Upload folder using huggingface_hub

ft_7b_NLSY79_numeric_ckpt_bo5/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "togethercomputer/llama-2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

ft_7b_NLSY79_numeric_ckpt_bo5/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 32000,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

ft_7b_NLSY79_numeric_ckpt_bo5/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcda92603fb8298e86c94f972bcac14b1cfc23b1c8f1dd9667af1728e2a2e5c
+size 4840396416

ft_7b_NLSY79_numeric_ckpt_bo5/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e7ffc8ed479880912677fac8aa7ab8b324a178ec0bc43076618698945f283c
+size 4857206856

ft_7b_NLSY79_numeric_ckpt_bo5/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a8efcde07c2b4d8e211a5e9166ffdeb2810d87fd367ab1fa78bc4ac01df610
+size 4857206904

ft_7b_NLSY79_numeric_ckpt_bo5/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5940bda8d8b6820ae48b63573141a9acfd391fb6f5a52215dece216d7e5ee4
+size 4857206904

ft_7b_NLSY79_numeric_ckpt_bo5/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0cee2bbc1a171d2474cad27cbdc02c85b5c7a4dc812d7b9c45cffc2bd02b5b
+size 4857206904

ft_7b_NLSY79_numeric_ckpt_bo5/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a113f479ff9aa57a6eb074c0c3e62b20dbb4f3cd2f43e035f4b56efc5a52996d
+size 2684472112

ft_7b_NLSY79_numeric_ckpt_bo5/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "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"
+  }
+}

ft_7b_NLSY79_numeric_ckpt_bo5/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ft_7b_NLSY79_numeric_ckpt_bo5/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' or message['role'] == 'tool' %}{{ bos_token + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

ft_7b_NLSY79_numeric_ckpt_bo5/trainer_state.json

@@ -0,0 +1,1053 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 28,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 12.081677436828613,
+      "learning_rate": 9.92857142857143e-06,
+      "loss": 1.0525,
+      "step": 1
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 5.285427093505859,
+      "learning_rate": 9.857142857142859e-06,
+      "loss": 0.7508,
+      "step": 2
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 4.433465003967285,
+      "learning_rate": 9.785714285714286e-06,
+      "loss": 0.4643,
+      "step": 3
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 6.333235740661621,
+      "learning_rate": 9.714285714285715e-06,
+      "loss": 0.3666,
+      "step": 4
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 2.5423436164855957,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.2368,
+      "step": 5
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 1.518909215927124,
+      "learning_rate": 9.571428571428573e-06,
+      "loss": 0.2168,
+      "step": 6
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.7196946144104004,
+      "learning_rate": 9.5e-06,
+      "loss": 0.2146,
+      "step": 7
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.4132509231567383,
+      "learning_rate": 9.42857142857143e-06,
+      "loss": 0.2065,
+      "step": 8
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 1.5003870725631714,
+      "learning_rate": 9.357142857142859e-06,
+      "loss": 0.1949,
+      "step": 9
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.591156542301178,
+      "learning_rate": 9.285714285714288e-06,
+      "loss": 0.1911,
+      "step": 10
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.4523528218269348,
+      "learning_rate": 9.214285714285715e-06,
+      "loss": 0.1843,
+      "step": 11
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.37661436200141907,
+      "learning_rate": 9.142857142857144e-06,
+      "loss": 0.1884,
+      "step": 12
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.4541841447353363,
+      "learning_rate": 9.071428571428573e-06,
+      "loss": 0.1762,
+      "step": 13
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4595728814601898,
+      "learning_rate": 9e-06,
+      "loss": 0.175,
+      "step": 14
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.4273124635219574,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.1754,
+      "step": 15
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.3979589343070984,
+      "learning_rate": 8.857142857142858e-06,
+      "loss": 0.1714,
+      "step": 16
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.38886794447898865,
+      "learning_rate": 8.785714285714286e-06,
+      "loss": 0.1698,
+      "step": 17
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.2782571315765381,
+      "learning_rate": 8.714285714285715e-06,
+      "loss": 0.1667,
+      "step": 18
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.40736621618270874,
+      "learning_rate": 8.642857142857144e-06,
+      "loss": 0.1571,
+      "step": 19
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.3938260078430176,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.1597,
+      "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.24732190370559692,
+      "learning_rate": 8.5e-06,
+      "loss": 0.164,
+      "step": 21
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.2385326325893402,
+      "learning_rate": 8.428571428571429e-06,
+      "loss": 0.1644,
+      "step": 22
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.2823322117328644,
+      "learning_rate": 8.357142857142858e-06,
+      "loss": 0.1626,
+      "step": 23
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.21747717261314392,
+      "learning_rate": 8.285714285714287e-06,
+      "loss": 0.1615,
+      "step": 24
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.21219764649868011,
+      "learning_rate": 8.214285714285714e-06,
+      "loss": 0.1572,
+      "step": 25
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.21892203390598297,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 0.1645,
+      "step": 26
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.2094288170337677,
+      "learning_rate": 8.071428571428572e-06,
+      "loss": 0.1541,
+      "step": 27
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.18000562489032745,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1538,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1590520143508911,
+      "eval_runtime": 2.1493,
+      "eval_samples_per_second": 58.625,
+      "eval_steps_per_second": 1.861,
+      "step": 28
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 0.18174391984939575,
+      "learning_rate": 7.928571428571429e-06,
+      "loss": 0.1597,
+      "step": 29
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.22220967710018158,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 0.1534,
+      "step": 30
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 0.17073528468608856,
+      "learning_rate": 7.785714285714287e-06,
+      "loss": 0.1557,
+      "step": 31
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.15626376867294312,
+      "learning_rate": 7.714285714285716e-06,
+      "loss": 0.1557,
+      "step": 32
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.23702695965766907,
+      "learning_rate": 7.642857142857143e-06,
+      "loss": 0.1609,
+      "step": 33
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.21649490296840668,
+      "learning_rate": 7.571428571428572e-06,
+      "loss": 0.1604,
+      "step": 34
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.1806497573852539,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.1502,
+      "step": 35
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.20161722600460052,
+      "learning_rate": 7.428571428571429e-06,
+      "loss": 0.1658,
+      "step": 36
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.16629658639431,
+      "learning_rate": 7.357142857142858e-06,
+      "loss": 0.1523,
+      "step": 37
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.2315870076417923,
+      "learning_rate": 7.285714285714286e-06,
+      "loss": 0.1589,
+      "step": 38
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.2570408582687378,
+      "learning_rate": 7.2142857142857145e-06,
+      "loss": 0.1552,
+      "step": 39
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.30357950925827026,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.1574,
+      "step": 40
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 0.35007497668266296,
+      "learning_rate": 7.0714285714285726e-06,
+      "loss": 0.1551,
+      "step": 41
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.2148563712835312,
+      "learning_rate": 7e-06,
+      "loss": 0.1517,
+      "step": 42
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 0.2838610112667084,
+      "learning_rate": 6.928571428571429e-06,
+      "loss": 0.1548,
+      "step": 43
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.2081470936536789,
+      "learning_rate": 6.857142857142858e-06,
+      "loss": 0.1518,
+      "step": 44
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.1889055073261261,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 0.1551,
+      "step": 45
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.2086947113275528,
+      "learning_rate": 6.714285714285714e-06,
+      "loss": 0.1544,
+      "step": 46
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 0.22598181664943695,
+      "learning_rate": 6.642857142857143e-06,
+      "loss": 0.1569,
+      "step": 47
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.2200927883386612,
+      "learning_rate": 6.571428571428572e-06,
+      "loss": 0.1542,
+      "step": 48
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.19812268018722534,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.1466,
+      "step": 49
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.20251977443695068,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 0.1503,
+      "step": 50
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.180288627743721,
+      "learning_rate": 6.357142857142858e-06,
+      "loss": 0.154,
+      "step": 51
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.1877080202102661,
+      "learning_rate": 6.285714285714286e-06,
+      "loss": 0.147,
+      "step": 52
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.16711044311523438,
+      "learning_rate": 6.214285714285715e-06,
+      "loss": 0.1535,
+      "step": 53
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.24658982455730438,
+      "learning_rate": 6.142857142857144e-06,
+      "loss": 0.1525,
+      "step": 54
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.19483476877212524,
+      "learning_rate": 6.071428571428571e-06,
+      "loss": 0.1506,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20001035928726196,
+      "learning_rate": 6e-06,
+      "loss": 0.1499,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.15051335096359253,
+      "eval_runtime": 2.1673,
+      "eval_samples_per_second": 58.137,
+      "eval_steps_per_second": 1.846,
+      "step": 56
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 0.2521534860134125,
+      "learning_rate": 5.928571428571429e-06,
+      "loss": 0.1477,
+      "step": 57
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.11569789797067642,
+      "learning_rate": 5.857142857142858e-06,
+      "loss": 0.1555,
+      "step": 58
+    },
+    {
+      "epoch": 2.107142857142857,
+      "grad_norm": 0.20440654456615448,
+      "learning_rate": 5.785714285714286e-06,
+      "loss": 0.1518,
+      "step": 59
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.22283302247524261,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.1487,
+      "step": 60
+    },
+    {
+      "epoch": 2.1785714285714284,
+      "grad_norm": 0.1489076167345047,
+      "learning_rate": 5.6428571428571435e-06,
+      "loss": 0.1473,
+      "step": 61
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.256145179271698,
+      "learning_rate": 5.571428571428572e-06,
+      "loss": 0.1494,
+      "step": 62
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.23553088307380676,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.1599,
+      "step": 63
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.3005368411540985,
+      "learning_rate": 5.428571428571429e-06,
+      "loss": 0.1505,
+      "step": 64
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 0.2602750062942505,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.1498,
+      "step": 65
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.19512447714805603,
+      "learning_rate": 5.285714285714286e-06,
+      "loss": 0.154,
+      "step": 66
+    },
+    {
+      "epoch": 2.392857142857143,
+      "grad_norm": 0.1901603788137436,
+      "learning_rate": 5.214285714285715e-06,
+      "loss": 0.144,
+      "step": 67
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.30498695373535156,
+      "learning_rate": 5.142857142857142e-06,
+      "loss": 0.1506,
+      "step": 68
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 0.2257249355316162,
+      "learning_rate": 5.071428571428571e-06,
+      "loss": 0.1494,
+      "step": 69
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.2071664184331894,
+      "learning_rate": 5e-06,
+      "loss": 0.1472,
+      "step": 70
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "grad_norm": 0.20181076228618622,
+      "learning_rate": 4.928571428571429e-06,
+      "loss": 0.1469,
+      "step": 71
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.2276153564453125,
+      "learning_rate": 4.857142857142858e-06,
+      "loss": 0.1385,
+      "step": 72
+    },
+    {
+      "epoch": 2.607142857142857,
+      "grad_norm": 0.20884571969509125,
+      "learning_rate": 4.785714285714287e-06,
+      "loss": 0.1467,
+      "step": 73
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.21689516305923462,
+      "learning_rate": 4.714285714285715e-06,
+      "loss": 0.1481,
+      "step": 74
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.17452067136764526,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.1475,
+      "step": 75
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.16819435358047485,
+      "learning_rate": 4.571428571428572e-06,
+      "loss": 0.1506,
+      "step": 76
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2525673806667328,
+      "learning_rate": 4.5e-06,
+      "loss": 0.1467,
+      "step": 77
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.14343217015266418,
+      "learning_rate": 4.428571428571429e-06,
+      "loss": 0.1425,
+      "step": 78
+    },
+    {
+      "epoch": 2.821428571428571,
+      "grad_norm": 0.16456633806228638,
+      "learning_rate": 4.357142857142857e-06,
+      "loss": 0.143,
+      "step": 79
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.18822863698005676,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.1487,
+      "step": 80
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 0.2158735692501068,
+      "learning_rate": 4.2142857142857145e-06,
+      "loss": 0.149,
+      "step": 81
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.1611018180847168,
+      "learning_rate": 4.1428571428571435e-06,
+      "loss": 0.147,
+      "step": 82
+    },
+    {
+      "epoch": 2.9642857142857144,
+      "grad_norm": 0.16799627244472504,
+      "learning_rate": 4.071428571428572e-06,
+      "loss": 0.1492,
+      "step": 83
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.13422495126724243,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1474,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.14775319397449493,
+      "eval_runtime": 2.2656,
+      "eval_samples_per_second": 55.613,
+      "eval_steps_per_second": 1.766,
+      "step": 84
+    },
+    {
+      "epoch": 3.0357142857142856,
+      "grad_norm": 0.20705361664295197,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.1517,
+      "step": 85
+    },
+    {
+      "epoch": 3.0714285714285716,
+      "grad_norm": 0.18867868185043335,
+      "learning_rate": 3.857142857142858e-06,
+      "loss": 0.1456,
+      "step": 86
+    },
+    {
+      "epoch": 3.107142857142857,
+      "grad_norm": 0.14404603838920593,
+      "learning_rate": 3.785714285714286e-06,
+      "loss": 0.1447,
+      "step": 87
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.19374044239521027,
+      "learning_rate": 3.7142857142857146e-06,
+      "loss": 0.1482,
+      "step": 88
+    },
+    {
+      "epoch": 3.1785714285714284,
+      "grad_norm": 0.18256932497024536,
+      "learning_rate": 3.642857142857143e-06,
+      "loss": 0.1511,
+      "step": 89
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.20517702400684357,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.1425,
+      "step": 90
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.15663719177246094,
+      "learning_rate": 3.5e-06,
+      "loss": 0.1382,
+      "step": 91
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.16562233865261078,
+      "learning_rate": 3.428571428571429e-06,
+      "loss": 0.1434,
+      "step": 92
+    },
+    {
+      "epoch": 3.3214285714285716,
+      "grad_norm": 0.18002949655056,
+      "learning_rate": 3.357142857142857e-06,
+      "loss": 0.1415,
+      "step": 93
+    },
+    {
+      "epoch": 3.357142857142857,
+      "grad_norm": 0.1938929408788681,
+      "learning_rate": 3.285714285714286e-06,
+      "loss": 0.1442,
+      "step": 94
+    },
+    {
+      "epoch": 3.392857142857143,
+      "grad_norm": 0.18171778321266174,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.1483,
+      "step": 95
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.15573526918888092,
+      "learning_rate": 3.142857142857143e-06,
+      "loss": 0.1469,
+      "step": 96
+    },
+    {
+      "epoch": 3.4642857142857144,
+      "grad_norm": 0.17476877570152283,
+      "learning_rate": 3.071428571428572e-06,
+      "loss": 0.1508,
+      "step": 97
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.22000928223133087,
+      "learning_rate": 3e-06,
+      "loss": 0.1489,
+      "step": 98
+    },
+    {
+      "epoch": 3.5357142857142856,
+      "grad_norm": 0.15354207158088684,
+      "learning_rate": 2.928571428571429e-06,
+      "loss": 0.1487,
+      "step": 99
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.18868641555309296,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.1427,
+      "step": 100
+    },
+    {
+      "epoch": 3.607142857142857,
+      "grad_norm": 0.1645778864622116,
+      "learning_rate": 2.785714285714286e-06,
+      "loss": 0.1499,
+      "step": 101
+    },
+    {
+      "epoch": 3.642857142857143,
+      "grad_norm": 0.1766495257616043,
+      "learning_rate": 2.7142857142857144e-06,
+      "loss": 0.1433,
+      "step": 102
+    },
+    {
+      "epoch": 3.678571428571429,
+      "grad_norm": 0.2021266520023346,
+      "learning_rate": 2.642857142857143e-06,
+      "loss": 0.1421,
+      "step": 103
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.15105552971363068,
+      "learning_rate": 2.571428571428571e-06,
+      "loss": 0.1417,
+      "step": 104
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.12559005618095398,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1456,
+      "step": 105
+    },
+    {
+      "epoch": 3.7857142857142856,
+      "grad_norm": 0.14722345769405365,
+      "learning_rate": 2.428571428571429e-06,
+      "loss": 0.146,
+      "step": 106
+    },
+    {
+      "epoch": 3.821428571428571,
+      "grad_norm": 0.15455345809459686,
+      "learning_rate": 2.3571428571428574e-06,
+      "loss": 0.1481,
+      "step": 107
+    },
+    {
+      "epoch": 3.857142857142857,
+      "grad_norm": 0.139808788895607,
+      "learning_rate": 2.285714285714286e-06,
+      "loss": 0.1428,
+      "step": 108
+    },
+    {
+      "epoch": 3.892857142857143,
+      "grad_norm": 0.1421094685792923,
+      "learning_rate": 2.2142857142857146e-06,
+      "loss": 0.1469,
+      "step": 109
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 0.15167543292045593,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.1395,
+      "step": 110
+    },
+    {
+      "epoch": 3.9642857142857144,
+      "grad_norm": 0.14574706554412842,
+      "learning_rate": 2.0714285714285717e-06,
+      "loss": 0.1412,
+      "step": 111
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12879705429077148,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1488,
+      "step": 112
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.14662690460681915,
+      "eval_runtime": 2.2658,
+      "eval_samples_per_second": 55.609,
+      "eval_steps_per_second": 1.765,
+      "step": 112
+    },
+    {
+      "epoch": 4.035714285714286,
+      "grad_norm": 0.14704079926013947,
+      "learning_rate": 1.928571428571429e-06,
+      "loss": 0.1421,
+      "step": 113
+    },
+    {
+      "epoch": 4.071428571428571,
+      "grad_norm": 0.16781854629516602,
+      "learning_rate": 1.8571428571428573e-06,
+      "loss": 0.1423,
+      "step": 114
+    },
+    {
+      "epoch": 4.107142857142857,
+      "grad_norm": 0.13000237941741943,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.1454,
+      "step": 115
+    },
+    {
+      "epoch": 4.142857142857143,
+      "grad_norm": 0.1692391037940979,
+      "learning_rate": 1.7142857142857145e-06,
+      "loss": 0.1438,
+      "step": 116
+    },
+    {
+      "epoch": 4.178571428571429,
+      "grad_norm": 0.13547258079051971,
+      "learning_rate": 1.642857142857143e-06,
+      "loss": 0.1467,
+      "step": 117
+    },
+    {
+      "epoch": 4.214285714285714,
+      "grad_norm": 0.15148146450519562,
+      "learning_rate": 1.5714285714285714e-06,
+      "loss": 0.1358,
+      "step": 118
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.1352066695690155,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1412,
+      "step": 119
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.17222042381763458,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.1461,
+      "step": 120
+    },
+    {
+      "epoch": 4.321428571428571,
+      "grad_norm": 0.14871928095817566,
+      "learning_rate": 1.3571428571428572e-06,
+      "loss": 0.1432,
+      "step": 121
+    },
+    {
+      "epoch": 4.357142857142857,
+      "grad_norm": 0.15067841112613678,
+      "learning_rate": 1.2857142857142856e-06,
+      "loss": 0.1415,
+      "step": 122
+    },
+    {
+      "epoch": 4.392857142857143,
+      "grad_norm": 0.14608663320541382,
+      "learning_rate": 1.2142857142857144e-06,
+      "loss": 0.142,
+      "step": 123
+    },
+    {
+      "epoch": 4.428571428571429,
+      "grad_norm": 0.15205149352550507,
+      "learning_rate": 1.142857142857143e-06,
+      "loss": 0.1476,
+      "step": 124
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 0.16045041382312775,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.1436,
+      "step": 125
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.1634548455476761,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1417,
+      "step": 126
+    },
+    {
+      "epoch": 4.535714285714286,
+      "grad_norm": 0.15137611329555511,
+      "learning_rate": 9.285714285714287e-07,
+      "loss": 0.1436,
+      "step": 127
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.15078158676624298,
+      "learning_rate": 8.571428571428572e-07,
+      "loss": 0.1413,
+      "step": 128
+    },
+    {
+      "epoch": 4.607142857142857,
+      "grad_norm": 0.1497843712568283,
+      "learning_rate": 7.857142857142857e-07,
+      "loss": 0.1424,
+      "step": 129
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.1408492922782898,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.1473,
+      "step": 130
+    },
+    {
+      "epoch": 4.678571428571429,
+      "grad_norm": 0.15160909295082092,
+      "learning_rate": 6.428571428571428e-07,
+      "loss": 0.1401,
+      "step": 131
+    },
+    {
+      "epoch": 4.714285714285714,
+      "grad_norm": 0.142478346824646,
+      "learning_rate": 5.714285714285715e-07,
+      "loss": 0.144,
+      "step": 132
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.1262168288230896,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.1422,
+      "step": 133
+    },
+    {
+      "epoch": 4.785714285714286,
+      "grad_norm": 0.14598068594932556,
+      "learning_rate": 4.285714285714286e-07,
+      "loss": 0.1455,
+      "step": 134
+    },
+    {
+      "epoch": 4.821428571428571,
+      "grad_norm": 0.13455575704574585,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.1458,
+      "step": 135
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 0.15703856945037842,
+      "learning_rate": 2.8571428571428575e-07,
+      "loss": 0.1472,
+      "step": 136
+    },
+    {
+      "epoch": 4.892857142857143,
+      "grad_norm": 0.1457439512014389,
+      "learning_rate": 2.142857142857143e-07,
+      "loss": 0.1419,
+      "step": 137
+    },
+    {
+      "epoch": 4.928571428571429,
+      "grad_norm": 0.1295253485441208,
+      "learning_rate": 1.4285714285714287e-07,
+      "loss": 0.133,
+      "step": 138
+    },
+    {
+      "epoch": 4.964285714285714,
+      "grad_norm": 0.13447636365890503,
+      "learning_rate": 7.142857142857144e-08,
+      "loss": 0.1447,
+      "step": 139
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.13733166456222534,
+      "learning_rate": 0.0,
+      "loss": 0.141,
+      "step": 140
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14620642364025116,
+      "eval_runtime": 2.257,
+      "eval_samples_per_second": 55.826,
+      "eval_steps_per_second": 1.772,
+      "step": 140
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 28,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.058737567091917e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}