.5032916069030762,
+      "eval_runtime": 1.9599,
+      "eval_samples_per_second": 58.168,
+      "eval_steps_per_second": 3.061,
+      "step": 20
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 11.355466842651367,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.1499,
+      "step": 30
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "eval_loss": 0.8391174674034119,
+      "eval_runtime": 1.9437,
+      "eval_samples_per_second": 58.65,
+      "eval_steps_per_second": 3.087,
+      "step": 30
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 5.648468017578125,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.7194,
+      "step": 40
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "eval_loss": 0.6716201305389404,
+      "eval_runtime": 1.9517,
+      "eval_samples_per_second": 58.411,
+      "eval_steps_per_second": 3.074,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 5.752841949462891,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.6811,
+      "step": 50
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "eval_loss": 0.6289324164390564,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 58.401,
+      "eval_steps_per_second": 3.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 3.414722204208374,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.5924,
+      "step": 60
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "eval_loss": 0.6140013337135315,
+      "eval_runtime": 1.94,
+      "eval_samples_per_second": 58.762,
+      "eval_steps_per_second": 3.093,
+      "step": 60
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 5.556036949157715,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.6135,
+      "step": 70
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "eval_loss": 0.6054026484489441,
+      "eval_runtime": 1.9659,
+      "eval_samples_per_second": 57.988,
+      "eval_steps_per_second": 3.052,
+      "step": 70
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 4.436710834503174,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.5952,
+      "step": 80
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "eval_loss": 0.5986860990524292,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 58.677,
+      "eval_steps_per_second": 3.088,
+      "step": 80
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 3.496018409729004,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.5887,
+      "step": 90
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "eval_loss": 0.594973623752594,
+      "eval_runtime": 1.9468,
+      "eval_samples_per_second": 58.558,
+      "eval_steps_per_second": 3.082,
+      "step": 90
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.3540539741516113,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.5634,
+      "step": 100
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "eval_loss": 0.5954164266586304,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 58.521,
+      "eval_steps_per_second": 3.08,
+      "step": 100
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "grad_norm": 2.9880635738372803,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.5827,
+      "step": 110
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "eval_loss": 0.5955133438110352,
+      "eval_runtime": 1.9432,
+      "eval_samples_per_second": 58.667,
+      "eval_steps_per_second": 3.088,
+      "step": 110
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 1.9405996799468994,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.5726,
+      "step": 120
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "eval_loss": 0.5951128602027893,
+      "eval_runtime": 1.9715,
+      "eval_samples_per_second": 57.824,
+      "eval_steps_per_second": 3.043,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.9948021173477173,
+      "learning_rate": 1e-05,
+      "loss": 0.6488,
+      "step": 130
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.5964463949203491,
+      "eval_runtime": 2.1032,
+      "eval_samples_per_second": 54.203,
+      "eval_steps_per_second": 2.853,
+      "step": 130
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 1.95350980758667,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.6218,
+      "step": 140
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "eval_loss": 0.5996471047401428,
+      "eval_runtime": 1.9539,
+      "eval_samples_per_second": 58.345,
+      "eval_steps_per_second": 3.071,
+      "step": 140
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 3.840015411376953,
+      "learning_rate": 1.1538461538461538e-05,
+      "loss": 0.5585,
+      "step": 150
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "eval_loss": 0.6000372767448425,
+      "eval_runtime": 1.9457,
+      "eval_samples_per_second": 58.592,
+      "eval_steps_per_second": 3.084,
+      "step": 150
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 2.345364809036255,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.5314,
+      "step": 160
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "eval_loss": 0.6025042533874512,
+      "eval_runtime": 1.9398,
+      "eval_samples_per_second": 58.768,
+      "eval_steps_per_second": 3.093,
+      "step": 160
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "grad_norm": 3.162071704864502,
+      "learning_rate": 1.3076923076923078e-05,
+      "loss": 0.6901,
+      "step": 170
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "eval_loss": 0.598171055316925,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.705,
+      "eval_steps_per_second": 3.09,
+      "step": 170
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 3.9432108402252197,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.6604,
+      "step": 180
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "eval_loss": 0.5974885821342468,
+      "eval_runtime": 1.9664,
+      "eval_samples_per_second": 57.975,
+      "eval_steps_per_second": 3.051,
+      "step": 180
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "grad_norm": 1.904718279838562,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 0.5806,
+      "step": 190
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "eval_loss": 0.6012160778045654,
+      "eval_runtime": 2.082,
+      "eval_samples_per_second": 54.755,
+      "eval_steps_per_second": 2.882,
+      "step": 190
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 2.2823173999786377,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.588,
+      "step": 200
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "eval_loss": 0.6052933931350708,
+      "eval_runtime": 1.9613,
+      "eval_samples_per_second": 58.124,
+      "eval_steps_per_second": 3.059,
+      "step": 200
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 1.8020161390304565,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.5826,
+      "step": 210
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "eval_loss": 0.6047356724739075,
+      "eval_runtime": 1.9487,
+      "eval_samples_per_second": 58.5,
+      "eval_steps_per_second": 3.079,
+      "step": 210
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 1.8297995328903198,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 0.5442,
+      "step": 220
+    },
+    {
+      "epoch": 0.676923076923077,
+      "eval_loss": 0.6105689406394958,
+      "eval_runtime": 2.0567,
+      "eval_samples_per_second": 55.429,
+      "eval_steps_per_second": 2.917,
+      "step": 220
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "grad_norm": 1.8141131401062012,
+      "learning_rate": 1.7692307692307694e-05,
+      "loss": 0.602,
+      "step": 230
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "eval_loss": 0.6149886250495911,
+      "eval_runtime": 2.1951,
+      "eval_samples_per_second": 51.933,
+      "eval_steps_per_second": 2.733,
+      "step": 230
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 2.093683958053589,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.6103,
+      "step": 240
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "eval_loss": 0.621900200843811,
+      "eval_runtime": 1.9465,
+      "eval_samples_per_second": 58.567,
+      "eval_steps_per_second": 3.082,
+      "step": 240
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.840038776397705,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 0.5775,
+      "step": 250
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 0.6232128739356995,
+      "eval_runtime": 1.9883,
+      "eval_samples_per_second": 57.334,
+      "eval_steps_per_second": 3.018,
+      "step": 250
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.7329185009002686,
+      "learning_rate": 2e-05,
+      "loss": 0.6808,
+      "step": 260
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.6226441264152527,
+      "eval_runtime": 1.9469,
+      "eval_samples_per_second": 58.553,
+      "eval_steps_per_second": 3.082,
+      "step": 260
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 2.738678455352783,
+      "learning_rate": 1.999909877856721e-05,
+      "loss": 0.5833,
+      "step": 270
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "eval_loss": 0.6240194439888,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.706,
+      "eval_steps_per_second": 3.09,
+      "step": 270
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 2.0359909534454346,
+      "learning_rate": 1.9996395276708856e-05,
+      "loss": 0.691,
+      "step": 280
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "eval_loss": 0.6267117857933044,
+      "eval_runtime": 1.939,
+      "eval_samples_per_second": 58.794,
+      "eval_steps_per_second": 3.094,
+      "step": 280
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "grad_norm": 1.7706685066223145,
+      "learning_rate": 1.9991889981715696e-05,
+      "loss": 0.6404,
+      "step": 290
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "eval_loss": 0.6222097873687744,
+      "eval_runtime": 1.9533,
+      "eval_samples_per_second": 58.363,
+      "eval_steps_per_second": 3.072,
+      "step": 290
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 2.129652976989746,
+      "learning_rate": 1.9985583705641418e-05,
+      "loss": 0.7109,
+      "step": 300
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": 0.6229674816131592,
+      "eval_runtime": 1.9467,
+      "eval_samples_per_second": 58.561,
+      "eval_steps_per_second": 3.082,
+      "step": 300
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "grad_norm": 1.8439427614212036,
+      "learning_rate": 1.9977477585156252e-05,
+      "loss": 0.6623,
+      "step": 310
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "eval_loss": 0.6273208856582642,
+      "eval_runtime": 2.0985,
+      "eval_samples_per_second": 54.324,
+      "eval_steps_per_second": 2.859,
+      "step": 310
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 2.1446306705474854,
+      "learning_rate": 1.9967573081342103e-05,
+      "loss": 0.5583,
+      "step": 320
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "eval_loss": 0.6260280013084412,
+      "eval_runtime": 1.9521,
+      "eval_samples_per_second": 58.398,
+      "eval_steps_per_second": 3.074,
+      "step": 320
+    },
+    {
+      "epoch": 1.0153846153846153,
+      "grad_norm": 1.9259562492370605,
+      "learning_rate": 1.9955871979429188e-05,
+      "loss": 0.4857,
+      "step": 330
+    },
+    {
+      "epoch": 1.0153846153846153,
+      "eval_loss": 0.6497873067855835,
+      "eval_runtime": 1.9489,
+      "eval_samples_per_second": 58.496,
+      "eval_steps_per_second": 3.079,
+      "step": 330
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 1.8625404834747314,
+      "learning_rate": 1.9942376388474282e-05,
+      "loss": 0.4152,
+      "step": 340
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "eval_loss": 0.6430822014808655,
+      "eval_runtime": 1.9534,
+      "eval_samples_per_second": 58.358,
+      "eval_steps_per_second": 3.071,
+      "step": 340
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 1.1712415218353271,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 0.3459,
+      "step": 350
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "eval_loss": 0.671064019203186,
+      "eval_runtime": 1.9772,
+      "eval_samples_per_second": 57.658,
+      "eval_steps_per_second": 3.035,
+      "step": 350
+    },
+    {
+      "epoch": 1.1076923076923078,
+      "grad_norm": 1.0710129737854004,
+      "learning_rate": 1.9910011792459086e-05,
+      "loss": 0.4307,
+      "step": 360
+    },
+    {
+      "epoch": 1.1076923076923078,
+      "eval_loss": 0.6545295119285583,
+      "eval_runtime": 2.0822,
+      "eval_samples_per_second": 54.749,
+      "eval_steps_per_second": 2.882,
+      "step": 360
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 1.839811086654663,
+      "learning_rate": 1.989114862093232e-05,
+      "loss": 0.4084,
+      "step": 370
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "eval_loss": 0.6743721961975098,
+      "eval_runtime": 1.962,
+      "eval_samples_per_second": 58.105,
+      "eval_steps_per_second": 3.058,
+      "step": 370
+    },
+    {
+      "epoch": 1.1692307692307693,
+      "grad_norm": 2.2416107654571533,
+      "learning_rate": 1.9870502626379127e-05,
+      "loss": 0.4203,
+      "step": 380
+    },
+    {
+      "epoch": 1.1692307692307693,
+      "eval_loss": 0.6703702211380005,
+      "eval_runtime": 2.0871,
+      "eval_samples_per_second": 54.621,
+      "eval_steps_per_second": 2.875,
+      "step": 380
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8775320053100586,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.3056,
+      "step": 390
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.680027425289154,
+      "eval_runtime": 2.0739,
+      "eval_samples_per_second": 54.97,
+      "eval_steps_per_second": 2.893,
+      "step": 390
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 2.1544764041900635,
+      "learning_rate": 1.9823877374156647e-05,
+      "loss": 0.4332,
+      "step": 400
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "eval_loss": 0.6662920117378235,
+      "eval_runtime": 1.9498,
+      "eval_samples_per_second": 58.466,
+      "eval_steps_per_second": 3.077,
+      "step": 400
+    },
+    {
+      "epoch": 1.2615384615384615,
+      "grad_norm": 1.740652084350586,
+      "learning_rate": 1.979790652042268e-05,
+      "loss": 0.3707,
+      "step": 410
+    },
+    {
+      "epoch": 1.2615384615384615,
+      "eval_loss": 0.6721649765968323,
+      "eval_runtime": 1.9421,
+      "eval_samples_per_second": 58.699,
+      "eval_steps_per_second": 3.089,
+      "step": 410
+    },
+    {
+      "epoch": 1.2923076923076924,
+      "grad_norm": 1.8645464181900024,
+      "learning_rate": 1.977016965001817e-05,
+      "loss": 0.412,
+      "step": 420
+    },
+    {
+      "epoch": 1.2923076923076924,
+      "eval_loss": 0.6605477333068848,
+      "eval_runtime": 1.9455,
+      "eval_samples_per_second": 58.597,
+      "eval_steps_per_second": 3.084,
+      "step": 420
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 1.3930943012237549,
+      "learning_rate": 1.9740671762355548e-05,
+      "loss": 0.388,
+      "step": 430
+    },
+    {
+      "epoch": 1.323076923076923,
+      "eval_loss": 0.6649342775344849,
+      "eval_runtime": 1.9497,
+      "eval_samples_per_second": 58.471,
+      "eval_steps_per_second": 3.077,
+      "step": 430
+    },
+    {
+      "epoch": 1.353846153846154,
+      "grad_norm": 1.8291655778884888,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.4118,
+      "step": 440
+    },
+    {
+      "epoch": 1.353846153846154,
+      "eval_loss": 0.6680696606636047,
+      "eval_runtime": 2.0262,
+      "eval_samples_per_second": 56.262,
+      "eval_steps_per_second": 2.961,
+      "step": 440
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.1135263442993164,
+      "learning_rate": 1.9676414519013782e-05,
+      "loss": 0.3205,
+      "step": 450
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "eval_loss": 0.6739374995231628,
+      "eval_runtime": 1.9443,
+      "eval_samples_per_second": 58.633,
+      "eval_steps_per_second": 3.086,
+      "step": 450
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 2.233457326889038,
+      "learning_rate": 1.9641666745335626e-05,
+      "loss": 0.3591,
+      "step": 460
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "eval_loss": 0.6751876473426819,
+      "eval_runtime": 1.9447,
+      "eval_samples_per_second": 58.622,
+      "eval_steps_per_second": 3.085,
+      "step": 460
+    },
+    {
+      "epoch": 1.4461538461538461,
+      "grad_norm": 1.815677523612976,
+      "learning_rate": 1.9605181116313725e-05,
+      "loss": 0.4107,
+      "step": 470
+    },
+    {
+      "epoch": 1.4461538461538461,
+      "eval_loss": 0.6670271158218384,
+      "eval_runtime": 1.9448,
+      "eval_samples_per_second": 58.618,
+      "eval_steps_per_second": 3.085,
+      "step": 470
+    },
+    {
+      "epoch": 1.476923076923077,
+      "grad_norm": 2.0177175998687744,
+      "learning_rate": 1.9566964208274254e-05,
+      "loss": 0.3954,
+      "step": 480
+    },
+    {
+      "epoch": 1.476923076923077,
+      "eval_loss": 0.6706439256668091,
+      "eval_runtime": 2.1454,
+      "eval_samples_per_second": 53.137,
+      "eval_steps_per_second": 2.797,
+      "step": 480
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 2.2797820568084717,
+      "learning_rate": 1.9527022909596537e-05,
+      "loss": 0.349,
+      "step": 490
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "eval_loss": 0.6916453242301941,
+      "eval_runtime": 1.9454,
+      "eval_samples_per_second": 58.599,
+      "eval_steps_per_second": 3.084,
+      "step": 490
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.6123872995376587,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 0.3796,
+      "step": 500
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 0.6646614670753479,
+      "eval_runtime": 1.9525,
+      "eval_samples_per_second": 58.386,
+      "eval_steps_per_second": 3.073,
+      "step": 500
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "grad_norm": 2.039036989212036,
+      "learning_rate": 1.9441996246603848e-05,
+      "loss": 0.4163,
+      "step": 510
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "eval_loss": 0.6671331524848938,
+      "eval_runtime": 1.9375,
+      "eval_samples_per_second": 58.84,
+      "eval_steps_per_second": 3.097,
+      "step": 510
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.8493613004684448,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3768,
+      "step": 520
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.6984831094741821,
+      "eval_runtime": 1.9384,
+      "eval_samples_per_second": 58.812,
+      "eval_steps_per_second": 3.095,
+      "step": 520
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "grad_norm": 1.1424219608306885,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.3985,
+      "step": 530
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "eval_loss": 0.6629871726036072,
+      "eval_runtime": 1.9471,
+      "eval_samples_per_second": 58.549,
+      "eval_steps_per_second": 3.082,
+      "step": 530
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "grad_norm": 1.8115930557250977,
+      "learning_rate": 1.9301713332493386e-05,
+      "loss": 0.397,
+      "step": 540
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "eval_loss": 0.6737513542175293,
+      "eval_runtime": 1.9496,
+      "eval_samples_per_second": 58.473,
+      "eval_steps_per_second": 3.078,
+      "step": 540
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.7575629949569702,
+      "learning_rate": 1.925158765744924e-05,
+      "loss": 0.4624,
+      "step": 550
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "eval_loss": 0.660962700843811,
+      "eval_runtime": 1.953,
+      "eval_samples_per_second": 58.372,
+      "eval_steps_per_second": 3.072,
+      "step": 550
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "grad_norm": 1.7702680826187134,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 0.3705,
+      "step": 560
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "eval_loss": 0.663165807723999,
+      "eval_runtime": 1.9548,
+      "eval_samples_per_second": 58.319,
+      "eval_steps_per_second": 3.069,
+      "step": 560
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "grad_norm": 1.4927833080291748,
+      "learning_rate": 1.9146343005342546e-05,
+      "loss": 0.3708,
+      "step": 570
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "eval_loss": 0.673720121383667,
+      "eval_runtime": 1.9582,
+      "eval_samples_per_second": 58.216,
+      "eval_steps_per_second": 3.064,
+      "step": 570
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 1.6623133420944214,
+      "learning_rate": 1.909124299802724e-05,
+      "loss": 0.399,
+      "step": 580
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "eval_loss": 0.6685453653335571,
+      "eval_runtime": 1.9645,
+      "eval_samples_per_second": 58.029,
+      "eval_steps_per_second": 3.054,
+      "step": 580
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "grad_norm": 2.253755807876587,
+      "learning_rate": 1.9034504346103825e-05,
+      "loss": 0.3642,
+      "step": 590
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "eval_loss": 0.6629040241241455,
+      "eval_runtime": 1.9527,
+      "eval_samples_per_second": 58.382,
+      "eval_steps_per_second": 3.073,
+      "step": 590
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 1.8123295307159424,
+      "learning_rate": 1.8976137276390145e-05,
+      "loss": 0.4213,
+      "step": 600
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "eval_loss": 0.6636160016059875,
+      "eval_runtime": 2.1305,
+      "eval_samples_per_second": 53.508,
+      "eval_steps_per_second": 2.816,
+      "step": 600
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 1.6377712488174438,
+      "learning_rate": 1.891615230921703e-05,
+      "loss": 0.3154,
+      "step": 610
+    },
+    {
+      "epoch": 1.876923076923077,
+      "eval_loss": 0.6621889472007751,
+      "eval_runtime": 1.9727,
+      "eval_samples_per_second": 57.789,
+      "eval_steps_per_second": 3.042,
+      "step": 610
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "grad_norm": 2.1680402755737305,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.421,
+      "step": 620
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "eval_loss": 0.6584432721138,
+      "eval_runtime": 1.9532,
+      "eval_samples_per_second": 58.367,
+      "eval_steps_per_second": 3.072,
+      "step": 620
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "grad_norm": 1.771596074104309,
+      "learning_rate": 1.879137221995095e-05,
+      "loss": 0.3625,
+      "step": 630
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "eval_loss": 0.6574673652648926,
+      "eval_runtime": 1.9593,
+      "eval_samples_per_second": 58.185,
+      "eval_steps_per_second": 3.062,
+      "step": 630
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 1.6291016340255737,
+      "learning_rate": 1.8726599588756144e-05,
+      "loss": 0.3787,
+      "step": 640
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "eval_loss": 0.6593620181083679,
+      "eval_runtime": 2.1362,
+      "eval_samples_per_second": 53.367,
+      "eval_steps_per_second": 2.809,
+      "step": 640
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.721921682357788,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.3923,
+      "step": 650
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6485319137573242,
+      "eval_runtime": 1.967,
+      "eval_samples_per_second": 57.957,
+      "eval_steps_per_second": 3.05,
+      "step": 650
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "grad_norm": 1.6391288042068481,
+      "learning_rate": 1.859234752562217e-05,
+      "loss": 0.2137,
+      "step": 660
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "eval_loss": 0.7283760905265808,
+      "eval_runtime": 1.9428,
+      "eval_samples_per_second": 58.678,
+      "eval_steps_per_second": 3.088,
+      "step": 660
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "grad_norm": 1.9791120290756226,
+      "learning_rate": 1.8522892291850335e-05,
+      "loss": 0.2221,
+      "step": 670
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "eval_loss": 0.7443767189979553,
+      "eval_runtime": 1.9429,
+      "eval_samples_per_second": 58.676,
+      "eval_steps_per_second": 3.088,
+      "step": 670
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 2.0093741416931152,
+      "learning_rate": 1.845190085543795e-05,
+      "loss": 0.1777,
+      "step": 680
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "eval_loss": 0.7445951700210571,
+      "eval_runtime": 1.9592,
+      "eval_samples_per_second": 58.186,
+      "eval_steps_per_second": 3.062,
+      "step": 680
+    },
+    {
+      "epoch": 2.123076923076923,
+      "grad_norm": 1.8424338102340698,
+      "learning_rate": 1.8379386012185813e-05,
+      "loss": 0.1755,
+      "step": 690
+    },
+    {
+      "epoch": 2.123076923076923,
+      "eval_loss": 0.7517443299293518,
+      "eval_runtime": 2.0747,
+      "eval_samples_per_second": 54.947,
+      "eval_steps_per_second": 2.892,
+      "step": 690
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.4635226726531982,
+      "learning_rate": 1.8305360832480118e-05,
+      "loss": 0.1742,
+      "step": 700
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "eval_loss": 0.7649147510528564,
+      "eval_runtime": 1.9437,
+      "eval_samples_per_second": 58.65,
+      "eval_steps_per_second": 3.087,
+      "step": 700
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 1.9029723405838013,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.2037,
+      "step": 710
+    },
+    {
+      "epoch": 2.184615384615385,
+      "eval_loss": 0.7539044618606567,
+      "eval_runtime": 2.1243,
+      "eval_samples_per_second": 53.664,
+      "eval_steps_per_second": 2.824,
+      "step": 710
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "grad_norm": 1.3570928573608398,
+      "learning_rate": 1.8152833103995443e-05,
+      "loss": 0.1954,
+      "step": 720
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "eval_loss": 0.7460123300552368,
+      "eval_runtime": 2.1466,
+      "eval_samples_per_second": 53.108,
+      "eval_steps_per_second": 2.795,
+      "step": 720
+    },
+    {
+      "epoch": 2.246153846153846,
+      "grad_norm": 1.5055183172225952,
+      "learning_rate": 1.807435804746807e-05,
+      "loss": 0.2027,
+      "step": 730
+    },
+    {
+      "epoch": 2.246153846153846,
+      "eval_loss": 0.7585832476615906,
+      "eval_runtime": 2.1298,
+      "eval_samples_per_second": 53.525,
+      "eval_steps_per_second": 2.817,
+      "step": 730
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 1.0890541076660156,
+      "learning_rate": 1.7994427634035016e-05,
+      "loss": 0.1867,
+      "step": 740
+    },
+    {
+      "epoch": 2.276923076923077,
+      "eval_loss": 0.7535340785980225,
+      "eval_runtime": 1.9471,
+      "eval_samples_per_second": 58.549,
+      "eval_steps_per_second": 3.082,
+      "step": 740
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.11017644405365,
+      "learning_rate": 1.791305627069662e-05,
+      "loss": 0.1875,
+      "step": 750
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 0.7587242126464844,
+      "eval_runtime": 1.9462,
+      "eval_samples_per_second": 58.575,
+      "eval_steps_per_second": 3.083,
+      "step": 750
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": 1.7792816162109375,
+      "learning_rate": 1.7830258624176224e-05,
+      "loss": 0.1841,
+      "step": 760
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "eval_loss": 0.7774962782859802,
+      "eval_runtime": 1.942,
+      "eval_samples_per_second": 58.703,
+      "eval_steps_per_second": 3.09,
+      "step": 760
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 1.384929895401001,
+      "learning_rate": 1.7746049618276545e-05,
+      "loss": 0.1724,
+      "step": 770
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "eval_loss": 0.7517464756965637,
+      "eval_runtime": 2.0655,
+      "eval_samples_per_second": 55.191,
+      "eval_steps_per_second": 2.905,
+      "step": 770
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.3608155250549316,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.1831,
+      "step": 780
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.7726874351501465,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 58.4,
+      "eval_steps_per_second": 3.074,
+      "step": 780
+    },
+    {
+      "epoch": 2.430769230769231,
+      "grad_norm": 0.9307472109794617,
+      "learning_rate": 1.7573458492761802e-05,
+      "loss": 0.1897,
+      "step": 790
+    },
+    {
+      "epoch": 2.430769230769231,
+      "eval_loss": 0.7573862075805664,
+      "eval_runtime": 1.9435,
+      "eval_samples_per_second": 58.658,
+      "eval_steps_per_second": 3.087,
+      "step": 790
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.0741816759109497,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.1936,
+      "step": 800
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "eval_loss": 0.7550384402275085,
+      "eval_runtime": 1.9506,
+      "eval_samples_per_second": 58.443,
+      "eval_steps_per_second": 3.076,
+      "step": 800
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 1.3956509828567505,
+      "learning_rate": 1.7395407322802374e-05,
+      "loss": 0.1969,
+      "step": 810
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "eval_loss": 0.7733697295188904,
+      "eval_runtime": 1.9492,
+      "eval_samples_per_second": 58.484,
+      "eval_steps_per_second": 3.078,
+      "step": 810
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": 1.529106855392456,
+      "learning_rate": 1.7304374183977032e-05,
+      "loss": 0.2222,
+      "step": 820
+    },
+    {
+      "epoch": 2.523076923076923,
+      "eval_loss": 0.753304660320282,
+      "eval_runtime": 1.9648,
+      "eval_samples_per_second": 58.022,
+      "eval_steps_per_second": 3.054,
+      "step": 820
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 1.6149755716323853,
+      "learning_rate": 1.7212024473438145e-05,
+      "loss": 0.1956,
+      "step": 830
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "eval_loss": 0.7569817900657654,
+      "eval_runtime": 1.9386,
+      "eval_samples_per_second": 58.804,
+      "eval_steps_per_second": 3.095,
+      "step": 830
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": 0.9965218901634216,
+      "learning_rate": 1.7118374836693407e-05,
+      "loss": 0.1945,
+      "step": 840
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "eval_loss": 0.7557573914527893,
+      "eval_runtime": 1.9446,
+      "eval_samples_per_second": 58.623,
+      "eval_steps_per_second": 3.085,
+      "step": 840
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 1.1858470439910889,
+      "learning_rate": 1.7023442153554776e-05,
+      "loss": 0.1964,
+      "step": 850
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "eval_loss": 0.7555262446403503,
+      "eval_runtime": 1.9665,
+      "eval_samples_per_second": 57.971,
+      "eval_steps_per_second": 3.051,
+      "step": 850
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 1.079675316810608,
+      "learning_rate": 1.6927243535095995e-05,
+      "loss": 0.2012,
+      "step": 860
+    },
+    {
+      "epoch": 2.646153846153846,
+      "eval_loss": 0.7503151893615723,
+      "eval_runtime": 1.9514,
+      "eval_samples_per_second": 58.421,
+      "eval_steps_per_second": 3.075,
+      "step": 860
+    },
+    {
+      "epoch": 2.676923076923077,
+      "grad_norm": 1.3259488344192505,
+      "learning_rate": 1.6829796320568416e-05,
+      "loss": 0.2022,
+      "step": 870
+    },
+    {
+      "epoch": 2.676923076923077,
+      "eval_loss": 0.7605793476104736,
+      "eval_runtime": 2.0581,
+      "eval_samples_per_second": 55.39,
+      "eval_steps_per_second": 2.915,
+      "step": 870
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": 1.1906328201293945,
+      "learning_rate": 1.67311180742757e-05,
+      "loss": 0.1874,
+      "step": 880
+    },
+    {
+      "epoch": 2.707692307692308,
+      "eval_loss": 0.767244815826416,
+      "eval_runtime": 1.9453,
+      "eval_samples_per_second": 58.602,
+      "eval_steps_per_second": 3.084,
+      "step": 880
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 1.5168702602386475,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.1939,
+      "step": 890
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "eval_loss": 0.7721065282821655,
+      "eval_runtime": 1.9592,
+      "eval_samples_per_second": 58.186,
+      "eval_steps_per_second": 3.062,
+      "step": 890
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 1.5762079954147339,
+      "learning_rate": 1.653013984983585e-05,
+      "loss": 0.1887,
+      "step": 900
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_loss": 0.7561252117156982,
+      "eval_runtime": 1.9488,
+      "eval_samples_per_second": 58.496,
+      "eval_steps_per_second": 3.079,
+      "step": 900
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.2828755378723145,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.2039,
+      "step": 910
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.7597094178199768,
+      "eval_runtime": 1.9419,
+      "eval_samples_per_second": 58.706,
+      "eval_steps_per_second": 3.09,
+      "step": 910
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 1.1010947227478027,
+      "learning_rate": 1.6324453755953772e-05,
+      "loss": 0.1845,
+      "step": 920
+    },
+    {
+      "epoch": 2.830769230769231,
+      "eval_loss": 0.7654496431350708,
+      "eval_runtime": 1.9494,
+      "eval_samples_per_second": 58.478,
+      "eval_steps_per_second": 3.078,
+      "step": 920
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "grad_norm": 1.676522970199585,
+      "learning_rate": 1.621989146838704e-05,
+      "loss": 0.2192,
+      "step": 930
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "eval_loss": 0.756608247756958,
+      "eval_runtime": 1.9502,
+      "eval_samples_per_second": 58.457,
+      "eval_steps_per_second": 3.077,
+      "step": 930
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": 1.453100562095642,
+      "learning_rate": 1.6114208080920125e-05,
+      "loss": 0.2055,
+      "step": 940
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "eval_loss": 0.7652134895324707,
+      "eval_runtime": 1.976,
+      "eval_samples_per_second": 57.692,
+      "eval_steps_per_second": 3.036,
+      "step": 940
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.3680988550186157,
+      "learning_rate": 1.600742264237979e-05,
+      "loss": 0.2038,
+      "step": 950
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_loss": 0.7622235417366028,
+      "eval_runtime": 1.9779,
+      "eval_samples_per_second": 57.638,
+      "eval_steps_per_second": 3.034,
+      "step": 950
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 1.6015321016311646,
+      "learning_rate": 1.5899554400231233e-05,
+      "loss": 0.2149,
+      "step": 960
+    },
+    {
+      "epoch": 2.953846153846154,
+      "eval_loss": 0.7541946172714233,
+      "eval_runtime": 1.9407,
+      "eval_samples_per_second": 58.74,
+      "eval_steps_per_second": 3.092,
+      "step": 960
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "grad_norm": 1.2561781406402588,
+      "learning_rate": 1.579062279710879e-05,
+      "loss": 0.1844,
+      "step": 970
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "eval_loss": 0.7695141434669495,
+      "eval_runtime": 1.9507,
+      "eval_samples_per_second": 58.442,
+      "eval_steps_per_second": 3.076,
+      "step": 970
+    },
+    {
+      "epoch": 3.0153846153846153,
+      "grad_norm": 0.7629246711730957,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.1376,
+      "step": 980
+    },
+    {
+      "epoch": 3.0153846153846153,
+      "eval_loss": 0.7860725522041321,
+      "eval_runtime": 1.9563,
+      "eval_samples_per_second": 58.273,
+      "eval_steps_per_second": 3.067,
+      "step": 980
+    },
+    {
+      "epoch": 3.046153846153846,
+      "grad_norm": 0.9552655816078186,
+      "learning_rate": 1.5569648233264395e-05,
+      "loss": 0.1065,
+      "step": 990
+    },
+    {
+      "epoch": 3.046153846153846,
+      "eval_loss": 0.8531390428543091,
+      "eval_runtime": 1.9499,
+      "eval_samples_per_second": 58.465,
+      "eval_steps_per_second": 3.077,
+      "step": 990
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 1.4238945245742798,
+      "learning_rate": 1.5457645101945046e-05,
+      "loss": 0.1083,
+      "step": 1000
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 0.8417089581489563,
+      "eval_runtime": 2.0647,
+      "eval_samples_per_second": 55.214,
+      "eval_steps_per_second": 2.906,
+      "step": 1000
+    },
+    {
+      "epoch": 3.1076923076923078,
+      "grad_norm": 1.0638066530227661,
+      "learning_rate": 1.5344658261278013e-05,
+      "loss": 0.1054,
+      "step": 1010
+    },
+    {
+      "epoch": 3.1076923076923078,
+      "eval_loss": 0.8362419009208679,
+      "eval_runtime": 1.9429,
+      "eval_samples_per_second": 58.675,
+      "eval_steps_per_second": 3.088,
+      "step": 1010
+    },
+    {
+      "epoch": 3.1384615384615384,
+      "grad_norm": 1.2013343572616577,
+      "learning_rate": 1.5230708076495777e-05,
+      "loss": 0.1104,
+      "step": 1020
+    },
+    {
+      "epoch": 3.1384615384615384,
+      "eval_loss": 0.821545422077179,
+      "eval_runtime": 2.0667,
+      "eval_samples_per_second": 55.162,
+      "eval_steps_per_second": 2.903,
+      "step": 1020
+    },
+    {
+      "epoch": 3.169230769230769,
+      "grad_norm": 1.0717769861221313,
+      "learning_rate": 1.5115815086468103e-05,
+      "loss": 0.1094,
+      "step": 1030
+    },
+    {
+      "epoch": 3.169230769230769,
+      "eval_loss": 0.819724977016449,
+      "eval_runtime": 1.9507,
+      "eval_samples_per_second": 58.442,
+      "eval_steps_per_second": 3.076,
+      "step": 1030
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.1035127639770508,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1044,
+      "step": 1040
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 0.8392235636711121,
+      "eval_runtime": 2.0622,
+      "eval_samples_per_second": 55.281,
+      "eval_steps_per_second": 2.91,
+      "step": 1040
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.8959378004074097,
+      "learning_rate": 1.4883283692099114e-05,
+      "loss": 0.1118,
+      "step": 1050
+    },
+    {
+      "epoch": 3.230769230769231,
+      "eval_loss": 0.8458349704742432,
+      "eval_runtime": 1.945,
+      "eval_samples_per_second": 58.612,
+      "eval_steps_per_second": 3.085,
+      "step": 1050
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 50,
+  "total_flos": 9.150193010212864e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1050/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a275a1f941882da99f851a4d3084b949cf3401949c2995ebc356025dd22836
+size 5112

checkpoint-1100/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
+}

checkpoint-1100/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": true,
+  "vocab_size": 32016
+}