Upload folder using huggingface_hub

ft_13b_NLSY79_with_birth_year_ckpt_bo5/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "togethercomputer/llama-2-13b",
+  "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": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 2,
+  "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_13b_NLSY79_with_birth_year_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": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06bb0ed058b63b053551eeb86a1c2a363e5dc0dd10450b9117c81b4cd84d274
+size 4881247856

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d179ec6b80cf5044cb3c8246aafcafbcf2bb430a35e40e8c9faba634f50a1fa0
+size 4970418112

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77041539382bfc097ef84e913cc4747993e393bde11ae53d11faa8123b923ca6
+size 4970418120

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2428ffa4be931a969d67ecfaced4f4d37176990eb843cf1ea8965d8a48d82a
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30719b4812fdb3ac2e56f4b259f66ebf0ed9c5cfa4720349ffe30a2940b17e22
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653faeed4fad622f36647758175968589299516ebafd1517628f5e239b9ca855
+size 4792119040

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e627aef98650c1cdcd18a30b4e6cde32226dfe06d76790513416899c7a0b760a
+size 4792160232

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8789fe6e429247af6bdfba6ee57e5420ed5e545119c75db5f13ba23b6b2fde49
+size 4792160224

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d08ca92e87729f5afaf5dc3a8dd1ebdf640c81c7abfb38d1ff33cef041dbcf5
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e9c1a759755d5b634590b4ff4e7ad01eeed2efb23139e9c7353002309f27c5
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0be31d88569ec7468f8b82bd320d020ca1dcbde68a094bd5f71e673f706e2e
+size 2983303184

ft_13b_NLSY79_with_birth_year_ckpt_bo5/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 52063457280
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.safetensors"
+  }
+}

ft_13b_NLSY79_with_birth_year_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_13b_NLSY79_with_birth_year_ckpt_bo5/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

ft_13b_NLSY79_with_birth_year_ckpt_bo5/trainer_state.json

@@ -0,0 +1,1123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 30,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 6.10371732711792,
+      "learning_rate": 9.933333333333334e-06,
+      "loss": 0.8999,
+      "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 4.2386980056762695,
+      "learning_rate": 9.866666666666668e-06,
+      "loss": 0.6358,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.190752029418945,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.3656,
+      "step": 3
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 3.69400691986084,
+      "learning_rate": 9.733333333333334e-06,
+      "loss": 0.2854,
+      "step": 4
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 5.543595790863037,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.2833,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9863700866699219,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.1986,
+      "step": 6
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.5164625644683838,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.1632,
+      "step": 7
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6566644906997681,
+      "learning_rate": 9.466666666666667e-06,
+      "loss": 0.1744,
+      "step": 8
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.5596315264701843,
+      "learning_rate": 9.4e-06,
+      "loss": 0.1623,
+      "step": 9
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.3632151484489441,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.1536,
+      "step": 10
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.33296090364456177,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 0.1524,
+      "step": 11
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.23948849737644196,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.1499,
+      "step": 12
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.2391127645969391,
+      "learning_rate": 9.133333333333335e-06,
+      "loss": 0.1469,
+      "step": 13
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.24332673847675323,
+      "learning_rate": 9.066666666666667e-06,
+      "loss": 0.1534,
+      "step": 14
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2306579053401947,
+      "learning_rate": 9e-06,
+      "loss": 0.1488,
+      "step": 15
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.25679492950439453,
+      "learning_rate": 8.933333333333333e-06,
+      "loss": 0.1488,
+      "step": 16
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.20723888278007507,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.1475,
+      "step": 17
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.17597271502017975,
+      "learning_rate": 8.8e-06,
+      "loss": 0.139,
+      "step": 18
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.17865020036697388,
+      "learning_rate": 8.733333333333333e-06,
+      "loss": 0.1373,
+      "step": 19
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.17698802053928375,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.1391,
+      "step": 20
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.18041200935840607,
+      "learning_rate": 8.6e-06,
+      "loss": 0.1397,
+      "step": 21
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.2079327553510666,
+      "learning_rate": 8.533333333333335e-06,
+      "loss": 0.1401,
+      "step": 22
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.22272850573062897,
+      "learning_rate": 8.466666666666668e-06,
+      "loss": 0.1438,
+      "step": 23
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.23448240756988525,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.138,
+      "step": 24
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.18506617844104767,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.138,
+      "step": 25
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.14668166637420654,
+      "learning_rate": 8.266666666666667e-06,
+      "loss": 0.1464,
+      "step": 26
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.14653900265693665,
+      "learning_rate": 8.2e-06,
+      "loss": 0.1413,
+      "step": 27
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.17851024866104126,
+      "learning_rate": 8.133333333333334e-06,
+      "loss": 0.135,
+      "step": 28
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.1355242282152176,
+      "learning_rate": 8.066666666666667e-06,
+      "loss": 0.1408,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14128847420215607,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1339,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.13814036548137665,
+      "eval_runtime": 5.0857,
+      "eval_samples_per_second": 26.152,
+      "eval_steps_per_second": 0.983,
+      "step": 30
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.11761270463466644,
+      "learning_rate": 7.933333333333334e-06,
+      "loss": 0.136,
+      "step": 31
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.1388135850429535,
+      "learning_rate": 7.866666666666667e-06,
+      "loss": 0.1323,
+      "step": 32
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.14063020050525665,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.1344,
+      "step": 33
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.18162883818149567,
+      "learning_rate": 7.733333333333334e-06,
+      "loss": 0.1429,
+      "step": 34
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.13052447140216827,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.1371,
+      "step": 35
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1630505621433258,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.1388,
+      "step": 36
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.1302003413438797,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.138,
+      "step": 37
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.15910622477531433,
+      "learning_rate": 7.4666666666666675e-06,
+      "loss": 0.1402,
+      "step": 38
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.11879561841487885,
+      "learning_rate": 7.4e-06,
+      "loss": 0.1342,
+      "step": 39
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.16946682333946228,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.136,
+      "step": 40
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.1313311755657196,
+      "learning_rate": 7.266666666666668e-06,
+      "loss": 0.1318,
+      "step": 41
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.13578346371650696,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.1382,
+      "step": 42
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.1512828916311264,
+      "learning_rate": 7.133333333333334e-06,
+      "loss": 0.1302,
+      "step": 43
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.10916333645582199,
+      "learning_rate": 7.066666666666667e-06,
+      "loss": 0.1391,
+      "step": 44
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.13526494801044464,
+      "learning_rate": 7e-06,
+      "loss": 0.132,
+      "step": 45
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.1314297318458557,
+      "learning_rate": 6.9333333333333344e-06,
+      "loss": 0.1369,
+      "step": 46
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.13408230245113373,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.1375,
+      "step": 47
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.12854315340518951,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.136,
+      "step": 48
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.14364668726921082,
+      "learning_rate": 6.733333333333334e-06,
+      "loss": 0.1377,
+      "step": 49
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.15223892033100128,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1387,
+      "step": 50
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.1596962809562683,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 0.1326,
+      "step": 51
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.11943280696868896,
+      "learning_rate": 6.533333333333334e-06,
+      "loss": 0.1339,
+      "step": 52
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.12389056384563446,
+      "learning_rate": 6.466666666666667e-06,
+      "loss": 0.1358,
+      "step": 53
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.1472788006067276,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.1364,
+      "step": 54
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.10884050279855728,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.1325,
+      "step": 55
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.1229044646024704,
+      "learning_rate": 6.266666666666668e-06,
+      "loss": 0.1378,
+      "step": 56
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.14050322771072388,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.1356,
+      "step": 57
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.12817811965942383,
+      "learning_rate": 6.133333333333334e-06,
+      "loss": 0.1313,
+      "step": 58
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.10586828738451004,
+      "learning_rate": 6.066666666666667e-06,
+      "loss": 0.1292,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11933338642120361,
+      "learning_rate": 6e-06,
+      "loss": 0.1293,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1349245011806488,
+      "eval_runtime": 5.1049,
+      "eval_samples_per_second": 26.053,
+      "eval_steps_per_second": 0.979,
+      "step": 60
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.1260538399219513,
+      "learning_rate": 5.933333333333335e-06,
+      "loss": 0.136,
+      "step": 61
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.13248437643051147,
+      "learning_rate": 5.8666666666666675e-06,
+      "loss": 0.1343,
+      "step": 62
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.11809269338846207,
+      "learning_rate": 5.8e-06,
+      "loss": 0.131,
+      "step": 63
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.15666112303733826,
+      "learning_rate": 5.733333333333334e-06,
+      "loss": 0.1392,
+      "step": 64
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.14150451123714447,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.1379,
+      "step": 65
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.19514329731464386,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.1324,
+      "step": 66
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.1542859524488449,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.1316,
+      "step": 67
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.11222638189792633,
+      "learning_rate": 5.466666666666667e-06,
+      "loss": 0.1267,
+      "step": 68
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.1451522707939148,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 0.1402,
+      "step": 69
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.1442539542913437,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1265,
+      "step": 70
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.11017484217882156,
+      "learning_rate": 5.2666666666666665e-06,
+      "loss": 0.1254,
+      "step": 71
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.14355315268039703,
+      "learning_rate": 5.2e-06,
+      "loss": 0.1343,
+      "step": 72
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.13706636428833008,
+      "learning_rate": 5.133333333333334e-06,
+      "loss": 0.1353,
+      "step": 73
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.12415317445993423,
+      "learning_rate": 5.0666666666666676e-06,
+      "loss": 0.1331,
+      "step": 74
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.11414925754070282,
+      "learning_rate": 5e-06,
+      "loss": 0.1309,
+      "step": 75
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.12472691386938095,
+      "learning_rate": 4.933333333333334e-06,
+      "loss": 0.1314,
+      "step": 76
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.11705971509218216,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.1319,
+      "step": 77
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.12357550859451294,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.1352,
+      "step": 78
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.15162983536720276,
+      "learning_rate": 4.7333333333333335e-06,
+      "loss": 0.139,
+      "step": 79
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.09958243370056152,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1276,
+      "step": 80
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.11421269178390503,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.1312,
+      "step": 81
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.11195037513971329,
+      "learning_rate": 4.533333333333334e-06,
+      "loss": 0.1321,
+      "step": 82
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.11523134261369705,
+      "learning_rate": 4.4666666666666665e-06,
+      "loss": 0.1313,
+      "step": 83
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.11751246452331543,
+      "learning_rate": 4.4e-06,
+      "loss": 0.133,
+      "step": 84
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.1188402846455574,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.1287,
+      "step": 85
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.10657908767461777,
+      "learning_rate": 4.266666666666668e-06,
+      "loss": 0.1333,
+      "step": 86
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.12412970513105392,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.1288,
+      "step": 87
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.17746040225028992,
+      "learning_rate": 4.133333333333333e-06,
+      "loss": 0.1339,
+      "step": 88
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.10868477076292038,
+      "learning_rate": 4.066666666666667e-06,
+      "loss": 0.1356,
+      "step": 89
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1185813769698143,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1326,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1336824744939804,
+      "eval_runtime": 5.1507,
+      "eval_samples_per_second": 25.822,
+      "eval_steps_per_second": 0.971,
+      "step": 90
+    },
+    {
+      "epoch": 3.033333333333333,
+      "grad_norm": 0.11488619446754456,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 0.131,
+      "step": 91
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.10928378999233246,
+      "learning_rate": 3.866666666666667e-06,
+      "loss": 0.1345,
+      "step": 92
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.10110938549041748,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.1303,
+      "step": 93
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.12675999104976654,
+      "learning_rate": 3.7333333333333337e-06,
+      "loss": 0.1319,
+      "step": 94
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.1208232045173645,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.1293,
+      "step": 95
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.15299072861671448,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.1358,
+      "step": 96
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.12157642841339111,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.1312,
+      "step": 97
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.12274779379367828,
+      "learning_rate": 3.4666666666666672e-06,
+      "loss": 0.1303,
+      "step": 98
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.12734395265579224,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.1281,
+      "step": 99
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.14279533922672272,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1338,
+      "step": 100
+    },
+    {
+      "epoch": 3.3666666666666667,
+      "grad_norm": 0.1106022521853447,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 0.1317,
+      "step": 101
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.11592163145542145,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.13,
+      "step": 102
+    },
+    {
+      "epoch": 3.4333333333333336,
+      "grad_norm": 0.10066878795623779,
+      "learning_rate": 3.133333333333334e-06,
+      "loss": 0.1322,
+      "step": 103
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.11758943647146225,
+      "learning_rate": 3.066666666666667e-06,
+      "loss": 0.1317,
+      "step": 104
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.10832509398460388,
+      "learning_rate": 3e-06,
+      "loss": 0.1319,
+      "step": 105
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.11265487968921661,
+      "learning_rate": 2.9333333333333338e-06,
+      "loss": 0.1271,
+      "step": 106
+    },
+    {
+      "epoch": 3.5666666666666664,
+      "grad_norm": 0.11846131831407547,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.1349,
+      "step": 107
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.10723351687192917,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.1291,
+      "step": 108
+    },
+    {
+      "epoch": 3.6333333333333333,
+      "grad_norm": 0.11523675173521042,
+      "learning_rate": 2.7333333333333336e-06,
+      "loss": 0.1347,
+      "step": 109
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.11500649899244308,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.123,
+      "step": 110
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.1065315380692482,
+      "learning_rate": 2.6e-06,
+      "loss": 0.1315,
+      "step": 111
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.12868285179138184,
+      "learning_rate": 2.5333333333333338e-06,
+      "loss": 0.1287,
+      "step": 112
+    },
+    {
+      "epoch": 3.7666666666666666,
+      "grad_norm": 0.12415234744548798,
+      "learning_rate": 2.466666666666667e-06,
+      "loss": 0.1323,
+      "step": 113
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.11514582484960556,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1318,
+      "step": 114
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 0.12490728497505188,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.1298,
+      "step": 115
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 0.13178136944770813,
+      "learning_rate": 2.266666666666667e-06,
+      "loss": 0.1241,
+      "step": 116
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.14608055353164673,
+      "learning_rate": 2.2e-06,
+      "loss": 0.1295,
+      "step": 117
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 0.11863338947296143,
+      "learning_rate": 2.133333333333334e-06,
+      "loss": 0.1289,
+      "step": 118
+    },
+    {
+      "epoch": 3.966666666666667,
+      "grad_norm": 0.10471713542938232,
+      "learning_rate": 2.0666666666666666e-06,
+      "loss": 0.1304,
+      "step": 119
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.1133182942867279,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1261,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1333937644958496,
+      "eval_runtime": 5.1675,
+      "eval_samples_per_second": 25.738,
+      "eval_steps_per_second": 0.968,
+      "step": 120
+    },
+    {
+      "epoch": 4.033333333333333,
+      "grad_norm": 0.15868131816387177,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 0.1274,
+      "step": 121
+    },
+    {
+      "epoch": 4.066666666666666,
+      "grad_norm": 0.11404120922088623,
+      "learning_rate": 1.8666666666666669e-06,
+      "loss": 0.1263,
+      "step": 122
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 0.14726702868938446,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.1299,
+      "step": 123
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 0.11830582469701767,
+      "learning_rate": 1.7333333333333336e-06,
+      "loss": 0.1287,
+      "step": 124
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.10336384922266006,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1305,
+      "step": 125
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.10795653611421585,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1258,
+      "step": 126
+    },
+    {
+      "epoch": 4.233333333333333,
+      "grad_norm": 0.10199574381113052,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.1263,
+      "step": 127
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.11366704106330872,
+      "learning_rate": 1.4666666666666669e-06,
+      "loss": 0.1302,
+      "step": 128
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.10286647081375122,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.1294,
+      "step": 129
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.09992268681526184,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.1264,
+      "step": 130
+    },
+    {
+      "epoch": 4.366666666666666,
+      "grad_norm": 0.11261553317308426,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 0.138,
+      "step": 131
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.10719994455575943,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.1258,
+      "step": 132
+    },
+    {
+      "epoch": 4.433333333333334,
+      "grad_norm": 0.1168169155716896,
+      "learning_rate": 1.1333333333333334e-06,
+      "loss": 0.1302,
+      "step": 133
+    },
+    {
+      "epoch": 4.466666666666667,
+      "grad_norm": 0.10857973247766495,
+      "learning_rate": 1.066666666666667e-06,
+      "loss": 0.1304,
+      "step": 134
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.1116151437163353,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1307,
+      "step": 135
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.10125888139009476,
+      "learning_rate": 9.333333333333334e-07,
+      "loss": 0.1242,
+      "step": 136
+    },
+    {
+      "epoch": 4.566666666666666,
+      "grad_norm": 0.10692555457353592,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.1311,
+      "step": 137
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.09675995260477066,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.1278,
+      "step": 138
+    },
+    {
+      "epoch": 4.633333333333333,
+      "grad_norm": 0.11734635382890701,
+      "learning_rate": 7.333333333333334e-07,
+      "loss": 0.1305,
+      "step": 139
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.09886398166418076,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1247,
+      "step": 140
+    },
+    {
+      "epoch": 4.7,
+      "grad_norm": 0.10761479288339615,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.1269,
+      "step": 141
+    },
+    {
+      "epoch": 4.733333333333333,
+      "grad_norm": 0.1263909935951233,
+      "learning_rate": 5.333333333333335e-07,
+      "loss": 0.1296,
+      "step": 142
+    },
+    {
+      "epoch": 4.766666666666667,
+      "grad_norm": 0.08287958800792694,
+      "learning_rate": 4.666666666666667e-07,
+      "loss": 0.1311,
+      "step": 143
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.11243335902690887,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.133,
+      "step": 144
+    },
+    {
+      "epoch": 4.833333333333333,
+      "grad_norm": 0.10419868677854538,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.129,
+      "step": 145
+    },
+    {
+      "epoch": 4.866666666666667,
+      "grad_norm": 0.10872695595026016,
+      "learning_rate": 2.666666666666667e-07,
+      "loss": 0.1337,
+      "step": 146
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.09898468106985092,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.1297,
+      "step": 147
+    },
+    {
+      "epoch": 4.933333333333334,
+      "grad_norm": 0.10123828053474426,
+      "learning_rate": 1.3333333333333336e-07,
+      "loss": 0.1244,
+      "step": 148
+    },
+    {
+      "epoch": 4.966666666666667,
+      "grad_norm": 0.10221458226442337,
+      "learning_rate": 6.666666666666668e-08,
+      "loss": 0.1282,
+      "step": 149
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.10288937389850616,
+      "learning_rate": 0.0,
+      "loss": 0.1255,
+      "step": 150
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.1328565627336502,
+      "eval_runtime": 5.4157,
+      "eval_samples_per_second": 24.558,
+      "eval_steps_per_second": 0.923,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8897680384550502e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}